Skip to content

OpenRAG is a comprehensive, single package Retrieval-Augmented Generation platform built on Langflow, Docling, and Opensearch.

Python

chore: upgrade Langflow version and flows (#2560)

Lucas Oliveiraa9c18341bf25
diff --git a/Dockerfile.langflow b/Dockerfile.langflow
index d0b3544b2..10cdecffb 100644
--- a/Dockerfile.langflow
+++ b/Dockerfile.langflow
@@ -14,7 +14,7 @@
# Then delete: this lxml-build stage, the libxml2 update and libxslt install in
# the runtime root step, and the lxml wheel swap after the pip install.
# -----------------------------------------------------------------------------
-FROM langflowai/langflow:base-1.12.3 AS lxml-build
+FROM langflowai/langflow:base-1.12.8 AS lxml-build
USER root
RUN microdnf install -y \
@@ -31,7 +31,7 @@ RUN pip wheel --no-cache-dir --no-deps --no-binary lxml -w /wheels \
# -----------------------------------------------------------------------------
# Stage: runtime
# -----------------------------------------------------------------------------
-FROM langflowai/langflow:base-1.12.3
+FROM langflowai/langflow:base-1.12.8
# Install uv, then pre-create the Langflow data directory as root.
# Langflow 1.12's base image runs as uid=1000, but /app itself is not writable.
diff --git a/Dockerfile.langflow.dev b/Dockerfile.langflow.dev
index 01e64feb4..b38ac0644 100644
--- a/Dockerfile.langflow.dev
+++ b/Dockerfile.langflow.dev
@@ -1,23 +1,32 @@
-# Development Dockerfile for building Langflow from source
-# Allows building from any Git branch/repo for testing
+# syntax=docker/dockerfile:1.4
-FROM registry.access.redhat.com/ubi10/python-314-minimal AS builder
+# Development Dockerfile for building Langflow from any Git branch/repository.
+# Keep this in sync with Dockerfile.langflow; the source checkout and frontend
+# build below are the only intentional differences.
-# Install system dependencies using microdnf (UBI minimal package manager)
-USER 0
+# lxml's PyPI wheels statically bundle their own libxml2 (2.14.6 as of lxml
+# 6.1.3), which is vulnerable to CVE-2026-86140 (fixed upstream in 2.15.4).
+# Rebuild lxml from source so it links against RHEL's patched system libxml2
+# (2.12.5-10.el10_2.4) instead. Remove this workaround once Langflow ships
+# both fixes in its base dependencies.
+FROM registry.access.redhat.com/ubi10/python-314-minimal
+
+USER root
-# Set environment variables
ENV PYTHONUNBUFFERED=1
ENV RUSTFLAGS="--cfg reqwest_unstable"
-# Accept build arguments for git repository and branch
+# Accept build arguments for the Langflow source to test.
ARG GIT_REPO=https://github.com/langflow-ai/langflow.git
ARG GIT_BRANCH=main
WORKDIR /app
+# Install the source-build toolchain and the patched runtime libraries. libxslt
+# is required by the source-built lxml wheel.
RUN microdnf update -y \
&& microdnf install -y \
+ 'libxml2 >= 2.12.5-10.el10_2.4' \
gcc \
gcc-c++ \
make \
@@ -29,45 +38,83 @@ RUN microdnf update -y \
npm \
rust cargo pkgconf-pkg-config openssl-devel \
python3.14-devel \
+ libxml2-devel \
+ libxslt \
+ libxslt-devel \
&& microdnf clean all \
&& rm -rf /var/cache/yum
-# Install uv for faster Python package management.
-# Upgrade pip first to patch CVE-2026-8643 (fixed in 26.1.2) in the base image.
+# Upgrade pip first to patch CVE-2026-8643 (fixed in 26.1.2) and install uv.
RUN python -m ensurepip --upgrade \
&& python -m pip install --no-cache-dir --upgrade "pip>=26.1.2" \
&& python -m pip install --no-cache-dir uv
-# Clone the repository and checkout the specified branch
-RUN echo "Cloning ${GIT_REPO} branch ${GIT_BRANCH}..." && \
- git clone --depth 1 --branch ${GIT_BRANCH} ${GIT_REPO} /app
+# Clone the selected Langflow branch.
+RUN echo "Cloning ${GIT_REPO} branch ${GIT_BRANCH}..." \
+ && git clone --depth 1 --branch "${GIT_BRANCH}" "${GIT_REPO}" /app
+# Patch the source before compiling the frontend, so the OpenRAG component
+# group is present in the built bundle.
COPY scripts/patch_langflow_openrag_bundle.py /tmp/patch_langflow_openrag_bundle.py
RUN python3 /tmp/patch_langflow_openrag_bundle.py /app/src/frontend/src/utils/styleUtils.ts
-# Install backend dependencies
+# Install backend dependencies before the frontend build.
RUN uv sync --frozen --no-install-project --no-editable --extra postgresql
-# Build frontend (split into steps to reduce peak memory usage)
WORKDIR /app/src/frontend
ENV PUPPETEER_SKIP_DOWNLOAD=true
-# Install dependencies first
RUN npm ci --maxsockets 1
-# Build with reduced memory - 4GB should be safer for most systems
RUN NODE_OPTIONS="--max_old_space_size=4096 --max-semi-space-size=128" npm run build
-# Copy built frontend
-RUN mkdir -p /app/src/backend/base/langflow/frontend && \
- cp -r build/* /app/src/backend/base/langflow/frontend/
-# Return to app directory and install the project
+# Install the branch itself plus the OpenRAG runtime integrations used by the
+# production image.
WORKDIR /app
-RUN uv sync --frozen --no-dev --no-editable --extra postgresql
-RUN uv pip uninstall litellm ragstack-ai-knowledge-store
-
+RUN uv sync --frozen --no-dev --no-editable --extra postgresql \
+ && uv pip uninstall litellm ragstack-ai-knowledge-store \
+ && uv pip install \
+ --extra-index-url https://download.pytorch.org/whl/cpu \
+ torch==2.13.0 \
+ torchvision==0.28.0 \
+ "transformers>=5.10.1,<6.0.0" \
+ "docling-core<3.0.0" \
+ "pypdf>=6.16.1,<7.0.0" \
+ openai \
+ langchain-openai \
+ anthropic \
+ langchain-anthropic \
+ google-generativeai \
+ langchain-google-genai \
+ langchain-ollama \
+ opensearch-py \
+ langfuse \
+ "ibm-watsonx-ai>=1.3.1,<2.0.0" \
+ "langchain-ibm~=1.1.0"
+
+# uv installs the branch as a non-editable package. Put the built frontend in
+# both the source tree and that installed package, which is where Langflow
+# resolves its static files at runtime.
+RUN frontend_dir="$(/app/.venv/bin/python -c 'from pathlib import Path; import langflow; print(Path(langflow.__file__).parent / "frontend")')" \
+ && mkdir -p /app/src/backend/base/langflow/frontend "${frontend_dir}" \
+ && cp -r /app/src/frontend/build/. /app/src/backend/base/langflow/frontend/ \
+ && cp -r /app/src/frontend/build/. "${frontend_dir}/"
+
+# Replace the binary lxml wheel after all installations so it remains linked
+# to the patched system libxml2. This is the source-build equivalent of the
+# lxml-build stage in Dockerfile.langflow.
+RUN lxml_version="$(uv pip show --python /app/.venv/bin/python lxml | awk '/^Version:/ {print $2}')" \
+ && uv pip install --python /app/.venv/bin/python --no-deps --reinstall \
+ --no-binary lxml "lxml==${lxml_version}"
+
+COPY flows/ /app/flows/
COPY custom_components/ /app/custom_components/
-# Expose ports
-EXPOSE 7860
+# Match the production image's bind-mount permission handling. The entrypoint
+# drops from root to uid 1000, so the branch checkout and Gunicorn control
+# directory must also be writable by that user.
+RUN mkdir -p /app/langflow-data \
+ && chmod 0777 /app/langflow-data \
+ && chown -R 1000:0 /app
+COPY --chmod=755 scripts/langflow-entrypoint.py /usr/local/bin/langflow-entrypoint
ENV LANGFLOW_SSRF_ALLOWED_HOSTS=localhost,127.0.0.1,host.docker.internal
ENV LANGFLOW_LOG_TRACE_LOCALS=false
@@ -78,9 +125,11 @@ ENV LANGFLOW_ALLOW_CUSTOM_COMPONENTS=false
ENV LANGFLOW_DANGEROUSLY_ALLOW_MULTI_WORKER_WITHOUT_SHARED_QUEUE=true
ENV LANGFLOW_DISABLE_TRACK_APIKEY_USAGE=true
-# CWE-426 fix: explicitly set PATH so system-owned directories are always resolved
-# first. App venv and ubi python dirs are appended last so they cannot shadow system binaries.
+# CWE-426 fix: explicitly set PATH so system-owned directories are always
+# resolved first. App venv and UBI Python directories are appended last.
ENV PATH=/usr/local/sbin:/usr/local/bin:/usr/sbin:/usr/bin:/sbin:/bin:/app/.venv/bin:/opt/app-root/bin:/opt/app-root/src/bin:/opt/app-root/src/.local/bin
-# Start the backend server
-CMD ["uv", "run", "langflow", "run", "--host", "0.0.0.0", "--port", "7860"]
+EXPOSE 7860
+
+ENTRYPOINT ["langflow-entrypoint"]
+CMD ["python", "-m", "langflow", "run", "--host", "0.0.0.0", "--port", "7860"]
diff --git a/flows/ingestion_flow.json b/flows/ingestion_flow.json
index 1847c18c7..22ab951e3 100644
--- a/flows/ingestion_flow.json
+++ b/flows/ingestion_flow.json
@@ -62,6 +62,7 @@
},
{
"animated": false,
+ "className": "",
"data": {
"sourceHandle": {
"dataType": "Operations",
@@ -93,6 +94,7 @@
},
{
"animated": false,
+ "className": "",
"data": {
"sourceHandle": {
"dataType": "ext:openrag:OpenRAGSplitTextComponent@extra",
@@ -122,6 +124,7 @@
},
{
"animated": false,
+ "className": "",
"data": {
"sourceHandle": {
"dataType": "ExportDoclingDocument",
@@ -149,6 +152,8 @@
"targetHandle": "{œfieldNameœ:œdfœ,œidœ:œOperations-IC6CDœ,œinputTypesœ:[œDataFrameœ,œTableœ],œtypeœ:œotherœ}"
},
{
+ "animated": false,
+ "className": "",
"data": {
"sourceHandle": {
"dataType": "Operations",
@@ -169,6 +174,7 @@
}
},
"id": "xy-edge__Operations-IC6CD{œdataTypeœ:œOperationsœ,œidœ:œOperations-IC6CDœ,œnameœ:œdataframe_outputœ,œoutput_typesœ:[œTableœ]}-Operations-VUCJC{œfieldNameœ:œdfœ,œidœ:œOperations-VUCJCœ,œinputTypesœ:[œDataFrameœ,œTableœ],œtypeœ:œotherœ}",
+ "selected": false,
"source": "Operations-IC6CD",
"sourceHandle": "{œdataTypeœ:œOperationsœ,œidœ:œOperations-IC6CDœ,œnameœ:œdataframe_outputœ,œoutput_typesœ:[œTableœ]}",
"target": "Operations-VUCJC",
@@ -673,10 +679,6 @@
},
"dragging": false,
"id": "DoclingRemote-Dp3PX",
- "measured": {
- "height": 52,
- "width": 192
- },
"position": {
"x": 377.3513331245854,
"y": 1841.1174193072818
@@ -949,10 +951,6 @@
},
"dragging": false,
"id": "ExportDoclingDocument-zZdRg",
- "measured": {
- "height": 52,
- "width": 192
- },
"position": {
"x": 648.3765412475954,
"y": 1839.7464467523132
@@ -1052,10 +1050,10 @@
],
"frozen": false,
"icon": "wand-sparkles",
- "last_updated": "2026-10-27T20:14:20.463Z",
+ "last_updated": "2026-10-29T18:16:38.729Z",
"legacy": false,
"metadata": {
- "code_hash": "f15ba610cfd0",
+ "code_hash": "6164f967d510",
"dependencies": {
"dependencies": [
{
@@ -1068,7 +1066,7 @@
},
{
"name": "lfx",
- "version": "1.12.3"
+ "version": "1.12.8"
},
{
"name": "jq",
@@ -1149,7 +1147,7 @@
"value": "5488df7c-b93f-4f87-a446-b67028bc0813"
},
"_frontend_node_folder_id": {
- "value": "f3f8bf74-7a73-4ab3-9769-0d8a4ebbaec9"
+ "value": "afa57272-6d34-4d1c-bf31-27ffad110b3a"
},
"_type": "Component",
"append_update_data": {
@@ -1244,7 +1242,7 @@
"show": true,
"title_case": false,
"type": "code",
- "value": "\"\"\"Unified Operations component.\n\nBrings together the previously separate JSON, Table, and Text operation\ncomponents into a single component. An \"Input Type\" selector (Text / JSON /\nTable) drives everything: it filters the \"Operation\" picker to the operations\nthat apply to that type, reveals the matching input (Text / JSON / Table) and\nits operation-specific fields, and advertises the appropriate output type.\n\nThe three original components (JSON Operations, Table Operations, Text\nOperations) remain available as legacy components for backward compatibility\nwith existing flows.\n\"\"\"\n\nimport ast\nimport contextlib\nimport json\nimport re\nfrom typing import TYPE_CHECKING, Any\n\nimport pandas as pd\nfrom json_repair import repair_json\n\nfrom lfx.custom import Component\nfrom lfx.field_typing import RangeSpec\nfrom lfx.inputs import DictInput, SortableListInput, TabInput\nfrom lfx.io import (\n BoolInput,\n DataFrameInput,\n DataInput,\n DropdownInput,\n IntInput,\n MessageTextInput,\n MultilineInput,\n Output,\n StrInput,\n)\nfrom lfx.log.logger import logger\nfrom lfx.schema import Data\nfrom lfx.schema.dataframe import DataFrame\nfrom lfx.schema.dotdict import dotdict\nfrom lfx.schema.message import Message\nfrom lfx.utils.jq_security import validate_jq_program\n\nif TYPE_CHECKING:\n from collections.abc import Callable\n\n# The \"Input Type\" selector tabs. Each value maps a Langflow data type to the\n# operations, input, and output that belong to it.\nINPUT_TYPES = [\"Text\", \"JSON\", \"Table\"]\n\n# Operations grouped by input type, in display order, each with the icon shown\n# in the Operation picker. This is the single source of truth for the picker;\n# update_build_config swaps the picker's options to the selected type's list.\nOPERATIONS_BY_TYPE: dict[str, list[dict[str, str]]] = {\n \"Text\": [\n {\"name\": \"Word Count\", \"icon\": \"hash\"},\n {\"name\": \"Case Conversion\", \"icon\": \"type\"},\n {\"name\": \"Text Replace\", \"icon\": \"replace\"},\n {\"name\": \"Text Extract\", \"icon\": \"search\"},\n {\"name\": \"Text Head\", \"icon\": \"chevron-left\"},\n {\"name\": \"Text Tail\", \"icon\": \"chevron-right\"},\n {\"name\": \"Text Strip\", \"icon\": \"minus\"},\n {\"name\": \"Text Join\", \"icon\": \"link\"},\n {\"name\": \"Text Clean\", \"icon\": \"sparkles\"},\n {\"name\": \"Text to DataFrame\", \"icon\": \"table\"},\n ],\n \"JSON\": [\n {\"name\": \"Select Keys\", \"icon\": \"lasso-select\"},\n {\"name\": \"Literal Eval\", \"icon\": \"braces\"},\n {\"name\": \"Combine\", \"icon\": \"merge\"},\n {\"name\": \"Append or Update\", \"icon\": \"circle-plus\"},\n {\"name\": \"Remove Keys\", \"icon\": \"eraser\"},\n {\"name\": \"Rename Keys\", \"icon\": \"pencil-line\"},\n {\"name\": \"Path Selection\", \"icon\": \"mouse-pointer\"},\n {\"name\": \"JQ Expression\", \"icon\": \"terminal\"},\n ],\n \"Table\": [\n {\"name\": \"Add Column\", \"icon\": \"plus\"},\n {\"name\": \"Concatenate\", \"icon\": \"combine\"},\n {\"name\": \"Drop Column\", \"icon\": \"minus\"},\n {\"name\": \"Filter\", \"icon\": \"filter\"},\n {\"name\": \"Head\", \"icon\": \"arrow-up\"},\n {\"name\": \"Merge\", \"icon\": \"merge\"},\n {\"name\": \"Rename Column\", \"icon\": \"pencil\"},\n {\"name\": \"Replace Value\", \"icon\": \"replace\"},\n {\"name\": \"Select Columns\", \"icon\": \"columns\"},\n {\"name\": \"Sort\", \"icon\": \"arrow-up-down\"},\n {\"name\": \"Tail\", \"icon\": \"arrow-down\"},\n {\"name\": \"Drop Duplicates\", \"icon\": \"copy-x\"},\n ],\n}\n\n# Operation-name sets derived from the picker, used for dispatch and output\n# routing. Keeping them derived from OPERATIONS_BY_TYPE avoids any drift.\nJSON_OPERATIONS = {op[\"name\"] for op in OPERATIONS_BY_TYPE[\"JSON\"]}\nTABLE_OPERATIONS = {op[\"name\"] for op in OPERATIONS_BY_TYPE[\"Table\"]}\nTEXT_OPERATIONS = {op[\"name\"] for op in OPERATIONS_BY_TYPE[\"Text\"]}\n\n# Each input type maps to its main input field and its default output. \"Text\"\n# normally outputs a Message; \"JSON\" a Data; \"Table\" a DataFrame. A few text\n# operations override this (Word Count -> Data, Text to DataFrame -> DataFrame).\nINPUT_TYPE_TO_MAIN_INPUT = {\"Text\": \"text_input\", \"JSON\": \"data\", \"Table\": \"df\"}\n\n# Case conversions for the Text \"Case Conversion\" operation.\nCASE_CONVERTERS: dict[str, Any] = {\n \"uppercase\": str.upper,\n \"lowercase\": str.lower,\n \"title\": str.title,\n \"capitalize\": str.capitalize,\n \"swapcase\": str.swapcase,\n}\n\n\nclass OperationsComponent(Component):\n display_name = \"Data Operations\"\n description = \"Perform operations on Text, JSON, and Tables from a single component.\"\n documentation: str = \"https://docs.langflow.org/components-processing#operations\"\n icon = \"wand-sparkles\"\n name = \"Operations\"\n metadata = {\n \"keywords\": [\n \"operations\",\n \"data operations\",\n \"json\",\n \"json operations\",\n \"table\",\n \"table operations\",\n \"dataframe\",\n \"dataframe operations\",\n \"text\",\n \"text operations\",\n \"select keys\",\n \"literal eval\",\n \"combine\",\n \"append or update\",\n \"remove keys\",\n \"rename keys\",\n \"path selection\",\n \"jq expression\",\n \"parse json\",\n \"add column\",\n \"concatenate\",\n \"drop column\",\n \"filter\",\n \"head\",\n \"merge\",\n \"rename column\",\n \"replace value\",\n \"select columns\",\n \"sort\",\n \"tail\",\n \"drop duplicates\",\n \"word count\",\n \"case conversion\",\n \"text replace\",\n \"text extract\",\n \"text join\",\n \"text clean\",\n \"text to dataframe\",\n \"data manipulation\",\n \"data transformation\",\n ],\n }\n\n # Operation -> operation-specific input fields to reveal when selected.\n OPERATION_FIELDS: dict[str, list[str]] = {\n # JSON\n \"Select Keys\": [\"select_keys_input\"],\n \"Literal Eval\": [],\n \"Combine\": [],\n \"Append or Update\": [\"append_update_data\"],\n \"Remove Keys\": [\"remove_keys_input\"],\n \"Rename Keys\": [\"rename_keys_input\"],\n \"Path Selection\": [\"mapped_json_display\", \"selected_key\"],\n \"JQ Expression\": [\"query\"],\n # Table\n \"Add Column\": [\"new_column_name\", \"new_column_value\"],\n \"Concatenate\": [],\n \"Drop Column\": [\"column_name\"],\n \"Filter\": [\"column_name\", \"filter_value\", \"filter_operator\"],\n \"Head\": [\"num_rows\"],\n \"Merge\": [\"left_dataframe\", \"right_dataframe\", \"merge_on_column\", \"merge_how\"],\n \"Rename Column\": [\"column_name\", \"new_column_name\"],\n \"Replace Value\": [\"column_name\", \"replace_value\", \"replacement_value\"],\n \"Select Columns\": [\"columns_to_select\"],\n \"Sort\": [\"column_name\", \"ascending\"],\n \"Tail\": [\"num_rows\"],\n \"Drop Duplicates\": [\"column_name\"],\n # Text\n \"Word Count\": [\"count_words\", \"count_characters\", \"count_lines\"],\n \"Case Conversion\": [\"case_type\"],\n \"Text Replace\": [\"search_pattern\", \"replacement_text\", \"use_regex\"],\n \"Text Extract\": [\"extract_pattern\", \"max_matches\"],\n \"Text Head\": [\"head_characters\"],\n \"Text Tail\": [\"tail_characters\"],\n \"Text Strip\": [\"strip_mode\", \"strip_characters\"],\n \"Text Join\": [\"text_input_2\"],\n \"Text Clean\": [\"remove_extra_spaces\", \"remove_special_chars\", \"remove_empty_lines\"],\n \"Text to DataFrame\": [\"table_separator\", \"has_header\"],\n }\n\n # The three main inputs (one per data type). They are never treated as\n # operation-specific fields; the input-type selector toggles them.\n MAIN_INPUTS = (\"text_input\", \"data\", \"df\")\n\n # Every operation-specific field (union of all the lists above), used to\n # hide and reset fields whenever the input type or operation changes.\n ALL_OPERATION_FIELDS: list[str] = [\n # JSON\n \"select_keys_input\",\n \"append_update_data\",\n \"remove_keys_input\",\n \"rename_keys_input\",\n \"mapped_json_display\",\n \"selected_key\",\n \"query\",\n # Table\n \"column_name\",\n \"filter_value\",\n \"filter_operator\",\n \"ascending\",\n \"new_column_name\",\n \"new_column_value\",\n \"columns_to_select\",\n \"num_rows\",\n \"replace_value\",\n \"replacement_value\",\n \"left_dataframe\",\n \"right_dataframe\",\n \"merge_on_column\",\n \"merge_how\",\n # Text\n \"table_separator\",\n \"has_header\",\n \"count_words\",\n \"count_characters\",\n \"count_lines\",\n \"case_type\",\n \"use_regex\",\n \"search_pattern\",\n \"replacement_text\",\n \"extract_pattern\",\n \"max_matches\",\n \"head_characters\",\n \"tail_characters\",\n \"strip_mode\",\n \"strip_characters\",\n \"text_input_2\",\n \"remove_extra_spaces\",\n \"remove_special_chars\",\n \"remove_empty_lines\",\n ]\n\n # Defaults applied to the JSON operation fields when the operation changes,\n # mirroring the JSON Operations component's reset behavior.\n OPERATION_FIELD_DEFAULTS: dict[str, Any] = {\n \"select_keys_input\": [],\n \"append_update_data\": {\"key\": \"value\"},\n \"remove_keys_input\": [],\n \"rename_keys_input\": {\"old_key\": \"new_key\"},\n \"mapped_json_display\": \"\",\n \"selected_key\": None,\n \"query\": \"\",\n }\n\n inputs = [\n # --- Input type selector: drives operations, input, and output ---\n TabInput(\n name=\"input_type\",\n display_name=\"Input Type\",\n options=INPUT_TYPES,\n value=\"Text\",\n info=\"Select the type of input to operate on.\",\n real_time_refresh=True,\n ),\n # --- Main inputs: one per data type, shown contextually ---\n MultilineInput(\n name=\"text_input\",\n display_name=\"Text\",\n info=\"The input text to process.\",\n show=True,\n ),\n DataInput(\n name=\"data\",\n display_name=\"JSON\",\n info=\"The JSON / Data object to operate on.\",\n is_list=True,\n show=False,\n ),\n DataFrameInput(\n name=\"df\",\n display_name=\"Table\",\n info=\"The input Table to operate on. Connect multiple Tables for merge or concatenate operations.\",\n is_list=True,\n show=False,\n ),\n # --- Operation picker (options are filtered by Input Type) ---\n SortableListInput(\n name=\"operation\",\n display_name=\"Operation\",\n placeholder=\"Select Operation\",\n info=\"Select the operation to perform. The matching fields and output appear once you choose one.\",\n options=OPERATIONS_BY_TYPE[\"Text\"],\n real_time_refresh=True,\n limit=1,\n ),\n # --- JSON operation fields ---\n MessageTextInput(\n name=\"select_keys_input\",\n display_name=\"Select Keys\",\n info=\"List of keys to select from the data. Only top-level keys can be selected.\",\n show=False,\n is_list=True,\n value=[],\n ),\n DictInput(\n name=\"append_update_data\",\n display_name=\"Append or Update\",\n info=\"Data to append or update the existing data with. Only top-level keys are checked.\",\n show=False,\n value={\"key\": \"value\"},\n is_list=True,\n ),\n MessageTextInput(\n name=\"remove_keys_input\",\n display_name=\"Remove Keys\",\n info=\"List of keys to remove from the data.\",\n show=False,\n is_list=True,\n value=[],\n ),\n DictInput(\n name=\"rename_keys_input\",\n display_name=\"Rename Keys\",\n info=\"List of keys to rename in the data.\",\n show=False,\n is_list=True,\n value={\"old_key\": \"new_key\"},\n ),\n MultilineInput(\n name=\"mapped_json_display\",\n display_name=\"JSON to Map\",\n info=\"Paste or preview your JSON here to explore its structure and select a path for extraction.\",\n required=False,\n refresh_button=True,\n real_time_refresh=True,\n placeholder=\"Add a JSON example.\",\n show=False,\n ),\n DropdownInput(\n name=\"selected_key\",\n display_name=\"Select Path\",\n options=[],\n required=False,\n dynamic=True,\n show=False,\n value=None,\n ),\n MessageTextInput(\n name=\"query\",\n display_name=\"JQ Expression\",\n info=\"JSON Query to filter the data. Used by Path Selection and JQ Expression operations.\",\n placeholder=\"e.g., .properties.id\",\n show=False,\n ),\n # --- Table operation fields ---\n StrInput(\n name=\"column_name\",\n display_name=\"Column Name\",\n info=\"The column name to use for the operation.\",\n dynamic=True,\n show=False,\n ),\n MessageTextInput(\n name=\"filter_value\",\n display_name=\"Filter Value\",\n info=\"The value to filter rows by.\",\n dynamic=True,\n show=False,\n ),\n DropdownInput(\n name=\"filter_operator\",\n display_name=\"Filter Operator\",\n options=[\n \"equals\",\n \"not equals\",\n \"contains\",\n \"not contains\",\n \"starts with\",\n \"ends with\",\n \"greater than\",\n \"less than\",\n ],\n value=\"equals\",\n info=\"The operator to apply for filtering rows.\",\n advanced=False,\n dynamic=True,\n show=False,\n ),\n BoolInput(\n name=\"ascending\",\n display_name=\"Sort Ascending\",\n info=\"Whether to sort in ascending order.\",\n dynamic=True,\n show=False,\n value=True,\n ),\n StrInput(\n name=\"new_column_name\",\n display_name=\"New Column Name\",\n info=\"The new column name when renaming or adding a column.\",\n dynamic=True,\n show=False,\n ),\n MessageTextInput(\n name=\"new_column_value\",\n display_name=\"New Column Value\",\n info=\"The value to populate the new column with.\",\n dynamic=True,\n show=False,\n ),\n StrInput(\n name=\"columns_to_select\",\n display_name=\"Columns to Select\",\n dynamic=True,\n is_list=True,\n show=False,\n ),\n IntInput(\n name=\"num_rows\",\n display_name=\"Number of Rows\",\n info=\"Number of rows to return (for head/tail).\",\n dynamic=True,\n show=False,\n value=5,\n ),\n MessageTextInput(\n name=\"replace_value\",\n display_name=\"Value to Replace\",\n info=\"The value to replace in the column.\",\n dynamic=True,\n show=False,\n ),\n MessageTextInput(\n name=\"replacement_value\",\n display_name=\"Replacement Value\",\n info=\"The value to replace with.\",\n dynamic=True,\n show=False,\n ),\n DataFrameInput(\n name=\"left_dataframe\",\n display_name=\"Left Table\",\n info=\"The left (primary) Table for merge operations. \"\n \"In a left merge, all rows from this table are preserved.\",\n dynamic=True,\n show=False,\n ),\n DataFrameInput(\n name=\"right_dataframe\",\n display_name=\"Right Table\",\n info=\"The right (secondary) Table for merge operations. \"\n \"In a right merge, all rows from this table are preserved.\",\n dynamic=True,\n show=False,\n ),\n StrInput(\n name=\"merge_on_column\",\n display_name=\"Merge On Column\",\n info=\"The column name to merge Tables on. Must exist in both Tables.\",\n dynamic=True,\n show=False,\n ),\n DropdownInput(\n name=\"merge_how\",\n display_name=\"Merge Type\",\n options=[\"inner\", \"outer\", \"left\", \"right\"],\n value=\"inner\",\n info=\"Type of merge: inner (intersection), outer (union), left, or right.\",\n dynamic=True,\n show=False,\n ),\n # --- Text operation fields ---\n StrInput(\n name=\"table_separator\",\n display_name=\"Table Separator\",\n info=\"Separator used in the table (default: '|').\",\n value=\"|\",\n dynamic=True,\n show=False,\n ),\n BoolInput(\n name=\"has_header\",\n display_name=\"Has Header\",\n info=\"Whether the table has a header row.\",\n value=True,\n dynamic=True,\n advanced=True,\n show=False,\n ),\n BoolInput(\n name=\"count_words\",\n display_name=\"Count Words\",\n info=\"Include word count in analysis.\",\n value=True,\n dynamic=True,\n advanced=True,\n show=False,\n ),\n BoolInput(\n name=\"count_characters\",\n display_name=\"Count Characters\",\n info=\"Include character count in analysis.\",\n value=True,\n dynamic=True,\n advanced=True,\n show=False,\n ),\n BoolInput(\n name=\"count_lines\",\n display_name=\"Count Lines\",\n info=\"Include line count in analysis.\",\n value=True,\n dynamic=True,\n advanced=True,\n show=False,\n ),\n DropdownInput(\n name=\"case_type\",\n display_name=\"Case Type\",\n options=[\"uppercase\", \"lowercase\", \"title\", \"capitalize\", \"swapcase\"],\n value=\"lowercase\",\n info=\"Type of case conversion to apply.\",\n dynamic=True,\n show=False,\n ),\n BoolInput(\n name=\"use_regex\",\n display_name=\"Use Regex\",\n info=\"Whether to treat search pattern as regex.\",\n value=False,\n dynamic=True,\n show=False,\n ),\n StrInput(\n name=\"search_pattern\",\n display_name=\"Search Pattern\",\n info=\"Text pattern to search for (supports regex).\",\n dynamic=True,\n show=False,\n ),\n StrInput(\n name=\"replacement_text\",\n display_name=\"Replacement Text\",\n info=\"Text to replace the search pattern with.\",\n dynamic=True,\n show=False,\n ),\n StrInput(\n name=\"extract_pattern\",\n display_name=\"Extract Pattern\",\n info=\"Regex pattern to extract from text.\",\n dynamic=True,\n show=False,\n ),\n IntInput(\n name=\"max_matches\",\n display_name=\"Max Matches\",\n info=\"Maximum number of matches to extract.\",\n value=10,\n dynamic=True,\n show=False,\n ),\n IntInput(\n name=\"head_characters\",\n display_name=\"Characters from Start\",\n info=\"Number of characters to extract from the beginning of text. Must be non-negative.\",\n value=100,\n dynamic=True,\n show=False,\n range_spec=RangeSpec(min=0, max=1000000, step=1, step_type=\"int\"),\n ),\n IntInput(\n name=\"tail_characters\",\n display_name=\"Characters from End\",\n info=\"Number of characters to extract from the end of text. Must be non-negative.\",\n value=100,\n dynamic=True,\n show=False,\n range_spec=RangeSpec(min=0, max=1000000, step=1, step_type=\"int\"),\n ),\n DropdownInput(\n name=\"strip_mode\",\n display_name=\"Strip Mode\",\n options=[\"both\", \"left\", \"right\"],\n value=\"both\",\n info=\"Which sides to strip whitespace from.\",\n dynamic=True,\n show=False,\n ),\n StrInput(\n name=\"strip_characters\",\n display_name=\"Characters to Strip\",\n info=\"Specific characters to remove (leave empty for whitespace).\",\n value=\"\",\n dynamic=True,\n show=False,\n ),\n MultilineInput(\n name=\"text_input_2\",\n display_name=\"Second Text Input\",\n info=\"Second text to join with the first text.\",\n dynamic=True,\n show=False,\n ),\n BoolInput(\n name=\"remove_extra_spaces\",\n display_name=\"Remove Extra Spaces\",\n info=\"Remove multiple consecutive spaces.\",\n value=True,\n dynamic=True,\n show=False,\n ),\n BoolInput(\n name=\"remove_special_chars\",\n display_name=\"Remove Special Characters\",\n info=\"Remove special characters except alphanumeric and spaces.\",\n value=False,\n dynamic=True,\n show=False,\n ),\n BoolInput(\n name=\"remove_empty_lines\",\n display_name=\"Remove Empty Lines\",\n info=\"Remove empty lines from text.\",\n value=False,\n dynamic=True,\n show=False,\n ),\n ]\n\n # Default output matches the default Input Type (\"Text\" -> Message).\n # update_outputs / update_frontend_node narrow it to the selected type and\n # operation.\n outputs = [Output(display_name=\"Message\", name=\"message_output\", method=\"as_message\")]\n\n # ------------------------------------------------------------------\n # Operation routing helpers\n # ------------------------------------------------------------------\n @staticmethod\n def _extract_operation_name(field_value: Any) -> str:\n \"\"\"Extract the operation name from a SortableListInput value.\"\"\"\n if isinstance(field_value, list) and len(field_value) > 0 and isinstance(field_value[0], dict):\n return field_value[0].get(\"name\", \"\")\n if isinstance(field_value, str):\n return field_value\n return \"\"\n\n def _operation_name(self) -> str:\n \"\"\"Get the currently selected operation name.\"\"\"\n return self._extract_operation_name(getattr(self, \"operation\", []))\n\n @staticmethod\n def _default_output_for_type(input_type: str) -> Output:\n \"\"\"Return the output advertised for an input type when no operation is selected yet.\"\"\"\n if input_type == \"JSON\":\n return Output(display_name=\"JSON\", name=\"data_output\", method=\"as_data\")\n if input_type == \"Table\":\n return Output(display_name=\"Table\", name=\"dataframe_output\", method=\"as_dataframe\")\n return Output(display_name=\"Message\", name=\"message_output\", method=\"as_message\")\n\n # ------------------------------------------------------------------\n # Dynamic UI\n # ------------------------------------------------------------------\n def _reset_operation_fields(self, build_config: dotdict) -> None:\n \"\"\"Hide every operation-specific field and restore its default value.\"\"\"\n for field in self.ALL_OPERATION_FIELDS:\n if field in build_config:\n build_config[field][\"show\"] = False\n if field in self.OPERATION_FIELD_DEFAULTS:\n build_config[field][\"value\"] = self.OPERATION_FIELD_DEFAULTS[field]\n\n def _show_main_input(self, build_config: dotdict, input_type: str, operation: str) -> None:\n \"\"\"Show only the main input that matches the input type; hide the others.\"\"\"\n for inp in self.MAIN_INPUTS:\n if inp in build_config:\n build_config[inp][\"show\"] = False\n build_config[inp][\"required\"] = False\n\n main_input = INPUT_TYPE_TO_MAIN_INPUT.get(input_type)\n if main_input and main_input in build_config:\n build_config[main_input][\"show\"] = True\n build_config[main_input][\"required\"] = True\n # The JSON \"Combine\" operation consumes a list of Data objects.\n if main_input == \"data\":\n build_config[\"data\"][\"is_list\"] = operation == \"Combine\"\n\n def update_build_config(self, build_config: dotdict, field_value: Any, field_name: str | None = None) -> dotdict:\n # Path Selection: refresh the available JSON paths from the pasted JSON.\n if field_name == \"mapped_json_display\":\n try:\n parsed_json = json.loads(field_value)\n keys = self.extract_all_paths(parsed_json)\n build_config[\"selected_key\"][\"options\"] = keys\n build_config[\"selected_key\"][\"show\"] = True\n except (json.JSONDecodeError, TypeError, ValueError) as e:\n logger.error(f\"Error parsing mapped JSON: {e}\")\n build_config[\"selected_key\"][\"show\"] = False\n return build_config\n\n # Input type changed: swap the operation list, clear the selection, and\n # show only the matching input. No operation-specific fields are shown\n # until an operation is picked.\n if field_name == \"input_type\":\n input_type = field_value if field_value in OPERATIONS_BY_TYPE else \"Text\"\n build_config[\"operation\"][\"options\"] = OPERATIONS_BY_TYPE[input_type]\n build_config[\"operation\"][\"value\"] = []\n self._reset_operation_fields(build_config)\n self._show_main_input(build_config, input_type, operation=\"\")\n return build_config\n\n # Operation changed: reset fields, show the input for the current type,\n # then reveal the operation-specific fields.\n if field_name == \"operation\":\n operation = self._extract_operation_name(field_value)\n self._reset_operation_fields(build_config)\n\n input_type = build_config.get(\"input_type\", {}).get(\"value\", \"Text\")\n self._show_main_input(build_config, input_type, operation)\n\n for field in self.OPERATION_FIELDS.get(operation, []):\n if field in build_config:\n build_config[field][\"show\"] = True\n\n return build_config\n\n return build_config\n\n def update_outputs(self, frontend_node: dict, field_name: str, field_value: Any) -> dict:\n \"\"\"Create the output(s) appropriate to the selected input type and operation.\"\"\"\n if field_name == \"input_type\":\n # Switching type clears the operation; advertise the type's default.\n input_type = field_value if field_value in OPERATIONS_BY_TYPE else \"Text\"\n frontend_node[\"outputs\"] = [self._default_output_for_type(input_type)]\n return frontend_node\n\n template = frontend_node.get(\"template\", {})\n input_type = template.get(\"input_type\", {}).get(\"value\", \"Text\")\n\n if field_name == \"operation\":\n operation = self._extract_operation_name(field_value)\n else:\n # Any other refresh (e.g. Path Selection's \"JSON to Map\" field)\n # reaches here on a freshly rebuilt node whose outputs were reset\n # to the class default (Message). Re-derive the output from the\n # saved operation so the refresh doesn't swap the real output type.\n operation = self._extract_operation_name(template.get(\"operation\", {}).get(\"value\", []))\n\n if not operation:\n # No operation selected: fall back to the input type's default output.\n frontend_node[\"outputs\"] = [self._default_output_for_type(input_type)]\n return frontend_node\n\n frontend_node[\"outputs\"] = []\n if operation in JSON_OPERATIONS or operation == \"Word Count\":\n frontend_node[\"outputs\"].append(Output(display_name=\"JSON\", name=\"data_output\", method=\"as_data\"))\n elif operation in TABLE_OPERATIONS or operation == \"Text to DataFrame\":\n frontend_node[\"outputs\"].append(\n Output(display_name=\"Table\", name=\"dataframe_output\", method=\"as_dataframe\")\n )\n elif operation == \"Text Join\":\n frontend_node[\"outputs\"].append(Output(display_name=\"Text\", name=\"text_output\", method=\"as_text\"))\n frontend_node[\"outputs\"].append(Output(display_name=\"Message\", name=\"message_output\", method=\"as_message\"))\n else:\n frontend_node[\"outputs\"].append(Output(display_name=\"Message\", name=\"message_output\", method=\"as_message\"))\n\n return frontend_node\n\n async def update_frontend_node(self, new_frontend_node: dict, current_frontend_node: dict) -> dict:\n \"\"\"Keep the operation options and outputs in sync with the saved input type on load.\"\"\"\n await super().update_frontend_node(new_frontend_node, current_frontend_node)\n\n template = new_frontend_node.get(\"template\", {})\n input_type = template.get(\"input_type\", {}).get(\"value\", \"Text\")\n if input_type not in OPERATIONS_BY_TYPE:\n input_type = \"Text\"\n\n # Filter the operation picker to the saved input type.\n if \"operation\" in template:\n template[\"operation\"][\"options\"] = OPERATIONS_BY_TYPE[input_type]\n\n # Re-derive the outputs from the saved input type + operation.\n operation_value = template.get(\"operation\", {}).get(\"value\", [])\n if self._extract_operation_name(operation_value):\n self.update_outputs(new_frontend_node, \"operation\", operation_value)\n else:\n self.update_outputs(new_frontend_node, \"input_type\", input_type)\n\n return new_frontend_node\n\n # ==================================================================\n # Output methods (referenced by update_outputs)\n # ==================================================================\n def as_data(self) -> Data:\n \"\"\"JSON-typed output: JSON operations and Word Count.\"\"\"\n operation = self._operation_name()\n if operation in JSON_OPERATIONS:\n handler = self._json_handlers().get(operation)\n if handler:\n try:\n return handler()\n except Exception as e:\n logger.error(f\"Error executing {operation}: {e!s}\")\n raise\n if operation == \"Word Count\":\n return self._word_count_data()\n return Data(data={})\n\n def as_dataframe(self) -> DataFrame:\n \"\"\"Table-typed output: Table operations and Text to DataFrame.\"\"\"\n operation = self._operation_name()\n if operation in TABLE_OPERATIONS:\n return self._run_table_operation(operation)\n if operation == \"Text to DataFrame\":\n return self._text_to_dataframe(getattr(self, \"text_input\", \"\") or \"\")\n return DataFrame(pd.DataFrame())\n\n def as_message(self) -> Message:\n \"\"\"Message-typed output: generic text operations (and Text Join).\"\"\"\n return Message(text=self._format_result_as_text(self._run_text_operation()))\n\n def as_text(self) -> Message:\n \"\"\"Text output for the Text Join operation.\"\"\"\n return self.as_message()\n\n # ==================================================================\n # JSON operations\n # ==================================================================\n @staticmethod\n def extract_all_paths(obj, path=\"\"):\n paths = []\n if isinstance(obj, dict):\n for k, v in obj.items():\n new_path = f\"{path}.{k}\" if path else f\".{k}\"\n paths.append(new_path)\n paths.extend(OperationsComponent.extract_all_paths(v, new_path))\n elif isinstance(obj, list) and obj:\n new_path = f\"{path}[0]\"\n paths.append(new_path)\n paths.extend(OperationsComponent.extract_all_paths(obj[0], new_path))\n return paths\n\n @staticmethod\n def remove_keys_recursive(obj, keys_to_remove):\n if isinstance(obj, dict):\n return {\n k: OperationsComponent.remove_keys_recursive(v, keys_to_remove)\n for k, v in obj.items()\n if k not in keys_to_remove\n }\n if isinstance(obj, list):\n return [OperationsComponent.remove_keys_recursive(item, keys_to_remove) for item in obj]\n return obj\n\n @staticmethod\n def rename_keys_recursive(obj, rename_map):\n if isinstance(obj, dict):\n return {\n rename_map.get(k, k): OperationsComponent.rename_keys_recursive(v, rename_map) for k, v in obj.items()\n }\n if isinstance(obj, list):\n return [OperationsComponent.rename_keys_recursive(item, rename_map) for item in obj]\n return obj\n\n def _json_handlers(self) -> \"dict[str, Callable[[], Data]]\":\n return {\n \"Select Keys\": self.select_keys,\n \"Literal Eval\": self.evaluate_data,\n \"Combine\": self.combine_data,\n \"Append or Update\": self.append_update,\n \"Remove Keys\": self.remove_keys,\n \"Rename Keys\": self.rename_keys,\n \"Path Selection\": self.json_path,\n \"JQ Expression\": self.json_query,\n }\n\n def get_data_dict(self) -> dict:\n \"\"\"Extract data dictionary from Data object.\"\"\"\n data = self.data[0] if isinstance(self.data, list) and len(self.data) == 1 else self.data\n return data.model_dump()\n\n def get_normalized_data(self) -> dict:\n \"\"\"Get normalized data dictionary, handling the 'data' key if present.\"\"\"\n data_dict = self.get_data_dict()\n return data_dict.get(\"data\", data_dict)\n\n def data_is_list(self) -> bool:\n \"\"\"Check if data contains multiple items.\"\"\"\n return isinstance(self.data, list) and len(self.data) > 1\n\n def validate_single_data(self, operation: str) -> None:\n \"\"\"Validate that the operation is being performed on a single data object.\"\"\"\n if self.data_is_list():\n msg = f\"{operation} operation is not supported for multiple data objects.\"\n raise ValueError(msg)\n\n def select_keys(self) -> Data:\n \"\"\"Select specific keys from the data dictionary.\"\"\"\n self.validate_single_data(\"Select Keys\")\n data_dict = self.get_normalized_data()\n filter_criteria: list[str] = self.select_keys_input\n\n if len(filter_criteria) == 1 and filter_criteria[0] == \"data\":\n filtered = data_dict[\"data\"]\n else:\n if not all(key in data_dict for key in filter_criteria):\n msg = f\"Select key not found in data. Available keys: {list(data_dict.keys())}\"\n raise ValueError(msg)\n filtered = {key: value for key, value in data_dict.items() if key in filter_criteria}\n\n return Data(data=filtered)\n\n def remove_keys(self) -> Data:\n \"\"\"Remove specified keys from the data dictionary, recursively.\"\"\"\n self.validate_single_data(\"Remove Keys\")\n data_dict = self.get_normalized_data()\n remove_keys_input: list[str] = self.remove_keys_input\n filtered = OperationsComponent.remove_keys_recursive(data_dict, set(remove_keys_input))\n return Data(data=filtered)\n\n def rename_keys(self) -> Data:\n \"\"\"Rename keys in the data dictionary, recursively.\"\"\"\n self.validate_single_data(\"Rename Keys\")\n data_dict = self.get_normalized_data()\n rename_keys_input: dict[str, str] = self.rename_keys_input\n renamed = OperationsComponent.rename_keys_recursive(data_dict, rename_keys_input)\n return Data(data=renamed)\n\n def recursive_eval(self, data: Any) -> Any:\n \"\"\"Recursively evaluate string values that look like Python literals.\"\"\"\n if isinstance(data, dict):\n return {k: self.recursive_eval(v) for k, v in data.items()}\n if isinstance(data, list):\n return [self.recursive_eval(item) for item in data]\n if isinstance(data, str):\n try:\n if (\n data.strip().startswith((\"{\", \"[\", \"(\", \"'\", '\"'))\n or data.strip().lower() in (\"true\", \"false\", \"none\")\n or data.strip().replace(\".\", \"\").isdigit()\n ):\n return ast.literal_eval(data)\n except (ValueError, SyntaxError, TypeError, MemoryError):\n return data\n else:\n return data\n return data\n\n def evaluate_data(self) -> Data:\n \"\"\"Evaluate string values in the data dictionary.\"\"\"\n self.validate_single_data(\"Literal Eval\")\n logger.info(\"evaluating data\")\n return Data(**self.recursive_eval(self.get_data_dict()))\n\n def combine_data(self) -> Data:\n \"\"\"Combine multiple data objects into one.\"\"\"\n logger.info(\"combining data\")\n if not self.data_is_list():\n return self.data[0] if self.data else Data(data={})\n\n data_dicts = [data.model_dump().get(\"data\", data.model_dump()) for data in self.data]\n combined_data: dict[str, Any] = {}\n\n for data_dict in data_dicts:\n for key, value in data_dict.items():\n if key not in combined_data:\n combined_data[key] = value\n elif isinstance(combined_data[key], list):\n if isinstance(value, list):\n combined_data[key].extend(value)\n else:\n combined_data[key].append(value)\n else:\n combined_data[key] = (\n [combined_data[key], value] if not isinstance(value, list) else [combined_data[key], *value]\n )\n\n return Data(**combined_data)\n\n def append_update(self) -> Data:\n \"\"\"Append or update the data with new key-value pairs.\"\"\"\n self.validate_single_data(\"Append or Update\")\n data_filtered = self.get_normalized_data()\n for key, value in self.append_update_data.items():\n data_filtered[key] = value\n return Data(**data_filtered)\n\n def json_path(self) -> Data:\n \"\"\"Extract a value from the data using the selected JQ path.\"\"\"\n try:\n import jq\n except ImportError:\n msg = \"jq is required for Path Selection. Install with: pip install jq\"\n raise ImportError(msg) from None\n\n try:\n if not self.data or not self.selected_key:\n msg = \"Missing input data or selected key.\"\n raise ValueError(msg)\n input_payload = self.data[0].data if isinstance(self.data, list) else self.data.data\n validate_jq_program(self.selected_key)\n compiled = jq.compile(self.selected_key)\n result = compiled.input(input_payload).first()\n if isinstance(result, dict):\n return Data(data=result)\n return Data(data={\"result\": result})\n except (ValueError, TypeError, KeyError) as e:\n self.status = f\"Error: {e!s}\"\n self.log(self.status)\n return Data(data={\"error\": str(e)})\n\n def json_query(self) -> Data:\n \"\"\"Run a JQ expression against the data.\"\"\"\n try:\n import jq\n except ImportError:\n msg = \"jq is required for JQ Expression. Install with: pip install jq\"\n raise ImportError(msg) from None\n\n if not self.query or not self.query.strip():\n msg = \"JSON Query is required and cannot be blank.\"\n raise ValueError(msg)\n raw_data = self.get_data_dict()\n try:\n input_str = json.dumps(raw_data)\n repaired = repair_json(input_str)\n data_json = json.loads(repaired)\n jq_input = data_json[\"data\"] if isinstance(data_json, dict) and \"data\" in data_json else data_json\n validate_jq_program(self.query)\n results = jq.compile(self.query).input(jq_input).all()\n if not results:\n msg = \"No result from JSON query.\"\n raise ValueError(msg)\n result = results[0] if len(results) == 1 else results\n if result is None or result == \"None\":\n msg = \"JSON query returned null/None. Check if the path exists in your data.\"\n raise ValueError(msg)\n if isinstance(result, dict):\n return Data(data=result)\n return Data(data={\"result\": result})\n except (ValueError, TypeError, KeyError, json.JSONDecodeError) as e:\n logger.error(f\"JSON Query failed: {e}\")\n msg = f\"JSON Query error: {e}\"\n raise ValueError(msg) from e\n\n # ==================================================================\n # Table operations\n # ==================================================================\n def _get_primary_dataframe(self) -> DataFrame:\n \"\"\"Get the first DataFrame from input (handles both single and list inputs).\"\"\"\n if isinstance(self.df, list):\n return self.df[0].copy() if self.df else DataFrame()\n return self.df.copy()\n\n def _run_table_operation(self, operation: str) -> DataFrame:\n # Merge and Concatenate use their own inputs, not the primary df.\n if operation == \"Merge\":\n return self.merge_dataframes()\n if operation == \"Concatenate\":\n return self.concatenate_dataframes()\n\n df_copy = self._get_primary_dataframe()\n table_handlers = {\n \"Filter\": self.filter_rows_by_value,\n \"Sort\": self.sort_by_column,\n \"Drop Column\": self.drop_column,\n \"Rename Column\": self.rename_column,\n \"Add Column\": self.add_column,\n \"Select Columns\": self.select_columns,\n \"Head\": self.head,\n \"Tail\": self.tail,\n \"Replace Value\": self.replace_values,\n \"Drop Duplicates\": self.drop_duplicates,\n }\n handler = table_handlers.get(operation)\n if handler is None:\n msg = f\"Unsupported operation: {operation}\"\n logger.error(msg)\n raise ValueError(msg)\n return handler(df_copy)\n\n def filter_rows_by_value(self, df: DataFrame) -> DataFrame:\n column = df[self.column_name]\n filter_value = self.filter_value\n operator = getattr(self, \"filter_operator\", \"equals\")\n\n if operator == \"equals\":\n mask = column == filter_value\n elif operator == \"not equals\":\n mask = column != filter_value\n elif operator == \"contains\":\n mask = column.astype(str).str.contains(str(filter_value), na=False)\n elif operator == \"not contains\":\n mask = ~column.astype(str).str.contains(str(filter_value), na=False)\n elif operator == \"starts with\":\n mask = column.astype(str).str.startswith(str(filter_value), na=False)\n elif operator == \"ends with\":\n mask = column.astype(str).str.endswith(str(filter_value), na=False)\n elif operator == \"greater than\":\n try:\n numeric_value = pd.to_numeric(filter_value)\n mask = column > numeric_value\n except (ValueError, TypeError):\n mask = column.astype(str) > str(filter_value)\n elif operator == \"less than\":\n try:\n numeric_value = pd.to_numeric(filter_value)\n mask = column < numeric_value\n except (ValueError, TypeError):\n mask = column.astype(str) < str(filter_value)\n else:\n mask = column == filter_value\n\n return DataFrame(df[mask])\n\n def sort_by_column(self, df: DataFrame) -> DataFrame:\n return DataFrame(df.sort_values(by=self.column_name, ascending=self.ascending))\n\n def drop_column(self, df: DataFrame) -> DataFrame:\n return DataFrame(df.drop(columns=[self.column_name]))\n\n def rename_column(self, df: DataFrame) -> DataFrame:\n return DataFrame(df.rename(columns={self.column_name: self.new_column_name}))\n\n def add_column(self, df: DataFrame) -> DataFrame:\n df[self.new_column_name] = [self.new_column_value] * len(df)\n return DataFrame(df)\n\n def select_columns(self, df: DataFrame) -> DataFrame:\n columns = [col.strip() for col in self.columns_to_select]\n return DataFrame(df[columns])\n\n def head(self, df: DataFrame) -> DataFrame:\n return DataFrame(df.head(self.num_rows))\n\n def tail(self, df: DataFrame) -> DataFrame:\n return DataFrame(df.tail(self.num_rows))\n\n def replace_values(self, df: DataFrame) -> DataFrame:\n df[self.column_name] = df[self.column_name].replace(self.replace_value, self.replacement_value)\n return DataFrame(df)\n\n def drop_duplicates(self, df: DataFrame) -> DataFrame:\n return DataFrame(df.drop_duplicates(subset=self.column_name))\n\n def concatenate_dataframes(self) -> DataFrame:\n \"\"\"Concatenate multiple DataFrames vertically (stack rows).\"\"\"\n if not isinstance(self.df, list) or len(self.df) == 0:\n return self.df.copy() if self.df is not None else DataFrame()\n\n if len(self.df) == 1:\n return self.df[0].copy()\n\n concatenated = pd.concat(self.df, ignore_index=True)\n return DataFrame(concatenated)\n\n def merge_dataframes(self) -> DataFrame:\n \"\"\"Merge two DataFrames based on a common column (join operation).\"\"\"\n left_df = getattr(self, \"left_dataframe\", None)\n right_df = getattr(self, \"right_dataframe\", None)\n\n if left_df is None:\n return DataFrame()\n if right_df is None:\n return left_df.copy()\n\n df_left = left_df.copy()\n df_right = right_df.copy()\n\n merge_on = getattr(self, \"merge_on_column\", None)\n merge_how = getattr(self, \"merge_how\", \"inner\")\n\n if merge_on:\n if merge_on not in df_left.columns:\n msg = f\"Column '{merge_on}' not found in left DataFrame. Available: {list(df_left.columns)}\"\n raise ValueError(msg)\n if merge_on not in df_right.columns:\n msg = f\"Column '{merge_on}' not found in right DataFrame. Available: {list(df_right.columns)}\"\n raise ValueError(msg)\n merged = df_left.merge(df_right, on=merge_on, how=merge_how, suffixes=(\"\", \"_right\"))\n else:\n merged = df_left.merge(df_right, left_index=True, right_index=True, how=merge_how, suffixes=(\"\", \"_right\"))\n\n cols_to_drop = []\n for col in merged.columns:\n if col.endswith(\"_right\"):\n original_col = col[:-6]\n if original_col in merged.columns:\n merged[original_col] = merged[original_col].combine_first(merged[col])\n cols_to_drop.append(col)\n\n if cols_to_drop:\n merged = merged.drop(columns=cols_to_drop)\n\n return DataFrame(merged)\n\n # ==================================================================\n # Text operations\n # ==================================================================\n def _run_text_operation(self) -> Any:\n \"\"\"Process text based on the selected operation (Message/Text outputs).\"\"\"\n text = getattr(self, \"text_input\", \"\")\n operation = self._operation_name()\n\n # Allow empty text for Text Join (second input may have content).\n if not text and operation != \"Text Join\":\n return None\n\n text_handlers = {\n \"Case Conversion\": self._case_conversion,\n \"Text Replace\": self._text_replace,\n \"Text Extract\": self._text_extract,\n \"Text Head\": self._text_head,\n \"Text Tail\": self._text_tail,\n \"Text Strip\": self._text_strip,\n \"Text Join\": self._text_join,\n \"Text Clean\": self._text_clean,\n }\n handler = text_handlers.get(operation)\n if handler:\n return handler(text)\n return text\n\n def _word_count_data(self) -> Data:\n \"\"\"Word Count operation result as a Data object.\"\"\"\n result = self._word_count(getattr(self, \"text_input\", \"\") or \"\")\n return Data(data=result)\n\n def _word_count(self, text: str) -> dict[str, Any]:\n \"\"\"Count words, characters, and lines in text.\"\"\"\n result: dict[str, Any] = {}\n text_str = str(text) if text else \"\"\n is_empty = not text_str or not text_str.strip()\n\n if getattr(self, \"count_words\", True):\n if is_empty:\n result[\"word_count\"] = 0\n result[\"unique_words\"] = 0\n else:\n words = text_str.split()\n result[\"word_count\"] = len(words)\n result[\"unique_words\"] = len(set(words))\n\n if getattr(self, \"count_characters\", True):\n if is_empty:\n result[\"character_count\"] = 0\n result[\"character_count_no_spaces\"] = 0\n else:\n result[\"character_count\"] = len(text_str)\n result[\"character_count_no_spaces\"] = len(text_str.replace(\" \", \"\"))\n\n if getattr(self, \"count_lines\", True):\n if is_empty:\n result[\"line_count\"] = 0\n result[\"non_empty_lines\"] = 0\n else:\n lines = text_str.split(\"\\n\")\n result[\"line_count\"] = len(lines)\n result[\"non_empty_lines\"] = len([line for line in lines if line.strip()])\n\n return result\n\n def _text_to_dataframe(self, text: str) -> DataFrame:\n \"\"\"Convert markdown-style table text to a DataFrame.\"\"\"\n lines = [line.strip() for line in text.strip().split(\"\\n\") if line.strip()]\n if not lines:\n return DataFrame(pd.DataFrame())\n\n separator = getattr(self, \"table_separator\", \"|\")\n has_header = getattr(self, \"has_header\", True)\n\n rows = self._parse_table_rows(lines, separator)\n if not rows:\n return DataFrame(pd.DataFrame())\n\n df = self._create_dataframe(rows, has_header=has_header)\n self._convert_numeric_columns(df)\n self.log(f\"Converted text to DataFrame: {len(df)} rows, {len(df.columns)} columns\")\n return DataFrame(df)\n\n def _parse_table_rows(self, lines: list[str], separator: str) -> list[list[str]]:\n rows = []\n for line in lines:\n cleaned_line = line.strip(separator)\n cells = [cell.strip() for cell in cleaned_line.split(separator)]\n rows.append(cells)\n return rows\n\n def _create_dataframe(self, rows: list[list[str]], *, has_header: bool) -> pd.DataFrame:\n if has_header and len(rows) > 1:\n header = rows[0]\n data_rows = rows[1:]\n header_col_count = len(header)\n for i, row in enumerate(data_rows):\n row_col_count = len(row)\n if row_col_count != header_col_count:\n msg = (\n f\"Header mismatch: {header_col_count} column(s) in header vs \"\n f\"{row_col_count} column(s) in data row {i + 1}. \"\n \"Please ensure the header has the same number of columns as your data.\"\n )\n raise ValueError(msg)\n return pd.DataFrame(data_rows, columns=header)\n\n max_cols = max(len(row) for row in rows) if rows else 0\n columns = [f\"col_{i}\" for i in range(max_cols)]\n return pd.DataFrame(rows, columns=columns)\n\n def _convert_numeric_columns(self, df: pd.DataFrame) -> None:\n for col in df.columns:\n with contextlib.suppress(ValueError, TypeError):\n df[col] = pd.to_numeric(df[col])\n\n def _case_conversion(self, text: str) -> str:\n case_type = getattr(self, \"case_type\", \"lowercase\")\n converter = CASE_CONVERTERS.get(case_type)\n return converter(text) if converter else text\n\n def _text_replace(self, text: str) -> str:\n search_pattern = getattr(self, \"search_pattern\", \"\")\n if not search_pattern:\n return text\n replacement_text = getattr(self, \"replacement_text\", \"\")\n use_regex = getattr(self, \"use_regex\", False)\n if use_regex:\n try:\n return re.sub(search_pattern, replacement_text, text)\n except re.error as e:\n self.log(f\"Invalid regex pattern: {e}\")\n return text\n return text.replace(search_pattern, replacement_text)\n\n def _text_extract(self, text: str) -> list[str]:\n extract_pattern = getattr(self, \"extract_pattern\", \"\")\n if not extract_pattern:\n return []\n max_matches = getattr(self, \"max_matches\", 10)\n try:\n matches = re.findall(extract_pattern, text)\n except re.error as e:\n msg = f\"Invalid regex pattern '{extract_pattern}': {e}\"\n raise ValueError(msg) from e\n return matches[:max_matches] if max_matches > 0 else matches\n\n def _text_head(self, text: str) -> str:\n head_characters = getattr(self, \"head_characters\", 100)\n if head_characters < 0:\n msg = f\"Characters from Start must be a non-negative integer, got {head_characters}\"\n raise ValueError(msg)\n if head_characters == 0:\n return \"\"\n return text[:head_characters]\n\n def _text_tail(self, text: str) -> str:\n tail_characters = getattr(self, \"tail_characters\", 100)\n if tail_characters < 0:\n msg = f\"Characters from End must be a non-negative integer, got {tail_characters}\"\n raise ValueError(msg)\n if tail_characters == 0:\n return \"\"\n return text[-tail_characters:]\n\n def _text_strip(self, text: str) -> str:\n strip_mode = getattr(self, \"strip_mode\", \"both\")\n strip_characters = getattr(self, \"strip_characters\", \"\")\n text_str = str(text) if text else \"\"\n chars_to_strip = strip_characters if strip_characters else None\n if strip_mode == \"left\":\n return text_str.lstrip(chars_to_strip)\n if strip_mode == \"right\":\n return text_str.rstrip(chars_to_strip)\n return text_str.strip(chars_to_strip)\n\n def _text_join(self, text: str) -> str:\n text_input_2 = getattr(self, \"text_input_2\", \"\")\n text1 = str(text) if text else \"\"\n text2 = str(text_input_2) if text_input_2 else \"\"\n if text1 and text2:\n return f\"{text1}\\n{text2}\"\n return text1 or text2\n\n def _text_clean(self, text: str) -> str:\n result = text\n if getattr(self, \"remove_extra_spaces\", True):\n # Collapse runs of horizontal whitespace but preserve newlines so\n # that remove_empty_lines stays effective when both are enabled.\n result = re.sub(r\"[^\\S\\n]+\", \" \", result)\n if getattr(self, \"remove_special_chars\", False):\n result = re.sub(r\"[^\\w\\s]\", \"\", result)\n if getattr(self, \"remove_empty_lines\", False):\n lines = [line for line in result.split(\"\\n\") if line.strip()]\n result = \"\\n\".join(lines)\n return result\n\n def _format_result_as_text(self, result: Any) -> str:\n if result is None:\n return \"\"\n if isinstance(result, list):\n return \"\\n\".join(str(item) for item in result)\n return str(result)\n"
+ "value": "\"\"\"Unified Operations component.\n\nBrings together the previously separate JSON, Table, and Text operation\ncomponents into a single component. An \"Input Type\" selector (Text / JSON /\nTable) drives everything: it filters the \"Operation\" picker to the operations\nthat apply to that type, reveals the matching input (Text / JSON / Table) and\nits operation-specific fields, and advertises the appropriate output type.\n\nThe three original components (JSON Operations, Table Operations, Text\nOperations) remain available as legacy components for backward compatibility\nwith existing flows.\n\"\"\"\n\nimport ast\nimport contextlib\nimport json\nimport re\nfrom typing import TYPE_CHECKING, Any\n\nimport pandas as pd\nfrom json_repair import repair_json\n\nfrom lfx.custom import Component\nfrom lfx.field_typing import RangeSpec\nfrom lfx.inputs import DictInput, SortableListInput, TabInput\nfrom lfx.io import (\n BoolInput,\n DataFrameInput,\n DataInput,\n DropdownInput,\n IntInput,\n MessageTextInput,\n MultilineInput,\n Output,\n StrInput,\n)\nfrom lfx.log.logger import logger\nfrom lfx.schema import Data\nfrom lfx.schema.dataframe import DataFrame\nfrom lfx.schema.dotdict import dotdict\nfrom lfx.schema.message import Message\nfrom lfx.utils.jq_security import validate_jq_program\n\nif TYPE_CHECKING:\n from collections.abc import Callable\n\n# The \"Input Type\" selector tabs. Each value maps a Langflow data type to the\n# operations, input, and output that belong to it.\nINPUT_TYPES = [\"Text\", \"JSON\", \"Table\"]\n\n# Operations grouped by input type, in display order, each with the icon shown\n# in the Operation picker. This is the single source of truth for the picker;\n# update_build_config swaps the picker's options to the selected type's list.\nOPERATIONS_BY_TYPE: dict[str, list[dict[str, str]]] = {\n \"Text\": [\n {\"name\": \"Word Count\", \"icon\": \"hash\"},\n {\"name\": \"Case Conversion\", \"icon\": \"type\"},\n {\"name\": \"Text Replace\", \"icon\": \"replace\"},\n {\"name\": \"Text Extract\", \"icon\": \"search\"},\n {\"name\": \"Text Head\", \"icon\": \"chevron-left\"},\n {\"name\": \"Text Tail\", \"icon\": \"chevron-right\"},\n {\"name\": \"Text Strip\", \"icon\": \"minus\"},\n {\"name\": \"Text Join\", \"icon\": \"link\"},\n {\"name\": \"Text Clean\", \"icon\": \"sparkles\"},\n {\"name\": \"Text to DataFrame\", \"icon\": \"table\"},\n ],\n \"JSON\": [\n {\"name\": \"Select Keys\", \"icon\": \"lasso-select\"},\n {\"name\": \"Literal Eval\", \"icon\": \"braces\"},\n {\"name\": \"Combine\", \"icon\": \"merge\"},\n {\"name\": \"Append or Update\", \"icon\": \"circle-plus\"},\n {\"name\": \"Remove Keys\", \"icon\": \"eraser\"},\n {\"name\": \"Rename Keys\", \"icon\": \"pencil-line\"},\n {\"name\": \"Path Selection\", \"icon\": \"mouse-pointer\"},\n {\"name\": \"JQ Expression\", \"icon\": \"terminal\"},\n ],\n \"Table\": [\n {\"name\": \"Add Column\", \"icon\": \"plus\"},\n {\"name\": \"Concatenate\", \"icon\": \"combine\"},\n {\"name\": \"Drop Column\", \"icon\": \"minus\"},\n {\"name\": \"Filter\", \"icon\": \"filter\"},\n {\"name\": \"Head\", \"icon\": \"arrow-up\"},\n {\"name\": \"Merge\", \"icon\": \"merge\"},\n {\"name\": \"Rename Column\", \"icon\": \"pencil\"},\n {\"name\": \"Replace Value\", \"icon\": \"replace\"},\n {\"name\": \"Select Columns\", \"icon\": \"columns\"},\n {\"name\": \"Sort\", \"icon\": \"arrow-up-down\"},\n {\"name\": \"Tail\", \"icon\": \"arrow-down\"},\n {\"name\": \"Drop Duplicates\", \"icon\": \"copy-x\"},\n ],\n}\n\n# Operation-name sets derived from the picker, used for dispatch and output\n# routing. Keeping them derived from OPERATIONS_BY_TYPE avoids any drift.\nJSON_OPERATIONS = {op[\"name\"] for op in OPERATIONS_BY_TYPE[\"JSON\"]}\nTABLE_OPERATIONS = {op[\"name\"] for op in OPERATIONS_BY_TYPE[\"Table\"]}\nTEXT_OPERATIONS = {op[\"name\"] for op in OPERATIONS_BY_TYPE[\"Text\"]}\n\n# Each input type maps to its main input field and its default output. \"Text\"\n# normally outputs a Message; \"JSON\" a Data; \"Table\" a DataFrame. A few text\n# operations override this (Word Count -> Data, Text to DataFrame -> DataFrame).\nINPUT_TYPE_TO_MAIN_INPUT = {\"Text\": \"text_input\", \"JSON\": \"data\", \"Table\": \"df\"}\n\n# Case conversions for the Text \"Case Conversion\" operation.\nCASE_CONVERTERS: dict[str, Any] = {\n \"uppercase\": str.upper,\n \"lowercase\": str.lower,\n \"title\": str.title,\n \"capitalize\": str.capitalize,\n \"swapcase\": str.swapcase,\n}\n\n# A markdown table's delimiter row (``|---|:--:|``) separates the header from the body.\nMARKDOWN_DELIMITER_CELL = re.compile(r\":?-+:?\")\n\n\nclass OperationsComponent(Component):\n display_name = \"Data Operations\"\n description = \"Perform operations on Text, JSON, and Tables from a single component.\"\n documentation: str = \"https://docs.langflow.org/components-processing#operations\"\n icon = \"wand-sparkles\"\n name = \"Operations\"\n metadata = {\n \"keywords\": [\n \"operations\",\n \"data operations\",\n \"json\",\n \"json operations\",\n \"table\",\n \"table operations\",\n \"dataframe\",\n \"dataframe operations\",\n \"text\",\n \"text operations\",\n \"select keys\",\n \"literal eval\",\n \"combine\",\n \"append or update\",\n \"remove keys\",\n \"rename keys\",\n \"path selection\",\n \"jq expression\",\n \"parse json\",\n \"add column\",\n \"concatenate\",\n \"drop column\",\n \"filter\",\n \"head\",\n \"merge\",\n \"rename column\",\n \"replace value\",\n \"select columns\",\n \"sort\",\n \"tail\",\n \"drop duplicates\",\n \"word count\",\n \"case conversion\",\n \"text replace\",\n \"text extract\",\n \"text join\",\n \"text clean\",\n \"text to dataframe\",\n \"data manipulation\",\n \"data transformation\",\n ],\n }\n\n # Operation -> operation-specific input fields to reveal when selected.\n OPERATION_FIELDS: dict[str, list[str]] = {\n # JSON\n \"Select Keys\": [\"select_keys_input\"],\n \"Literal Eval\": [],\n \"Combine\": [],\n \"Append or Update\": [\"append_update_data\"],\n \"Remove Keys\": [\"remove_keys_input\"],\n \"Rename Keys\": [\"rename_keys_input\"],\n \"Path Selection\": [\"mapped_json_display\", \"selected_key\"],\n \"JQ Expression\": [\"query\"],\n # Table\n \"Add Column\": [\"new_column_name\", \"new_column_value\"],\n \"Concatenate\": [],\n \"Drop Column\": [\"column_name\"],\n \"Filter\": [\"column_name\", \"filter_value\", \"filter_operator\"],\n \"Head\": [\"num_rows\"],\n \"Merge\": [\"left_dataframe\", \"right_dataframe\", \"merge_on_column\", \"merge_how\"],\n \"Rename Column\": [\"column_name\", \"new_column_name\"],\n \"Replace Value\": [\"column_name\", \"replace_value\", \"replacement_value\"],\n \"Select Columns\": [\"columns_to_select\"],\n \"Sort\": [\"column_name\", \"ascending\"],\n \"Tail\": [\"num_rows\"],\n \"Drop Duplicates\": [\"column_name\"],\n # Text\n \"Word Count\": [\"count_words\", \"count_characters\", \"count_lines\"],\n \"Case Conversion\": [\"case_type\"],\n \"Text Replace\": [\"search_pattern\", \"replacement_text\", \"use_regex\"],\n \"Text Extract\": [\"extract_pattern\", \"max_matches\"],\n \"Text Head\": [\"head_characters\"],\n \"Text Tail\": [\"tail_characters\"],\n \"Text Strip\": [\"strip_mode\", \"strip_characters\"],\n \"Text Join\": [\"text_input_2\"],\n \"Text Clean\": [\"remove_extra_spaces\", \"remove_special_chars\", \"remove_empty_lines\"],\n \"Text to DataFrame\": [\"table_separator\", \"has_header\"],\n }\n\n # The three main inputs (one per data type). They are never treated as\n # operation-specific fields; the input-type selector toggles them.\n MAIN_INPUTS = (\"text_input\", \"data\", \"df\")\n\n # Every operation-specific field (union of all the lists above), used to\n # hide and reset fields whenever the input type or operation changes.\n ALL_OPERATION_FIELDS: list[str] = [\n # JSON\n \"select_keys_input\",\n \"append_update_data\",\n \"remove_keys_input\",\n \"rename_keys_input\",\n \"mapped_json_display\",\n \"selected_key\",\n \"query\",\n # Table\n \"column_name\",\n \"filter_value\",\n \"filter_operator\",\n \"ascending\",\n \"new_column_name\",\n \"new_column_value\",\n \"columns_to_select\",\n \"num_rows\",\n \"replace_value\",\n \"replacement_value\",\n \"left_dataframe\",\n \"right_dataframe\",\n \"merge_on_column\",\n \"merge_how\",\n # Text\n \"table_separator\",\n \"has_header\",\n \"count_words\",\n \"count_characters\",\n \"count_lines\",\n \"case_type\",\n \"use_regex\",\n \"search_pattern\",\n \"replacement_text\",\n \"extract_pattern\",\n \"max_matches\",\n \"head_characters\",\n \"tail_characters\",\n \"strip_mode\",\n \"strip_characters\",\n \"text_input_2\",\n \"remove_extra_spaces\",\n \"remove_special_chars\",\n \"remove_empty_lines\",\n ]\n\n # Defaults applied to the JSON operation fields when the operation changes,\n # mirroring the JSON Operations component's reset behavior.\n OPERATION_FIELD_DEFAULTS: dict[str, Any] = {\n \"select_keys_input\": [],\n \"append_update_data\": {\"key\": \"value\"},\n \"remove_keys_input\": [],\n \"rename_keys_input\": {\"old_key\": \"new_key\"},\n \"mapped_json_display\": \"\",\n \"selected_key\": None,\n \"query\": \"\",\n }\n\n inputs = [\n # --- Input type selector: drives operations, input, and output ---\n TabInput(\n name=\"input_type\",\n display_name=\"Input Type\",\n options=INPUT_TYPES,\n value=\"Text\",\n info=\"Select the type of input to operate on.\",\n real_time_refresh=True,\n ),\n # --- Main inputs: one per data type, shown contextually ---\n MultilineInput(\n name=\"text_input\",\n display_name=\"Text\",\n info=\"The input text to process.\",\n show=True,\n ),\n DataInput(\n name=\"data\",\n display_name=\"JSON\",\n info=\"The JSON / Data object to operate on.\",\n is_list=True,\n show=False,\n ),\n DataFrameInput(\n name=\"df\",\n display_name=\"Table\",\n info=\"The input Table to operate on. Connect multiple Tables for merge or concatenate operations.\",\n is_list=True,\n show=False,\n ),\n # --- Operation picker (options are filtered by Input Type) ---\n SortableListInput(\n name=\"operation\",\n display_name=\"Operation\",\n placeholder=\"Select Operation\",\n info=\"Select the operation to perform. The matching fields and output appear once you choose one.\",\n options=OPERATIONS_BY_TYPE[\"Text\"],\n real_time_refresh=True,\n limit=1,\n ),\n # --- JSON operation fields ---\n MessageTextInput(\n name=\"select_keys_input\",\n display_name=\"Select Keys\",\n info=\"List of keys to select from the data. Only top-level keys can be selected.\",\n show=False,\n is_list=True,\n value=[],\n ),\n DictInput(\n name=\"append_update_data\",\n display_name=\"Append or Update\",\n info=\"Data to append or update the existing data with. Only top-level keys are checked.\",\n show=False,\n value={\"key\": \"value\"},\n is_list=True,\n ),\n MessageTextInput(\n name=\"remove_keys_input\",\n display_name=\"Remove Keys\",\n info=\"List of keys to remove from the data.\",\n show=False,\n is_list=True,\n value=[],\n ),\n DictInput(\n name=\"rename_keys_input\",\n display_name=\"Rename Keys\",\n info=\"List of keys to rename in the data.\",\n show=False,\n is_list=True,\n value={\"old_key\": \"new_key\"},\n ),\n MultilineInput(\n name=\"mapped_json_display\",\n display_name=\"JSON to Map\",\n info=\"Paste or preview your JSON here to explore its structure and select a path for extraction.\",\n required=False,\n refresh_button=True,\n real_time_refresh=True,\n placeholder=\"Add a JSON example.\",\n show=False,\n ),\n DropdownInput(\n name=\"selected_key\",\n display_name=\"Select Path\",\n options=[],\n required=False,\n dynamic=True,\n show=False,\n value=None,\n ),\n MessageTextInput(\n name=\"query\",\n display_name=\"JQ Expression\",\n info=\"JSON Query to filter the data. Used by Path Selection and JQ Expression operations.\",\n placeholder=\"e.g., .properties.id\",\n show=False,\n ),\n # --- Table operation fields ---\n StrInput(\n name=\"column_name\",\n display_name=\"Column Name\",\n info=\"The column name to use for the operation.\",\n dynamic=True,\n show=False,\n ),\n MessageTextInput(\n name=\"filter_value\",\n display_name=\"Filter Value\",\n info=\"The value to filter rows by.\",\n dynamic=True,\n show=False,\n ),\n DropdownInput(\n name=\"filter_operator\",\n display_name=\"Filter Operator\",\n options=[\n \"equals\",\n \"not equals\",\n \"contains\",\n \"not contains\",\n \"starts with\",\n \"ends with\",\n \"greater than\",\n \"less than\",\n ],\n value=\"equals\",\n info=\"The operator to apply for filtering rows.\",\n advanced=False,\n dynamic=True,\n show=False,\n ),\n BoolInput(\n name=\"ascending\",\n display_name=\"Sort Ascending\",\n info=\"Whether to sort in ascending order.\",\n dynamic=True,\n show=False,\n value=True,\n ),\n StrInput(\n name=\"new_column_name\",\n display_name=\"New Column Name\",\n info=\"The new column name when renaming or adding a column.\",\n dynamic=True,\n show=False,\n ),\n MessageTextInput(\n name=\"new_column_value\",\n display_name=\"New Column Value\",\n info=\"The value to populate the new column with.\",\n dynamic=True,\n show=False,\n ),\n StrInput(\n name=\"columns_to_select\",\n display_name=\"Columns to Select\",\n dynamic=True,\n is_list=True,\n show=False,\n ),\n IntInput(\n name=\"num_rows\",\n display_name=\"Number of Rows\",\n info=\"Number of rows to return (for head/tail).\",\n dynamic=True,\n show=False,\n value=5,\n ),\n MessageTextInput(\n name=\"replace_value\",\n display_name=\"Value to Replace\",\n info=\"The value to replace in the column.\",\n dynamic=True,\n show=False,\n ),\n MessageTextInput(\n name=\"replacement_value\",\n display_name=\"Replacement Value\",\n info=\"The value to replace with.\",\n dynamic=True,\n show=False,\n ),\n DataFrameInput(\n name=\"left_dataframe\",\n display_name=\"Left Table\",\n info=\"The left (primary) Table for merge operations. \"\n \"In a left merge, all rows from this table are preserved.\",\n dynamic=True,\n show=False,\n ),\n DataFrameInput(\n name=\"right_dataframe\",\n display_name=\"Right Table\",\n info=\"The right (secondary) Table for merge operations. \"\n \"In a right merge, all rows from this table are preserved.\",\n dynamic=True,\n show=False,\n ),\n StrInput(\n name=\"merge_on_column\",\n display_name=\"Merge On Column\",\n info=\"The column name to merge Tables on. Must exist in both Tables.\",\n dynamic=True,\n show=False,\n ),\n DropdownInput(\n name=\"merge_how\",\n display_name=\"Merge Type\",\n options=[\"inner\", \"outer\", \"left\", \"right\"],\n value=\"inner\",\n info=\"Type of merge: inner (intersection), outer (union), left, or right.\",\n dynamic=True,\n show=False,\n ),\n # --- Text operation fields ---\n StrInput(\n name=\"table_separator\",\n display_name=\"Table Separator\",\n info=\"Separator used in the table (default: '|').\",\n value=\"|\",\n dynamic=True,\n show=False,\n ),\n BoolInput(\n name=\"has_header\",\n display_name=\"Has Header\",\n info=\"Whether the table has a header row.\",\n value=True,\n dynamic=True,\n advanced=True,\n show=False,\n ),\n BoolInput(\n name=\"count_words\",\n display_name=\"Count Words\",\n info=\"Include word count in analysis.\",\n value=True,\n dynamic=True,\n advanced=True,\n show=False,\n ),\n BoolInput(\n name=\"count_characters\",\n display_name=\"Count Characters\",\n info=\"Include character count in analysis.\",\n value=True,\n dynamic=True,\n advanced=True,\n show=False,\n ),\n BoolInput(\n name=\"count_lines\",\n display_name=\"Count Lines\",\n info=\"Include line count in analysis.\",\n value=True,\n dynamic=True,\n advanced=True,\n show=False,\n ),\n DropdownInput(\n name=\"case_type\",\n display_name=\"Case Type\",\n options=[\"uppercase\", \"lowercase\", \"title\", \"capitalize\", \"swapcase\"],\n value=\"lowercase\",\n info=\"Type of case conversion to apply.\",\n dynamic=True,\n show=False,\n ),\n BoolInput(\n name=\"use_regex\",\n display_name=\"Use Regex\",\n info=\"Whether to treat search pattern as regex.\",\n value=False,\n dynamic=True,\n show=False,\n ),\n StrInput(\n name=\"search_pattern\",\n display_name=\"Search Pattern\",\n info=\"Text pattern to search for (supports regex).\",\n dynamic=True,\n show=False,\n ),\n StrInput(\n name=\"replacement_text\",\n display_name=\"Replacement Text\",\n info=\"Text to replace the search pattern with.\",\n dynamic=True,\n show=False,\n ),\n StrInput(\n name=\"extract_pattern\",\n display_name=\"Extract Pattern\",\n info=\"Regex pattern to extract from text.\",\n dynamic=True,\n show=False,\n ),\n IntInput(\n name=\"max_matches\",\n display_name=\"Max Matches\",\n info=\"Maximum number of matches to extract.\",\n value=10,\n dynamic=True,\n show=False,\n ),\n IntInput(\n name=\"head_characters\",\n display_name=\"Characters from Start\",\n info=\"Number of characters to extract from the beginning of text. Must be non-negative.\",\n value=100,\n dynamic=True,\n show=False,\n range_spec=RangeSpec(min=0, max=1000000, step=1, step_type=\"int\"),\n ),\n IntInput(\n name=\"tail_characters\",\n display_name=\"Characters from End\",\n info=\"Number of characters to extract from the end of text. Must be non-negative.\",\n value=100,\n dynamic=True,\n show=False,\n range_spec=RangeSpec(min=0, max=1000000, step=1, step_type=\"int\"),\n ),\n DropdownInput(\n name=\"strip_mode\",\n display_name=\"Strip Mode\",\n options=[\"both\", \"left\", \"right\"],\n value=\"both\",\n info=\"Which sides to strip whitespace from.\",\n dynamic=True,\n show=False,\n ),\n StrInput(\n name=\"strip_characters\",\n display_name=\"Characters to Strip\",\n info=\"Specific characters to remove (leave empty for whitespace).\",\n value=\"\",\n dynamic=True,\n show=False,\n ),\n MultilineInput(\n name=\"text_input_2\",\n display_name=\"Second Text Input\",\n info=\"Second text to join with the first text.\",\n dynamic=True,\n show=False,\n ),\n BoolInput(\n name=\"remove_extra_spaces\",\n display_name=\"Remove Extra Spaces\",\n info=\"Remove multiple consecutive spaces.\",\n value=True,\n dynamic=True,\n show=False,\n ),\n BoolInput(\n name=\"remove_special_chars\",\n display_name=\"Remove Special Characters\",\n info=\"Remove special characters except alphanumeric and spaces.\",\n value=False,\n dynamic=True,\n show=False,\n ),\n BoolInput(\n name=\"remove_empty_lines\",\n display_name=\"Remove Empty Lines\",\n info=\"Remove empty lines from text.\",\n value=False,\n dynamic=True,\n show=False,\n ),\n ]\n\n # Default output matches the default Input Type (\"Text\" -> Message).\n # update_outputs / update_frontend_node narrow it to the selected type and\n # operation.\n outputs = [Output(display_name=\"Message\", name=\"message_output\", method=\"as_message\")]\n\n # ------------------------------------------------------------------\n # Operation routing helpers\n # ------------------------------------------------------------------\n @staticmethod\n def _extract_operation_name(field_value: Any) -> str:\n \"\"\"Extract the operation name from a SortableListInput value.\"\"\"\n if isinstance(field_value, list) and len(field_value) > 0 and isinstance(field_value[0], dict):\n return field_value[0].get(\"name\", \"\")\n if isinstance(field_value, str):\n return field_value\n return \"\"\n\n def _operation_name(self) -> str:\n \"\"\"Get the currently selected operation name.\"\"\"\n return self._extract_operation_name(getattr(self, \"operation\", []))\n\n @staticmethod\n def _default_output_for_type(input_type: str) -> Output:\n \"\"\"Return the output advertised for an input type when no operation is selected yet.\"\"\"\n if input_type == \"JSON\":\n return Output(display_name=\"JSON\", name=\"data_output\", method=\"as_data\")\n if input_type == \"Table\":\n return Output(display_name=\"Table\", name=\"dataframe_output\", method=\"as_dataframe\")\n return Output(display_name=\"Message\", name=\"message_output\", method=\"as_message\")\n\n # ------------------------------------------------------------------\n # Dynamic UI\n # ------------------------------------------------------------------\n def _reset_operation_fields(self, build_config: dotdict) -> None:\n \"\"\"Hide every operation-specific field and restore its default value.\"\"\"\n for field in self.ALL_OPERATION_FIELDS:\n if field in build_config:\n build_config[field][\"show\"] = False\n if field in self.OPERATION_FIELD_DEFAULTS:\n build_config[field][\"value\"] = self.OPERATION_FIELD_DEFAULTS[field]\n\n def _show_main_input(self, build_config: dotdict, input_type: str, operation: str) -> None:\n \"\"\"Show only the main input that matches the input type; hide the others.\"\"\"\n for inp in self.MAIN_INPUTS:\n if inp in build_config:\n build_config[inp][\"show\"] = False\n build_config[inp][\"required\"] = False\n\n main_input = INPUT_TYPE_TO_MAIN_INPUT.get(input_type)\n if main_input and main_input in build_config:\n build_config[main_input][\"show\"] = True\n build_config[main_input][\"required\"] = True\n # The JSON \"Combine\" operation consumes a list of Data objects.\n if main_input == \"data\":\n build_config[\"data\"][\"is_list\"] = operation == \"Combine\"\n\n def update_build_config(self, build_config: dotdict, field_value: Any, field_name: str | None = None) -> dotdict:\n # Path Selection: refresh the available JSON paths from the pasted JSON.\n if field_name == \"mapped_json_display\":\n try:\n parsed_json = json.loads(field_value)\n keys = self.extract_all_paths(parsed_json)\n build_config[\"selected_key\"][\"options\"] = keys\n build_config[\"selected_key\"][\"show\"] = True\n except (json.JSONDecodeError, TypeError, ValueError) as e:\n logger.error(f\"Error parsing mapped JSON: {e}\")\n build_config[\"selected_key\"][\"show\"] = False\n return build_config\n\n # Input type changed: swap the operation list, clear the selection, and\n # show only the matching input. No operation-specific fields are shown\n # until an operation is picked.\n if field_name == \"input_type\":\n input_type = field_value if field_value in OPERATIONS_BY_TYPE else \"Text\"\n build_config[\"operation\"][\"options\"] = OPERATIONS_BY_TYPE[input_type]\n build_config[\"operation\"][\"value\"] = []\n self._reset_operation_fields(build_config)\n self._show_main_input(build_config, input_type, operation=\"\")\n return build_config\n\n # Operation changed: reset fields, show the input for the current type,\n # then reveal the operation-specific fields.\n if field_name == \"operation\":\n operation = self._extract_operation_name(field_value)\n self._reset_operation_fields(build_config)\n\n input_type = build_config.get(\"input_type\", {}).get(\"value\", \"Text\")\n self._show_main_input(build_config, input_type, operation)\n\n for field in self.OPERATION_FIELDS.get(operation, []):\n if field in build_config:\n build_config[field][\"show\"] = True\n\n return build_config\n\n return build_config\n\n def update_outputs(self, frontend_node: dict, field_name: str, field_value: Any) -> dict:\n \"\"\"Create the output(s) appropriate to the selected input type and operation.\"\"\"\n if field_name == \"input_type\":\n # Switching type clears the operation; advertise the type's default.\n input_type = field_value if field_value in OPERATIONS_BY_TYPE else \"Text\"\n frontend_node[\"outputs\"] = [self._default_output_for_type(input_type)]\n return frontend_node\n\n template = frontend_node.get(\"template\", {})\n input_type = template.get(\"input_type\", {}).get(\"value\", \"Text\")\n\n if field_name == \"operation\":\n operation = self._extract_operation_name(field_value)\n else:\n # Any other refresh (e.g. Path Selection's \"JSON to Map\" field)\n # reaches here on a freshly rebuilt node whose outputs were reset\n # to the class default (Message). Re-derive the output from the\n # saved operation so the refresh doesn't swap the real output type.\n operation = self._extract_operation_name(template.get(\"operation\", {}).get(\"value\", []))\n\n if not operation:\n # No operation selected: fall back to the input type's default output.\n frontend_node[\"outputs\"] = [self._default_output_for_type(input_type)]\n return frontend_node\n\n frontend_node[\"outputs\"] = []\n if operation in JSON_OPERATIONS or operation == \"Word Count\":\n frontend_node[\"outputs\"].append(Output(display_name=\"JSON\", name=\"data_output\", method=\"as_data\"))\n elif operation in TABLE_OPERATIONS or operation == \"Text to DataFrame\":\n frontend_node[\"outputs\"].append(\n Output(display_name=\"Table\", name=\"dataframe_output\", method=\"as_dataframe\")\n )\n elif operation == \"Text Join\":\n frontend_node[\"outputs\"].append(Output(display_name=\"Text\", name=\"text_output\", method=\"as_text\"))\n frontend_node[\"outputs\"].append(Output(display_name=\"Message\", name=\"message_output\", method=\"as_message\"))\n else:\n frontend_node[\"outputs\"].append(Output(display_name=\"Message\", name=\"message_output\", method=\"as_message\"))\n\n return frontend_node\n\n async def update_frontend_node(self, new_frontend_node: dict, current_frontend_node: dict) -> dict:\n \"\"\"Keep the operation options and outputs in sync with the saved input type on load.\"\"\"\n await super().update_frontend_node(new_frontend_node, current_frontend_node)\n\n template = new_frontend_node.get(\"template\", {})\n input_type = template.get(\"input_type\", {}).get(\"value\", \"Text\")\n if input_type not in OPERATIONS_BY_TYPE:\n input_type = \"Text\"\n\n # Filter the operation picker to the saved input type.\n if \"operation\" in template:\n template[\"operation\"][\"options\"] = OPERATIONS_BY_TYPE[input_type]\n\n # Re-derive the outputs from the saved input type + operation.\n operation_value = template.get(\"operation\", {}).get(\"value\", [])\n if self._extract_operation_name(operation_value):\n self.update_outputs(new_frontend_node, \"operation\", operation_value)\n else:\n self.update_outputs(new_frontend_node, \"input_type\", input_type)\n\n return new_frontend_node\n\n # ==================================================================\n # Output methods (referenced by update_outputs)\n # ==================================================================\n def as_data(self) -> Data:\n \"\"\"JSON-typed output: JSON operations and Word Count.\"\"\"\n operation = self._operation_name()\n if operation in JSON_OPERATIONS:\n handler = self._json_handlers().get(operation)\n if handler:\n try:\n return handler()\n except Exception as e:\n logger.error(f\"Error executing {operation}: {e!s}\")\n raise\n if operation == \"Word Count\":\n return self._word_count_data()\n return Data(data={})\n\n def as_dataframe(self) -> DataFrame:\n \"\"\"Table-typed output: Table operations and Text to DataFrame.\"\"\"\n operation = self._operation_name()\n if operation in TABLE_OPERATIONS:\n return self._run_table_operation(operation)\n if operation == \"Text to DataFrame\":\n return self._text_to_dataframe(getattr(self, \"text_input\", \"\") or \"\")\n return DataFrame(pd.DataFrame())\n\n def as_message(self) -> Message:\n \"\"\"Message-typed output: generic text operations (and Text Join).\"\"\"\n return Message(text=self._format_result_as_text(self._run_text_operation()))\n\n def as_text(self) -> Message:\n \"\"\"Text output for the Text Join operation.\"\"\"\n return self.as_message()\n\n # ==================================================================\n # JSON operations\n # ==================================================================\n @staticmethod\n def extract_all_paths(obj, path=\"\"):\n paths = []\n if isinstance(obj, dict):\n for k, v in obj.items():\n new_path = f\"{path}.{k}\" if path else f\".{k}\"\n paths.append(new_path)\n paths.extend(OperationsComponent.extract_all_paths(v, new_path))\n elif isinstance(obj, list) and obj:\n new_path = f\"{path}[0]\"\n paths.append(new_path)\n paths.extend(OperationsComponent.extract_all_paths(obj[0], new_path))\n return paths\n\n @staticmethod\n def remove_keys_recursive(obj, keys_to_remove):\n if isinstance(obj, dict):\n return {\n k: OperationsComponent.remove_keys_recursive(v, keys_to_remove)\n for k, v in obj.items()\n if k not in keys_to_remove\n }\n if isinstance(obj, list):\n return [OperationsComponent.remove_keys_recursive(item, keys_to_remove) for item in obj]\n return obj\n\n @staticmethod\n def rename_keys_recursive(obj, rename_map):\n if isinstance(obj, dict):\n return {\n rename_map.get(k, k): OperationsComponent.rename_keys_recursive(v, rename_map) for k, v in obj.items()\n }\n if isinstance(obj, list):\n return [OperationsComponent.rename_keys_recursive(item, rename_map) for item in obj]\n return obj\n\n def _json_handlers(self) -> \"dict[str, Callable[[], Data]]\":\n return {\n \"Select Keys\": self.select_keys,\n \"Literal Eval\": self.evaluate_data,\n \"Combine\": self.combine_data,\n \"Append or Update\": self.append_update,\n \"Remove Keys\": self.remove_keys,\n \"Rename Keys\": self.rename_keys,\n \"Path Selection\": self.json_path,\n \"JQ Expression\": self.json_query,\n }\n\n def get_data_dict(self) -> dict:\n \"\"\"Extract data dictionary from Data object.\"\"\"\n data = self.data[0] if isinstance(self.data, list) and len(self.data) == 1 else self.data\n return data.model_dump()\n\n def get_normalized_data(self) -> dict:\n \"\"\"Get normalized data dictionary, handling the 'data' key if present.\"\"\"\n data_dict = self.get_data_dict()\n return data_dict.get(\"data\", data_dict)\n\n def data_is_list(self) -> bool:\n \"\"\"Check if data contains multiple items.\"\"\"\n return isinstance(self.data, list) and len(self.data) > 1\n\n def validate_single_data(self, operation: str) -> None:\n \"\"\"Validate that the operation is being performed on a single data object.\"\"\"\n if self.data_is_list():\n msg = f\"{operation} operation is not supported for multiple data objects.\"\n raise ValueError(msg)\n\n def select_keys(self) -> Data:\n \"\"\"Select specific keys from the data dictionary.\"\"\"\n self.validate_single_data(\"Select Keys\")\n data_dict = self.get_normalized_data()\n filter_criteria: list[str] = self.select_keys_input\n\n if len(filter_criteria) == 1 and filter_criteria[0] == \"data\":\n filtered = data_dict[\"data\"]\n else:\n if not all(key in data_dict for key in filter_criteria):\n msg = f\"Select key not found in data. Available keys: {list(data_dict.keys())}\"\n raise ValueError(msg)\n filtered = {key: value for key, value in data_dict.items() if key in filter_criteria}\n\n return Data(data=filtered)\n\n def remove_keys(self) -> Data:\n \"\"\"Remove specified keys from the data dictionary, recursively.\"\"\"\n self.validate_single_data(\"Remove Keys\")\n data_dict = self.get_normalized_data()\n remove_keys_input: list[str] = self.remove_keys_input\n filtered = OperationsComponent.remove_keys_recursive(data_dict, set(remove_keys_input))\n return Data(data=filtered)\n\n def rename_keys(self) -> Data:\n \"\"\"Rename keys in the data dictionary, recursively.\"\"\"\n self.validate_single_data(\"Rename Keys\")\n data_dict = self.get_normalized_data()\n rename_keys_input: dict[str, str] = self.rename_keys_input\n renamed = OperationsComponent.rename_keys_recursive(data_dict, rename_keys_input)\n return Data(data=renamed)\n\n def recursive_eval(self, data: Any) -> Any:\n \"\"\"Recursively evaluate string values that look like Python literals.\"\"\"\n if isinstance(data, dict):\n return {k: self.recursive_eval(v) for k, v in data.items()}\n if isinstance(data, list):\n return [self.recursive_eval(item) for item in data]\n if isinstance(data, str):\n try:\n if (\n data.strip().startswith((\"{\", \"[\", \"(\", \"'\", '\"'))\n or data.strip().lower() in (\"true\", \"false\", \"none\")\n or data.strip().replace(\".\", \"\").isdigit()\n ):\n return ast.literal_eval(data)\n except (ValueError, SyntaxError, TypeError, MemoryError):\n return data\n else:\n return data\n return data\n\n def evaluate_data(self) -> Data:\n \"\"\"Evaluate string values in the data dictionary.\"\"\"\n self.validate_single_data(\"Literal Eval\")\n logger.info(\"evaluating data\")\n return Data(**self.recursive_eval(self.get_data_dict()))\n\n def combine_data(self) -> Data:\n \"\"\"Combine multiple data objects into one.\"\"\"\n logger.info(\"combining data\")\n if not self.data_is_list():\n return self.data[0] if self.data else Data(data={})\n\n data_dicts = [data.model_dump().get(\"data\", data.model_dump()) for data in self.data]\n combined_data: dict[str, Any] = {}\n\n for data_dict in data_dicts:\n for key, value in data_dict.items():\n if key not in combined_data:\n combined_data[key] = value\n elif isinstance(combined_data[key], list):\n if isinstance(value, list):\n combined_data[key].extend(value)\n else:\n combined_data[key].append(value)\n else:\n combined_data[key] = (\n [combined_data[key], value] if not isinstance(value, list) else [combined_data[key], *value]\n )\n\n return Data(**combined_data)\n\n def append_update(self) -> Data:\n \"\"\"Append or update the data with new key-value pairs.\"\"\"\n self.validate_single_data(\"Append or Update\")\n data_filtered = self.get_normalized_data()\n for key, value in self.append_update_data.items():\n data_filtered[key] = value\n return Data(**data_filtered)\n\n def json_path(self) -> Data:\n \"\"\"Extract a value from the data using the selected JQ path.\"\"\"\n try:\n import jq\n except ImportError:\n msg = \"jq is required for Path Selection. Install with: pip install jq\"\n raise ImportError(msg) from None\n\n try:\n if not self.data or not self.selected_key:\n msg = \"Missing input data or selected key.\"\n raise ValueError(msg)\n input_payload = self.data[0].data if isinstance(self.data, list) else self.data.data\n validate_jq_program(self.selected_key)\n compiled = jq.compile(self.selected_key)\n result = compiled.input(input_payload).first()\n if isinstance(result, dict):\n return Data(data=result)\n return Data(data={\"result\": result})\n except (ValueError, TypeError, KeyError) as e:\n self.status = f\"Error: {e!s}\"\n self.log(self.status)\n return Data(data={\"error\": str(e)})\n\n def json_query(self) -> Data:\n \"\"\"Run a JQ expression against the data.\"\"\"\n try:\n import jq\n except ImportError:\n msg = \"jq is required for JQ Expression. Install with: pip install jq\"\n raise ImportError(msg) from None\n\n if not self.query or not self.query.strip():\n msg = \"JSON Query is required and cannot be blank.\"\n raise ValueError(msg)\n raw_data = self.get_data_dict()\n try:\n input_str = json.dumps(raw_data)\n repaired = repair_json(input_str)\n data_json = json.loads(repaired)\n jq_input = data_json[\"data\"] if isinstance(data_json, dict) and \"data\" in data_json else data_json\n validate_jq_program(self.query)\n results = jq.compile(self.query).input(jq_input).all()\n if not results:\n msg = \"No result from JSON query.\"\n raise ValueError(msg)\n result = results[0] if len(results) == 1 else results\n if result is None or result == \"None\":\n msg = \"JSON query returned null/None. Check if the path exists in your data.\"\n raise ValueError(msg)\n if isinstance(result, dict):\n return Data(data=result)\n return Data(data={\"result\": result})\n except (ValueError, TypeError, KeyError, json.JSONDecodeError) as e:\n logger.error(f\"JSON Query failed: {e}\")\n msg = f\"JSON Query error: {e}\"\n raise ValueError(msg) from e\n\n # ==================================================================\n # Table operations\n # ==================================================================\n def _get_primary_dataframe(self) -> DataFrame:\n \"\"\"Get the first DataFrame from input (handles both single and list inputs).\"\"\"\n if isinstance(self.df, list):\n return self.df[0].copy() if self.df else DataFrame()\n return self.df.copy()\n\n def _run_table_operation(self, operation: str) -> DataFrame:\n # Merge and Concatenate use their own inputs, not the primary df.\n if operation == \"Merge\":\n return self.merge_dataframes()\n if operation == \"Concatenate\":\n return self.concatenate_dataframes()\n\n df_copy = self._get_primary_dataframe()\n table_handlers = {\n \"Filter\": self.filter_rows_by_value,\n \"Sort\": self.sort_by_column,\n \"Drop Column\": self.drop_column,\n \"Rename Column\": self.rename_column,\n \"Add Column\": self.add_column,\n \"Select Columns\": self.select_columns,\n \"Head\": self.head,\n \"Tail\": self.tail,\n \"Replace Value\": self.replace_values,\n \"Drop Duplicates\": self.drop_duplicates,\n }\n handler = table_handlers.get(operation)\n if handler is None:\n msg = f\"Unsupported operation: {operation}\"\n logger.error(msg)\n raise ValueError(msg)\n return handler(df_copy)\n\n @staticmethod\n def _comparable_filter_value(column: pd.Series, filter_value: Any) -> Any:\n \"\"\"Return a text input as a number when the column is numeric.\n\n Filter and Replace Value inputs arrive as text, and ``30 == \"30\"`` never matches in pandas.\n A blank input stays text: ``pd.to_numeric(\"\")`` is NaN, which would match missing cells.\n \"\"\"\n if filter_value in (None, \"\"):\n return filter_value\n if pd.api.types.is_numeric_dtype(column) and not pd.api.types.is_bool_dtype(column):\n try:\n return pd.to_numeric(filter_value)\n except (ValueError, TypeError):\n return filter_value\n return filter_value\n\n def filter_rows_by_value(self, df: DataFrame) -> DataFrame:\n column = df[self.column_name]\n filter_value = self.filter_value\n operator = getattr(self, \"filter_operator\", \"equals\")\n\n if operator == \"equals\":\n mask = column == self._comparable_filter_value(column, filter_value)\n elif operator == \"not equals\":\n mask = column != self._comparable_filter_value(column, filter_value)\n elif operator == \"contains\":\n mask = column.astype(str).str.contains(str(filter_value), na=False)\n elif operator == \"not contains\":\n mask = ~column.astype(str).str.contains(str(filter_value), na=False)\n elif operator == \"starts with\":\n mask = column.astype(str).str.startswith(str(filter_value), na=False)\n elif operator == \"ends with\":\n mask = column.astype(str).str.endswith(str(filter_value), na=False)\n elif operator == \"greater than\":\n try:\n numeric_value = pd.to_numeric(filter_value)\n mask = column > numeric_value\n except (ValueError, TypeError):\n mask = column.astype(str) > str(filter_value)\n elif operator == \"less than\":\n try:\n numeric_value = pd.to_numeric(filter_value)\n mask = column < numeric_value\n except (ValueError, TypeError):\n mask = column.astype(str) < str(filter_value)\n else:\n mask = column == self._comparable_filter_value(column, filter_value)\n\n return DataFrame(df[mask])\n\n def sort_by_column(self, df: DataFrame) -> DataFrame:\n return DataFrame(df.sort_values(by=self.column_name, ascending=self.ascending))\n\n def drop_column(self, df: DataFrame) -> DataFrame:\n return DataFrame(df.drop(columns=[self.column_name]))\n\n def rename_column(self, df: DataFrame) -> DataFrame:\n return DataFrame(df.rename(columns={self.column_name: self.new_column_name}))\n\n def add_column(self, df: DataFrame) -> DataFrame:\n df[self.new_column_name] = [self.new_column_value] * len(df)\n return DataFrame(df)\n\n def select_columns(self, df: DataFrame) -> DataFrame:\n columns = [col.strip() for col in self.columns_to_select]\n return DataFrame(df[columns])\n\n def head(self, df: DataFrame) -> DataFrame:\n return DataFrame(df.head(self.num_rows))\n\n def tail(self, df: DataFrame) -> DataFrame:\n return DataFrame(df.tail(self.num_rows))\n\n def replace_values(self, df: DataFrame) -> DataFrame:\n column = df[self.column_name]\n replace_val = self._comparable_filter_value(column, self.replace_value)\n replacement_val = self._comparable_filter_value(column, self.replacement_value)\n try:\n result = column.replace(replace_val, replacement_val)\n except TypeError:\n if not (\n isinstance(column.dtype, pd.api.extensions.ExtensionDtype)\n and pd.api.types.is_integer_dtype(column.dtype)\n ):\n raise\n # Nullable integers reject fractional/text replacements instead of widening like NumPy columns.\n widened = column.astype(\"Float64\" if pd.api.types.is_float(replacement_val) else object)\n # A float cannot represent every Int64 value. Preserve unrelated large integers exactly.\n if not widened.astype(object).equals(column.astype(object)):\n widened = column.astype(object)\n result = widened.mask(column.eq(replace_val).fillna(value=False), replacement_val)\n df[self.column_name] = result\n return DataFrame(df)\n\n def drop_duplicates(self, df: DataFrame) -> DataFrame:\n return DataFrame(df.drop_duplicates(subset=self.column_name))\n\n def concatenate_dataframes(self) -> DataFrame:\n \"\"\"Concatenate multiple DataFrames vertically (stack rows).\"\"\"\n if not isinstance(self.df, list) or len(self.df) == 0:\n return self.df.copy() if self.df is not None else DataFrame()\n\n if len(self.df) == 1:\n return self.df[0].copy()\n\n concatenated = pd.concat(self.df, ignore_index=True)\n return DataFrame(concatenated)\n\n def merge_dataframes(self) -> DataFrame:\n \"\"\"Merge two DataFrames based on a common column (join operation).\"\"\"\n left_df = getattr(self, \"left_dataframe\", None)\n right_df = getattr(self, \"right_dataframe\", None)\n\n if left_df is None:\n return DataFrame()\n if right_df is None:\n return left_df.copy()\n\n df_left = left_df.copy()\n df_right = right_df.copy()\n\n merge_on = getattr(self, \"merge_on_column\", None)\n merge_how = getattr(self, \"merge_how\", \"inner\")\n\n # Track only columns created by this merge, without colliding with input names.\n right_columns = {}\n used_columns = set(df_left.columns) | set(df_right.columns)\n for col in df_left.columns.intersection(df_right.columns):\n if merge_on and col == merge_on:\n continue\n right_col = f\"{col}_right\"\n while right_col in used_columns:\n right_col += \"_right\"\n right_columns[col] = right_col\n used_columns.add(right_col)\n df_right = df_right.rename(columns=right_columns)\n\n if merge_on:\n if merge_on not in df_left.columns:\n msg = f\"Column '{merge_on}' not found in left DataFrame. Available: {list(df_left.columns)}\"\n raise ValueError(msg)\n if merge_on not in df_right.columns:\n msg = f\"Column '{merge_on}' not found in right DataFrame. Available: {list(df_right.columns)}\"\n raise ValueError(msg)\n merged = df_left.merge(df_right, on=merge_on, how=merge_how)\n else:\n merged = df_left.merge(df_right, left_index=True, right_index=True, how=merge_how)\n\n cols_to_drop = []\n for col, right_col in right_columns.items():\n merged[col] = merged[col].combine_first(merged[right_col])\n cols_to_drop.append(right_col)\n\n if cols_to_drop:\n merged = merged.drop(columns=cols_to_drop)\n\n return DataFrame(merged)\n\n # ==================================================================\n # Text operations\n # ==================================================================\n def _run_text_operation(self) -> Any:\n \"\"\"Process text based on the selected operation (Message/Text outputs).\"\"\"\n text = getattr(self, \"text_input\", \"\")\n operation = self._operation_name()\n\n # Allow empty text for Text Join (second input may have content).\n if not text and operation != \"Text Join\":\n return None\n\n text_handlers = {\n \"Case Conversion\": self._case_conversion,\n \"Text Replace\": self._text_replace,\n \"Text Extract\": self._text_extract,\n \"Text Head\": self._text_head,\n \"Text Tail\": self._text_tail,\n \"Text Strip\": self._text_strip,\n \"Text Join\": self._text_join,\n \"Text Clean\": self._text_clean,\n }\n handler = text_handlers.get(operation)\n if handler:\n return handler(text)\n return text\n\n def _word_count_data(self) -> Data:\n \"\"\"Word Count operation result as a Data object.\"\"\"\n result = self._word_count(getattr(self, \"text_input\", \"\") or \"\")\n return Data(data=result)\n\n def _word_count(self, text: str) -> dict[str, Any]:\n \"\"\"Count words, characters, and lines in text.\"\"\"\n result: dict[str, Any] = {}\n text_str = str(text) if text else \"\"\n is_empty = not text_str or not text_str.strip()\n\n if getattr(self, \"count_words\", True):\n if is_empty:\n result[\"word_count\"] = 0\n result[\"unique_words\"] = 0\n else:\n words = text_str.split()\n result[\"word_count\"] = len(words)\n result[\"unique_words\"] = len(set(words))\n\n if getattr(self, \"count_characters\", True):\n if is_empty:\n result[\"character_count\"] = 0\n result[\"character_count_no_spaces\"] = 0\n else:\n result[\"character_count\"] = len(text_str)\n result[\"character_count_no_spaces\"] = len(text_str.replace(\" \", \"\"))\n\n if getattr(self, \"count_lines\", True):\n if is_empty:\n result[\"line_count\"] = 0\n result[\"non_empty_lines\"] = 0\n else:\n lines = text_str.split(\"\\n\")\n result[\"line_count\"] = len(lines)\n result[\"non_empty_lines\"] = len([line for line in lines if line.strip()])\n\n return result\n\n def _text_to_dataframe(self, text: str) -> DataFrame:\n \"\"\"Convert markdown-style table text to a DataFrame.\"\"\"\n lines = [line.strip() for line in text.strip().split(\"\\n\") if line.strip()]\n if not lines:\n return DataFrame(pd.DataFrame())\n\n separator = getattr(self, \"table_separator\", \"|\")\n has_header = getattr(self, \"has_header\", True)\n\n rows = self._parse_table_rows(lines, separator, has_header=has_header)\n if not rows:\n return DataFrame(pd.DataFrame())\n\n df = self._create_dataframe(rows, has_header=has_header)\n self._convert_numeric_columns(df)\n self.log(f\"Converted text to DataFrame: {len(df)} rows, {len(df.columns)} columns\")\n return DataFrame(df)\n\n def _parse_table_rows(self, lines: list[str], separator: str, *, has_header: bool = True) -> list[list[str]]:\n rows = []\n for index, line in enumerate(lines):\n cleaned_line = line.strip(separator)\n cells = [cell.strip() for cell in cleaned_line.split(separator)]\n # Skip the markdown delimiter row under the header instead of reading it as data.\n if has_header and index == 1 and all(MARKDOWN_DELIMITER_CELL.fullmatch(cell) for cell in cells):\n continue\n rows.append(cells)\n return rows\n\n def _create_dataframe(self, rows: list[list[str]], *, has_header: bool) -> pd.DataFrame:\n if has_header and rows:\n header = rows[0]\n data_rows = rows[1:]\n header_col_count = len(header)\n for i, row in enumerate(data_rows):\n row_col_count = len(row)\n if row_col_count != header_col_count:\n msg = (\n f\"Header mismatch: {header_col_count} column(s) in header vs \"\n f\"{row_col_count} column(s) in data row {i + 1}. \"\n \"Please ensure the header has the same number of columns as your data.\"\n )\n raise ValueError(msg)\n return pd.DataFrame(data_rows, columns=header)\n\n max_cols = max(len(row) for row in rows) if rows else 0\n columns = [f\"col_{i}\" for i in range(max_cols)]\n return pd.DataFrame(rows, columns=columns)\n\n def _convert_numeric_columns(self, df: pd.DataFrame) -> None:\n for col in df.columns:\n with contextlib.suppress(ValueError, TypeError):\n df[col] = pd.to_numeric(df[col])\n\n def _case_conversion(self, text: str) -> str:\n case_type = getattr(self, \"case_type\", \"lowercase\")\n converter = CASE_CONVERTERS.get(case_type)\n return converter(text) if converter else text\n\n def _text_replace(self, text: str) -> str:\n search_pattern = getattr(self, \"search_pattern\", \"\")\n if not search_pattern:\n return text\n replacement_text = getattr(self, \"replacement_text\", \"\")\n use_regex = getattr(self, \"use_regex\", False)\n if use_regex:\n try:\n return re.sub(search_pattern, replacement_text, text)\n except re.error as e:\n self.log(f\"Invalid regex pattern: {e}\")\n return text\n return text.replace(search_pattern, replacement_text)\n\n def _text_extract(self, text: str) -> list[str]:\n extract_pattern = getattr(self, \"extract_pattern\", \"\")\n if not extract_pattern:\n return []\n max_matches = getattr(self, \"max_matches\", 10)\n try:\n matches = re.findall(extract_pattern, text)\n except re.error as e:\n msg = f\"Invalid regex pattern '{extract_pattern}': {e}\"\n raise ValueError(msg) from e\n return matches[:max_matches] if max_matches > 0 else matches\n\n def _text_head(self, text: str) -> str:\n head_characters = getattr(self, \"head_characters\", 100)\n if head_characters < 0:\n msg = f\"Characters from Start must be a non-negative integer, got {head_characters}\"\n raise ValueError(msg)\n if head_characters == 0:\n return \"\"\n return text[:head_characters]\n\n def _text_tail(self, text: str) -> str:\n tail_characters = getattr(self, \"tail_characters\", 100)\n if tail_characters < 0:\n msg = f\"Characters from End must be a non-negative integer, got {tail_characters}\"\n raise ValueError(msg)\n if tail_characters == 0:\n return \"\"\n return text[-tail_characters:]\n\n def _text_strip(self, text: str) -> str:\n strip_mode = getattr(self, \"strip_mode\", \"both\")\n strip_characters = getattr(self, \"strip_characters\", \"\")\n text_str = str(text) if text else \"\"\n chars_to_strip = strip_characters if strip_characters else None\n if strip_mode == \"left\":\n return text_str.lstrip(chars_to_strip)\n if strip_mode == \"right\":\n return text_str.rstrip(chars_to_strip)\n return text_str.strip(chars_to_strip)\n\n def _text_join(self, text: str) -> str:\n text_input_2 = getattr(self, \"text_input_2\", \"\")\n text1 = str(text) if text else \"\"\n text2 = str(text_input_2) if text_input_2 else \"\"\n if text1 and text2:\n return f\"{text1}\\n{text2}\"\n return text1 or text2\n\n def _text_clean(self, text: str) -> str:\n result = text\n if getattr(self, \"remove_extra_spaces\", True):\n # Collapse runs of horizontal whitespace but preserve newlines so\n # that remove_empty_lines stays effective when both are enabled.\n result = re.sub(r\"[^\\S\\n]+\", \" \", result)\n if getattr(self, \"remove_special_chars\", False):\n result = re.sub(r\"[^\\w\\s]\", \"\", result)\n if getattr(self, \"remove_empty_lines\", False):\n lines = [line for line in result.split(\"\\n\") if line.strip()]\n result = \"\\n\".join(lines)\n return result\n\n def _format_result_as_text(self, result: Any) -> str:\n if result is None:\n return \"\"\n if isinstance(result, list):\n return \"\\n\".join(str(item) for item in result)\n return str(result)\n"
},
"column_name": {
"_input_type": "StrInput",
@@ -2342,10 +2340,6 @@
},
"dragging": false,
"id": "Operations-IC6CD",
- "measured": {
- "height": 80,
- "width": 192
- },
"position": {
"x": 922.8558031751697,
"y": 1830.0439761689086
@@ -2418,10 +2412,10 @@
],
"frozen": false,
"icon": "wand-sparkles",
- "last_updated": "2026-10-27T20:14:15.099Z",
+ "last_updated": "2026-10-29T18:16:47.706Z",
"legacy": false,
"metadata": {
- "code_hash": "f15ba610cfd0",
+ "code_hash": "6164f967d510",
"dependencies": {
"dependencies": [
{
@@ -2434,7 +2428,7 @@
},
{
"name": "lfx",
- "version": "1.12.3"
+ "version": "1.12.8"
},
{
"name": "jq",
@@ -2515,7 +2509,7 @@
"value": "5488df7c-b93f-4f87-a446-b67028bc0813"
},
"_frontend_node_folder_id": {
- "value": "f3f8bf74-7a73-4ab3-9769-0d8a4ebbaec9"
+ "value": "afa57272-6d34-4d1c-bf31-27ffad110b3a"
},
"_type": "Component",
"append_update_data": {
@@ -2610,7 +2604,7 @@
"show": true,
"title_case": false,
"type": "code",
- "value": "\"\"\"Unified Operations component.\n\nBrings together the previously separate JSON, Table, and Text operation\ncomponents into a single component. An \"Input Type\" selector (Text / JSON /\nTable) drives everything: it filters the \"Operation\" picker to the operations\nthat apply to that type, reveals the matching input (Text / JSON / Table) and\nits operation-specific fields, and advertises the appropriate output type.\n\nThe three original components (JSON Operations, Table Operations, Text\nOperations) remain available as legacy components for backward compatibility\nwith existing flows.\n\"\"\"\n\nimport ast\nimport contextlib\nimport json\nimport re\nfrom typing import TYPE_CHECKING, Any\n\nimport pandas as pd\nfrom json_repair import repair_json\n\nfrom lfx.custom import Component\nfrom lfx.field_typing import RangeSpec\nfrom lfx.inputs import DictInput, SortableListInput, TabInput\nfrom lfx.io import (\n BoolInput,\n DataFrameInput,\n DataInput,\n DropdownInput,\n IntInput,\n MessageTextInput,\n MultilineInput,\n Output,\n StrInput,\n)\nfrom lfx.log.logger import logger\nfrom lfx.schema import Data\nfrom lfx.schema.dataframe import DataFrame\nfrom lfx.schema.dotdict import dotdict\nfrom lfx.schema.message import Message\nfrom lfx.utils.jq_security import validate_jq_program\n\nif TYPE_CHECKING:\n from collections.abc import Callable\n\n# The \"Input Type\" selector tabs. Each value maps a Langflow data type to the\n# operations, input, and output that belong to it.\nINPUT_TYPES = [\"Text\", \"JSON\", \"Table\"]\n\n# Operations grouped by input type, in display order, each with the icon shown\n# in the Operation picker. This is the single source of truth for the picker;\n# update_build_config swaps the picker's options to the selected type's list.\nOPERATIONS_BY_TYPE: dict[str, list[dict[str, str]]] = {\n \"Text\": [\n {\"name\": \"Word Count\", \"icon\": \"hash\"},\n {\"name\": \"Case Conversion\", \"icon\": \"type\"},\n {\"name\": \"Text Replace\", \"icon\": \"replace\"},\n {\"name\": \"Text Extract\", \"icon\": \"search\"},\n {\"name\": \"Text Head\", \"icon\": \"chevron-left\"},\n {\"name\": \"Text Tail\", \"icon\": \"chevron-right\"},\n {\"name\": \"Text Strip\", \"icon\": \"minus\"},\n {\"name\": \"Text Join\", \"icon\": \"link\"},\n {\"name\": \"Text Clean\", \"icon\": \"sparkles\"},\n {\"name\": \"Text to DataFrame\", \"icon\": \"table\"},\n ],\n \"JSON\": [\n {\"name\": \"Select Keys\", \"icon\": \"lasso-select\"},\n {\"name\": \"Literal Eval\", \"icon\": \"braces\"},\n {\"name\": \"Combine\", \"icon\": \"merge\"},\n {\"name\": \"Append or Update\", \"icon\": \"circle-plus\"},\n {\"name\": \"Remove Keys\", \"icon\": \"eraser\"},\n {\"name\": \"Rename Keys\", \"icon\": \"pencil-line\"},\n {\"name\": \"Path Selection\", \"icon\": \"mouse-pointer\"},\n {\"name\": \"JQ Expression\", \"icon\": \"terminal\"},\n ],\n \"Table\": [\n {\"name\": \"Add Column\", \"icon\": \"plus\"},\n {\"name\": \"Concatenate\", \"icon\": \"combine\"},\n {\"name\": \"Drop Column\", \"icon\": \"minus\"},\n {\"name\": \"Filter\", \"icon\": \"filter\"},\n {\"name\": \"Head\", \"icon\": \"arrow-up\"},\n {\"name\": \"Merge\", \"icon\": \"merge\"},\n {\"name\": \"Rename Column\", \"icon\": \"pencil\"},\n {\"name\": \"Replace Value\", \"icon\": \"replace\"},\n {\"name\": \"Select Columns\", \"icon\": \"columns\"},\n {\"name\": \"Sort\", \"icon\": \"arrow-up-down\"},\n {\"name\": \"Tail\", \"icon\": \"arrow-down\"},\n {\"name\": \"Drop Duplicates\", \"icon\": \"copy-x\"},\n ],\n}\n\n# Operation-name sets derived from the picker, used for dispatch and output\n# routing. Keeping them derived from OPERATIONS_BY_TYPE avoids any drift.\nJSON_OPERATIONS = {op[\"name\"] for op in OPERATIONS_BY_TYPE[\"JSON\"]}\nTABLE_OPERATIONS = {op[\"name\"] for op in OPERATIONS_BY_TYPE[\"Table\"]}\nTEXT_OPERATIONS = {op[\"name\"] for op in OPERATIONS_BY_TYPE[\"Text\"]}\n\n# Each input type maps to its main input field and its default output. \"Text\"\n# normally outputs a Message; \"JSON\" a Data; \"Table\" a DataFrame. A few text\n# operations override this (Word Count -> Data, Text to DataFrame -> DataFrame).\nINPUT_TYPE_TO_MAIN_INPUT = {\"Text\": \"text_input\", \"JSON\": \"data\", \"Table\": \"df\"}\n\n# Case conversions for the Text \"Case Conversion\" operation.\nCASE_CONVERTERS: dict[str, Any] = {\n \"uppercase\": str.upper,\n \"lowercase\": str.lower,\n \"title\": str.title,\n \"capitalize\": str.capitalize,\n \"swapcase\": str.swapcase,\n}\n\n\nclass OperationsComponent(Component):\n display_name = \"Data Operations\"\n description = \"Perform operations on Text, JSON, and Tables from a single component.\"\n documentation: str = \"https://docs.langflow.org/components-processing#operations\"\n icon = \"wand-sparkles\"\n name = \"Operations\"\n metadata = {\n \"keywords\": [\n \"operations\",\n \"data operations\",\n \"json\",\n \"json operations\",\n \"table\",\n \"table operations\",\n \"dataframe\",\n \"dataframe operations\",\n \"text\",\n \"text operations\",\n \"select keys\",\n \"literal eval\",\n \"combine\",\n \"append or update\",\n \"remove keys\",\n \"rename keys\",\n \"path selection\",\n \"jq expression\",\n \"parse json\",\n \"add column\",\n \"concatenate\",\n \"drop column\",\n \"filter\",\n \"head\",\n \"merge\",\n \"rename column\",\n \"replace value\",\n \"select columns\",\n \"sort\",\n \"tail\",\n \"drop duplicates\",\n \"word count\",\n \"case conversion\",\n \"text replace\",\n \"text extract\",\n \"text join\",\n \"text clean\",\n \"text to dataframe\",\n \"data manipulation\",\n \"data transformation\",\n ],\n }\n\n # Operation -> operation-specific input fields to reveal when selected.\n OPERATION_FIELDS: dict[str, list[str]] = {\n # JSON\n \"Select Keys\": [\"select_keys_input\"],\n \"Literal Eval\": [],\n \"Combine\": [],\n \"Append or Update\": [\"append_update_data\"],\n \"Remove Keys\": [\"remove_keys_input\"],\n \"Rename Keys\": [\"rename_keys_input\"],\n \"Path Selection\": [\"mapped_json_display\", \"selected_key\"],\n \"JQ Expression\": [\"query\"],\n # Table\n \"Add Column\": [\"new_column_name\", \"new_column_value\"],\n \"Concatenate\": [],\n \"Drop Column\": [\"column_name\"],\n \"Filter\": [\"column_name\", \"filter_value\", \"filter_operator\"],\n \"Head\": [\"num_rows\"],\n \"Merge\": [\"left_dataframe\", \"right_dataframe\", \"merge_on_column\", \"merge_how\"],\n \"Rename Column\": [\"column_name\", \"new_column_name\"],\n \"Replace Value\": [\"column_name\", \"replace_value\", \"replacement_value\"],\n \"Select Columns\": [\"columns_to_select\"],\n \"Sort\": [\"column_name\", \"ascending\"],\n \"Tail\": [\"num_rows\"],\n \"Drop Duplicates\": [\"column_name\"],\n # Text\n \"Word Count\": [\"count_words\", \"count_characters\", \"count_lines\"],\n \"Case Conversion\": [\"case_type\"],\n \"Text Replace\": [\"search_pattern\", \"replacement_text\", \"use_regex\"],\n \"Text Extract\": [\"extract_pattern\", \"max_matches\"],\n \"Text Head\": [\"head_characters\"],\n \"Text Tail\": [\"tail_characters\"],\n \"Text Strip\": [\"strip_mode\", \"strip_characters\"],\n \"Text Join\": [\"text_input_2\"],\n \"Text Clean\": [\"remove_extra_spaces\", \"remove_special_chars\", \"remove_empty_lines\"],\n \"Text to DataFrame\": [\"table_separator\", \"has_header\"],\n }\n\n # The three main inputs (one per data type). They are never treated as\n # operation-specific fields; the input-type selector toggles them.\n MAIN_INPUTS = (\"text_input\", \"data\", \"df\")\n\n # Every operation-specific field (union of all the lists above), used to\n # hide and reset fields whenever the input type or operation changes.\n ALL_OPERATION_FIELDS: list[str] = [\n # JSON\n \"select_keys_input\",\n \"append_update_data\",\n \"remove_keys_input\",\n \"rename_keys_input\",\n \"mapped_json_display\",\n \"selected_key\",\n \"query\",\n # Table\n \"column_name\",\n \"filter_value\",\n \"filter_operator\",\n \"ascending\",\n \"new_column_name\",\n \"new_column_value\",\n \"columns_to_select\",\n \"num_rows\",\n \"replace_value\",\n \"replacement_value\",\n \"left_dataframe\",\n \"right_dataframe\",\n \"merge_on_column\",\n \"merge_how\",\n # Text\n \"table_separator\",\n \"has_header\",\n \"count_words\",\n \"count_characters\",\n \"count_lines\",\n \"case_type\",\n \"use_regex\",\n \"search_pattern\",\n \"replacement_text\",\n \"extract_pattern\",\n \"max_matches\",\n \"head_characters\",\n \"tail_characters\",\n \"strip_mode\",\n \"strip_characters\",\n \"text_input_2\",\n \"remove_extra_spaces\",\n \"remove_special_chars\",\n \"remove_empty_lines\",\n ]\n\n # Defaults applied to the JSON operation fields when the operation changes,\n # mirroring the JSON Operations component's reset behavior.\n OPERATION_FIELD_DEFAULTS: dict[str, Any] = {\n \"select_keys_input\": [],\n \"append_update_data\": {\"key\": \"value\"},\n \"remove_keys_input\": [],\n \"rename_keys_input\": {\"old_key\": \"new_key\"},\n \"mapped_json_display\": \"\",\n \"selected_key\": None,\n \"query\": \"\",\n }\n\n inputs = [\n # --- Input type selector: drives operations, input, and output ---\n TabInput(\n name=\"input_type\",\n display_name=\"Input Type\",\n options=INPUT_TYPES,\n value=\"Text\",\n info=\"Select the type of input to operate on.\",\n real_time_refresh=True,\n ),\n # --- Main inputs: one per data type, shown contextually ---\n MultilineInput(\n name=\"text_input\",\n display_name=\"Text\",\n info=\"The input text to process.\",\n show=True,\n ),\n DataInput(\n name=\"data\",\n display_name=\"JSON\",\n info=\"The JSON / Data object to operate on.\",\n is_list=True,\n show=False,\n ),\n DataFrameInput(\n name=\"df\",\n display_name=\"Table\",\n info=\"The input Table to operate on. Connect multiple Tables for merge or concatenate operations.\",\n is_list=True,\n show=False,\n ),\n # --- Operation picker (options are filtered by Input Type) ---\n SortableListInput(\n name=\"operation\",\n display_name=\"Operation\",\n placeholder=\"Select Operation\",\n info=\"Select the operation to perform. The matching fields and output appear once you choose one.\",\n options=OPERATIONS_BY_TYPE[\"Text\"],\n real_time_refresh=True,\n limit=1,\n ),\n # --- JSON operation fields ---\n MessageTextInput(\n name=\"select_keys_input\",\n display_name=\"Select Keys\",\n info=\"List of keys to select from the data. Only top-level keys can be selected.\",\n show=False,\n is_list=True,\n value=[],\n ),\n DictInput(\n name=\"append_update_data\",\n display_name=\"Append or Update\",\n info=\"Data to append or update the existing data with. Only top-level keys are checked.\",\n show=False,\n value={\"key\": \"value\"},\n is_list=True,\n ),\n MessageTextInput(\n name=\"remove_keys_input\",\n display_name=\"Remove Keys\",\n info=\"List of keys to remove from the data.\",\n show=False,\n is_list=True,\n value=[],\n ),\n DictInput(\n name=\"rename_keys_input\",\n display_name=\"Rename Keys\",\n info=\"List of keys to rename in the data.\",\n show=False,\n is_list=True,\n value={\"old_key\": \"new_key\"},\n ),\n MultilineInput(\n name=\"mapped_json_display\",\n display_name=\"JSON to Map\",\n info=\"Paste or preview your JSON here to explore its structure and select a path for extraction.\",\n required=False,\n refresh_button=True,\n real_time_refresh=True,\n placeholder=\"Add a JSON example.\",\n show=False,\n ),\n DropdownInput(\n name=\"selected_key\",\n display_name=\"Select Path\",\n options=[],\n required=False,\n dynamic=True,\n show=False,\n value=None,\n ),\n MessageTextInput(\n name=\"query\",\n display_name=\"JQ Expression\",\n info=\"JSON Query to filter the data. Used by Path Selection and JQ Expression operations.\",\n placeholder=\"e.g., .properties.id\",\n show=False,\n ),\n # --- Table operation fields ---\n StrInput(\n name=\"column_name\",\n display_name=\"Column Name\",\n info=\"The column name to use for the operation.\",\n dynamic=True,\n show=False,\n ),\n MessageTextInput(\n name=\"filter_value\",\n display_name=\"Filter Value\",\n info=\"The value to filter rows by.\",\n dynamic=True,\n show=False,\n ),\n DropdownInput(\n name=\"filter_operator\",\n display_name=\"Filter Operator\",\n options=[\n \"equals\",\n \"not equals\",\n \"contains\",\n \"not contains\",\n \"starts with\",\n \"ends with\",\n \"greater than\",\n \"less than\",\n ],\n value=\"equals\",\n info=\"The operator to apply for filtering rows.\",\n advanced=False,\n dynamic=True,\n show=False,\n ),\n BoolInput(\n name=\"ascending\",\n display_name=\"Sort Ascending\",\n info=\"Whether to sort in ascending order.\",\n dynamic=True,\n show=False,\n value=True,\n ),\n StrInput(\n name=\"new_column_name\",\n display_name=\"New Column Name\",\n info=\"The new column name when renaming or adding a column.\",\n dynamic=True,\n show=False,\n ),\n MessageTextInput(\n name=\"new_column_value\",\n display_name=\"New Column Value\",\n info=\"The value to populate the new column with.\",\n dynamic=True,\n show=False,\n ),\n StrInput(\n name=\"columns_to_select\",\n display_name=\"Columns to Select\",\n dynamic=True,\n is_list=True,\n show=False,\n ),\n IntInput(\n name=\"num_rows\",\n display_name=\"Number of Rows\",\n info=\"Number of rows to return (for head/tail).\",\n dynamic=True,\n show=False,\n value=5,\n ),\n MessageTextInput(\n name=\"replace_value\",\n display_name=\"Value to Replace\",\n info=\"The value to replace in the column.\",\n dynamic=True,\n show=False,\n ),\n MessageTextInput(\n name=\"replacement_value\",\n display_name=\"Replacement Value\",\n info=\"The value to replace with.\",\n dynamic=True,\n show=False,\n ),\n DataFrameInput(\n name=\"left_dataframe\",\n display_name=\"Left Table\",\n info=\"The left (primary) Table for merge operations. \"\n \"In a left merge, all rows from this table are preserved.\",\n dynamic=True,\n show=False,\n ),\n DataFrameInput(\n name=\"right_dataframe\",\n display_name=\"Right Table\",\n info=\"The right (secondary) Table for merge operations. \"\n \"In a right merge, all rows from this table are preserved.\",\n dynamic=True,\n show=False,\n ),\n StrInput(\n name=\"merge_on_column\",\n display_name=\"Merge On Column\",\n info=\"The column name to merge Tables on. Must exist in both Tables.\",\n dynamic=True,\n show=False,\n ),\n DropdownInput(\n name=\"merge_how\",\n display_name=\"Merge Type\",\n options=[\"inner\", \"outer\", \"left\", \"right\"],\n value=\"inner\",\n info=\"Type of merge: inner (intersection), outer (union), left, or right.\",\n dynamic=True,\n show=False,\n ),\n # --- Text operation fields ---\n StrInput(\n name=\"table_separator\",\n display_name=\"Table Separator\",\n info=\"Separator used in the table (default: '|').\",\n value=\"|\",\n dynamic=True,\n show=False,\n ),\n BoolInput(\n name=\"has_header\",\n display_name=\"Has Header\",\n info=\"Whether the table has a header row.\",\n value=True,\n dynamic=True,\n advanced=True,\n show=False,\n ),\n BoolInput(\n name=\"count_words\",\n display_name=\"Count Words\",\n info=\"Include word count in analysis.\",\n value=True,\n dynamic=True,\n advanced=True,\n show=False,\n ),\n BoolInput(\n name=\"count_characters\",\n display_name=\"Count Characters\",\n info=\"Include character count in analysis.\",\n value=True,\n dynamic=True,\n advanced=True,\n show=False,\n ),\n BoolInput(\n name=\"count_lines\",\n display_name=\"Count Lines\",\n info=\"Include line count in analysis.\",\n value=True,\n dynamic=True,\n advanced=True,\n show=False,\n ),\n DropdownInput(\n name=\"case_type\",\n display_name=\"Case Type\",\n options=[\"uppercase\", \"lowercase\", \"title\", \"capitalize\", \"swapcase\"],\n value=\"lowercase\",\n info=\"Type of case conversion to apply.\",\n dynamic=True,\n show=False,\n ),\n BoolInput(\n name=\"use_regex\",\n display_name=\"Use Regex\",\n info=\"Whether to treat search pattern as regex.\",\n value=False,\n dynamic=True,\n show=False,\n ),\n StrInput(\n name=\"search_pattern\",\n display_name=\"Search Pattern\",\n info=\"Text pattern to search for (supports regex).\",\n dynamic=True,\n show=False,\n ),\n StrInput(\n name=\"replacement_text\",\n display_name=\"Replacement Text\",\n info=\"Text to replace the search pattern with.\",\n dynamic=True,\n show=False,\n ),\n StrInput(\n name=\"extract_pattern\",\n display_name=\"Extract Pattern\",\n info=\"Regex pattern to extract from text.\",\n dynamic=True,\n show=False,\n ),\n IntInput(\n name=\"max_matches\",\n display_name=\"Max Matches\",\n info=\"Maximum number of matches to extract.\",\n value=10,\n dynamic=True,\n show=False,\n ),\n IntInput(\n name=\"head_characters\",\n display_name=\"Characters from Start\",\n info=\"Number of characters to extract from the beginning of text. Must be non-negative.\",\n value=100,\n dynamic=True,\n show=False,\n range_spec=RangeSpec(min=0, max=1000000, step=1, step_type=\"int\"),\n ),\n IntInput(\n name=\"tail_characters\",\n display_name=\"Characters from End\",\n info=\"Number of characters to extract from the end of text. Must be non-negative.\",\n value=100,\n dynamic=True,\n show=False,\n range_spec=RangeSpec(min=0, max=1000000, step=1, step_type=\"int\"),\n ),\n DropdownInput(\n name=\"strip_mode\",\n display_name=\"Strip Mode\",\n options=[\"both\", \"left\", \"right\"],\n value=\"both\",\n info=\"Which sides to strip whitespace from.\",\n dynamic=True,\n show=False,\n ),\n StrInput(\n name=\"strip_characters\",\n display_name=\"Characters to Strip\",\n info=\"Specific characters to remove (leave empty for whitespace).\",\n value=\"\",\n dynamic=True,\n show=False,\n ),\n MultilineInput(\n name=\"text_input_2\",\n display_name=\"Second Text Input\",\n info=\"Second text to join with the first text.\",\n dynamic=True,\n show=False,\n ),\n BoolInput(\n name=\"remove_extra_spaces\",\n display_name=\"Remove Extra Spaces\",\n info=\"Remove multiple consecutive spaces.\",\n value=True,\n dynamic=True,\n show=False,\n ),\n BoolInput(\n name=\"remove_special_chars\",\n display_name=\"Remove Special Characters\",\n info=\"Remove special characters except alphanumeric and spaces.\",\n value=False,\n dynamic=True,\n show=False,\n ),\n BoolInput(\n name=\"remove_empty_lines\",\n display_name=\"Remove Empty Lines\",\n info=\"Remove empty lines from text.\",\n value=False,\n dynamic=True,\n show=False,\n ),\n ]\n\n # Default output matches the default Input Type (\"Text\" -> Message).\n # update_outputs / update_frontend_node narrow it to the selected type and\n # operation.\n outputs = [Output(display_name=\"Message\", name=\"message_output\", method=\"as_message\")]\n\n # ------------------------------------------------------------------\n # Operation routing helpers\n # ------------------------------------------------------------------\n @staticmethod\n def _extract_operation_name(field_value: Any) -> str:\n \"\"\"Extract the operation name from a SortableListInput value.\"\"\"\n if isinstance(field_value, list) and len(field_value) > 0 and isinstance(field_value[0], dict):\n return field_value[0].get(\"name\", \"\")\n if isinstance(field_value, str):\n return field_value\n return \"\"\n\n def _operation_name(self) -> str:\n \"\"\"Get the currently selected operation name.\"\"\"\n return self._extract_operation_name(getattr(self, \"operation\", []))\n\n @staticmethod\n def _default_output_for_type(input_type: str) -> Output:\n \"\"\"Return the output advertised for an input type when no operation is selected yet.\"\"\"\n if input_type == \"JSON\":\n return Output(display_name=\"JSON\", name=\"data_output\", method=\"as_data\")\n if input_type == \"Table\":\n return Output(display_name=\"Table\", name=\"dataframe_output\", method=\"as_dataframe\")\n return Output(display_name=\"Message\", name=\"message_output\", method=\"as_message\")\n\n # ------------------------------------------------------------------\n # Dynamic UI\n # ------------------------------------------------------------------\n def _reset_operation_fields(self, build_config: dotdict) -> None:\n \"\"\"Hide every operation-specific field and restore its default value.\"\"\"\n for field in self.ALL_OPERATION_FIELDS:\n if field in build_config:\n build_config[field][\"show\"] = False\n if field in self.OPERATION_FIELD_DEFAULTS:\n build_config[field][\"value\"] = self.OPERATION_FIELD_DEFAULTS[field]\n\n def _show_main_input(self, build_config: dotdict, input_type: str, operation: str) -> None:\n \"\"\"Show only the main input that matches the input type; hide the others.\"\"\"\n for inp in self.MAIN_INPUTS:\n if inp in build_config:\n build_config[inp][\"show\"] = False\n build_config[inp][\"required\"] = False\n\n main_input = INPUT_TYPE_TO_MAIN_INPUT.get(input_type)\n if main_input and main_input in build_config:\n build_config[main_input][\"show\"] = True\n build_config[main_input][\"required\"] = True\n # The JSON \"Combine\" operation consumes a list of Data objects.\n if main_input == \"data\":\n build_config[\"data\"][\"is_list\"] = operation == \"Combine\"\n\n def update_build_config(self, build_config: dotdict, field_value: Any, field_name: str | None = None) -> dotdict:\n # Path Selection: refresh the available JSON paths from the pasted JSON.\n if field_name == \"mapped_json_display\":\n try:\n parsed_json = json.loads(field_value)\n keys = self.extract_all_paths(parsed_json)\n build_config[\"selected_key\"][\"options\"] = keys\n build_config[\"selected_key\"][\"show\"] = True\n except (json.JSONDecodeError, TypeError, ValueError) as e:\n logger.error(f\"Error parsing mapped JSON: {e}\")\n build_config[\"selected_key\"][\"show\"] = False\n return build_config\n\n # Input type changed: swap the operation list, clear the selection, and\n # show only the matching input. No operation-specific fields are shown\n # until an operation is picked.\n if field_name == \"input_type\":\n input_type = field_value if field_value in OPERATIONS_BY_TYPE else \"Text\"\n build_config[\"operation\"][\"options\"] = OPERATIONS_BY_TYPE[input_type]\n build_config[\"operation\"][\"value\"] = []\n self._reset_operation_fields(build_config)\n self._show_main_input(build_config, input_type, operation=\"\")\n return build_config\n\n # Operation changed: reset fields, show the input for the current type,\n # then reveal the operation-specific fields.\n if field_name == \"operation\":\n operation = self._extract_operation_name(field_value)\n self._reset_operation_fields(build_config)\n\n input_type = build_config.get(\"input_type\", {}).get(\"value\", \"Text\")\n self._show_main_input(build_config, input_type, operation)\n\n for field in self.OPERATION_FIELDS.get(operation, []):\n if field in build_config:\n build_config[field][\"show\"] = True\n\n return build_config\n\n return build_config\n\n def update_outputs(self, frontend_node: dict, field_name: str, field_value: Any) -> dict:\n \"\"\"Create the output(s) appropriate to the selected input type and operation.\"\"\"\n if field_name == \"input_type\":\n # Switching type clears the operation; advertise the type's default.\n input_type = field_value if field_value in OPERATIONS_BY_TYPE else \"Text\"\n frontend_node[\"outputs\"] = [self._default_output_for_type(input_type)]\n return frontend_node\n\n template = frontend_node.get(\"template\", {})\n input_type = template.get(\"input_type\", {}).get(\"value\", \"Text\")\n\n if field_name == \"operation\":\n operation = self._extract_operation_name(field_value)\n else:\n # Any other refresh (e.g. Path Selection's \"JSON to Map\" field)\n # reaches here on a freshly rebuilt node whose outputs were reset\n # to the class default (Message). Re-derive the output from the\n # saved operation so the refresh doesn't swap the real output type.\n operation = self._extract_operation_name(template.get(\"operation\", {}).get(\"value\", []))\n\n if not operation:\n # No operation selected: fall back to the input type's default output.\n frontend_node[\"outputs\"] = [self._default_output_for_type(input_type)]\n return frontend_node\n\n frontend_node[\"outputs\"] = []\n if operation in JSON_OPERATIONS or operation == \"Word Count\":\n frontend_node[\"outputs\"].append(Output(display_name=\"JSON\", name=\"data_output\", method=\"as_data\"))\n elif operation in TABLE_OPERATIONS or operation == \"Text to DataFrame\":\n frontend_node[\"outputs\"].append(\n Output(display_name=\"Table\", name=\"dataframe_output\", method=\"as_dataframe\")\n )\n elif operation == \"Text Join\":\n frontend_node[\"outputs\"].append(Output(display_name=\"Text\", name=\"text_output\", method=\"as_text\"))\n frontend_node[\"outputs\"].append(Output(display_name=\"Message\", name=\"message_output\", method=\"as_message\"))\n else:\n frontend_node[\"outputs\"].append(Output(display_name=\"Message\", name=\"message_output\", method=\"as_message\"))\n\n return frontend_node\n\n async def update_frontend_node(self, new_frontend_node: dict, current_frontend_node: dict) -> dict:\n \"\"\"Keep the operation options and outputs in sync with the saved input type on load.\"\"\"\n await super().update_frontend_node(new_frontend_node, current_frontend_node)\n\n template = new_frontend_node.get(\"template\", {})\n input_type = template.get(\"input_type\", {}).get(\"value\", \"Text\")\n if input_type not in OPERATIONS_BY_TYPE:\n input_type = \"Text\"\n\n # Filter the operation picker to the saved input type.\n if \"operation\" in template:\n template[\"operation\"][\"options\"] = OPERATIONS_BY_TYPE[input_type]\n\n # Re-derive the outputs from the saved input type + operation.\n operation_value = template.get(\"operation\", {}).get(\"value\", [])\n if self._extract_operation_name(operation_value):\n self.update_outputs(new_frontend_node, \"operation\", operation_value)\n else:\n self.update_outputs(new_frontend_node, \"input_type\", input_type)\n\n return new_frontend_node\n\n # ==================================================================\n # Output methods (referenced by update_outputs)\n # ==================================================================\n def as_data(self) -> Data:\n \"\"\"JSON-typed output: JSON operations and Word Count.\"\"\"\n operation = self._operation_name()\n if operation in JSON_OPERATIONS:\n handler = self._json_handlers().get(operation)\n if handler:\n try:\n return handler()\n except Exception as e:\n logger.error(f\"Error executing {operation}: {e!s}\")\n raise\n if operation == \"Word Count\":\n return self._word_count_data()\n return Data(data={})\n\n def as_dataframe(self) -> DataFrame:\n \"\"\"Table-typed output: Table operations and Text to DataFrame.\"\"\"\n operation = self._operation_name()\n if operation in TABLE_OPERATIONS:\n return self._run_table_operation(operation)\n if operation == \"Text to DataFrame\":\n return self._text_to_dataframe(getattr(self, \"text_input\", \"\") or \"\")\n return DataFrame(pd.DataFrame())\n\n def as_message(self) -> Message:\n \"\"\"Message-typed output: generic text operations (and Text Join).\"\"\"\n return Message(text=self._format_result_as_text(self._run_text_operation()))\n\n def as_text(self) -> Message:\n \"\"\"Text output for the Text Join operation.\"\"\"\n return self.as_message()\n\n # ==================================================================\n # JSON operations\n # ==================================================================\n @staticmethod\n def extract_all_paths(obj, path=\"\"):\n paths = []\n if isinstance(obj, dict):\n for k, v in obj.items():\n new_path = f\"{path}.{k}\" if path else f\".{k}\"\n paths.append(new_path)\n paths.extend(OperationsComponent.extract_all_paths(v, new_path))\n elif isinstance(obj, list) and obj:\n new_path = f\"{path}[0]\"\n paths.append(new_path)\n paths.extend(OperationsComponent.extract_all_paths(obj[0], new_path))\n return paths\n\n @staticmethod\n def remove_keys_recursive(obj, keys_to_remove):\n if isinstance(obj, dict):\n return {\n k: OperationsComponent.remove_keys_recursive(v, keys_to_remove)\n for k, v in obj.items()\n if k not in keys_to_remove\n }\n if isinstance(obj, list):\n return [OperationsComponent.remove_keys_recursive(item, keys_to_remove) for item in obj]\n return obj\n\n @staticmethod\n def rename_keys_recursive(obj, rename_map):\n if isinstance(obj, dict):\n return {\n rename_map.get(k, k): OperationsComponent.rename_keys_recursive(v, rename_map) for k, v in obj.items()\n }\n if isinstance(obj, list):\n return [OperationsComponent.rename_keys_recursive(item, rename_map) for item in obj]\n return obj\n\n def _json_handlers(self) -> \"dict[str, Callable[[], Data]]\":\n return {\n \"Select Keys\": self.select_keys,\n \"Literal Eval\": self.evaluate_data,\n \"Combine\": self.combine_data,\n \"Append or Update\": self.append_update,\n \"Remove Keys\": self.remove_keys,\n \"Rename Keys\": self.rename_keys,\n \"Path Selection\": self.json_path,\n \"JQ Expression\": self.json_query,\n }\n\n def get_data_dict(self) -> dict:\n \"\"\"Extract data dictionary from Data object.\"\"\"\n data = self.data[0] if isinstance(self.data, list) and len(self.data) == 1 else self.data\n return data.model_dump()\n\n def get_normalized_data(self) -> dict:\n \"\"\"Get normalized data dictionary, handling the 'data' key if present.\"\"\"\n data_dict = self.get_data_dict()\n return data_dict.get(\"data\", data_dict)\n\n def data_is_list(self) -> bool:\n \"\"\"Check if data contains multiple items.\"\"\"\n return isinstance(self.data, list) and len(self.data) > 1\n\n def validate_single_data(self, operation: str) -> None:\n \"\"\"Validate that the operation is being performed on a single data object.\"\"\"\n if self.data_is_list():\n msg = f\"{operation} operation is not supported for multiple data objects.\"\n raise ValueError(msg)\n\n def select_keys(self) -> Data:\n \"\"\"Select specific keys from the data dictionary.\"\"\"\n self.validate_single_data(\"Select Keys\")\n data_dict = self.get_normalized_data()\n filter_criteria: list[str] = self.select_keys_input\n\n if len(filter_criteria) == 1 and filter_criteria[0] == \"data\":\n filtered = data_dict[\"data\"]\n else:\n if not all(key in data_dict for key in filter_criteria):\n msg = f\"Select key not found in data. Available keys: {list(data_dict.keys())}\"\n raise ValueError(msg)\n filtered = {key: value for key, value in data_dict.items() if key in filter_criteria}\n\n return Data(data=filtered)\n\n def remove_keys(self) -> Data:\n \"\"\"Remove specified keys from the data dictionary, recursively.\"\"\"\n self.validate_single_data(\"Remove Keys\")\n data_dict = self.get_normalized_data()\n remove_keys_input: list[str] = self.remove_keys_input\n filtered = OperationsComponent.remove_keys_recursive(data_dict, set(remove_keys_input))\n return Data(data=filtered)\n\n def rename_keys(self) -> Data:\n \"\"\"Rename keys in the data dictionary, recursively.\"\"\"\n self.validate_single_data(\"Rename Keys\")\n data_dict = self.get_normalized_data()\n rename_keys_input: dict[str, str] = self.rename_keys_input\n renamed = OperationsComponent.rename_keys_recursive(data_dict, rename_keys_input)\n return Data(data=renamed)\n\n def recursive_eval(self, data: Any) -> Any:\n \"\"\"Recursively evaluate string values that look like Python literals.\"\"\"\n if isinstance(data, dict):\n return {k: self.recursive_eval(v) for k, v in data.items()}\n if isinstance(data, list):\n return [self.recursive_eval(item) for item in data]\n if isinstance(data, str):\n try:\n if (\n data.strip().startswith((\"{\", \"[\", \"(\", \"'\", '\"'))\n or data.strip().lower() in (\"true\", \"false\", \"none\")\n or data.strip().replace(\".\", \"\").isdigit()\n ):\n return ast.literal_eval(data)\n except (ValueError, SyntaxError, TypeError, MemoryError):\n return data\n else:\n return data\n return data\n\n def evaluate_data(self) -> Data:\n \"\"\"Evaluate string values in the data dictionary.\"\"\"\n self.validate_single_data(\"Literal Eval\")\n logger.info(\"evaluating data\")\n return Data(**self.recursive_eval(self.get_data_dict()))\n\n def combine_data(self) -> Data:\n \"\"\"Combine multiple data objects into one.\"\"\"\n logger.info(\"combining data\")\n if not self.data_is_list():\n return self.data[0] if self.data else Data(data={})\n\n data_dicts = [data.model_dump().get(\"data\", data.model_dump()) for data in self.data]\n combined_data: dict[str, Any] = {}\n\n for data_dict in data_dicts:\n for key, value in data_dict.items():\n if key not in combined_data:\n combined_data[key] = value\n elif isinstance(combined_data[key], list):\n if isinstance(value, list):\n combined_data[key].extend(value)\n else:\n combined_data[key].append(value)\n else:\n combined_data[key] = (\n [combined_data[key], value] if not isinstance(value, list) else [combined_data[key], *value]\n )\n\n return Data(**combined_data)\n\n def append_update(self) -> Data:\n \"\"\"Append or update the data with new key-value pairs.\"\"\"\n self.validate_single_data(\"Append or Update\")\n data_filtered = self.get_normalized_data()\n for key, value in self.append_update_data.items():\n data_filtered[key] = value\n return Data(**data_filtered)\n\n def json_path(self) -> Data:\n \"\"\"Extract a value from the data using the selected JQ path.\"\"\"\n try:\n import jq\n except ImportError:\n msg = \"jq is required for Path Selection. Install with: pip install jq\"\n raise ImportError(msg) from None\n\n try:\n if not self.data or not self.selected_key:\n msg = \"Missing input data or selected key.\"\n raise ValueError(msg)\n input_payload = self.data[0].data if isinstance(self.data, list) else self.data.data\n validate_jq_program(self.selected_key)\n compiled = jq.compile(self.selected_key)\n result = compiled.input(input_payload).first()\n if isinstance(result, dict):\n return Data(data=result)\n return Data(data={\"result\": result})\n except (ValueError, TypeError, KeyError) as e:\n self.status = f\"Error: {e!s}\"\n self.log(self.status)\n return Data(data={\"error\": str(e)})\n\n def json_query(self) -> Data:\n \"\"\"Run a JQ expression against the data.\"\"\"\n try:\n import jq\n except ImportError:\n msg = \"jq is required for JQ Expression. Install with: pip install jq\"\n raise ImportError(msg) from None\n\n if not self.query or not self.query.strip():\n msg = \"JSON Query is required and cannot be blank.\"\n raise ValueError(msg)\n raw_data = self.get_data_dict()\n try:\n input_str = json.dumps(raw_data)\n repaired = repair_json(input_str)\n data_json = json.loads(repaired)\n jq_input = data_json[\"data\"] if isinstance(data_json, dict) and \"data\" in data_json else data_json\n validate_jq_program(self.query)\n results = jq.compile(self.query).input(jq_input).all()\n if not results:\n msg = \"No result from JSON query.\"\n raise ValueError(msg)\n result = results[0] if len(results) == 1 else results\n if result is None or result == \"None\":\n msg = \"JSON query returned null/None. Check if the path exists in your data.\"\n raise ValueError(msg)\n if isinstance(result, dict):\n return Data(data=result)\n return Data(data={\"result\": result})\n except (ValueError, TypeError, KeyError, json.JSONDecodeError) as e:\n logger.error(f\"JSON Query failed: {e}\")\n msg = f\"JSON Query error: {e}\"\n raise ValueError(msg) from e\n\n # ==================================================================\n # Table operations\n # ==================================================================\n def _get_primary_dataframe(self) -> DataFrame:\n \"\"\"Get the first DataFrame from input (handles both single and list inputs).\"\"\"\n if isinstance(self.df, list):\n return self.df[0].copy() if self.df else DataFrame()\n return self.df.copy()\n\n def _run_table_operation(self, operation: str) -> DataFrame:\n # Merge and Concatenate use their own inputs, not the primary df.\n if operation == \"Merge\":\n return self.merge_dataframes()\n if operation == \"Concatenate\":\n return self.concatenate_dataframes()\n\n df_copy = self._get_primary_dataframe()\n table_handlers = {\n \"Filter\": self.filter_rows_by_value,\n \"Sort\": self.sort_by_column,\n \"Drop Column\": self.drop_column,\n \"Rename Column\": self.rename_column,\n \"Add Column\": self.add_column,\n \"Select Columns\": self.select_columns,\n \"Head\": self.head,\n \"Tail\": self.tail,\n \"Replace Value\": self.replace_values,\n \"Drop Duplicates\": self.drop_duplicates,\n }\n handler = table_handlers.get(operation)\n if handler is None:\n msg = f\"Unsupported operation: {operation}\"\n logger.error(msg)\n raise ValueError(msg)\n return handler(df_copy)\n\n def filter_rows_by_value(self, df: DataFrame) -> DataFrame:\n column = df[self.column_name]\n filter_value = self.filter_value\n operator = getattr(self, \"filter_operator\", \"equals\")\n\n if operator == \"equals\":\n mask = column == filter_value\n elif operator == \"not equals\":\n mask = column != filter_value\n elif operator == \"contains\":\n mask = column.astype(str).str.contains(str(filter_value), na=False)\n elif operator == \"not contains\":\n mask = ~column.astype(str).str.contains(str(filter_value), na=False)\n elif operator == \"starts with\":\n mask = column.astype(str).str.startswith(str(filter_value), na=False)\n elif operator == \"ends with\":\n mask = column.astype(str).str.endswith(str(filter_value), na=False)\n elif operator == \"greater than\":\n try:\n numeric_value = pd.to_numeric(filter_value)\n mask = column > numeric_value\n except (ValueError, TypeError):\n mask = column.astype(str) > str(filter_value)\n elif operator == \"less than\":\n try:\n numeric_value = pd.to_numeric(filter_value)\n mask = column < numeric_value\n except (ValueError, TypeError):\n mask = column.astype(str) < str(filter_value)\n else:\n mask = column == filter_value\n\n return DataFrame(df[mask])\n\n def sort_by_column(self, df: DataFrame) -> DataFrame:\n return DataFrame(df.sort_values(by=self.column_name, ascending=self.ascending))\n\n def drop_column(self, df: DataFrame) -> DataFrame:\n return DataFrame(df.drop(columns=[self.column_name]))\n\n def rename_column(self, df: DataFrame) -> DataFrame:\n return DataFrame(df.rename(columns={self.column_name: self.new_column_name}))\n\n def add_column(self, df: DataFrame) -> DataFrame:\n df[self.new_column_name] = [self.new_column_value] * len(df)\n return DataFrame(df)\n\n def select_columns(self, df: DataFrame) -> DataFrame:\n columns = [col.strip() for col in self.columns_to_select]\n return DataFrame(df[columns])\n\n def head(self, df: DataFrame) -> DataFrame:\n return DataFrame(df.head(self.num_rows))\n\n def tail(self, df: DataFrame) -> DataFrame:\n return DataFrame(df.tail(self.num_rows))\n\n def replace_values(self, df: DataFrame) -> DataFrame:\n df[self.column_name] = df[self.column_name].replace(self.replace_value, self.replacement_value)\n return DataFrame(df)\n\n def drop_duplicates(self, df: DataFrame) -> DataFrame:\n return DataFrame(df.drop_duplicates(subset=self.column_name))\n\n def concatenate_dataframes(self) -> DataFrame:\n \"\"\"Concatenate multiple DataFrames vertically (stack rows).\"\"\"\n if not isinstance(self.df, list) or len(self.df) == 0:\n return self.df.copy() if self.df is not None else DataFrame()\n\n if len(self.df) == 1:\n return self.df[0].copy()\n\n concatenated = pd.concat(self.df, ignore_index=True)\n return DataFrame(concatenated)\n\n def merge_dataframes(self) -> DataFrame:\n \"\"\"Merge two DataFrames based on a common column (join operation).\"\"\"\n left_df = getattr(self, \"left_dataframe\", None)\n right_df = getattr(self, \"right_dataframe\", None)\n\n if left_df is None:\n return DataFrame()\n if right_df is None:\n return left_df.copy()\n\n df_left = left_df.copy()\n df_right = right_df.copy()\n\n merge_on = getattr(self, \"merge_on_column\", None)\n merge_how = getattr(self, \"merge_how\", \"inner\")\n\n if merge_on:\n if merge_on not in df_left.columns:\n msg = f\"Column '{merge_on}' not found in left DataFrame. Available: {list(df_left.columns)}\"\n raise ValueError(msg)\n if merge_on not in df_right.columns:\n msg = f\"Column '{merge_on}' not found in right DataFrame. Available: {list(df_right.columns)}\"\n raise ValueError(msg)\n merged = df_left.merge(df_right, on=merge_on, how=merge_how, suffixes=(\"\", \"_right\"))\n else:\n merged = df_left.merge(df_right, left_index=True, right_index=True, how=merge_how, suffixes=(\"\", \"_right\"))\n\n cols_to_drop = []\n for col in merged.columns:\n if col.endswith(\"_right\"):\n original_col = col[:-6]\n if original_col in merged.columns:\n merged[original_col] = merged[original_col].combine_first(merged[col])\n cols_to_drop.append(col)\n\n if cols_to_drop:\n merged = merged.drop(columns=cols_to_drop)\n\n return DataFrame(merged)\n\n # ==================================================================\n # Text operations\n # ==================================================================\n def _run_text_operation(self) -> Any:\n \"\"\"Process text based on the selected operation (Message/Text outputs).\"\"\"\n text = getattr(self, \"text_input\", \"\")\n operation = self._operation_name()\n\n # Allow empty text for Text Join (second input may have content).\n if not text and operation != \"Text Join\":\n return None\n\n text_handlers = {\n \"Case Conversion\": self._case_conversion,\n \"Text Replace\": self._text_replace,\n \"Text Extract\": self._text_extract,\n \"Text Head\": self._text_head,\n \"Text Tail\": self._text_tail,\n \"Text Strip\": self._text_strip,\n \"Text Join\": self._text_join,\n \"Text Clean\": self._text_clean,\n }\n handler = text_handlers.get(operation)\n if handler:\n return handler(text)\n return text\n\n def _word_count_data(self) -> Data:\n \"\"\"Word Count operation result as a Data object.\"\"\"\n result = self._word_count(getattr(self, \"text_input\", \"\") or \"\")\n return Data(data=result)\n\n def _word_count(self, text: str) -> dict[str, Any]:\n \"\"\"Count words, characters, and lines in text.\"\"\"\n result: dict[str, Any] = {}\n text_str = str(text) if text else \"\"\n is_empty = not text_str or not text_str.strip()\n\n if getattr(self, \"count_words\", True):\n if is_empty:\n result[\"word_count\"] = 0\n result[\"unique_words\"] = 0\n else:\n words = text_str.split()\n result[\"word_count\"] = len(words)\n result[\"unique_words\"] = len(set(words))\n\n if getattr(self, \"count_characters\", True):\n if is_empty:\n result[\"character_count\"] = 0\n result[\"character_count_no_spaces\"] = 0\n else:\n result[\"character_count\"] = len(text_str)\n result[\"character_count_no_spaces\"] = len(text_str.replace(\" \", \"\"))\n\n if getattr(self, \"count_lines\", True):\n if is_empty:\n result[\"line_count\"] = 0\n result[\"non_empty_lines\"] = 0\n else:\n lines = text_str.split(\"\\n\")\n result[\"line_count\"] = len(lines)\n result[\"non_empty_lines\"] = len([line for line in lines if line.strip()])\n\n return result\n\n def _text_to_dataframe(self, text: str) -> DataFrame:\n \"\"\"Convert markdown-style table text to a DataFrame.\"\"\"\n lines = [line.strip() for line in text.strip().split(\"\\n\") if line.strip()]\n if not lines:\n return DataFrame(pd.DataFrame())\n\n separator = getattr(self, \"table_separator\", \"|\")\n has_header = getattr(self, \"has_header\", True)\n\n rows = self._parse_table_rows(lines, separator)\n if not rows:\n return DataFrame(pd.DataFrame())\n\n df = self._create_dataframe(rows, has_header=has_header)\n self._convert_numeric_columns(df)\n self.log(f\"Converted text to DataFrame: {len(df)} rows, {len(df.columns)} columns\")\n return DataFrame(df)\n\n def _parse_table_rows(self, lines: list[str], separator: str) -> list[list[str]]:\n rows = []\n for line in lines:\n cleaned_line = line.strip(separator)\n cells = [cell.strip() for cell in cleaned_line.split(separator)]\n rows.append(cells)\n return rows\n\n def _create_dataframe(self, rows: list[list[str]], *, has_header: bool) -> pd.DataFrame:\n if has_header and len(rows) > 1:\n header = rows[0]\n data_rows = rows[1:]\n header_col_count = len(header)\n for i, row in enumerate(data_rows):\n row_col_count = len(row)\n if row_col_count != header_col_count:\n msg = (\n f\"Header mismatch: {header_col_count} column(s) in header vs \"\n f\"{row_col_count} column(s) in data row {i + 1}. \"\n \"Please ensure the header has the same number of columns as your data.\"\n )\n raise ValueError(msg)\n return pd.DataFrame(data_rows, columns=header)\n\n max_cols = max(len(row) for row in rows) if rows else 0\n columns = [f\"col_{i}\" for i in range(max_cols)]\n return pd.DataFrame(rows, columns=columns)\n\n def _convert_numeric_columns(self, df: pd.DataFrame) -> None:\n for col in df.columns:\n with contextlib.suppress(ValueError, TypeError):\n df[col] = pd.to_numeric(df[col])\n\n def _case_conversion(self, text: str) -> str:\n case_type = getattr(self, \"case_type\", \"lowercase\")\n converter = CASE_CONVERTERS.get(case_type)\n return converter(text) if converter else text\n\n def _text_replace(self, text: str) -> str:\n search_pattern = getattr(self, \"search_pattern\", \"\")\n if not search_pattern:\n return text\n replacement_text = getattr(self, \"replacement_text\", \"\")\n use_regex = getattr(self, \"use_regex\", False)\n if use_regex:\n try:\n return re.sub(search_pattern, replacement_text, text)\n except re.error as e:\n self.log(f\"Invalid regex pattern: {e}\")\n return text\n return text.replace(search_pattern, replacement_text)\n\n def _text_extract(self, text: str) -> list[str]:\n extract_pattern = getattr(self, \"extract_pattern\", \"\")\n if not extract_pattern:\n return []\n max_matches = getattr(self, \"max_matches\", 10)\n try:\n matches = re.findall(extract_pattern, text)\n except re.error as e:\n msg = f\"Invalid regex pattern '{extract_pattern}': {e}\"\n raise ValueError(msg) from e\n return matches[:max_matches] if max_matches > 0 else matches\n\n def _text_head(self, text: str) -> str:\n head_characters = getattr(self, \"head_characters\", 100)\n if head_characters < 0:\n msg = f\"Characters from Start must be a non-negative integer, got {head_characters}\"\n raise ValueError(msg)\n if head_characters == 0:\n return \"\"\n return text[:head_characters]\n\n def _text_tail(self, text: str) -> str:\n tail_characters = getattr(self, \"tail_characters\", 100)\n if tail_characters < 0:\n msg = f\"Characters from End must be a non-negative integer, got {tail_characters}\"\n raise ValueError(msg)\n if tail_characters == 0:\n return \"\"\n return text[-tail_characters:]\n\n def _text_strip(self, text: str) -> str:\n strip_mode = getattr(self, \"strip_mode\", \"both\")\n strip_characters = getattr(self, \"strip_characters\", \"\")\n text_str = str(text) if text else \"\"\n chars_to_strip = strip_characters if strip_characters else None\n if strip_mode == \"left\":\n return text_str.lstrip(chars_to_strip)\n if strip_mode == \"right\":\n return text_str.rstrip(chars_to_strip)\n return text_str.strip(chars_to_strip)\n\n def _text_join(self, text: str) -> str:\n text_input_2 = getattr(self, \"text_input_2\", \"\")\n text1 = str(text) if text else \"\"\n text2 = str(text_input_2) if text_input_2 else \"\"\n if text1 and text2:\n return f\"{text1}\\n{text2}\"\n return text1 or text2\n\n def _text_clean(self, text: str) -> str:\n result = text\n if getattr(self, \"remove_extra_spaces\", True):\n # Collapse runs of horizontal whitespace but preserve newlines so\n # that remove_empty_lines stays effective when both are enabled.\n result = re.sub(r\"[^\\S\\n]+\", \" \", result)\n if getattr(self, \"remove_special_chars\", False):\n result = re.sub(r\"[^\\w\\s]\", \"\", result)\n if getattr(self, \"remove_empty_lines\", False):\n lines = [line for line in result.split(\"\\n\") if line.strip()]\n result = \"\\n\".join(lines)\n return result\n\n def _format_result_as_text(self, result: Any) -> str:\n if result is None:\n return \"\"\n if isinstance(result, list):\n return \"\\n\".join(str(item) for item in result)\n return str(result)\n"
+ "value": "\"\"\"Unified Operations component.\n\nBrings together the previously separate JSON, Table, and Text operation\ncomponents into a single component. An \"Input Type\" selector (Text / JSON /\nTable) drives everything: it filters the \"Operation\" picker to the operations\nthat apply to that type, reveals the matching input (Text / JSON / Table) and\nits operation-specific fields, and advertises the appropriate output type.\n\nThe three original components (JSON Operations, Table Operations, Text\nOperations) remain available as legacy components for backward compatibility\nwith existing flows.\n\"\"\"\n\nimport ast\nimport contextlib\nimport json\nimport re\nfrom typing import TYPE_CHECKING, Any\n\nimport pandas as pd\nfrom json_repair import repair_json\n\nfrom lfx.custom import Component\nfrom lfx.field_typing import RangeSpec\nfrom lfx.inputs import DictInput, SortableListInput, TabInput\nfrom lfx.io import (\n BoolInput,\n DataFrameInput,\n DataInput,\n DropdownInput,\n IntInput,\n MessageTextInput,\n MultilineInput,\n Output,\n StrInput,\n)\nfrom lfx.log.logger import logger\nfrom lfx.schema import Data\nfrom lfx.schema.dataframe import DataFrame\nfrom lfx.schema.dotdict import dotdict\nfrom lfx.schema.message import Message\nfrom lfx.utils.jq_security import validate_jq_program\n\nif TYPE_CHECKING:\n from collections.abc import Callable\n\n# The \"Input Type\" selector tabs. Each value maps a Langflow data type to the\n# operations, input, and output that belong to it.\nINPUT_TYPES = [\"Text\", \"JSON\", \"Table\"]\n\n# Operations grouped by input type, in display order, each with the icon shown\n# in the Operation picker. This is the single source of truth for the picker;\n# update_build_config swaps the picker's options to the selected type's list.\nOPERATIONS_BY_TYPE: dict[str, list[dict[str, str]]] = {\n \"Text\": [\n {\"name\": \"Word Count\", \"icon\": \"hash\"},\n {\"name\": \"Case Conversion\", \"icon\": \"type\"},\n {\"name\": \"Text Replace\", \"icon\": \"replace\"},\n {\"name\": \"Text Extract\", \"icon\": \"search\"},\n {\"name\": \"Text Head\", \"icon\": \"chevron-left\"},\n {\"name\": \"Text Tail\", \"icon\": \"chevron-right\"},\n {\"name\": \"Text Strip\", \"icon\": \"minus\"},\n {\"name\": \"Text Join\", \"icon\": \"link\"},\n {\"name\": \"Text Clean\", \"icon\": \"sparkles\"},\n {\"name\": \"Text to DataFrame\", \"icon\": \"table\"},\n ],\n \"JSON\": [\n {\"name\": \"Select Keys\", \"icon\": \"lasso-select\"},\n {\"name\": \"Literal Eval\", \"icon\": \"braces\"},\n {\"name\": \"Combine\", \"icon\": \"merge\"},\n {\"name\": \"Append or Update\", \"icon\": \"circle-plus\"},\n {\"name\": \"Remove Keys\", \"icon\": \"eraser\"},\n {\"name\": \"Rename Keys\", \"icon\": \"pencil-line\"},\n {\"name\": \"Path Selection\", \"icon\": \"mouse-pointer\"},\n {\"name\": \"JQ Expression\", \"icon\": \"terminal\"},\n ],\n \"Table\": [\n {\"name\": \"Add Column\", \"icon\": \"plus\"},\n {\"name\": \"Concatenate\", \"icon\": \"combine\"},\n {\"name\": \"Drop Column\", \"icon\": \"minus\"},\n {\"name\": \"Filter\", \"icon\": \"filter\"},\n {\"name\": \"Head\", \"icon\": \"arrow-up\"},\n {\"name\": \"Merge\", \"icon\": \"merge\"},\n {\"name\": \"Rename Column\", \"icon\": \"pencil\"},\n {\"name\": \"Replace Value\", \"icon\": \"replace\"},\n {\"name\": \"Select Columns\", \"icon\": \"columns\"},\n {\"name\": \"Sort\", \"icon\": \"arrow-up-down\"},\n {\"name\": \"Tail\", \"icon\": \"arrow-down\"},\n {\"name\": \"Drop Duplicates\", \"icon\": \"copy-x\"},\n ],\n}\n\n# Operation-name sets derived from the picker, used for dispatch and output\n# routing. Keeping them derived from OPERATIONS_BY_TYPE avoids any drift.\nJSON_OPERATIONS = {op[\"name\"] for op in OPERATIONS_BY_TYPE[\"JSON\"]}\nTABLE_OPERATIONS = {op[\"name\"] for op in OPERATIONS_BY_TYPE[\"Table\"]}\nTEXT_OPERATIONS = {op[\"name\"] for op in OPERATIONS_BY_TYPE[\"Text\"]}\n\n# Each input type maps to its main input field and its default output. \"Text\"\n# normally outputs a Message; \"JSON\" a Data; \"Table\" a DataFrame. A few text\n# operations override this (Word Count -> Data, Text to DataFrame -> DataFrame).\nINPUT_TYPE_TO_MAIN_INPUT = {\"Text\": \"text_input\", \"JSON\": \"data\", \"Table\": \"df\"}\n\n# Case conversions for the Text \"Case Conversion\" operation.\nCASE_CONVERTERS: dict[str, Any] = {\n \"uppercase\": str.upper,\n \"lowercase\": str.lower,\n \"title\": str.title,\n \"capitalize\": str.capitalize,\n \"swapcase\": str.swapcase,\n}\n\n# A markdown table's delimiter row (``|---|:--:|``) separates the header from the body.\nMARKDOWN_DELIMITER_CELL = re.compile(r\":?-+:?\")\n\n\nclass OperationsComponent(Component):\n display_name = \"Data Operations\"\n description = \"Perform operations on Text, JSON, and Tables from a single component.\"\n documentation: str = \"https://docs.langflow.org/components-processing#operations\"\n icon = \"wand-sparkles\"\n name = \"Operations\"\n metadata = {\n \"keywords\": [\n \"operations\",\n \"data operations\",\n \"json\",\n \"json operations\",\n \"table\",\n \"table operations\",\n \"dataframe\",\n \"dataframe operations\",\n \"text\",\n \"text operations\",\n \"select keys\",\n \"literal eval\",\n \"combine\",\n \"append or update\",\n \"remove keys\",\n \"rename keys\",\n \"path selection\",\n \"jq expression\",\n \"parse json\",\n \"add column\",\n \"concatenate\",\n \"drop column\",\n \"filter\",\n \"head\",\n \"merge\",\n \"rename column\",\n \"replace value\",\n \"select columns\",\n \"sort\",\n \"tail\",\n \"drop duplicates\",\n \"word count\",\n \"case conversion\",\n \"text replace\",\n \"text extract\",\n \"text join\",\n \"text clean\",\n \"text to dataframe\",\n \"data manipulation\",\n \"data transformation\",\n ],\n }\n\n # Operation -> operation-specific input fields to reveal when selected.\n OPERATION_FIELDS: dict[str, list[str]] = {\n # JSON\n \"Select Keys\": [\"select_keys_input\"],\n \"Literal Eval\": [],\n \"Combine\": [],\n \"Append or Update\": [\"append_update_data\"],\n \"Remove Keys\": [\"remove_keys_input\"],\n \"Rename Keys\": [\"rename_keys_input\"],\n \"Path Selection\": [\"mapped_json_display\", \"selected_key\"],\n \"JQ Expression\": [\"query\"],\n # Table\n \"Add Column\": [\"new_column_name\", \"new_column_value\"],\n \"Concatenate\": [],\n \"Drop Column\": [\"column_name\"],\n \"Filter\": [\"column_name\", \"filter_value\", \"filter_operator\"],\n \"Head\": [\"num_rows\"],\n \"Merge\": [\"left_dataframe\", \"right_dataframe\", \"merge_on_column\", \"merge_how\"],\n \"Rename Column\": [\"column_name\", \"new_column_name\"],\n \"Replace Value\": [\"column_name\", \"replace_value\", \"replacement_value\"],\n \"Select Columns\": [\"columns_to_select\"],\n \"Sort\": [\"column_name\", \"ascending\"],\n \"Tail\": [\"num_rows\"],\n \"Drop Duplicates\": [\"column_name\"],\n # Text\n \"Word Count\": [\"count_words\", \"count_characters\", \"count_lines\"],\n \"Case Conversion\": [\"case_type\"],\n \"Text Replace\": [\"search_pattern\", \"replacement_text\", \"use_regex\"],\n \"Text Extract\": [\"extract_pattern\", \"max_matches\"],\n \"Text Head\": [\"head_characters\"],\n \"Text Tail\": [\"tail_characters\"],\n \"Text Strip\": [\"strip_mode\", \"strip_characters\"],\n \"Text Join\": [\"text_input_2\"],\n \"Text Clean\": [\"remove_extra_spaces\", \"remove_special_chars\", \"remove_empty_lines\"],\n \"Text to DataFrame\": [\"table_separator\", \"has_header\"],\n }\n\n # The three main inputs (one per data type). They are never treated as\n # operation-specific fields; the input-type selector toggles them.\n MAIN_INPUTS = (\"text_input\", \"data\", \"df\")\n\n # Every operation-specific field (union of all the lists above), used to\n # hide and reset fields whenever the input type or operation changes.\n ALL_OPERATION_FIELDS: list[str] = [\n # JSON\n \"select_keys_input\",\n \"append_update_data\",\n \"remove_keys_input\",\n \"rename_keys_input\",\n \"mapped_json_display\",\n \"selected_key\",\n \"query\",\n # Table\n \"column_name\",\n \"filter_value\",\n \"filter_operator\",\n \"ascending\",\n \"new_column_name\",\n \"new_column_value\",\n \"columns_to_select\",\n \"num_rows\",\n \"replace_value\",\n \"replacement_value\",\n \"left_dataframe\",\n \"right_dataframe\",\n \"merge_on_column\",\n \"merge_how\",\n # Text\n \"table_separator\",\n \"has_header\",\n \"count_words\",\n \"count_characters\",\n \"count_lines\",\n \"case_type\",\n \"use_regex\",\n \"search_pattern\",\n \"replacement_text\",\n \"extract_pattern\",\n \"max_matches\",\n \"head_characters\",\n \"tail_characters\",\n \"strip_mode\",\n \"strip_characters\",\n \"text_input_2\",\n \"remove_extra_spaces\",\n \"remove_special_chars\",\n \"remove_empty_lines\",\n ]\n\n # Defaults applied to the JSON operation fields when the operation changes,\n # mirroring the JSON Operations component's reset behavior.\n OPERATION_FIELD_DEFAULTS: dict[str, Any] = {\n \"select_keys_input\": [],\n \"append_update_data\": {\"key\": \"value\"},\n \"remove_keys_input\": [],\n \"rename_keys_input\": {\"old_key\": \"new_key\"},\n \"mapped_json_display\": \"\",\n \"selected_key\": None,\n \"query\": \"\",\n }\n\n inputs = [\n # --- Input type selector: drives operations, input, and output ---\n TabInput(\n name=\"input_type\",\n display_name=\"Input Type\",\n options=INPUT_TYPES,\n value=\"Text\",\n info=\"Select the type of input to operate on.\",\n real_time_refresh=True,\n ),\n # --- Main inputs: one per data type, shown contextually ---\n MultilineInput(\n name=\"text_input\",\n display_name=\"Text\",\n info=\"The input text to process.\",\n show=True,\n ),\n DataInput(\n name=\"data\",\n display_name=\"JSON\",\n info=\"The JSON / Data object to operate on.\",\n is_list=True,\n show=False,\n ),\n DataFrameInput(\n name=\"df\",\n display_name=\"Table\",\n info=\"The input Table to operate on. Connect multiple Tables for merge or concatenate operations.\",\n is_list=True,\n show=False,\n ),\n # --- Operation picker (options are filtered by Input Type) ---\n SortableListInput(\n name=\"operation\",\n display_name=\"Operation\",\n placeholder=\"Select Operation\",\n info=\"Select the operation to perform. The matching fields and output appear once you choose one.\",\n options=OPERATIONS_BY_TYPE[\"Text\"],\n real_time_refresh=True,\n limit=1,\n ),\n # --- JSON operation fields ---\n MessageTextInput(\n name=\"select_keys_input\",\n display_name=\"Select Keys\",\n info=\"List of keys to select from the data. Only top-level keys can be selected.\",\n show=False,\n is_list=True,\n value=[],\n ),\n DictInput(\n name=\"append_update_data\",\n display_name=\"Append or Update\",\n info=\"Data to append or update the existing data with. Only top-level keys are checked.\",\n show=False,\n value={\"key\": \"value\"},\n is_list=True,\n ),\n MessageTextInput(\n name=\"remove_keys_input\",\n display_name=\"Remove Keys\",\n info=\"List of keys to remove from the data.\",\n show=False,\n is_list=True,\n value=[],\n ),\n DictInput(\n name=\"rename_keys_input\",\n display_name=\"Rename Keys\",\n info=\"List of keys to rename in the data.\",\n show=False,\n is_list=True,\n value={\"old_key\": \"new_key\"},\n ),\n MultilineInput(\n name=\"mapped_json_display\",\n display_name=\"JSON to Map\",\n info=\"Paste or preview your JSON here to explore its structure and select a path for extraction.\",\n required=False,\n refresh_button=True,\n real_time_refresh=True,\n placeholder=\"Add a JSON example.\",\n show=False,\n ),\n DropdownInput(\n name=\"selected_key\",\n display_name=\"Select Path\",\n options=[],\n required=False,\n dynamic=True,\n show=False,\n value=None,\n ),\n MessageTextInput(\n name=\"query\",\n display_name=\"JQ Expression\",\n info=\"JSON Query to filter the data. Used by Path Selection and JQ Expression operations.\",\n placeholder=\"e.g., .properties.id\",\n show=False,\n ),\n # --- Table operation fields ---\n StrInput(\n name=\"column_name\",\n display_name=\"Column Name\",\n info=\"The column name to use for the operation.\",\n dynamic=True,\n show=False,\n ),\n MessageTextInput(\n name=\"filter_value\",\n display_name=\"Filter Value\",\n info=\"The value to filter rows by.\",\n dynamic=True,\n show=False,\n ),\n DropdownInput(\n name=\"filter_operator\",\n display_name=\"Filter Operator\",\n options=[\n \"equals\",\n \"not equals\",\n \"contains\",\n \"not contains\",\n \"starts with\",\n \"ends with\",\n \"greater than\",\n \"less than\",\n ],\n value=\"equals\",\n info=\"The operator to apply for filtering rows.\",\n advanced=False,\n dynamic=True,\n show=False,\n ),\n BoolInput(\n name=\"ascending\",\n display_name=\"Sort Ascending\",\n info=\"Whether to sort in ascending order.\",\n dynamic=True,\n show=False,\n value=True,\n ),\n StrInput(\n name=\"new_column_name\",\n display_name=\"New Column Name\",\n info=\"The new column name when renaming or adding a column.\",\n dynamic=True,\n show=False,\n ),\n MessageTextInput(\n name=\"new_column_value\",\n display_name=\"New Column Value\",\n info=\"The value to populate the new column with.\",\n dynamic=True,\n show=False,\n ),\n StrInput(\n name=\"columns_to_select\",\n display_name=\"Columns to Select\",\n dynamic=True,\n is_list=True,\n show=False,\n ),\n IntInput(\n name=\"num_rows\",\n display_name=\"Number of Rows\",\n info=\"Number of rows to return (for head/tail).\",\n dynamic=True,\n show=False,\n value=5,\n ),\n MessageTextInput(\n name=\"replace_value\",\n display_name=\"Value to Replace\",\n info=\"The value to replace in the column.\",\n dynamic=True,\n show=False,\n ),\n MessageTextInput(\n name=\"replacement_value\",\n display_name=\"Replacement Value\",\n info=\"The value to replace with.\",\n dynamic=True,\n show=False,\n ),\n DataFrameInput(\n name=\"left_dataframe\",\n display_name=\"Left Table\",\n info=\"The left (primary) Table for merge operations. \"\n \"In a left merge, all rows from this table are preserved.\",\n dynamic=True,\n show=False,\n ),\n DataFrameInput(\n name=\"right_dataframe\",\n display_name=\"Right Table\",\n info=\"The right (secondary) Table for merge operations. \"\n \"In a right merge, all rows from this table are preserved.\",\n dynamic=True,\n show=False,\n ),\n StrInput(\n name=\"merge_on_column\",\n display_name=\"Merge On Column\",\n info=\"The column name to merge Tables on. Must exist in both Tables.\",\n dynamic=True,\n show=False,\n ),\n DropdownInput(\n name=\"merge_how\",\n display_name=\"Merge Type\",\n options=[\"inner\", \"outer\", \"left\", \"right\"],\n value=\"inner\",\n info=\"Type of merge: inner (intersection), outer (union), left, or right.\",\n dynamic=True,\n show=False,\n ),\n # --- Text operation fields ---\n StrInput(\n name=\"table_separator\",\n display_name=\"Table Separator\",\n info=\"Separator used in the table (default: '|').\",\n value=\"|\",\n dynamic=True,\n show=False,\n ),\n BoolInput(\n name=\"has_header\",\n display_name=\"Has Header\",\n info=\"Whether the table has a header row.\",\n value=True,\n dynamic=True,\n advanced=True,\n show=False,\n ),\n BoolInput(\n name=\"count_words\",\n display_name=\"Count Words\",\n info=\"Include word count in analysis.\",\n value=True,\n dynamic=True,\n advanced=True,\n show=False,\n ),\n BoolInput(\n name=\"count_characters\",\n display_name=\"Count Characters\",\n info=\"Include character count in analysis.\",\n value=True,\n dynamic=True,\n advanced=True,\n show=False,\n ),\n BoolInput(\n name=\"count_lines\",\n display_name=\"Count Lines\",\n info=\"Include line count in analysis.\",\n value=True,\n dynamic=True,\n advanced=True,\n show=False,\n ),\n DropdownInput(\n name=\"case_type\",\n display_name=\"Case Type\",\n options=[\"uppercase\", \"lowercase\", \"title\", \"capitalize\", \"swapcase\"],\n value=\"lowercase\",\n info=\"Type of case conversion to apply.\",\n dynamic=True,\n show=False,\n ),\n BoolInput(\n name=\"use_regex\",\n display_name=\"Use Regex\",\n info=\"Whether to treat search pattern as regex.\",\n value=False,\n dynamic=True,\n show=False,\n ),\n StrInput(\n name=\"search_pattern\",\n display_name=\"Search Pattern\",\n info=\"Text pattern to search for (supports regex).\",\n dynamic=True,\n show=False,\n ),\n StrInput(\n name=\"replacement_text\",\n display_name=\"Replacement Text\",\n info=\"Text to replace the search pattern with.\",\n dynamic=True,\n show=False,\n ),\n StrInput(\n name=\"extract_pattern\",\n display_name=\"Extract Pattern\",\n info=\"Regex pattern to extract from text.\",\n dynamic=True,\n show=False,\n ),\n IntInput(\n name=\"max_matches\",\n display_name=\"Max Matches\",\n info=\"Maximum number of matches to extract.\",\n value=10,\n dynamic=True,\n show=False,\n ),\n IntInput(\n name=\"head_characters\",\n display_name=\"Characters from Start\",\n info=\"Number of characters to extract from the beginning of text. Must be non-negative.\",\n value=100,\n dynamic=True,\n show=False,\n range_spec=RangeSpec(min=0, max=1000000, step=1, step_type=\"int\"),\n ),\n IntInput(\n name=\"tail_characters\",\n display_name=\"Characters from End\",\n info=\"Number of characters to extract from the end of text. Must be non-negative.\",\n value=100,\n dynamic=True,\n show=False,\n range_spec=RangeSpec(min=0, max=1000000, step=1, step_type=\"int\"),\n ),\n DropdownInput(\n name=\"strip_mode\",\n display_name=\"Strip Mode\",\n options=[\"both\", \"left\", \"right\"],\n value=\"both\",\n info=\"Which sides to strip whitespace from.\",\n dynamic=True,\n show=False,\n ),\n StrInput(\n name=\"strip_characters\",\n display_name=\"Characters to Strip\",\n info=\"Specific characters to remove (leave empty for whitespace).\",\n value=\"\",\n dynamic=True,\n show=False,\n ),\n MultilineInput(\n name=\"text_input_2\",\n display_name=\"Second Text Input\",\n info=\"Second text to join with the first text.\",\n dynamic=True,\n show=False,\n ),\n BoolInput(\n name=\"remove_extra_spaces\",\n display_name=\"Remove Extra Spaces\",\n info=\"Remove multiple consecutive spaces.\",\n value=True,\n dynamic=True,\n show=False,\n ),\n BoolInput(\n name=\"remove_special_chars\",\n display_name=\"Remove Special Characters\",\n info=\"Remove special characters except alphanumeric and spaces.\",\n value=False,\n dynamic=True,\n show=False,\n ),\n BoolInput(\n name=\"remove_empty_lines\",\n display_name=\"Remove Empty Lines\",\n info=\"Remove empty lines from text.\",\n value=False,\n dynamic=True,\n show=False,\n ),\n ]\n\n # Default output matches the default Input Type (\"Text\" -> Message).\n # update_outputs / update_frontend_node narrow it to the selected type and\n # operation.\n outputs = [Output(display_name=\"Message\", name=\"message_output\", method=\"as_message\")]\n\n # ------------------------------------------------------------------\n # Operation routing helpers\n # ------------------------------------------------------------------\n @staticmethod\n def _extract_operation_name(field_value: Any) -> str:\n \"\"\"Extract the operation name from a SortableListInput value.\"\"\"\n if isinstance(field_value, list) and len(field_value) > 0 and isinstance(field_value[0], dict):\n return field_value[0].get(\"name\", \"\")\n if isinstance(field_value, str):\n return field_value\n return \"\"\n\n def _operation_name(self) -> str:\n \"\"\"Get the currently selected operation name.\"\"\"\n return self._extract_operation_name(getattr(self, \"operation\", []))\n\n @staticmethod\n def _default_output_for_type(input_type: str) -> Output:\n \"\"\"Return the output advertised for an input type when no operation is selected yet.\"\"\"\n if input_type == \"JSON\":\n return Output(display_name=\"JSON\", name=\"data_output\", method=\"as_data\")\n if input_type == \"Table\":\n return Output(display_name=\"Table\", name=\"dataframe_output\", method=\"as_dataframe\")\n return Output(display_name=\"Message\", name=\"message_output\", method=\"as_message\")\n\n # ------------------------------------------------------------------\n # Dynamic UI\n # ------------------------------------------------------------------\n def _reset_operation_fields(self, build_config: dotdict) -> None:\n \"\"\"Hide every operation-specific field and restore its default value.\"\"\"\n for field in self.ALL_OPERATION_FIELDS:\n if field in build_config:\n build_config[field][\"show\"] = False\n if field in self.OPERATION_FIELD_DEFAULTS:\n build_config[field][\"value\"] = self.OPERATION_FIELD_DEFAULTS[field]\n\n def _show_main_input(self, build_config: dotdict, input_type: str, operation: str) -> None:\n \"\"\"Show only the main input that matches the input type; hide the others.\"\"\"\n for inp in self.MAIN_INPUTS:\n if inp in build_config:\n build_config[inp][\"show\"] = False\n build_config[inp][\"required\"] = False\n\n main_input = INPUT_TYPE_TO_MAIN_INPUT.get(input_type)\n if main_input and main_input in build_config:\n build_config[main_input][\"show\"] = True\n build_config[main_input][\"required\"] = True\n # The JSON \"Combine\" operation consumes a list of Data objects.\n if main_input == \"data\":\n build_config[\"data\"][\"is_list\"] = operation == \"Combine\"\n\n def update_build_config(self, build_config: dotdict, field_value: Any, field_name: str | None = None) -> dotdict:\n # Path Selection: refresh the available JSON paths from the pasted JSON.\n if field_name == \"mapped_json_display\":\n try:\n parsed_json = json.loads(field_value)\n keys = self.extract_all_paths(parsed_json)\n build_config[\"selected_key\"][\"options\"] = keys\n build_config[\"selected_key\"][\"show\"] = True\n except (json.JSONDecodeError, TypeError, ValueError) as e:\n logger.error(f\"Error parsing mapped JSON: {e}\")\n build_config[\"selected_key\"][\"show\"] = False\n return build_config\n\n # Input type changed: swap the operation list, clear the selection, and\n # show only the matching input. No operation-specific fields are shown\n # until an operation is picked.\n if field_name == \"input_type\":\n input_type = field_value if field_value in OPERATIONS_BY_TYPE else \"Text\"\n build_config[\"operation\"][\"options\"] = OPERATIONS_BY_TYPE[input_type]\n build_config[\"operation\"][\"value\"] = []\n self._reset_operation_fields(build_config)\n self._show_main_input(build_config, input_type, operation=\"\")\n return build_config\n\n # Operation changed: reset fields, show the input for the current type,\n # then reveal the operation-specific fields.\n if field_name == \"operation\":\n operation = self._extract_operation_name(field_value)\n self._reset_operation_fields(build_config)\n\n input_type = build_config.get(\"input_type\", {}).get(\"value\", \"Text\")\n self._show_main_input(build_config, input_type, operation)\n\n for field in self.OPERATION_FIELDS.get(operation, []):\n if field in build_config:\n build_config[field][\"show\"] = True\n\n return build_config\n\n return build_config\n\n def update_outputs(self, frontend_node: dict, field_name: str, field_value: Any) -> dict:\n \"\"\"Create the output(s) appropriate to the selected input type and operation.\"\"\"\n if field_name == \"input_type\":\n # Switching type clears the operation; advertise the type's default.\n input_type = field_value if field_value in OPERATIONS_BY_TYPE else \"Text\"\n frontend_node[\"outputs\"] = [self._default_output_for_type(input_type)]\n return frontend_node\n\n template = frontend_node.get(\"template\", {})\n input_type = template.get(\"input_type\", {}).get(\"value\", \"Text\")\n\n if field_name == \"operation\":\n operation = self._extract_operation_name(field_value)\n else:\n # Any other refresh (e.g. Path Selection's \"JSON to Map\" field)\n # reaches here on a freshly rebuilt node whose outputs were reset\n # to the class default (Message). Re-derive the output from the\n # saved operation so the refresh doesn't swap the real output type.\n operation = self._extract_operation_name(template.get(\"operation\", {}).get(\"value\", []))\n\n if not operation:\n # No operation selected: fall back to the input type's default output.\n frontend_node[\"outputs\"] = [self._default_output_for_type(input_type)]\n return frontend_node\n\n frontend_node[\"outputs\"] = []\n if operation in JSON_OPERATIONS or operation == \"Word Count\":\n frontend_node[\"outputs\"].append(Output(display_name=\"JSON\", name=\"data_output\", method=\"as_data\"))\n elif operation in TABLE_OPERATIONS or operation == \"Text to DataFrame\":\n frontend_node[\"outputs\"].append(\n Output(display_name=\"Table\", name=\"dataframe_output\", method=\"as_dataframe\")\n )\n elif operation == \"Text Join\":\n frontend_node[\"outputs\"].append(Output(display_name=\"Text\", name=\"text_output\", method=\"as_text\"))\n frontend_node[\"outputs\"].append(Output(display_name=\"Message\", name=\"message_output\", method=\"as_message\"))\n else:\n frontend_node[\"outputs\"].append(Output(display_name=\"Message\", name=\"message_output\", method=\"as_message\"))\n\n return frontend_node\n\n async def update_frontend_node(self, new_frontend_node: dict, current_frontend_node: dict) -> dict:\n \"\"\"Keep the operation options and outputs in sync with the saved input type on load.\"\"\"\n await super().update_frontend_node(new_frontend_node, current_frontend_node)\n\n template = new_frontend_node.get(\"template\", {})\n input_type = template.get(\"input_type\", {}).get(\"value\", \"Text\")\n if input_type not in OPERATIONS_BY_TYPE:\n input_type = \"Text\"\n\n # Filter the operation picker to the saved input type.\n if \"operation\" in template:\n template[\"operation\"][\"options\"] = OPERATIONS_BY_TYPE[input_type]\n\n # Re-derive the outputs from the saved input type + operation.\n operation_value = template.get(\"operation\", {}).get(\"value\", [])\n if self._extract_operation_name(operation_value):\n self.update_outputs(new_frontend_node, \"operation\", operation_value)\n else:\n self.update_outputs(new_frontend_node, \"input_type\", input_type)\n\n return new_frontend_node\n\n # ==================================================================\n # Output methods (referenced by update_outputs)\n # ==================================================================\n def as_data(self) -> Data:\n \"\"\"JSON-typed output: JSON operations and Word Count.\"\"\"\n operation = self._operation_name()\n if operation in JSON_OPERATIONS:\n handler = self._json_handlers().get(operation)\n if handler:\n try:\n return handler()\n except Exception as e:\n logger.error(f\"Error executing {operation}: {e!s}\")\n raise\n if operation == \"Word Count\":\n return self._word_count_data()\n return Data(data={})\n\n def as_dataframe(self) -> DataFrame:\n \"\"\"Table-typed output: Table operations and Text to DataFrame.\"\"\"\n operation = self._operation_name()\n if operation in TABLE_OPERATIONS:\n return self._run_table_operation(operation)\n if operation == \"Text to DataFrame\":\n return self._text_to_dataframe(getattr(self, \"text_input\", \"\") or \"\")\n return DataFrame(pd.DataFrame())\n\n def as_message(self) -> Message:\n \"\"\"Message-typed output: generic text operations (and Text Join).\"\"\"\n return Message(text=self._format_result_as_text(self._run_text_operation()))\n\n def as_text(self) -> Message:\n \"\"\"Text output for the Text Join operation.\"\"\"\n return self.as_message()\n\n # ==================================================================\n # JSON operations\n # ==================================================================\n @staticmethod\n def extract_all_paths(obj, path=\"\"):\n paths = []\n if isinstance(obj, dict):\n for k, v in obj.items():\n new_path = f\"{path}.{k}\" if path else f\".{k}\"\n paths.append(new_path)\n paths.extend(OperationsComponent.extract_all_paths(v, new_path))\n elif isinstance(obj, list) and obj:\n new_path = f\"{path}[0]\"\n paths.append(new_path)\n paths.extend(OperationsComponent.extract_all_paths(obj[0], new_path))\n return paths\n\n @staticmethod\n def remove_keys_recursive(obj, keys_to_remove):\n if isinstance(obj, dict):\n return {\n k: OperationsComponent.remove_keys_recursive(v, keys_to_remove)\n for k, v in obj.items()\n if k not in keys_to_remove\n }\n if isinstance(obj, list):\n return [OperationsComponent.remove_keys_recursive(item, keys_to_remove) for item in obj]\n return obj\n\n @staticmethod\n def rename_keys_recursive(obj, rename_map):\n if isinstance(obj, dict):\n return {\n rename_map.get(k, k): OperationsComponent.rename_keys_recursive(v, rename_map) for k, v in obj.items()\n }\n if isinstance(obj, list):\n return [OperationsComponent.rename_keys_recursive(item, rename_map) for item in obj]\n return obj\n\n def _json_handlers(self) -> \"dict[str, Callable[[], Data]]\":\n return {\n \"Select Keys\": self.select_keys,\n \"Literal Eval\": self.evaluate_data,\n \"Combine\": self.combine_data,\n \"Append or Update\": self.append_update,\n \"Remove Keys\": self.remove_keys,\n \"Rename Keys\": self.rename_keys,\n \"Path Selection\": self.json_path,\n \"JQ Expression\": self.json_query,\n }\n\n def get_data_dict(self) -> dict:\n \"\"\"Extract data dictionary from Data object.\"\"\"\n data = self.data[0] if isinstance(self.data, list) and len(self.data) == 1 else self.data\n return data.model_dump()\n\n def get_normalized_data(self) -> dict:\n \"\"\"Get normalized data dictionary, handling the 'data' key if present.\"\"\"\n data_dict = self.get_data_dict()\n return data_dict.get(\"data\", data_dict)\n\n def data_is_list(self) -> bool:\n \"\"\"Check if data contains multiple items.\"\"\"\n return isinstance(self.data, list) and len(self.data) > 1\n\n def validate_single_data(self, operation: str) -> None:\n \"\"\"Validate that the operation is being performed on a single data object.\"\"\"\n if self.data_is_list():\n msg = f\"{operation} operation is not supported for multiple data objects.\"\n raise ValueError(msg)\n\n def select_keys(self) -> Data:\n \"\"\"Select specific keys from the data dictionary.\"\"\"\n self.validate_single_data(\"Select Keys\")\n data_dict = self.get_normalized_data()\n filter_criteria: list[str] = self.select_keys_input\n\n if len(filter_criteria) == 1 and filter_criteria[0] == \"data\":\n filtered = data_dict[\"data\"]\n else:\n if not all(key in data_dict for key in filter_criteria):\n msg = f\"Select key not found in data. Available keys: {list(data_dict.keys())}\"\n raise ValueError(msg)\n filtered = {key: value for key, value in data_dict.items() if key in filter_criteria}\n\n return Data(data=filtered)\n\n def remove_keys(self) -> Data:\n \"\"\"Remove specified keys from the data dictionary, recursively.\"\"\"\n self.validate_single_data(\"Remove Keys\")\n data_dict = self.get_normalized_data()\n remove_keys_input: list[str] = self.remove_keys_input\n filtered = OperationsComponent.remove_keys_recursive(data_dict, set(remove_keys_input))\n return Data(data=filtered)\n\n def rename_keys(self) -> Data:\n \"\"\"Rename keys in the data dictionary, recursively.\"\"\"\n self.validate_single_data(\"Rename Keys\")\n data_dict = self.get_normalized_data()\n rename_keys_input: dict[str, str] = self.rename_keys_input\n renamed = OperationsComponent.rename_keys_recursive(data_dict, rename_keys_input)\n return Data(data=renamed)\n\n def recursive_eval(self, data: Any) -> Any:\n \"\"\"Recursively evaluate string values that look like Python literals.\"\"\"\n if isinstance(data, dict):\n return {k: self.recursive_eval(v) for k, v in data.items()}\n if isinstance(data, list):\n return [self.recursive_eval(item) for item in data]\n if isinstance(data, str):\n try:\n if (\n data.strip().startswith((\"{\", \"[\", \"(\", \"'\", '\"'))\n or data.strip().lower() in (\"true\", \"false\", \"none\")\n or data.strip().replace(\".\", \"\").isdigit()\n ):\n return ast.literal_eval(data)\n except (ValueError, SyntaxError, TypeError, MemoryError):\n return data\n else:\n return data\n return data\n\n def evaluate_data(self) -> Data:\n \"\"\"Evaluate string values in the data dictionary.\"\"\"\n self.validate_single_data(\"Literal Eval\")\n logger.info(\"evaluating data\")\n return Data(**self.recursive_eval(self.get_data_dict()))\n\n def combine_data(self) -> Data:\n \"\"\"Combine multiple data objects into one.\"\"\"\n logger.info(\"combining data\")\n if not self.data_is_list():\n return self.data[0] if self.data else Data(data={})\n\n data_dicts = [data.model_dump().get(\"data\", data.model_dump()) for data in self.data]\n combined_data: dict[str, Any] = {}\n\n for data_dict in data_dicts:\n for key, value in data_dict.items():\n if key not in combined_data:\n combined_data[key] = value\n elif isinstance(combined_data[key], list):\n if isinstance(value, list):\n combined_data[key].extend(value)\n else:\n combined_data[key].append(value)\n else:\n combined_data[key] = (\n [combined_data[key], value] if not isinstance(value, list) else [combined_data[key], *value]\n )\n\n return Data(**combined_data)\n\n def append_update(self) -> Data:\n \"\"\"Append or update the data with new key-value pairs.\"\"\"\n self.validate_single_data(\"Append or Update\")\n data_filtered = self.get_normalized_data()\n for key, value in self.append_update_data.items():\n data_filtered[key] = value\n return Data(**data_filtered)\n\n def json_path(self) -> Data:\n \"\"\"Extract a value from the data using the selected JQ path.\"\"\"\n try:\n import jq\n except ImportError:\n msg = \"jq is required for Path Selection. Install with: pip install jq\"\n raise ImportError(msg) from None\n\n try:\n if not self.data or not self.selected_key:\n msg = \"Missing input data or selected key.\"\n raise ValueError(msg)\n input_payload = self.data[0].data if isinstance(self.data, list) else self.data.data\n validate_jq_program(self.selected_key)\n compiled = jq.compile(self.selected_key)\n result = compiled.input(input_payload).first()\n if isinstance(result, dict):\n return Data(data=result)\n return Data(data={\"result\": result})\n except (ValueError, TypeError, KeyError) as e:\n self.status = f\"Error: {e!s}\"\n self.log(self.status)\n return Data(data={\"error\": str(e)})\n\n def json_query(self) -> Data:\n \"\"\"Run a JQ expression against the data.\"\"\"\n try:\n import jq\n except ImportError:\n msg = \"jq is required for JQ Expression. Install with: pip install jq\"\n raise ImportError(msg) from None\n\n if not self.query or not self.query.strip():\n msg = \"JSON Query is required and cannot be blank.\"\n raise ValueError(msg)\n raw_data = self.get_data_dict()\n try:\n input_str = json.dumps(raw_data)\n repaired = repair_json(input_str)\n data_json = json.loads(repaired)\n jq_input = data_json[\"data\"] if isinstance(data_json, dict) and \"data\" in data_json else data_json\n validate_jq_program(self.query)\n results = jq.compile(self.query).input(jq_input).all()\n if not results:\n msg = \"No result from JSON query.\"\n raise ValueError(msg)\n result = results[0] if len(results) == 1 else results\n if result is None or result == \"None\":\n msg = \"JSON query returned null/None. Check if the path exists in your data.\"\n raise ValueError(msg)\n if isinstance(result, dict):\n return Data(data=result)\n return Data(data={\"result\": result})\n except (ValueError, TypeError, KeyError, json.JSONDecodeError) as e:\n logger.error(f\"JSON Query failed: {e}\")\n msg = f\"JSON Query error: {e}\"\n raise ValueError(msg) from e\n\n # ==================================================================\n # Table operations\n # ==================================================================\n def _get_primary_dataframe(self) -> DataFrame:\n \"\"\"Get the first DataFrame from input (handles both single and list inputs).\"\"\"\n if isinstance(self.df, list):\n return self.df[0].copy() if self.df else DataFrame()\n return self.df.copy()\n\n def _run_table_operation(self, operation: str) -> DataFrame:\n # Merge and Concatenate use their own inputs, not the primary df.\n if operation == \"Merge\":\n return self.merge_dataframes()\n if operation == \"Concatenate\":\n return self.concatenate_dataframes()\n\n df_copy = self._get_primary_dataframe()\n table_handlers = {\n \"Filter\": self.filter_rows_by_value,\n \"Sort\": self.sort_by_column,\n \"Drop Column\": self.drop_column,\n \"Rename Column\": self.rename_column,\n \"Add Column\": self.add_column,\n \"Select Columns\": self.select_columns,\n \"Head\": self.head,\n \"Tail\": self.tail,\n \"Replace Value\": self.replace_values,\n \"Drop Duplicates\": self.drop_duplicates,\n }\n handler = table_handlers.get(operation)\n if handler is None:\n msg = f\"Unsupported operation: {operation}\"\n logger.error(msg)\n raise ValueError(msg)\n return handler(df_copy)\n\n @staticmethod\n def _comparable_filter_value(column: pd.Series, filter_value: Any) -> Any:\n \"\"\"Return a text input as a number when the column is numeric.\n\n Filter and Replace Value inputs arrive as text, and ``30 == \"30\"`` never matches in pandas.\n A blank input stays text: ``pd.to_numeric(\"\")`` is NaN, which would match missing cells.\n \"\"\"\n if filter_value in (None, \"\"):\n return filter_value\n if pd.api.types.is_numeric_dtype(column) and not pd.api.types.is_bool_dtype(column):\n try:\n return pd.to_numeric(filter_value)\n except (ValueError, TypeError):\n return filter_value\n return filter_value\n\n def filter_rows_by_value(self, df: DataFrame) -> DataFrame:\n column = df[self.column_name]\n filter_value = self.filter_value\n operator = getattr(self, \"filter_operator\", \"equals\")\n\n if operator == \"equals\":\n mask = column == self._comparable_filter_value(column, filter_value)\n elif operator == \"not equals\":\n mask = column != self._comparable_filter_value(column, filter_value)\n elif operator == \"contains\":\n mask = column.astype(str).str.contains(str(filter_value), na=False)\n elif operator == \"not contains\":\n mask = ~column.astype(str).str.contains(str(filter_value), na=False)\n elif operator == \"starts with\":\n mask = column.astype(str).str.startswith(str(filter_value), na=False)\n elif operator == \"ends with\":\n mask = column.astype(str).str.endswith(str(filter_value), na=False)\n elif operator == \"greater than\":\n try:\n numeric_value = pd.to_numeric(filter_value)\n mask = column > numeric_value\n except (ValueError, TypeError):\n mask = column.astype(str) > str(filter_value)\n elif operator == \"less than\":\n try:\n numeric_value = pd.to_numeric(filter_value)\n mask = column < numeric_value\n except (ValueError, TypeError):\n mask = column.astype(str) < str(filter_value)\n else:\n mask = column == self._comparable_filter_value(column, filter_value)\n\n return DataFrame(df[mask])\n\n def sort_by_column(self, df: DataFrame) -> DataFrame:\n return DataFrame(df.sort_values(by=self.column_name, ascending=self.ascending))\n\n def drop_column(self, df: DataFrame) -> DataFrame:\n return DataFrame(df.drop(columns=[self.column_name]))\n\n def rename_column(self, df: DataFrame) -> DataFrame:\n return DataFrame(df.rename(columns={self.column_name: self.new_column_name}))\n\n def add_column(self, df: DataFrame) -> DataFrame:\n df[self.new_column_name] = [self.new_column_value] * len(df)\n return DataFrame(df)\n\n def select_columns(self, df: DataFrame) -> DataFrame:\n columns = [col.strip() for col in self.columns_to_select]\n return DataFrame(df[columns])\n\n def head(self, df: DataFrame) -> DataFrame:\n return DataFrame(df.head(self.num_rows))\n\n def tail(self, df: DataFrame) -> DataFrame:\n return DataFrame(df.tail(self.num_rows))\n\n def replace_values(self, df: DataFrame) -> DataFrame:\n column = df[self.column_name]\n replace_val = self._comparable_filter_value(column, self.replace_value)\n replacement_val = self._comparable_filter_value(column, self.replacement_value)\n try:\n result = column.replace(replace_val, replacement_val)\n except TypeError:\n if not (\n isinstance(column.dtype, pd.api.extensions.ExtensionDtype)\n and pd.api.types.is_integer_dtype(column.dtype)\n ):\n raise\n # Nullable integers reject fractional/text replacements instead of widening like NumPy columns.\n widened = column.astype(\"Float64\" if pd.api.types.is_float(replacement_val) else object)\n # A float cannot represent every Int64 value. Preserve unrelated large integers exactly.\n if not widened.astype(object).equals(column.astype(object)):\n widened = column.astype(object)\n result = widened.mask(column.eq(replace_val).fillna(value=False), replacement_val)\n df[self.column_name] = result\n return DataFrame(df)\n\n def drop_duplicates(self, df: DataFrame) -> DataFrame:\n return DataFrame(df.drop_duplicates(subset=self.column_name))\n\n def concatenate_dataframes(self) -> DataFrame:\n \"\"\"Concatenate multiple DataFrames vertically (stack rows).\"\"\"\n if not isinstance(self.df, list) or len(self.df) == 0:\n return self.df.copy() if self.df is not None else DataFrame()\n\n if len(self.df) == 1:\n return self.df[0].copy()\n\n concatenated = pd.concat(self.df, ignore_index=True)\n return DataFrame(concatenated)\n\n def merge_dataframes(self) -> DataFrame:\n \"\"\"Merge two DataFrames based on a common column (join operation).\"\"\"\n left_df = getattr(self, \"left_dataframe\", None)\n right_df = getattr(self, \"right_dataframe\", None)\n\n if left_df is None:\n return DataFrame()\n if right_df is None:\n return left_df.copy()\n\n df_left = left_df.copy()\n df_right = right_df.copy()\n\n merge_on = getattr(self, \"merge_on_column\", None)\n merge_how = getattr(self, \"merge_how\", \"inner\")\n\n # Track only columns created by this merge, without colliding with input names.\n right_columns = {}\n used_columns = set(df_left.columns) | set(df_right.columns)\n for col in df_left.columns.intersection(df_right.columns):\n if merge_on and col == merge_on:\n continue\n right_col = f\"{col}_right\"\n while right_col in used_columns:\n right_col += \"_right\"\n right_columns[col] = right_col\n used_columns.add(right_col)\n df_right = df_right.rename(columns=right_columns)\n\n if merge_on:\n if merge_on not in df_left.columns:\n msg = f\"Column '{merge_on}' not found in left DataFrame. Available: {list(df_left.columns)}\"\n raise ValueError(msg)\n if merge_on not in df_right.columns:\n msg = f\"Column '{merge_on}' not found in right DataFrame. Available: {list(df_right.columns)}\"\n raise ValueError(msg)\n merged = df_left.merge(df_right, on=merge_on, how=merge_how)\n else:\n merged = df_left.merge(df_right, left_index=True, right_index=True, how=merge_how)\n\n cols_to_drop = []\n for col, right_col in right_columns.items():\n merged[col] = merged[col].combine_first(merged[right_col])\n cols_to_drop.append(right_col)\n\n if cols_to_drop:\n merged = merged.drop(columns=cols_to_drop)\n\n return DataFrame(merged)\n\n # ==================================================================\n # Text operations\n # ==================================================================\n def _run_text_operation(self) -> Any:\n \"\"\"Process text based on the selected operation (Message/Text outputs).\"\"\"\n text = getattr(self, \"text_input\", \"\")\n operation = self._operation_name()\n\n # Allow empty text for Text Join (second input may have content).\n if not text and operation != \"Text Join\":\n return None\n\n text_handlers = {\n \"Case Conversion\": self._case_conversion,\n \"Text Replace\": self._text_replace,\n \"Text Extract\": self._text_extract,\n \"Text Head\": self._text_head,\n \"Text Tail\": self._text_tail,\n \"Text Strip\": self._text_strip,\n \"Text Join\": self._text_join,\n \"Text Clean\": self._text_clean,\n }\n handler = text_handlers.get(operation)\n if handler:\n return handler(text)\n return text\n\n def _word_count_data(self) -> Data:\n \"\"\"Word Count operation result as a Data object.\"\"\"\n result = self._word_count(getattr(self, \"text_input\", \"\") or \"\")\n return Data(data=result)\n\n def _word_count(self, text: str) -> dict[str, Any]:\n \"\"\"Count words, characters, and lines in text.\"\"\"\n result: dict[str, Any] = {}\n text_str = str(text) if text else \"\"\n is_empty = not text_str or not text_str.strip()\n\n if getattr(self, \"count_words\", True):\n if is_empty:\n result[\"word_count\"] = 0\n result[\"unique_words\"] = 0\n else:\n words = text_str.split()\n result[\"word_count\"] = len(words)\n result[\"unique_words\"] = len(set(words))\n\n if getattr(self, \"count_characters\", True):\n if is_empty:\n result[\"character_count\"] = 0\n result[\"character_count_no_spaces\"] = 0\n else:\n result[\"character_count\"] = len(text_str)\n result[\"character_count_no_spaces\"] = len(text_str.replace(\" \", \"\"))\n\n if getattr(self, \"count_lines\", True):\n if is_empty:\n result[\"line_count\"] = 0\n result[\"non_empty_lines\"] = 0\n else:\n lines = text_str.split(\"\\n\")\n result[\"line_count\"] = len(lines)\n result[\"non_empty_lines\"] = len([line for line in lines if line.strip()])\n\n return result\n\n def _text_to_dataframe(self, text: str) -> DataFrame:\n \"\"\"Convert markdown-style table text to a DataFrame.\"\"\"\n lines = [line.strip() for line in text.strip().split(\"\\n\") if line.strip()]\n if not lines:\n return DataFrame(pd.DataFrame())\n\n separator = getattr(self, \"table_separator\", \"|\")\n has_header = getattr(self, \"has_header\", True)\n\n rows = self._parse_table_rows(lines, separator, has_header=has_header)\n if not rows:\n return DataFrame(pd.DataFrame())\n\n df = self._create_dataframe(rows, has_header=has_header)\n self._convert_numeric_columns(df)\n self.log(f\"Converted text to DataFrame: {len(df)} rows, {len(df.columns)} columns\")\n return DataFrame(df)\n\n def _parse_table_rows(self, lines: list[str], separator: str, *, has_header: bool = True) -> list[list[str]]:\n rows = []\n for index, line in enumerate(lines):\n cleaned_line = line.strip(separator)\n cells = [cell.strip() for cell in cleaned_line.split(separator)]\n # Skip the markdown delimiter row under the header instead of reading it as data.\n if has_header and index == 1 and all(MARKDOWN_DELIMITER_CELL.fullmatch(cell) for cell in cells):\n continue\n rows.append(cells)\n return rows\n\n def _create_dataframe(self, rows: list[list[str]], *, has_header: bool) -> pd.DataFrame:\n if has_header and rows:\n header = rows[0]\n data_rows = rows[1:]\n header_col_count = len(header)\n for i, row in enumerate(data_rows):\n row_col_count = len(row)\n if row_col_count != header_col_count:\n msg = (\n f\"Header mismatch: {header_col_count} column(s) in header vs \"\n f\"{row_col_count} column(s) in data row {i + 1}. \"\n \"Please ensure the header has the same number of columns as your data.\"\n )\n raise ValueError(msg)\n return pd.DataFrame(data_rows, columns=header)\n\n max_cols = max(len(row) for row in rows) if rows else 0\n columns = [f\"col_{i}\" for i in range(max_cols)]\n return pd.DataFrame(rows, columns=columns)\n\n def _convert_numeric_columns(self, df: pd.DataFrame) -> None:\n for col in df.columns:\n with contextlib.suppress(ValueError, TypeError):\n df[col] = pd.to_numeric(df[col])\n\n def _case_conversion(self, text: str) -> str:\n case_type = getattr(self, \"case_type\", \"lowercase\")\n converter = CASE_CONVERTERS.get(case_type)\n return converter(text) if converter else text\n\n def _text_replace(self, text: str) -> str:\n search_pattern = getattr(self, \"search_pattern\", \"\")\n if not search_pattern:\n return text\n replacement_text = getattr(self, \"replacement_text\", \"\")\n use_regex = getattr(self, \"use_regex\", False)\n if use_regex:\n try:\n return re.sub(search_pattern, replacement_text, text)\n except re.error as e:\n self.log(f\"Invalid regex pattern: {e}\")\n return text\n return text.replace(search_pattern, replacement_text)\n\n def _text_extract(self, text: str) -> list[str]:\n extract_pattern = getattr(self, \"extract_pattern\", \"\")\n if not extract_pattern:\n return []\n max_matches = getattr(self, \"max_matches\", 10)\n try:\n matches = re.findall(extract_pattern, text)\n except re.error as e:\n msg = f\"Invalid regex pattern '{extract_pattern}': {e}\"\n raise ValueError(msg) from e\n return matches[:max_matches] if max_matches > 0 else matches\n\n def _text_head(self, text: str) -> str:\n head_characters = getattr(self, \"head_characters\", 100)\n if head_characters < 0:\n msg = f\"Characters from Start must be a non-negative integer, got {head_characters}\"\n raise ValueError(msg)\n if head_characters == 0:\n return \"\"\n return text[:head_characters]\n\n def _text_tail(self, text: str) -> str:\n tail_characters = getattr(self, \"tail_characters\", 100)\n if tail_characters < 0:\n msg = f\"Characters from End must be a non-negative integer, got {tail_characters}\"\n raise ValueError(msg)\n if tail_characters == 0:\n return \"\"\n return text[-tail_characters:]\n\n def _text_strip(self, text: str) -> str:\n strip_mode = getattr(self, \"strip_mode\", \"both\")\n strip_characters = getattr(self, \"strip_characters\", \"\")\n text_str = str(text) if text else \"\"\n chars_to_strip = strip_characters if strip_characters else None\n if strip_mode == \"left\":\n return text_str.lstrip(chars_to_strip)\n if strip_mode == \"right\":\n return text_str.rstrip(chars_to_strip)\n return text_str.strip(chars_to_strip)\n\n def _text_join(self, text: str) -> str:\n text_input_2 = getattr(self, \"text_input_2\", \"\")\n text1 = str(text) if text else \"\"\n text2 = str(text_input_2) if text_input_2 else \"\"\n if text1 and text2:\n return f\"{text1}\\n{text2}\"\n return text1 or text2\n\n def _text_clean(self, text: str) -> str:\n result = text\n if getattr(self, \"remove_extra_spaces\", True):\n # Collapse runs of horizontal whitespace but preserve newlines so\n # that remove_empty_lines stays effective when both are enabled.\n result = re.sub(r\"[^\\S\\n]+\", \" \", result)\n if getattr(self, \"remove_special_chars\", False):\n result = re.sub(r\"[^\\w\\s]\", \"\", result)\n if getattr(self, \"remove_empty_lines\", False):\n lines = [line for line in result.split(\"\\n\") if line.strip()]\n result = \"\\n\".join(lines)\n return result\n\n def _format_result_as_text(self, result: Any) -> str:\n if result is None:\n return \"\"\n if isinstance(result, list):\n return \"\\n\".join(str(item) for item in result)\n return str(result)\n"
},
"column_name": {
"_input_type": "StrInput",
@@ -3708,10 +3702,6 @@
},
"dragging": false,
"id": "Operations-VUCJC",
- "measured": {
- "height": 80,
- "width": 192
- },
"position": {
"x": 1209.814890352602,
"y": 1833.3550221261078
@@ -3914,10 +3904,6 @@
},
"dragging": false,
"id": "OpenAICompatibleEmbedding-MloZd",
- "measured": {
- "height": 52,
- "width": 192
- },
"position": {
"x": 1481.2824937463324,
"y": 1946.082713977874
@@ -4840,10 +4826,6 @@
},
"dragging": false,
"id": "OpenSearchVectorStoreComponentMultimodalMultiEmbedding-WaE28",
- "measured": {
- "height": 188,
- "width": 192
- },
"position": {
"x": 1782.4529230544917,
"y": 1889.4261474579816
@@ -5120,10 +5102,6 @@
},
"dragging": false,
"id": "ext:openrag:OpenRAGSplitTextComponent@extra-0ttMH",
- "measured": {
- "height": 80,
- "width": 192
- },
"position": {
"x": 1480.0015861525885,
"y": 1826.6203215715343
@@ -5133,16 +5111,16 @@
}
],
"viewport": {
- "x": 112.92283618168915,
- "y": -599.3634033121324,
- "zoom": 0.48571813243964146
+ "x": -384.55512601779697,
+ "y": -1192.2699535694164,
+ "zoom": 0.805631081977362
}
},
"description": "Load your data for chat context with Retrieval Augmented Generation.",
"endpoint_name": null,
"id": "5488df7c-b93f-4f87-a446-b67028bc0813",
"is_component": false,
- "last_tested_version": "1.12.3",
+ "last_tested_version": "1.12.8",
"locked": true,
"name": "OpenSearch Ingestion Flow",
"tags": [
diff --git a/flows/openrag_agent.json b/flows/openrag_agent.json
index ae3cb5f41..3b55dd995 100644
--- a/flows/openrag_agent.json
+++ b/flows/openrag_agent.json
@@ -254,6 +254,8 @@
"targetHandle": "{œfieldNameœ:œtoolsœ,œidœ:œAgent-Nfw7uœ,œinputTypesœ:[œToolœ],œtypeœ:œotherœ}"
},
{
+ "animated": false,
+ "className": "",
"data": {
"sourceHandle": {
"dataType": "Agent",
@@ -277,6 +279,7 @@
}
},
"id": "xy-edge__Agent-Nfw7u{œdataTypeœ:œAgentœ,œidœ:œAgent-Nfw7uœ,œnameœ:œresponseœ,œoutput_typesœ:[œMessageœ]}-ChatOutput-gWl8E{œfieldNameœ:œinput_valueœ,œidœ:œChatOutput-gWl8Eœ,œinputTypesœ:[œDataœ,œJSONœ,œDataFrameœ,œTableœ,œMessageœ],œtypeœ:œotherœ}",
+ "selected": false,
"source": "Agent-Nfw7u",
"sourceHandle": "{œdataTypeœ:œAgentœ,œidœ:œAgent-Nfw7uœ,œnameœ:œresponseœ,œoutput_typesœ:[œMessageœ]}",
"target": "ChatOutput-gWl8E",
@@ -608,10 +611,6 @@
},
"dragging": false,
"id": "ChatInput-ci8VE",
- "measured": {
- "height": 52,
- "width": 192
- },
"position": {
"x": 566.8287104227669,
"y": 2025.1942793814123
@@ -648,22 +647,21 @@
"frozen": false,
"icon": "MessagesSquare",
"legacy": false,
- "lf_version": "1.9.0",
"metadata": {
- "code_hash": "84009527d08c",
+ "code_hash": "0aab1c78e1dc",
"dependencies": {
"dependencies": [
{
"name": "orjson",
- "version": "3.11.8"
+ "version": "3.11.9"
},
{
"name": "fastapi",
- "version": "0.135.1"
+ "version": "0.139.2"
},
{
"name": "lfx",
- "version": null
+ "version": "1.12.8"
}
],
"total_dependencies": 3
@@ -697,6 +695,7 @@
"clean_data": {
"_input_type": "BoolInput",
"advanced": true,
+ "api_editable": false,
"display_name": "Basic Clean Data",
"dynamic": false,
"info": "Whether to clean data before converting to string.",
@@ -716,6 +715,7 @@
},
"code": {
"advanced": true,
+ "api_editable": false,
"dynamic": true,
"fileTypes": [],
"file_path": "",
@@ -730,11 +730,12 @@
"show": true,
"title_case": false,
"type": "code",
- "value": "from collections.abc import Generator\nfrom typing import Any\n\nimport orjson\nfrom fastapi.encoders import jsonable_encoder\n\nfrom lfx.base.io.chat import ChatComponent\nfrom lfx.helpers.data import safe_convert\nfrom lfx.inputs.inputs import BoolInput, DropdownInput, HandleInput, MessageTextInput\nfrom lfx.schema.data import Data\nfrom lfx.schema.dataframe import DataFrame\nfrom lfx.schema.message import Message\nfrom lfx.schema.properties import Source\nfrom lfx.template.field.base import Output\nfrom lfx.utils.constants import (\n MESSAGE_SENDER_AI,\n MESSAGE_SENDER_NAME_AI,\n MESSAGE_SENDER_USER,\n)\n\n\nclass ChatOutput(ChatComponent):\n display_name = \"Chat Output\"\n description = \"Display a chat message in the Playground.\"\n documentation: str = \"https://docs.langflow.org/chat-input-and-output\"\n icon = \"MessagesSquare\"\n name = \"ChatOutput\"\n minimized = True\n\n inputs = [\n HandleInput(\n name=\"input_value\",\n display_name=\"Inputs\",\n info=\"Message to be passed as output.\",\n input_types=[\"Data\", \"JSON\", \"DataFrame\", \"Table\", \"Message\"],\n required=True,\n ),\n BoolInput(\n name=\"should_store_message\",\n display_name=\"Store Messages\",\n info=\"Store the message in the history.\",\n value=True,\n advanced=True,\n ),\n DropdownInput(\n name=\"sender\",\n display_name=\"Sender Type\",\n options=[MESSAGE_SENDER_AI, MESSAGE_SENDER_USER],\n value=MESSAGE_SENDER_AI,\n advanced=True,\n info=\"Type of sender.\",\n ),\n MessageTextInput(\n name=\"sender_name\",\n display_name=\"Sender Name\",\n info=\"Name of the sender.\",\n value=MESSAGE_SENDER_NAME_AI,\n advanced=True,\n ),\n MessageTextInput(\n name=\"session_id\",\n display_name=\"Session ID\",\n info=\"The session ID of the chat. If empty, the current session ID parameter will be used.\",\n advanced=True,\n ),\n MessageTextInput(\n name=\"context_id\",\n display_name=\"Context ID\",\n info=\"The context ID of the chat. Adds an extra layer to the local memory.\",\n value=\"\",\n advanced=True,\n ),\n MessageTextInput(\n name=\"data_template\",\n display_name=\"Data Template\",\n value=\"{text}\",\n advanced=True,\n info=\"Template to convert Data to Text. If left empty, it will be dynamically set to the Data's text key.\",\n ),\n BoolInput(\n name=\"clean_data\",\n display_name=\"Basic Clean Data\",\n value=True,\n advanced=True,\n info=\"Whether to clean data before converting to string.\",\n ),\n ]\n outputs = [\n Output(\n display_name=\"Output Message\",\n name=\"message\",\n method=\"message_response\",\n ),\n ]\n\n def _build_source(self, id_: str | None, display_name: str | None, source: str | None) -> Source:\n source_dict = {}\n if id_:\n source_dict[\"id\"] = id_\n if display_name:\n source_dict[\"display_name\"] = display_name\n if source:\n # Handle case where source is a ChatOpenAI object\n if hasattr(source, \"model_name\"):\n source_dict[\"source\"] = source.model_name\n elif hasattr(source, \"model\"):\n source_dict[\"source\"] = str(source.model)\n else:\n source_dict[\"source\"] = str(source)\n return Source(**source_dict)\n\n async def message_response(self) -> Message:\n # First convert the input to string if needed\n text = self.convert_to_string()\n\n # Get source properties\n source, _, display_name, source_id = self.get_properties_from_source_component()\n\n # Create or use existing Message object\n if isinstance(self.input_value, Message) and not self.is_connected_to_chat_input():\n message = self.input_value\n # Update message properties\n message.text = text\n # Preserve existing session_id from the incoming message if it exists\n existing_session_id = message.session_id\n else:\n message = Message(text=text)\n existing_session_id = None\n\n # Set message properties\n message.sender = self.sender\n message.sender_name = self.sender_name\n # Preserve session_id from incoming message, or use component/graph session_id\n message.session_id = (\n self.session_id or existing_session_id or (self.graph.session_id if hasattr(self, \"graph\") else None) or \"\"\n )\n message.context_id = self.context_id\n message.flow_id = self.graph.flow_id if hasattr(self, \"graph\") else None\n message.properties.source = self._build_source(source_id, display_name, source)\n\n # Store message if needed\n if message.session_id and self.should_store_message:\n stored_message = await self.send_message(message)\n self.message.value = stored_message\n message = stored_message\n\n # Set accumulated token usage from all upstream LLM vertices.\n # This must happen AFTER send_message() because streaming captures\n # usage from chunks and would overwrite accumulated totals.\n if hasattr(self, \"_vertex\") and self._vertex is not None:\n accumulated_usage = self._vertex._accumulate_upstream_token_usage() # noqa: SLF001\n if accumulated_usage:\n message.properties.usage = accumulated_usage\n if self.should_store_message and message.get_id():\n message = await self._update_stored_message(message)\n await self._send_message_event(message, id_=message.get_id())\n\n self.status = message\n return message\n\n def _serialize_data(self, data: Data) -> str:\n \"\"\"Serialize Data object to JSON string.\"\"\"\n # Convert data.data to JSON-serializable format\n serializable_data = jsonable_encoder(data.data)\n # Serialize with orjson, enabling pretty printing with indentation\n json_bytes = orjson.dumps(serializable_data, option=orjson.OPT_INDENT_2)\n # Convert bytes to string and wrap in Markdown code blocks\n return \"```json\\n\" + json_bytes.decode(\"utf-8\") + \"\\n```\"\n\n def _validate_input(self) -> None:\n \"\"\"Validate the input data and raise ValueError if invalid.\"\"\"\n if self.input_value is None:\n msg = \"Input data cannot be None\"\n raise ValueError(msg)\n if isinstance(self.input_value, list) and not all(\n isinstance(item, Message | Data | DataFrame | str) for item in self.input_value\n ):\n invalid_types = [\n type(item).__name__\n for item in self.input_value\n if not isinstance(item, Message | Data | DataFrame | str)\n ]\n msg = f\"Expected Data or DataFrame or Message or str, got {invalid_types}\"\n raise TypeError(msg)\n if not isinstance(\n self.input_value,\n Message | Data | DataFrame | str | list | Generator | type(None),\n ):\n type_name = type(self.input_value).__name__\n msg = f\"Expected Data or DataFrame or Message or str, Generator or None, got {type_name}\"\n raise TypeError(msg)\n\n def convert_to_string(self) -> str | Generator[Any, None, None]:\n \"\"\"Convert input data to string with proper error handling.\"\"\"\n self._validate_input()\n if isinstance(self.input_value, list):\n clean_data: bool = getattr(self, \"clean_data\", False)\n return \"\\n\".join([safe_convert(item, clean_data=clean_data) for item in self.input_value])\n if isinstance(self.input_value, Generator):\n return self.input_value\n return safe_convert(self.input_value)\n"
+ "value": "from collections.abc import Generator\nfrom typing import Any\n\nimport orjson\nfrom fastapi.encoders import jsonable_encoder\n\nfrom lfx.base.io.chat import ChatComponent\nfrom lfx.helpers.data import safe_convert\nfrom lfx.inputs.inputs import BoolInput, DropdownInput, HandleInput, MessageTextInput\nfrom lfx.schema.data import Data\nfrom lfx.schema.dataframe import DataFrame\nfrom lfx.schema.message import Message\nfrom lfx.schema.properties import Source\nfrom lfx.template.field.base import Output\nfrom lfx.utils.constants import (\n MESSAGE_SENDER_AI,\n MESSAGE_SENDER_NAME_AI,\n MESSAGE_SENDER_USER,\n)\n\n\nclass ChatOutput(ChatComponent):\n display_name = \"Chat Output\"\n description = \"Display a chat message in the Playground.\"\n documentation: str = \"https://docs.langflow.org/chat-input-and-output\"\n icon = \"MessagesSquare\"\n name = \"ChatOutput\"\n minimized = True\n\n inputs = [\n HandleInput(\n name=\"input_value\",\n display_name=\"Inputs\",\n info=\"Message to be passed as output.\",\n input_types=[\"Data\", \"JSON\", \"DataFrame\", \"Table\", \"Message\"],\n required=True,\n ),\n BoolInput(\n name=\"should_store_message\",\n display_name=\"Store Messages\",\n info=\"Store the message in the history.\",\n value=True,\n advanced=True,\n ),\n DropdownInput(\n name=\"sender\",\n display_name=\"Sender Type\",\n options=[MESSAGE_SENDER_AI, MESSAGE_SENDER_USER],\n value=MESSAGE_SENDER_AI,\n advanced=True,\n info=\"Type of sender.\",\n ),\n MessageTextInput(\n name=\"sender_name\",\n display_name=\"Sender Name\",\n info=\"Name of the sender.\",\n value=MESSAGE_SENDER_NAME_AI,\n advanced=True,\n ),\n MessageTextInput(\n name=\"session_id\",\n display_name=\"Session ID\",\n info=\"The session ID of the chat. If empty, the current session ID parameter will be used.\",\n advanced=True,\n ),\n MessageTextInput(\n name=\"context_id\",\n display_name=\"Context ID\",\n info=\"The context ID of the chat. Adds an extra layer to the local memory.\",\n value=\"\",\n advanced=True,\n ),\n MessageTextInput(\n name=\"data_template\",\n display_name=\"Data Template\",\n value=\"{text}\",\n advanced=True,\n info=\"Template to convert Data to Text. If left empty, it will be dynamically set to the Data's text key.\",\n ),\n BoolInput(\n name=\"clean_data\",\n display_name=\"Basic Clean Data\",\n value=True,\n advanced=True,\n info=\"Whether to clean data before converting to string.\",\n ),\n ]\n outputs = [\n Output(\n display_name=\"Output Message\",\n name=\"message\",\n method=\"message_response\",\n ),\n ]\n\n def _build_source(self, id_: str | None, display_name: str | None, source: str | None) -> Source:\n source_dict = {}\n if id_:\n source_dict[\"id\"] = id_\n if display_name:\n source_dict[\"display_name\"] = display_name\n if source:\n # Handle case where source is a ChatOpenAI object\n if hasattr(source, \"model_name\"):\n source_dict[\"source\"] = source.model_name\n elif hasattr(source, \"model\"):\n source_dict[\"source\"] = str(source.model)\n else:\n source_dict[\"source\"] = str(source)\n return Source(**source_dict)\n\n async def message_response(self) -> Message:\n # First convert the input to string if needed\n text = self.convert_to_string()\n\n # Get source properties\n source, _, display_name, source_id = self.get_properties_from_source_component()\n\n # Create or use existing Message object\n if isinstance(self.input_value, Message) and not self.is_connected_to_chat_input():\n message = self.input_value\n # Update message properties\n message.text = text\n # Preserve existing session_id from the incoming message if it exists\n existing_session_id = message.session_id\n else:\n message = Message(text=text)\n existing_session_id = None\n\n # Set message properties\n message.sender = self.sender\n message.sender_name = self.sender_name\n # Preserve session_id from incoming message, or use component/graph session_id\n message.session_id = (\n self.session_id or existing_session_id or (self.graph.session_id if hasattr(self, \"graph\") else None) or \"\"\n )\n message.context_id = self.context_id\n message.flow_id = self.graph.flow_id if hasattr(self, \"graph\") else None\n message.properties.source = self._build_source(source_id, display_name, source)\n\n # Store message if needed\n if message.session_id and self.should_store_message:\n stored_message = await self.send_message(message)\n self.message.value = stored_message\n message = stored_message\n\n # Set accumulated token usage from all upstream LLM vertices.\n # This must happen AFTER send_message() because streaming captures\n # usage from chunks and would overwrite accumulated totals.\n if hasattr(self, \"_vertex\") and self._vertex is not None:\n accumulated_usage = self._vertex._accumulate_upstream_token_usage() # noqa: SLF001\n if accumulated_usage:\n message.properties.usage = accumulated_usage\n if self.should_store_message and message.get_id():\n message = await self._update_stored_message(message)\n await self._send_message_event(message, id_=message.get_id())\n\n self.status = message\n return message\n\n def _serialize_data(self, data: Data) -> str:\n \"\"\"Serialize Data object to JSON string.\"\"\"\n # Convert data.data to JSON-serializable format\n serializable_data = jsonable_encoder(data.data)\n # Serialize with orjson, enabling pretty printing with indentation\n json_bytes = orjson.dumps(serializable_data, option=orjson.OPT_INDENT_2)\n # Convert bytes to string and wrap in Markdown code blocks\n return \"```json\\n\" + json_bytes.decode(\"utf-8\") + \"\\n```\"\n\n def _validate_input(self) -> None:\n \"\"\"Validate the input data and raise ValueError if invalid.\"\"\"\n if self.input_value is None:\n msg = \"Input data cannot be None\"\n raise ValueError(msg)\n if isinstance(self.input_value, list) and not all(\n isinstance(item, Message | Data | DataFrame | str) for item in self.input_value\n ):\n invalid_types = [\n type(item).__name__\n for item in self.input_value\n if not isinstance(item, Message | Data | DataFrame | str)\n ]\n msg = f\"Expected Data or DataFrame or Message or str, got {invalid_types}\"\n raise TypeError(msg)\n if not isinstance(\n self.input_value,\n Message | Data | DataFrame | str | list | Generator | type(None),\n ):\n type_name = type(self.input_value).__name__\n msg = f\"Expected Data or DataFrame or Message or str, Generator or None, got {type_name}\"\n raise TypeError(msg)\n\n def convert_to_string(self) -> str | Generator[Any, None, None]:\n \"\"\"Convert input data to string with proper error handling.\"\"\"\n self._validate_input()\n clean_data: bool = getattr(self, \"clean_data\", False)\n if isinstance(self.input_value, list):\n return \"\\n\".join([safe_convert(item, clean_data=clean_data) for item in self.input_value])\n if isinstance(self.input_value, Generator):\n return self.input_value\n return safe_convert(self.input_value, clean_data=clean_data)\n"
},
"context_id": {
"_input_type": "MessageTextInput",
"advanced": true,
+ "api_editable": false,
"display_name": "Context ID",
"dynamic": false,
"info": "The context ID of the chat. Adds an extra layer to the local memory.",
@@ -760,6 +761,7 @@
"data_template": {
"_input_type": "MessageTextInput",
"advanced": true,
+ "api_editable": false,
"display_name": "Data Template",
"dynamic": false,
"info": "Template to convert Data to Text. If left empty, it will be dynamically set to the Data's text key.",
@@ -785,6 +787,7 @@
"input_value": {
"_input_type": "HandleInput",
"advanced": false,
+ "api_editable": false,
"display_name": "Inputs",
"dynamic": false,
"info": "Message to be passed as output.",
@@ -811,6 +814,7 @@
"sender": {
"_input_type": "DropdownInput",
"advanced": true,
+ "api_editable": false,
"combobox": false,
"dialog_inputs": {},
"display_name": "Sender Type",
@@ -838,6 +842,7 @@
"sender_name": {
"_input_type": "MessageTextInput",
"advanced": true,
+ "api_editable": false,
"display_name": "Sender Name",
"dynamic": false,
"info": "Name of the sender.",
@@ -863,6 +868,7 @@
"session_id": {
"_input_type": "MessageTextInput",
"advanced": true,
+ "api_editable": false,
"display_name": "Session ID",
"dynamic": false,
"info": "The session ID of the chat. If empty, the current session ID parameter will be used.",
@@ -888,6 +894,7 @@
"should_store_message": {
"_input_type": "BoolInput",
"advanced": true,
+ "api_editable": false,
"display_name": "Store Messages",
"dynamic": false,
"info": "Store the message in the history.",
@@ -913,10 +920,6 @@
},
"dragging": false,
"id": "ChatOutput-gWl8E",
- "measured": {
- "height": 52,
- "width": 192
- },
"position": {
"x": 2299.158081073581,
"y": 1794.4902117179074
@@ -966,7 +969,7 @@
"icon": "bot",
"legacy": false,
"metadata": {
- "code_hash": "52a387b4d967",
+ "code_hash": "14306d4a9373",
"dependencies": {
"dependencies": [
{
@@ -975,15 +978,15 @@
},
{
"name": "langgraph",
- "version": "1.2.9"
+ "version": "1.2.14"
},
{
"name": "lfx",
- "version": "1.12.2"
+ "version": "1.12.8"
},
{
"name": "langchain_core",
- "version": "1.6.3"
+ "version": "1.7.0"
}
],
"total_dependencies": 4
@@ -1147,7 +1150,7 @@
"show": true,
"title_case": false,
"type": "code",
- "value": "from __future__ import annotations\n\nimport uuid\nfrom collections.abc import Mapping\nfrom contextlib import contextmanager\nfrom datetime import datetime, timezone\nfrom typing import TYPE_CHECKING, Any, cast\n\nfrom langchain.agents import create_agent\nfrom langchain.agents.middleware import (\n HumanInTheLoopMiddleware,\n ModelCallLimitMiddleware,\n ToolRetryMiddleware,\n)\nfrom langgraph.types import Command\n\nfrom lfx.components.models_and_agents.agent_helpers.graph_event_adapter import (\n adapt_graph_events_to_executor_shape,\n)\nfrom lfx.components.models_and_agents.agent_helpers.messages_input_builder import (\n build_initial_messages,\n)\nfrom lfx.components.models_and_agents.agent_helpers.placeholder_corrective_middleware import (\n WatsonXPlaceholderMiddleware,\n)\nfrom lfx.components.models_and_agents.agent_helpers.single_tool_call_middleware import (\n SingleToolCallMiddleware,\n)\nfrom lfx.components.models_and_agents.agent_helpers.tool_approval import ToolApprovalMixin\nfrom lfx.components.models_and_agents.agent_helpers.tool_call_id_middleware import ToolCallIDMiddleware\nfrom lfx.components.models_and_agents.memory import MemoryComponent, _safe_graph_user_id, aget_agent_chat_history\n\nif TYPE_CHECKING:\n from collections.abc import Awaitable, Callable\n\n from langchain_core.tools import Tool\n\n from lfx.schema.log import OnTokenFunctionType, SendMessageFunctionType\n\nfrom lfx.base.agents.agent import LCToolsAgentComponent\nfrom lfx.base.agents.callback import AgentAsyncHandler\nfrom lfx.base.agents.default_system_prompt import DEFAULT_SYSTEM_PROMPT_TEMPLATE\nfrom lfx.base.agents.events import AgentPausedError, ExceptionWithMessageError, process_agent_events\nfrom lfx.base.agents.token_callback import TokenUsageCallbackHandler\nfrom lfx.base.agents.utils import get_chat_output_sender_name\nfrom lfx.base.constants import STREAM_INFO_TEXT\nfrom lfx.base.models.unified_models import (\n get_language_model_options,\n get_llm,\n handle_model_input_update,\n)\nfrom lfx.base.models.watsonx_constants import IBM_WATSONX_URLS\nfrom lfx.components.agentics.helpers.model_config import validate_model_selection\nfrom lfx.components.helpers import CalculatorComponent, CurrentDateComponent\nfrom lfx.components.langchain_utilities.ibm_granite_handler import is_watsonx_model\nfrom lfx.components.langchain_utilities.tool_calling import ToolCallingAgentComponent\nfrom lfx.custom.custom_component.component import get_component_toolkit\nfrom lfx.field_typing.range_spec import RangeSpec\nfrom lfx.inputs.inputs import BoolInput, DropdownInput, ModelInput, StrInput\nfrom lfx.io import IntInput, MessageTextInput, MultilineInput, Output, SecretStrInput, TableInput\nfrom lfx.log.logger import logger\nfrom lfx.memory import delete_message\nfrom lfx.schema.data import Data\nfrom lfx.schema.dotdict import dotdict\nfrom lfx.schema.message import Message\nfrom lfx.schema.table import EditMode\nfrom lfx.utils.constants import MESSAGE_SENDER_AI\n\n\ndef set_advanced_true(component_input):\n component_input.advanced = True\n return component_input\n\n\ndef _agent_base_inputs():\n \"\"\"Return base inputs tailored to AgentComponent's create_agent path.\n\n `get_base_inputs()` returns a shared list — replace, don't mutate. We drop\n inputs that are no-ops here and override info text on the inputs whose\n semantics shifted under create_agent.\n\n `verbose` is dropped because the create_agent event stream already surfaces\n every agent step via the \"Agent Steps\" content blocks; the legacy boolean\n has nothing to toggle. Saved flows that still carry a `verbose` value just\n ignore it on load (the schema no longer declares it).\n \"\"\"\n drop = {\"verbose\"}\n overrides = {\n \"handle_parsing_errors\": BoolInput(\n name=\"handle_parsing_errors\",\n display_name=\"Handle Parse Errors\",\n value=True,\n advanced=True,\n info=(\n \"Adds tool-execution retry as a safety net. `create_agent` already \"\n \"feeds tool-call validation errors back to the LLM automatically; \"\n \"this flag layers `ToolRetryMiddleware` on top so transient tool \"\n \"runtime failures are retried (max 2 retries).\"\n ),\n ),\n \"max_iterations\": IntInput(\n name=\"max_iterations\",\n display_name=\"Max Iterations\",\n value=15,\n advanced=True,\n range_spec=RangeSpec(min=1, max=128000, step=1, step_type=\"int\"),\n info=(\n \"Maximum number of model calls the agent can make before stopping \"\n \"(maps to `ModelCallLimitMiddleware.run_limit` on the create_agent \"\n \"path). Must be at least 1 — it is a safety cap, never 'unlimited'.\"\n ),\n ),\n }\n return [overrides.get(inp.name, inp) for inp in LCToolsAgentComponent.get_base_inputs() if inp.name not in drop]\n\n\ndef _extract_text_content(value) -> str:\n \"\"\"Pull a string payload from a Message-like, AIMessage-like, or string value.\"\"\"\n if isinstance(value, str):\n return value\n text = getattr(value, \"text\", None)\n if isinstance(text, str):\n return text\n content = getattr(value, \"content\", None)\n if isinstance(content, str):\n return content\n return str(value) if value is not None else \"\"\n\n\n@contextmanager\ndef _suppress_send_message(component: Any):\n \"\"\"Temporarily replace component.send_message with a no-op for the duration of the block.\n\n Used during the structured-output prompt fallback: run_agent streams the agent's\n final answer through self.send_message (correct for message_response), but in\n json_response the orchestrator parses that text into structured Data which the\n downstream Chat Output emits — leaving the original emission in place produces a\n duplicate message in the playground. The original method is always restored on exit,\n even when the wrapped call raises.\n \"\"\"\n original = component.send_message\n\n async def _noop(message, *_args, **_kwargs):\n return message\n\n component.send_message = _noop\n try:\n yield\n finally:\n component.send_message = original\n\n\nclass AgentComponent(ToolApprovalMixin, ToolCallingAgentComponent):\n display_name: str = \"Agent\"\n description: str = \"Define the agent's instructions, then enter a task to complete using tools.\"\n documentation: str = \"https://docs.langflow.org/agents\"\n icon = \"bot\"\n beta = False\n name = \"Agent\"\n\n memory_inputs = [set_advanced_true(component_input) for component_input in MemoryComponent().inputs]\n\n inputs = [\n ModelInput(\n name=\"model\",\n display_name=\"Language Model\",\n info=\"Select your model provider\",\n real_time_refresh=True,\n required=True,\n # Agents require tool calling — the filter is honored by\n # ``handle_model_input_update`` so models that can't run with\n # tools never reach the picker (and any saved selection that\n # no longer satisfies the constraint is auto-replaced).\n filters={\"tool_calling\": True},\n ),\n SecretStrInput(\n name=\"api_key\",\n display_name=\"API Key\",\n info=\"Overrides global provider settings. Leave blank to use your pre-configured API Key.\",\n real_time_refresh=True,\n advanced=True,\n ),\n DropdownInput(\n name=\"base_url_ibm_watsonx\",\n display_name=\"watsonx API Endpoint\",\n info=\"The base URL of the API (IBM watsonx.ai only)\",\n options=IBM_WATSONX_URLS,\n value=IBM_WATSONX_URLS[0],\n combobox=True,\n show=False,\n real_time_refresh=True,\n ),\n StrInput(\n name=\"project_id\",\n display_name=\"watsonx Project ID\",\n info=\"The project ID associated with the foundation model (IBM watsonx.ai only)\",\n show=False,\n required=False,\n ),\n MultilineInput(\n name=\"system_prompt\",\n display_name=\"Agent Instructions\",\n info=(\n \"System Prompt: Initial instructions and context provided to guide the agent's behavior. \"\n \"Supports dynamic placeholders: {current_date}, {model_name}, {optional_user_context}.\"\n ),\n value=DEFAULT_SYSTEM_PROMPT_TEMPLATE,\n advanced=False,\n ),\n MessageTextInput(\n name=\"context_id\",\n display_name=\"Context ID\",\n info=\"The context ID of the chat. Adds an extra layer to the local memory.\",\n value=\"\",\n advanced=True,\n ),\n IntInput(\n name=\"n_messages\",\n display_name=\"Number of Chat History Messages\",\n value=100,\n info=\"Number of chat history messages to retrieve.\",\n advanced=True,\n show=True,\n ),\n IntInput(\n name=\"max_tokens\",\n display_name=\"Max Tokens\",\n info=\"Maximum number of tokens to generate. Set to 0 for no explicit limit. Field name varies by provider.\",\n advanced=True,\n range_spec=RangeSpec(min=0, max=128000, step=1, step_type=\"int\"),\n ),\n MultilineInput(\n name=\"format_instructions\",\n display_name=\"Output Format Instructions\",\n info=\"Generic Template for structured output formatting. Valid only with Structured response.\",\n value=(\n \"You are an AI that extracts structured JSON objects from unstructured text. \"\n \"Use a predefined schema with expected types (str, int, float, bool, dict). \"\n \"Extract ALL relevant instances that match the schema - if multiple patterns exist, capture them all. \"\n \"Fill missing or ambiguous values with defaults: null for missing values. \"\n \"Remove exact duplicates but keep variations that have different field values. \"\n \"Always return valid JSON in the expected format, never throw errors. \"\n \"If multiple objects can be extracted, return them all in the structured format.\"\n ),\n advanced=True,\n ),\n TableInput(\n name=\"output_schema\",\n display_name=\"Output Schema\",\n info=(\n \"Schema Validation: Define the structure and data types for structured output. \"\n \"No validation if no output schema.\"\n ),\n advanced=True,\n required=False,\n value=[],\n table_schema=[\n {\n \"name\": \"name\",\n \"display_name\": \"Name\",\n \"type\": \"str\",\n \"description\": \"Specify the name of the output field.\",\n \"default\": \"field\",\n \"edit_mode\": EditMode.INLINE,\n },\n {\n \"name\": \"description\",\n \"display_name\": \"Description\",\n \"type\": \"str\",\n \"description\": \"Describe the purpose of the output field.\",\n \"default\": \"description of field\",\n \"edit_mode\": EditMode.POPOVER,\n },\n {\n \"name\": \"type\",\n \"display_name\": \"Type\",\n \"type\": \"str\",\n \"edit_mode\": EditMode.INLINE,\n \"description\": (\"Indicate the data type of the output field (e.g., str, int, float, bool, dict).\"),\n \"options\": [\"str\", \"int\", \"float\", \"bool\", \"dict\"],\n \"default\": \"str\",\n },\n {\n \"name\": \"multiple\",\n \"display_name\": \"As List\",\n \"type\": \"boolean\",\n \"description\": \"Set to True if this output field should be a list of the specified type.\",\n \"default\": \"False\",\n \"edit_mode\": EditMode.INLINE,\n },\n ],\n ),\n *_agent_base_inputs(),\n # removed memory inputs from agent component\n # *memory_inputs,\n BoolInput(\n name=\"stream\",\n display_name=\"Stream\",\n info=STREAM_INFO_TEXT,\n value=True,\n advanced=True,\n ),\n BoolInput(\n name=\"add_current_date_tool\",\n display_name=\"Current Date\",\n advanced=True,\n info=\"If true, will add a tool to the agent that returns the current date.\",\n value=True,\n ),\n BoolInput(\n name=\"add_calculator_tool\",\n display_name=\"Calculator\",\n advanced=True,\n info=(\n \"If true, adds a zero-config arithmetic calculator tool to the agent \"\n \"(safe: only +, -, *, /, ** operators via AST).\"\n ),\n value=True,\n ),\n ]\n outputs = [\n Output(name=\"response\", display_name=\"Response\", method=\"message_response\"),\n Output(\n name=\"structured_response\",\n display_name=\"Structured Response\",\n method=\"json_response\",\n types=[\"Data\"],\n ),\n ]\n\n async def _additional_model_provider_policy_ids(self, purpose, parameters=None) -> tuple[str, ...]:\n \"\"\"Gate the provider selector retained by legacy Agent/ALTK flows.\"\"\"\n _ = purpose\n from lfx.base.models.provider_registry import resolve_provider_id\n\n effective_parameters = parameters if isinstance(parameters, Mapping) else getattr(self, \"_parameters\", None)\n if not isinstance(effective_parameters, Mapping):\n effective_parameters = {}\n selected_model = effective_parameters.get(\"model\", getattr(self, \"model\", None))\n if selected_model:\n # The shared Component hook already handles a selected ModelInput;\n # connected model objects are gated by their upstream vertex.\n return ()\n legacy_provider = effective_parameters.get(\"agent_llm\", getattr(self, \"agent_llm\", None))\n if not isinstance(legacy_provider, str) or not legacy_provider.strip() or legacy_provider == \"Custom\":\n return ()\n return (resolve_provider_id(legacy_provider),)\n\n async def _filter_legacy_provider_options(self, build_config: Mapping[str, Any]) -> None:\n \"\"\"Filter ALTK/legacy Agent provider choices through the active scope.\"\"\"\n from lfx.services.model_provider_policy import ModelProviderPolicyPurpose, aresolve_model_provider_policy\n\n provider_field = build_config.get(\"agent_llm\")\n if not isinstance(provider_field, dict):\n return\n options = provider_field.get(\"options\")\n if not isinstance(options, list):\n return\n candidates = [option for option in options if isinstance(option, str) and option != \"Custom\"]\n if not candidates:\n return\n snapshot = await aresolve_model_provider_policy(\n user_id=self.user_id,\n providers=candidates,\n purpose=ModelProviderPolicyPurpose.CONFIGURE,\n )\n allowed = set(snapshot.filter(candidates))\n keep_indexes = [index for index, option in enumerate(options) if option == \"Custom\" or option in allowed]\n provider_field[\"options\"] = [options[index] for index in keep_indexes]\n metadata = provider_field.get(\"options_metadata\")\n if isinstance(metadata, list) and len(metadata) == len(options):\n provider_field[\"options_metadata\"] = [metadata[index] for index in keep_indexes]\n\n def _resolve_selected_model(self):\n \"\"\"Resolve the selected model, including legacy agent_llm/model_name inputs.\"\"\"\n try:\n from langchain_core.language_models import BaseLanguageModel\n\n if isinstance(self.model, BaseLanguageModel):\n return self.model\n except ImportError:\n pass\n\n if isinstance(self.model, list) and self.model:\n return self.model\n\n legacy_provider = getattr(self, \"agent_llm\", None)\n legacy_model_name = getattr(self, \"model_name\", None)\n if not legacy_provider or not legacy_model_name:\n return self.model\n\n options = get_language_model_options(user_id=self.user_id)\n for option in options:\n if option.get(\"provider\") == legacy_provider and option.get(\"name\") == legacy_model_name:\n return [option]\n\n return [\n {\n \"name\": legacy_model_name,\n \"provider\": legacy_provider,\n \"metadata\": {},\n }\n ]\n\n def _get_max_tokens_value(self):\n \"\"\"Return the user-supplied max_tokens or None when unset/zero.\"\"\"\n val = getattr(self, \"max_tokens\", None)\n if val in {\"\", 0}:\n return None\n return val\n\n def _get_llm(self):\n \"\"\"Override parent to include max_tokens from the Agent's input field.\n\n Streaming is mandatory for AgentComponent: ``runnable.astream_events(v2)`` only\n emits ``on_chat_model_stream`` chunks when the underlying chat model is\n instantiated with ``streaming=True``. Unlike the LanguageModel component (where\n ``stream`` is a user-facing toggle), the Agent has no opt-out — the toggle is\n kept in the UI for backwards compatibility but is intentionally ignored here.\n Without ``stream=True``, the chat model accumulates the whole response and\n only emits ``on_chat_model_end``, silently disabling the Playground's live-\n typing view and breaking the streaming contract on the /events surface.\n \"\"\"\n return get_llm(\n model=self.model,\n user_id=self.user_id,\n api_key=getattr(self, \"api_key\", None),\n stream=True,\n max_tokens=self._get_max_tokens_value(),\n watsonx_url=getattr(self, \"base_url_ibm_watsonx\", None),\n watsonx_project_id=getattr(self, \"project_id\", None),\n overrides=getattr(self, \"_model_overrides\", None),\n )\n\n async def get_agent_requirements(self):\n \"\"\"Get the agent requirements for the agent.\"\"\"\n from langchain_core.tools import StructuredTool\n\n from lfx.services.model_provider_policy import ModelProviderPolicyPurpose\n\n await self.arequire_model_provider_policy(ModelProviderPolicyPurpose.USE)\n\n selected_model = self._resolve_selected_model()\n try:\n from langchain_core.language_models import BaseLanguageModel\n\n is_connected_model = isinstance(selected_model, BaseLanguageModel)\n except ImportError:\n is_connected_model = False\n\n if not is_connected_model:\n validate_model_selection(selected_model)\n\n # Ensure _get_llm() uses the resolved model (e.g. from legacy agent_llm/model_name)\n self.model = selected_model\n llm_model = self._get_llm()\n if llm_model is None:\n msg = \"No language model selected. Please choose a model to proceed.\"\n raise ValueError(msg)\n\n # Get memory data\n self.chat_history = await self.get_memory_data()\n await logger.adebug(f\"Retrieved {len(self.chat_history)} chat history messages\")\n if isinstance(self.chat_history, Message):\n self.chat_history = [self.chat_history]\n\n # Add current date tool if enabled\n if self.add_current_date_tool:\n if not isinstance(self.tools, list): # type: ignore[has-type]\n self.tools = []\n current_date_tool = (await CurrentDateComponent(**self.get_base_args()).to_toolkit()).pop(0)\n\n if not isinstance(current_date_tool, StructuredTool):\n msg = \"CurrentDateComponent must be converted to a StructuredTool\"\n raise TypeError(msg)\n # Skip if an externally-connected tool already provides the same name.\n # Duplicate tool names are rejected by Anthropic/Gemini with HTTP 400.\n if not any(getattr(t, \"name\", None) == current_date_tool.name for t in self.tools):\n self.tools.append(current_date_tool)\n\n # Add calculator tool if enabled (zero-config arithmetic)\n if getattr(self, \"add_calculator_tool\", False):\n if not isinstance(self.tools, list): # type: ignore[has-type]\n self.tools = []\n calculator_tool = (await CalculatorComponent(**self.get_base_args()).to_toolkit()).pop(0)\n\n if not isinstance(calculator_tool, StructuredTool):\n msg = \"CalculatorComponent must be converted to a StructuredTool\"\n raise TypeError(msg)\n # Skip if an externally-connected tool already provides the same name.\n # Duplicate tool names are rejected by Anthropic/Gemini with HTTP 400.\n if not any(getattr(t, \"name\", None) == calculator_tool.name for t in self.tools):\n self.tools.append(calculator_tool)\n\n # Set shared callbacks for tracing the tools used by the agent\n self.set_tools_callbacks(self.tools, self._get_shared_callbacks())\n\n return llm_model, self.chat_history, self.tools\n\n def _get_resolved_model_name(self) -> str:\n \"\"\"Best-effort human-readable model name for {model_name} injection.\"\"\"\n try:\n from langchain_core.language_models import BaseLanguageModel\n\n if isinstance(self.model, BaseLanguageModel):\n return type(self.model).__name__\n except ImportError:\n pass\n\n if isinstance(self.model, list) and self.model:\n first = self.model[0]\n if isinstance(first, dict):\n name = first.get(\"name\")\n if isinstance(name, str) and name:\n return name\n\n legacy_model_name = getattr(self, \"model_name\", None)\n if isinstance(legacy_model_name, str) and legacy_model_name:\n return legacy_model_name\n return \"\"\n\n def _inject_dynamic_prompt_values(self, prompt: Any | None) -> str | None:\n \"\"\"Replace known env placeholders in the system prompt.\n\n Handles {current_date}, {model_name}, and {optional_user_context} (the\n last one ships with the structured DEFAULT_SYSTEM_PROMPT_TEMPLATE and\n is currently unused at the AgentComponent layer, so it resolves to \"\").\n Uses str.replace (not str.format) so user prompts containing literal\n braces such as JSON examples ({\"key\": 1}) never break the agent.\n\n `system_prompt` is a connectable MultilineInput, so the value can arrive\n as a Message (e.g. a Prompt node wired in). Normalize it to text first —\n a raw Message has no `.replace` and used to crash the agent build.\n \"\"\"\n if prompt is None:\n return None\n prompt = _extract_text_content(prompt)\n if not prompt:\n return prompt\n replacements = {\n \"{current_date}\": datetime.now(tz=timezone.utc).strftime(\"%Y-%m-%d %H:%M:%S UTC\"),\n \"{model_name}\": self._get_resolved_model_name(),\n \"{optional_user_context}\": \"\",\n }\n for placeholder, value in replacements.items():\n prompt = prompt.replace(placeholder, value)\n return prompt\n\n def create_agent_runnable(self, *, allow_interrupts: bool = True):\n \"\"\"Build the LangGraph `CompiledStateGraph` via `langchain.agents.create_agent`.\n\n Replaces the legacy `AgentExecutor` runnable inherited from\n `ToolCallingAgentComponent`. Other agent components (tool_calling, csv, json,\n openapi, sql*, vector_store_router) keep the legacy path — only AgentComponent\n runs on the new graph API.\n\n `max_iterations` and `handle_parsing_errors` (legacy AgentExecutor knobs) are\n translated to LangGraph middleware. Without that translation those user inputs\n would silently become no-ops on the new API.\n\n Provider notes:\n - WatsonX/Granite work natively with create_agent — `ChatWatsonx.bind_tools`\n handles tool_choice correctly. The legacy `create_granite_agent` path was\n dropped because it hardcoded `tool_choice='required'`, which the WatsonX\n API now rejects.\n - Ollama and other small/local models often emit malformed tool args. The\n ToolRetryMiddleware (default `retry_on=(Exception,)`, `on_failure='continue'`)\n catches Pydantic ValidationErrors from bad args and feeds the error back\n to the LLM as a retry signal, so the agent recovers gracefully.\n \"\"\"\n llm = self._get_llm()\n tools = self.tools or []\n\n # Eager bind_tools validation. `create_agent(...)` is lazy — without this,\n # an LLM that doesn't support tool calling fails on the first user message\n # instead of when the user wires up the component, which is a much worse UX.\n # Gated on a non-empty tools list so a no-tool Agent on a plain chat model\n # (which legitimately has no `bind_tools`) isn't shut out at flow-build time.\n # Providers signal \"no tool calling\" inconsistently — `NotImplementedError`\n # (langchain default), `AttributeError` (no `bind_tools` attr), or `TypeError`\n # (signature mismatch). Treat all three as the same UX failure.\n if tools:\n try:\n llm.bind_tools(tools)\n except (NotImplementedError, AttributeError, TypeError) as exc:\n # Include the underlying error so a broken tool schema or a\n # provider implementation bug is not silently disguised as a\n # \"model can't call tools\" UX error.\n msg = (\n f\"{self.display_name} does not support tool calling, \"\n \"or one of the connected tools failed to bind. \"\n \"Please connect a tool-calling capable language model and \"\n f\"verify your tools are well-formed. Underlying error: {exc!s}\"\n )\n raise NotImplementedError(msg) from exc\n\n middleware = self._build_middleware(llm, allow_interrupts=allow_interrupts)\n checkpointer = self._build_agent_checkpointer() if allow_interrupts else None\n return create_agent(\n model=llm,\n tools=tools,\n system_prompt=self.system_prompt or \"\",\n middleware=middleware or None,\n checkpointer=checkpointer,\n )\n\n def _compute_recursion_limit(self) -> int:\n \"\"\"Derive the LangGraph recursion_limit from the user-set max_iterations.\n\n Mirrors the clamp in `_build_middleware` (max(1, max_iterations)) so a\n saved 0 or negative value cannot under-cap the graph below one full\n iteration. The +5 buffer covers start/end/router overhead.\n \"\"\"\n raw = getattr(self, \"max_iterations\", None)\n run_limit = max(1, int(raw)) if raw is not None else 15\n return run_limit * 2 + 5\n\n def _build_middleware(self, llm: Any, *, allow_interrupts: bool = True) -> list:\n # `llm` is passed in (rather than re-fetched via `self._get_llm()`)\n # because some providers do credential resolution / client instantiation\n # lazily on each call. The caller — `create_agent_runnable` — already\n # resolved it once for `bind_tools`, so reuse that instance here.\n middleware: list = []\n # LangChain accepts missing IDs on AIMessage.tool_calls, but LangGraph's\n # invalid-call path and ToolRetryMiddleware both require a string when\n # they construct an error ToolMessage. Normalize at the model boundary\n # so either recovery path can return the error to the model instead of\n # crashing the flow.\n if self.tools:\n middleware.append(ToolCallIDMiddleware())\n max_iterations = getattr(self, \"max_iterations\", None)\n if max_iterations is not None:\n # `max_iterations` is a safety cap, not an \"unlimited\" toggle. A saved\n # 0 or negative value (falsy) must NOT silently drop the limiter and\n # allow an unbounded model/tool loop — clamp it to a real minimum.\n run_limit = max(1, int(max_iterations))\n middleware.append(ModelCallLimitMiddleware(run_limit=run_limit))\n # ToolRetryMiddleware only matters when there ARE tools to retry. Attaching\n # it on a no-tools agent inflates the compiled graph and adds per-invocation\n # middleware overhead for nothing, which is a measurable contributor to\n # trivial-prompt latency (QA UI-003).\n if getattr(self, \"handle_parsing_errors\", False) and self.tools:\n middleware.append(ToolRetryMiddleware(max_retries=2))\n # WatsonX models have two known platform quirks; both still reproduce on\n # the current API, so we keep the protections from the legacy\n # `create_granite_agent` path.\n # 1. Multi-tool-call assistant turns are rejected (\"This model only\n # supports single tool-calls at once!\"). Clamp to one per turn.\n # 2. Tool args occasionally come back as literal placeholder strings\n # (e.g. `<result-from-search>`). Re-invoke once with a corrective\n # SystemMessage.\n # Order: SingleToolCallMiddleware first (outermost) so the clamp is\n # applied to the final response, including any corrective re-invoke\n # produced by WatsonXPlaceholderMiddleware.\n if is_watsonx_model(llm):\n middleware.append(SingleToolCallMiddleware())\n middleware.append(WatsonXPlaceholderMiddleware())\n # Human-in-the-loop: attach only when a tool is gated AND interrupts are allowed\n # (the structured-output path disables them), keeping ungated flows unchanged.\n interrupt_on = self._gated_interrupt_on() if allow_interrupts else {}\n if interrupt_on:\n middleware.append(HumanInTheLoopMiddleware(interrupt_on=interrupt_on))\n return middleware\n\n async def run_agent(self, agent) -> Message:\n \"\"\"Run the LangGraph `CompiledStateGraph` and return the final agent Message.\n\n Overrides the legacy `LCAgentComponent.run_agent` (which builds an\n `{\"input\": str, \"chat_history\": [...]}` dict for `AgentExecutor`). The graph\n wants `{\"messages\": [BaseMessage, ...]}`. The event stream is wrapped with\n `adapt_graph_events_to_executor_shape` so the legacy `process_agent_events`\n (in `lfx.base.agents.events`) can be reused unchanged.\n \"\"\"\n messages = build_initial_messages(\n input_value=self.input_value,\n chat_history=getattr(self, \"chat_history\", None),\n )\n input_dict = {\"messages\": messages}\n\n agent_message = self._build_initial_agent_message()\n token_usage_handler = TokenUsageCallbackHandler()\n\n # Stream tokens to the event manager when running inside the Langflow runtime.\n # This is what powers the live-typing view in the chat UI.\n on_token_callback: OnTokenFunctionType | None = None\n if getattr(self, \"_event_manager\", None):\n on_token_callback = cast(\"OnTokenFunctionType\", self._event_manager.on_token)\n\n # Align LangGraph's `recursion_limit` with `max_iterations` so the\n # middleware cap (ModelCallLimitMiddleware) is what bounds the loop —\n # not LangGraph's default 25-step guard, which fires at ~12 model+tool\n # iterations and raises a raw GraphRecursionError (QA UI-009/UI-010).\n # Each iteration is ~2 graph steps (model node + tools node); add 5\n # for start/end overhead.\n recursion_limit = self._compute_recursion_limit()\n\n agent_config: dict[str, Any] = {\n \"callbacks\": [\n AgentAsyncHandler(self.log),\n token_usage_handler,\n *self._get_shared_callbacks(),\n ],\n \"recursion_limit\": recursion_limit,\n }\n # The durable checkpointer keys on the per-run thread_id; it must be in the\n # astream_events config (not just create_agent) for both initial run and resume.\n thread_id = self._agent_thread_id()\n get_pending_interrupt = None\n stream_input: Any = input_dict\n # A checkpointer is only present when the agent was built with interrupts enabled\n # (the structured-output path builds without one); never probe its state otherwise.\n interrupts_enabled = getattr(agent, \"checkpointer\", None) is not None\n if interrupts_enabled and thread_id and self._gated_interrupt_on():\n agent_config[\"configurable\"] = {\"thread_id\": thread_id}\n get_pending_interrupt = self._pending_interrupt_getter(agent, agent_config)\n if self._has_candidate_decision(thread_id):\n # The injected decision must match the pending interrupt's nonce, so read\n # the interrupt first; a matched decision resumes the checkpointed thread.\n value, interrupt_id = await self._read_pending_interrupt(agent, agent_config)\n decision = self._injected_agent_decision(thread_id, interrupt_id)\n if decision is not None:\n action_requests = (value or {}).get(\"action_requests\") or []\n stream_input = Command(\n resume={\"decisions\": self._build_resume_decisions(decision, action_requests)}\n )\n stream = adapt_graph_events_to_executor_shape(\n agent.astream_events(stream_input, config=agent_config, version=\"v2\")\n )\n try:\n result = await process_agent_events(\n stream,\n agent_message,\n cast(\"SendMessageFunctionType\", self.send_message),\n on_token_callback,\n get_pending_interrupt=get_pending_interrupt,\n )\n except AgentPausedError as e:\n # Why: retract the empty partial bubble (leaks as \"[]\"); the HITL card supersedes it, resume re-emits it.\n paused_message = e.agent_message or agent_message\n msg_id = paused_message.get_id()\n if msg_id:\n await delete_message(id_=msg_id)\n await self._send_message_event(paused_message, category=\"remove_message\")\n return self._suspend_for_tool_approval(e.request, paused_message)\n except ExceptionWithMessageError as e:\n # Drop the half-stored partial message from the DB (only if it was\n # actually persisted) and tell the frontend to remove the stale bubble.\n if hasattr(e, \"agent_message\"):\n msg_id = e.agent_message.get_id()\n if msg_id:\n await delete_message(id_=msg_id)\n await self._send_message_event(e.agent_message, category=\"remove_message\")\n # exception(), not error(f\"...{e}\"): this class's str() interpolates the model's\n # partial completion, and passing the exception rather than formatting it is what\n # gives the exported record an error.type to triage on.\n logger.exception(\"Agent run failed after a partial message was emitted\")\n raise\n\n usage_data = token_usage_handler.get_usage()\n if usage_data:\n self._token_usage = usage_data\n result.properties.usage = usage_data\n # Only round-trip the DB when the message was stored (Chat Output wired).\n # `_should_skip_message=True` leaves `result.get_id()` empty; persisting\n # then would create a phantom row.\n if result.get_id():\n stored_result = await self._update_stored_message(result)\n await self._send_message_event(stored_result)\n result = stored_result\n\n self.status = result\n return result\n\n def _build_initial_agent_message(self) -> Message:\n \"\"\"Construct the placeholder agent Message that `process_agent_events` mutates.\"\"\"\n if hasattr(self, \"graph\"):\n session_id = self.graph.session_id\n elif hasattr(self, \"_session_id\"):\n session_id = self._session_id\n else:\n session_id = None\n\n sender_name = get_chat_output_sender_name(self) or self.display_name or \"AI\"\n return Message(\n sender=MESSAGE_SENDER_AI,\n sender_name=sender_name,\n properties={\"icon\": \"Bot\", \"state\": \"partial\"},\n # `text=\"\"` sentinel so MessageTable's no_content check accepts\n # an in-flight agent message whose content_blocks haven't been\n # populated yet. Mirrors ChatInput's convention.\n text=\"\",\n # Flat chronological event log; see lfx.base.agents.events.\n content_blocks=[],\n session_id=session_id or uuid.uuid4(),\n )\n\n def _selected_model_remediation_context(self) -> tuple[str | None, str | None, Any | None]:\n \"\"\"Return provider/name plus a connected model target, when present.\"\"\"\n try:\n selected = self._resolve_selected_model()\n if isinstance(selected, list) and selected and isinstance(selected[0], dict):\n return selected[0].get(\"provider\"), selected[0].get(\"name\"), None\n\n from langchain_core.language_models import BaseLanguageModel\n\n if isinstance(selected, BaseLanguageModel):\n model_name = None\n for attr in (\"model_name\", \"model\", \"model_id\"):\n value = getattr(selected, attr, None)\n if isinstance(value, str) and value:\n model_name = value\n break\n return self._connected_model_provider(selected), model_name, selected\n except (AttributeError, TypeError, ValueError, KeyError, ImportError):\n pass\n return None, None, None\n\n def _connected_model_provider(self, model: Any) -> str | None:\n \"\"\"Resolve a connected model's provider from the source component.\n\n Runtime model classes are not provider identities: OpenAI, OpenRouter,\n and compatible endpoints can all produce ``ChatOpenAI``. The incoming\n model edge preserves the source component, so prefer its explicit\n provider override or selected-model metadata, then its provider display\n name. If the Agent is used without graph provenance, leave the provider\n unknown so provider-scoped remediations remain disabled.\n \"\"\"\n vertex = getattr(self, \"_vertex\", None)\n if vertex is None:\n return None\n source_id = vertex.get_incoming_edge_by_target_param(\"model\")\n if not source_id:\n return None\n source = vertex.graph.get_vertex(source_id)\n component = getattr(source, \"custom_component\", None)\n if component is None:\n return None\n\n candidate = getattr(component, \"provider\", None)\n\n if not isinstance(candidate, str) or not candidate:\n selected_model = getattr(component, \"model\", None)\n if isinstance(selected_model, list) and selected_model and isinstance(selected_model[0], dict):\n candidate = selected_model[0].get(\"provider\")\n\n if not isinstance(candidate, str) or not candidate:\n candidate = getattr(component, \"display_name\", None)\n if not isinstance(candidate, str) or not candidate:\n return None\n\n from lfx.base.models.unified_models.provider_queries import get_model_provider_metadata\n\n provider_metadata = get_model_provider_metadata().get(candidate, {})\n expected_class = provider_metadata.get(\"mapping\", {}).get(\"model_class\")\n model_classes = {base.__name__ for base in type(model).__mro__}\n return candidate if expected_class in model_classes else None\n\n async def _run_agent_with_model_remediation(\n self,\n run_once: Callable[[], Awaitable[Message]],\n ) -> Message:\n \"\"\"Run one Agent operation, retrying safe provider-validation failures.\n\n Registered remediations must identify request-validation failures that\n occur before tool execution. A failure that can happen after a tool runs\n must instead retry at the model-call boundary to avoid repeating tool\n side effects.\n \"\"\"\n from lfx.base.models.model_remediation import apply_overrides_to_model, find_remediation, remember\n\n provider, model_name, connected_model = self._selected_model_remediation_context()\n applied: set[str] = set()\n while True:\n try:\n result = await run_once()\n except (ValueError, TypeError, KeyError):\n await logger.aexception(\"Agent run failed\")\n raise\n except Exception as exc:\n # run_agent may wrap the provider error in ExceptionWithMessageError, whose\n # str() carries the model's partial completion. Matching on it locally is fine;\n # logging it is not, so the record below passes the exception instead.\n error_text = f\"{exc} {getattr(exc, '__cause__', '') or ''}\"\n remediation = find_remediation(error_text, provider, already_applied=applied)\n if remediation is None:\n await logger.aexception(\"Agent run failed with no remediation available\")\n raise\n if connected_model is not None and not apply_overrides_to_model(connected_model, remediation.overrides):\n await logger.aerror(\n f\"model.remediation.unapplied name={remediation.name} provider={provider} model={model_name}\"\n )\n raise\n applied.add(remediation.name)\n if connected_model is None:\n self._model_overrides = {\n **(getattr(self, \"_model_overrides\", None) or {}),\n **remediation.overrides,\n }\n else:\n # Connected outputs are shared objects across downstream flow\n # branches. The mutation is intentionally flow-scoped: sibling\n # branches holding this model will see the matched override too.\n await logger.adebug(\n f\"model.remediation.shared_model name={remediation.name} provider={provider} model={model_name}\"\n )\n await logger.awarning(\n f\"model.remediation.applied name={remediation.name} provider={provider} model={model_name}\"\n )\n else:\n if connected_model is None and getattr(self, \"_model_overrides\", None):\n remember(provider, model_name, self._model_overrides)\n return result\n\n async def message_response(self) -> Message:\n async def _run_once() -> Message:\n llm_model, self.chat_history, self.tools = await self.get_agent_requirements()\n self.set(\n llm=llm_model,\n tools=self.tools or [],\n chat_history=self.chat_history,\n input_value=self.input_value,\n system_prompt=self._inject_dynamic_prompt_values(self.system_prompt),\n )\n agent = self.create_agent_runnable()\n return await self.run_agent(agent)\n\n result = await self._run_agent_with_model_remediation(_run_once)\n self._agent_result = result\n return result\n\n async def json_response(self) -> Data:\n \"\"\"Produce structured Data via native LLM structured output, with prompt-based fallback.\n\n Native path (no tools, llm has with_structured_output) bypasses the agent loop and\n returns provider-validated JSON. When tools are attached, falls back to running the\n agent with a schema-augmented system prompt and parsing the final message content.\n \"\"\"\n from lfx.components.models_and_agents.structured_output.structured_output_orchestrator import (\n orchestrate_structured_output,\n )\n\n try:\n llm_model, self.chat_history, self.tools = await self.get_agent_requirements()\n except (ValueError, TypeError) as exc:\n await logger.aexception(\"json_response.requirements_failed\")\n return Data(data={\"content\": \"\", \"error\": str(exc)})\n\n injected_system_prompt = self._inject_dynamic_prompt_values(getattr(self, \"system_prompt\", \"\") or \"\") or \"\"\n format_instructions = getattr(self, \"format_instructions\", \"\") or \"\"\n output_schema = getattr(self, \"output_schema\", None) or []\n has_tools = bool(self.tools)\n\n async def _run_agent_for_fallback(augmented_prompt: str) -> str:\n first_attempt = True\n\n async def _run_once() -> Message:\n nonlocal first_attempt, llm_model\n if first_attempt:\n first_attempt = False\n else:\n llm_model, self.chat_history, self.tools = await self.get_agent_requirements()\n self.set(\n llm=llm_model,\n tools=self.tools or [],\n chat_history=self.chat_history,\n input_value=self.input_value,\n system_prompt=augmented_prompt,\n )\n # Structured output cannot suspend mid-parse: disable tool-approval interrupts.\n agent_runnable = self.create_agent_runnable(allow_interrupts=False)\n return await self.run_agent(agent_runnable)\n\n with _suppress_send_message(self):\n result = await self._run_agent_with_model_remediation(_run_once)\n return _extract_text_content(result)\n\n try:\n return await orchestrate_structured_output(\n llm=llm_model,\n output_schema=output_schema,\n system_prompt=injected_system_prompt,\n format_instructions=format_instructions,\n input_value=_extract_text_content(self.input_value),\n run_prompt_fallback=_run_agent_for_fallback,\n prefer_native=not has_tools,\n )\n except (\n ExceptionWithMessageError,\n ValueError,\n TypeError,\n NotImplementedError,\n AttributeError,\n ) as exc:\n await logger.aexception(\"json_response.orchestration_failed\")\n return Data(data={\"content\": \"\", \"error\": str(exc)})\n\n async def get_memory_data(self):\n # Scope by flow_id so default playground session names (e.g. \"New Session 0\")\n # cannot leak chat history across unrelated flows. See issue #13059.\n # The helper also returns [] when n_messages == 0, preserving the\n # explicit \"memory disabled\" contract from MemoryComponent.retrieve_messages.\n messages = await aget_agent_chat_history(\n session_id=self.graph.session_id,\n flow_id=getattr(self.graph, \"flow_id\", None),\n context_id=self.context_id,\n n_messages=self.n_messages,\n user_id=_safe_graph_user_id(self),\n )\n return [\n message for message in messages if getattr(message, \"id\", None) != getattr(self.input_value, \"id\", None)\n ]\n\n def update_input_types(self, build_config: dotdict) -> dotdict:\n \"\"\"Update input types for all fields in build_config.\"\"\"\n for key, value in build_config.items():\n if isinstance(value, dict):\n if value.get(\"input_types\") is None:\n build_config[key][\"input_types\"] = []\n elif hasattr(value, \"input_types\") and value.input_types is None:\n value.input_types = []\n return build_config\n\n async def update_build_config(\n self,\n build_config: dotdict,\n field_value: list[dict],\n field_name: str | None = None,\n ) -> dotdict:\n from lfx.services.model_provider_policy import ModelProviderPolicyPurpose\n\n policy_parameters = dict(getattr(self, \"_parameters\", {}) or {})\n if field_name:\n policy_parameters[field_name] = field_value\n await self.arequire_model_provider_policy(\n ModelProviderPolicyPurpose.CONFIGURE,\n parameters=policy_parameters,\n )\n # Update model options with caching (for all field changes).\n # The tool-calling constraint lives on the ModelInput's ``filters``\n # field (declared above); ``handle_model_input_update`` reads it\n # and applies the filter to both the dropdown options and the\n # sticky-default re-injection path.\n build_config = handle_model_input_update(\n component=self,\n build_config=dict(build_config),\n field_value=field_value,\n field_name=field_name,\n )\n build_config = dotdict(build_config)\n\n if field_name == \"model\":\n build_config = self.update_input_types(build_config)\n\n # Validate required keys. `verbose` was dropped from the input set\n # (see `_agent_base_inputs` — the create_agent event stream already\n # surfaces every step), so it is intentionally NOT required here.\n # Saved flows that still carry a `verbose` value just ignore it on\n # load.\n default_keys = [\n \"code\",\n \"_type\",\n \"model\",\n \"tools\",\n \"input_value\",\n \"add_current_date_tool\",\n \"add_calculator_tool\",\n \"system_prompt\",\n \"max_iterations\",\n \"handle_parsing_errors\",\n ]\n missing_keys = [key for key in default_keys if key not in build_config]\n if missing_keys:\n msg = f\"Missing required keys in build_config: {missing_keys}\"\n raise ValueError(msg)\n await self._filter_legacy_provider_options(build_config)\n return dotdict({k: v.to_dict() if hasattr(v, \"to_dict\") else v for k, v in build_config.items()})\n\n async def _get_tools(self) -> list[Tool]:\n component_toolkit = get_component_toolkit()\n\n tools = component_toolkit(component=self).get_tools(\n tool_name=\"Call_Agent\",\n # here we do not use the shared callbacks as we are exposing the agent as a tool\n callbacks=self.get_langchain_callbacks(),\n )\n if hasattr(self, \"tools_metadata\"):\n tools = component_toolkit(component=self, metadata=self.tools_metadata).update_tools_metadata(tools=tools)\n\n return tools\n"
+ "value": "from __future__ import annotations\n\nimport uuid\nfrom collections.abc import Mapping\nfrom contextlib import contextmanager\nfrom datetime import datetime, timezone\nfrom typing import TYPE_CHECKING, Any, cast\n\nfrom langchain.agents import create_agent\nfrom langchain.agents.middleware import (\n HumanInTheLoopMiddleware,\n ModelCallLimitMiddleware,\n ToolRetryMiddleware,\n)\nfrom langgraph.types import Command\n\nfrom lfx.components.models_and_agents.agent_helpers.graph_event_adapter import (\n adapt_graph_events_to_executor_shape,\n)\nfrom lfx.components.models_and_agents.agent_helpers.messages_input_builder import (\n build_initial_messages,\n)\nfrom lfx.components.models_and_agents.agent_helpers.placeholder_corrective_middleware import (\n WatsonXPlaceholderMiddleware,\n)\nfrom lfx.components.models_and_agents.agent_helpers.single_tool_call_middleware import (\n SingleToolCallMiddleware,\n)\nfrom lfx.components.models_and_agents.agent_helpers.tool_approval import ToolApprovalMixin\nfrom lfx.components.models_and_agents.agent_helpers.tool_call_id_middleware import ToolCallIDMiddleware\nfrom lfx.components.models_and_agents.memory import MemoryComponent, _safe_graph_user_id, aget_agent_chat_history\n\nif TYPE_CHECKING:\n from collections.abc import Awaitable, Callable\n\n from langchain_core.tools import Tool\n\n from lfx.schema.log import OnTokenFunctionType, SendMessageFunctionType\n\nfrom lfx.base.agents.agent import LCToolsAgentComponent\nfrom lfx.base.agents.callback import AgentAsyncHandler\nfrom lfx.base.agents.default_system_prompt import DEFAULT_SYSTEM_PROMPT_TEMPLATE\nfrom lfx.base.agents.events import AgentPausedError, ExceptionWithMessageError, process_agent_events\nfrom lfx.base.agents.token_callback import TokenUsageCallbackHandler\nfrom lfx.base.agents.utils import get_chat_output_sender_name\nfrom lfx.base.constants import STREAM_INFO_TEXT\nfrom lfx.base.models.unified_models import (\n get_language_model_options,\n get_llm,\n handle_model_input_update,\n)\nfrom lfx.base.models.watsonx_constants import IBM_WATSONX_URLS\nfrom lfx.components.agentics.helpers.model_config import validate_model_selection\nfrom lfx.components.helpers import CalculatorComponent, CurrentDateComponent\nfrom lfx.components.langchain_utilities.ibm_granite_handler import is_watsonx_model\nfrom lfx.components.langchain_utilities.tool_calling import ToolCallingAgentComponent\nfrom lfx.custom.custom_component.component import get_component_toolkit\nfrom lfx.field_typing.range_spec import RangeSpec\nfrom lfx.inputs.inputs import BoolInput, DropdownInput, ModelInput, StrInput\nfrom lfx.io import IntInput, MessageTextInput, MultilineInput, Output, SecretStrInput, TableInput\nfrom lfx.log.logger import logger\nfrom lfx.memory import delete_message\nfrom lfx.schema.data import Data\nfrom lfx.schema.dotdict import dotdict\nfrom lfx.schema.message import Message\nfrom lfx.schema.table import EditMode\nfrom lfx.utils.constants import MESSAGE_SENDER_AI\n\n\ndef set_advanced_true(component_input):\n component_input.advanced = True\n return component_input\n\n\ndef _agent_base_inputs():\n \"\"\"Return base inputs tailored to AgentComponent's create_agent path.\n\n `get_base_inputs()` returns a shared list — replace, don't mutate. We drop\n inputs that are no-ops here and override info text on the inputs whose\n semantics shifted under create_agent.\n\n `verbose` is dropped because the create_agent event stream already surfaces\n every agent step via the \"Agent Steps\" content blocks; the legacy boolean\n has nothing to toggle. Saved flows that still carry a `verbose` value just\n ignore it on load (the schema no longer declares it).\n \"\"\"\n drop = {\"verbose\"}\n overrides = {\n \"handle_parsing_errors\": BoolInput(\n name=\"handle_parsing_errors\",\n display_name=\"Handle Parse Errors\",\n value=True,\n advanced=True,\n info=(\n \"Adds tool-execution retry as a safety net. `create_agent` already \"\n \"feeds tool-call validation errors back to the LLM automatically; \"\n \"this flag layers `ToolRetryMiddleware` on top so transient tool \"\n \"runtime failures are retried (max 2 retries).\"\n ),\n ),\n \"max_iterations\": IntInput(\n name=\"max_iterations\",\n display_name=\"Max Iterations\",\n value=15,\n advanced=True,\n range_spec=RangeSpec(min=1, max=128000, step=1, step_type=\"int\"),\n info=(\n \"Maximum number of model calls the agent can make before stopping \"\n \"(maps to `ModelCallLimitMiddleware.run_limit` on the create_agent \"\n \"path). Must be at least 1 — it is a safety cap, never 'unlimited'.\"\n ),\n ),\n }\n return [overrides.get(inp.name, inp) for inp in LCToolsAgentComponent.get_base_inputs() if inp.name not in drop]\n\n\ndef _extract_text_content(value) -> str:\n \"\"\"Pull a string payload from a Message-like, AIMessage-like, or string value.\"\"\"\n if isinstance(value, str):\n return value\n text = getattr(value, \"text\", None)\n if isinstance(text, str):\n return text\n content = getattr(value, \"content\", None)\n if isinstance(content, str):\n return content\n return str(value) if value is not None else \"\"\n\n\n@contextmanager\ndef _suppress_send_message(component: Any):\n \"\"\"Temporarily replace component.send_message with a no-op for the duration of the block.\n\n Used during the structured-output prompt fallback: run_agent streams the agent's\n final answer through self.send_message (correct for message_response), but in\n json_response the orchestrator parses that text into structured Data which the\n downstream Chat Output emits — leaving the original emission in place produces a\n duplicate message in the playground. The original method is always restored on exit,\n even when the wrapped call raises.\n \"\"\"\n original = component.send_message\n\n async def _noop(message, *_args, **_kwargs):\n return message\n\n component.send_message = _noop\n try:\n yield\n finally:\n component.send_message = original\n\n\nclass AgentComponent(ToolApprovalMixin, ToolCallingAgentComponent):\n display_name: str = \"Agent\"\n description: str = \"Define the agent's instructions, then enter a task to complete using tools.\"\n documentation: str = \"https://docs.langflow.org/agents\"\n icon = \"bot\"\n beta = False\n name = \"Agent\"\n\n memory_inputs = [set_advanced_true(component_input) for component_input in MemoryComponent().inputs]\n\n inputs = [\n ModelInput(\n name=\"model\",\n display_name=\"Language Model\",\n info=\"Select your model provider\",\n real_time_refresh=True,\n required=True,\n # Agents require tool calling — the filter is honored by\n # ``handle_model_input_update`` so models that can't run with\n # tools never reach the picker (and any saved selection that\n # no longer satisfies the constraint is auto-replaced).\n filters={\"tool_calling\": True},\n ),\n SecretStrInput(\n name=\"api_key\",\n display_name=\"API Key\",\n info=\"Overrides global provider settings. Leave blank to use your pre-configured API Key.\",\n real_time_refresh=True,\n advanced=True,\n ),\n DropdownInput(\n name=\"base_url_ibm_watsonx\",\n display_name=\"watsonx API Endpoint\",\n info=\"The base URL of the API (IBM watsonx.ai only)\",\n options=IBM_WATSONX_URLS,\n value=IBM_WATSONX_URLS[0],\n combobox=True,\n show=False,\n real_time_refresh=True,\n ),\n StrInput(\n name=\"project_id\",\n display_name=\"watsonx Project ID\",\n info=\"The project ID associated with the foundation model (IBM watsonx.ai only)\",\n show=False,\n required=False,\n ),\n MultilineInput(\n name=\"system_prompt\",\n display_name=\"Agent Instructions\",\n info=(\n \"System Prompt: Initial instructions and context provided to guide the agent's behavior. \"\n \"Supports dynamic placeholders: {current_date}, {model_name}, {optional_user_context}.\"\n ),\n value=DEFAULT_SYSTEM_PROMPT_TEMPLATE,\n advanced=False,\n ),\n MessageTextInput(\n name=\"context_id\",\n display_name=\"Context ID\",\n info=\"The context ID of the chat. Adds an extra layer to the local memory.\",\n value=\"\",\n advanced=True,\n ),\n IntInput(\n name=\"n_messages\",\n display_name=\"Number of Chat History Messages\",\n value=100,\n info=\"Number of chat history messages to retrieve.\",\n advanced=True,\n show=True,\n ),\n IntInput(\n name=\"max_tokens\",\n display_name=\"Max Tokens\",\n info=\"Maximum number of tokens to generate. Set to 0 for no explicit limit. Field name varies by provider.\",\n advanced=True,\n range_spec=RangeSpec(min=0, max=128000, step=1, step_type=\"int\"),\n ),\n MultilineInput(\n name=\"format_instructions\",\n display_name=\"Output Format Instructions\",\n info=\"Generic Template for structured output formatting. Valid only with Structured response.\",\n value=(\n \"You are an AI that extracts structured JSON objects from unstructured text. \"\n \"Use a predefined schema with expected types (str, int, float, bool, dict). \"\n \"Extract ALL relevant instances that match the schema - if multiple patterns exist, capture them all. \"\n \"Fill missing or ambiguous values with defaults: null for missing values. \"\n \"Remove exact duplicates but keep variations that have different field values. \"\n \"Always return valid JSON in the expected format, never throw errors. \"\n \"If multiple objects can be extracted, return them all in the structured format.\"\n ),\n advanced=True,\n ),\n TableInput(\n name=\"output_schema\",\n display_name=\"Output Schema\",\n info=(\n \"Schema Validation: Define the structure and data types for structured output. \"\n \"No validation if no output schema.\"\n ),\n advanced=True,\n required=False,\n value=[],\n table_schema=[\n {\n \"name\": \"name\",\n \"display_name\": \"Name\",\n \"type\": \"str\",\n \"description\": \"Specify the name of the output field.\",\n \"default\": \"field\",\n \"edit_mode\": EditMode.INLINE,\n },\n {\n \"name\": \"description\",\n \"display_name\": \"Description\",\n \"type\": \"str\",\n \"description\": \"Describe the purpose of the output field.\",\n \"default\": \"description of field\",\n \"edit_mode\": EditMode.POPOVER,\n },\n {\n \"name\": \"type\",\n \"display_name\": \"Type\",\n \"type\": \"str\",\n \"edit_mode\": EditMode.INLINE,\n \"description\": (\"Indicate the data type of the output field (e.g., str, int, float, bool, dict).\"),\n \"options\": [\"str\", \"int\", \"float\", \"bool\", \"dict\"],\n \"default\": \"str\",\n },\n {\n \"name\": \"multiple\",\n \"display_name\": \"As List\",\n \"type\": \"boolean\",\n \"description\": \"Set to True if this output field should be a list of the specified type.\",\n \"default\": \"False\",\n \"edit_mode\": EditMode.INLINE,\n },\n ],\n ),\n *_agent_base_inputs(),\n # removed memory inputs from agent component\n # *memory_inputs,\n BoolInput(\n name=\"stream\",\n display_name=\"Stream\",\n info=STREAM_INFO_TEXT,\n value=True,\n advanced=True,\n ),\n BoolInput(\n name=\"add_current_date_tool\",\n display_name=\"Current Date\",\n advanced=True,\n info=\"If true, will add a tool to the agent that returns the current date.\",\n value=True,\n ),\n BoolInput(\n name=\"add_calculator_tool\",\n display_name=\"Calculator\",\n advanced=True,\n info=(\n \"If true, adds a zero-config arithmetic calculator tool to the agent \"\n \"(safe: only +, -, *, /, ** operators via AST).\"\n ),\n value=True,\n ),\n ]\n outputs = [\n Output(name=\"response\", display_name=\"Response\", method=\"message_response\"),\n Output(\n name=\"structured_response\",\n display_name=\"Structured Response\",\n method=\"json_response\",\n types=[\"Data\"],\n ),\n ]\n\n async def _additional_model_provider_policy_ids(self, purpose, parameters=None) -> tuple[str, ...]:\n \"\"\"Gate the provider selector retained by legacy Agent/ALTK flows.\"\"\"\n _ = purpose\n from lfx.base.models.provider_registry import resolve_provider_id\n\n effective_parameters = parameters if isinstance(parameters, Mapping) else getattr(self, \"_parameters\", None)\n if not isinstance(effective_parameters, Mapping):\n effective_parameters = {}\n selected_model = effective_parameters.get(\"model\", getattr(self, \"model\", None))\n if selected_model:\n # The shared Component hook already handles a selected ModelInput;\n # connected model objects are gated by their upstream vertex.\n return ()\n legacy_provider = effective_parameters.get(\"agent_llm\", getattr(self, \"agent_llm\", None))\n if not isinstance(legacy_provider, str) or not legacy_provider.strip() or legacy_provider == \"Custom\":\n return ()\n return (resolve_provider_id(legacy_provider),)\n\n async def _filter_legacy_provider_options(self, build_config: Mapping[str, Any]) -> None:\n \"\"\"Filter ALTK/legacy Agent provider choices through the active scope.\"\"\"\n from lfx.services.model_provider_policy import ModelProviderPolicyPurpose, aresolve_model_provider_policy\n\n provider_field = build_config.get(\"agent_llm\")\n if not isinstance(provider_field, dict):\n return\n options = provider_field.get(\"options\")\n if not isinstance(options, list):\n return\n candidates = [option for option in options if isinstance(option, str) and option != \"Custom\"]\n if not candidates:\n return\n snapshot = await aresolve_model_provider_policy(\n user_id=self.user_id,\n providers=candidates,\n purpose=ModelProviderPolicyPurpose.CONFIGURE,\n )\n allowed = set(snapshot.filter(candidates))\n keep_indexes = [index for index, option in enumerate(options) if option == \"Custom\" or option in allowed]\n provider_field[\"options\"] = [options[index] for index in keep_indexes]\n metadata = provider_field.get(\"options_metadata\")\n if isinstance(metadata, list) and len(metadata) == len(options):\n provider_field[\"options_metadata\"] = [metadata[index] for index in keep_indexes]\n\n def _resolve_selected_model(self):\n \"\"\"Resolve the selected model, including legacy agent_llm/model_name inputs.\"\"\"\n try:\n from langchain_core.language_models import BaseLanguageModel\n\n if isinstance(self.model, BaseLanguageModel):\n return self.model\n except ImportError:\n pass\n\n if isinstance(self.model, list) and self.model:\n return self.model\n\n legacy_provider = getattr(self, \"agent_llm\", None)\n legacy_model_name = getattr(self, \"model_name\", None)\n if not legacy_provider or not legacy_model_name:\n return self.model\n\n options = get_language_model_options(user_id=self.user_id)\n for option in options:\n if option.get(\"provider\") == legacy_provider and option.get(\"name\") == legacy_model_name:\n return [option]\n\n return [\n {\n \"name\": legacy_model_name,\n \"provider\": legacy_provider,\n \"metadata\": {},\n }\n ]\n\n def _get_max_tokens_value(self):\n \"\"\"Return the user-supplied max_tokens or None when unset/zero.\"\"\"\n val = getattr(self, \"max_tokens\", None)\n if val in {\"\", 0}:\n return None\n return val\n\n def _get_llm(self):\n \"\"\"Override parent to include max_tokens from the Agent's input field.\n\n Streaming is mandatory for AgentComponent: ``runnable.astream_events(v2)`` only\n emits ``on_chat_model_stream`` chunks when the underlying chat model is\n instantiated with ``streaming=True``. Unlike the LanguageModel component (where\n ``stream`` is a user-facing toggle), the Agent has no opt-out — the toggle is\n kept in the UI for backwards compatibility but is intentionally ignored here.\n Without ``stream=True``, the chat model accumulates the whole response and\n only emits ``on_chat_model_end``, silently disabling the Playground's live-\n typing view and breaking the streaming contract on the /events surface.\n \"\"\"\n return get_llm(\n model=self.model,\n user_id=self.user_id,\n api_key=getattr(self, \"api_key\", None),\n stream=True,\n max_tokens=self._get_max_tokens_value(),\n watsonx_url=getattr(self, \"base_url_ibm_watsonx\", None),\n watsonx_project_id=getattr(self, \"project_id\", None),\n overrides=getattr(self, \"_model_overrides\", None),\n )\n\n async def get_agent_requirements(self):\n \"\"\"Get the agent requirements for the agent.\"\"\"\n from langchain_core.tools import StructuredTool\n\n from lfx.services.model_provider_policy import ModelProviderPolicyPurpose\n\n await self.arequire_model_provider_policy(ModelProviderPolicyPurpose.USE)\n\n selected_model = self._resolve_selected_model()\n try:\n from langchain_core.language_models import BaseLanguageModel\n\n is_connected_model = isinstance(selected_model, BaseLanguageModel)\n except ImportError:\n is_connected_model = False\n\n if not is_connected_model:\n validate_model_selection(selected_model)\n\n # Ensure _get_llm() uses the resolved model (e.g. from legacy agent_llm/model_name)\n self.model = selected_model\n llm_model = self._get_llm()\n if llm_model is None:\n msg = \"No language model selected. Please choose a model to proceed.\"\n raise ValueError(msg)\n\n # Get memory data\n self.chat_history = await self.get_memory_data()\n await logger.adebug(f\"Retrieved {len(self.chat_history)} chat history messages\")\n if isinstance(self.chat_history, Message):\n self.chat_history = [self.chat_history]\n\n # Add current date tool if enabled\n if self.add_current_date_tool:\n if not isinstance(self.tools, list): # type: ignore[has-type]\n self.tools = []\n current_date_tool = (await CurrentDateComponent(**self.get_base_args()).to_toolkit()).pop(0)\n\n if not isinstance(current_date_tool, StructuredTool):\n msg = \"CurrentDateComponent must be converted to a StructuredTool\"\n raise TypeError(msg)\n # Skip if an externally-connected tool already provides the same name.\n # Duplicate tool names are rejected by Anthropic/Gemini with HTTP 400.\n if not any(getattr(t, \"name\", None) == current_date_tool.name for t in self.tools):\n self.tools.append(current_date_tool)\n\n # Add calculator tool if enabled (zero-config arithmetic)\n if getattr(self, \"add_calculator_tool\", False):\n if not isinstance(self.tools, list): # type: ignore[has-type]\n self.tools = []\n calculator_tool = (await CalculatorComponent(**self.get_base_args()).to_toolkit()).pop(0)\n\n if not isinstance(calculator_tool, StructuredTool):\n msg = \"CalculatorComponent must be converted to a StructuredTool\"\n raise TypeError(msg)\n # Skip if an externally-connected tool already provides the same name.\n # Duplicate tool names are rejected by Anthropic/Gemini with HTTP 400.\n if not any(getattr(t, \"name\", None) == calculator_tool.name for t in self.tools):\n self.tools.append(calculator_tool)\n\n # Set shared callbacks for tracing the tools used by the agent\n self.set_tools_callbacks(self.tools, self._get_shared_callbacks())\n\n return llm_model, self.chat_history, self.tools\n\n def _get_resolved_model_name(self) -> str:\n \"\"\"Best-effort human-readable model name for {model_name} injection.\"\"\"\n try:\n from langchain_core.language_models import BaseLanguageModel\n\n if isinstance(self.model, BaseLanguageModel):\n return type(self.model).__name__\n except ImportError:\n pass\n\n if isinstance(self.model, list) and self.model:\n first = self.model[0]\n if isinstance(first, dict):\n name = first.get(\"name\")\n if isinstance(name, str) and name:\n return name\n\n legacy_model_name = getattr(self, \"model_name\", None)\n if isinstance(legacy_model_name, str) and legacy_model_name:\n return legacy_model_name\n return \"\"\n\n def _inject_dynamic_prompt_values(self, prompt: Any | None) -> str | None:\n \"\"\"Replace known env placeholders in the system prompt.\n\n Handles {current_date}, {model_name}, and {optional_user_context} (the\n last one ships with the structured DEFAULT_SYSTEM_PROMPT_TEMPLATE and\n is currently unused at the AgentComponent layer, so it resolves to \"\").\n Uses str.replace (not str.format) so user prompts containing literal\n braces such as JSON examples ({\"key\": 1}) never break the agent.\n\n `system_prompt` is a connectable MultilineInput, so the value can arrive\n as a Message (e.g. a Prompt node wired in). Normalize it to text first —\n a raw Message has no `.replace` and used to crash the agent build.\n \"\"\"\n if prompt is None:\n return None\n prompt = _extract_text_content(prompt)\n if not prompt:\n return prompt\n replacements = {\n \"{current_date}\": datetime.now(tz=timezone.utc).strftime(\"%Y-%m-%d %H:%M:%S UTC\"),\n \"{model_name}\": self._get_resolved_model_name(),\n \"{optional_user_context}\": \"\",\n }\n for placeholder, value in replacements.items():\n prompt = prompt.replace(placeholder, value)\n return prompt\n\n def create_agent_runnable(self, *, allow_interrupts: bool = True):\n \"\"\"Build the LangGraph `CompiledStateGraph` via `langchain.agents.create_agent`.\n\n Replaces the legacy `AgentExecutor` runnable inherited from\n `ToolCallingAgentComponent`. Other agent components (tool_calling, csv, json,\n openapi, sql*, vector_store_router) keep the legacy path — only AgentComponent\n runs on the new graph API.\n\n `max_iterations` and `handle_parsing_errors` (legacy AgentExecutor knobs) are\n translated to LangGraph middleware. Without that translation those user inputs\n would silently become no-ops on the new API.\n\n Provider notes:\n - WatsonX/Granite work natively with create_agent — `ChatWatsonx.bind_tools`\n handles tool_choice correctly. The legacy `create_granite_agent` path was\n dropped because it hardcoded `tool_choice='required'`, which the WatsonX\n API now rejects.\n - Ollama and other small/local models often emit malformed tool args. The\n ToolRetryMiddleware (default `retry_on=(Exception,)`, `on_failure='continue'`)\n catches Pydantic ValidationErrors from bad args and feeds the error back\n to the LLM as a retry signal, so the agent recovers gracefully.\n \"\"\"\n llm = self._get_llm()\n tools = self.tools or []\n\n # Eager bind_tools validation. `create_agent(...)` is lazy — without this,\n # an LLM that doesn't support tool calling fails on the first user message\n # instead of when the user wires up the component, which is a much worse UX.\n # Gated on a non-empty tools list so a no-tool Agent on a plain chat model\n # (which legitimately has no `bind_tools`) isn't shut out at flow-build time.\n # Providers signal \"no tool calling\" inconsistently — `NotImplementedError`\n # (langchain default), `AttributeError` (no `bind_tools` attr), or `TypeError`\n # (signature mismatch). Treat all three as the same UX failure.\n if tools:\n try:\n llm.bind_tools(tools)\n except (NotImplementedError, AttributeError, TypeError) as exc:\n # Include the underlying error so a broken tool schema or a\n # provider implementation bug is not silently disguised as a\n # \"model can't call tools\" UX error.\n msg = (\n f\"{self.display_name} does not support tool calling, \"\n \"or one of the connected tools failed to bind. \"\n \"Please connect a tool-calling capable language model and \"\n f\"verify your tools are well-formed. Underlying error: {exc!s}\"\n )\n raise NotImplementedError(msg) from exc\n\n middleware = self._build_middleware(llm, allow_interrupts=allow_interrupts)\n checkpointer = self._build_agent_checkpointer() if allow_interrupts else None\n return create_agent(\n model=llm,\n tools=tools,\n system_prompt=self.system_prompt or \"\",\n middleware=middleware or None,\n checkpointer=checkpointer,\n )\n\n def _compute_recursion_limit(self) -> int:\n \"\"\"Derive the LangGraph recursion_limit from the user-set max_iterations.\n\n Mirrors the clamp in `_build_middleware` (max(1, max_iterations)) so a\n saved 0 or negative value cannot under-cap the graph below one full\n iteration.\n\n A tool-calling cycle visits the model-call limiter's before_model and\n after_model nodes, the model, and tools. When any tool requires approval,\n HumanInTheLoopMiddleware adds another after_model node to every cycle,\n even if the model repeatedly calls an ungated tool. Leave transition\n room so the model-call limiter can end the run first.\n \"\"\"\n raw = getattr(self, \"max_iterations\", None)\n run_limit = max(1, int(raw)) if raw is not None else 15\n steps_per_cycle = 4 + bool(self._gated_interrupt_on())\n return run_limit * steps_per_cycle + 10\n\n def _build_middleware(self, llm: Any, *, allow_interrupts: bool = True) -> list:\n # `llm` is passed in (rather than re-fetched via `self._get_llm()`)\n # because some providers do credential resolution / client instantiation\n # lazily on each call. The caller — `create_agent_runnable` — already\n # resolved it once for `bind_tools`, so reuse that instance here.\n middleware: list = []\n # LangChain accepts missing IDs on AIMessage.tool_calls, but LangGraph's\n # invalid-call path and ToolRetryMiddleware both require a string when\n # they construct an error ToolMessage. Normalize at the model boundary\n # so either recovery path can return the error to the model instead of\n # crashing the flow.\n if self.tools:\n middleware.append(ToolCallIDMiddleware())\n max_iterations = getattr(self, \"max_iterations\", None)\n if max_iterations is not None:\n # `max_iterations` is a safety cap, not an \"unlimited\" toggle. A saved\n # 0 or negative value (falsy) must NOT silently drop the limiter and\n # allow an unbounded model/tool loop — clamp it to a real minimum.\n run_limit = max(1, int(max_iterations))\n middleware.append(ModelCallLimitMiddleware(run_limit=run_limit))\n # ToolRetryMiddleware only matters when there ARE tools to retry. Attaching\n # it on a no-tools agent inflates the compiled graph and adds per-invocation\n # middleware overhead for nothing, which is a measurable contributor to\n # trivial-prompt latency (QA UI-003).\n if getattr(self, \"handle_parsing_errors\", False) and self.tools:\n middleware.append(ToolRetryMiddleware(max_retries=2))\n # WatsonX models have two known platform quirks; both still reproduce on\n # the current API, so we keep the protections from the legacy\n # `create_granite_agent` path.\n # 1. Multi-tool-call assistant turns are rejected (\"This model only\n # supports single tool-calls at once!\"). Clamp to one per turn.\n # 2. Tool args occasionally come back as literal placeholder strings\n # (e.g. `<result-from-search>`). Re-invoke once with a corrective\n # SystemMessage.\n # Order: SingleToolCallMiddleware first (outermost) so the clamp is\n # applied to the final response, including any corrective re-invoke\n # produced by WatsonXPlaceholderMiddleware.\n if is_watsonx_model(llm):\n middleware.append(SingleToolCallMiddleware())\n middleware.append(WatsonXPlaceholderMiddleware())\n # Human-in-the-loop: attach only when a tool is gated AND interrupts are allowed\n # (the structured-output path disables them), keeping ungated flows unchanged.\n interrupt_on = self._gated_interrupt_on() if allow_interrupts else {}\n if interrupt_on:\n middleware.append(HumanInTheLoopMiddleware(interrupt_on=interrupt_on))\n return middleware\n\n async def run_agent(self, agent) -> Message:\n \"\"\"Run the LangGraph `CompiledStateGraph` and return the final agent Message.\n\n Overrides the legacy `LCAgentComponent.run_agent` (which builds an\n `{\"input\": str, \"chat_history\": [...]}` dict for `AgentExecutor`). The graph\n wants `{\"messages\": [BaseMessage, ...]}`. The event stream is wrapped with\n `adapt_graph_events_to_executor_shape` so the legacy `process_agent_events`\n (in `lfx.base.agents.events`) can be reused unchanged.\n \"\"\"\n messages = build_initial_messages(\n input_value=self.input_value,\n chat_history=getattr(self, \"chat_history\", None),\n )\n input_dict = {\"messages\": messages}\n\n agent_message = self._build_initial_agent_message()\n token_usage_handler = TokenUsageCallbackHandler()\n\n # Stream tokens to the event manager when running inside the Langflow runtime.\n # This is what powers the live-typing view in the chat UI.\n on_token_callback: OnTokenFunctionType | None = None\n if getattr(self, \"_event_manager\", None):\n on_token_callback = cast(\"OnTokenFunctionType\", self._event_manager.on_token)\n\n # Align LangGraph's `recursion_limit` with `max_iterations` so the\n # middleware cap (ModelCallLimitMiddleware) is what bounds the loop —\n # not LangGraph's default 25-step guard, which fires at ~12 model+tool\n # iterations and raises a raw GraphRecursionError (QA UI-009/UI-010).\n # Include the extra after_model node when tool approval is configured.\n recursion_limit = self._compute_recursion_limit()\n\n agent_config: dict[str, Any] = {\n \"callbacks\": [\n AgentAsyncHandler(self.log),\n token_usage_handler,\n *self._get_shared_callbacks(),\n ],\n \"recursion_limit\": recursion_limit,\n }\n # The durable checkpointer keys on the per-run thread_id; it must be in the\n # astream_events config (not just create_agent) for both initial run and resume.\n thread_id = self._agent_thread_id()\n get_pending_interrupt = None\n stream_input: Any = input_dict\n # A checkpointer is only present when the agent was built with interrupts enabled\n # (the structured-output path builds without one); never probe its state otherwise.\n interrupts_enabled = getattr(agent, \"checkpointer\", None) is not None\n if interrupts_enabled and thread_id and self._gated_interrupt_on():\n agent_config[\"configurable\"] = {\"thread_id\": thread_id}\n get_pending_interrupt = self._pending_interrupt_getter(agent, agent_config)\n if self._has_candidate_decision(thread_id):\n # The injected decision must match the pending interrupt's nonce, so read\n # the interrupt first; a matched decision resumes the checkpointed thread.\n value, interrupt_id = await self._read_pending_interrupt(agent, agent_config)\n decision = self._injected_agent_decision(thread_id, interrupt_id)\n if decision is not None:\n action_requests = (value or {}).get(\"action_requests\") or []\n stream_input = Command(\n resume={\"decisions\": self._build_resume_decisions(decision, action_requests)}\n )\n stream = adapt_graph_events_to_executor_shape(\n agent.astream_events(stream_input, config=agent_config, version=\"v2\")\n )\n try:\n result = await process_agent_events(\n stream,\n agent_message,\n cast(\"SendMessageFunctionType\", self.send_message),\n on_token_callback,\n get_pending_interrupt=get_pending_interrupt,\n )\n except AgentPausedError as e:\n # Why: retract the empty partial bubble (leaks as \"[]\"); the HITL card supersedes it, resume re-emits it.\n paused_message = e.agent_message or agent_message\n msg_id = paused_message.get_id()\n if msg_id:\n await delete_message(id_=msg_id)\n await self._send_message_event(paused_message, category=\"remove_message\")\n return self._suspend_for_tool_approval(e.request, paused_message)\n except ExceptionWithMessageError as e:\n # Drop the half-stored partial message from the DB (only if it was\n # actually persisted) and tell the frontend to remove the stale bubble.\n if hasattr(e, \"agent_message\"):\n msg_id = e.agent_message.get_id()\n if msg_id:\n await delete_message(id_=msg_id)\n await self._send_message_event(e.agent_message, category=\"remove_message\")\n # exception(), not error(f\"...{e}\"): this class's str() interpolates the model's\n # partial completion, and passing the exception rather than formatting it is what\n # gives the exported record an error.type to triage on.\n logger.exception(\"Agent run failed after a partial message was emitted\")\n raise\n\n usage_data = token_usage_handler.get_usage()\n if usage_data:\n self._token_usage = usage_data\n result.properties.usage = usage_data\n # Only round-trip the DB when the message was stored (Chat Output wired).\n # `_should_skip_message=True` leaves `result.get_id()` empty; persisting\n # then would create a phantom row.\n if result.get_id():\n stored_result = await self._update_stored_message(result)\n await self._send_message_event(stored_result)\n result = stored_result\n\n self.status = result\n return result\n\n def _build_initial_agent_message(self) -> Message:\n \"\"\"Construct the placeholder agent Message that `process_agent_events` mutates.\"\"\"\n if hasattr(self, \"graph\"):\n session_id = self.graph.session_id\n elif hasattr(self, \"_session_id\"):\n session_id = self._session_id\n else:\n session_id = None\n\n sender_name = get_chat_output_sender_name(self) or self.display_name or \"AI\"\n return Message(\n sender=MESSAGE_SENDER_AI,\n sender_name=sender_name,\n properties={\"icon\": \"Bot\", \"state\": \"partial\"},\n # `text=\"\"` sentinel so MessageTable's no_content check accepts\n # an in-flight agent message whose content_blocks haven't been\n # populated yet. Mirrors ChatInput's convention.\n text=\"\",\n # Flat chronological event log; see lfx.base.agents.events.\n content_blocks=[],\n session_id=session_id or uuid.uuid4(),\n )\n\n def _selected_model_remediation_context(self) -> tuple[str | None, str | None, Any | None]:\n \"\"\"Return provider/name plus a connected model target, when present.\"\"\"\n try:\n selected = self._resolve_selected_model()\n if isinstance(selected, list) and selected and isinstance(selected[0], dict):\n return selected[0].get(\"provider\"), selected[0].get(\"name\"), None\n\n from langchain_core.language_models import BaseLanguageModel\n\n if isinstance(selected, BaseLanguageModel):\n model_name = None\n for attr in (\"model_name\", \"model\", \"model_id\"):\n value = getattr(selected, attr, None)\n if isinstance(value, str) and value:\n model_name = value\n break\n return self._connected_model_provider(selected), model_name, selected\n except (AttributeError, TypeError, ValueError, KeyError, ImportError):\n pass\n return None, None, None\n\n def _connected_model_provider(self, model: Any) -> str | None:\n \"\"\"Resolve a connected model's provider from the source component.\n\n Runtime model classes are not provider identities: OpenAI, OpenRouter,\n and compatible endpoints can all produce ``ChatOpenAI``. The incoming\n model edge preserves the source component, so prefer its explicit\n provider override or selected-model metadata, then its provider display\n name. If the Agent is used without graph provenance, leave the provider\n unknown so provider-scoped remediations remain disabled.\n \"\"\"\n vertex = getattr(self, \"_vertex\", None)\n if vertex is None:\n return None\n source_id = vertex.get_incoming_edge_by_target_param(\"model\")\n if not source_id:\n return None\n source = vertex.graph.get_vertex(source_id)\n component = getattr(source, \"custom_component\", None)\n if component is None:\n return None\n\n candidate = getattr(component, \"provider\", None)\n\n if not isinstance(candidate, str) or not candidate:\n selected_model = getattr(component, \"model\", None)\n if isinstance(selected_model, list) and selected_model and isinstance(selected_model[0], dict):\n candidate = selected_model[0].get(\"provider\")\n\n if not isinstance(candidate, str) or not candidate:\n candidate = getattr(component, \"display_name\", None)\n if not isinstance(candidate, str) or not candidate:\n return None\n\n from lfx.base.models.unified_models.provider_queries import get_model_provider_metadata\n\n provider_metadata = get_model_provider_metadata().get(candidate, {})\n expected_class = provider_metadata.get(\"mapping\", {}).get(\"model_class\")\n model_classes = {base.__name__ for base in type(model).__mro__}\n return candidate if expected_class in model_classes else None\n\n async def _run_agent_with_model_remediation(\n self,\n run_once: Callable[[], Awaitable[Message]],\n ) -> Message:\n \"\"\"Run one Agent operation, retrying safe provider-validation failures.\n\n Registered remediations must identify request-validation failures that\n occur before tool execution. A failure that can happen after a tool runs\n must instead retry at the model-call boundary to avoid repeating tool\n side effects.\n \"\"\"\n from lfx.base.models.model_remediation import apply_overrides_to_model, find_remediation, remember\n\n provider, model_name, connected_model = self._selected_model_remediation_context()\n applied: set[str] = set()\n while True:\n try:\n result = await run_once()\n except (ValueError, TypeError, KeyError):\n await logger.aexception(\"Agent run failed\")\n raise\n except Exception as exc:\n # run_agent may wrap the provider error in ExceptionWithMessageError, whose\n # str() carries the model's partial completion. Matching on it locally is fine;\n # logging it is not, so the record below passes the exception instead.\n error_text = f\"{exc} {getattr(exc, '__cause__', '') or ''}\"\n remediation = find_remediation(error_text, provider, already_applied=applied)\n if remediation is None:\n await logger.aexception(\"Agent run failed with no remediation available\")\n raise\n if connected_model is not None and not apply_overrides_to_model(connected_model, remediation.overrides):\n await logger.aerror(\n f\"model.remediation.unapplied name={remediation.name} provider={provider} model={model_name}\"\n )\n raise\n applied.add(remediation.name)\n if connected_model is None:\n self._model_overrides = {\n **(getattr(self, \"_model_overrides\", None) or {}),\n **remediation.overrides,\n }\n else:\n # Connected outputs are shared objects across downstream flow\n # branches. The mutation is intentionally flow-scoped: sibling\n # branches holding this model will see the matched override too.\n await logger.adebug(\n f\"model.remediation.shared_model name={remediation.name} provider={provider} model={model_name}\"\n )\n await logger.awarning(\n f\"model.remediation.applied name={remediation.name} provider={provider} model={model_name}\"\n )\n else:\n if connected_model is None and getattr(self, \"_model_overrides\", None):\n remember(provider, model_name, self._model_overrides)\n return result\n\n async def message_response(self) -> Message:\n async def _run_once() -> Message:\n llm_model, self.chat_history, self.tools = await self.get_agent_requirements()\n self.set(\n llm=llm_model,\n tools=self.tools or [],\n chat_history=self.chat_history,\n input_value=self.input_value,\n system_prompt=self._inject_dynamic_prompt_values(self.system_prompt),\n )\n agent = self.create_agent_runnable()\n return await self.run_agent(agent)\n\n result = await self._run_agent_with_model_remediation(_run_once)\n self._agent_result = result\n return result\n\n async def json_response(self) -> Data:\n \"\"\"Produce structured Data via native LLM structured output, with prompt-based fallback.\n\n Native path (no tools, llm has with_structured_output) bypasses the agent loop and\n returns provider-validated JSON. When tools are attached, falls back to running the\n agent with a schema-augmented system prompt and parsing the final message content.\n \"\"\"\n from lfx.components.models_and_agents.structured_output.structured_output_orchestrator import (\n orchestrate_structured_output,\n )\n\n try:\n llm_model, self.chat_history, self.tools = await self.get_agent_requirements()\n except (ValueError, TypeError) as exc:\n await logger.aexception(\"json_response.requirements_failed\")\n return Data(data={\"content\": \"\", \"error\": str(exc)})\n\n injected_system_prompt = self._inject_dynamic_prompt_values(getattr(self, \"system_prompt\", \"\") or \"\") or \"\"\n format_instructions = getattr(self, \"format_instructions\", \"\") or \"\"\n output_schema = getattr(self, \"output_schema\", None) or []\n has_tools = bool(self.tools)\n\n async def _run_agent_for_fallback(augmented_prompt: str) -> str:\n first_attempt = True\n\n async def _run_once() -> Message:\n nonlocal first_attempt, llm_model\n if first_attempt:\n first_attempt = False\n else:\n llm_model, self.chat_history, self.tools = await self.get_agent_requirements()\n self.set(\n llm=llm_model,\n tools=self.tools or [],\n chat_history=self.chat_history,\n input_value=self.input_value,\n system_prompt=augmented_prompt,\n )\n # Structured output cannot suspend mid-parse: disable tool-approval interrupts.\n agent_runnable = self.create_agent_runnable(allow_interrupts=False)\n return await self.run_agent(agent_runnable)\n\n with _suppress_send_message(self):\n result = await self._run_agent_with_model_remediation(_run_once)\n return _extract_text_content(result)\n\n try:\n return await orchestrate_structured_output(\n llm=llm_model,\n output_schema=output_schema,\n system_prompt=injected_system_prompt,\n format_instructions=format_instructions,\n input_value=_extract_text_content(self.input_value),\n run_prompt_fallback=_run_agent_for_fallback,\n prefer_native=not has_tools,\n )\n except (\n ExceptionWithMessageError,\n ValueError,\n TypeError,\n NotImplementedError,\n AttributeError,\n ) as exc:\n await logger.aexception(\"json_response.orchestration_failed\")\n return Data(data={\"content\": \"\", \"error\": str(exc)})\n\n async def get_memory_data(self):\n # Scope by flow_id so default playground session names (e.g. \"New Session 0\")\n # cannot leak chat history across unrelated flows. See issue #13059.\n # The helper also returns [] when n_messages == 0, preserving the\n # explicit \"memory disabled\" contract from MemoryComponent.retrieve_messages.\n messages = await aget_agent_chat_history(\n session_id=self.graph.session_id,\n flow_id=getattr(self.graph, \"flow_id\", None),\n context_id=self.context_id,\n n_messages=self.n_messages,\n user_id=_safe_graph_user_id(self),\n )\n return [\n message for message in messages if getattr(message, \"id\", None) != getattr(self.input_value, \"id\", None)\n ]\n\n def update_input_types(self, build_config: dotdict) -> dotdict:\n \"\"\"Update input types for all fields in build_config.\"\"\"\n for key, value in build_config.items():\n if isinstance(value, dict):\n if value.get(\"input_types\") is None:\n build_config[key][\"input_types\"] = []\n elif hasattr(value, \"input_types\") and value.input_types is None:\n value.input_types = []\n return build_config\n\n async def update_build_config(\n self,\n build_config: dotdict,\n field_value: list[dict],\n field_name: str | None = None,\n ) -> dotdict:\n from lfx.services.model_provider_policy import ModelProviderPolicyPurpose\n\n policy_parameters = dict(getattr(self, \"_parameters\", {}) or {})\n if field_name:\n policy_parameters[field_name] = field_value\n await self.arequire_model_provider_policy(\n ModelProviderPolicyPurpose.CONFIGURE,\n parameters=policy_parameters,\n )\n # Update model options with caching (for all field changes).\n # The tool-calling constraint lives on the ModelInput's ``filters``\n # field (declared above); ``handle_model_input_update`` reads it\n # and applies the filter to both the dropdown options and the\n # sticky-default re-injection path.\n build_config = handle_model_input_update(\n component=self,\n build_config=dict(build_config),\n field_value=field_value,\n field_name=field_name,\n )\n build_config = dotdict(build_config)\n\n if field_name == \"model\":\n build_config = self.update_input_types(build_config)\n\n # Validate required keys. `verbose` was dropped from the input set\n # (see `_agent_base_inputs` — the create_agent event stream already\n # surfaces every step), so it is intentionally NOT required here.\n # Saved flows that still carry a `verbose` value just ignore it on\n # load.\n default_keys = [\n \"code\",\n \"_type\",\n \"model\",\n \"tools\",\n \"input_value\",\n \"add_current_date_tool\",\n \"add_calculator_tool\",\n \"system_prompt\",\n \"max_iterations\",\n \"handle_parsing_errors\",\n ]\n missing_keys = [key for key in default_keys if key not in build_config]\n if missing_keys:\n msg = f\"Missing required keys in build_config: {missing_keys}\"\n raise ValueError(msg)\n await self._filter_legacy_provider_options(build_config)\n return dotdict({k: v.to_dict() if hasattr(v, \"to_dict\") else v for k, v in build_config.items()})\n\n async def _get_tools(self) -> list[Tool]:\n component_toolkit = get_component_toolkit()\n\n tools = component_toolkit(component=self).get_tools(\n tool_name=\"Call_Agent\",\n # here we do not use the shared callbacks as we are exposing the agent as a tool\n callbacks=self.get_langchain_callbacks(),\n )\n if hasattr(self, \"tools_metadata\"):\n tools = component_toolkit(component=self, metadata=self.tools_metadata).update_tools_metadata(tools=tools)\n\n return tools\n"
},
"context_id": {
"_input_type": "MessageTextInput",
@@ -1562,10 +1565,6 @@
},
"dragging": false,
"id": "Agent-Nfw7u",
- "measured": {
- "height": 431,
- "width": 320
- },
"position": {
"x": 1852.9501767300426,
"y": 1606.8625850497745
@@ -1594,7 +1593,7 @@
],
"frozen": false,
"icon": "calculator",
- "last_updated": "2026-09-16T13:50:51.378Z",
+ "last_updated": "2026-10-29T18:15:34.726Z",
"legacy": false,
"metadata": {
"code_hash": "d0b2936e74fa",
@@ -1615,7 +1614,7 @@
{
"allows_loop": false,
"cache": true,
- "display_name": "Toolset",
+ "display_name": "JSON",
"group_outputs": false,
"hidden": null,
"loop_types": null,
@@ -1637,7 +1636,7 @@
"value": "1098eea1-6649-4e1d-aed1-b77249fb8dd0"
},
"_frontend_node_folder_id": {
- "value": "de367ed7-7bbb-4e2e-ba97-12db63476e42"
+ "value": "afa57272-6d34-4d1c-bf31-27ffad110b3a"
},
"_type": "Component",
"code": {
@@ -1735,10 +1734,6 @@
},
"dragging": false,
"id": "CalculatorComponent-KrlMH",
- "measured": {
- "height": 52,
- "width": 192
- },
"position": {
"x": 1354.9559315259569,
"y": 1572.0374911360082
@@ -1956,10 +1951,6 @@
},
"dragging": false,
"id": "Prompt Template-7kZsI",
- "measured": {
- "height": 80,
- "width": 192
- },
"position": {
"x": 998.1664626584457,
"y": 2010.5977206525736
@@ -2115,10 +2106,6 @@
},
"dragging": false,
"id": "TextInput-i0a3P",
- "measured": {
- "height": 52,
- "width": 192
- },
"position": {
"x": 564.9101816547212,
"y": 1824.034735248319
@@ -2153,15 +2140,15 @@
],
"frozen": false,
"icon": "Mcp",
- "last_updated": "2026-09-16T13:50:51.380Z",
+ "last_updated": "2026-10-29T18:16:15.575Z",
"legacy": false,
"metadata": {
- "code_hash": "5a77bca15146",
+ "code_hash": "9c81bfe8e4e5",
"dependencies": {
"dependencies": [
{
"name": "langchain_core",
- "version": "1.6.2"
+ "version": "1.7.0"
},
{
"name": "pydantic",
@@ -2169,11 +2156,11 @@
},
{
"name": "lfx",
- "version": "1.12.0"
+ "version": "1.12.8"
},
{
"name": "langflow",
- "version": "1.12.0"
+ "version": "1.12.8"
}
],
"total_dependencies": 4
@@ -2208,7 +2195,7 @@
"value": "1098eea1-6649-4e1d-aed1-b77249fb8dd0"
},
"_frontend_node_folder_id": {
- "value": "de367ed7-7bbb-4e2e-ba97-12db63476e42"
+ "value": "afa57272-6d34-4d1c-bf31-27ffad110b3a"
},
"_type": "Component",
"code": {
@@ -2228,7 +2215,7 @@
"show": true,
"title_case": false,
"type": "code",
- "value": "from __future__ import annotations\n\nimport asyncio\nimport hashlib\nimport json\nimport time\nimport uuid\nfrom types import UnionType\nfrom typing import Any, cast, get_args, get_origin\n\nfrom langchain_core.tools import StructuredTool # noqa: TC002\nfrom pydantic import BaseModel\n\nfrom lfx.base.agents.utils import maybe_unflatten_dict, safe_cache_get, safe_cache_set\nfrom lfx.base.mcp.util import (\n MCPStdioClient,\n MCPStreamableHttpClient,\n config_uses_global_variables,\n update_tools,\n)\nfrom lfx.base.tools.constants import TOOL_OUTPUT_DISPLAY_NAME, TOOL_OUTPUT_NAME\nfrom lfx.custom.custom_component.component_with_cache import ComponentWithCache\nfrom lfx.inputs.inputs import InputTypes # noqa: TC001\nfrom lfx.io import BoolInput, DictInput, DropdownInput, FloatInput, McpInput, MessageTextInput, Output\nfrom lfx.io.schema import schema_to_langflow_inputs\nfrom lfx.log.logger import logger\nfrom lfx.schema.dataframe import DataFrame\nfrom lfx.schema.message import Message\nfrom lfx.services.deps import get_storage_service, session_scope\n\n\ndef resolve_mcp_config(\n server_name: str, # noqa: ARG001\n server_config_from_value: dict | None,\n server_config_from_db: dict | None,\n) -> dict | None:\n \"\"\"Resolve MCP server config with proper precedence.\n\n Resolves the configuration for an MCP server with the following precedence:\n 1. Database config (takes priority) - ensures edits are reflected\n 2. Config from value/tweaks (fallback) - allows REST API to provide config for new servers\n\n Args:\n server_name: Name of the MCP server\n server_config_from_value: Config provided via value/tweaks (optional)\n server_config_from_db: Config from database (optional)\n\n Returns:\n Final config to use (DB takes priority, falls back to value)\n Returns None if no config found in either location\n \"\"\"\n if server_config_from_db:\n return server_config_from_db\n return server_config_from_value\n\n\n# TODO(legacy-cleanup): This file is ~800 lines, over the 500-line guideline. Split\n# helper functions (resolve_mcp_config, connection resolution) from the MCPToolsComponent\n# orchestration logic in a follow-up PR.\nclass MCPToolsComponent(ComponentWithCache):\n \"\"\"MCP Tools component.\n\n Behaviour notes:\n - Stale agent tools vs server were caused by Langflow caching the Toolset output\n (``Output.cache=True`` plus the persisted ``output.value`` in saved flow JSON), not\n only by the user-facing \"Use Cached Server\" (``use_cache``) toggle. ``_build_tool_output``\n declares the Toolset output with ``cache=False`` and ``map_outputs`` overrides the\n persisted value for existing flows so every run resolves a fresh tool list.\n - ``update_tool_list`` is serialized with an ``asyncio.Lock`` so concurrent calls do not\n share the same Streamable HTTP client session; overlapping POST/DELETE cycles otherwise\n surface as HTTP 404 and the MCP SDK reports ``Session terminated``.\n - All diagnostic logs are at DEBUG level to avoid swamping logs on hot paths (an agent\n may call ``_get_tools`` per step). Header values are never logged; only header *keys*.\n \"\"\"\n\n # Short-lived in-memory cache window (seconds) for ``_get_tools``. When the\n # same header-hash key is requested again within this window the cached tool\n # list is reused so parallel agent runs that share identical auth don't\n # each pay for a fresh MCP round-trip. Set to ``0`` to disable. This is\n # distinct from the \"Use Cached Server\" (``use_cache``) toggle which only\n # controls the shared cross-request server cache.\n TOOL_TTL_SECS: int = 30\n # Upper bound on the per-component-lineage TTL cache. Oldest entries are evicted\n # when the cap is reached. Keeps memory bounded for flows where the same\n # component handles many rotating auth contexts (e.g. per-tenant tokens).\n TOOL_TTL_MAX_ENTRIES: int = 32\n # Upper bound on the shared cross-request ``servers`` cache. Each\n # (server_name, header-hash) pair is a distinct entry; without a bound a\n # tenant that rotates session tokens would grow this map without limit.\n SHARED_SERVERS_CACHE_MAX_ENTRIES: int = 64\n\n schema_inputs: list = []\n tools: list[StructuredTool] = []\n _not_load_actions: bool = False\n _tool_cache: dict = {}\n _last_selected_server: str | None = None # Cache for the last selected server\n\n def __init__(self, **data) -> None:\n super().__init__(**data)\n # Initialize cache keys to avoid CacheMiss when accessing them\n self._ensure_cache_structure()\n\n # Initialize clients with access to the component cache.\n # Per-component timeout is normalized and applied immediately before MCP calls.\n self.stdio_client: MCPStdioClient = MCPStdioClient(component_cache=self._shared_component_cache)\n self.streamable_http_client: MCPStreamableHttpClient = MCPStreamableHttpClient(\n component_cache=self._shared_component_cache\n )\n # One MCP stdio/streamable client pair per component; concurrent update_tool_list calls\n # otherwise race (session DELETE vs POST) and the MCP SDK surfaces HTTP 404 as \"Session terminated\".\n self._update_tool_list_lock = asyncio.Lock()\n # Per-component-lineage TTL cache for ``_get_tools``:\n # {cache_key: (monotonic_ts, tools)}. Freshly instantiated components get their own\n # dict; ``__deepcopy__`` shares it only with that component's invocation copies.\n # A class-level dict would instead expose entries to every MCPToolsComponent in the\n # process, leaking tool lists across tenants that happen to hash to the same key.\n self._ttl_tool_cache: dict[str, tuple[float, list]] = {}\n\n def __deepcopy__(self, memo: dict) -> MCPToolsComponent:\n \"\"\"Keep the per-component tool cache available to isolated invocation copies.\"\"\"\n component_copy = cast(\"MCPToolsComponent\", super().__deepcopy__(memo))\n # Component tools are deep-copied for every invocation to isolate mutable inputs.\n # Those copies belong to the same component execution lineage, so sharing this\n # bounded, auth-scoped cache preserves its TTL without exposing it to independently\n # instantiated components.\n component_copy._ttl_tool_cache = self._ttl_tool_cache # noqa: SLF001\n return component_copy\n\n def _ensure_cache_structure(self):\n \"\"\"Ensure the cache has the required structure.\"\"\"\n # Check if servers key exists and is not CacheMiss\n servers_value = safe_cache_get(self._shared_component_cache, \"servers\")\n if servers_value is None:\n safe_cache_set(self._shared_component_cache, \"servers\", {})\n\n # Check if last_selected_server key exists and is not CacheMiss\n last_server_value = safe_cache_get(self._shared_component_cache, \"last_selected_server\")\n if last_server_value is None:\n safe_cache_set(self._shared_component_cache, \"last_selected_server\", \"\")\n\n def _normalized_headers_for_cache(self) -> dict[str, str]:\n \"\"\"Component headers as a dict for stable cache keying (auth / tweaks).\"\"\"\n component_headers = getattr(self, \"headers\", None) or []\n if isinstance(component_headers, list):\n return {\n str(item[\"key\"]): str(item[\"value\"])\n for item in component_headers\n if isinstance(item, dict) and \"key\" in item and \"value\" in item\n }\n if isinstance(component_headers, dict):\n return {str(k): str(v) for k, v in component_headers.items()}\n return {}\n\n def _normalize_tool_execution_timeout(self) -> float | None:\n \"\"\"Normalize the timeout input and reject negative values with a field-specific error.\"\"\"\n timeout_value = getattr(self, \"tool_execution_timeout\", 0.0)\n\n if timeout_value in (None, \"\"):\n return None\n\n try:\n val = float(timeout_value)\n except (ValueError, TypeError):\n return None\n\n if val < 0:\n msg = \"Tool Execution Timeout must be greater than or equal to 0.\"\n raise ValueError(msg)\n\n return val if val else None\n\n def _mcp_servers_cache_key(self, server_name: str) -> str:\n \"\"\"Cache key for shared servers map.\n\n Includes the authenticated user, headers, and timeout so tenant/auth/tweak/timeout\n changes get distinct entries.\n \"\"\"\n if not server_name:\n return \"\"\n\n raw_timeout = getattr(self, \"tool_execution_timeout\", 0.0) or 0.0\n normalized_timeout = max(0.0, float(raw_timeout))\n\n hdrs = self._normalized_headers_for_cache()\n\n # Build cache key components\n cache_data = {\n \"headers\": hdrs,\n \"timeout\": normalized_timeout,\n }\n\n user_id = self._mcp_cache_user_id()\n if user_id:\n cache_data[\"user_id\"] = user_id\n\n # Preserve the compact per-instance TTL key when there is no authenticated user.\n # Shared caching is disabled for that case in ``update_tool_list`` below.\n if not hdrs and normalized_timeout == 0.0 and not user_id:\n return server_name\n\n payload = json.dumps(cache_data, sort_keys=True)\n digest = hashlib.sha256(payload.encode()).hexdigest()[:16]\n return f\"{server_name}:{digest}\"\n\n def _mcp_cache_user_id(self) -> str | None:\n \"\"\"Return the authenticated user id without requiring a fully attached graph.\n\n Components are also instantiated without a vertex while the UI builds component\n metadata. Accessing ``self.user_id`` in that state raises, so inspect the backing\n fields directly and fail closed by returning ``None`` when no authenticated scope\n is available.\n \"\"\"\n user_id = getattr(self, \"_user_id\", None)\n if not user_id:\n graph = getattr(getattr(self, \"_vertex\", None), \"graph\", None)\n user_id = getattr(graph, \"user_id\", None)\n return str(user_id) if user_id else None\n\n def _build_tool_output(self) -> Output:\n # Do not cache Toolset output. This is separate from the MCP \"Use Cached Server\" (use_cache)\n # toggle: Langflow's Output.cache defaults to True and was memoizing the first to_toolkit()\n # result, so per-request tweaks/headers never refreshed bound tools even when use_cache=False.\n return Output(\n name=TOOL_OUTPUT_NAME,\n display_name=TOOL_OUTPUT_DISPLAY_NAME,\n method=\"to_toolkit\",\n types=[\"Tool\"],\n cache=False,\n )\n\n def map_outputs(self) -> None:\n \"\"\"Override the persisted ``component_as_tool`` cache flag from saved flow JSON.\n\n ``_build_tool_output`` already returns the output with ``cache=False``, but the\n flow JSON for existing flows often stores ``cache: true`` for ``component_as_tool``\n and that persisted value wins over the declaration. Forcing ``cache=False`` here\n guarantees saved flows also bypass Output memoization and get a fresh tool list\n on every run.\n \"\"\"\n super().map_outputs()\n if TOOL_OUTPUT_NAME in self._outputs_map:\n self._outputs_map[TOOL_OUTPUT_NAME].cache = False\n\n default_keys: list[str] = [\n \"code\",\n \"_type\",\n \"tool_mode\",\n \"tool_placeholder\",\n \"mcp_server\",\n \"tool\",\n \"use_cache\",\n \"verify_ssl\",\n \"headers\",\n \"tool_execution_timeout\",\n ]\n\n display_name = \"MCP Tools\"\n description = \"Connect to an MCP server to use its tools.\"\n documentation: str = \"https://docs.langflow.org/mcp-tools\"\n icon = \"Mcp\"\n name = \"MCPTools\"\n\n inputs = [\n McpInput(\n name=\"mcp_server\",\n display_name=\"MCP Server\",\n info=\"Select the MCP Server that will be used by this component\",\n real_time_refresh=True,\n ),\n BoolInput(\n name=\"use_cache\",\n display_name=\"Use Cached Server\",\n info=(\n \"Enable caching of MCP Server and tools to improve performance. \"\n \"Disable to always fetch fresh tools and server updates.\"\n ),\n value=False,\n advanced=True,\n ),\n BoolInput(\n name=\"verify_ssl\",\n display_name=\"Verify SSL Certificate\",\n info=(\n \"Enable SSL certificate verification for HTTPS connections. \"\n \"Disable only for development/testing with self-signed certificates.\"\n ),\n value=True,\n advanced=True,\n ),\n DictInput(\n name=\"headers\",\n display_name=\"Headers\",\n info=(\n \"HTTP headers to include with MCP server requests. \"\n \"Useful for authentication (e.g., Authorization header). \"\n \"These headers override any headers configured in the MCP server settings.\"\n ),\n advanced=True,\n is_list=True,\n ),\n FloatInput(\n name=\"tool_execution_timeout\",\n display_name=\"Tool Execution Timeout (seconds)\",\n info=(\n \"Maximum time to wait for tool execution before timing out. \"\n \"Supports decimal values for sub-second timeouts (e.g., 0.01 for 10ms). \"\n \"Set to 0 to use the system-configured MCP timeout.\"\n ),\n value=0.0,\n range_spec={\"min\": 0.0, \"max\": 3600.0, \"step\": 0.01},\n real_time_refresh=True,\n advanced=True,\n ),\n DropdownInput(\n name=\"tool\",\n display_name=\"Tool\",\n options=[],\n value=\"\",\n info=\"Select the tool to execute\",\n show=False,\n required=True,\n real_time_refresh=True,\n refresh_button=True,\n ),\n MessageTextInput(\n name=\"tool_placeholder\",\n display_name=\"Tool Placeholder\",\n info=\"Placeholder for the tool\",\n value=\"\",\n show=False,\n # Tool Mode is a capability of the component, not of the selected\n # server. Advertising it up front keeps the toolbar from waiting\n # for the MCP server's tool-discovery request to finish.\n tool_mode=True,\n ),\n ]\n\n outputs = [\n Output(display_name=\"Response\", name=\"response\", method=\"build_output\"),\n ]\n\n async def _validate_schema_inputs(self, tool_obj) -> list[InputTypes]:\n \"\"\"Validate and process schema inputs for a tool.\"\"\"\n try:\n if not tool_obj or not hasattr(tool_obj, \"args_schema\"):\n msg = \"Invalid tool object or missing input schema\"\n raise ValueError(msg)\n\n input_schema = tool_obj.args_schema\n if not input_schema:\n msg = f\"Empty input schema for tool '{tool_obj.name}'\"\n raise ValueError(msg)\n\n schema_inputs = schema_to_langflow_inputs(input_schema)\n if not schema_inputs:\n msg = f\"No input parameters defined for tool '{tool_obj.name}'\"\n await logger.awarning(msg)\n return []\n\n except Exception as e:\n msg = f\"Error validating schema inputs: {e!s}\"\n await logger.aexception(msg)\n raise ValueError(msg) from e\n else:\n return schema_inputs\n\n async def _ensure_cached_mcp_stdio_access(self, server_config: dict) -> None:\n \"\"\"Reapply the current stdio policy before returning cached tools.\"\"\"\n try:\n from langflow.api.v2.mcp import ensure_mcp_stdio_access\n from langflow.services.database.models.user.crud import get_user_by_id\n\n from lfx.services.deps import get_settings_service\n except ModuleNotFoundError as e:\n missing_module = e.name or \"\"\n if missing_module != \"langflow\" and not missing_module.startswith(\"langflow.\"):\n raise\n return\n\n async with session_scope() as db:\n if not self.user_id:\n msg = \"User ID is required for fetching MCP tools.\"\n raise ValueError(msg)\n current_user = await get_user_by_id(db, self.user_id)\n\n ensure_mcp_stdio_access(server_config, current_user, get_settings_service().settings)\n\n async def update_tool_list(self, mcp_server_value=None):\n # Accepts mcp_server_value as dict {name, config} or uses self.mcp_server\n mcp_server = mcp_server_value if mcp_server_value is not None else getattr(self, \"mcp_server\", None)\n server_name = None\n server_config_from_value = None\n if isinstance(mcp_server, dict):\n server_name = mcp_server.get(\"name\")\n server_config_from_value = mcp_server.get(\"config\")\n else:\n server_name = mcp_server\n if not server_name:\n self.tools = []\n await logger.adebug(\"MCP update_tool_list: empty server_name, clearing tools\")\n return [], {\"name\": server_name, \"config\": server_config_from_value}\n\n servers_cache_key = self._mcp_servers_cache_key(server_name)\n\n # Check if caching is enabled, default to False. The cross-request cache must never\n # be used without an authenticated tenant scope; the per-instance TTL cache remains\n # available in standalone/UI contexts.\n use_cache = getattr(self, \"use_cache\", False)\n use_shared_cache = use_cache and self._mcp_cache_user_id() is not None\n header_keys = sorted(self._normalized_headers_for_cache().keys())\n await logger.adebug(\n \"MCP update_tool_list: start server=%r use_cache=%s use_shared_cache=%s shared_cache_key=%r header_keys=%s\",\n server_name,\n use_cache,\n use_shared_cache,\n servers_cache_key,\n header_keys,\n )\n\n async with self._update_tool_list_lock:\n # Use shared cache if available and caching is enabled\n cached = None\n if use_shared_cache:\n servers_cache = safe_cache_get(self._shared_component_cache, \"servers\", {})\n cached = servers_cache.get(servers_cache_key) if isinstance(servers_cache, dict) else None\n\n if cached is not None:\n try:\n tools_from_cache = cached[\"tools\"]\n server_config_from_value = cached[\"config\"]\n except (TypeError, KeyError, AttributeError) as e:\n # Handle corrupted cache data by clearing it and continuing to fetch fresh tools\n msg = f\"Unable to use cached data for MCP Server{server_name}: {e}\"\n await logger.awarning(msg)\n # Clear the corrupted cache entry\n current_servers_cache = safe_cache_get(self._shared_component_cache, \"servers\", {})\n if isinstance(current_servers_cache, dict) and servers_cache_key in current_servers_cache:\n current_servers_cache.pop(servers_cache_key)\n safe_cache_set(self._shared_component_cache, \"servers\", current_servers_cache)\n else:\n try:\n await self._ensure_cached_mcp_stdio_access(server_config_from_value)\n except Exception as e:\n msg = f\"Error updating tool list: {e!s}\"\n await logger.aexception(msg)\n raise ValueError(msg) from e\n else:\n self.tools = tools_from_cache\n self.tool_names = [t.name for t in self.tools if hasattr(t, \"name\")]\n self._tool_cache = cached[\"tool_cache\"]\n await logger.adebug(\n \"MCP update_tool_list: shared_servers_cache HIT count=%d server=%r\",\n len(self.tools),\n server_name,\n )\n return self.tools, {\"name\": server_name, \"config\": server_config_from_value}\n\n try:\n # Try to fetch from database first to ensure we have the latest config.\n # This ensures database updates (like editing a server) take effect.\n # When running in LFX standalone mode the full Langflow package and\n # database may not be available — in that case we skip the DB lookup\n # and fall back to the config embedded in the flow (server_config_from_value).\n server_config_from_db = None\n current_user = None\n settings_service = None\n ensure_mcp_stdio_access = None\n try:\n from langflow.api.v2.mcp import ensure_mcp_stdio_access, get_server\n from langflow.services.database.models.user.crud import get_user_by_id\n\n from lfx.services.deps import get_settings_service\n except ModuleNotFoundError as e:\n # Deliberately `except ModuleNotFoundError` (not `except ImportError`): a\n # plain ImportError here means `get_server` / `get_user_by_id` was removed\n # from an installed Langflow — a real API break that should NOT be\n # swallowed as \"standalone mode\". ModuleNotFoundError alone covers the\n # \"Langflow absent\" case.\n #\n # Even within ModuleNotFoundError, only treat this as LFX standalone mode\n # when one of the target Langflow modules is itself missing. Transitive\n # ModuleNotFoundError (e.g. a dependency like sqlmodel failing to import\n # inside langflow.*) indicates a real bug in the full Langflow stack and\n # must surface — otherwise we would silently use a stale flow-embedded\n # config when DB config should have taken precedence.\n missing_module = e.name or \"\"\n is_langflow_standalone = missing_module == \"langflow\" or missing_module.startswith(\"langflow.\")\n if not is_langflow_standalone:\n raise\n await logger.ainfo(\n \"Langflow package not available; using MCP server config from flow value (LFX standalone mode).\"\n )\n else:\n async with session_scope() as db:\n if not self.user_id:\n msg = \"User ID is required for fetching MCP tools.\"\n raise ValueError(msg)\n current_user = await get_user_by_id(db, self.user_id)\n settings_service = get_settings_service()\n\n # Try to get server config from DB/API\n server_config_from_db = await get_server(\n server_name,\n current_user,\n db,\n storage_service=get_storage_service(),\n settings_service=settings_service,\n )\n\n # Resolve config with proper precedence: DB takes priority, falls back to value\n server_config = resolve_mcp_config(\n server_name=server_name,\n server_config_from_value=server_config_from_value,\n server_config_from_db=server_config_from_db,\n )\n\n if not server_config:\n self.tools = []\n await logger.awarning(\n \"MCP update_tool_list: no server_config after resolve server=%r\",\n server_name,\n )\n msg = (\n f\"MCP server '{server_name}' is not configured. \"\n \"Add a server with this name in Settings > MCP Servers before running this flow.\"\n )\n raise ValueError(msg)\n\n # The REST API applies this policy when a stdio server is registered,\n # but imported flows can carry the same process-spawning config in the\n # MCP component value. Reapply the policy to the resolved config at the\n # component boundary before update_tools reaches the subprocess client.\n if ensure_mcp_stdio_access is not None and current_user is not None and settings_service is not None:\n ensure_mcp_stdio_access(server_config, current_user, settings_service.settings)\n\n # Add verify_ssl option to server config if not present\n if \"verify_ssl\" not in server_config:\n verify_ssl = getattr(self, \"verify_ssl\", True)\n server_config[\"verify_ssl\"] = verify_ssl\n\n # Merge headers from component input with server config headers\n # Component headers take precedence over server config headers\n component_headers = getattr(self, \"headers\", None) or []\n if component_headers:\n # Convert list of {\"key\": k, \"value\": v} to dict\n component_headers_dict = {}\n if isinstance(component_headers, list):\n for item in component_headers:\n if isinstance(item, dict) and \"key\" in item and \"value\" in item:\n component_headers_dict[item[\"key\"]] = item[\"value\"]\n elif isinstance(component_headers, dict):\n component_headers_dict = component_headers\n\n if component_headers_dict:\n existing_headers = server_config.get(\"headers\", {}) or {}\n # Ensure existing_headers is a dict (convert from list if needed)\n if isinstance(existing_headers, list):\n existing_dict = {}\n for item in existing_headers:\n if isinstance(item, dict) and \"key\" in item and \"value\" in item:\n existing_dict[item[\"key\"]] = item[\"value\"]\n existing_headers = existing_dict\n merged_headers = {**existing_headers, **component_headers_dict}\n server_config[\"headers\"] = merged_headers\n # Get request_variables from graph context for global variable resolution\n request_variables = None\n end_user_id = None\n if hasattr(self, \"graph\") and self.graph:\n if hasattr(self.graph, \"context\"):\n request_variables = self.graph.context.get(\"request_variables\")\n # Serving-plane end-user id (set by the entry-point scoping); forwarded only\n # to allowlisted internal MCP targets by update_tools (fail-closed).\n end_user_id = getattr(self.graph, \"end_user_id\", None)\n\n # Load global variables only when the config actually references them, so a\n # static config still costs no query -- but a URL-only reference now counts.\n # The load must NOT be skipped just because the request carried overrides: a\n # request that overrides one variable still needs every other referenced\n # variable resolved from the database.\n db_variables: dict[str, str] | None = None\n if config_uses_global_variables(server_config):\n try:\n from lfx.services.deps import get_variable_service\n\n variable_service = get_variable_service()\n # ``get_all_decrypted_variables`` is DB-service-only; the minimal\n # lfx VariableService (now registered by ``lfx serve``) lacks it, so\n # skip cleanly rather than raising into the broad except below.\n if variable_service and hasattr(variable_service, \"get_all_decrypted_variables\"):\n async with session_scope() as db:\n db_variables = await variable_service.get_all_decrypted_variables(\n user_id=self.user_id, session=db\n )\n except Exception as e: # noqa: BLE001\n await logger.awarning(\"Failed to load global variables for MCP component\", exc_info=e)\n\n # Headers may resolve from either source, per-request values winning on\n # conflict (matching ``CustomComponent.get_variable``). Dropping the database\n # side whenever the request carried anything would send an unresolved variable\n # *name* upstream as the header value (#14604).\n #\n # The URL still resolves from the database only, via ``url_variables`` below:\n # request_variables carry the caller's X-Langflow-Global-Var-* values, and a\n # caller must not be able to choose where this flow connects.\n request_variables = {**(db_variables or {}), **(request_variables or {})} or None\n\n await logger.adebug(\n \"MCP update_tool_list: calling update_tools server=%r mode_headers=%s\",\n server_name,\n sorted((server_config.get(\"headers\") or {}).keys())\n if isinstance(server_config.get(\"headers\"), dict)\n else \"list-or-empty\",\n )\n\n timeout = self._normalize_tool_execution_timeout()\n\n _, tool_list, tool_cache = await update_tools(\n server_name=server_name,\n server_config=server_config,\n mcp_stdio_client=self.stdio_client,\n mcp_streamable_http_client=self.streamable_http_client,\n request_variables=request_variables,\n url_variables=db_variables,\n tool_execution_timeout=timeout,\n current_user_id=self.user_id,\n end_user_id=end_user_id,\n )\n\n self.tool_names = [tool.name for tool in tool_list if hasattr(tool, \"name\")]\n self._tool_cache = tool_cache\n self.tools = tool_list\n\n await logger.adebug(\n \"MCP update_tool_list: fetched from MCP count=%d server=%r\",\n len(tool_list),\n server_name,\n )\n\n # Cache the result only if caching is enabled\n if use_shared_cache:\n cache_data = {\n \"tools\": tool_list,\n \"tool_names\": self.tool_names,\n \"tool_cache\": tool_cache,\n \"config\": server_config,\n }\n\n # Safely update the servers cache with bounded size (FIFO eviction).\n current_servers_cache = safe_cache_get(self._shared_component_cache, \"servers\", {})\n if isinstance(current_servers_cache, dict):\n # Because the cache key now includes a header hash, a tenant that\n # rotates session tokens would grow this map without bound. Drop\n # the oldest entry when over the limit.\n max_entries = self.SHARED_SERVERS_CACHE_MAX_ENTRIES\n while (\n len(current_servers_cache) >= max_entries and servers_cache_key not in current_servers_cache\n ):\n oldest_key = next(iter(current_servers_cache))\n current_servers_cache.pop(oldest_key, None)\n current_servers_cache[servers_cache_key] = cache_data\n safe_cache_set(self._shared_component_cache, \"servers\", current_servers_cache)\n await logger.adebug(\n \"MCP update_tool_list: wrote shared_servers_cache key=%r size=%d\",\n servers_cache_key,\n len(current_servers_cache),\n )\n\n except (TimeoutError, asyncio.TimeoutError) as e:\n msg = (\n f\"Timeout updating tool list: {e!s}. \"\n \"Raise ``LANGFLOW_MCP_SERVER_TIMEOUT`` for the deployment if the MCP \"\n \"server legitimately needs more time to respond.\"\n )\n await logger.aexception(msg)\n raise TimeoutError(msg) from e\n except Exception as e:\n msg = f\"Error updating tool list: {e!s}\"\n await logger.aexception(msg)\n raise ValueError(msg) from e\n else:\n return tool_list, {\"name\": server_name, \"config\": server_config}\n\n async def update_build_config(self, build_config: dict, field_value: str, field_name: str | None = None) -> dict:\n \"\"\"Toggle the visibility of connection-specific fields based on the selected mode.\"\"\"\n try:\n is_refresh = bool(build_config.get(\"is_refresh\", False))\n if field_name == \"tool\":\n try:\n # Always refresh tools when cache is disabled, or when tools list is empty\n # This ensures database edits are reflected immediately when cache is disabled\n use_cache = getattr(self, \"use_cache\", False)\n if is_refresh:\n self.tools = []\n if is_refresh or len(self.tools) == 0 or not use_cache:\n try:\n self.tools, build_config[\"mcp_server\"][\"value\"] = await self.update_tool_list()\n build_config[\"tool\"][\"options\"] = [tool.name for tool in self.tools]\n build_config[\"tool\"][\"placeholder\"] = \"Select a tool\"\n except (TimeoutError, asyncio.TimeoutError) as e:\n msg = f\"Timeout updating tool list: {e!s}\"\n await logger.aexception(msg)\n if not build_config[\"tools_metadata\"][\"show\"]:\n build_config[\"tool\"][\"show\"] = True\n build_config[\"tool\"][\"options\"] = []\n build_config[\"tool\"][\"value\"] = \"\"\n build_config[\"tool\"][\"placeholder\"] = msg\n else:\n build_config[\"tool\"][\"show\"] = False\n except ValueError as e:\n msg = f\"Error updating tool list: {e!s}\"\n await logger.aexception(msg)\n if not build_config[\"tools_metadata\"][\"show\"]:\n build_config[\"tool\"][\"show\"] = True\n build_config[\"tool\"][\"options\"] = []\n build_config[\"tool\"][\"value\"] = \"\"\n build_config[\"tool\"][\"placeholder\"] = msg\n else:\n build_config[\"tool\"][\"show\"] = False\n\n if field_value == \"\":\n return build_config\n tool_obj = None\n for tool in self.tools:\n if tool.name == field_value:\n tool_obj = tool\n break\n if tool_obj is None:\n msg = f\"Tool {field_value} not found in available tools: {self.tools}\"\n await logger.awarning(msg)\n return build_config\n await self._update_tool_config(build_config, field_value)\n except Exception as e:\n build_config[\"tool\"][\"options\"] = []\n msg = f\"Failed to update tools: {e!s}\"\n raise ValueError(msg) from e\n else:\n return build_config\n elif field_name == \"mcp_server\":\n if not field_value:\n build_config[\"tool\"][\"show\"] = False\n build_config[\"tool\"][\"options\"] = []\n build_config[\"tool\"][\"value\"] = \"\"\n build_config[\"tool\"][\"placeholder\"] = \"\"\n build_config[\"tool_placeholder\"][\"tool_mode\"] = True\n self.remove_non_default_keys(build_config)\n return build_config\n\n build_config[\"tool_placeholder\"][\"tool_mode\"] = True\n\n current_server_name = field_value.get(\"name\") if isinstance(field_value, dict) else field_value\n build_config_server_value = build_config.get(\"mcp_server\", {}).get(\"value\")\n build_config_server_name = (\n build_config_server_value.get(\"name\")\n if isinstance(build_config_server_value, dict)\n else build_config_server_value\n )\n servers_cache_key_ui = self._mcp_servers_cache_key(current_server_name) if current_server_name else \"\"\n _last_selected_server = safe_cache_get(self._shared_component_cache, \"last_selected_server\", \"\")\n # Only treat as a server change if there was a previous server selection.\n # Cold cache (_last_selected_server=\"\") on initial flow load is NOT a server change —\n # the user didn't switch anything, the backend just hasn't seen this component yet.\n server_changed = bool(\n (_last_selected_server and current_server_name != _last_selected_server)\n or (build_config_server_name and current_server_name != build_config_server_name)\n )\n\n # Determine if \"Tool Mode\" is active by checking if the tool dropdown is hidden.\n is_in_tool_mode = build_config[\"tools_metadata\"][\"show\"]\n\n # Get use_cache setting to determine if we should use cached data\n use_cache = getattr(self, \"use_cache\", False)\n has_shared_cache_scope = self._mcp_cache_user_id() is not None\n use_shared_cache = use_cache and has_shared_cache_scope\n\n # Fast path: if server didn't change and we already have options, keep them as-is\n # BUT only if caching is enabled, we're in tool mode, or it's the initial load\n existing_options = build_config.get(\"tool\", {}).get(\"options\") or []\n if not is_refresh and not server_changed and existing_options:\n # In non-tool mode with cache disabled, skip the fast path to force refresh\n # BUT on initial load (cold cache), always preserve saved options from the flow\n if not is_in_tool_mode and not use_cache and _last_selected_server:\n pass # Continue to refresh logic below (user-initiated with cache disabled)\n else:\n if not is_in_tool_mode:\n build_config[\"tool\"][\"show\"] = True\n safe_cache_set(self._shared_component_cache, \"last_selected_server\", current_server_name)\n return build_config\n\n # To avoid unnecessary updates, only proceed if the server has actually changed\n # OR if caching is disabled (to force refresh in non-tool mode)\n if (\n not is_refresh\n and (_last_selected_server in (current_server_name, \"\"))\n and build_config[\"tool\"][\"show\"]\n and use_shared_cache\n ):\n if current_server_name:\n servers_cache = safe_cache_get(self._shared_component_cache, \"servers\", {})\n if isinstance(servers_cache, dict):\n cached = servers_cache.get(servers_cache_key_ui)\n if cached is not None and cached.get(\"tool_names\"):\n cached_tools = cached[\"tool_names\"]\n current_tools = build_config[\"tool\"][\"options\"]\n if current_tools == cached_tools:\n return build_config\n else:\n return build_config\n safe_cache_set(self._shared_component_cache, \"last_selected_server\", current_server_name)\n\n # When cache is disabled, clear any cached data for this server\n # This ensures we always fetch fresh data from the database\n if (is_refresh or not use_cache) and current_server_name and has_shared_cache_scope:\n servers_cache = safe_cache_get(self._shared_component_cache, \"servers\", {})\n if isinstance(servers_cache, dict) and servers_cache_key_ui in servers_cache:\n servers_cache.pop(servers_cache_key_ui)\n safe_cache_set(self._shared_component_cache, \"servers\", servers_cache)\n\n # Check if tools are already cached for this server before clearing\n cached_tools = None\n if current_server_name and use_shared_cache and not is_refresh:\n servers_cache = safe_cache_get(self._shared_component_cache, \"servers\", {})\n if isinstance(servers_cache, dict):\n cached = servers_cache.get(servers_cache_key_ui)\n if cached is not None:\n try:\n cached_tools = cached[\"tools\"]\n self.tools = cached_tools\n self.tool_names = cached[\"tool_names\"]\n self._tool_cache = cached[\"tool_cache\"]\n except (TypeError, KeyError, AttributeError) as e:\n # Handle corrupted cache data by ignoring it\n msg = f\"Unable to use cached data for MCP Server,{current_server_name}: {e}\"\n await logger.awarning(msg)\n cached_tools = None\n\n # Clear tools when cache is disabled OR when we don't have cached tools\n # This ensures fresh tools are fetched after database edits\n if is_refresh or not cached_tools or not use_cache:\n self.tools = [] # Clear previous tools to force refresh\n\n # Clear previous tool inputs if:\n # 1. Server actually changed\n # 2. Cache is disabled (meaning tool list will be refreshed)\n if is_refresh or server_changed or not use_cache:\n self.remove_non_default_keys(build_config)\n\n # Only show the tool dropdown if not in tool_mode\n if not is_in_tool_mode:\n build_config[\"tool\"][\"show\"] = True\n if cached_tools:\n # Use cached tools to populate options immediately\n build_config[\"tool\"][\"options\"] = [tool.name for tool in cached_tools]\n build_config[\"tool\"][\"placeholder\"] = \"Select a tool\"\n else:\n # Actually fetch tools now instead of deferring to a frontend callback.\n # The frontend has no reliable mechanism to trigger a second\n # update_build_config call for the \"tool\" field after this response,\n # so we must populate the options here.\n try:\n self.tools, build_config[\"mcp_server\"][\"value\"] = await self.update_tool_list(\n mcp_server_value=field_value\n )\n build_config[\"tool\"][\"options\"] = [tool.name for tool in self.tools]\n build_config[\"tool\"][\"placeholder\"] = \"Select a tool\"\n except (TimeoutError, asyncio.TimeoutError) as e:\n msg = f\"Timeout loading tools for MCP server: {e!s}\"\n await logger.aexception(msg)\n build_config[\"tool\"][\"options\"] = []\n build_config[\"tool\"][\"placeholder\"] = \"Timeout on MCP server\"\n except (ValueError, ImportError, ConnectionError, OSError, RuntimeError) as e:\n msg = f\"Error loading tools for MCP server: {e!s}\"\n await logger.aexception(msg)\n build_config[\"tool\"][\"options\"] = []\n build_config[\"tool\"][\"placeholder\"] = (\n \"Error on MCP Server\" if \"'NoneType' object has no attribute 'id'\" in msg else msg\n )\n # Force a value refresh only when the user genuinely switched servers.\n # server_changed is only True for real user-initiated changes (not initial load).\n if server_changed:\n build_config[\"tool\"][\"value\"] = uuid.uuid4()\n else:\n # Keep the tool dropdown hidden if in tool_mode\n self._not_load_actions = True\n build_config[\"tool\"][\"show\"] = False\n\n elif field_name == \"tool_mode\":\n build_config[\"tool\"][\"placeholder\"] = \"\"\n build_config[\"tool\"][\"show\"] = not bool(field_value) and bool(build_config[\"mcp_server\"])\n self.remove_non_default_keys(build_config)\n self.tool = build_config[\"tool\"][\"value\"]\n if field_value:\n self._not_load_actions = True\n else:\n build_config[\"tool\"][\"value\"] = uuid.uuid4()\n build_config[\"tool\"][\"show\"] = True\n # Fetch tools immediately instead of showing \"Loading tools...\"\n try:\n self.tools, build_config[\"mcp_server\"][\"value\"] = await self.update_tool_list()\n build_config[\"tool\"][\"options\"] = [tool.name for tool in self.tools]\n build_config[\"tool\"][\"placeholder\"] = \"Select a tool\"\n except (TimeoutError, asyncio.TimeoutError) as e:\n msg = f\"Timeout loading tools when toggling tool mode: {e!s}\"\n await logger.aexception(msg)\n build_config[\"tool\"][\"options\"] = []\n build_config[\"tool\"][\"placeholder\"] = msg\n except (ValueError, ImportError, ConnectionError, OSError, RuntimeError) as e:\n msg = f\"Error loading tools when toggling tool mode: {e!s}\"\n await logger.aexception(msg)\n build_config[\"tool\"][\"options\"] = []\n build_config[\"tool\"][\"placeholder\"] = msg\n elif field_name == \"tool_execution_timeout\":\n try:\n val = float(field_value) if field_value not in (None, \"\") else 0.0\n except (ValueError, TypeError):\n val = 0.0\n if val < 0:\n build_config[\"tool_execution_timeout\"][\"placeholder\"] = (\n \"⚠ Value must be ≥ 0. Negative timeouts cause immediate failures.\"\n )\n build_config[\"tool_execution_timeout\"][\"value\"] = 0.0\n else:\n build_config[\"tool_execution_timeout\"][\"placeholder\"] = \"\"\n elif field_name == \"tools_metadata\":\n self._not_load_actions = False\n\n except Exception as e:\n msg = f\"Error in update_build_config: {e!s}\"\n await logger.aexception(msg)\n raise ValueError(msg) from e\n else:\n return build_config\n\n @staticmethod\n def _unwrap_optional_annotation(annotation: Any) -> Any:\n \"\"\"Remove a single None branch from a union annotation.\"\"\"\n if isinstance(annotation, UnionType):\n non_none = [item for item in get_args(annotation) if item is not type(None)]\n if len(non_none) == 1:\n return non_none[0]\n return annotation\n\n if get_origin(annotation) is None:\n return annotation\n\n non_none = [item for item in get_args(annotation) if item is not type(None)]\n if len(non_none) == 1 and len(non_none) != len(get_args(annotation)):\n return non_none[0]\n return annotation\n\n @classmethod\n def _is_object_like_annotation(cls, annotation: Any) -> bool:\n \"\"\"Return True when the annotation represents a dict-like payload.\"\"\"\n annotation = cls._unwrap_optional_annotation(annotation)\n origin = get_origin(annotation)\n if origin is dict:\n return True\n return annotation is dict or (isinstance(annotation, type) and issubclass(annotation, BaseModel))\n\n @classmethod\n def _should_include_tool_argument(cls, model_field: Any, value: Any) -> bool:\n \"\"\"Omit blank optional values so MCP server defaults remain intact.\"\"\"\n if value is None:\n return False\n\n if model_field.is_required():\n return True\n\n if isinstance(value, str) and value == \"\":\n return False\n\n return not (\n value == {} and model_field.default is None and cls._is_object_like_annotation(model_field.annotation)\n )\n\n def _build_tool_kwargs(self, args_schema: type[BaseModel]) -> dict[str, Any]:\n \"\"\"Collect tool kwargs from component inputs, omitting blank optional values.\"\"\"\n kwargs: dict[str, Any] = {}\n for arg_name, model_field in args_schema.model_fields.items():\n value = getattr(self, arg_name, None)\n if isinstance(value, Message):\n value = value.text\n\n if self._should_include_tool_argument(model_field, value):\n kwargs[arg_name] = value\n\n return kwargs\n\n def get_inputs_for_all_tools(self, tools: list) -> dict:\n \"\"\"Get input schemas for all tools.\"\"\"\n inputs = {}\n for tool in tools:\n if not tool or not hasattr(tool, \"name\"):\n continue\n try:\n langflow_inputs = schema_to_langflow_inputs(tool.args_schema)\n inputs[tool.name] = langflow_inputs\n except (AttributeError, ValueError, TypeError, KeyError) as e:\n msg = f\"Error getting inputs for tool {getattr(tool, 'name', 'unknown')}: {e!s}\"\n logger.exception(msg)\n continue\n return inputs\n\n def remove_non_default_keys(self, build_config: dict) -> None:\n \"\"\"Remove non-default keys from the build config.\"\"\"\n for key in list(build_config.keys()):\n if key not in self.default_keys:\n build_config.pop(key)\n\n async def _update_tool_config(self, build_config: dict, tool_name: str) -> None:\n \"\"\"Update tool configuration with proper error handling.\"\"\"\n if not self.tools:\n self.tools, build_config[\"mcp_server\"][\"value\"] = await self.update_tool_list()\n\n if not tool_name:\n return\n\n tool_obj = next((tool for tool in self.tools if tool.name == tool_name), None)\n if not tool_obj:\n msg = f\"Tool {tool_name} not found in available tools: {self.tools}\"\n self.remove_non_default_keys(build_config)\n build_config[\"tool\"][\"value\"] = \"\"\n await logger.awarning(msg)\n return\n\n try:\n # Store current values before removing inputs (only for the current tool)\n current_values = {}\n for key, value in build_config.items():\n if key not in self.default_keys and isinstance(value, dict) and \"value\" in value:\n current_values[key] = value[\"value\"]\n\n # Remove ALL non-default keys (all previous tool inputs)\n self.remove_non_default_keys(build_config)\n\n # Get and validate new inputs for the selected tool\n self.schema_inputs = await self._validate_schema_inputs(tool_obj)\n if not self.schema_inputs:\n msg = f\"No input parameters to configure for tool '{tool_name}'\"\n await logger.ainfo(msg)\n return\n\n # Add new inputs to build config for the selected tool only\n for schema_input in self.schema_inputs:\n if not schema_input or not hasattr(schema_input, \"name\"):\n msg = \"Invalid schema input detected, skipping\"\n await logger.awarning(msg)\n continue\n\n try:\n name = schema_input.name\n input_dict = schema_input.to_dict()\n input_dict.setdefault(\"value\", None)\n input_dict.setdefault(\"required\", True)\n\n build_config[name] = input_dict\n\n # Preserve existing value if the parameter name exists in current_values\n if name in current_values:\n build_config[name][\"value\"] = current_values[name]\n\n except (AttributeError, KeyError, TypeError) as e:\n msg = f\"Error processing schema input {schema_input}: {e!s}\"\n await logger.aexception(msg)\n continue\n except ValueError as e:\n msg = f\"Schema validation error for tool {tool_name}: {e!s}\"\n await logger.aexception(msg)\n self.schema_inputs = []\n return\n except (AttributeError, KeyError, TypeError) as e:\n msg = f\"Error updating tool config: {e!s}\"\n await logger.aexception(msg)\n raise ValueError(msg) from e\n\n async def build_output(self) -> DataFrame:\n \"\"\"Build output with improved error handling and validation.\"\"\"\n try:\n self.tools, _ = await self.update_tool_list()\n if self.tool != \"\":\n # Set session context for persistent MCP sessions using Langflow session ID\n session_context = self._get_session_context()\n if session_context:\n self.stdio_client.set_session_context(session_context)\n self.streamable_http_client.set_session_context(session_context)\n exec_tool = self._tool_cache[self.tool]\n kwargs = self._build_tool_kwargs(exec_tool.args_schema)\n unflattened_kwargs = maybe_unflatten_dict(kwargs)\n\n output = await exec_tool.coroutine(**unflattened_kwargs)\n if getattr(output, \"isError\", False):\n # isError=True is a FAILED call; treating its content as data makes it look successful.\n error_text = \" \".join(str(item.model_dump().get(\"text\") or \"\") for item in output.content).strip()\n msg = f\"MCP tool '{self.tool}' failed: {error_text or 'no error detail provided'}\"\n raise ValueError(msg)\n tool_content = []\n for item in output.content:\n item_dict = item.model_dump()\n item_dict = self.process_output_item(item_dict)\n tool_content.append(item_dict)\n\n if isinstance(tool_content, list) and all(isinstance(x, dict) for x in tool_content):\n return DataFrame(tool_content)\n return DataFrame(data=tool_content)\n return DataFrame(data=[{\"error\": \"You must select a tool\"}])\n except Exception as e:\n msg = f\"Error in build_output: {e!s}\"\n await logger.aexception(msg)\n raise ValueError(msg) from e\n\n def process_output_item(self, item_dict):\n \"\"\"Process the output of a tool.\"\"\"\n if item_dict.get(\"type\") == \"text\":\n text = item_dict.get(\"text\")\n try:\n parsed = json.loads(text)\n # Ensure we always return a dictionary for DataFrame compatibility\n if isinstance(parsed, dict):\n return parsed\n # Wrap non-dict parsed values in a dictionary\n return {\"text\": text, \"parsed_value\": parsed, \"type\": \"text\"} # noqa: TRY300\n except json.JSONDecodeError:\n return item_dict\n return item_dict\n\n def _get_session_context(self) -> str | None:\n \"\"\"Get the Langflow session ID for MCP session caching.\"\"\"\n # Try to get session ID from the component's execution context\n if hasattr(self, \"graph\") and hasattr(self.graph, \"session_id\"):\n session_id = self.graph.session_id\n # Include server name to ensure different servers get different sessions\n server_name = \"\"\n mcp_server = getattr(self, \"mcp_server\", None)\n if isinstance(mcp_server, dict):\n server_name = mcp_server.get(\"name\", \"\")\n elif mcp_server:\n server_name = str(mcp_server)\n return f\"{session_id}_{server_name}\" if session_id else None\n return None\n\n async def _get_tools(self):\n \"\"\"Load tools for the agent toolkit; always refresh from ``update_tool_list``.\n\n ``_not_load_actions`` only applies to UI build_config flows (tool dropdown). Agent\n runs must always bind the current tool list (including after header/tweak changes).\n\n A short-lived TTL cache (``TOOL_TTL_SECS``, header-hash-keyed) skips the MCP\n round-trip when the same auth context is re-queried quickly (e.g. parallel agent\n steps sharing the same tweaked headers). The cache is per component lineage (including\n isolated invocation copies) and bounded by ``TOOL_TTL_MAX_ENTRIES``; it is distinct from\n the \"Use Cached Server\" (``use_cache``) toggle which controls the shared cross-request cache.\n \"\"\"\n mcp_server = getattr(self, \"mcp_server\", None)\n srv = mcp_server.get(\"name\") if isinstance(mcp_server, dict) else mcp_server\n\n ttl = self.TOOL_TTL_SECS\n ttl_key = self._mcp_servers_cache_key(srv or \"\") if ttl > 0 and srv else \"\"\n\n # TTL cache lookup + expired-entry eviction.\n if ttl > 0 and ttl_key:\n cached = self._ttl_tool_cache.get(ttl_key)\n if cached is not None:\n ts, cached_tools = cached\n age = time.monotonic() - ts\n if age < ttl:\n await logger.adebug(\n \"MCP _get_tools: TTL cache hit count=%d age=%.1fs server=%r\",\n len(cached_tools),\n age,\n srv,\n )\n return cached_tools\n # Stale — drop it so the size check below stays tight.\n self._ttl_tool_cache.pop(ttl_key, None)\n\n await logger.adebug(\"MCP _get_tools: fetching tool list server=%r\", srv)\n tools, _ = await self.update_tool_list(mcp_server)\n await logger.adebug(\"MCP _get_tools: fetched %d tools server=%r\", len(tools), srv)\n\n # TTL cache store with bounded size (FIFO eviction of the oldest entry).\n if ttl > 0 and ttl_key and tools:\n if len(self._ttl_tool_cache) >= self.TOOL_TTL_MAX_ENTRIES:\n # dict preserves insertion order — pop the oldest entry.\n oldest_key = next(iter(self._ttl_tool_cache))\n self._ttl_tool_cache.pop(oldest_key, None)\n self._ttl_tool_cache[ttl_key] = (time.monotonic(), tools)\n\n return tools\n"
+ "value": "from __future__ import annotations\n\nimport asyncio\nimport hashlib\nimport json\nimport time\nimport uuid\nfrom types import UnionType\nfrom typing import Any, cast, get_args, get_origin\n\nfrom langchain_core.tools import StructuredTool # noqa: TC002\nfrom pydantic import BaseModel\n\nfrom lfx.base.agents.utils import maybe_unflatten_dict, safe_cache_get, safe_cache_set\nfrom lfx.base.mcp.util import (\n MCPStdioClient,\n MCPStreamableHttpClient,\n config_uses_global_variables,\n update_tools,\n)\nfrom lfx.base.tools.constants import TOOL_OUTPUT_DISPLAY_NAME, TOOL_OUTPUT_NAME\nfrom lfx.custom.custom_component.component_with_cache import ComponentWithCache\nfrom lfx.inputs.inputs import InputTypes # noqa: TC001\nfrom lfx.io import BoolInput, DictInput, DropdownInput, FloatInput, McpInput, MessageTextInput, Output\nfrom lfx.io.schema import schema_to_langflow_inputs\nfrom lfx.log.logger import logger\nfrom lfx.schema.dataframe import DataFrame\nfrom lfx.schema.message import Message\nfrom lfx.services.deps import get_storage_service, session_scope\n\n\ndef resolve_mcp_config(\n server_name: str, # noqa: ARG001\n server_config_from_value: dict | None,\n server_config_from_db: dict | None,\n) -> dict | None:\n \"\"\"Resolve MCP server config with proper precedence.\n\n Resolves the configuration for an MCP server with the following precedence:\n 1. Database config (takes priority) - ensures edits are reflected\n 2. Config from value/tweaks (fallback) - allows REST API to provide config for new servers\n\n Args:\n server_name: Name of the MCP server\n server_config_from_value: Config provided via value/tweaks (optional)\n server_config_from_db: Config from database (optional)\n\n Returns:\n Final config to use (DB takes priority, falls back to value)\n Returns None if no config found in either location\n \"\"\"\n if server_config_from_db:\n return server_config_from_db\n return server_config_from_value\n\n\n# TODO(legacy-cleanup): This file is ~800 lines, over the 500-line guideline. Split\n# helper functions (resolve_mcp_config, connection resolution) from the MCPToolsComponent\n# orchestration logic in a follow-up PR.\nclass MCPToolsComponent(ComponentWithCache):\n \"\"\"MCP Tools component.\n\n Behaviour notes:\n - Stale agent tools vs server were caused by Langflow caching the Toolset output\n (``Output.cache=True`` plus the persisted ``output.value`` in saved flow JSON), not\n only by the user-facing \"Use Cached Server\" (``use_cache``) toggle. ``_build_tool_output``\n declares the Toolset output with ``cache=False`` and ``map_outputs`` overrides the\n persisted value for existing flows so every run resolves a fresh tool list.\n - ``update_tool_list`` is serialized with an ``asyncio.Lock`` so concurrent calls do not\n share the same Streamable HTTP client session; overlapping POST/DELETE cycles otherwise\n surface as HTTP 404 and the MCP SDK reports ``Session terminated``.\n - All diagnostic logs are at DEBUG level to avoid swamping logs on hot paths (an agent\n may call ``_get_tools`` per step). Header values are never logged; only header *keys*.\n \"\"\"\n\n # Short-lived in-memory cache window (seconds) for ``_get_tools``. When the\n # same header-hash key is requested again within this window the cached tool\n # list is reused so parallel agent runs that share identical auth don't\n # each pay for a fresh MCP round-trip. Set to ``0`` to disable. This is\n # distinct from the \"Use Cached Server\" (``use_cache``) toggle which only\n # controls the shared cross-request server cache.\n TOOL_TTL_SECS: int = 30\n # Upper bound on the per-component-lineage TTL cache. Oldest entries are evicted\n # when the cap is reached. Keeps memory bounded for flows where the same\n # component handles many rotating auth contexts (e.g. per-tenant tokens).\n TOOL_TTL_MAX_ENTRIES: int = 32\n # Upper bound on the shared cross-request ``servers`` cache. Each\n # (server_name, header-hash) pair is a distinct entry; without a bound a\n # tenant that rotates session tokens would grow this map without limit.\n SHARED_SERVERS_CACHE_MAX_ENTRIES: int = 64\n\n schema_inputs: list = []\n tools: list[StructuredTool] = []\n _not_load_actions: bool = False\n _tool_cache: dict = {}\n _last_selected_server: str | None = None # Cache for the last selected server\n\n def __init__(self, **data) -> None:\n super().__init__(**data)\n # Initialize cache keys to avoid CacheMiss when accessing them\n self._ensure_cache_structure()\n\n # Initialize clients with access to the component cache.\n # Per-component timeout is normalized and applied immediately before MCP calls.\n self.stdio_client: MCPStdioClient = MCPStdioClient(component_cache=self._shared_component_cache)\n self.streamable_http_client: MCPStreamableHttpClient = MCPStreamableHttpClient(\n component_cache=self._shared_component_cache\n )\n # One MCP stdio/streamable client pair per component; concurrent update_tool_list calls\n # otherwise race (session DELETE vs POST) and the MCP SDK surfaces HTTP 404 as \"Session terminated\".\n self._update_tool_list_lock = asyncio.Lock()\n # Per-component-lineage TTL cache for ``_get_tools``:\n # {cache_key: (monotonic_ts, tools)}. Freshly instantiated components get their own\n # dict; ``__deepcopy__`` shares it only with that component's invocation copies.\n # A class-level dict would instead expose entries to every MCPToolsComponent in the\n # process, leaking tool lists across tenants that happen to hash to the same key.\n self._ttl_tool_cache: dict[str, tuple[float, list]] = {}\n\n def __deepcopy__(self, memo: dict) -> MCPToolsComponent:\n \"\"\"Keep the per-component tool cache available to isolated invocation copies.\"\"\"\n component_copy = cast(\"MCPToolsComponent\", super().__deepcopy__(memo))\n # Component tools are deep-copied for every invocation to isolate mutable inputs.\n # Those copies belong to the same component execution lineage, so sharing this\n # bounded, auth-scoped cache preserves its TTL without exposing it to independently\n # instantiated components.\n component_copy._ttl_tool_cache = self._ttl_tool_cache # noqa: SLF001\n return component_copy\n\n def _ensure_cache_structure(self):\n \"\"\"Ensure the cache has the required structure.\"\"\"\n # Check if servers key exists and is not CacheMiss\n servers_value = safe_cache_get(self._shared_component_cache, \"servers\")\n if servers_value is None:\n safe_cache_set(self._shared_component_cache, \"servers\", {})\n\n # Check if last_selected_server key exists and is not CacheMiss\n last_server_value = safe_cache_get(self._shared_component_cache, \"last_selected_server\")\n if last_server_value is None:\n safe_cache_set(self._shared_component_cache, \"last_selected_server\", \"\")\n\n def _normalized_headers_for_cache(self) -> dict[str, str]:\n \"\"\"Component headers as a dict for stable cache keying (auth / tweaks).\"\"\"\n component_headers = getattr(self, \"headers\", None) or []\n if isinstance(component_headers, list):\n return {\n str(item[\"key\"]): str(item[\"value\"])\n for item in component_headers\n if isinstance(item, dict) and \"key\" in item and \"value\" in item\n }\n if isinstance(component_headers, dict):\n return {str(k): str(v) for k, v in component_headers.items()}\n return {}\n\n def _normalize_tool_execution_timeout(self) -> float | None:\n \"\"\"Normalize the timeout input and reject negative values with a field-specific error.\"\"\"\n timeout_value = getattr(self, \"tool_execution_timeout\", 0.0)\n\n if timeout_value in (None, \"\"):\n return None\n\n try:\n val = float(timeout_value)\n except (ValueError, TypeError):\n return None\n\n if val < 0:\n msg = \"Tool Execution Timeout must be greater than or equal to 0.\"\n raise ValueError(msg)\n\n return val if val else None\n\n def _mcp_servers_cache_key(self, server_name: str) -> str:\n \"\"\"Cache key for shared servers map.\n\n Includes the authenticated user, headers, and timeout so tenant/auth/tweak/timeout\n changes get distinct entries.\n \"\"\"\n if not server_name:\n return \"\"\n\n raw_timeout = getattr(self, \"tool_execution_timeout\", 0.0) or 0.0\n normalized_timeout = max(0.0, float(raw_timeout))\n\n hdrs = self._normalized_headers_for_cache()\n\n # Build cache key components\n cache_data = {\n \"headers\": hdrs,\n \"timeout\": normalized_timeout,\n }\n\n user_id = self._mcp_cache_user_id()\n if user_id:\n cache_data[\"user_id\"] = user_id\n\n # Preserve the compact per-instance TTL key when there is no authenticated user.\n # Shared caching is disabled for that case in ``update_tool_list`` below.\n if not hdrs and normalized_timeout == 0.0 and not user_id:\n return server_name\n\n payload = json.dumps(cache_data, sort_keys=True)\n digest = hashlib.sha256(payload.encode()).hexdigest()[:16]\n return f\"{server_name}:{digest}\"\n\n def _mcp_cache_user_id(self) -> str | None:\n \"\"\"Return the authenticated user id without requiring a fully attached graph.\n\n Components are also instantiated without a vertex while the UI builds component\n metadata. Accessing ``self.user_id`` in that state raises, so inspect the backing\n fields directly and fail closed by returning ``None`` when no authenticated scope\n is available.\n \"\"\"\n user_id = getattr(self, \"_user_id\", None)\n if not user_id:\n graph = getattr(getattr(self, \"_vertex\", None), \"graph\", None)\n user_id = getattr(graph, \"user_id\", None)\n return str(user_id) if user_id else None\n\n def _build_tool_output(self) -> Output:\n # Do not cache Toolset output. This is separate from the MCP \"Use Cached Server\" (use_cache)\n # toggle: Langflow's Output.cache defaults to True and was memoizing the first to_toolkit()\n # result, so per-request tweaks/headers never refreshed bound tools even when use_cache=False.\n return Output(\n name=TOOL_OUTPUT_NAME,\n display_name=TOOL_OUTPUT_DISPLAY_NAME,\n method=\"to_toolkit\",\n types=[\"Tool\"],\n cache=False,\n )\n\n def map_outputs(self) -> None:\n \"\"\"Override the persisted ``component_as_tool`` cache flag from saved flow JSON.\n\n ``_build_tool_output`` already returns the output with ``cache=False``, but the\n flow JSON for existing flows often stores ``cache: true`` for ``component_as_tool``\n and that persisted value wins over the declaration. Forcing ``cache=False`` here\n guarantees saved flows also bypass Output memoization and get a fresh tool list\n on every run.\n \"\"\"\n super().map_outputs()\n if TOOL_OUTPUT_NAME in self._outputs_map:\n self._outputs_map[TOOL_OUTPUT_NAME].cache = False\n\n default_keys: list[str] = [\n \"code\",\n \"_type\",\n \"tool_mode\",\n \"tool_placeholder\",\n \"mcp_server\",\n \"tool\",\n \"use_cache\",\n \"verify_ssl\",\n \"headers\",\n \"tool_execution_timeout\",\n ]\n\n display_name = \"MCP Tools\"\n description = \"Connect to an MCP server to use its tools.\"\n documentation: str = \"https://docs.langflow.org/mcp-tools\"\n icon = \"Mcp\"\n name = \"MCPTools\"\n\n inputs = [\n McpInput(\n name=\"mcp_server\",\n display_name=\"MCP Server\",\n info=\"Select the MCP Server that will be used by this component\",\n real_time_refresh=True,\n ),\n BoolInput(\n name=\"use_cache\",\n display_name=\"Use Cached Server\",\n info=(\n \"Enable caching of MCP Server and tools to improve performance. \"\n \"Disable to always fetch fresh tools and server updates.\"\n ),\n value=False,\n advanced=True,\n ),\n BoolInput(\n name=\"verify_ssl\",\n display_name=\"Verify SSL Certificate\",\n info=(\n \"Enable SSL certificate verification for HTTPS connections. \"\n \"Disable only for development/testing with self-signed certificates.\"\n ),\n value=True,\n advanced=True,\n ),\n DictInput(\n name=\"headers\",\n display_name=\"Headers\",\n info=(\n \"HTTP headers to include with MCP server requests. \"\n \"Useful for authentication (e.g., Authorization header). \"\n \"These headers override any headers configured in the MCP server settings.\"\n ),\n advanced=True,\n is_list=True,\n ),\n FloatInput(\n name=\"tool_execution_timeout\",\n display_name=\"Tool Execution Timeout (seconds)\",\n info=(\n \"Maximum time to wait for tool execution before timing out. \"\n \"Supports decimal values for sub-second timeouts (e.g., 0.01 for 10ms). \"\n \"Set to 0 to use the system-configured MCP timeout.\"\n ),\n value=0.0,\n range_spec={\"min\": 0.0, \"max\": 3600.0, \"step\": 0.01},\n real_time_refresh=True,\n advanced=True,\n ),\n DropdownInput(\n name=\"tool\",\n display_name=\"Tool\",\n options=[],\n value=\"\",\n info=\"Select the tool to execute\",\n show=False,\n required=True,\n real_time_refresh=True,\n refresh_button=True,\n ),\n MessageTextInput(\n name=\"tool_placeholder\",\n display_name=\"Tool Placeholder\",\n info=\"Placeholder for the tool\",\n value=\"\",\n show=False,\n # Tool Mode is a capability of the component, not of the selected\n # server. Advertising it up front keeps the toolbar from waiting\n # for the MCP server's tool-discovery request to finish.\n tool_mode=True,\n ),\n ]\n\n outputs = [\n Output(display_name=\"Response\", name=\"response\", method=\"build_output\"),\n ]\n\n async def _validate_schema_inputs(self, tool_obj) -> list[InputTypes]:\n \"\"\"Validate and process schema inputs for a tool.\"\"\"\n try:\n if not tool_obj or not hasattr(tool_obj, \"args_schema\"):\n msg = \"Invalid tool object or missing input schema\"\n raise ValueError(msg)\n\n input_schema = tool_obj.args_schema\n if not input_schema:\n msg = f\"Empty input schema for tool '{tool_obj.name}'\"\n raise ValueError(msg)\n\n schema_inputs = schema_to_langflow_inputs(input_schema)\n if not schema_inputs:\n msg = f\"No input parameters defined for tool '{tool_obj.name}'\"\n await logger.awarning(msg)\n return []\n\n except Exception as e:\n msg = f\"Error validating schema inputs: {e!s}\"\n await logger.aexception(msg)\n raise ValueError(msg) from e\n else:\n return schema_inputs\n\n async def _ensure_cached_mcp_stdio_access(self, server_config: dict) -> None:\n \"\"\"Reapply the current stdio policy before returning cached tools.\"\"\"\n try:\n from langflow.api.v2.mcp import ensure_mcp_stdio_access\n from langflow.services.database.models.user.crud import get_user_by_id\n\n from lfx.services.deps import get_settings_service\n except ModuleNotFoundError as e:\n missing_module = e.name or \"\"\n if missing_module != \"langflow\" and not missing_module.startswith(\"langflow.\"):\n raise\n return\n\n async with session_scope() as db:\n if not self.user_id:\n msg = \"User ID is required for fetching MCP tools.\"\n raise ValueError(msg)\n current_user = await get_user_by_id(db, self.user_id)\n\n ensure_mcp_stdio_access(server_config, current_user, get_settings_service().settings)\n\n async def update_tool_list(self, mcp_server_value=None):\n # Accepts mcp_server_value as dict {name, config} or uses self.mcp_server\n mcp_server = mcp_server_value if mcp_server_value is not None else getattr(self, \"mcp_server\", None)\n server_name = None\n server_config_from_value = None\n if isinstance(mcp_server, dict):\n server_name = mcp_server.get(\"name\")\n server_config_from_value = mcp_server.get(\"config\")\n else:\n server_name = mcp_server\n if not server_name:\n self.tools = []\n await logger.adebug(\"MCP update_tool_list: empty server_name, clearing tools\")\n return [], {\"name\": server_name, \"config\": server_config_from_value}\n\n servers_cache_key = self._mcp_servers_cache_key(server_name)\n\n # Check if caching is enabled, default to False. The cross-request cache must never\n # be used without an authenticated tenant scope; the per-instance TTL cache remains\n # available in standalone/UI contexts.\n use_cache = getattr(self, \"use_cache\", False)\n use_shared_cache = use_cache and self._mcp_cache_user_id() is not None\n header_keys = sorted(self._normalized_headers_for_cache().keys())\n await logger.adebug(\n \"MCP update_tool_list: start server=%r use_cache=%s use_shared_cache=%s shared_cache_key=%r header_keys=%s\",\n server_name,\n use_cache,\n use_shared_cache,\n servers_cache_key,\n header_keys,\n )\n\n async with self._update_tool_list_lock:\n # Use shared cache if available and caching is enabled\n cached = None\n if use_shared_cache:\n servers_cache = safe_cache_get(self._shared_component_cache, \"servers\", {})\n cached = servers_cache.get(servers_cache_key) if isinstance(servers_cache, dict) else None\n\n if cached is not None:\n try:\n tools_from_cache = cached[\"tools\"]\n server_config_from_value = cached[\"config\"]\n except (TypeError, KeyError, AttributeError) as e:\n # Handle corrupted cache data by clearing it and continuing to fetch fresh tools\n msg = f\"Unable to use cached data for MCP Server{server_name}: {e}\"\n await logger.awarning(msg)\n # Clear the corrupted cache entry\n current_servers_cache = safe_cache_get(self._shared_component_cache, \"servers\", {})\n if isinstance(current_servers_cache, dict) and servers_cache_key in current_servers_cache:\n current_servers_cache.pop(servers_cache_key)\n safe_cache_set(self._shared_component_cache, \"servers\", current_servers_cache)\n else:\n try:\n await self._ensure_cached_mcp_stdio_access(server_config_from_value)\n except Exception as e:\n msg = f\"Error updating tool list: {e!s}\"\n await logger.aexception(msg)\n raise ValueError(msg) from e\n else:\n self.tools = tools_from_cache\n self.tool_names = [t.name for t in self.tools if hasattr(t, \"name\")]\n self._tool_cache = cached[\"tool_cache\"]\n await logger.adebug(\n \"MCP update_tool_list: shared_servers_cache HIT count=%d server=%r\",\n len(self.tools),\n server_name,\n )\n return self.tools, {\"name\": server_name, \"config\": server_config_from_value}\n\n try:\n # Try to fetch from database first to ensure we have the latest config.\n # This ensures database updates (like editing a server) take effect.\n # When running in LFX standalone mode the full Langflow package and\n # database may not be available — in that case we skip the DB lookup\n # and fall back to the config embedded in the flow (server_config_from_value).\n server_config_from_db = None\n current_user = None\n settings_service = None\n ensure_mcp_stdio_access = None\n try:\n from langflow.api.v2.mcp import ensure_mcp_stdio_access, get_server\n from langflow.services.database.models.user.crud import get_user_by_id\n\n from lfx.services.deps import get_settings_service\n except ModuleNotFoundError as e:\n # Deliberately `except ModuleNotFoundError` (not `except ImportError`): a\n # plain ImportError here means `get_server` / `get_user_by_id` was removed\n # from an installed Langflow — a real API break that should NOT be\n # swallowed as \"standalone mode\". ModuleNotFoundError alone covers the\n # \"Langflow absent\" case.\n #\n # Even within ModuleNotFoundError, only treat this as LFX standalone mode\n # when one of the target Langflow modules is itself missing. Transitive\n # ModuleNotFoundError (e.g. a dependency like sqlmodel failing to import\n # inside langflow.*) indicates a real bug in the full Langflow stack and\n # must surface — otherwise we would silently use a stale flow-embedded\n # config when DB config should have taken precedence.\n missing_module = e.name or \"\"\n is_langflow_standalone = missing_module == \"langflow\" or missing_module.startswith(\"langflow.\")\n if not is_langflow_standalone:\n raise\n await logger.ainfo(\n \"Langflow package not available; using MCP server config from flow value (LFX standalone mode).\"\n )\n else:\n async with session_scope() as db:\n if not self.user_id:\n msg = \"User ID is required for fetching MCP tools.\"\n raise ValueError(msg)\n current_user = await get_user_by_id(db, self.user_id)\n settings_service = get_settings_service()\n\n # Try to get server config from DB/API\n server_config_from_db = await get_server(\n server_name,\n current_user,\n db,\n storage_service=get_storage_service(),\n settings_service=settings_service,\n )\n\n # Resolve config with proper precedence: DB takes priority, falls back to value\n server_config = resolve_mcp_config(\n server_name=server_name,\n server_config_from_value=server_config_from_value,\n server_config_from_db=server_config_from_db,\n )\n\n if not server_config:\n self.tools = []\n await logger.awarning(\n \"MCP update_tool_list: no server_config after resolve server=%r\",\n server_name,\n )\n msg = (\n f\"MCP server '{server_name}' is not configured. \"\n \"Add a server with this name in Settings > MCP Servers before running this flow.\"\n )\n raise ValueError(msg)\n\n # The REST API applies this policy when a stdio server is registered,\n # but imported flows can carry the same process-spawning config in the\n # MCP component value. Reapply the policy to the resolved config at the\n # component boundary before update_tools reaches the subprocess client.\n if ensure_mcp_stdio_access is not None and current_user is not None and settings_service is not None:\n ensure_mcp_stdio_access(server_config, current_user, settings_service.settings)\n\n # Add verify_ssl option to server config if not present\n if \"verify_ssl\" not in server_config:\n verify_ssl = getattr(self, \"verify_ssl\", True)\n server_config[\"verify_ssl\"] = verify_ssl\n\n # Merge headers from component input with server config headers\n # Component headers take precedence over server config headers\n component_headers = getattr(self, \"headers\", None) or []\n if component_headers:\n # Convert list of {\"key\": k, \"value\": v} to dict\n component_headers_dict = {}\n if isinstance(component_headers, list):\n for item in component_headers:\n if isinstance(item, dict) and \"key\" in item and \"value\" in item:\n component_headers_dict[item[\"key\"]] = item[\"value\"]\n elif isinstance(component_headers, dict):\n component_headers_dict = component_headers\n\n if component_headers_dict:\n existing_headers = server_config.get(\"headers\", {}) or {}\n # Ensure existing_headers is a dict (convert from list if needed)\n if isinstance(existing_headers, list):\n existing_dict = {}\n for item in existing_headers:\n if isinstance(item, dict) and \"key\" in item and \"value\" in item:\n existing_dict[item[\"key\"]] = item[\"value\"]\n existing_headers = existing_dict\n merged_headers = {**existing_headers, **component_headers_dict}\n server_config[\"headers\"] = merged_headers\n # Get request_variables from graph context for global variable resolution\n request_variables = None\n end_user_id = None\n if hasattr(self, \"graph\") and self.graph:\n if hasattr(self.graph, \"context\"):\n request_variables = self.graph.context.get(\"request_variables\")\n # Serving-plane end-user id (set by the entry-point scoping); forwarded only\n # to allowlisted internal MCP targets by update_tools (fail-closed).\n end_user_id = getattr(self.graph, \"end_user_id\", None)\n\n # Load global variables only when the config actually references them, so a\n # static config still costs no query -- but a URL-only reference now counts.\n # The load must NOT be skipped just because the request carried overrides: a\n # request that overrides one variable still needs every other referenced\n # variable resolved from the database.\n db_variables: dict[str, str] | None = None\n if config_uses_global_variables(server_config):\n try:\n from lfx.services.deps import get_variable_service\n\n variable_service = get_variable_service()\n # ``get_all_decrypted_variables`` is DB-service-only; the minimal\n # lfx VariableService (now registered by ``lfx serve``) lacks it, so\n # skip cleanly rather than raising into the broad except below.\n if variable_service and hasattr(variable_service, \"get_all_decrypted_variables\"):\n async with session_scope() as db:\n db_variables = await variable_service.get_all_decrypted_variables(\n user_id=self.user_id, session=db\n )\n except Exception as e: # noqa: BLE001\n await logger.awarning(\"Failed to load global variables for MCP component\", exc_info=e)\n\n # Headers may resolve from either source, per-request values winning on\n # conflict (matching ``CustomComponent.get_variable``). Dropping the database\n # side whenever the request carried anything would send an unresolved variable\n # *name* upstream as the header value (#14604).\n #\n # The URL still resolves from the database only, via ``url_variables`` below:\n # request_variables carry the caller's X-Langflow-Global-Var-* values, and a\n # caller must not be able to choose where this flow connects.\n request_variables = {**(db_variables or {}), **(request_variables or {})} or None\n\n await logger.adebug(\n \"MCP update_tool_list: calling update_tools server=%r mode_headers=%s\",\n server_name,\n sorted((server_config.get(\"headers\") or {}).keys())\n if isinstance(server_config.get(\"headers\"), dict)\n else \"list-or-empty\",\n )\n\n timeout = self._normalize_tool_execution_timeout()\n\n _, tool_list, tool_cache = await update_tools(\n server_name=server_name,\n server_config=server_config,\n mcp_stdio_client=self.stdio_client,\n mcp_streamable_http_client=self.streamable_http_client,\n request_variables=request_variables,\n url_variables=db_variables,\n tool_execution_timeout=timeout,\n current_user_id=self.user_id,\n end_user_id=end_user_id,\n )\n\n self.tool_names = [tool.name for tool in tool_list if hasattr(tool, \"name\")]\n self._tool_cache = tool_cache\n self.tools = tool_list\n\n await logger.adebug(\n \"MCP update_tool_list: fetched from MCP count=%d server=%r\",\n len(tool_list),\n server_name,\n )\n\n # Cache the result only if caching is enabled\n if use_shared_cache:\n cache_data = {\n \"tools\": tool_list,\n \"tool_names\": self.tool_names,\n \"tool_cache\": tool_cache,\n \"config\": server_config,\n }\n\n # Safely update the servers cache with bounded size (FIFO eviction).\n current_servers_cache = safe_cache_get(self._shared_component_cache, \"servers\", {})\n if isinstance(current_servers_cache, dict):\n # Because the cache key now includes a header hash, a tenant that\n # rotates session tokens would grow this map without bound. Drop\n # the oldest entry when over the limit.\n max_entries = self.SHARED_SERVERS_CACHE_MAX_ENTRIES\n while (\n len(current_servers_cache) >= max_entries and servers_cache_key not in current_servers_cache\n ):\n oldest_key = next(iter(current_servers_cache))\n current_servers_cache.pop(oldest_key, None)\n current_servers_cache[servers_cache_key] = cache_data\n safe_cache_set(self._shared_component_cache, \"servers\", current_servers_cache)\n await logger.adebug(\n \"MCP update_tool_list: wrote shared_servers_cache key=%r size=%d\",\n servers_cache_key,\n len(current_servers_cache),\n )\n\n except (TimeoutError, asyncio.TimeoutError) as e:\n msg = (\n f\"Timeout updating tool list: {e!s}. \"\n \"Raise ``LANGFLOW_MCP_SERVER_TIMEOUT`` for the deployment if the MCP \"\n \"server legitimately needs more time to respond.\"\n )\n await logger.aexception(msg)\n raise TimeoutError(msg) from e\n except Exception as e:\n msg = f\"Error updating tool list: {e!s}\"\n await logger.aexception(msg)\n raise ValueError(msg) from e\n else:\n return tool_list, {\"name\": server_name, \"config\": server_config}\n\n async def update_build_config(self, build_config: dict, field_value: str, field_name: str | None = None) -> dict:\n \"\"\"Toggle the visibility of connection-specific fields based on the selected mode.\"\"\"\n try:\n is_refresh = bool(build_config.get(\"is_refresh\", False))\n if field_name == \"tool\":\n try:\n # Always refresh tools when cache is disabled, or when tools list is empty\n # This ensures database edits are reflected immediately when cache is disabled\n use_cache = getattr(self, \"use_cache\", False)\n if is_refresh:\n self.tools = []\n if is_refresh or len(self.tools) == 0 or not use_cache:\n try:\n self.tools, build_config[\"mcp_server\"][\"value\"] = await self.update_tool_list()\n build_config[\"tool\"][\"options\"] = [tool.name for tool in self.tools]\n build_config[\"tool\"][\"placeholder\"] = \"Select a tool\"\n except (TimeoutError, asyncio.TimeoutError) as e:\n msg = f\"Timeout updating tool list: {e!s}\"\n await logger.aexception(msg)\n if not build_config[\"tools_metadata\"][\"show\"]:\n build_config[\"tool\"][\"show\"] = True\n build_config[\"tool\"][\"options\"] = []\n build_config[\"tool\"][\"value\"] = \"\"\n build_config[\"tool\"][\"placeholder\"] = msg\n else:\n build_config[\"tool\"][\"show\"] = False\n except ValueError as e:\n msg = f\"Error updating tool list: {e!s}\"\n await logger.aexception(msg)\n if not build_config[\"tools_metadata\"][\"show\"]:\n build_config[\"tool\"][\"show\"] = True\n build_config[\"tool\"][\"options\"] = []\n build_config[\"tool\"][\"value\"] = \"\"\n build_config[\"tool\"][\"placeholder\"] = msg\n else:\n build_config[\"tool\"][\"show\"] = False\n\n if field_value == \"\":\n return build_config\n tool_obj = None\n for tool in self.tools:\n if tool.name == field_value:\n tool_obj = tool\n break\n if tool_obj is None:\n msg = f\"Tool {field_value} not found in available tools: {self.tools}\"\n await logger.awarning(msg)\n return build_config\n await self._update_tool_config(build_config, field_value)\n except Exception as e:\n build_config[\"tool\"][\"options\"] = []\n msg = f\"Failed to update tools: {e!s}\"\n raise ValueError(msg) from e\n else:\n return build_config\n elif field_name == \"mcp_server\":\n if not field_value:\n build_config[\"tool\"][\"show\"] = False\n build_config[\"tool\"][\"options\"] = []\n build_config[\"tool\"][\"value\"] = \"\"\n build_config[\"tool\"][\"placeholder\"] = \"\"\n build_config[\"tool_placeholder\"][\"tool_mode\"] = True\n self.remove_non_default_keys(build_config)\n return build_config\n\n build_config[\"tool_placeholder\"][\"tool_mode\"] = True\n\n current_server_name = field_value.get(\"name\") if isinstance(field_value, dict) else field_value\n build_config_server_value = build_config.get(\"mcp_server\", {}).get(\"value\")\n build_config_server_name = (\n build_config_server_value.get(\"name\")\n if isinstance(build_config_server_value, dict)\n else build_config_server_value\n )\n servers_cache_key_ui = self._mcp_servers_cache_key(current_server_name) if current_server_name else \"\"\n _last_selected_server = safe_cache_get(self._shared_component_cache, \"last_selected_server\", \"\")\n # Only treat as a server change if there was a previous server selection.\n # Cold cache (_last_selected_server=\"\") on initial flow load is NOT a server change —\n # the user didn't switch anything, the backend just hasn't seen this component yet.\n server_changed = bool(\n (_last_selected_server and current_server_name != _last_selected_server)\n or (build_config_server_name and current_server_name != build_config_server_name)\n )\n\n # Determine if \"Tool Mode\" is active by checking if the tool dropdown is hidden.\n is_in_tool_mode = build_config[\"tools_metadata\"][\"show\"]\n\n # Get use_cache setting to determine if we should use cached data\n use_cache = getattr(self, \"use_cache\", False)\n has_shared_cache_scope = self._mcp_cache_user_id() is not None\n use_shared_cache = use_cache and has_shared_cache_scope\n\n # Fast path: if server didn't change and we already have options, keep them as-is\n # BUT only if caching is enabled, we're in tool mode, or it's the initial load\n existing_options = build_config.get(\"tool\", {}).get(\"options\") or []\n if not is_refresh and not server_changed and existing_options:\n # In non-tool mode with cache disabled, skip the fast path to force refresh\n # BUT on initial load (cold cache), always preserve saved options from the flow\n if not is_in_tool_mode and not use_cache and _last_selected_server:\n pass # Continue to refresh logic below (user-initiated with cache disabled)\n else:\n if not is_in_tool_mode:\n build_config[\"tool\"][\"show\"] = True\n safe_cache_set(self._shared_component_cache, \"last_selected_server\", current_server_name)\n return build_config\n\n # To avoid unnecessary updates, only proceed if the server has actually changed\n # OR if caching is disabled (to force refresh in non-tool mode)\n if (\n not is_refresh\n and (_last_selected_server in (current_server_name, \"\"))\n and build_config[\"tool\"][\"show\"]\n and use_shared_cache\n ):\n if current_server_name:\n servers_cache = safe_cache_get(self._shared_component_cache, \"servers\", {})\n if isinstance(servers_cache, dict):\n cached = servers_cache.get(servers_cache_key_ui)\n if cached is not None and cached.get(\"tool_names\"):\n cached_tools = cached[\"tool_names\"]\n current_tools = build_config[\"tool\"][\"options\"]\n if current_tools == cached_tools:\n return build_config\n else:\n return build_config\n safe_cache_set(self._shared_component_cache, \"last_selected_server\", current_server_name)\n\n # When cache is disabled, clear any cached data for this server\n # This ensures we always fetch fresh data from the database\n if (is_refresh or not use_cache) and current_server_name and has_shared_cache_scope:\n servers_cache = safe_cache_get(self._shared_component_cache, \"servers\", {})\n if isinstance(servers_cache, dict) and servers_cache_key_ui in servers_cache:\n servers_cache.pop(servers_cache_key_ui)\n safe_cache_set(self._shared_component_cache, \"servers\", servers_cache)\n\n # Check if tools are already cached for this server before clearing\n cached_tools = None\n if current_server_name and use_shared_cache and not is_refresh:\n servers_cache = safe_cache_get(self._shared_component_cache, \"servers\", {})\n if isinstance(servers_cache, dict):\n cached = servers_cache.get(servers_cache_key_ui)\n if cached is not None:\n try:\n cached_tools = cached[\"tools\"]\n self.tools = cached_tools\n self.tool_names = cached[\"tool_names\"]\n self._tool_cache = cached[\"tool_cache\"]\n except (TypeError, KeyError, AttributeError) as e:\n # Handle corrupted cache data by ignoring it\n msg = f\"Unable to use cached data for MCP Server,{current_server_name}: {e}\"\n await logger.awarning(msg)\n cached_tools = None\n\n # Clear tools when cache is disabled OR when we don't have cached tools\n # This ensures fresh tools are fetched after database edits\n if is_refresh or not cached_tools or not use_cache:\n self.tools = [] # Clear previous tools to force refresh\n\n # Clear previous tool inputs if:\n # 1. Server actually changed\n # 2. Cache is disabled (meaning tool list will be refreshed)\n if is_refresh or server_changed or not use_cache:\n self.remove_non_default_keys(build_config)\n\n # Only show the tool dropdown if not in tool_mode\n if not is_in_tool_mode:\n build_config[\"tool\"][\"show\"] = True\n if cached_tools:\n # Use cached tools to populate options immediately\n build_config[\"tool\"][\"options\"] = [tool.name for tool in cached_tools]\n build_config[\"tool\"][\"placeholder\"] = \"Select a tool\"\n else:\n # Actually fetch tools now instead of deferring to a frontend callback.\n # The frontend has no reliable mechanism to trigger a second\n # update_build_config call for the \"tool\" field after this response,\n # so we must populate the options here.\n try:\n self.tools, build_config[\"mcp_server\"][\"value\"] = await self.update_tool_list(\n mcp_server_value=field_value\n )\n build_config[\"tool\"][\"options\"] = [tool.name for tool in self.tools]\n build_config[\"tool\"][\"placeholder\"] = \"Select a tool\"\n except (TimeoutError, asyncio.TimeoutError) as e:\n msg = f\"Timeout loading tools for MCP server: {e!s}\"\n await logger.aexception(msg)\n build_config[\"tool\"][\"options\"] = []\n build_config[\"tool\"][\"placeholder\"] = \"Timeout on MCP server\"\n except (ValueError, ImportError, ConnectionError, OSError, RuntimeError) as e:\n msg = f\"Error loading tools for MCP server: {e!s}\"\n await logger.aexception(msg)\n build_config[\"tool\"][\"options\"] = []\n build_config[\"tool\"][\"placeholder\"] = (\n \"Error on MCP Server\" if \"'NoneType' object has no attribute 'id'\" in msg else msg\n )\n # Force a value refresh only when the user genuinely switched servers.\n # server_changed is only True for real user-initiated changes (not initial load).\n if server_changed:\n build_config[\"tool\"][\"value\"] = uuid.uuid4()\n else:\n # Keep the tool dropdown hidden if in tool_mode\n self._not_load_actions = True\n build_config[\"tool\"][\"show\"] = False\n\n elif field_name == \"tool_mode\":\n build_config[\"tool\"][\"placeholder\"] = \"\"\n build_config[\"tool\"][\"show\"] = not bool(field_value) and bool(build_config[\"mcp_server\"])\n self.remove_non_default_keys(build_config)\n self.tool = build_config[\"tool\"][\"value\"]\n if field_value:\n self._not_load_actions = True\n else:\n build_config[\"tool\"][\"value\"] = uuid.uuid4()\n build_config[\"tool\"][\"show\"] = True\n # Fetch tools immediately instead of showing \"Loading tools...\"\n try:\n self.tools, build_config[\"mcp_server\"][\"value\"] = await self.update_tool_list()\n build_config[\"tool\"][\"options\"] = [tool.name for tool in self.tools]\n build_config[\"tool\"][\"placeholder\"] = \"Select a tool\"\n except (TimeoutError, asyncio.TimeoutError) as e:\n msg = f\"Timeout loading tools when toggling tool mode: {e!s}\"\n await logger.aexception(msg)\n build_config[\"tool\"][\"options\"] = []\n build_config[\"tool\"][\"placeholder\"] = msg\n except (ValueError, ImportError, ConnectionError, OSError, RuntimeError) as e:\n msg = f\"Error loading tools when toggling tool mode: {e!s}\"\n await logger.aexception(msg)\n build_config[\"tool\"][\"options\"] = []\n build_config[\"tool\"][\"placeholder\"] = msg\n elif field_name == \"tool_execution_timeout\":\n try:\n val = float(field_value) if field_value not in (None, \"\") else 0.0\n except (ValueError, TypeError):\n val = 0.0\n if val < 0:\n build_config[\"tool_execution_timeout\"][\"placeholder\"] = (\n \"⚠ Value must be ≥ 0. Negative timeouts cause immediate failures.\"\n )\n build_config[\"tool_execution_timeout\"][\"value\"] = 0.0\n else:\n build_config[\"tool_execution_timeout\"][\"placeholder\"] = \"\"\n elif field_name == \"tools_metadata\":\n self._not_load_actions = False\n\n except Exception as e:\n msg = f\"Error in update_build_config: {e!s}\"\n await logger.aexception(msg)\n raise ValueError(msg) from e\n else:\n return build_config\n\n @staticmethod\n def _unwrap_optional_annotation(annotation: Any) -> Any:\n \"\"\"Remove a single None branch from a union annotation.\"\"\"\n if isinstance(annotation, UnionType):\n non_none = [item for item in get_args(annotation) if item is not type(None)]\n if len(non_none) == 1:\n return non_none[0]\n return annotation\n\n if get_origin(annotation) is None:\n return annotation\n\n non_none = [item for item in get_args(annotation) if item is not type(None)]\n if len(non_none) == 1 and len(non_none) != len(get_args(annotation)):\n return non_none[0]\n return annotation\n\n @classmethod\n def _is_object_like_annotation(cls, annotation: Any) -> bool:\n \"\"\"Return True when the annotation represents a dict-like payload.\"\"\"\n annotation = cls._unwrap_optional_annotation(annotation)\n origin = get_origin(annotation)\n if origin is dict:\n return True\n return annotation is dict or (isinstance(annotation, type) and issubclass(annotation, BaseModel))\n\n @classmethod\n def _should_include_tool_argument(cls, model_field: Any, value: Any) -> bool:\n \"\"\"Omit blank optional values so MCP server defaults remain intact.\"\"\"\n if value is None:\n return False\n\n if model_field.is_required():\n return True\n\n if isinstance(value, str) and value == \"\":\n return False\n\n return not (\n value == {} and model_field.default is None and cls._is_object_like_annotation(model_field.annotation)\n )\n\n def _build_tool_kwargs(self, args_schema: type[BaseModel]) -> dict[str, Any]:\n \"\"\"Collect tool kwargs from component inputs, omitting blank optional values.\"\"\"\n kwargs: dict[str, Any] = {}\n for arg_name, model_field in args_schema.model_fields.items():\n # MCP argument names come from the server and can match component methods or metadata.\n value = self._attributes.get(arg_name)\n if arg_name not in self._attributes and arg_name in self._inputs:\n value = self._inputs[arg_name].value\n if isinstance(value, Message):\n value = value.text\n\n if self._should_include_tool_argument(model_field, value):\n kwargs[arg_name] = value\n\n return kwargs\n\n def get_inputs_for_all_tools(self, tools: list) -> dict:\n \"\"\"Get input schemas for all tools.\"\"\"\n inputs = {}\n for tool in tools:\n if not tool or not hasattr(tool, \"name\"):\n continue\n try:\n langflow_inputs = schema_to_langflow_inputs(tool.args_schema)\n inputs[tool.name] = langflow_inputs\n except (AttributeError, ValueError, TypeError, KeyError) as e:\n msg = f\"Error getting inputs for tool {getattr(tool, 'name', 'unknown')}: {e!s}\"\n logger.exception(msg)\n continue\n return inputs\n\n def remove_non_default_keys(self, build_config: dict) -> None:\n \"\"\"Remove non-default keys from the build config.\"\"\"\n for key in list(build_config.keys()):\n if key not in self.default_keys:\n build_config.pop(key)\n\n async def _update_tool_config(self, build_config: dict, tool_name: str) -> None:\n \"\"\"Update tool configuration with proper error handling.\"\"\"\n if not self.tools:\n self.tools, build_config[\"mcp_server\"][\"value\"] = await self.update_tool_list()\n\n if not tool_name:\n return\n\n tool_obj = next((tool for tool in self.tools if tool.name == tool_name), None)\n if not tool_obj:\n msg = f\"Tool {tool_name} not found in available tools: {self.tools}\"\n self.remove_non_default_keys(build_config)\n build_config[\"tool\"][\"value\"] = \"\"\n await logger.awarning(msg)\n return\n\n try:\n # Store current values before removing inputs (only for the current tool)\n current_values = {}\n for key, value in build_config.items():\n if key not in self.default_keys and isinstance(value, dict) and \"value\" in value:\n current_values[key] = value[\"value\"]\n\n # Remove ALL non-default keys (all previous tool inputs)\n self.remove_non_default_keys(build_config)\n\n # Get and validate new inputs for the selected tool\n self.schema_inputs = await self._validate_schema_inputs(tool_obj)\n if not self.schema_inputs:\n msg = f\"No input parameters to configure for tool '{tool_name}'\"\n await logger.ainfo(msg)\n return\n\n # Add new inputs to build config for the selected tool only\n for schema_input in self.schema_inputs:\n if not schema_input or not hasattr(schema_input, \"name\"):\n msg = \"Invalid schema input detected, skipping\"\n await logger.awarning(msg)\n continue\n\n try:\n name = schema_input.name\n input_dict = schema_input.to_dict()\n input_dict.setdefault(\"value\", None)\n input_dict.setdefault(\"required\", True)\n\n build_config[name] = input_dict\n\n # Preserve existing value if the parameter name exists in current_values\n if name in current_values:\n build_config[name][\"value\"] = current_values[name]\n\n except (AttributeError, KeyError, TypeError) as e:\n msg = f\"Error processing schema input {schema_input}: {e!s}\"\n await logger.aexception(msg)\n continue\n except ValueError as e:\n msg = f\"Schema validation error for tool {tool_name}: {e!s}\"\n await logger.aexception(msg)\n self.schema_inputs = []\n return\n except (AttributeError, KeyError, TypeError) as e:\n msg = f\"Error updating tool config: {e!s}\"\n await logger.aexception(msg)\n raise ValueError(msg) from e\n\n async def build_output(self) -> DataFrame:\n \"\"\"Build output with improved error handling and validation.\"\"\"\n try:\n self.tools, _ = await self.update_tool_list()\n if self.tool != \"\":\n # Set session context for persistent MCP sessions using Langflow session ID\n session_context = self._get_session_context()\n if session_context:\n self.stdio_client.set_session_context(session_context)\n self.streamable_http_client.set_session_context(session_context)\n exec_tool = self._tool_cache[self.tool]\n kwargs = self._build_tool_kwargs(exec_tool.args_schema)\n unflattened_kwargs = maybe_unflatten_dict(kwargs)\n\n output = await exec_tool.coroutine(**unflattened_kwargs)\n if getattr(output, \"isError\", False):\n # isError=True is a FAILED call; treating its content as data makes it look successful.\n error_text = \" \".join(str(item.model_dump().get(\"text\") or \"\") for item in output.content).strip()\n msg = f\"MCP tool '{self.tool}' failed: {error_text or 'no error detail provided'}\"\n raise ValueError(msg)\n tool_content = []\n for item in output.content:\n item_dict = item.model_dump()\n item_dict = self.process_output_item(item_dict)\n tool_content.append(item_dict)\n\n if isinstance(tool_content, list) and all(isinstance(x, dict) for x in tool_content):\n return DataFrame(tool_content)\n return DataFrame(data=tool_content)\n return DataFrame(data=[{\"error\": \"You must select a tool\"}])\n except Exception as e:\n msg = f\"Error in build_output: {e!s}\"\n await logger.aexception(msg)\n raise ValueError(msg) from e\n\n def process_output_item(self, item_dict):\n \"\"\"Process the output of a tool.\"\"\"\n if item_dict.get(\"type\") == \"text\":\n text = item_dict.get(\"text\")\n try:\n parsed = json.loads(text)\n # Ensure we always return a dictionary for DataFrame compatibility\n if isinstance(parsed, dict):\n return parsed\n # Wrap non-dict parsed values in a dictionary\n return {\"text\": text, \"parsed_value\": parsed, \"type\": \"text\"} # noqa: TRY300\n except json.JSONDecodeError:\n return item_dict\n return item_dict\n\n def _get_session_context(self) -> str | None:\n \"\"\"Get the Langflow session ID for MCP session caching.\"\"\"\n # Try to get session ID from the component's execution context\n if hasattr(self, \"graph\") and hasattr(self.graph, \"session_id\"):\n session_id = self.graph.session_id\n # Include server name to ensure different servers get different sessions\n server_name = \"\"\n mcp_server = getattr(self, \"mcp_server\", None)\n if isinstance(mcp_server, dict):\n server_name = mcp_server.get(\"name\", \"\")\n elif mcp_server:\n server_name = str(mcp_server)\n return f\"{session_id}_{server_name}\" if session_id else None\n return None\n\n async def _get_tools(self):\n \"\"\"Load tools for the agent toolkit; always refresh from ``update_tool_list``.\n\n ``_not_load_actions`` only applies to UI build_config flows (tool dropdown). Agent\n runs must always bind the current tool list (including after header/tweak changes).\n\n A short-lived TTL cache (``TOOL_TTL_SECS``, header-hash-keyed) skips the MCP\n round-trip when the same auth context is re-queried quickly (e.g. parallel agent\n steps sharing the same tweaked headers). The cache is per component lineage (including\n isolated invocation copies) and bounded by ``TOOL_TTL_MAX_ENTRIES``; it is distinct from\n the \"Use Cached Server\" (``use_cache``) toggle which controls the shared cross-request cache.\n \"\"\"\n mcp_server = getattr(self, \"mcp_server\", None)\n srv = mcp_server.get(\"name\") if isinstance(mcp_server, dict) else mcp_server\n\n ttl = self.TOOL_TTL_SECS\n ttl_key = self._mcp_servers_cache_key(srv or \"\") if ttl > 0 and srv else \"\"\n\n # TTL cache lookup + expired-entry eviction.\n if ttl > 0 and ttl_key:\n cached = self._ttl_tool_cache.get(ttl_key)\n if cached is not None:\n ts, cached_tools = cached\n age = time.monotonic() - ts\n if age < ttl:\n await logger.adebug(\n \"MCP _get_tools: TTL cache hit count=%d age=%.1fs server=%r\",\n len(cached_tools),\n age,\n srv,\n )\n return cached_tools\n # Stale — drop it so the size check below stays tight.\n self._ttl_tool_cache.pop(ttl_key, None)\n\n await logger.adebug(\"MCP _get_tools: fetching tool list server=%r\", srv)\n tools, _ = await self.update_tool_list(mcp_server)\n await logger.adebug(\"MCP _get_tools: fetched %d tools server=%r\", len(tools), srv)\n\n # TTL cache store with bounded size (FIFO eviction of the oldest entry).\n if ttl > 0 and ttl_key and tools:\n if len(self._ttl_tool_cache) >= self.TOOL_TTL_MAX_ENTRIES:\n # dict preserves insertion order — pop the oldest entry.\n oldest_key = next(iter(self._ttl_tool_cache))\n self._ttl_tool_cache.pop(oldest_key, None)\n self._ttl_tool_cache[ttl_key] = (time.monotonic(), tools)\n\n return tools\n"
},
"headers": {
"_input_type": "DictInput",
@@ -2469,15 +2456,11 @@
},
"dragging": false,
"id": "MCPTools-uu7m3",
- "measured": {
- "height": 52,
- "width": 192
- },
"position": {
- "x": 1354.9717187892868,
- "y": 1390.1647783430062
+ "x": 1349.7106454154339,
+ "y": 1389.6849508019752
},
- "selected": false,
+ "selected": true,
"type": "genericNode"
},
{
@@ -2675,10 +2658,6 @@
},
"dragging": false,
"id": "OpenAICompatibleEmbedding-ix4WD",
- "measured": {
- "height": 52,
- "width": 192
- },
"position": {
"x": 564.5974527712519,
"y": 1726.63184778373
@@ -2735,7 +2714,7 @@
],
"frozen": false,
"icon": "OpenSearch",
- "last_updated": "2026-09-16T13:50:51.381Z",
+ "last_updated": "2026-10-29T18:15:34.737Z",
"legacy": false,
"metadata": {
"code_hash": "1a2a5b8d0ca7",
@@ -2772,7 +2751,7 @@
{
"allows_loop": false,
"cache": true,
- "display_name": "Toolset",
+ "display_name": "Search Results",
"group_outputs": false,
"hidden": null,
"loop_types": null,
@@ -2794,7 +2773,7 @@
"value": "1098eea1-6649-4e1d-aed1-b77249fb8dd0"
},
"_frontend_node_folder_id": {
- "value": "de367ed7-7bbb-4e2e-ba97-12db63476e42"
+ "value": "afa57272-6d34-4d1c-bf31-27ffad110b3a"
},
"_type": "Component",
"auth_mode": {
@@ -3650,10 +3629,6 @@
},
"dragging": false,
"id": "OpenSearchVectorStoreComponentMultimodalMultiEmbedding-3x7Ll",
- "measured": {
- "height": 971,
- "width": 320
- },
"position": {
"x": 1325.2370822527334,
"y": 1777.486986803783
@@ -3989,10 +3964,6 @@
},
"dragging": false,
"id": "OpenAICompatibleLLM-u2sHy",
- "measured": {
- "height": 80,
- "width": 192
- },
"position": {
"x": 1353.9033717672569,
"y": 1464.2864703820715
@@ -4002,16 +3973,16 @@
}
],
"viewport": {
- "x": -96.62088161770657,
- "y": -663.0789136004726,
- "zoom": 0.5122246092163092
+ "x": -38.57383234988595,
+ "y": -743.3719143709377,
+ "zoom": 0.6083891782554004
}
},
"description": "OpenRAG OpenSearch Agent",
"endpoint_name": null,
"id": "1098eea1-6649-4e1d-aed1-b77249fb8dd0",
"is_component": false,
- "last_tested_version": "1.12.2",
+ "last_tested_version": "1.12.8",
"locked": true,
"name": "OpenRAG OpenSearch Agent Flow",
"tags": [
diff --git a/flows/openrag_nudges.json b/flows/openrag_nudges.json
index 73f10c356..1f677204b 100644
--- a/flows/openrag_nudges.json
+++ b/flows/openrag_nudges.json
@@ -416,10 +416,6 @@
},
"dragging": false,
"id": "Prompt Template-Wo6kR",
- "measured": {
- "height": 80,
- "width": 192
- },
"position": {
"x": 1153.5888851298432,
"y": 1486.860784211668
@@ -722,10 +718,6 @@
},
"dragging": false,
"id": "ChatInput-7W1BE",
- "measured": {
- "height": 52,
- "width": 192
- },
"position": {
"x": 847.7008874324687,
"y": 1560.6273308605132
@@ -763,20 +755,20 @@
"icon": "MessagesSquare",
"legacy": false,
"metadata": {
- "code_hash": "84009527d08c",
+ "code_hash": "0aab1c78e1dc",
"dependencies": {
"dependencies": [
{
"name": "orjson",
- "version": "3.11.8"
+ "version": "3.11.9"
},
{
"name": "fastapi",
- "version": "0.135.1"
+ "version": "0.139.2"
},
{
"name": "lfx",
- "version": null
+ "version": "1.12.8"
}
],
"total_dependencies": 3
@@ -810,6 +802,7 @@
"clean_data": {
"_input_type": "BoolInput",
"advanced": true,
+ "api_editable": false,
"display_name": "Basic Clean Data",
"dynamic": false,
"info": "Whether to clean data before converting to string.",
@@ -829,6 +822,7 @@
},
"code": {
"advanced": true,
+ "api_editable": false,
"dynamic": true,
"fileTypes": [],
"file_path": "",
@@ -843,11 +837,12 @@
"show": true,
"title_case": false,
"type": "code",
- "value": "from collections.abc import Generator\nfrom typing import Any\n\nimport orjson\nfrom fastapi.encoders import jsonable_encoder\n\nfrom lfx.base.io.chat import ChatComponent\nfrom lfx.helpers.data import safe_convert\nfrom lfx.inputs.inputs import BoolInput, DropdownInput, HandleInput, MessageTextInput\nfrom lfx.schema.data import Data\nfrom lfx.schema.dataframe import DataFrame\nfrom lfx.schema.message import Message\nfrom lfx.schema.properties import Source\nfrom lfx.template.field.base import Output\nfrom lfx.utils.constants import (\n MESSAGE_SENDER_AI,\n MESSAGE_SENDER_NAME_AI,\n MESSAGE_SENDER_USER,\n)\n\n\nclass ChatOutput(ChatComponent):\n display_name = \"Chat Output\"\n description = \"Display a chat message in the Playground.\"\n documentation: str = \"https://docs.langflow.org/chat-input-and-output\"\n icon = \"MessagesSquare\"\n name = \"ChatOutput\"\n minimized = True\n\n inputs = [\n HandleInput(\n name=\"input_value\",\n display_name=\"Inputs\",\n info=\"Message to be passed as output.\",\n input_types=[\"Data\", \"JSON\", \"DataFrame\", \"Table\", \"Message\"],\n required=True,\n ),\n BoolInput(\n name=\"should_store_message\",\n display_name=\"Store Messages\",\n info=\"Store the message in the history.\",\n value=True,\n advanced=True,\n ),\n DropdownInput(\n name=\"sender\",\n display_name=\"Sender Type\",\n options=[MESSAGE_SENDER_AI, MESSAGE_SENDER_USER],\n value=MESSAGE_SENDER_AI,\n advanced=True,\n info=\"Type of sender.\",\n ),\n MessageTextInput(\n name=\"sender_name\",\n display_name=\"Sender Name\",\n info=\"Name of the sender.\",\n value=MESSAGE_SENDER_NAME_AI,\n advanced=True,\n ),\n MessageTextInput(\n name=\"session_id\",\n display_name=\"Session ID\",\n info=\"The session ID of the chat. If empty, the current session ID parameter will be used.\",\n advanced=True,\n ),\n MessageTextInput(\n name=\"context_id\",\n display_name=\"Context ID\",\n info=\"The context ID of the chat. Adds an extra layer to the local memory.\",\n value=\"\",\n advanced=True,\n ),\n MessageTextInput(\n name=\"data_template\",\n display_name=\"Data Template\",\n value=\"{text}\",\n advanced=True,\n info=\"Template to convert Data to Text. If left empty, it will be dynamically set to the Data's text key.\",\n ),\n BoolInput(\n name=\"clean_data\",\n display_name=\"Basic Clean Data\",\n value=True,\n advanced=True,\n info=\"Whether to clean data before converting to string.\",\n ),\n ]\n outputs = [\n Output(\n display_name=\"Output Message\",\n name=\"message\",\n method=\"message_response\",\n ),\n ]\n\n def _build_source(self, id_: str | None, display_name: str | None, source: str | None) -> Source:\n source_dict = {}\n if id_:\n source_dict[\"id\"] = id_\n if display_name:\n source_dict[\"display_name\"] = display_name\n if source:\n # Handle case where source is a ChatOpenAI object\n if hasattr(source, \"model_name\"):\n source_dict[\"source\"] = source.model_name\n elif hasattr(source, \"model\"):\n source_dict[\"source\"] = str(source.model)\n else:\n source_dict[\"source\"] = str(source)\n return Source(**source_dict)\n\n async def message_response(self) -> Message:\n # First convert the input to string if needed\n text = self.convert_to_string()\n\n # Get source properties\n source, _, display_name, source_id = self.get_properties_from_source_component()\n\n # Create or use existing Message object\n if isinstance(self.input_value, Message) and not self.is_connected_to_chat_input():\n message = self.input_value\n # Update message properties\n message.text = text\n # Preserve existing session_id from the incoming message if it exists\n existing_session_id = message.session_id\n else:\n message = Message(text=text)\n existing_session_id = None\n\n # Set message properties\n message.sender = self.sender\n message.sender_name = self.sender_name\n # Preserve session_id from incoming message, or use component/graph session_id\n message.session_id = (\n self.session_id or existing_session_id or (self.graph.session_id if hasattr(self, \"graph\") else None) or \"\"\n )\n message.context_id = self.context_id\n message.flow_id = self.graph.flow_id if hasattr(self, \"graph\") else None\n message.properties.source = self._build_source(source_id, display_name, source)\n\n # Store message if needed\n if message.session_id and self.should_store_message:\n stored_message = await self.send_message(message)\n self.message.value = stored_message\n message = stored_message\n\n # Set accumulated token usage from all upstream LLM vertices.\n # This must happen AFTER send_message() because streaming captures\n # usage from chunks and would overwrite accumulated totals.\n if hasattr(self, \"_vertex\") and self._vertex is not None:\n accumulated_usage = self._vertex._accumulate_upstream_token_usage() # noqa: SLF001\n if accumulated_usage:\n message.properties.usage = accumulated_usage\n if self.should_store_message and message.get_id():\n message = await self._update_stored_message(message)\n await self._send_message_event(message, id_=message.get_id())\n\n self.status = message\n return message\n\n def _serialize_data(self, data: Data) -> str:\n \"\"\"Serialize Data object to JSON string.\"\"\"\n # Convert data.data to JSON-serializable format\n serializable_data = jsonable_encoder(data.data)\n # Serialize with orjson, enabling pretty printing with indentation\n json_bytes = orjson.dumps(serializable_data, option=orjson.OPT_INDENT_2)\n # Convert bytes to string and wrap in Markdown code blocks\n return \"```json\\n\" + json_bytes.decode(\"utf-8\") + \"\\n```\"\n\n def _validate_input(self) -> None:\n \"\"\"Validate the input data and raise ValueError if invalid.\"\"\"\n if self.input_value is None:\n msg = \"Input data cannot be None\"\n raise ValueError(msg)\n if isinstance(self.input_value, list) and not all(\n isinstance(item, Message | Data | DataFrame | str) for item in self.input_value\n ):\n invalid_types = [\n type(item).__name__\n for item in self.input_value\n if not isinstance(item, Message | Data | DataFrame | str)\n ]\n msg = f\"Expected Data or DataFrame or Message or str, got {invalid_types}\"\n raise TypeError(msg)\n if not isinstance(\n self.input_value,\n Message | Data | DataFrame | str | list | Generator | type(None),\n ):\n type_name = type(self.input_value).__name__\n msg = f\"Expected Data or DataFrame or Message or str, Generator or None, got {type_name}\"\n raise TypeError(msg)\n\n def convert_to_string(self) -> str | Generator[Any, None, None]:\n \"\"\"Convert input data to string with proper error handling.\"\"\"\n self._validate_input()\n if isinstance(self.input_value, list):\n clean_data: bool = getattr(self, \"clean_data\", False)\n return \"\\n\".join([safe_convert(item, clean_data=clean_data) for item in self.input_value])\n if isinstance(self.input_value, Generator):\n return self.input_value\n return safe_convert(self.input_value)\n"
+ "value": "from collections.abc import Generator\nfrom typing import Any\n\nimport orjson\nfrom fastapi.encoders import jsonable_encoder\n\nfrom lfx.base.io.chat import ChatComponent\nfrom lfx.helpers.data import safe_convert\nfrom lfx.inputs.inputs import BoolInput, DropdownInput, HandleInput, MessageTextInput\nfrom lfx.schema.data import Data\nfrom lfx.schema.dataframe import DataFrame\nfrom lfx.schema.message import Message\nfrom lfx.schema.properties import Source\nfrom lfx.template.field.base import Output\nfrom lfx.utils.constants import (\n MESSAGE_SENDER_AI,\n MESSAGE_SENDER_NAME_AI,\n MESSAGE_SENDER_USER,\n)\n\n\nclass ChatOutput(ChatComponent):\n display_name = \"Chat Output\"\n description = \"Display a chat message in the Playground.\"\n documentation: str = \"https://docs.langflow.org/chat-input-and-output\"\n icon = \"MessagesSquare\"\n name = \"ChatOutput\"\n minimized = True\n\n inputs = [\n HandleInput(\n name=\"input_value\",\n display_name=\"Inputs\",\n info=\"Message to be passed as output.\",\n input_types=[\"Data\", \"JSON\", \"DataFrame\", \"Table\", \"Message\"],\n required=True,\n ),\n BoolInput(\n name=\"should_store_message\",\n display_name=\"Store Messages\",\n info=\"Store the message in the history.\",\n value=True,\n advanced=True,\n ),\n DropdownInput(\n name=\"sender\",\n display_name=\"Sender Type\",\n options=[MESSAGE_SENDER_AI, MESSAGE_SENDER_USER],\n value=MESSAGE_SENDER_AI,\n advanced=True,\n info=\"Type of sender.\",\n ),\n MessageTextInput(\n name=\"sender_name\",\n display_name=\"Sender Name\",\n info=\"Name of the sender.\",\n value=MESSAGE_SENDER_NAME_AI,\n advanced=True,\n ),\n MessageTextInput(\n name=\"session_id\",\n display_name=\"Session ID\",\n info=\"The session ID of the chat. If empty, the current session ID parameter will be used.\",\n advanced=True,\n ),\n MessageTextInput(\n name=\"context_id\",\n display_name=\"Context ID\",\n info=\"The context ID of the chat. Adds an extra layer to the local memory.\",\n value=\"\",\n advanced=True,\n ),\n MessageTextInput(\n name=\"data_template\",\n display_name=\"Data Template\",\n value=\"{text}\",\n advanced=True,\n info=\"Template to convert Data to Text. If left empty, it will be dynamically set to the Data's text key.\",\n ),\n BoolInput(\n name=\"clean_data\",\n display_name=\"Basic Clean Data\",\n value=True,\n advanced=True,\n info=\"Whether to clean data before converting to string.\",\n ),\n ]\n outputs = [\n Output(\n display_name=\"Output Message\",\n name=\"message\",\n method=\"message_response\",\n ),\n ]\n\n def _build_source(self, id_: str | None, display_name: str | None, source: str | None) -> Source:\n source_dict = {}\n if id_:\n source_dict[\"id\"] = id_\n if display_name:\n source_dict[\"display_name\"] = display_name\n if source:\n # Handle case where source is a ChatOpenAI object\n if hasattr(source, \"model_name\"):\n source_dict[\"source\"] = source.model_name\n elif hasattr(source, \"model\"):\n source_dict[\"source\"] = str(source.model)\n else:\n source_dict[\"source\"] = str(source)\n return Source(**source_dict)\n\n async def message_response(self) -> Message:\n # First convert the input to string if needed\n text = self.convert_to_string()\n\n # Get source properties\n source, _, display_name, source_id = self.get_properties_from_source_component()\n\n # Create or use existing Message object\n if isinstance(self.input_value, Message) and not self.is_connected_to_chat_input():\n message = self.input_value\n # Update message properties\n message.text = text\n # Preserve existing session_id from the incoming message if it exists\n existing_session_id = message.session_id\n else:\n message = Message(text=text)\n existing_session_id = None\n\n # Set message properties\n message.sender = self.sender\n message.sender_name = self.sender_name\n # Preserve session_id from incoming message, or use component/graph session_id\n message.session_id = (\n self.session_id or existing_session_id or (self.graph.session_id if hasattr(self, \"graph\") else None) or \"\"\n )\n message.context_id = self.context_id\n message.flow_id = self.graph.flow_id if hasattr(self, \"graph\") else None\n message.properties.source = self._build_source(source_id, display_name, source)\n\n # Store message if needed\n if message.session_id and self.should_store_message:\n stored_message = await self.send_message(message)\n self.message.value = stored_message\n message = stored_message\n\n # Set accumulated token usage from all upstream LLM vertices.\n # This must happen AFTER send_message() because streaming captures\n # usage from chunks and would overwrite accumulated totals.\n if hasattr(self, \"_vertex\") and self._vertex is not None:\n accumulated_usage = self._vertex._accumulate_upstream_token_usage() # noqa: SLF001\n if accumulated_usage:\n message.properties.usage = accumulated_usage\n if self.should_store_message and message.get_id():\n message = await self._update_stored_message(message)\n await self._send_message_event(message, id_=message.get_id())\n\n self.status = message\n return message\n\n def _serialize_data(self, data: Data) -> str:\n \"\"\"Serialize Data object to JSON string.\"\"\"\n # Convert data.data to JSON-serializable format\n serializable_data = jsonable_encoder(data.data)\n # Serialize with orjson, enabling pretty printing with indentation\n json_bytes = orjson.dumps(serializable_data, option=orjson.OPT_INDENT_2)\n # Convert bytes to string and wrap in Markdown code blocks\n return \"```json\\n\" + json_bytes.decode(\"utf-8\") + \"\\n```\"\n\n def _validate_input(self) -> None:\n \"\"\"Validate the input data and raise ValueError if invalid.\"\"\"\n if self.input_value is None:\n msg = \"Input data cannot be None\"\n raise ValueError(msg)\n if isinstance(self.input_value, list) and not all(\n isinstance(item, Message | Data | DataFrame | str) for item in self.input_value\n ):\n invalid_types = [\n type(item).__name__\n for item in self.input_value\n if not isinstance(item, Message | Data | DataFrame | str)\n ]\n msg = f\"Expected Data or DataFrame or Message or str, got {invalid_types}\"\n raise TypeError(msg)\n if not isinstance(\n self.input_value,\n Message | Data | DataFrame | str | list | Generator | type(None),\n ):\n type_name = type(self.input_value).__name__\n msg = f\"Expected Data or DataFrame or Message or str, Generator or None, got {type_name}\"\n raise TypeError(msg)\n\n def convert_to_string(self) -> str | Generator[Any, None, None]:\n \"\"\"Convert input data to string with proper error handling.\"\"\"\n self._validate_input()\n clean_data: bool = getattr(self, \"clean_data\", False)\n if isinstance(self.input_value, list):\n return \"\\n\".join([safe_convert(item, clean_data=clean_data) for item in self.input_value])\n if isinstance(self.input_value, Generator):\n return self.input_value\n return safe_convert(self.input_value, clean_data=clean_data)\n"
},
"context_id": {
"_input_type": "MessageTextInput",
"advanced": true,
+ "api_editable": false,
"display_name": "Context ID",
"dynamic": false,
"info": "The context ID of the chat. Adds an extra layer to the local memory.",
@@ -873,6 +868,7 @@
"data_template": {
"_input_type": "MessageTextInput",
"advanced": true,
+ "api_editable": false,
"display_name": "Data Template",
"dynamic": false,
"info": "Template to convert Data to Text. If left empty, it will be dynamically set to the Data's text key.",
@@ -898,6 +894,7 @@
"input_value": {
"_input_type": "HandleInput",
"advanced": false,
+ "api_editable": false,
"display_name": "Inputs",
"dynamic": false,
"info": "Message to be passed as output.",
@@ -924,6 +921,7 @@
"sender": {
"_input_type": "DropdownInput",
"advanced": true,
+ "api_editable": false,
"combobox": false,
"dialog_inputs": {},
"display_name": "Sender Type",
@@ -951,6 +949,7 @@
"sender_name": {
"_input_type": "MessageTextInput",
"advanced": true,
+ "api_editable": false,
"display_name": "Sender Name",
"dynamic": false,
"info": "Name of the sender.",
@@ -976,6 +975,7 @@
"session_id": {
"_input_type": "MessageTextInput",
"advanced": true,
+ "api_editable": false,
"display_name": "Session ID",
"dynamic": false,
"info": "The session ID of the chat. If empty, the current session ID parameter will be used.",
@@ -1001,6 +1001,7 @@
"should_store_message": {
"_input_type": "BoolInput",
"advanced": true,
+ "api_editable": false,
"display_name": "Store Messages",
"dynamic": false,
"info": "Store the message in the history.",
@@ -1026,10 +1027,6 @@
},
"dragging": false,
"id": "ChatOutput-axewE",
- "measured": {
- "height": 52,
- "width": 192
- },
"position": {
"x": 1746.4377826023422,
"y": 1516.674256662252
@@ -1188,10 +1185,6 @@
},
"dragging": false,
"id": "TextInput-BG2U3",
- "measured": {
- "height": 129,
- "width": 192
- },
"position": {
"x": -64.9892298542755,
"y": 1521.7195088276985
@@ -1394,10 +1387,6 @@
},
"dragging": false,
"id": "ParserComponent-x6BS7",
- "measured": {
- "height": 80,
- "width": 192
- },
"position": {
"x": 851.661470235947,
"y": 1429.639922711361
@@ -2325,10 +2314,6 @@
},
"dragging": false,
"id": "ext:openrag:OpenSearchVectorStoreComponentMultimodalMultiEmbedding@extra-yrQui",
- "measured": {
- "height": 134,
- "width": 192
- },
"position": {
"x": 427.43787902817417,
"y": 1385.8198377353997
@@ -2531,10 +2516,6 @@
},
"dragging": false,
"id": "OpenAICompatibleEmbedding-CdOpv",
- "measured": {
- "height": 52,
- "width": 192
- },
"position": {
"x": -59.381270855785424,
"y": 1384.3606108469412
@@ -2870,10 +2851,6 @@
},
"dragging": false,
"id": "OpenAICompatibleLLM-0PA0e",
- "measured": {
- "height": 80,
- "width": 192
- },
"position": {
"x": 1465.188148380901,
"y": 1500.6561249291267
@@ -2883,16 +2860,16 @@
}
],
"viewport": {
- "x": 62.972880126394784,
- "y": -487.04165750950597,
- "zoom": 0.6467039747513049
+ "x": -32.13162615756107,
+ "y": -436.5092869506609,
+ "zoom": 0.5926192448490153
}
},
"description": "OpenRAG OpenSearch Nudges generator, based on the OpenSearch documents and the chat history.",
"endpoint_name": null,
"id": "ebc01d31-1976-46ce-a385-b0240327226c",
"is_component": false,
- "last_tested_version": "1.12.0",
+ "last_tested_version": "1.12.8",
"locked": true,
"name": "OpenRAG OpenSearch Nudges Flow",
"tags": [
diff --git a/flows/openrag_url_mcp.json b/flows/openrag_url_mcp.json
index 689cc51b6..2cff82493 100644
--- a/flows/openrag_url_mcp.json
+++ b/flows/openrag_url_mcp.json
@@ -91,105 +91,110 @@
},
{
"animated": false,
+ "className": "",
"data": {
"sourceHandle": {
- "dataType": "URLComponent",
- "id": "URLComponent-lnA0q",
- "name": "page_results",
+ "dataType": "Operations",
+ "id": "Operations-fX1Im",
+ "name": "dataframe_output",
"output_types": [
"Table"
]
},
"targetHandle": {
- "fieldName": "df",
- "id": "Operations-jsRu6",
+ "fieldName": "data_inputs",
+ "id": "ext:openrag:OpenRAGSplitTextComponent@extra-tutKN",
"inputTypes": [
+ "Data",
+ "JSON",
"DataFrame",
- "Table"
+ "Table",
+ "Message"
],
"type": "other"
}
},
- "id": "xy-edge__URLComponent-lnA0q{œdataTypeœ:œURLComponentœ,œidœ:œURLComponent-lnA0qœ,œnameœ:œpage_resultsœ,œoutput_typesœ:[œTableœ]}-Operations-jsRu6{œfieldNameœ:œdfœ,œidœ:œOperations-jsRu6œ,œinputTypesœ:[œDataFrameœ,œTableœ],œtypeœ:œotherœ}",
+ "id": "xy-edge__Operations-fX1Im{œdataTypeœ:œOperationsœ,œidœ:œOperations-fX1Imœ,œnameœ:œdataframe_outputœ,œoutput_typesœ:[œTableœ]}-ext:openrag:OpenRAGSplitTextComponent@extra-tutKN{œfieldNameœ:œdata_inputsœ,œidœ:œext:openrag:OpenRAGSplitTextComponent@extra-tutKNœ,œinputTypesœ:[œDataœ,œJSONœ,œDataFrameœ,œTableœ,œMessageœ],œtypeœ:œotherœ}",
"selected": false,
- "source": "URLComponent-lnA0q",
- "sourceHandle": "{œdataTypeœ:œURLComponentœ,œidœ:œURLComponent-lnA0qœ,œnameœ:œpage_resultsœ,œoutput_typesœ:[œTableœ]}",
- "target": "Operations-jsRu6",
- "targetHandle": "{œfieldNameœ:œdfœ,œidœ:œOperations-jsRu6œ,œinputTypesœ:[œDataFrameœ,œTableœ],œtypeœ:œotherœ}"
+ "source": "Operations-fX1Im",
+ "sourceHandle": "{œdataTypeœ:œOperationsœ,œidœ:œOperations-fX1Imœ,œnameœ:œdataframe_outputœ,œoutput_typesœ:[œTableœ]}",
+ "target": "ext:openrag:OpenRAGSplitTextComponent@extra-tutKN",
+ "targetHandle": "{œfieldNameœ:œdata_inputsœ,œidœ:œext:openrag:OpenRAGSplitTextComponent@extra-tutKNœ,œinputTypesœ:[œDataœ,œJSONœ,œDataFrameœ,œTableœ,œMessageœ],œtypeœ:œotherœ}"
},
{
"animated": false,
+ "className": "",
"data": {
"sourceHandle": {
- "dataType": "Operations",
- "id": "Operations-jsRu6",
- "name": "dataframe_output",
+ "dataType": "ext:openrag:OpenRAGSplitTextComponent@extra",
+ "id": "ext:openrag:OpenRAGSplitTextComponent@extra-tutKN",
+ "name": "dataframe",
"output_types": [
"Table"
]
},
"targetHandle": {
- "fieldName": "df",
- "id": "Operations-fX1Im",
+ "fieldName": "ingest_data",
+ "id": "OpenSearchVectorStoreComponentMultimodalMultiEmbedding-dihKf",
"inputTypes": [
+ "Data",
"DataFrame",
"Table"
],
"type": "other"
}
},
- "id": "xy-edge__Operations-jsRu6{œdataTypeœ:œOperationsœ,œidœ:œOperations-jsRu6œ,œnameœ:œdataframe_outputœ,œoutput_typesœ:[œTableœ]}-Operations-fX1Im{œfieldNameœ:œdfœ,œidœ:œOperations-fX1Imœ,œinputTypesœ:[œDataFrameœ,œTableœ],œtypeœ:œotherœ}",
+ "id": "xy-edge__ext:openrag:OpenRAGSplitTextComponent@extra-tutKN{œdataTypeœ:œext:openrag:OpenRAGSplitTextComponent@extraœ,œidœ:œext:openrag:OpenRAGSplitTextComponent@extra-tutKNœ,œnameœ:œdataframeœ,œoutput_typesœ:[œTableœ]}-OpenSearchVectorStoreComponentMultimodalMultiEmbedding-dihKf{œfieldNameœ:œingest_dataœ,œidœ:œOpenSearchVectorStoreComponentMultimodalMultiEmbedding-dihKfœ,œinputTypesœ:[œDataœ,œDataFrameœ,œTableœ],œtypeœ:œotherœ}",
"selected": false,
- "source": "Operations-jsRu6",
- "sourceHandle": "{œdataTypeœ:œOperationsœ,œidœ:œOperations-jsRu6œ,œnameœ:œdataframe_outputœ,œoutput_typesœ:[œTableœ]}",
- "target": "Operations-fX1Im",
- "targetHandle": "{œfieldNameœ:œdfœ,œidœ:œOperations-fX1Imœ,œinputTypesœ:[œDataFrameœ,œTableœ],œtypeœ:œotherœ}"
+ "source": "ext:openrag:OpenRAGSplitTextComponent@extra-tutKN",
+ "sourceHandle": "{œdataTypeœ:œext:openrag:OpenRAGSplitTextComponent@extraœ,œidœ:œext:openrag:OpenRAGSplitTextComponent@extra-tutKNœ,œnameœ:œdataframeœ,œoutput_typesœ:[œTableœ]}",
+ "target": "OpenSearchVectorStoreComponentMultimodalMultiEmbedding-dihKf",
+ "targetHandle": "{œfieldNameœ:œingest_dataœ,œidœ:œOpenSearchVectorStoreComponentMultimodalMultiEmbedding-dihKfœ,œinputTypesœ:[œDataœ,œDataFrameœ,œTableœ],œtypeœ:œotherœ}"
},
{
"animated": false,
+ "className": "",
"data": {
"sourceHandle": {
- "dataType": "Operations",
- "id": "Operations-fX1Im",
- "name": "dataframe_output",
+ "dataType": "URLComponent",
+ "id": "URLComponent-lnA0q",
+ "name": "page_results",
"output_types": [
"Table"
]
},
"targetHandle": {
- "fieldName": "data_inputs",
- "id": "ext:openrag:OpenRAGSplitTextComponent@extra-tutKN",
+ "fieldName": "df",
+ "id": "Operations-jsRu6",
"inputTypes": [
- "Data",
- "JSON",
"DataFrame",
- "Table",
- "Message"
+ "Table"
],
"type": "other"
}
},
- "id": "xy-edge__Operations-fX1Im{œdataTypeœ:œOperationsœ,œidœ:œOperations-fX1Imœ,œnameœ:œdataframe_outputœ,œoutput_typesœ:[œTableœ]}-ext:openrag:OpenRAGSplitTextComponent@extra-tutKN{œfieldNameœ:œdata_inputsœ,œidœ:œext:openrag:OpenRAGSplitTextComponent@extra-tutKNœ,œinputTypesœ:[œDataœ,œJSONœ,œDataFrameœ,œTableœ,œMessageœ],œtypeœ:œotherœ}",
+ "id": "xy-edge__URLComponent-lnA0q{œdataTypeœ:œURLComponentœ,œidœ:œURLComponent-lnA0qœ,œnameœ:œpage_resultsœ,œoutput_typesœ:[œTableœ]}-Operations-jsRu6{œfieldNameœ:œdfœ,œidœ:œOperations-jsRu6œ,œinputTypesœ:[œDataFrameœ,œTableœ],œtypeœ:œotherœ}",
"selected": false,
- "source": "Operations-fX1Im",
- "sourceHandle": "{œdataTypeœ:œOperationsœ,œidœ:œOperations-fX1Imœ,œnameœ:œdataframe_outputœ,œoutput_typesœ:[œTableœ]}",
- "target": "ext:openrag:OpenRAGSplitTextComponent@extra-tutKN",
- "targetHandle": "{œfieldNameœ:œdata_inputsœ,œidœ:œext:openrag:OpenRAGSplitTextComponent@extra-tutKNœ,œinputTypesœ:[œDataœ,œJSONœ,œDataFrameœ,œTableœ,œMessageœ],œtypeœ:œotherœ}"
+ "source": "URLComponent-lnA0q",
+ "sourceHandle": "{œdataTypeœ:œURLComponentœ,œidœ:œURLComponent-lnA0qœ,œnameœ:œpage_resultsœ,œoutput_typesœ:[œTableœ]}",
+ "target": "Operations-jsRu6",
+ "targetHandle": "{œfieldNameœ:œdfœ,œidœ:œOperations-jsRu6œ,œinputTypesœ:[œDataFrameœ,œTableœ],œtypeœ:œotherœ}"
},
{
"animated": false,
+ "className": "",
"data": {
"sourceHandle": {
- "dataType": "ext:openrag:OpenRAGSplitTextComponent@extra",
- "id": "ext:openrag:OpenRAGSplitTextComponent@extra-tutKN",
- "name": "dataframe",
+ "dataType": "Operations",
+ "id": "Operations-jsRu6",
+ "name": "dataframe_output",
"output_types": [
"Table"
]
},
"targetHandle": {
"fieldName": "df",
- "id": "Operations-uhog5",
+ "id": "Operations-fX1Im",
"inputTypes": [
"DataFrame",
"Table"
@@ -197,15 +202,16 @@
"type": "other"
}
},
- "id": "xy-edge__ext:openrag:OpenRAGSplitTextComponent@extra-tutKN{œdataTypeœ:œext:openrag:OpenRAGSplitTextComponent@extraœ,œidœ:œext:openrag:OpenRAGSplitTextComponent@extra-tutKNœ,œnameœ:œdataframeœ,œoutput_typesœ:[œTableœ]}-Operations-uhog5{œfieldNameœ:œdfœ,œidœ:œOperations-uhog5œ,œinputTypesœ:[œDataFrameœ,œTableœ],œtypeœ:œotherœ}",
+ "id": "xy-edge__Operations-jsRu6{œdataTypeœ:œOperationsœ,œidœ:œOperations-jsRu6œ,œnameœ:œdataframe_outputœ,œoutput_typesœ:[œTableœ]}-Operations-fX1Im{œfieldNameœ:œdfœ,œidœ:œOperations-fX1Imœ,œinputTypesœ:[œDataFrameœ,œTableœ],œtypeœ:œotherœ}",
"selected": false,
- "source": "ext:openrag:OpenRAGSplitTextComponent@extra-tutKN",
- "sourceHandle": "{œdataTypeœ:œext:openrag:OpenRAGSplitTextComponent@extraœ,œidœ:œext:openrag:OpenRAGSplitTextComponent@extra-tutKNœ,œnameœ:œdataframeœ,œoutput_typesœ:[œTableœ]}",
- "target": "Operations-uhog5",
- "targetHandle": "{œfieldNameœ:œdfœ,œidœ:œOperations-uhog5œ,œinputTypesœ:[œDataFrameœ,œTableœ],œtypeœ:œotherœ}"
+ "source": "Operations-jsRu6",
+ "sourceHandle": "{œdataTypeœ:œOperationsœ,œidœ:œOperations-jsRu6œ,œnameœ:œdataframe_outputœ,œoutput_typesœ:[œTableœ]}",
+ "target": "Operations-fX1Im",
+ "targetHandle": "{œfieldNameœ:œdfœ,œidœ:œOperations-fX1Imœ,œinputTypesœ:[œDataFrameœ,œTableœ],œtypeœ:œotherœ}"
},
{
"animated": false,
+ "className": "",
"data": {
"sourceHandle": {
"dataType": "ext:openrag:OpenRAGSplitTextComponent@extra",
@@ -216,22 +222,21 @@
]
},
"targetHandle": {
- "fieldName": "ingest_data",
- "id": "OpenSearchVectorStoreComponentMultimodalMultiEmbedding-dihKf",
+ "fieldName": "df",
+ "id": "Operations-uhog5",
"inputTypes": [
- "Data",
"DataFrame",
"Table"
],
"type": "other"
}
},
- "id": "xy-edge__ext:openrag:OpenRAGSplitTextComponent@extra-tutKN{œdataTypeœ:œext:openrag:OpenRAGSplitTextComponent@extraœ,œidœ:œext:openrag:OpenRAGSplitTextComponent@extra-tutKNœ,œnameœ:œdataframeœ,œoutput_typesœ:[œTableœ]}-OpenSearchVectorStoreComponentMultimodalMultiEmbedding-dihKf{œfieldNameœ:œingest_dataœ,œidœ:œOpenSearchVectorStoreComponentMultimodalMultiEmbedding-dihKfœ,œinputTypesœ:[œDataœ,œDataFrameœ,œTableœ],œtypeœ:œotherœ}",
+ "id": "xy-edge__ext:openrag:OpenRAGSplitTextComponent@extra-tutKN{œdataTypeœ:œext:openrag:OpenRAGSplitTextComponent@extraœ,œidœ:œext:openrag:OpenRAGSplitTextComponent@extra-tutKNœ,œnameœ:œdataframeœ,œoutput_typesœ:[œTableœ]}-Operations-uhog5{œfieldNameœ:œdfœ,œidœ:œOperations-uhog5œ,œinputTypesœ:[œDataFrameœ,œTableœ],œtypeœ:œotherœ}",
"selected": false,
"source": "ext:openrag:OpenRAGSplitTextComponent@extra-tutKN",
"sourceHandle": "{œdataTypeœ:œext:openrag:OpenRAGSplitTextComponent@extraœ,œidœ:œext:openrag:OpenRAGSplitTextComponent@extra-tutKNœ,œnameœ:œdataframeœ,œoutput_typesœ:[œTableœ]}",
- "target": "OpenSearchVectorStoreComponentMultimodalMultiEmbedding-dihKf",
- "targetHandle": "{œfieldNameœ:œingest_dataœ,œidœ:œOpenSearchVectorStoreComponentMultimodalMultiEmbedding-dihKfœ,œinputTypesœ:[œDataœ,œDataFrameœ,œTableœ],œtypeœ:œotherœ}"
+ "target": "Operations-uhog5",
+ "targetHandle": "{œfieldNameœ:œdfœ,œidœ:œOperations-uhog5œ,œinputTypesœ:[œDataFrameœ,œTableœ],œtypeœ:œotherœ}"
}
],
"nodes": [
@@ -669,10 +674,6 @@
},
"dragging": false,
"id": "URLComponent-lnA0q",
- "measured": {
- "height": 52,
- "width": 192
- },
"position": {
"x": 1115.3066289711646,
"y": 1622.0353383977624
@@ -975,10 +976,6 @@
},
"dragging": false,
"id": "ChatInput-sskrk",
- "measured": {
- "height": 52,
- "width": 192
- },
"position": {
"x": 827.8885363214571,
"y": 1622.940629214967
@@ -1016,20 +1013,20 @@
"icon": "MessagesSquare",
"legacy": false,
"metadata": {
- "code_hash": "84009527d08c",
+ "code_hash": "0aab1c78e1dc",
"dependencies": {
"dependencies": [
{
"name": "orjson",
- "version": "3.11.8"
+ "version": "3.11.9"
},
{
"name": "fastapi",
- "version": "0.135.1"
+ "version": "0.139.2"
},
{
"name": "lfx",
- "version": null
+ "version": "1.12.8"
}
],
"total_dependencies": 3
@@ -1063,6 +1060,7 @@
"clean_data": {
"_input_type": "BoolInput",
"advanced": true,
+ "api_editable": false,
"display_name": "Basic Clean Data",
"dynamic": false,
"info": "Whether to clean data before converting to string.",
@@ -1082,6 +1080,7 @@
},
"code": {
"advanced": true,
+ "api_editable": false,
"dynamic": true,
"fileTypes": [],
"file_path": "",
@@ -1096,11 +1095,12 @@
"show": true,
"title_case": false,
"type": "code",
- "value": "from collections.abc import Generator\nfrom typing import Any\n\nimport orjson\nfrom fastapi.encoders import jsonable_encoder\n\nfrom lfx.base.io.chat import ChatComponent\nfrom lfx.helpers.data import safe_convert\nfrom lfx.inputs.inputs import BoolInput, DropdownInput, HandleInput, MessageTextInput\nfrom lfx.schema.data import Data\nfrom lfx.schema.dataframe import DataFrame\nfrom lfx.schema.message import Message\nfrom lfx.schema.properties import Source\nfrom lfx.template.field.base import Output\nfrom lfx.utils.constants import (\n MESSAGE_SENDER_AI,\n MESSAGE_SENDER_NAME_AI,\n MESSAGE_SENDER_USER,\n)\n\n\nclass ChatOutput(ChatComponent):\n display_name = \"Chat Output\"\n description = \"Display a chat message in the Playground.\"\n documentation: str = \"https://docs.langflow.org/chat-input-and-output\"\n icon = \"MessagesSquare\"\n name = \"ChatOutput\"\n minimized = True\n\n inputs = [\n HandleInput(\n name=\"input_value\",\n display_name=\"Inputs\",\n info=\"Message to be passed as output.\",\n input_types=[\"Data\", \"JSON\", \"DataFrame\", \"Table\", \"Message\"],\n required=True,\n ),\n BoolInput(\n name=\"should_store_message\",\n display_name=\"Store Messages\",\n info=\"Store the message in the history.\",\n value=True,\n advanced=True,\n ),\n DropdownInput(\n name=\"sender\",\n display_name=\"Sender Type\",\n options=[MESSAGE_SENDER_AI, MESSAGE_SENDER_USER],\n value=MESSAGE_SENDER_AI,\n advanced=True,\n info=\"Type of sender.\",\n ),\n MessageTextInput(\n name=\"sender_name\",\n display_name=\"Sender Name\",\n info=\"Name of the sender.\",\n value=MESSAGE_SENDER_NAME_AI,\n advanced=True,\n ),\n MessageTextInput(\n name=\"session_id\",\n display_name=\"Session ID\",\n info=\"The session ID of the chat. If empty, the current session ID parameter will be used.\",\n advanced=True,\n ),\n MessageTextInput(\n name=\"context_id\",\n display_name=\"Context ID\",\n info=\"The context ID of the chat. Adds an extra layer to the local memory.\",\n value=\"\",\n advanced=True,\n ),\n MessageTextInput(\n name=\"data_template\",\n display_name=\"Data Template\",\n value=\"{text}\",\n advanced=True,\n info=\"Template to convert Data to Text. If left empty, it will be dynamically set to the Data's text key.\",\n ),\n BoolInput(\n name=\"clean_data\",\n display_name=\"Basic Clean Data\",\n value=True,\n advanced=True,\n info=\"Whether to clean data before converting to string.\",\n ),\n ]\n outputs = [\n Output(\n display_name=\"Output Message\",\n name=\"message\",\n method=\"message_response\",\n ),\n ]\n\n def _build_source(self, id_: str | None, display_name: str | None, source: str | None) -> Source:\n source_dict = {}\n if id_:\n source_dict[\"id\"] = id_\n if display_name:\n source_dict[\"display_name\"] = display_name\n if source:\n # Handle case where source is a ChatOpenAI object\n if hasattr(source, \"model_name\"):\n source_dict[\"source\"] = source.model_name\n elif hasattr(source, \"model\"):\n source_dict[\"source\"] = str(source.model)\n else:\n source_dict[\"source\"] = str(source)\n return Source(**source_dict)\n\n async def message_response(self) -> Message:\n # First convert the input to string if needed\n text = self.convert_to_string()\n\n # Get source properties\n source, _, display_name, source_id = self.get_properties_from_source_component()\n\n # Create or use existing Message object\n if isinstance(self.input_value, Message) and not self.is_connected_to_chat_input():\n message = self.input_value\n # Update message properties\n message.text = text\n # Preserve existing session_id from the incoming message if it exists\n existing_session_id = message.session_id\n else:\n message = Message(text=text)\n existing_session_id = None\n\n # Set message properties\n message.sender = self.sender\n message.sender_name = self.sender_name\n # Preserve session_id from incoming message, or use component/graph session_id\n message.session_id = (\n self.session_id or existing_session_id or (self.graph.session_id if hasattr(self, \"graph\") else None) or \"\"\n )\n message.context_id = self.context_id\n message.flow_id = self.graph.flow_id if hasattr(self, \"graph\") else None\n message.properties.source = self._build_source(source_id, display_name, source)\n\n # Store message if needed\n if message.session_id and self.should_store_message:\n stored_message = await self.send_message(message)\n self.message.value = stored_message\n message = stored_message\n\n # Set accumulated token usage from all upstream LLM vertices.\n # This must happen AFTER send_message() because streaming captures\n # usage from chunks and would overwrite accumulated totals.\n if hasattr(self, \"_vertex\") and self._vertex is not None:\n accumulated_usage = self._vertex._accumulate_upstream_token_usage() # noqa: SLF001\n if accumulated_usage:\n message.properties.usage = accumulated_usage\n if self.should_store_message and message.get_id():\n message = await self._update_stored_message(message)\n await self._send_message_event(message, id_=message.get_id())\n\n self.status = message\n return message\n\n def _serialize_data(self, data: Data) -> str:\n \"\"\"Serialize Data object to JSON string.\"\"\"\n # Convert data.data to JSON-serializable format\n serializable_data = jsonable_encoder(data.data)\n # Serialize with orjson, enabling pretty printing with indentation\n json_bytes = orjson.dumps(serializable_data, option=orjson.OPT_INDENT_2)\n # Convert bytes to string and wrap in Markdown code blocks\n return \"```json\\n\" + json_bytes.decode(\"utf-8\") + \"\\n```\"\n\n def _validate_input(self) -> None:\n \"\"\"Validate the input data and raise ValueError if invalid.\"\"\"\n if self.input_value is None:\n msg = \"Input data cannot be None\"\n raise ValueError(msg)\n if isinstance(self.input_value, list) and not all(\n isinstance(item, Message | Data | DataFrame | str) for item in self.input_value\n ):\n invalid_types = [\n type(item).__name__\n for item in self.input_value\n if not isinstance(item, Message | Data | DataFrame | str)\n ]\n msg = f\"Expected Data or DataFrame or Message or str, got {invalid_types}\"\n raise TypeError(msg)\n if not isinstance(\n self.input_value,\n Message | Data | DataFrame | str | list | Generator | type(None),\n ):\n type_name = type(self.input_value).__name__\n msg = f\"Expected Data or DataFrame or Message or str, Generator or None, got {type_name}\"\n raise TypeError(msg)\n\n def convert_to_string(self) -> str | Generator[Any, None, None]:\n \"\"\"Convert input data to string with proper error handling.\"\"\"\n self._validate_input()\n if isinstance(self.input_value, list):\n clean_data: bool = getattr(self, \"clean_data\", False)\n return \"\\n\".join([safe_convert(item, clean_data=clean_data) for item in self.input_value])\n if isinstance(self.input_value, Generator):\n return self.input_value\n return safe_convert(self.input_value)\n"
+ "value": "from collections.abc import Generator\nfrom typing import Any\n\nimport orjson\nfrom fastapi.encoders import jsonable_encoder\n\nfrom lfx.base.io.chat import ChatComponent\nfrom lfx.helpers.data import safe_convert\nfrom lfx.inputs.inputs import BoolInput, DropdownInput, HandleInput, MessageTextInput\nfrom lfx.schema.data import Data\nfrom lfx.schema.dataframe import DataFrame\nfrom lfx.schema.message import Message\nfrom lfx.schema.properties import Source\nfrom lfx.template.field.base import Output\nfrom lfx.utils.constants import (\n MESSAGE_SENDER_AI,\n MESSAGE_SENDER_NAME_AI,\n MESSAGE_SENDER_USER,\n)\n\n\nclass ChatOutput(ChatComponent):\n display_name = \"Chat Output\"\n description = \"Display a chat message in the Playground.\"\n documentation: str = \"https://docs.langflow.org/chat-input-and-output\"\n icon = \"MessagesSquare\"\n name = \"ChatOutput\"\n minimized = True\n\n inputs = [\n HandleInput(\n name=\"input_value\",\n display_name=\"Inputs\",\n info=\"Message to be passed as output.\",\n input_types=[\"Data\", \"JSON\", \"DataFrame\", \"Table\", \"Message\"],\n required=True,\n ),\n BoolInput(\n name=\"should_store_message\",\n display_name=\"Store Messages\",\n info=\"Store the message in the history.\",\n value=True,\n advanced=True,\n ),\n DropdownInput(\n name=\"sender\",\n display_name=\"Sender Type\",\n options=[MESSAGE_SENDER_AI, MESSAGE_SENDER_USER],\n value=MESSAGE_SENDER_AI,\n advanced=True,\n info=\"Type of sender.\",\n ),\n MessageTextInput(\n name=\"sender_name\",\n display_name=\"Sender Name\",\n info=\"Name of the sender.\",\n value=MESSAGE_SENDER_NAME_AI,\n advanced=True,\n ),\n MessageTextInput(\n name=\"session_id\",\n display_name=\"Session ID\",\n info=\"The session ID of the chat. If empty, the current session ID parameter will be used.\",\n advanced=True,\n ),\n MessageTextInput(\n name=\"context_id\",\n display_name=\"Context ID\",\n info=\"The context ID of the chat. Adds an extra layer to the local memory.\",\n value=\"\",\n advanced=True,\n ),\n MessageTextInput(\n name=\"data_template\",\n display_name=\"Data Template\",\n value=\"{text}\",\n advanced=True,\n info=\"Template to convert Data to Text. If left empty, it will be dynamically set to the Data's text key.\",\n ),\n BoolInput(\n name=\"clean_data\",\n display_name=\"Basic Clean Data\",\n value=True,\n advanced=True,\n info=\"Whether to clean data before converting to string.\",\n ),\n ]\n outputs = [\n Output(\n display_name=\"Output Message\",\n name=\"message\",\n method=\"message_response\",\n ),\n ]\n\n def _build_source(self, id_: str | None, display_name: str | None, source: str | None) -> Source:\n source_dict = {}\n if id_:\n source_dict[\"id\"] = id_\n if display_name:\n source_dict[\"display_name\"] = display_name\n if source:\n # Handle case where source is a ChatOpenAI object\n if hasattr(source, \"model_name\"):\n source_dict[\"source\"] = source.model_name\n elif hasattr(source, \"model\"):\n source_dict[\"source\"] = str(source.model)\n else:\n source_dict[\"source\"] = str(source)\n return Source(**source_dict)\n\n async def message_response(self) -> Message:\n # First convert the input to string if needed\n text = self.convert_to_string()\n\n # Get source properties\n source, _, display_name, source_id = self.get_properties_from_source_component()\n\n # Create or use existing Message object\n if isinstance(self.input_value, Message) and not self.is_connected_to_chat_input():\n message = self.input_value\n # Update message properties\n message.text = text\n # Preserve existing session_id from the incoming message if it exists\n existing_session_id = message.session_id\n else:\n message = Message(text=text)\n existing_session_id = None\n\n # Set message properties\n message.sender = self.sender\n message.sender_name = self.sender_name\n # Preserve session_id from incoming message, or use component/graph session_id\n message.session_id = (\n self.session_id or existing_session_id or (self.graph.session_id if hasattr(self, \"graph\") else None) or \"\"\n )\n message.context_id = self.context_id\n message.flow_id = self.graph.flow_id if hasattr(self, \"graph\") else None\n message.properties.source = self._build_source(source_id, display_name, source)\n\n # Store message if needed\n if message.session_id and self.should_store_message:\n stored_message = await self.send_message(message)\n self.message.value = stored_message\n message = stored_message\n\n # Set accumulated token usage from all upstream LLM vertices.\n # This must happen AFTER send_message() because streaming captures\n # usage from chunks and would overwrite accumulated totals.\n if hasattr(self, \"_vertex\") and self._vertex is not None:\n accumulated_usage = self._vertex._accumulate_upstream_token_usage() # noqa: SLF001\n if accumulated_usage:\n message.properties.usage = accumulated_usage\n if self.should_store_message and message.get_id():\n message = await self._update_stored_message(message)\n await self._send_message_event(message, id_=message.get_id())\n\n self.status = message\n return message\n\n def _serialize_data(self, data: Data) -> str:\n \"\"\"Serialize Data object to JSON string.\"\"\"\n # Convert data.data to JSON-serializable format\n serializable_data = jsonable_encoder(data.data)\n # Serialize with orjson, enabling pretty printing with indentation\n json_bytes = orjson.dumps(serializable_data, option=orjson.OPT_INDENT_2)\n # Convert bytes to string and wrap in Markdown code blocks\n return \"```json\\n\" + json_bytes.decode(\"utf-8\") + \"\\n```\"\n\n def _validate_input(self) -> None:\n \"\"\"Validate the input data and raise ValueError if invalid.\"\"\"\n if self.input_value is None:\n msg = \"Input data cannot be None\"\n raise ValueError(msg)\n if isinstance(self.input_value, list) and not all(\n isinstance(item, Message | Data | DataFrame | str) for item in self.input_value\n ):\n invalid_types = [\n type(item).__name__\n for item in self.input_value\n if not isinstance(item, Message | Data | DataFrame | str)\n ]\n msg = f\"Expected Data or DataFrame or Message or str, got {invalid_types}\"\n raise TypeError(msg)\n if not isinstance(\n self.input_value,\n Message | Data | DataFrame | str | list | Generator | type(None),\n ):\n type_name = type(self.input_value).__name__\n msg = f\"Expected Data or DataFrame or Message or str, Generator or None, got {type_name}\"\n raise TypeError(msg)\n\n def convert_to_string(self) -> str | Generator[Any, None, None]:\n \"\"\"Convert input data to string with proper error handling.\"\"\"\n self._validate_input()\n clean_data: bool = getattr(self, \"clean_data\", False)\n if isinstance(self.input_value, list):\n return \"\\n\".join([safe_convert(item, clean_data=clean_data) for item in self.input_value])\n if isinstance(self.input_value, Generator):\n return self.input_value\n return safe_convert(self.input_value, clean_data=clean_data)\n"
},
"context_id": {
"_input_type": "MessageTextInput",
"advanced": true,
+ "api_editable": false,
"display_name": "Context ID",
"dynamic": false,
"info": "The context ID of the chat. Adds an extra layer to the local memory.",
@@ -1126,6 +1126,7 @@
"data_template": {
"_input_type": "MessageTextInput",
"advanced": true,
+ "api_editable": false,
"display_name": "Data Template",
"dynamic": false,
"info": "Template to convert Data to Text. If left empty, it will be dynamically set to the Data's text key.",
@@ -1151,6 +1152,7 @@
"input_value": {
"_input_type": "HandleInput",
"advanced": false,
+ "api_editable": false,
"display_name": "Inputs",
"dynamic": false,
"info": "Message to be passed as output.",
@@ -1177,6 +1179,7 @@
"sender": {
"_input_type": "DropdownInput",
"advanced": true,
+ "api_editable": false,
"combobox": false,
"dialog_inputs": {},
"display_name": "Sender Type",
@@ -1204,6 +1207,7 @@
"sender_name": {
"_input_type": "MessageTextInput",
"advanced": true,
+ "api_editable": false,
"display_name": "Sender Name",
"dynamic": false,
"info": "Name of the sender.",
@@ -1229,6 +1233,7 @@
"session_id": {
"_input_type": "MessageTextInput",
"advanced": true,
+ "api_editable": false,
"display_name": "Session ID",
"dynamic": false,
"info": "The session ID of the chat. If empty, the current session ID parameter will be used.",
@@ -1254,6 +1259,7 @@
"should_store_message": {
"_input_type": "BoolInput",
"advanced": true,
+ "api_editable": false,
"display_name": "Store Messages",
"dynamic": false,
"info": "Store the message in the history.",
@@ -1279,13 +1285,9 @@
},
"dragging": false,
"id": "ChatOutput-0XHyo",
- "measured": {
- "height": 52,
- "width": 192
- },
"position": {
- "x": 2675.9026631331253,
- "y": 1625.0395041941492
+ "x": 2658.4795344391887,
+ "y": 1602.1716477833572
},
"selected": false,
"type": "genericNode"
@@ -1355,10 +1357,10 @@
],
"frozen": false,
"icon": "wand-sparkles",
- "last_updated": "2026-10-27T20:16:08.410Z",
+ "last_updated": "2026-10-29T18:15:19.833Z",
"legacy": false,
"metadata": {
- "code_hash": "f15ba610cfd0",
+ "code_hash": "6164f967d510",
"dependencies": {
"dependencies": [
{
@@ -1371,7 +1373,7 @@
},
{
"name": "lfx",
- "version": "1.12.3"
+ "version": "1.12.8"
},
{
"name": "jq",
@@ -1452,7 +1454,7 @@
"value": "72c3d17c-2dac-4a73-b48a-6518473d7830"
},
"_frontend_node_folder_id": {
- "value": "f3f8bf74-7a73-4ab3-9769-0d8a4ebbaec9"
+ "value": "afa57272-6d34-4d1c-bf31-27ffad110b3a"
},
"_type": "Component",
"append_update_data": {
@@ -1547,7 +1549,7 @@
"show": true,
"title_case": false,
"type": "code",
- "value": "\"\"\"Unified Operations component.\n\nBrings together the previously separate JSON, Table, and Text operation\ncomponents into a single component. An \"Input Type\" selector (Text / JSON /\nTable) drives everything: it filters the \"Operation\" picker to the operations\nthat apply to that type, reveals the matching input (Text / JSON / Table) and\nits operation-specific fields, and advertises the appropriate output type.\n\nThe three original components (JSON Operations, Table Operations, Text\nOperations) remain available as legacy components for backward compatibility\nwith existing flows.\n\"\"\"\n\nimport ast\nimport contextlib\nimport json\nimport re\nfrom typing import TYPE_CHECKING, Any\n\nimport pandas as pd\nfrom json_repair import repair_json\n\nfrom lfx.custom import Component\nfrom lfx.field_typing import RangeSpec\nfrom lfx.inputs import DictInput, SortableListInput, TabInput\nfrom lfx.io import (\n BoolInput,\n DataFrameInput,\n DataInput,\n DropdownInput,\n IntInput,\n MessageTextInput,\n MultilineInput,\n Output,\n StrInput,\n)\nfrom lfx.log.logger import logger\nfrom lfx.schema import Data\nfrom lfx.schema.dataframe import DataFrame\nfrom lfx.schema.dotdict import dotdict\nfrom lfx.schema.message import Message\nfrom lfx.utils.jq_security import validate_jq_program\n\nif TYPE_CHECKING:\n from collections.abc import Callable\n\n# The \"Input Type\" selector tabs. Each value maps a Langflow data type to the\n# operations, input, and output that belong to it.\nINPUT_TYPES = [\"Text\", \"JSON\", \"Table\"]\n\n# Operations grouped by input type, in display order, each with the icon shown\n# in the Operation picker. This is the single source of truth for the picker;\n# update_build_config swaps the picker's options to the selected type's list.\nOPERATIONS_BY_TYPE: dict[str, list[dict[str, str]]] = {\n \"Text\": [\n {\"name\": \"Word Count\", \"icon\": \"hash\"},\n {\"name\": \"Case Conversion\", \"icon\": \"type\"},\n {\"name\": \"Text Replace\", \"icon\": \"replace\"},\n {\"name\": \"Text Extract\", \"icon\": \"search\"},\n {\"name\": \"Text Head\", \"icon\": \"chevron-left\"},\n {\"name\": \"Text Tail\", \"icon\": \"chevron-right\"},\n {\"name\": \"Text Strip\", \"icon\": \"minus\"},\n {\"name\": \"Text Join\", \"icon\": \"link\"},\n {\"name\": \"Text Clean\", \"icon\": \"sparkles\"},\n {\"name\": \"Text to DataFrame\", \"icon\": \"table\"},\n ],\n \"JSON\": [\n {\"name\": \"Select Keys\", \"icon\": \"lasso-select\"},\n {\"name\": \"Literal Eval\", \"icon\": \"braces\"},\n {\"name\": \"Combine\", \"icon\": \"merge\"},\n {\"name\": \"Append or Update\", \"icon\": \"circle-plus\"},\n {\"name\": \"Remove Keys\", \"icon\": \"eraser\"},\n {\"name\": \"Rename Keys\", \"icon\": \"pencil-line\"},\n {\"name\": \"Path Selection\", \"icon\": \"mouse-pointer\"},\n {\"name\": \"JQ Expression\", \"icon\": \"terminal\"},\n ],\n \"Table\": [\n {\"name\": \"Add Column\", \"icon\": \"plus\"},\n {\"name\": \"Concatenate\", \"icon\": \"combine\"},\n {\"name\": \"Drop Column\", \"icon\": \"minus\"},\n {\"name\": \"Filter\", \"icon\": \"filter\"},\n {\"name\": \"Head\", \"icon\": \"arrow-up\"},\n {\"name\": \"Merge\", \"icon\": \"merge\"},\n {\"name\": \"Rename Column\", \"icon\": \"pencil\"},\n {\"name\": \"Replace Value\", \"icon\": \"replace\"},\n {\"name\": \"Select Columns\", \"icon\": \"columns\"},\n {\"name\": \"Sort\", \"icon\": \"arrow-up-down\"},\n {\"name\": \"Tail\", \"icon\": \"arrow-down\"},\n {\"name\": \"Drop Duplicates\", \"icon\": \"copy-x\"},\n ],\n}\n\n# Operation-name sets derived from the picker, used for dispatch and output\n# routing. Keeping them derived from OPERATIONS_BY_TYPE avoids any drift.\nJSON_OPERATIONS = {op[\"name\"] for op in OPERATIONS_BY_TYPE[\"JSON\"]}\nTABLE_OPERATIONS = {op[\"name\"] for op in OPERATIONS_BY_TYPE[\"Table\"]}\nTEXT_OPERATIONS = {op[\"name\"] for op in OPERATIONS_BY_TYPE[\"Text\"]}\n\n# Each input type maps to its main input field and its default output. \"Text\"\n# normally outputs a Message; \"JSON\" a Data; \"Table\" a DataFrame. A few text\n# operations override this (Word Count -> Data, Text to DataFrame -> DataFrame).\nINPUT_TYPE_TO_MAIN_INPUT = {\"Text\": \"text_input\", \"JSON\": \"data\", \"Table\": \"df\"}\n\n# Case conversions for the Text \"Case Conversion\" operation.\nCASE_CONVERTERS: dict[str, Any] = {\n \"uppercase\": str.upper,\n \"lowercase\": str.lower,\n \"title\": str.title,\n \"capitalize\": str.capitalize,\n \"swapcase\": str.swapcase,\n}\n\n\nclass OperationsComponent(Component):\n display_name = \"Data Operations\"\n description = \"Perform operations on Text, JSON, and Tables from a single component.\"\n documentation: str = \"https://docs.langflow.org/components-processing#operations\"\n icon = \"wand-sparkles\"\n name = \"Operations\"\n metadata = {\n \"keywords\": [\n \"operations\",\n \"data operations\",\n \"json\",\n \"json operations\",\n \"table\",\n \"table operations\",\n \"dataframe\",\n \"dataframe operations\",\n \"text\",\n \"text operations\",\n \"select keys\",\n \"literal eval\",\n \"combine\",\n \"append or update\",\n \"remove keys\",\n \"rename keys\",\n \"path selection\",\n \"jq expression\",\n \"parse json\",\n \"add column\",\n \"concatenate\",\n \"drop column\",\n \"filter\",\n \"head\",\n \"merge\",\n \"rename column\",\n \"replace value\",\n \"select columns\",\n \"sort\",\n \"tail\",\n \"drop duplicates\",\n \"word count\",\n \"case conversion\",\n \"text replace\",\n \"text extract\",\n \"text join\",\n \"text clean\",\n \"text to dataframe\",\n \"data manipulation\",\n \"data transformation\",\n ],\n }\n\n # Operation -> operation-specific input fields to reveal when selected.\n OPERATION_FIELDS: dict[str, list[str]] = {\n # JSON\n \"Select Keys\": [\"select_keys_input\"],\n \"Literal Eval\": [],\n \"Combine\": [],\n \"Append or Update\": [\"append_update_data\"],\n \"Remove Keys\": [\"remove_keys_input\"],\n \"Rename Keys\": [\"rename_keys_input\"],\n \"Path Selection\": [\"mapped_json_display\", \"selected_key\"],\n \"JQ Expression\": [\"query\"],\n # Table\n \"Add Column\": [\"new_column_name\", \"new_column_value\"],\n \"Concatenate\": [],\n \"Drop Column\": [\"column_name\"],\n \"Filter\": [\"column_name\", \"filter_value\", \"filter_operator\"],\n \"Head\": [\"num_rows\"],\n \"Merge\": [\"left_dataframe\", \"right_dataframe\", \"merge_on_column\", \"merge_how\"],\n \"Rename Column\": [\"column_name\", \"new_column_name\"],\n \"Replace Value\": [\"column_name\", \"replace_value\", \"replacement_value\"],\n \"Select Columns\": [\"columns_to_select\"],\n \"Sort\": [\"column_name\", \"ascending\"],\n \"Tail\": [\"num_rows\"],\n \"Drop Duplicates\": [\"column_name\"],\n # Text\n \"Word Count\": [\"count_words\", \"count_characters\", \"count_lines\"],\n \"Case Conversion\": [\"case_type\"],\n \"Text Replace\": [\"search_pattern\", \"replacement_text\", \"use_regex\"],\n \"Text Extract\": [\"extract_pattern\", \"max_matches\"],\n \"Text Head\": [\"head_characters\"],\n \"Text Tail\": [\"tail_characters\"],\n \"Text Strip\": [\"strip_mode\", \"strip_characters\"],\n \"Text Join\": [\"text_input_2\"],\n \"Text Clean\": [\"remove_extra_spaces\", \"remove_special_chars\", \"remove_empty_lines\"],\n \"Text to DataFrame\": [\"table_separator\", \"has_header\"],\n }\n\n # The three main inputs (one per data type). They are never treated as\n # operation-specific fields; the input-type selector toggles them.\n MAIN_INPUTS = (\"text_input\", \"data\", \"df\")\n\n # Every operation-specific field (union of all the lists above), used to\n # hide and reset fields whenever the input type or operation changes.\n ALL_OPERATION_FIELDS: list[str] = [\n # JSON\n \"select_keys_input\",\n \"append_update_data\",\n \"remove_keys_input\",\n \"rename_keys_input\",\n \"mapped_json_display\",\n \"selected_key\",\n \"query\",\n # Table\n \"column_name\",\n \"filter_value\",\n \"filter_operator\",\n \"ascending\",\n \"new_column_name\",\n \"new_column_value\",\n \"columns_to_select\",\n \"num_rows\",\n \"replace_value\",\n \"replacement_value\",\n \"left_dataframe\",\n \"right_dataframe\",\n \"merge_on_column\",\n \"merge_how\",\n # Text\n \"table_separator\",\n \"has_header\",\n \"count_words\",\n \"count_characters\",\n \"count_lines\",\n \"case_type\",\n \"use_regex\",\n \"search_pattern\",\n \"replacement_text\",\n \"extract_pattern\",\n \"max_matches\",\n \"head_characters\",\n \"tail_characters\",\n \"strip_mode\",\n \"strip_characters\",\n \"text_input_2\",\n \"remove_extra_spaces\",\n \"remove_special_chars\",\n \"remove_empty_lines\",\n ]\n\n # Defaults applied to the JSON operation fields when the operation changes,\n # mirroring the JSON Operations component's reset behavior.\n OPERATION_FIELD_DEFAULTS: dict[str, Any] = {\n \"select_keys_input\": [],\n \"append_update_data\": {\"key\": \"value\"},\n \"remove_keys_input\": [],\n \"rename_keys_input\": {\"old_key\": \"new_key\"},\n \"mapped_json_display\": \"\",\n \"selected_key\": None,\n \"query\": \"\",\n }\n\n inputs = [\n # --- Input type selector: drives operations, input, and output ---\n TabInput(\n name=\"input_type\",\n display_name=\"Input Type\",\n options=INPUT_TYPES,\n value=\"Text\",\n info=\"Select the type of input to operate on.\",\n real_time_refresh=True,\n ),\n # --- Main inputs: one per data type, shown contextually ---\n MultilineInput(\n name=\"text_input\",\n display_name=\"Text\",\n info=\"The input text to process.\",\n show=True,\n ),\n DataInput(\n name=\"data\",\n display_name=\"JSON\",\n info=\"The JSON / Data object to operate on.\",\n is_list=True,\n show=False,\n ),\n DataFrameInput(\n name=\"df\",\n display_name=\"Table\",\n info=\"The input Table to operate on. Connect multiple Tables for merge or concatenate operations.\",\n is_list=True,\n show=False,\n ),\n # --- Operation picker (options are filtered by Input Type) ---\n SortableListInput(\n name=\"operation\",\n display_name=\"Operation\",\n placeholder=\"Select Operation\",\n info=\"Select the operation to perform. The matching fields and output appear once you choose one.\",\n options=OPERATIONS_BY_TYPE[\"Text\"],\n real_time_refresh=True,\n limit=1,\n ),\n # --- JSON operation fields ---\n MessageTextInput(\n name=\"select_keys_input\",\n display_name=\"Select Keys\",\n info=\"List of keys to select from the data. Only top-level keys can be selected.\",\n show=False,\n is_list=True,\n value=[],\n ),\n DictInput(\n name=\"append_update_data\",\n display_name=\"Append or Update\",\n info=\"Data to append or update the existing data with. Only top-level keys are checked.\",\n show=False,\n value={\"key\": \"value\"},\n is_list=True,\n ),\n MessageTextInput(\n name=\"remove_keys_input\",\n display_name=\"Remove Keys\",\n info=\"List of keys to remove from the data.\",\n show=False,\n is_list=True,\n value=[],\n ),\n DictInput(\n name=\"rename_keys_input\",\n display_name=\"Rename Keys\",\n info=\"List of keys to rename in the data.\",\n show=False,\n is_list=True,\n value={\"old_key\": \"new_key\"},\n ),\n MultilineInput(\n name=\"mapped_json_display\",\n display_name=\"JSON to Map\",\n info=\"Paste or preview your JSON here to explore its structure and select a path for extraction.\",\n required=False,\n refresh_button=True,\n real_time_refresh=True,\n placeholder=\"Add a JSON example.\",\n show=False,\n ),\n DropdownInput(\n name=\"selected_key\",\n display_name=\"Select Path\",\n options=[],\n required=False,\n dynamic=True,\n show=False,\n value=None,\n ),\n MessageTextInput(\n name=\"query\",\n display_name=\"JQ Expression\",\n info=\"JSON Query to filter the data. Used by Path Selection and JQ Expression operations.\",\n placeholder=\"e.g., .properties.id\",\n show=False,\n ),\n # --- Table operation fields ---\n StrInput(\n name=\"column_name\",\n display_name=\"Column Name\",\n info=\"The column name to use for the operation.\",\n dynamic=True,\n show=False,\n ),\n MessageTextInput(\n name=\"filter_value\",\n display_name=\"Filter Value\",\n info=\"The value to filter rows by.\",\n dynamic=True,\n show=False,\n ),\n DropdownInput(\n name=\"filter_operator\",\n display_name=\"Filter Operator\",\n options=[\n \"equals\",\n \"not equals\",\n \"contains\",\n \"not contains\",\n \"starts with\",\n \"ends with\",\n \"greater than\",\n \"less than\",\n ],\n value=\"equals\",\n info=\"The operator to apply for filtering rows.\",\n advanced=False,\n dynamic=True,\n show=False,\n ),\n BoolInput(\n name=\"ascending\",\n display_name=\"Sort Ascending\",\n info=\"Whether to sort in ascending order.\",\n dynamic=True,\n show=False,\n value=True,\n ),\n StrInput(\n name=\"new_column_name\",\n display_name=\"New Column Name\",\n info=\"The new column name when renaming or adding a column.\",\n dynamic=True,\n show=False,\n ),\n MessageTextInput(\n name=\"new_column_value\",\n display_name=\"New Column Value\",\n info=\"The value to populate the new column with.\",\n dynamic=True,\n show=False,\n ),\n StrInput(\n name=\"columns_to_select\",\n display_name=\"Columns to Select\",\n dynamic=True,\n is_list=True,\n show=False,\n ),\n IntInput(\n name=\"num_rows\",\n display_name=\"Number of Rows\",\n info=\"Number of rows to return (for head/tail).\",\n dynamic=True,\n show=False,\n value=5,\n ),\n MessageTextInput(\n name=\"replace_value\",\n display_name=\"Value to Replace\",\n info=\"The value to replace in the column.\",\n dynamic=True,\n show=False,\n ),\n MessageTextInput(\n name=\"replacement_value\",\n display_name=\"Replacement Value\",\n info=\"The value to replace with.\",\n dynamic=True,\n show=False,\n ),\n DataFrameInput(\n name=\"left_dataframe\",\n display_name=\"Left Table\",\n info=\"The left (primary) Table for merge operations. \"\n \"In a left merge, all rows from this table are preserved.\",\n dynamic=True,\n show=False,\n ),\n DataFrameInput(\n name=\"right_dataframe\",\n display_name=\"Right Table\",\n info=\"The right (secondary) Table for merge operations. \"\n \"In a right merge, all rows from this table are preserved.\",\n dynamic=True,\n show=False,\n ),\n StrInput(\n name=\"merge_on_column\",\n display_name=\"Merge On Column\",\n info=\"The column name to merge Tables on. Must exist in both Tables.\",\n dynamic=True,\n show=False,\n ),\n DropdownInput(\n name=\"merge_how\",\n display_name=\"Merge Type\",\n options=[\"inner\", \"outer\", \"left\", \"right\"],\n value=\"inner\",\n info=\"Type of merge: inner (intersection), outer (union), left, or right.\",\n dynamic=True,\n show=False,\n ),\n # --- Text operation fields ---\n StrInput(\n name=\"table_separator\",\n display_name=\"Table Separator\",\n info=\"Separator used in the table (default: '|').\",\n value=\"|\",\n dynamic=True,\n show=False,\n ),\n BoolInput(\n name=\"has_header\",\n display_name=\"Has Header\",\n info=\"Whether the table has a header row.\",\n value=True,\n dynamic=True,\n advanced=True,\n show=False,\n ),\n BoolInput(\n name=\"count_words\",\n display_name=\"Count Words\",\n info=\"Include word count in analysis.\",\n value=True,\n dynamic=True,\n advanced=True,\n show=False,\n ),\n BoolInput(\n name=\"count_characters\",\n display_name=\"Count Characters\",\n info=\"Include character count in analysis.\",\n value=True,\n dynamic=True,\n advanced=True,\n show=False,\n ),\n BoolInput(\n name=\"count_lines\",\n display_name=\"Count Lines\",\n info=\"Include line count in analysis.\",\n value=True,\n dynamic=True,\n advanced=True,\n show=False,\n ),\n DropdownInput(\n name=\"case_type\",\n display_name=\"Case Type\",\n options=[\"uppercase\", \"lowercase\", \"title\", \"capitalize\", \"swapcase\"],\n value=\"lowercase\",\n info=\"Type of case conversion to apply.\",\n dynamic=True,\n show=False,\n ),\n BoolInput(\n name=\"use_regex\",\n display_name=\"Use Regex\",\n info=\"Whether to treat search pattern as regex.\",\n value=False,\n dynamic=True,\n show=False,\n ),\n StrInput(\n name=\"search_pattern\",\n display_name=\"Search Pattern\",\n info=\"Text pattern to search for (supports regex).\",\n dynamic=True,\n show=False,\n ),\n StrInput(\n name=\"replacement_text\",\n display_name=\"Replacement Text\",\n info=\"Text to replace the search pattern with.\",\n dynamic=True,\n show=False,\n ),\n StrInput(\n name=\"extract_pattern\",\n display_name=\"Extract Pattern\",\n info=\"Regex pattern to extract from text.\",\n dynamic=True,\n show=False,\n ),\n IntInput(\n name=\"max_matches\",\n display_name=\"Max Matches\",\n info=\"Maximum number of matches to extract.\",\n value=10,\n dynamic=True,\n show=False,\n ),\n IntInput(\n name=\"head_characters\",\n display_name=\"Characters from Start\",\n info=\"Number of characters to extract from the beginning of text. Must be non-negative.\",\n value=100,\n dynamic=True,\n show=False,\n range_spec=RangeSpec(min=0, max=1000000, step=1, step_type=\"int\"),\n ),\n IntInput(\n name=\"tail_characters\",\n display_name=\"Characters from End\",\n info=\"Number of characters to extract from the end of text. Must be non-negative.\",\n value=100,\n dynamic=True,\n show=False,\n range_spec=RangeSpec(min=0, max=1000000, step=1, step_type=\"int\"),\n ),\n DropdownInput(\n name=\"strip_mode\",\n display_name=\"Strip Mode\",\n options=[\"both\", \"left\", \"right\"],\n value=\"both\",\n info=\"Which sides to strip whitespace from.\",\n dynamic=True,\n show=False,\n ),\n StrInput(\n name=\"strip_characters\",\n display_name=\"Characters to Strip\",\n info=\"Specific characters to remove (leave empty for whitespace).\",\n value=\"\",\n dynamic=True,\n show=False,\n ),\n MultilineInput(\n name=\"text_input_2\",\n display_name=\"Second Text Input\",\n info=\"Second text to join with the first text.\",\n dynamic=True,\n show=False,\n ),\n BoolInput(\n name=\"remove_extra_spaces\",\n display_name=\"Remove Extra Spaces\",\n info=\"Remove multiple consecutive spaces.\",\n value=True,\n dynamic=True,\n show=False,\n ),\n BoolInput(\n name=\"remove_special_chars\",\n display_name=\"Remove Special Characters\",\n info=\"Remove special characters except alphanumeric and spaces.\",\n value=False,\n dynamic=True,\n show=False,\n ),\n BoolInput(\n name=\"remove_empty_lines\",\n display_name=\"Remove Empty Lines\",\n info=\"Remove empty lines from text.\",\n value=False,\n dynamic=True,\n show=False,\n ),\n ]\n\n # Default output matches the default Input Type (\"Text\" -> Message).\n # update_outputs / update_frontend_node narrow it to the selected type and\n # operation.\n outputs = [Output(display_name=\"Message\", name=\"message_output\", method=\"as_message\")]\n\n # ------------------------------------------------------------------\n # Operation routing helpers\n # ------------------------------------------------------------------\n @staticmethod\n def _extract_operation_name(field_value: Any) -> str:\n \"\"\"Extract the operation name from a SortableListInput value.\"\"\"\n if isinstance(field_value, list) and len(field_value) > 0 and isinstance(field_value[0], dict):\n return field_value[0].get(\"name\", \"\")\n if isinstance(field_value, str):\n return field_value\n return \"\"\n\n def _operation_name(self) -> str:\n \"\"\"Get the currently selected operation name.\"\"\"\n return self._extract_operation_name(getattr(self, \"operation\", []))\n\n @staticmethod\n def _default_output_for_type(input_type: str) -> Output:\n \"\"\"Return the output advertised for an input type when no operation is selected yet.\"\"\"\n if input_type == \"JSON\":\n return Output(display_name=\"JSON\", name=\"data_output\", method=\"as_data\")\n if input_type == \"Table\":\n return Output(display_name=\"Table\", name=\"dataframe_output\", method=\"as_dataframe\")\n return Output(display_name=\"Message\", name=\"message_output\", method=\"as_message\")\n\n # ------------------------------------------------------------------\n # Dynamic UI\n # ------------------------------------------------------------------\n def _reset_operation_fields(self, build_config: dotdict) -> None:\n \"\"\"Hide every operation-specific field and restore its default value.\"\"\"\n for field in self.ALL_OPERATION_FIELDS:\n if field in build_config:\n build_config[field][\"show\"] = False\n if field in self.OPERATION_FIELD_DEFAULTS:\n build_config[field][\"value\"] = self.OPERATION_FIELD_DEFAULTS[field]\n\n def _show_main_input(self, build_config: dotdict, input_type: str, operation: str) -> None:\n \"\"\"Show only the main input that matches the input type; hide the others.\"\"\"\n for inp in self.MAIN_INPUTS:\n if inp in build_config:\n build_config[inp][\"show\"] = False\n build_config[inp][\"required\"] = False\n\n main_input = INPUT_TYPE_TO_MAIN_INPUT.get(input_type)\n if main_input and main_input in build_config:\n build_config[main_input][\"show\"] = True\n build_config[main_input][\"required\"] = True\n # The JSON \"Combine\" operation consumes a list of Data objects.\n if main_input == \"data\":\n build_config[\"data\"][\"is_list\"] = operation == \"Combine\"\n\n def update_build_config(self, build_config: dotdict, field_value: Any, field_name: str | None = None) -> dotdict:\n # Path Selection: refresh the available JSON paths from the pasted JSON.\n if field_name == \"mapped_json_display\":\n try:\n parsed_json = json.loads(field_value)\n keys = self.extract_all_paths(parsed_json)\n build_config[\"selected_key\"][\"options\"] = keys\n build_config[\"selected_key\"][\"show\"] = True\n except (json.JSONDecodeError, TypeError, ValueError) as e:\n logger.error(f\"Error parsing mapped JSON: {e}\")\n build_config[\"selected_key\"][\"show\"] = False\n return build_config\n\n # Input type changed: swap the operation list, clear the selection, and\n # show only the matching input. No operation-specific fields are shown\n # until an operation is picked.\n if field_name == \"input_type\":\n input_type = field_value if field_value in OPERATIONS_BY_TYPE else \"Text\"\n build_config[\"operation\"][\"options\"] = OPERATIONS_BY_TYPE[input_type]\n build_config[\"operation\"][\"value\"] = []\n self._reset_operation_fields(build_config)\n self._show_main_input(build_config, input_type, operation=\"\")\n return build_config\n\n # Operation changed: reset fields, show the input for the current type,\n # then reveal the operation-specific fields.\n if field_name == \"operation\":\n operation = self._extract_operation_name(field_value)\n self._reset_operation_fields(build_config)\n\n input_type = build_config.get(\"input_type\", {}).get(\"value\", \"Text\")\n self._show_main_input(build_config, input_type, operation)\n\n for field in self.OPERATION_FIELDS.get(operation, []):\n if field in build_config:\n build_config[field][\"show\"] = True\n\n return build_config\n\n return build_config\n\n def update_outputs(self, frontend_node: dict, field_name: str, field_value: Any) -> dict:\n \"\"\"Create the output(s) appropriate to the selected input type and operation.\"\"\"\n if field_name == \"input_type\":\n # Switching type clears the operation; advertise the type's default.\n input_type = field_value if field_value in OPERATIONS_BY_TYPE else \"Text\"\n frontend_node[\"outputs\"] = [self._default_output_for_type(input_type)]\n return frontend_node\n\n template = frontend_node.get(\"template\", {})\n input_type = template.get(\"input_type\", {}).get(\"value\", \"Text\")\n\n if field_name == \"operation\":\n operation = self._extract_operation_name(field_value)\n else:\n # Any other refresh (e.g. Path Selection's \"JSON to Map\" field)\n # reaches here on a freshly rebuilt node whose outputs were reset\n # to the class default (Message). Re-derive the output from the\n # saved operation so the refresh doesn't swap the real output type.\n operation = self._extract_operation_name(template.get(\"operation\", {}).get(\"value\", []))\n\n if not operation:\n # No operation selected: fall back to the input type's default output.\n frontend_node[\"outputs\"] = [self._default_output_for_type(input_type)]\n return frontend_node\n\n frontend_node[\"outputs\"] = []\n if operation in JSON_OPERATIONS or operation == \"Word Count\":\n frontend_node[\"outputs\"].append(Output(display_name=\"JSON\", name=\"data_output\", method=\"as_data\"))\n elif operation in TABLE_OPERATIONS or operation == \"Text to DataFrame\":\n frontend_node[\"outputs\"].append(\n Output(display_name=\"Table\", name=\"dataframe_output\", method=\"as_dataframe\")\n )\n elif operation == \"Text Join\":\n frontend_node[\"outputs\"].append(Output(display_name=\"Text\", name=\"text_output\", method=\"as_text\"))\n frontend_node[\"outputs\"].append(Output(display_name=\"Message\", name=\"message_output\", method=\"as_message\"))\n else:\n frontend_node[\"outputs\"].append(Output(display_name=\"Message\", name=\"message_output\", method=\"as_message\"))\n\n return frontend_node\n\n async def update_frontend_node(self, new_frontend_node: dict, current_frontend_node: dict) -> dict:\n \"\"\"Keep the operation options and outputs in sync with the saved input type on load.\"\"\"\n await super().update_frontend_node(new_frontend_node, current_frontend_node)\n\n template = new_frontend_node.get(\"template\", {})\n input_type = template.get(\"input_type\", {}).get(\"value\", \"Text\")\n if input_type not in OPERATIONS_BY_TYPE:\n input_type = \"Text\"\n\n # Filter the operation picker to the saved input type.\n if \"operation\" in template:\n template[\"operation\"][\"options\"] = OPERATIONS_BY_TYPE[input_type]\n\n # Re-derive the outputs from the saved input type + operation.\n operation_value = template.get(\"operation\", {}).get(\"value\", [])\n if self._extract_operation_name(operation_value):\n self.update_outputs(new_frontend_node, \"operation\", operation_value)\n else:\n self.update_outputs(new_frontend_node, \"input_type\", input_type)\n\n return new_frontend_node\n\n # ==================================================================\n # Output methods (referenced by update_outputs)\n # ==================================================================\n def as_data(self) -> Data:\n \"\"\"JSON-typed output: JSON operations and Word Count.\"\"\"\n operation = self._operation_name()\n if operation in JSON_OPERATIONS:\n handler = self._json_handlers().get(operation)\n if handler:\n try:\n return handler()\n except Exception as e:\n logger.error(f\"Error executing {operation}: {e!s}\")\n raise\n if operation == \"Word Count\":\n return self._word_count_data()\n return Data(data={})\n\n def as_dataframe(self) -> DataFrame:\n \"\"\"Table-typed output: Table operations and Text to DataFrame.\"\"\"\n operation = self._operation_name()\n if operation in TABLE_OPERATIONS:\n return self._run_table_operation(operation)\n if operation == \"Text to DataFrame\":\n return self._text_to_dataframe(getattr(self, \"text_input\", \"\") or \"\")\n return DataFrame(pd.DataFrame())\n\n def as_message(self) -> Message:\n \"\"\"Message-typed output: generic text operations (and Text Join).\"\"\"\n return Message(text=self._format_result_as_text(self._run_text_operation()))\n\n def as_text(self) -> Message:\n \"\"\"Text output for the Text Join operation.\"\"\"\n return self.as_message()\n\n # ==================================================================\n # JSON operations\n # ==================================================================\n @staticmethod\n def extract_all_paths(obj, path=\"\"):\n paths = []\n if isinstance(obj, dict):\n for k, v in obj.items():\n new_path = f\"{path}.{k}\" if path else f\".{k}\"\n paths.append(new_path)\n paths.extend(OperationsComponent.extract_all_paths(v, new_path))\n elif isinstance(obj, list) and obj:\n new_path = f\"{path}[0]\"\n paths.append(new_path)\n paths.extend(OperationsComponent.extract_all_paths(obj[0], new_path))\n return paths\n\n @staticmethod\n def remove_keys_recursive(obj, keys_to_remove):\n if isinstance(obj, dict):\n return {\n k: OperationsComponent.remove_keys_recursive(v, keys_to_remove)\n for k, v in obj.items()\n if k not in keys_to_remove\n }\n if isinstance(obj, list):\n return [OperationsComponent.remove_keys_recursive(item, keys_to_remove) for item in obj]\n return obj\n\n @staticmethod\n def rename_keys_recursive(obj, rename_map):\n if isinstance(obj, dict):\n return {\n rename_map.get(k, k): OperationsComponent.rename_keys_recursive(v, rename_map) for k, v in obj.items()\n }\n if isinstance(obj, list):\n return [OperationsComponent.rename_keys_recursive(item, rename_map) for item in obj]\n return obj\n\n def _json_handlers(self) -> \"dict[str, Callable[[], Data]]\":\n return {\n \"Select Keys\": self.select_keys,\n \"Literal Eval\": self.evaluate_data,\n \"Combine\": self.combine_data,\n \"Append or Update\": self.append_update,\n \"Remove Keys\": self.remove_keys,\n \"Rename Keys\": self.rename_keys,\n \"Path Selection\": self.json_path,\n \"JQ Expression\": self.json_query,\n }\n\n def get_data_dict(self) -> dict:\n \"\"\"Extract data dictionary from Data object.\"\"\"\n data = self.data[0] if isinstance(self.data, list) and len(self.data) == 1 else self.data\n return data.model_dump()\n\n def get_normalized_data(self) -> dict:\n \"\"\"Get normalized data dictionary, handling the 'data' key if present.\"\"\"\n data_dict = self.get_data_dict()\n return data_dict.get(\"data\", data_dict)\n\n def data_is_list(self) -> bool:\n \"\"\"Check if data contains multiple items.\"\"\"\n return isinstance(self.data, list) and len(self.data) > 1\n\n def validate_single_data(self, operation: str) -> None:\n \"\"\"Validate that the operation is being performed on a single data object.\"\"\"\n if self.data_is_list():\n msg = f\"{operation} operation is not supported for multiple data objects.\"\n raise ValueError(msg)\n\n def select_keys(self) -> Data:\n \"\"\"Select specific keys from the data dictionary.\"\"\"\n self.validate_single_data(\"Select Keys\")\n data_dict = self.get_normalized_data()\n filter_criteria: list[str] = self.select_keys_input\n\n if len(filter_criteria) == 1 and filter_criteria[0] == \"data\":\n filtered = data_dict[\"data\"]\n else:\n if not all(key in data_dict for key in filter_criteria):\n msg = f\"Select key not found in data. Available keys: {list(data_dict.keys())}\"\n raise ValueError(msg)\n filtered = {key: value for key, value in data_dict.items() if key in filter_criteria}\n\n return Data(data=filtered)\n\n def remove_keys(self) -> Data:\n \"\"\"Remove specified keys from the data dictionary, recursively.\"\"\"\n self.validate_single_data(\"Remove Keys\")\n data_dict = self.get_normalized_data()\n remove_keys_input: list[str] = self.remove_keys_input\n filtered = OperationsComponent.remove_keys_recursive(data_dict, set(remove_keys_input))\n return Data(data=filtered)\n\n def rename_keys(self) -> Data:\n \"\"\"Rename keys in the data dictionary, recursively.\"\"\"\n self.validate_single_data(\"Rename Keys\")\n data_dict = self.get_normalized_data()\n rename_keys_input: dict[str, str] = self.rename_keys_input\n renamed = OperationsComponent.rename_keys_recursive(data_dict, rename_keys_input)\n return Data(data=renamed)\n\n def recursive_eval(self, data: Any) -> Any:\n \"\"\"Recursively evaluate string values that look like Python literals.\"\"\"\n if isinstance(data, dict):\n return {k: self.recursive_eval(v) for k, v in data.items()}\n if isinstance(data, list):\n return [self.recursive_eval(item) for item in data]\n if isinstance(data, str):\n try:\n if (\n data.strip().startswith((\"{\", \"[\", \"(\", \"'\", '\"'))\n or data.strip().lower() in (\"true\", \"false\", \"none\")\n or data.strip().replace(\".\", \"\").isdigit()\n ):\n return ast.literal_eval(data)\n except (ValueError, SyntaxError, TypeError, MemoryError):\n return data\n else:\n return data\n return data\n\n def evaluate_data(self) -> Data:\n \"\"\"Evaluate string values in the data dictionary.\"\"\"\n self.validate_single_data(\"Literal Eval\")\n logger.info(\"evaluating data\")\n return Data(**self.recursive_eval(self.get_data_dict()))\n\n def combine_data(self) -> Data:\n \"\"\"Combine multiple data objects into one.\"\"\"\n logger.info(\"combining data\")\n if not self.data_is_list():\n return self.data[0] if self.data else Data(data={})\n\n data_dicts = [data.model_dump().get(\"data\", data.model_dump()) for data in self.data]\n combined_data: dict[str, Any] = {}\n\n for data_dict in data_dicts:\n for key, value in data_dict.items():\n if key not in combined_data:\n combined_data[key] = value\n elif isinstance(combined_data[key], list):\n if isinstance(value, list):\n combined_data[key].extend(value)\n else:\n combined_data[key].append(value)\n else:\n combined_data[key] = (\n [combined_data[key], value] if not isinstance(value, list) else [combined_data[key], *value]\n )\n\n return Data(**combined_data)\n\n def append_update(self) -> Data:\n \"\"\"Append or update the data with new key-value pairs.\"\"\"\n self.validate_single_data(\"Append or Update\")\n data_filtered = self.get_normalized_data()\n for key, value in self.append_update_data.items():\n data_filtered[key] = value\n return Data(**data_filtered)\n\n def json_path(self) -> Data:\n \"\"\"Extract a value from the data using the selected JQ path.\"\"\"\n try:\n import jq\n except ImportError:\n msg = \"jq is required for Path Selection. Install with: pip install jq\"\n raise ImportError(msg) from None\n\n try:\n if not self.data or not self.selected_key:\n msg = \"Missing input data or selected key.\"\n raise ValueError(msg)\n input_payload = self.data[0].data if isinstance(self.data, list) else self.data.data\n validate_jq_program(self.selected_key)\n compiled = jq.compile(self.selected_key)\n result = compiled.input(input_payload).first()\n if isinstance(result, dict):\n return Data(data=result)\n return Data(data={\"result\": result})\n except (ValueError, TypeError, KeyError) as e:\n self.status = f\"Error: {e!s}\"\n self.log(self.status)\n return Data(data={\"error\": str(e)})\n\n def json_query(self) -> Data:\n \"\"\"Run a JQ expression against the data.\"\"\"\n try:\n import jq\n except ImportError:\n msg = \"jq is required for JQ Expression. Install with: pip install jq\"\n raise ImportError(msg) from None\n\n if not self.query or not self.query.strip():\n msg = \"JSON Query is required and cannot be blank.\"\n raise ValueError(msg)\n raw_data = self.get_data_dict()\n try:\n input_str = json.dumps(raw_data)\n repaired = repair_json(input_str)\n data_json = json.loads(repaired)\n jq_input = data_json[\"data\"] if isinstance(data_json, dict) and \"data\" in data_json else data_json\n validate_jq_program(self.query)\n results = jq.compile(self.query).input(jq_input).all()\n if not results:\n msg = \"No result from JSON query.\"\n raise ValueError(msg)\n result = results[0] if len(results) == 1 else results\n if result is None or result == \"None\":\n msg = \"JSON query returned null/None. Check if the path exists in your data.\"\n raise ValueError(msg)\n if isinstance(result, dict):\n return Data(data=result)\n return Data(data={\"result\": result})\n except (ValueError, TypeError, KeyError, json.JSONDecodeError) as e:\n logger.error(f\"JSON Query failed: {e}\")\n msg = f\"JSON Query error: {e}\"\n raise ValueError(msg) from e\n\n # ==================================================================\n # Table operations\n # ==================================================================\n def _get_primary_dataframe(self) -> DataFrame:\n \"\"\"Get the first DataFrame from input (handles both single and list inputs).\"\"\"\n if isinstance(self.df, list):\n return self.df[0].copy() if self.df else DataFrame()\n return self.df.copy()\n\n def _run_table_operation(self, operation: str) -> DataFrame:\n # Merge and Concatenate use their own inputs, not the primary df.\n if operation == \"Merge\":\n return self.merge_dataframes()\n if operation == \"Concatenate\":\n return self.concatenate_dataframes()\n\n df_copy = self._get_primary_dataframe()\n table_handlers = {\n \"Filter\": self.filter_rows_by_value,\n \"Sort\": self.sort_by_column,\n \"Drop Column\": self.drop_column,\n \"Rename Column\": self.rename_column,\n \"Add Column\": self.add_column,\n \"Select Columns\": self.select_columns,\n \"Head\": self.head,\n \"Tail\": self.tail,\n \"Replace Value\": self.replace_values,\n \"Drop Duplicates\": self.drop_duplicates,\n }\n handler = table_handlers.get(operation)\n if handler is None:\n msg = f\"Unsupported operation: {operation}\"\n logger.error(msg)\n raise ValueError(msg)\n return handler(df_copy)\n\n def filter_rows_by_value(self, df: DataFrame) -> DataFrame:\n column = df[self.column_name]\n filter_value = self.filter_value\n operator = getattr(self, \"filter_operator\", \"equals\")\n\n if operator == \"equals\":\n mask = column == filter_value\n elif operator == \"not equals\":\n mask = column != filter_value\n elif operator == \"contains\":\n mask = column.astype(str).str.contains(str(filter_value), na=False)\n elif operator == \"not contains\":\n mask = ~column.astype(str).str.contains(str(filter_value), na=False)\n elif operator == \"starts with\":\n mask = column.astype(str).str.startswith(str(filter_value), na=False)\n elif operator == \"ends with\":\n mask = column.astype(str).str.endswith(str(filter_value), na=False)\n elif operator == \"greater than\":\n try:\n numeric_value = pd.to_numeric(filter_value)\n mask = column > numeric_value\n except (ValueError, TypeError):\n mask = column.astype(str) > str(filter_value)\n elif operator == \"less than\":\n try:\n numeric_value = pd.to_numeric(filter_value)\n mask = column < numeric_value\n except (ValueError, TypeError):\n mask = column.astype(str) < str(filter_value)\n else:\n mask = column == filter_value\n\n return DataFrame(df[mask])\n\n def sort_by_column(self, df: DataFrame) -> DataFrame:\n return DataFrame(df.sort_values(by=self.column_name, ascending=self.ascending))\n\n def drop_column(self, df: DataFrame) -> DataFrame:\n return DataFrame(df.drop(columns=[self.column_name]))\n\n def rename_column(self, df: DataFrame) -> DataFrame:\n return DataFrame(df.rename(columns={self.column_name: self.new_column_name}))\n\n def add_column(self, df: DataFrame) -> DataFrame:\n df[self.new_column_name] = [self.new_column_value] * len(df)\n return DataFrame(df)\n\n def select_columns(self, df: DataFrame) -> DataFrame:\n columns = [col.strip() for col in self.columns_to_select]\n return DataFrame(df[columns])\n\n def head(self, df: DataFrame) -> DataFrame:\n return DataFrame(df.head(self.num_rows))\n\n def tail(self, df: DataFrame) -> DataFrame:\n return DataFrame(df.tail(self.num_rows))\n\n def replace_values(self, df: DataFrame) -> DataFrame:\n df[self.column_name] = df[self.column_name].replace(self.replace_value, self.replacement_value)\n return DataFrame(df)\n\n def drop_duplicates(self, df: DataFrame) -> DataFrame:\n return DataFrame(df.drop_duplicates(subset=self.column_name))\n\n def concatenate_dataframes(self) -> DataFrame:\n \"\"\"Concatenate multiple DataFrames vertically (stack rows).\"\"\"\n if not isinstance(self.df, list) or len(self.df) == 0:\n return self.df.copy() if self.df is not None else DataFrame()\n\n if len(self.df) == 1:\n return self.df[0].copy()\n\n concatenated = pd.concat(self.df, ignore_index=True)\n return DataFrame(concatenated)\n\n def merge_dataframes(self) -> DataFrame:\n \"\"\"Merge two DataFrames based on a common column (join operation).\"\"\"\n left_df = getattr(self, \"left_dataframe\", None)\n right_df = getattr(self, \"right_dataframe\", None)\n\n if left_df is None:\n return DataFrame()\n if right_df is None:\n return left_df.copy()\n\n df_left = left_df.copy()\n df_right = right_df.copy()\n\n merge_on = getattr(self, \"merge_on_column\", None)\n merge_how = getattr(self, \"merge_how\", \"inner\")\n\n if merge_on:\n if merge_on not in df_left.columns:\n msg = f\"Column '{merge_on}' not found in left DataFrame. Available: {list(df_left.columns)}\"\n raise ValueError(msg)\n if merge_on not in df_right.columns:\n msg = f\"Column '{merge_on}' not found in right DataFrame. Available: {list(df_right.columns)}\"\n raise ValueError(msg)\n merged = df_left.merge(df_right, on=merge_on, how=merge_how, suffixes=(\"\", \"_right\"))\n else:\n merged = df_left.merge(df_right, left_index=True, right_index=True, how=merge_how, suffixes=(\"\", \"_right\"))\n\n cols_to_drop = []\n for col in merged.columns:\n if col.endswith(\"_right\"):\n original_col = col[:-6]\n if original_col in merged.columns:\n merged[original_col] = merged[original_col].combine_first(merged[col])\n cols_to_drop.append(col)\n\n if cols_to_drop:\n merged = merged.drop(columns=cols_to_drop)\n\n return DataFrame(merged)\n\n # ==================================================================\n # Text operations\n # ==================================================================\n def _run_text_operation(self) -> Any:\n \"\"\"Process text based on the selected operation (Message/Text outputs).\"\"\"\n text = getattr(self, \"text_input\", \"\")\n operation = self._operation_name()\n\n # Allow empty text for Text Join (second input may have content).\n if not text and operation != \"Text Join\":\n return None\n\n text_handlers = {\n \"Case Conversion\": self._case_conversion,\n \"Text Replace\": self._text_replace,\n \"Text Extract\": self._text_extract,\n \"Text Head\": self._text_head,\n \"Text Tail\": self._text_tail,\n \"Text Strip\": self._text_strip,\n \"Text Join\": self._text_join,\n \"Text Clean\": self._text_clean,\n }\n handler = text_handlers.get(operation)\n if handler:\n return handler(text)\n return text\n\n def _word_count_data(self) -> Data:\n \"\"\"Word Count operation result as a Data object.\"\"\"\n result = self._word_count(getattr(self, \"text_input\", \"\") or \"\")\n return Data(data=result)\n\n def _word_count(self, text: str) -> dict[str, Any]:\n \"\"\"Count words, characters, and lines in text.\"\"\"\n result: dict[str, Any] = {}\n text_str = str(text) if text else \"\"\n is_empty = not text_str or not text_str.strip()\n\n if getattr(self, \"count_words\", True):\n if is_empty:\n result[\"word_count\"] = 0\n result[\"unique_words\"] = 0\n else:\n words = text_str.split()\n result[\"word_count\"] = len(words)\n result[\"unique_words\"] = len(set(words))\n\n if getattr(self, \"count_characters\", True):\n if is_empty:\n result[\"character_count\"] = 0\n result[\"character_count_no_spaces\"] = 0\n else:\n result[\"character_count\"] = len(text_str)\n result[\"character_count_no_spaces\"] = len(text_str.replace(\" \", \"\"))\n\n if getattr(self, \"count_lines\", True):\n if is_empty:\n result[\"line_count\"] = 0\n result[\"non_empty_lines\"] = 0\n else:\n lines = text_str.split(\"\\n\")\n result[\"line_count\"] = len(lines)\n result[\"non_empty_lines\"] = len([line for line in lines if line.strip()])\n\n return result\n\n def _text_to_dataframe(self, text: str) -> DataFrame:\n \"\"\"Convert markdown-style table text to a DataFrame.\"\"\"\n lines = [line.strip() for line in text.strip().split(\"\\n\") if line.strip()]\n if not lines:\n return DataFrame(pd.DataFrame())\n\n separator = getattr(self, \"table_separator\", \"|\")\n has_header = getattr(self, \"has_header\", True)\n\n rows = self._parse_table_rows(lines, separator)\n if not rows:\n return DataFrame(pd.DataFrame())\n\n df = self._create_dataframe(rows, has_header=has_header)\n self._convert_numeric_columns(df)\n self.log(f\"Converted text to DataFrame: {len(df)} rows, {len(df.columns)} columns\")\n return DataFrame(df)\n\n def _parse_table_rows(self, lines: list[str], separator: str) -> list[list[str]]:\n rows = []\n for line in lines:\n cleaned_line = line.strip(separator)\n cells = [cell.strip() for cell in cleaned_line.split(separator)]\n rows.append(cells)\n return rows\n\n def _create_dataframe(self, rows: list[list[str]], *, has_header: bool) -> pd.DataFrame:\n if has_header and len(rows) > 1:\n header = rows[0]\n data_rows = rows[1:]\n header_col_count = len(header)\n for i, row in enumerate(data_rows):\n row_col_count = len(row)\n if row_col_count != header_col_count:\n msg = (\n f\"Header mismatch: {header_col_count} column(s) in header vs \"\n f\"{row_col_count} column(s) in data row {i + 1}. \"\n \"Please ensure the header has the same number of columns as your data.\"\n )\n raise ValueError(msg)\n return pd.DataFrame(data_rows, columns=header)\n\n max_cols = max(len(row) for row in rows) if rows else 0\n columns = [f\"col_{i}\" for i in range(max_cols)]\n return pd.DataFrame(rows, columns=columns)\n\n def _convert_numeric_columns(self, df: pd.DataFrame) -> None:\n for col in df.columns:\n with contextlib.suppress(ValueError, TypeError):\n df[col] = pd.to_numeric(df[col])\n\n def _case_conversion(self, text: str) -> str:\n case_type = getattr(self, \"case_type\", \"lowercase\")\n converter = CASE_CONVERTERS.get(case_type)\n return converter(text) if converter else text\n\n def _text_replace(self, text: str) -> str:\n search_pattern = getattr(self, \"search_pattern\", \"\")\n if not search_pattern:\n return text\n replacement_text = getattr(self, \"replacement_text\", \"\")\n use_regex = getattr(self, \"use_regex\", False)\n if use_regex:\n try:\n return re.sub(search_pattern, replacement_text, text)\n except re.error as e:\n self.log(f\"Invalid regex pattern: {e}\")\n return text\n return text.replace(search_pattern, replacement_text)\n\n def _text_extract(self, text: str) -> list[str]:\n extract_pattern = getattr(self, \"extract_pattern\", \"\")\n if not extract_pattern:\n return []\n max_matches = getattr(self, \"max_matches\", 10)\n try:\n matches = re.findall(extract_pattern, text)\n except re.error as e:\n msg = f\"Invalid regex pattern '{extract_pattern}': {e}\"\n raise ValueError(msg) from e\n return matches[:max_matches] if max_matches > 0 else matches\n\n def _text_head(self, text: str) -> str:\n head_characters = getattr(self, \"head_characters\", 100)\n if head_characters < 0:\n msg = f\"Characters from Start must be a non-negative integer, got {head_characters}\"\n raise ValueError(msg)\n if head_characters == 0:\n return \"\"\n return text[:head_characters]\n\n def _text_tail(self, text: str) -> str:\n tail_characters = getattr(self, \"tail_characters\", 100)\n if tail_characters < 0:\n msg = f\"Characters from End must be a non-negative integer, got {tail_characters}\"\n raise ValueError(msg)\n if tail_characters == 0:\n return \"\"\n return text[-tail_characters:]\n\n def _text_strip(self, text: str) -> str:\n strip_mode = getattr(self, \"strip_mode\", \"both\")\n strip_characters = getattr(self, \"strip_characters\", \"\")\n text_str = str(text) if text else \"\"\n chars_to_strip = strip_characters if strip_characters else None\n if strip_mode == \"left\":\n return text_str.lstrip(chars_to_strip)\n if strip_mode == \"right\":\n return text_str.rstrip(chars_to_strip)\n return text_str.strip(chars_to_strip)\n\n def _text_join(self, text: str) -> str:\n text_input_2 = getattr(self, \"text_input_2\", \"\")\n text1 = str(text) if text else \"\"\n text2 = str(text_input_2) if text_input_2 else \"\"\n if text1 and text2:\n return f\"{text1}\\n{text2}\"\n return text1 or text2\n\n def _text_clean(self, text: str) -> str:\n result = text\n if getattr(self, \"remove_extra_spaces\", True):\n # Collapse runs of horizontal whitespace but preserve newlines so\n # that remove_empty_lines stays effective when both are enabled.\n result = re.sub(r\"[^\\S\\n]+\", \" \", result)\n if getattr(self, \"remove_special_chars\", False):\n result = re.sub(r\"[^\\w\\s]\", \"\", result)\n if getattr(self, \"remove_empty_lines\", False):\n lines = [line for line in result.split(\"\\n\") if line.strip()]\n result = \"\\n\".join(lines)\n return result\n\n def _format_result_as_text(self, result: Any) -> str:\n if result is None:\n return \"\"\n if isinstance(result, list):\n return \"\\n\".join(str(item) for item in result)\n return str(result)\n"
+ "value": "\"\"\"Unified Operations component.\n\nBrings together the previously separate JSON, Table, and Text operation\ncomponents into a single component. An \"Input Type\" selector (Text / JSON /\nTable) drives everything: it filters the \"Operation\" picker to the operations\nthat apply to that type, reveals the matching input (Text / JSON / Table) and\nits operation-specific fields, and advertises the appropriate output type.\n\nThe three original components (JSON Operations, Table Operations, Text\nOperations) remain available as legacy components for backward compatibility\nwith existing flows.\n\"\"\"\n\nimport ast\nimport contextlib\nimport json\nimport re\nfrom typing import TYPE_CHECKING, Any\n\nimport pandas as pd\nfrom json_repair import repair_json\n\nfrom lfx.custom import Component\nfrom lfx.field_typing import RangeSpec\nfrom lfx.inputs import DictInput, SortableListInput, TabInput\nfrom lfx.io import (\n BoolInput,\n DataFrameInput,\n DataInput,\n DropdownInput,\n IntInput,\n MessageTextInput,\n MultilineInput,\n Output,\n StrInput,\n)\nfrom lfx.log.logger import logger\nfrom lfx.schema import Data\nfrom lfx.schema.dataframe import DataFrame\nfrom lfx.schema.dotdict import dotdict\nfrom lfx.schema.message import Message\nfrom lfx.utils.jq_security import validate_jq_program\n\nif TYPE_CHECKING:\n from collections.abc import Callable\n\n# The \"Input Type\" selector tabs. Each value maps a Langflow data type to the\n# operations, input, and output that belong to it.\nINPUT_TYPES = [\"Text\", \"JSON\", \"Table\"]\n\n# Operations grouped by input type, in display order, each with the icon shown\n# in the Operation picker. This is the single source of truth for the picker;\n# update_build_config swaps the picker's options to the selected type's list.\nOPERATIONS_BY_TYPE: dict[str, list[dict[str, str]]] = {\n \"Text\": [\n {\"name\": \"Word Count\", \"icon\": \"hash\"},\n {\"name\": \"Case Conversion\", \"icon\": \"type\"},\n {\"name\": \"Text Replace\", \"icon\": \"replace\"},\n {\"name\": \"Text Extract\", \"icon\": \"search\"},\n {\"name\": \"Text Head\", \"icon\": \"chevron-left\"},\n {\"name\": \"Text Tail\", \"icon\": \"chevron-right\"},\n {\"name\": \"Text Strip\", \"icon\": \"minus\"},\n {\"name\": \"Text Join\", \"icon\": \"link\"},\n {\"name\": \"Text Clean\", \"icon\": \"sparkles\"},\n {\"name\": \"Text to DataFrame\", \"icon\": \"table\"},\n ],\n \"JSON\": [\n {\"name\": \"Select Keys\", \"icon\": \"lasso-select\"},\n {\"name\": \"Literal Eval\", \"icon\": \"braces\"},\n {\"name\": \"Combine\", \"icon\": \"merge\"},\n {\"name\": \"Append or Update\", \"icon\": \"circle-plus\"},\n {\"name\": \"Remove Keys\", \"icon\": \"eraser\"},\n {\"name\": \"Rename Keys\", \"icon\": \"pencil-line\"},\n {\"name\": \"Path Selection\", \"icon\": \"mouse-pointer\"},\n {\"name\": \"JQ Expression\", \"icon\": \"terminal\"},\n ],\n \"Table\": [\n {\"name\": \"Add Column\", \"icon\": \"plus\"},\n {\"name\": \"Concatenate\", \"icon\": \"combine\"},\n {\"name\": \"Drop Column\", \"icon\": \"minus\"},\n {\"name\": \"Filter\", \"icon\": \"filter\"},\n {\"name\": \"Head\", \"icon\": \"arrow-up\"},\n {\"name\": \"Merge\", \"icon\": \"merge\"},\n {\"name\": \"Rename Column\", \"icon\": \"pencil\"},\n {\"name\": \"Replace Value\", \"icon\": \"replace\"},\n {\"name\": \"Select Columns\", \"icon\": \"columns\"},\n {\"name\": \"Sort\", \"icon\": \"arrow-up-down\"},\n {\"name\": \"Tail\", \"icon\": \"arrow-down\"},\n {\"name\": \"Drop Duplicates\", \"icon\": \"copy-x\"},\n ],\n}\n\n# Operation-name sets derived from the picker, used for dispatch and output\n# routing. Keeping them derived from OPERATIONS_BY_TYPE avoids any drift.\nJSON_OPERATIONS = {op[\"name\"] for op in OPERATIONS_BY_TYPE[\"JSON\"]}\nTABLE_OPERATIONS = {op[\"name\"] for op in OPERATIONS_BY_TYPE[\"Table\"]}\nTEXT_OPERATIONS = {op[\"name\"] for op in OPERATIONS_BY_TYPE[\"Text\"]}\n\n# Each input type maps to its main input field and its default output. \"Text\"\n# normally outputs a Message; \"JSON\" a Data; \"Table\" a DataFrame. A few text\n# operations override this (Word Count -> Data, Text to DataFrame -> DataFrame).\nINPUT_TYPE_TO_MAIN_INPUT = {\"Text\": \"text_input\", \"JSON\": \"data\", \"Table\": \"df\"}\n\n# Case conversions for the Text \"Case Conversion\" operation.\nCASE_CONVERTERS: dict[str, Any] = {\n \"uppercase\": str.upper,\n \"lowercase\": str.lower,\n \"title\": str.title,\n \"capitalize\": str.capitalize,\n \"swapcase\": str.swapcase,\n}\n\n# A markdown table's delimiter row (``|---|:--:|``) separates the header from the body.\nMARKDOWN_DELIMITER_CELL = re.compile(r\":?-+:?\")\n\n\nclass OperationsComponent(Component):\n display_name = \"Data Operations\"\n description = \"Perform operations on Text, JSON, and Tables from a single component.\"\n documentation: str = \"https://docs.langflow.org/components-processing#operations\"\n icon = \"wand-sparkles\"\n name = \"Operations\"\n metadata = {\n \"keywords\": [\n \"operations\",\n \"data operations\",\n \"json\",\n \"json operations\",\n \"table\",\n \"table operations\",\n \"dataframe\",\n \"dataframe operations\",\n \"text\",\n \"text operations\",\n \"select keys\",\n \"literal eval\",\n \"combine\",\n \"append or update\",\n \"remove keys\",\n \"rename keys\",\n \"path selection\",\n \"jq expression\",\n \"parse json\",\n \"add column\",\n \"concatenate\",\n \"drop column\",\n \"filter\",\n \"head\",\n \"merge\",\n \"rename column\",\n \"replace value\",\n \"select columns\",\n \"sort\",\n \"tail\",\n \"drop duplicates\",\n \"word count\",\n \"case conversion\",\n \"text replace\",\n \"text extract\",\n \"text join\",\n \"text clean\",\n \"text to dataframe\",\n \"data manipulation\",\n \"data transformation\",\n ],\n }\n\n # Operation -> operation-specific input fields to reveal when selected.\n OPERATION_FIELDS: dict[str, list[str]] = {\n # JSON\n \"Select Keys\": [\"select_keys_input\"],\n \"Literal Eval\": [],\n \"Combine\": [],\n \"Append or Update\": [\"append_update_data\"],\n \"Remove Keys\": [\"remove_keys_input\"],\n \"Rename Keys\": [\"rename_keys_input\"],\n \"Path Selection\": [\"mapped_json_display\", \"selected_key\"],\n \"JQ Expression\": [\"query\"],\n # Table\n \"Add Column\": [\"new_column_name\", \"new_column_value\"],\n \"Concatenate\": [],\n \"Drop Column\": [\"column_name\"],\n \"Filter\": [\"column_name\", \"filter_value\", \"filter_operator\"],\n \"Head\": [\"num_rows\"],\n \"Merge\": [\"left_dataframe\", \"right_dataframe\", \"merge_on_column\", \"merge_how\"],\n \"Rename Column\": [\"column_name\", \"new_column_name\"],\n \"Replace Value\": [\"column_name\", \"replace_value\", \"replacement_value\"],\n \"Select Columns\": [\"columns_to_select\"],\n \"Sort\": [\"column_name\", \"ascending\"],\n \"Tail\": [\"num_rows\"],\n \"Drop Duplicates\": [\"column_name\"],\n # Text\n \"Word Count\": [\"count_words\", \"count_characters\", \"count_lines\"],\n \"Case Conversion\": [\"case_type\"],\n \"Text Replace\": [\"search_pattern\", \"replacement_text\", \"use_regex\"],\n \"Text Extract\": [\"extract_pattern\", \"max_matches\"],\n \"Text Head\": [\"head_characters\"],\n \"Text Tail\": [\"tail_characters\"],\n \"Text Strip\": [\"strip_mode\", \"strip_characters\"],\n \"Text Join\": [\"text_input_2\"],\n \"Text Clean\": [\"remove_extra_spaces\", \"remove_special_chars\", \"remove_empty_lines\"],\n \"Text to DataFrame\": [\"table_separator\", \"has_header\"],\n }\n\n # The three main inputs (one per data type). They are never treated as\n # operation-specific fields; the input-type selector toggles them.\n MAIN_INPUTS = (\"text_input\", \"data\", \"df\")\n\n # Every operation-specific field (union of all the lists above), used to\n # hide and reset fields whenever the input type or operation changes.\n ALL_OPERATION_FIELDS: list[str] = [\n # JSON\n \"select_keys_input\",\n \"append_update_data\",\n \"remove_keys_input\",\n \"rename_keys_input\",\n \"mapped_json_display\",\n \"selected_key\",\n \"query\",\n # Table\n \"column_name\",\n \"filter_value\",\n \"filter_operator\",\n \"ascending\",\n \"new_column_name\",\n \"new_column_value\",\n \"columns_to_select\",\n \"num_rows\",\n \"replace_value\",\n \"replacement_value\",\n \"left_dataframe\",\n \"right_dataframe\",\n \"merge_on_column\",\n \"merge_how\",\n # Text\n \"table_separator\",\n \"has_header\",\n \"count_words\",\n \"count_characters\",\n \"count_lines\",\n \"case_type\",\n \"use_regex\",\n \"search_pattern\",\n \"replacement_text\",\n \"extract_pattern\",\n \"max_matches\",\n \"head_characters\",\n \"tail_characters\",\n \"strip_mode\",\n \"strip_characters\",\n \"text_input_2\",\n \"remove_extra_spaces\",\n \"remove_special_chars\",\n \"remove_empty_lines\",\n ]\n\n # Defaults applied to the JSON operation fields when the operation changes,\n # mirroring the JSON Operations component's reset behavior.\n OPERATION_FIELD_DEFAULTS: dict[str, Any] = {\n \"select_keys_input\": [],\n \"append_update_data\": {\"key\": \"value\"},\n \"remove_keys_input\": [],\n \"rename_keys_input\": {\"old_key\": \"new_key\"},\n \"mapped_json_display\": \"\",\n \"selected_key\": None,\n \"query\": \"\",\n }\n\n inputs = [\n # --- Input type selector: drives operations, input, and output ---\n TabInput(\n name=\"input_type\",\n display_name=\"Input Type\",\n options=INPUT_TYPES,\n value=\"Text\",\n info=\"Select the type of input to operate on.\",\n real_time_refresh=True,\n ),\n # --- Main inputs: one per data type, shown contextually ---\n MultilineInput(\n name=\"text_input\",\n display_name=\"Text\",\n info=\"The input text to process.\",\n show=True,\n ),\n DataInput(\n name=\"data\",\n display_name=\"JSON\",\n info=\"The JSON / Data object to operate on.\",\n is_list=True,\n show=False,\n ),\n DataFrameInput(\n name=\"df\",\n display_name=\"Table\",\n info=\"The input Table to operate on. Connect multiple Tables for merge or concatenate operations.\",\n is_list=True,\n show=False,\n ),\n # --- Operation picker (options are filtered by Input Type) ---\n SortableListInput(\n name=\"operation\",\n display_name=\"Operation\",\n placeholder=\"Select Operation\",\n info=\"Select the operation to perform. The matching fields and output appear once you choose one.\",\n options=OPERATIONS_BY_TYPE[\"Text\"],\n real_time_refresh=True,\n limit=1,\n ),\n # --- JSON operation fields ---\n MessageTextInput(\n name=\"select_keys_input\",\n display_name=\"Select Keys\",\n info=\"List of keys to select from the data. Only top-level keys can be selected.\",\n show=False,\n is_list=True,\n value=[],\n ),\n DictInput(\n name=\"append_update_data\",\n display_name=\"Append or Update\",\n info=\"Data to append or update the existing data with. Only top-level keys are checked.\",\n show=False,\n value={\"key\": \"value\"},\n is_list=True,\n ),\n MessageTextInput(\n name=\"remove_keys_input\",\n display_name=\"Remove Keys\",\n info=\"List of keys to remove from the data.\",\n show=False,\n is_list=True,\n value=[],\n ),\n DictInput(\n name=\"rename_keys_input\",\n display_name=\"Rename Keys\",\n info=\"List of keys to rename in the data.\",\n show=False,\n is_list=True,\n value={\"old_key\": \"new_key\"},\n ),\n MultilineInput(\n name=\"mapped_json_display\",\n display_name=\"JSON to Map\",\n info=\"Paste or preview your JSON here to explore its structure and select a path for extraction.\",\n required=False,\n refresh_button=True,\n real_time_refresh=True,\n placeholder=\"Add a JSON example.\",\n show=False,\n ),\n DropdownInput(\n name=\"selected_key\",\n display_name=\"Select Path\",\n options=[],\n required=False,\n dynamic=True,\n show=False,\n value=None,\n ),\n MessageTextInput(\n name=\"query\",\n display_name=\"JQ Expression\",\n info=\"JSON Query to filter the data. Used by Path Selection and JQ Expression operations.\",\n placeholder=\"e.g., .properties.id\",\n show=False,\n ),\n # --- Table operation fields ---\n StrInput(\n name=\"column_name\",\n display_name=\"Column Name\",\n info=\"The column name to use for the operation.\",\n dynamic=True,\n show=False,\n ),\n MessageTextInput(\n name=\"filter_value\",\n display_name=\"Filter Value\",\n info=\"The value to filter rows by.\",\n dynamic=True,\n show=False,\n ),\n DropdownInput(\n name=\"filter_operator\",\n display_name=\"Filter Operator\",\n options=[\n \"equals\",\n \"not equals\",\n \"contains\",\n \"not contains\",\n \"starts with\",\n \"ends with\",\n \"greater than\",\n \"less than\",\n ],\n value=\"equals\",\n info=\"The operator to apply for filtering rows.\",\n advanced=False,\n dynamic=True,\n show=False,\n ),\n BoolInput(\n name=\"ascending\",\n display_name=\"Sort Ascending\",\n info=\"Whether to sort in ascending order.\",\n dynamic=True,\n show=False,\n value=True,\n ),\n StrInput(\n name=\"new_column_name\",\n display_name=\"New Column Name\",\n info=\"The new column name when renaming or adding a column.\",\n dynamic=True,\n show=False,\n ),\n MessageTextInput(\n name=\"new_column_value\",\n display_name=\"New Column Value\",\n info=\"The value to populate the new column with.\",\n dynamic=True,\n show=False,\n ),\n StrInput(\n name=\"columns_to_select\",\n display_name=\"Columns to Select\",\n dynamic=True,\n is_list=True,\n show=False,\n ),\n IntInput(\n name=\"num_rows\",\n display_name=\"Number of Rows\",\n info=\"Number of rows to return (for head/tail).\",\n dynamic=True,\n show=False,\n value=5,\n ),\n MessageTextInput(\n name=\"replace_value\",\n display_name=\"Value to Replace\",\n info=\"The value to replace in the column.\",\n dynamic=True,\n show=False,\n ),\n MessageTextInput(\n name=\"replacement_value\",\n display_name=\"Replacement Value\",\n info=\"The value to replace with.\",\n dynamic=True,\n show=False,\n ),\n DataFrameInput(\n name=\"left_dataframe\",\n display_name=\"Left Table\",\n info=\"The left (primary) Table for merge operations. \"\n \"In a left merge, all rows from this table are preserved.\",\n dynamic=True,\n show=False,\n ),\n DataFrameInput(\n name=\"right_dataframe\",\n display_name=\"Right Table\",\n info=\"The right (secondary) Table for merge operations. \"\n \"In a right merge, all rows from this table are preserved.\",\n dynamic=True,\n show=False,\n ),\n StrInput(\n name=\"merge_on_column\",\n display_name=\"Merge On Column\",\n info=\"The column name to merge Tables on. Must exist in both Tables.\",\n dynamic=True,\n show=False,\n ),\n DropdownInput(\n name=\"merge_how\",\n display_name=\"Merge Type\",\n options=[\"inner\", \"outer\", \"left\", \"right\"],\n value=\"inner\",\n info=\"Type of merge: inner (intersection), outer (union), left, or right.\",\n dynamic=True,\n show=False,\n ),\n # --- Text operation fields ---\n StrInput(\n name=\"table_separator\",\n display_name=\"Table Separator\",\n info=\"Separator used in the table (default: '|').\",\n value=\"|\",\n dynamic=True,\n show=False,\n ),\n BoolInput(\n name=\"has_header\",\n display_name=\"Has Header\",\n info=\"Whether the table has a header row.\",\n value=True,\n dynamic=True,\n advanced=True,\n show=False,\n ),\n BoolInput(\n name=\"count_words\",\n display_name=\"Count Words\",\n info=\"Include word count in analysis.\",\n value=True,\n dynamic=True,\n advanced=True,\n show=False,\n ),\n BoolInput(\n name=\"count_characters\",\n display_name=\"Count Characters\",\n info=\"Include character count in analysis.\",\n value=True,\n dynamic=True,\n advanced=True,\n show=False,\n ),\n BoolInput(\n name=\"count_lines\",\n display_name=\"Count Lines\",\n info=\"Include line count in analysis.\",\n value=True,\n dynamic=True,\n advanced=True,\n show=False,\n ),\n DropdownInput(\n name=\"case_type\",\n display_name=\"Case Type\",\n options=[\"uppercase\", \"lowercase\", \"title\", \"capitalize\", \"swapcase\"],\n value=\"lowercase\",\n info=\"Type of case conversion to apply.\",\n dynamic=True,\n show=False,\n ),\n BoolInput(\n name=\"use_regex\",\n display_name=\"Use Regex\",\n info=\"Whether to treat search pattern as regex.\",\n value=False,\n dynamic=True,\n show=False,\n ),\n StrInput(\n name=\"search_pattern\",\n display_name=\"Search Pattern\",\n info=\"Text pattern to search for (supports regex).\",\n dynamic=True,\n show=False,\n ),\n StrInput(\n name=\"replacement_text\",\n display_name=\"Replacement Text\",\n info=\"Text to replace the search pattern with.\",\n dynamic=True,\n show=False,\n ),\n StrInput(\n name=\"extract_pattern\",\n display_name=\"Extract Pattern\",\n info=\"Regex pattern to extract from text.\",\n dynamic=True,\n show=False,\n ),\n IntInput(\n name=\"max_matches\",\n display_name=\"Max Matches\",\n info=\"Maximum number of matches to extract.\",\n value=10,\n dynamic=True,\n show=False,\n ),\n IntInput(\n name=\"head_characters\",\n display_name=\"Characters from Start\",\n info=\"Number of characters to extract from the beginning of text. Must be non-negative.\",\n value=100,\n dynamic=True,\n show=False,\n range_spec=RangeSpec(min=0, max=1000000, step=1, step_type=\"int\"),\n ),\n IntInput(\n name=\"tail_characters\",\n display_name=\"Characters from End\",\n info=\"Number of characters to extract from the end of text. Must be non-negative.\",\n value=100,\n dynamic=True,\n show=False,\n range_spec=RangeSpec(min=0, max=1000000, step=1, step_type=\"int\"),\n ),\n DropdownInput(\n name=\"strip_mode\",\n display_name=\"Strip Mode\",\n options=[\"both\", \"left\", \"right\"],\n value=\"both\",\n info=\"Which sides to strip whitespace from.\",\n dynamic=True,\n show=False,\n ),\n StrInput(\n name=\"strip_characters\",\n display_name=\"Characters to Strip\",\n info=\"Specific characters to remove (leave empty for whitespace).\",\n value=\"\",\n dynamic=True,\n show=False,\n ),\n MultilineInput(\n name=\"text_input_2\",\n display_name=\"Second Text Input\",\n info=\"Second text to join with the first text.\",\n dynamic=True,\n show=False,\n ),\n BoolInput(\n name=\"remove_extra_spaces\",\n display_name=\"Remove Extra Spaces\",\n info=\"Remove multiple consecutive spaces.\",\n value=True,\n dynamic=True,\n show=False,\n ),\n BoolInput(\n name=\"remove_special_chars\",\n display_name=\"Remove Special Characters\",\n info=\"Remove special characters except alphanumeric and spaces.\",\n value=False,\n dynamic=True,\n show=False,\n ),\n BoolInput(\n name=\"remove_empty_lines\",\n display_name=\"Remove Empty Lines\",\n info=\"Remove empty lines from text.\",\n value=False,\n dynamic=True,\n show=False,\n ),\n ]\n\n # Default output matches the default Input Type (\"Text\" -> Message).\n # update_outputs / update_frontend_node narrow it to the selected type and\n # operation.\n outputs = [Output(display_name=\"Message\", name=\"message_output\", method=\"as_message\")]\n\n # ------------------------------------------------------------------\n # Operation routing helpers\n # ------------------------------------------------------------------\n @staticmethod\n def _extract_operation_name(field_value: Any) -> str:\n \"\"\"Extract the operation name from a SortableListInput value.\"\"\"\n if isinstance(field_value, list) and len(field_value) > 0 and isinstance(field_value[0], dict):\n return field_value[0].get(\"name\", \"\")\n if isinstance(field_value, str):\n return field_value\n return \"\"\n\n def _operation_name(self) -> str:\n \"\"\"Get the currently selected operation name.\"\"\"\n return self._extract_operation_name(getattr(self, \"operation\", []))\n\n @staticmethod\n def _default_output_for_type(input_type: str) -> Output:\n \"\"\"Return the output advertised for an input type when no operation is selected yet.\"\"\"\n if input_type == \"JSON\":\n return Output(display_name=\"JSON\", name=\"data_output\", method=\"as_data\")\n if input_type == \"Table\":\n return Output(display_name=\"Table\", name=\"dataframe_output\", method=\"as_dataframe\")\n return Output(display_name=\"Message\", name=\"message_output\", method=\"as_message\")\n\n # ------------------------------------------------------------------\n # Dynamic UI\n # ------------------------------------------------------------------\n def _reset_operation_fields(self, build_config: dotdict) -> None:\n \"\"\"Hide every operation-specific field and restore its default value.\"\"\"\n for field in self.ALL_OPERATION_FIELDS:\n if field in build_config:\n build_config[field][\"show\"] = False\n if field in self.OPERATION_FIELD_DEFAULTS:\n build_config[field][\"value\"] = self.OPERATION_FIELD_DEFAULTS[field]\n\n def _show_main_input(self, build_config: dotdict, input_type: str, operation: str) -> None:\n \"\"\"Show only the main input that matches the input type; hide the others.\"\"\"\n for inp in self.MAIN_INPUTS:\n if inp in build_config:\n build_config[inp][\"show\"] = False\n build_config[inp][\"required\"] = False\n\n main_input = INPUT_TYPE_TO_MAIN_INPUT.get(input_type)\n if main_input and main_input in build_config:\n build_config[main_input][\"show\"] = True\n build_config[main_input][\"required\"] = True\n # The JSON \"Combine\" operation consumes a list of Data objects.\n if main_input == \"data\":\n build_config[\"data\"][\"is_list\"] = operation == \"Combine\"\n\n def update_build_config(self, build_config: dotdict, field_value: Any, field_name: str | None = None) -> dotdict:\n # Path Selection: refresh the available JSON paths from the pasted JSON.\n if field_name == \"mapped_json_display\":\n try:\n parsed_json = json.loads(field_value)\n keys = self.extract_all_paths(parsed_json)\n build_config[\"selected_key\"][\"options\"] = keys\n build_config[\"selected_key\"][\"show\"] = True\n except (json.JSONDecodeError, TypeError, ValueError) as e:\n logger.error(f\"Error parsing mapped JSON: {e}\")\n build_config[\"selected_key\"][\"show\"] = False\n return build_config\n\n # Input type changed: swap the operation list, clear the selection, and\n # show only the matching input. No operation-specific fields are shown\n # until an operation is picked.\n if field_name == \"input_type\":\n input_type = field_value if field_value in OPERATIONS_BY_TYPE else \"Text\"\n build_config[\"operation\"][\"options\"] = OPERATIONS_BY_TYPE[input_type]\n build_config[\"operation\"][\"value\"] = []\n self._reset_operation_fields(build_config)\n self._show_main_input(build_config, input_type, operation=\"\")\n return build_config\n\n # Operation changed: reset fields, show the input for the current type,\n # then reveal the operation-specific fields.\n if field_name == \"operation\":\n operation = self._extract_operation_name(field_value)\n self._reset_operation_fields(build_config)\n\n input_type = build_config.get(\"input_type\", {}).get(\"value\", \"Text\")\n self._show_main_input(build_config, input_type, operation)\n\n for field in self.OPERATION_FIELDS.get(operation, []):\n if field in build_config:\n build_config[field][\"show\"] = True\n\n return build_config\n\n return build_config\n\n def update_outputs(self, frontend_node: dict, field_name: str, field_value: Any) -> dict:\n \"\"\"Create the output(s) appropriate to the selected input type and operation.\"\"\"\n if field_name == \"input_type\":\n # Switching type clears the operation; advertise the type's default.\n input_type = field_value if field_value in OPERATIONS_BY_TYPE else \"Text\"\n frontend_node[\"outputs\"] = [self._default_output_for_type(input_type)]\n return frontend_node\n\n template = frontend_node.get(\"template\", {})\n input_type = template.get(\"input_type\", {}).get(\"value\", \"Text\")\n\n if field_name == \"operation\":\n operation = self._extract_operation_name(field_value)\n else:\n # Any other refresh (e.g. Path Selection's \"JSON to Map\" field)\n # reaches here on a freshly rebuilt node whose outputs were reset\n # to the class default (Message). Re-derive the output from the\n # saved operation so the refresh doesn't swap the real output type.\n operation = self._extract_operation_name(template.get(\"operation\", {}).get(\"value\", []))\n\n if not operation:\n # No operation selected: fall back to the input type's default output.\n frontend_node[\"outputs\"] = [self._default_output_for_type(input_type)]\n return frontend_node\n\n frontend_node[\"outputs\"] = []\n if operation in JSON_OPERATIONS or operation == \"Word Count\":\n frontend_node[\"outputs\"].append(Output(display_name=\"JSON\", name=\"data_output\", method=\"as_data\"))\n elif operation in TABLE_OPERATIONS or operation == \"Text to DataFrame\":\n frontend_node[\"outputs\"].append(\n Output(display_name=\"Table\", name=\"dataframe_output\", method=\"as_dataframe\")\n )\n elif operation == \"Text Join\":\n frontend_node[\"outputs\"].append(Output(display_name=\"Text\", name=\"text_output\", method=\"as_text\"))\n frontend_node[\"outputs\"].append(Output(display_name=\"Message\", name=\"message_output\", method=\"as_message\"))\n else:\n frontend_node[\"outputs\"].append(Output(display_name=\"Message\", name=\"message_output\", method=\"as_message\"))\n\n return frontend_node\n\n async def update_frontend_node(self, new_frontend_node: dict, current_frontend_node: dict) -> dict:\n \"\"\"Keep the operation options and outputs in sync with the saved input type on load.\"\"\"\n await super().update_frontend_node(new_frontend_node, current_frontend_node)\n\n template = new_frontend_node.get(\"template\", {})\n input_type = template.get(\"input_type\", {}).get(\"value\", \"Text\")\n if input_type not in OPERATIONS_BY_TYPE:\n input_type = \"Text\"\n\n # Filter the operation picker to the saved input type.\n if \"operation\" in template:\n template[\"operation\"][\"options\"] = OPERATIONS_BY_TYPE[input_type]\n\n # Re-derive the outputs from the saved input type + operation.\n operation_value = template.get(\"operation\", {}).get(\"value\", [])\n if self._extract_operation_name(operation_value):\n self.update_outputs(new_frontend_node, \"operation\", operation_value)\n else:\n self.update_outputs(new_frontend_node, \"input_type\", input_type)\n\n return new_frontend_node\n\n # ==================================================================\n # Output methods (referenced by update_outputs)\n # ==================================================================\n def as_data(self) -> Data:\n \"\"\"JSON-typed output: JSON operations and Word Count.\"\"\"\n operation = self._operation_name()\n if operation in JSON_OPERATIONS:\n handler = self._json_handlers().get(operation)\n if handler:\n try:\n return handler()\n except Exception as e:\n logger.error(f\"Error executing {operation}: {e!s}\")\n raise\n if operation == \"Word Count\":\n return self._word_count_data()\n return Data(data={})\n\n def as_dataframe(self) -> DataFrame:\n \"\"\"Table-typed output: Table operations and Text to DataFrame.\"\"\"\n operation = self._operation_name()\n if operation in TABLE_OPERATIONS:\n return self._run_table_operation(operation)\n if operation == \"Text to DataFrame\":\n return self._text_to_dataframe(getattr(self, \"text_input\", \"\") or \"\")\n return DataFrame(pd.DataFrame())\n\n def as_message(self) -> Message:\n \"\"\"Message-typed output: generic text operations (and Text Join).\"\"\"\n return Message(text=self._format_result_as_text(self._run_text_operation()))\n\n def as_text(self) -> Message:\n \"\"\"Text output for the Text Join operation.\"\"\"\n return self.as_message()\n\n # ==================================================================\n # JSON operations\n # ==================================================================\n @staticmethod\n def extract_all_paths(obj, path=\"\"):\n paths = []\n if isinstance(obj, dict):\n for k, v in obj.items():\n new_path = f\"{path}.{k}\" if path else f\".{k}\"\n paths.append(new_path)\n paths.extend(OperationsComponent.extract_all_paths(v, new_path))\n elif isinstance(obj, list) and obj:\n new_path = f\"{path}[0]\"\n paths.append(new_path)\n paths.extend(OperationsComponent.extract_all_paths(obj[0], new_path))\n return paths\n\n @staticmethod\n def remove_keys_recursive(obj, keys_to_remove):\n if isinstance(obj, dict):\n return {\n k: OperationsComponent.remove_keys_recursive(v, keys_to_remove)\n for k, v in obj.items()\n if k not in keys_to_remove\n }\n if isinstance(obj, list):\n return [OperationsComponent.remove_keys_recursive(item, keys_to_remove) for item in obj]\n return obj\n\n @staticmethod\n def rename_keys_recursive(obj, rename_map):\n if isinstance(obj, dict):\n return {\n rename_map.get(k, k): OperationsComponent.rename_keys_recursive(v, rename_map) for k, v in obj.items()\n }\n if isinstance(obj, list):\n return [OperationsComponent.rename_keys_recursive(item, rename_map) for item in obj]\n return obj\n\n def _json_handlers(self) -> \"dict[str, Callable[[], Data]]\":\n return {\n \"Select Keys\": self.select_keys,\n \"Literal Eval\": self.evaluate_data,\n \"Combine\": self.combine_data,\n \"Append or Update\": self.append_update,\n \"Remove Keys\": self.remove_keys,\n \"Rename Keys\": self.rename_keys,\n \"Path Selection\": self.json_path,\n \"JQ Expression\": self.json_query,\n }\n\n def get_data_dict(self) -> dict:\n \"\"\"Extract data dictionary from Data object.\"\"\"\n data = self.data[0] if isinstance(self.data, list) and len(self.data) == 1 else self.data\n return data.model_dump()\n\n def get_normalized_data(self) -> dict:\n \"\"\"Get normalized data dictionary, handling the 'data' key if present.\"\"\"\n data_dict = self.get_data_dict()\n return data_dict.get(\"data\", data_dict)\n\n def data_is_list(self) -> bool:\n \"\"\"Check if data contains multiple items.\"\"\"\n return isinstance(self.data, list) and len(self.data) > 1\n\n def validate_single_data(self, operation: str) -> None:\n \"\"\"Validate that the operation is being performed on a single data object.\"\"\"\n if self.data_is_list():\n msg = f\"{operation} operation is not supported for multiple data objects.\"\n raise ValueError(msg)\n\n def select_keys(self) -> Data:\n \"\"\"Select specific keys from the data dictionary.\"\"\"\n self.validate_single_data(\"Select Keys\")\n data_dict = self.get_normalized_data()\n filter_criteria: list[str] = self.select_keys_input\n\n if len(filter_criteria) == 1 and filter_criteria[0] == \"data\":\n filtered = data_dict[\"data\"]\n else:\n if not all(key in data_dict for key in filter_criteria):\n msg = f\"Select key not found in data. Available keys: {list(data_dict.keys())}\"\n raise ValueError(msg)\n filtered = {key: value for key, value in data_dict.items() if key in filter_criteria}\n\n return Data(data=filtered)\n\n def remove_keys(self) -> Data:\n \"\"\"Remove specified keys from the data dictionary, recursively.\"\"\"\n self.validate_single_data(\"Remove Keys\")\n data_dict = self.get_normalized_data()\n remove_keys_input: list[str] = self.remove_keys_input\n filtered = OperationsComponent.remove_keys_recursive(data_dict, set(remove_keys_input))\n return Data(data=filtered)\n\n def rename_keys(self) -> Data:\n \"\"\"Rename keys in the data dictionary, recursively.\"\"\"\n self.validate_single_data(\"Rename Keys\")\n data_dict = self.get_normalized_data()\n rename_keys_input: dict[str, str] = self.rename_keys_input\n renamed = OperationsComponent.rename_keys_recursive(data_dict, rename_keys_input)\n return Data(data=renamed)\n\n def recursive_eval(self, data: Any) -> Any:\n \"\"\"Recursively evaluate string values that look like Python literals.\"\"\"\n if isinstance(data, dict):\n return {k: self.recursive_eval(v) for k, v in data.items()}\n if isinstance(data, list):\n return [self.recursive_eval(item) for item in data]\n if isinstance(data, str):\n try:\n if (\n data.strip().startswith((\"{\", \"[\", \"(\", \"'\", '\"'))\n or data.strip().lower() in (\"true\", \"false\", \"none\")\n or data.strip().replace(\".\", \"\").isdigit()\n ):\n return ast.literal_eval(data)\n except (ValueError, SyntaxError, TypeError, MemoryError):\n return data\n else:\n return data\n return data\n\n def evaluate_data(self) -> Data:\n \"\"\"Evaluate string values in the data dictionary.\"\"\"\n self.validate_single_data(\"Literal Eval\")\n logger.info(\"evaluating data\")\n return Data(**self.recursive_eval(self.get_data_dict()))\n\n def combine_data(self) -> Data:\n \"\"\"Combine multiple data objects into one.\"\"\"\n logger.info(\"combining data\")\n if not self.data_is_list():\n return self.data[0] if self.data else Data(data={})\n\n data_dicts = [data.model_dump().get(\"data\", data.model_dump()) for data in self.data]\n combined_data: dict[str, Any] = {}\n\n for data_dict in data_dicts:\n for key, value in data_dict.items():\n if key not in combined_data:\n combined_data[key] = value\n elif isinstance(combined_data[key], list):\n if isinstance(value, list):\n combined_data[key].extend(value)\n else:\n combined_data[key].append(value)\n else:\n combined_data[key] = (\n [combined_data[key], value] if not isinstance(value, list) else [combined_data[key], *value]\n )\n\n return Data(**combined_data)\n\n def append_update(self) -> Data:\n \"\"\"Append or update the data with new key-value pairs.\"\"\"\n self.validate_single_data(\"Append or Update\")\n data_filtered = self.get_normalized_data()\n for key, value in self.append_update_data.items():\n data_filtered[key] = value\n return Data(**data_filtered)\n\n def json_path(self) -> Data:\n \"\"\"Extract a value from the data using the selected JQ path.\"\"\"\n try:\n import jq\n except ImportError:\n msg = \"jq is required for Path Selection. Install with: pip install jq\"\n raise ImportError(msg) from None\n\n try:\n if not self.data or not self.selected_key:\n msg = \"Missing input data or selected key.\"\n raise ValueError(msg)\n input_payload = self.data[0].data if isinstance(self.data, list) else self.data.data\n validate_jq_program(self.selected_key)\n compiled = jq.compile(self.selected_key)\n result = compiled.input(input_payload).first()\n if isinstance(result, dict):\n return Data(data=result)\n return Data(data={\"result\": result})\n except (ValueError, TypeError, KeyError) as e:\n self.status = f\"Error: {e!s}\"\n self.log(self.status)\n return Data(data={\"error\": str(e)})\n\n def json_query(self) -> Data:\n \"\"\"Run a JQ expression against the data.\"\"\"\n try:\n import jq\n except ImportError:\n msg = \"jq is required for JQ Expression. Install with: pip install jq\"\n raise ImportError(msg) from None\n\n if not self.query or not self.query.strip():\n msg = \"JSON Query is required and cannot be blank.\"\n raise ValueError(msg)\n raw_data = self.get_data_dict()\n try:\n input_str = json.dumps(raw_data)\n repaired = repair_json(input_str)\n data_json = json.loads(repaired)\n jq_input = data_json[\"data\"] if isinstance(data_json, dict) and \"data\" in data_json else data_json\n validate_jq_program(self.query)\n results = jq.compile(self.query).input(jq_input).all()\n if not results:\n msg = \"No result from JSON query.\"\n raise ValueError(msg)\n result = results[0] if len(results) == 1 else results\n if result is None or result == \"None\":\n msg = \"JSON query returned null/None. Check if the path exists in your data.\"\n raise ValueError(msg)\n if isinstance(result, dict):\n return Data(data=result)\n return Data(data={\"result\": result})\n except (ValueError, TypeError, KeyError, json.JSONDecodeError) as e:\n logger.error(f\"JSON Query failed: {e}\")\n msg = f\"JSON Query error: {e}\"\n raise ValueError(msg) from e\n\n # ==================================================================\n # Table operations\n # ==================================================================\n def _get_primary_dataframe(self) -> DataFrame:\n \"\"\"Get the first DataFrame from input (handles both single and list inputs).\"\"\"\n if isinstance(self.df, list):\n return self.df[0].copy() if self.df else DataFrame()\n return self.df.copy()\n\n def _run_table_operation(self, operation: str) -> DataFrame:\n # Merge and Concatenate use their own inputs, not the primary df.\n if operation == \"Merge\":\n return self.merge_dataframes()\n if operation == \"Concatenate\":\n return self.concatenate_dataframes()\n\n df_copy = self._get_primary_dataframe()\n table_handlers = {\n \"Filter\": self.filter_rows_by_value,\n \"Sort\": self.sort_by_column,\n \"Drop Column\": self.drop_column,\n \"Rename Column\": self.rename_column,\n \"Add Column\": self.add_column,\n \"Select Columns\": self.select_columns,\n \"Head\": self.head,\n \"Tail\": self.tail,\n \"Replace Value\": self.replace_values,\n \"Drop Duplicates\": self.drop_duplicates,\n }\n handler = table_handlers.get(operation)\n if handler is None:\n msg = f\"Unsupported operation: {operation}\"\n logger.error(msg)\n raise ValueError(msg)\n return handler(df_copy)\n\n @staticmethod\n def _comparable_filter_value(column: pd.Series, filter_value: Any) -> Any:\n \"\"\"Return a text input as a number when the column is numeric.\n\n Filter and Replace Value inputs arrive as text, and ``30 == \"30\"`` never matches in pandas.\n A blank input stays text: ``pd.to_numeric(\"\")`` is NaN, which would match missing cells.\n \"\"\"\n if filter_value in (None, \"\"):\n return filter_value\n if pd.api.types.is_numeric_dtype(column) and not pd.api.types.is_bool_dtype(column):\n try:\n return pd.to_numeric(filter_value)\n except (ValueError, TypeError):\n return filter_value\n return filter_value\n\n def filter_rows_by_value(self, df: DataFrame) -> DataFrame:\n column = df[self.column_name]\n filter_value = self.filter_value\n operator = getattr(self, \"filter_operator\", \"equals\")\n\n if operator == \"equals\":\n mask = column == self._comparable_filter_value(column, filter_value)\n elif operator == \"not equals\":\n mask = column != self._comparable_filter_value(column, filter_value)\n elif operator == \"contains\":\n mask = column.astype(str).str.contains(str(filter_value), na=False)\n elif operator == \"not contains\":\n mask = ~column.astype(str).str.contains(str(filter_value), na=False)\n elif operator == \"starts with\":\n mask = column.astype(str).str.startswith(str(filter_value), na=False)\n elif operator == \"ends with\":\n mask = column.astype(str).str.endswith(str(filter_value), na=False)\n elif operator == \"greater than\":\n try:\n numeric_value = pd.to_numeric(filter_value)\n mask = column > numeric_value\n except (ValueError, TypeError):\n mask = column.astype(str) > str(filter_value)\n elif operator == \"less than\":\n try:\n numeric_value = pd.to_numeric(filter_value)\n mask = column < numeric_value\n except (ValueError, TypeError):\n mask = column.astype(str) < str(filter_value)\n else:\n mask = column == self._comparable_filter_value(column, filter_value)\n\n return DataFrame(df[mask])\n\n def sort_by_column(self, df: DataFrame) -> DataFrame:\n return DataFrame(df.sort_values(by=self.column_name, ascending=self.ascending))\n\n def drop_column(self, df: DataFrame) -> DataFrame:\n return DataFrame(df.drop(columns=[self.column_name]))\n\n def rename_column(self, df: DataFrame) -> DataFrame:\n return DataFrame(df.rename(columns={self.column_name: self.new_column_name}))\n\n def add_column(self, df: DataFrame) -> DataFrame:\n df[self.new_column_name] = [self.new_column_value] * len(df)\n return DataFrame(df)\n\n def select_columns(self, df: DataFrame) -> DataFrame:\n columns = [col.strip() for col in self.columns_to_select]\n return DataFrame(df[columns])\n\n def head(self, df: DataFrame) -> DataFrame:\n return DataFrame(df.head(self.num_rows))\n\n def tail(self, df: DataFrame) -> DataFrame:\n return DataFrame(df.tail(self.num_rows))\n\n def replace_values(self, df: DataFrame) -> DataFrame:\n column = df[self.column_name]\n replace_val = self._comparable_filter_value(column, self.replace_value)\n replacement_val = self._comparable_filter_value(column, self.replacement_value)\n try:\n result = column.replace(replace_val, replacement_val)\n except TypeError:\n if not (\n isinstance(column.dtype, pd.api.extensions.ExtensionDtype)\n and pd.api.types.is_integer_dtype(column.dtype)\n ):\n raise\n # Nullable integers reject fractional/text replacements instead of widening like NumPy columns.\n widened = column.astype(\"Float64\" if pd.api.types.is_float(replacement_val) else object)\n # A float cannot represent every Int64 value. Preserve unrelated large integers exactly.\n if not widened.astype(object).equals(column.astype(object)):\n widened = column.astype(object)\n result = widened.mask(column.eq(replace_val).fillna(value=False), replacement_val)\n df[self.column_name] = result\n return DataFrame(df)\n\n def drop_duplicates(self, df: DataFrame) -> DataFrame:\n return DataFrame(df.drop_duplicates(subset=self.column_name))\n\n def concatenate_dataframes(self) -> DataFrame:\n \"\"\"Concatenate multiple DataFrames vertically (stack rows).\"\"\"\n if not isinstance(self.df, list) or len(self.df) == 0:\n return self.df.copy() if self.df is not None else DataFrame()\n\n if len(self.df) == 1:\n return self.df[0].copy()\n\n concatenated = pd.concat(self.df, ignore_index=True)\n return DataFrame(concatenated)\n\n def merge_dataframes(self) -> DataFrame:\n \"\"\"Merge two DataFrames based on a common column (join operation).\"\"\"\n left_df = getattr(self, \"left_dataframe\", None)\n right_df = getattr(self, \"right_dataframe\", None)\n\n if left_df is None:\n return DataFrame()\n if right_df is None:\n return left_df.copy()\n\n df_left = left_df.copy()\n df_right = right_df.copy()\n\n merge_on = getattr(self, \"merge_on_column\", None)\n merge_how = getattr(self, \"merge_how\", \"inner\")\n\n # Track only columns created by this merge, without colliding with input names.\n right_columns = {}\n used_columns = set(df_left.columns) | set(df_right.columns)\n for col in df_left.columns.intersection(df_right.columns):\n if merge_on and col == merge_on:\n continue\n right_col = f\"{col}_right\"\n while right_col in used_columns:\n right_col += \"_right\"\n right_columns[col] = right_col\n used_columns.add(right_col)\n df_right = df_right.rename(columns=right_columns)\n\n if merge_on:\n if merge_on not in df_left.columns:\n msg = f\"Column '{merge_on}' not found in left DataFrame. Available: {list(df_left.columns)}\"\n raise ValueError(msg)\n if merge_on not in df_right.columns:\n msg = f\"Column '{merge_on}' not found in right DataFrame. Available: {list(df_right.columns)}\"\n raise ValueError(msg)\n merged = df_left.merge(df_right, on=merge_on, how=merge_how)\n else:\n merged = df_left.merge(df_right, left_index=True, right_index=True, how=merge_how)\n\n cols_to_drop = []\n for col, right_col in right_columns.items():\n merged[col] = merged[col].combine_first(merged[right_col])\n cols_to_drop.append(right_col)\n\n if cols_to_drop:\n merged = merged.drop(columns=cols_to_drop)\n\n return DataFrame(merged)\n\n # ==================================================================\n # Text operations\n # ==================================================================\n def _run_text_operation(self) -> Any:\n \"\"\"Process text based on the selected operation (Message/Text outputs).\"\"\"\n text = getattr(self, \"text_input\", \"\")\n operation = self._operation_name()\n\n # Allow empty text for Text Join (second input may have content).\n if not text and operation != \"Text Join\":\n return None\n\n text_handlers = {\n \"Case Conversion\": self._case_conversion,\n \"Text Replace\": self._text_replace,\n \"Text Extract\": self._text_extract,\n \"Text Head\": self._text_head,\n \"Text Tail\": self._text_tail,\n \"Text Strip\": self._text_strip,\n \"Text Join\": self._text_join,\n \"Text Clean\": self._text_clean,\n }\n handler = text_handlers.get(operation)\n if handler:\n return handler(text)\n return text\n\n def _word_count_data(self) -> Data:\n \"\"\"Word Count operation result as a Data object.\"\"\"\n result = self._word_count(getattr(self, \"text_input\", \"\") or \"\")\n return Data(data=result)\n\n def _word_count(self, text: str) -> dict[str, Any]:\n \"\"\"Count words, characters, and lines in text.\"\"\"\n result: dict[str, Any] = {}\n text_str = str(text) if text else \"\"\n is_empty = not text_str or not text_str.strip()\n\n if getattr(self, \"count_words\", True):\n if is_empty:\n result[\"word_count\"] = 0\n result[\"unique_words\"] = 0\n else:\n words = text_str.split()\n result[\"word_count\"] = len(words)\n result[\"unique_words\"] = len(set(words))\n\n if getattr(self, \"count_characters\", True):\n if is_empty:\n result[\"character_count\"] = 0\n result[\"character_count_no_spaces\"] = 0\n else:\n result[\"character_count\"] = len(text_str)\n result[\"character_count_no_spaces\"] = len(text_str.replace(\" \", \"\"))\n\n if getattr(self, \"count_lines\", True):\n if is_empty:\n result[\"line_count\"] = 0\n result[\"non_empty_lines\"] = 0\n else:\n lines = text_str.split(\"\\n\")\n result[\"line_count\"] = len(lines)\n result[\"non_empty_lines\"] = len([line for line in lines if line.strip()])\n\n return result\n\n def _text_to_dataframe(self, text: str) -> DataFrame:\n \"\"\"Convert markdown-style table text to a DataFrame.\"\"\"\n lines = [line.strip() for line in text.strip().split(\"\\n\") if line.strip()]\n if not lines:\n return DataFrame(pd.DataFrame())\n\n separator = getattr(self, \"table_separator\", \"|\")\n has_header = getattr(self, \"has_header\", True)\n\n rows = self._parse_table_rows(lines, separator, has_header=has_header)\n if not rows:\n return DataFrame(pd.DataFrame())\n\n df = self._create_dataframe(rows, has_header=has_header)\n self._convert_numeric_columns(df)\n self.log(f\"Converted text to DataFrame: {len(df)} rows, {len(df.columns)} columns\")\n return DataFrame(df)\n\n def _parse_table_rows(self, lines: list[str], separator: str, *, has_header: bool = True) -> list[list[str]]:\n rows = []\n for index, line in enumerate(lines):\n cleaned_line = line.strip(separator)\n cells = [cell.strip() for cell in cleaned_line.split(separator)]\n # Skip the markdown delimiter row under the header instead of reading it as data.\n if has_header and index == 1 and all(MARKDOWN_DELIMITER_CELL.fullmatch(cell) for cell in cells):\n continue\n rows.append(cells)\n return rows\n\n def _create_dataframe(self, rows: list[list[str]], *, has_header: bool) -> pd.DataFrame:\n if has_header and rows:\n header = rows[0]\n data_rows = rows[1:]\n header_col_count = len(header)\n for i, row in enumerate(data_rows):\n row_col_count = len(row)\n if row_col_count != header_col_count:\n msg = (\n f\"Header mismatch: {header_col_count} column(s) in header vs \"\n f\"{row_col_count} column(s) in data row {i + 1}. \"\n \"Please ensure the header has the same number of columns as your data.\"\n )\n raise ValueError(msg)\n return pd.DataFrame(data_rows, columns=header)\n\n max_cols = max(len(row) for row in rows) if rows else 0\n columns = [f\"col_{i}\" for i in range(max_cols)]\n return pd.DataFrame(rows, columns=columns)\n\n def _convert_numeric_columns(self, df: pd.DataFrame) -> None:\n for col in df.columns:\n with contextlib.suppress(ValueError, TypeError):\n df[col] = pd.to_numeric(df[col])\n\n def _case_conversion(self, text: str) -> str:\n case_type = getattr(self, \"case_type\", \"lowercase\")\n converter = CASE_CONVERTERS.get(case_type)\n return converter(text) if converter else text\n\n def _text_replace(self, text: str) -> str:\n search_pattern = getattr(self, \"search_pattern\", \"\")\n if not search_pattern:\n return text\n replacement_text = getattr(self, \"replacement_text\", \"\")\n use_regex = getattr(self, \"use_regex\", False)\n if use_regex:\n try:\n return re.sub(search_pattern, replacement_text, text)\n except re.error as e:\n self.log(f\"Invalid regex pattern: {e}\")\n return text\n return text.replace(search_pattern, replacement_text)\n\n def _text_extract(self, text: str) -> list[str]:\n extract_pattern = getattr(self, \"extract_pattern\", \"\")\n if not extract_pattern:\n return []\n max_matches = getattr(self, \"max_matches\", 10)\n try:\n matches = re.findall(extract_pattern, text)\n except re.error as e:\n msg = f\"Invalid regex pattern '{extract_pattern}': {e}\"\n raise ValueError(msg) from e\n return matches[:max_matches] if max_matches > 0 else matches\n\n def _text_head(self, text: str) -> str:\n head_characters = getattr(self, \"head_characters\", 100)\n if head_characters < 0:\n msg = f\"Characters from Start must be a non-negative integer, got {head_characters}\"\n raise ValueError(msg)\n if head_characters == 0:\n return \"\"\n return text[:head_characters]\n\n def _text_tail(self, text: str) -> str:\n tail_characters = getattr(self, \"tail_characters\", 100)\n if tail_characters < 0:\n msg = f\"Characters from End must be a non-negative integer, got {tail_characters}\"\n raise ValueError(msg)\n if tail_characters == 0:\n return \"\"\n return text[-tail_characters:]\n\n def _text_strip(self, text: str) -> str:\n strip_mode = getattr(self, \"strip_mode\", \"both\")\n strip_characters = getattr(self, \"strip_characters\", \"\")\n text_str = str(text) if text else \"\"\n chars_to_strip = strip_characters if strip_characters else None\n if strip_mode == \"left\":\n return text_str.lstrip(chars_to_strip)\n if strip_mode == \"right\":\n return text_str.rstrip(chars_to_strip)\n return text_str.strip(chars_to_strip)\n\n def _text_join(self, text: str) -> str:\n text_input_2 = getattr(self, \"text_input_2\", \"\")\n text1 = str(text) if text else \"\"\n text2 = str(text_input_2) if text_input_2 else \"\"\n if text1 and text2:\n return f\"{text1}\\n{text2}\"\n return text1 or text2\n\n def _text_clean(self, text: str) -> str:\n result = text\n if getattr(self, \"remove_extra_spaces\", True):\n # Collapse runs of horizontal whitespace but preserve newlines so\n # that remove_empty_lines stays effective when both are enabled.\n result = re.sub(r\"[^\\S\\n]+\", \" \", result)\n if getattr(self, \"remove_special_chars\", False):\n result = re.sub(r\"[^\\w\\s]\", \"\", result)\n if getattr(self, \"remove_empty_lines\", False):\n lines = [line for line in result.split(\"\\n\") if line.strip()]\n result = \"\\n\".join(lines)\n return result\n\n def _format_result_as_text(self, result: Any) -> str:\n if result is None:\n return \"\"\n if isinstance(result, list):\n return \"\\n\".join(str(item) for item in result)\n return str(result)\n"
},
"column_name": {
"_input_type": "StrInput",
@@ -2647,10 +2649,6 @@
},
"dragging": false,
"id": "Operations-uhog5",
- "measured": {
- "height": 52,
- "width": 192
- },
"position": {
"x": 2376.4766535070735,
"y": 1459.7730731731808
@@ -2723,10 +2721,10 @@
],
"frozen": false,
"icon": "wand-sparkles",
- "last_updated": "2026-10-27T20:15:39.924Z",
+ "last_updated": "2026-10-29T18:14:49.919Z",
"legacy": false,
"metadata": {
- "code_hash": "f15ba610cfd0",
+ "code_hash": "6164f967d510",
"dependencies": {
"dependencies": [
{
@@ -2739,7 +2737,7 @@
},
{
"name": "lfx",
- "version": "1.12.3"
+ "version": "1.12.8"
},
{
"name": "jq",
@@ -2820,7 +2818,7 @@
"value": "72c3d17c-2dac-4a73-b48a-6518473d7830"
},
"_frontend_node_folder_id": {
- "value": "f3f8bf74-7a73-4ab3-9769-0d8a4ebbaec9"
+ "value": "afa57272-6d34-4d1c-bf31-27ffad110b3a"
},
"_type": "Component",
"append_update_data": {
@@ -2915,7 +2913,7 @@
"show": true,
"title_case": false,
"type": "code",
- "value": "\"\"\"Unified Operations component.\n\nBrings together the previously separate JSON, Table, and Text operation\ncomponents into a single component. An \"Input Type\" selector (Text / JSON /\nTable) drives everything: it filters the \"Operation\" picker to the operations\nthat apply to that type, reveals the matching input (Text / JSON / Table) and\nits operation-specific fields, and advertises the appropriate output type.\n\nThe three original components (JSON Operations, Table Operations, Text\nOperations) remain available as legacy components for backward compatibility\nwith existing flows.\n\"\"\"\n\nimport ast\nimport contextlib\nimport json\nimport re\nfrom typing import TYPE_CHECKING, Any\n\nimport pandas as pd\nfrom json_repair import repair_json\n\nfrom lfx.custom import Component\nfrom lfx.field_typing import RangeSpec\nfrom lfx.inputs import DictInput, SortableListInput, TabInput\nfrom lfx.io import (\n BoolInput,\n DataFrameInput,\n DataInput,\n DropdownInput,\n IntInput,\n MessageTextInput,\n MultilineInput,\n Output,\n StrInput,\n)\nfrom lfx.log.logger import logger\nfrom lfx.schema import Data\nfrom lfx.schema.dataframe import DataFrame\nfrom lfx.schema.dotdict import dotdict\nfrom lfx.schema.message import Message\nfrom lfx.utils.jq_security import validate_jq_program\n\nif TYPE_CHECKING:\n from collections.abc import Callable\n\n# The \"Input Type\" selector tabs. Each value maps a Langflow data type to the\n# operations, input, and output that belong to it.\nINPUT_TYPES = [\"Text\", \"JSON\", \"Table\"]\n\n# Operations grouped by input type, in display order, each with the icon shown\n# in the Operation picker. This is the single source of truth for the picker;\n# update_build_config swaps the picker's options to the selected type's list.\nOPERATIONS_BY_TYPE: dict[str, list[dict[str, str]]] = {\n \"Text\": [\n {\"name\": \"Word Count\", \"icon\": \"hash\"},\n {\"name\": \"Case Conversion\", \"icon\": \"type\"},\n {\"name\": \"Text Replace\", \"icon\": \"replace\"},\n {\"name\": \"Text Extract\", \"icon\": \"search\"},\n {\"name\": \"Text Head\", \"icon\": \"chevron-left\"},\n {\"name\": \"Text Tail\", \"icon\": \"chevron-right\"},\n {\"name\": \"Text Strip\", \"icon\": \"minus\"},\n {\"name\": \"Text Join\", \"icon\": \"link\"},\n {\"name\": \"Text Clean\", \"icon\": \"sparkles\"},\n {\"name\": \"Text to DataFrame\", \"icon\": \"table\"},\n ],\n \"JSON\": [\n {\"name\": \"Select Keys\", \"icon\": \"lasso-select\"},\n {\"name\": \"Literal Eval\", \"icon\": \"braces\"},\n {\"name\": \"Combine\", \"icon\": \"merge\"},\n {\"name\": \"Append or Update\", \"icon\": \"circle-plus\"},\n {\"name\": \"Remove Keys\", \"icon\": \"eraser\"},\n {\"name\": \"Rename Keys\", \"icon\": \"pencil-line\"},\n {\"name\": \"Path Selection\", \"icon\": \"mouse-pointer\"},\n {\"name\": \"JQ Expression\", \"icon\": \"terminal\"},\n ],\n \"Table\": [\n {\"name\": \"Add Column\", \"icon\": \"plus\"},\n {\"name\": \"Concatenate\", \"icon\": \"combine\"},\n {\"name\": \"Drop Column\", \"icon\": \"minus\"},\n {\"name\": \"Filter\", \"icon\": \"filter\"},\n {\"name\": \"Head\", \"icon\": \"arrow-up\"},\n {\"name\": \"Merge\", \"icon\": \"merge\"},\n {\"name\": \"Rename Column\", \"icon\": \"pencil\"},\n {\"name\": \"Replace Value\", \"icon\": \"replace\"},\n {\"name\": \"Select Columns\", \"icon\": \"columns\"},\n {\"name\": \"Sort\", \"icon\": \"arrow-up-down\"},\n {\"name\": \"Tail\", \"icon\": \"arrow-down\"},\n {\"name\": \"Drop Duplicates\", \"icon\": \"copy-x\"},\n ],\n}\n\n# Operation-name sets derived from the picker, used for dispatch and output\n# routing. Keeping them derived from OPERATIONS_BY_TYPE avoids any drift.\nJSON_OPERATIONS = {op[\"name\"] for op in OPERATIONS_BY_TYPE[\"JSON\"]}\nTABLE_OPERATIONS = {op[\"name\"] for op in OPERATIONS_BY_TYPE[\"Table\"]}\nTEXT_OPERATIONS = {op[\"name\"] for op in OPERATIONS_BY_TYPE[\"Text\"]}\n\n# Each input type maps to its main input field and its default output. \"Text\"\n# normally outputs a Message; \"JSON\" a Data; \"Table\" a DataFrame. A few text\n# operations override this (Word Count -> Data, Text to DataFrame -> DataFrame).\nINPUT_TYPE_TO_MAIN_INPUT = {\"Text\": \"text_input\", \"JSON\": \"data\", \"Table\": \"df\"}\n\n# Case conversions for the Text \"Case Conversion\" operation.\nCASE_CONVERTERS: dict[str, Any] = {\n \"uppercase\": str.upper,\n \"lowercase\": str.lower,\n \"title\": str.title,\n \"capitalize\": str.capitalize,\n \"swapcase\": str.swapcase,\n}\n\n\nclass OperationsComponent(Component):\n display_name = \"Data Operations\"\n description = \"Perform operations on Text, JSON, and Tables from a single component.\"\n documentation: str = \"https://docs.langflow.org/components-processing#operations\"\n icon = \"wand-sparkles\"\n name = \"Operations\"\n metadata = {\n \"keywords\": [\n \"operations\",\n \"data operations\",\n \"json\",\n \"json operations\",\n \"table\",\n \"table operations\",\n \"dataframe\",\n \"dataframe operations\",\n \"text\",\n \"text operations\",\n \"select keys\",\n \"literal eval\",\n \"combine\",\n \"append or update\",\n \"remove keys\",\n \"rename keys\",\n \"path selection\",\n \"jq expression\",\n \"parse json\",\n \"add column\",\n \"concatenate\",\n \"drop column\",\n \"filter\",\n \"head\",\n \"merge\",\n \"rename column\",\n \"replace value\",\n \"select columns\",\n \"sort\",\n \"tail\",\n \"drop duplicates\",\n \"word count\",\n \"case conversion\",\n \"text replace\",\n \"text extract\",\n \"text join\",\n \"text clean\",\n \"text to dataframe\",\n \"data manipulation\",\n \"data transformation\",\n ],\n }\n\n # Operation -> operation-specific input fields to reveal when selected.\n OPERATION_FIELDS: dict[str, list[str]] = {\n # JSON\n \"Select Keys\": [\"select_keys_input\"],\n \"Literal Eval\": [],\n \"Combine\": [],\n \"Append or Update\": [\"append_update_data\"],\n \"Remove Keys\": [\"remove_keys_input\"],\n \"Rename Keys\": [\"rename_keys_input\"],\n \"Path Selection\": [\"mapped_json_display\", \"selected_key\"],\n \"JQ Expression\": [\"query\"],\n # Table\n \"Add Column\": [\"new_column_name\", \"new_column_value\"],\n \"Concatenate\": [],\n \"Drop Column\": [\"column_name\"],\n \"Filter\": [\"column_name\", \"filter_value\", \"filter_operator\"],\n \"Head\": [\"num_rows\"],\n \"Merge\": [\"left_dataframe\", \"right_dataframe\", \"merge_on_column\", \"merge_how\"],\n \"Rename Column\": [\"column_name\", \"new_column_name\"],\n \"Replace Value\": [\"column_name\", \"replace_value\", \"replacement_value\"],\n \"Select Columns\": [\"columns_to_select\"],\n \"Sort\": [\"column_name\", \"ascending\"],\n \"Tail\": [\"num_rows\"],\n \"Drop Duplicates\": [\"column_name\"],\n # Text\n \"Word Count\": [\"count_words\", \"count_characters\", \"count_lines\"],\n \"Case Conversion\": [\"case_type\"],\n \"Text Replace\": [\"search_pattern\", \"replacement_text\", \"use_regex\"],\n \"Text Extract\": [\"extract_pattern\", \"max_matches\"],\n \"Text Head\": [\"head_characters\"],\n \"Text Tail\": [\"tail_characters\"],\n \"Text Strip\": [\"strip_mode\", \"strip_characters\"],\n \"Text Join\": [\"text_input_2\"],\n \"Text Clean\": [\"remove_extra_spaces\", \"remove_special_chars\", \"remove_empty_lines\"],\n \"Text to DataFrame\": [\"table_separator\", \"has_header\"],\n }\n\n # The three main inputs (one per data type). They are never treated as\n # operation-specific fields; the input-type selector toggles them.\n MAIN_INPUTS = (\"text_input\", \"data\", \"df\")\n\n # Every operation-specific field (union of all the lists above), used to\n # hide and reset fields whenever the input type or operation changes.\n ALL_OPERATION_FIELDS: list[str] = [\n # JSON\n \"select_keys_input\",\n \"append_update_data\",\n \"remove_keys_input\",\n \"rename_keys_input\",\n \"mapped_json_display\",\n \"selected_key\",\n \"query\",\n # Table\n \"column_name\",\n \"filter_value\",\n \"filter_operator\",\n \"ascending\",\n \"new_column_name\",\n \"new_column_value\",\n \"columns_to_select\",\n \"num_rows\",\n \"replace_value\",\n \"replacement_value\",\n \"left_dataframe\",\n \"right_dataframe\",\n \"merge_on_column\",\n \"merge_how\",\n # Text\n \"table_separator\",\n \"has_header\",\n \"count_words\",\n \"count_characters\",\n \"count_lines\",\n \"case_type\",\n \"use_regex\",\n \"search_pattern\",\n \"replacement_text\",\n \"extract_pattern\",\n \"max_matches\",\n \"head_characters\",\n \"tail_characters\",\n \"strip_mode\",\n \"strip_characters\",\n \"text_input_2\",\n \"remove_extra_spaces\",\n \"remove_special_chars\",\n \"remove_empty_lines\",\n ]\n\n # Defaults applied to the JSON operation fields when the operation changes,\n # mirroring the JSON Operations component's reset behavior.\n OPERATION_FIELD_DEFAULTS: dict[str, Any] = {\n \"select_keys_input\": [],\n \"append_update_data\": {\"key\": \"value\"},\n \"remove_keys_input\": [],\n \"rename_keys_input\": {\"old_key\": \"new_key\"},\n \"mapped_json_display\": \"\",\n \"selected_key\": None,\n \"query\": \"\",\n }\n\n inputs = [\n # --- Input type selector: drives operations, input, and output ---\n TabInput(\n name=\"input_type\",\n display_name=\"Input Type\",\n options=INPUT_TYPES,\n value=\"Text\",\n info=\"Select the type of input to operate on.\",\n real_time_refresh=True,\n ),\n # --- Main inputs: one per data type, shown contextually ---\n MultilineInput(\n name=\"text_input\",\n display_name=\"Text\",\n info=\"The input text to process.\",\n show=True,\n ),\n DataInput(\n name=\"data\",\n display_name=\"JSON\",\n info=\"The JSON / Data object to operate on.\",\n is_list=True,\n show=False,\n ),\n DataFrameInput(\n name=\"df\",\n display_name=\"Table\",\n info=\"The input Table to operate on. Connect multiple Tables for merge or concatenate operations.\",\n is_list=True,\n show=False,\n ),\n # --- Operation picker (options are filtered by Input Type) ---\n SortableListInput(\n name=\"operation\",\n display_name=\"Operation\",\n placeholder=\"Select Operation\",\n info=\"Select the operation to perform. The matching fields and output appear once you choose one.\",\n options=OPERATIONS_BY_TYPE[\"Text\"],\n real_time_refresh=True,\n limit=1,\n ),\n # --- JSON operation fields ---\n MessageTextInput(\n name=\"select_keys_input\",\n display_name=\"Select Keys\",\n info=\"List of keys to select from the data. Only top-level keys can be selected.\",\n show=False,\n is_list=True,\n value=[],\n ),\n DictInput(\n name=\"append_update_data\",\n display_name=\"Append or Update\",\n info=\"Data to append or update the existing data with. Only top-level keys are checked.\",\n show=False,\n value={\"key\": \"value\"},\n is_list=True,\n ),\n MessageTextInput(\n name=\"remove_keys_input\",\n display_name=\"Remove Keys\",\n info=\"List of keys to remove from the data.\",\n show=False,\n is_list=True,\n value=[],\n ),\n DictInput(\n name=\"rename_keys_input\",\n display_name=\"Rename Keys\",\n info=\"List of keys to rename in the data.\",\n show=False,\n is_list=True,\n value={\"old_key\": \"new_key\"},\n ),\n MultilineInput(\n name=\"mapped_json_display\",\n display_name=\"JSON to Map\",\n info=\"Paste or preview your JSON here to explore its structure and select a path for extraction.\",\n required=False,\n refresh_button=True,\n real_time_refresh=True,\n placeholder=\"Add a JSON example.\",\n show=False,\n ),\n DropdownInput(\n name=\"selected_key\",\n display_name=\"Select Path\",\n options=[],\n required=False,\n dynamic=True,\n show=False,\n value=None,\n ),\n MessageTextInput(\n name=\"query\",\n display_name=\"JQ Expression\",\n info=\"JSON Query to filter the data. Used by Path Selection and JQ Expression operations.\",\n placeholder=\"e.g., .properties.id\",\n show=False,\n ),\n # --- Table operation fields ---\n StrInput(\n name=\"column_name\",\n display_name=\"Column Name\",\n info=\"The column name to use for the operation.\",\n dynamic=True,\n show=False,\n ),\n MessageTextInput(\n name=\"filter_value\",\n display_name=\"Filter Value\",\n info=\"The value to filter rows by.\",\n dynamic=True,\n show=False,\n ),\n DropdownInput(\n name=\"filter_operator\",\n display_name=\"Filter Operator\",\n options=[\n \"equals\",\n \"not equals\",\n \"contains\",\n \"not contains\",\n \"starts with\",\n \"ends with\",\n \"greater than\",\n \"less than\",\n ],\n value=\"equals\",\n info=\"The operator to apply for filtering rows.\",\n advanced=False,\n dynamic=True,\n show=False,\n ),\n BoolInput(\n name=\"ascending\",\n display_name=\"Sort Ascending\",\n info=\"Whether to sort in ascending order.\",\n dynamic=True,\n show=False,\n value=True,\n ),\n StrInput(\n name=\"new_column_name\",\n display_name=\"New Column Name\",\n info=\"The new column name when renaming or adding a column.\",\n dynamic=True,\n show=False,\n ),\n MessageTextInput(\n name=\"new_column_value\",\n display_name=\"New Column Value\",\n info=\"The value to populate the new column with.\",\n dynamic=True,\n show=False,\n ),\n StrInput(\n name=\"columns_to_select\",\n display_name=\"Columns to Select\",\n dynamic=True,\n is_list=True,\n show=False,\n ),\n IntInput(\n name=\"num_rows\",\n display_name=\"Number of Rows\",\n info=\"Number of rows to return (for head/tail).\",\n dynamic=True,\n show=False,\n value=5,\n ),\n MessageTextInput(\n name=\"replace_value\",\n display_name=\"Value to Replace\",\n info=\"The value to replace in the column.\",\n dynamic=True,\n show=False,\n ),\n MessageTextInput(\n name=\"replacement_value\",\n display_name=\"Replacement Value\",\n info=\"The value to replace with.\",\n dynamic=True,\n show=False,\n ),\n DataFrameInput(\n name=\"left_dataframe\",\n display_name=\"Left Table\",\n info=\"The left (primary) Table for merge operations. \"\n \"In a left merge, all rows from this table are preserved.\",\n dynamic=True,\n show=False,\n ),\n DataFrameInput(\n name=\"right_dataframe\",\n display_name=\"Right Table\",\n info=\"The right (secondary) Table for merge operations. \"\n \"In a right merge, all rows from this table are preserved.\",\n dynamic=True,\n show=False,\n ),\n StrInput(\n name=\"merge_on_column\",\n display_name=\"Merge On Column\",\n info=\"The column name to merge Tables on. Must exist in both Tables.\",\n dynamic=True,\n show=False,\n ),\n DropdownInput(\n name=\"merge_how\",\n display_name=\"Merge Type\",\n options=[\"inner\", \"outer\", \"left\", \"right\"],\n value=\"inner\",\n info=\"Type of merge: inner (intersection), outer (union), left, or right.\",\n dynamic=True,\n show=False,\n ),\n # --- Text operation fields ---\n StrInput(\n name=\"table_separator\",\n display_name=\"Table Separator\",\n info=\"Separator used in the table (default: '|').\",\n value=\"|\",\n dynamic=True,\n show=False,\n ),\n BoolInput(\n name=\"has_header\",\n display_name=\"Has Header\",\n info=\"Whether the table has a header row.\",\n value=True,\n dynamic=True,\n advanced=True,\n show=False,\n ),\n BoolInput(\n name=\"count_words\",\n display_name=\"Count Words\",\n info=\"Include word count in analysis.\",\n value=True,\n dynamic=True,\n advanced=True,\n show=False,\n ),\n BoolInput(\n name=\"count_characters\",\n display_name=\"Count Characters\",\n info=\"Include character count in analysis.\",\n value=True,\n dynamic=True,\n advanced=True,\n show=False,\n ),\n BoolInput(\n name=\"count_lines\",\n display_name=\"Count Lines\",\n info=\"Include line count in analysis.\",\n value=True,\n dynamic=True,\n advanced=True,\n show=False,\n ),\n DropdownInput(\n name=\"case_type\",\n display_name=\"Case Type\",\n options=[\"uppercase\", \"lowercase\", \"title\", \"capitalize\", \"swapcase\"],\n value=\"lowercase\",\n info=\"Type of case conversion to apply.\",\n dynamic=True,\n show=False,\n ),\n BoolInput(\n name=\"use_regex\",\n display_name=\"Use Regex\",\n info=\"Whether to treat search pattern as regex.\",\n value=False,\n dynamic=True,\n show=False,\n ),\n StrInput(\n name=\"search_pattern\",\n display_name=\"Search Pattern\",\n info=\"Text pattern to search for (supports regex).\",\n dynamic=True,\n show=False,\n ),\n StrInput(\n name=\"replacement_text\",\n display_name=\"Replacement Text\",\n info=\"Text to replace the search pattern with.\",\n dynamic=True,\n show=False,\n ),\n StrInput(\n name=\"extract_pattern\",\n display_name=\"Extract Pattern\",\n info=\"Regex pattern to extract from text.\",\n dynamic=True,\n show=False,\n ),\n IntInput(\n name=\"max_matches\",\n display_name=\"Max Matches\",\n info=\"Maximum number of matches to extract.\",\n value=10,\n dynamic=True,\n show=False,\n ),\n IntInput(\n name=\"head_characters\",\n display_name=\"Characters from Start\",\n info=\"Number of characters to extract from the beginning of text. Must be non-negative.\",\n value=100,\n dynamic=True,\n show=False,\n range_spec=RangeSpec(min=0, max=1000000, step=1, step_type=\"int\"),\n ),\n IntInput(\n name=\"tail_characters\",\n display_name=\"Characters from End\",\n info=\"Number of characters to extract from the end of text. Must be non-negative.\",\n value=100,\n dynamic=True,\n show=False,\n range_spec=RangeSpec(min=0, max=1000000, step=1, step_type=\"int\"),\n ),\n DropdownInput(\n name=\"strip_mode\",\n display_name=\"Strip Mode\",\n options=[\"both\", \"left\", \"right\"],\n value=\"both\",\n info=\"Which sides to strip whitespace from.\",\n dynamic=True,\n show=False,\n ),\n StrInput(\n name=\"strip_characters\",\n display_name=\"Characters to Strip\",\n info=\"Specific characters to remove (leave empty for whitespace).\",\n value=\"\",\n dynamic=True,\n show=False,\n ),\n MultilineInput(\n name=\"text_input_2\",\n display_name=\"Second Text Input\",\n info=\"Second text to join with the first text.\",\n dynamic=True,\n show=False,\n ),\n BoolInput(\n name=\"remove_extra_spaces\",\n display_name=\"Remove Extra Spaces\",\n info=\"Remove multiple consecutive spaces.\",\n value=True,\n dynamic=True,\n show=False,\n ),\n BoolInput(\n name=\"remove_special_chars\",\n display_name=\"Remove Special Characters\",\n info=\"Remove special characters except alphanumeric and spaces.\",\n value=False,\n dynamic=True,\n show=False,\n ),\n BoolInput(\n name=\"remove_empty_lines\",\n display_name=\"Remove Empty Lines\",\n info=\"Remove empty lines from text.\",\n value=False,\n dynamic=True,\n show=False,\n ),\n ]\n\n # Default output matches the default Input Type (\"Text\" -> Message).\n # update_outputs / update_frontend_node narrow it to the selected type and\n # operation.\n outputs = [Output(display_name=\"Message\", name=\"message_output\", method=\"as_message\")]\n\n # ------------------------------------------------------------------\n # Operation routing helpers\n # ------------------------------------------------------------------\n @staticmethod\n def _extract_operation_name(field_value: Any) -> str:\n \"\"\"Extract the operation name from a SortableListInput value.\"\"\"\n if isinstance(field_value, list) and len(field_value) > 0 and isinstance(field_value[0], dict):\n return field_value[0].get(\"name\", \"\")\n if isinstance(field_value, str):\n return field_value\n return \"\"\n\n def _operation_name(self) -> str:\n \"\"\"Get the currently selected operation name.\"\"\"\n return self._extract_operation_name(getattr(self, \"operation\", []))\n\n @staticmethod\n def _default_output_for_type(input_type: str) -> Output:\n \"\"\"Return the output advertised for an input type when no operation is selected yet.\"\"\"\n if input_type == \"JSON\":\n return Output(display_name=\"JSON\", name=\"data_output\", method=\"as_data\")\n if input_type == \"Table\":\n return Output(display_name=\"Table\", name=\"dataframe_output\", method=\"as_dataframe\")\n return Output(display_name=\"Message\", name=\"message_output\", method=\"as_message\")\n\n # ------------------------------------------------------------------\n # Dynamic UI\n # ------------------------------------------------------------------\n def _reset_operation_fields(self, build_config: dotdict) -> None:\n \"\"\"Hide every operation-specific field and restore its default value.\"\"\"\n for field in self.ALL_OPERATION_FIELDS:\n if field in build_config:\n build_config[field][\"show\"] = False\n if field in self.OPERATION_FIELD_DEFAULTS:\n build_config[field][\"value\"] = self.OPERATION_FIELD_DEFAULTS[field]\n\n def _show_main_input(self, build_config: dotdict, input_type: str, operation: str) -> None:\n \"\"\"Show only the main input that matches the input type; hide the others.\"\"\"\n for inp in self.MAIN_INPUTS:\n if inp in build_config:\n build_config[inp][\"show\"] = False\n build_config[inp][\"required\"] = False\n\n main_input = INPUT_TYPE_TO_MAIN_INPUT.get(input_type)\n if main_input and main_input in build_config:\n build_config[main_input][\"show\"] = True\n build_config[main_input][\"required\"] = True\n # The JSON \"Combine\" operation consumes a list of Data objects.\n if main_input == \"data\":\n build_config[\"data\"][\"is_list\"] = operation == \"Combine\"\n\n def update_build_config(self, build_config: dotdict, field_value: Any, field_name: str | None = None) -> dotdict:\n # Path Selection: refresh the available JSON paths from the pasted JSON.\n if field_name == \"mapped_json_display\":\n try:\n parsed_json = json.loads(field_value)\n keys = self.extract_all_paths(parsed_json)\n build_config[\"selected_key\"][\"options\"] = keys\n build_config[\"selected_key\"][\"show\"] = True\n except (json.JSONDecodeError, TypeError, ValueError) as e:\n logger.error(f\"Error parsing mapped JSON: {e}\")\n build_config[\"selected_key\"][\"show\"] = False\n return build_config\n\n # Input type changed: swap the operation list, clear the selection, and\n # show only the matching input. No operation-specific fields are shown\n # until an operation is picked.\n if field_name == \"input_type\":\n input_type = field_value if field_value in OPERATIONS_BY_TYPE else \"Text\"\n build_config[\"operation\"][\"options\"] = OPERATIONS_BY_TYPE[input_type]\n build_config[\"operation\"][\"value\"] = []\n self._reset_operation_fields(build_config)\n self._show_main_input(build_config, input_type, operation=\"\")\n return build_config\n\n # Operation changed: reset fields, show the input for the current type,\n # then reveal the operation-specific fields.\n if field_name == \"operation\":\n operation = self._extract_operation_name(field_value)\n self._reset_operation_fields(build_config)\n\n input_type = build_config.get(\"input_type\", {}).get(\"value\", \"Text\")\n self._show_main_input(build_config, input_type, operation)\n\n for field in self.OPERATION_FIELDS.get(operation, []):\n if field in build_config:\n build_config[field][\"show\"] = True\n\n return build_config\n\n return build_config\n\n def update_outputs(self, frontend_node: dict, field_name: str, field_value: Any) -> dict:\n \"\"\"Create the output(s) appropriate to the selected input type and operation.\"\"\"\n if field_name == \"input_type\":\n # Switching type clears the operation; advertise the type's default.\n input_type = field_value if field_value in OPERATIONS_BY_TYPE else \"Text\"\n frontend_node[\"outputs\"] = [self._default_output_for_type(input_type)]\n return frontend_node\n\n template = frontend_node.get(\"template\", {})\n input_type = template.get(\"input_type\", {}).get(\"value\", \"Text\")\n\n if field_name == \"operation\":\n operation = self._extract_operation_name(field_value)\n else:\n # Any other refresh (e.g. Path Selection's \"JSON to Map\" field)\n # reaches here on a freshly rebuilt node whose outputs were reset\n # to the class default (Message). Re-derive the output from the\n # saved operation so the refresh doesn't swap the real output type.\n operation = self._extract_operation_name(template.get(\"operation\", {}).get(\"value\", []))\n\n if not operation:\n # No operation selected: fall back to the input type's default output.\n frontend_node[\"outputs\"] = [self._default_output_for_type(input_type)]\n return frontend_node\n\n frontend_node[\"outputs\"] = []\n if operation in JSON_OPERATIONS or operation == \"Word Count\":\n frontend_node[\"outputs\"].append(Output(display_name=\"JSON\", name=\"data_output\", method=\"as_data\"))\n elif operation in TABLE_OPERATIONS or operation == \"Text to DataFrame\":\n frontend_node[\"outputs\"].append(\n Output(display_name=\"Table\", name=\"dataframe_output\", method=\"as_dataframe\")\n )\n elif operation == \"Text Join\":\n frontend_node[\"outputs\"].append(Output(display_name=\"Text\", name=\"text_output\", method=\"as_text\"))\n frontend_node[\"outputs\"].append(Output(display_name=\"Message\", name=\"message_output\", method=\"as_message\"))\n else:\n frontend_node[\"outputs\"].append(Output(display_name=\"Message\", name=\"message_output\", method=\"as_message\"))\n\n return frontend_node\n\n async def update_frontend_node(self, new_frontend_node: dict, current_frontend_node: dict) -> dict:\n \"\"\"Keep the operation options and outputs in sync with the saved input type on load.\"\"\"\n await super().update_frontend_node(new_frontend_node, current_frontend_node)\n\n template = new_frontend_node.get(\"template\", {})\n input_type = template.get(\"input_type\", {}).get(\"value\", \"Text\")\n if input_type not in OPERATIONS_BY_TYPE:\n input_type = \"Text\"\n\n # Filter the operation picker to the saved input type.\n if \"operation\" in template:\n template[\"operation\"][\"options\"] = OPERATIONS_BY_TYPE[input_type]\n\n # Re-derive the outputs from the saved input type + operation.\n operation_value = template.get(\"operation\", {}).get(\"value\", [])\n if self._extract_operation_name(operation_value):\n self.update_outputs(new_frontend_node, \"operation\", operation_value)\n else:\n self.update_outputs(new_frontend_node, \"input_type\", input_type)\n\n return new_frontend_node\n\n # ==================================================================\n # Output methods (referenced by update_outputs)\n # ==================================================================\n def as_data(self) -> Data:\n \"\"\"JSON-typed output: JSON operations and Word Count.\"\"\"\n operation = self._operation_name()\n if operation in JSON_OPERATIONS:\n handler = self._json_handlers().get(operation)\n if handler:\n try:\n return handler()\n except Exception as e:\n logger.error(f\"Error executing {operation}: {e!s}\")\n raise\n if operation == \"Word Count\":\n return self._word_count_data()\n return Data(data={})\n\n def as_dataframe(self) -> DataFrame:\n \"\"\"Table-typed output: Table operations and Text to DataFrame.\"\"\"\n operation = self._operation_name()\n if operation in TABLE_OPERATIONS:\n return self._run_table_operation(operation)\n if operation == \"Text to DataFrame\":\n return self._text_to_dataframe(getattr(self, \"text_input\", \"\") or \"\")\n return DataFrame(pd.DataFrame())\n\n def as_message(self) -> Message:\n \"\"\"Message-typed output: generic text operations (and Text Join).\"\"\"\n return Message(text=self._format_result_as_text(self._run_text_operation()))\n\n def as_text(self) -> Message:\n \"\"\"Text output for the Text Join operation.\"\"\"\n return self.as_message()\n\n # ==================================================================\n # JSON operations\n # ==================================================================\n @staticmethod\n def extract_all_paths(obj, path=\"\"):\n paths = []\n if isinstance(obj, dict):\n for k, v in obj.items():\n new_path = f\"{path}.{k}\" if path else f\".{k}\"\n paths.append(new_path)\n paths.extend(OperationsComponent.extract_all_paths(v, new_path))\n elif isinstance(obj, list) and obj:\n new_path = f\"{path}[0]\"\n paths.append(new_path)\n paths.extend(OperationsComponent.extract_all_paths(obj[0], new_path))\n return paths\n\n @staticmethod\n def remove_keys_recursive(obj, keys_to_remove):\n if isinstance(obj, dict):\n return {\n k: OperationsComponent.remove_keys_recursive(v, keys_to_remove)\n for k, v in obj.items()\n if k not in keys_to_remove\n }\n if isinstance(obj, list):\n return [OperationsComponent.remove_keys_recursive(item, keys_to_remove) for item in obj]\n return obj\n\n @staticmethod\n def rename_keys_recursive(obj, rename_map):\n if isinstance(obj, dict):\n return {\n rename_map.get(k, k): OperationsComponent.rename_keys_recursive(v, rename_map) for k, v in obj.items()\n }\n if isinstance(obj, list):\n return [OperationsComponent.rename_keys_recursive(item, rename_map) for item in obj]\n return obj\n\n def _json_handlers(self) -> \"dict[str, Callable[[], Data]]\":\n return {\n \"Select Keys\": self.select_keys,\n \"Literal Eval\": self.evaluate_data,\n \"Combine\": self.combine_data,\n \"Append or Update\": self.append_update,\n \"Remove Keys\": self.remove_keys,\n \"Rename Keys\": self.rename_keys,\n \"Path Selection\": self.json_path,\n \"JQ Expression\": self.json_query,\n }\n\n def get_data_dict(self) -> dict:\n \"\"\"Extract data dictionary from Data object.\"\"\"\n data = self.data[0] if isinstance(self.data, list) and len(self.data) == 1 else self.data\n return data.model_dump()\n\n def get_normalized_data(self) -> dict:\n \"\"\"Get normalized data dictionary, handling the 'data' key if present.\"\"\"\n data_dict = self.get_data_dict()\n return data_dict.get(\"data\", data_dict)\n\n def data_is_list(self) -> bool:\n \"\"\"Check if data contains multiple items.\"\"\"\n return isinstance(self.data, list) and len(self.data) > 1\n\n def validate_single_data(self, operation: str) -> None:\n \"\"\"Validate that the operation is being performed on a single data object.\"\"\"\n if self.data_is_list():\n msg = f\"{operation} operation is not supported for multiple data objects.\"\n raise ValueError(msg)\n\n def select_keys(self) -> Data:\n \"\"\"Select specific keys from the data dictionary.\"\"\"\n self.validate_single_data(\"Select Keys\")\n data_dict = self.get_normalized_data()\n filter_criteria: list[str] = self.select_keys_input\n\n if len(filter_criteria) == 1 and filter_criteria[0] == \"data\":\n filtered = data_dict[\"data\"]\n else:\n if not all(key in data_dict for key in filter_criteria):\n msg = f\"Select key not found in data. Available keys: {list(data_dict.keys())}\"\n raise ValueError(msg)\n filtered = {key: value for key, value in data_dict.items() if key in filter_criteria}\n\n return Data(data=filtered)\n\n def remove_keys(self) -> Data:\n \"\"\"Remove specified keys from the data dictionary, recursively.\"\"\"\n self.validate_single_data(\"Remove Keys\")\n data_dict = self.get_normalized_data()\n remove_keys_input: list[str] = self.remove_keys_input\n filtered = OperationsComponent.remove_keys_recursive(data_dict, set(remove_keys_input))\n return Data(data=filtered)\n\n def rename_keys(self) -> Data:\n \"\"\"Rename keys in the data dictionary, recursively.\"\"\"\n self.validate_single_data(\"Rename Keys\")\n data_dict = self.get_normalized_data()\n rename_keys_input: dict[str, str] = self.rename_keys_input\n renamed = OperationsComponent.rename_keys_recursive(data_dict, rename_keys_input)\n return Data(data=renamed)\n\n def recursive_eval(self, data: Any) -> Any:\n \"\"\"Recursively evaluate string values that look like Python literals.\"\"\"\n if isinstance(data, dict):\n return {k: self.recursive_eval(v) for k, v in data.items()}\n if isinstance(data, list):\n return [self.recursive_eval(item) for item in data]\n if isinstance(data, str):\n try:\n if (\n data.strip().startswith((\"{\", \"[\", \"(\", \"'\", '\"'))\n or data.strip().lower() in (\"true\", \"false\", \"none\")\n or data.strip().replace(\".\", \"\").isdigit()\n ):\n return ast.literal_eval(data)\n except (ValueError, SyntaxError, TypeError, MemoryError):\n return data\n else:\n return data\n return data\n\n def evaluate_data(self) -> Data:\n \"\"\"Evaluate string values in the data dictionary.\"\"\"\n self.validate_single_data(\"Literal Eval\")\n logger.info(\"evaluating data\")\n return Data(**self.recursive_eval(self.get_data_dict()))\n\n def combine_data(self) -> Data:\n \"\"\"Combine multiple data objects into one.\"\"\"\n logger.info(\"combining data\")\n if not self.data_is_list():\n return self.data[0] if self.data else Data(data={})\n\n data_dicts = [data.model_dump().get(\"data\", data.model_dump()) for data in self.data]\n combined_data: dict[str, Any] = {}\n\n for data_dict in data_dicts:\n for key, value in data_dict.items():\n if key not in combined_data:\n combined_data[key] = value\n elif isinstance(combined_data[key], list):\n if isinstance(value, list):\n combined_data[key].extend(value)\n else:\n combined_data[key].append(value)\n else:\n combined_data[key] = (\n [combined_data[key], value] if not isinstance(value, list) else [combined_data[key], *value]\n )\n\n return Data(**combined_data)\n\n def append_update(self) -> Data:\n \"\"\"Append or update the data with new key-value pairs.\"\"\"\n self.validate_single_data(\"Append or Update\")\n data_filtered = self.get_normalized_data()\n for key, value in self.append_update_data.items():\n data_filtered[key] = value\n return Data(**data_filtered)\n\n def json_path(self) -> Data:\n \"\"\"Extract a value from the data using the selected JQ path.\"\"\"\n try:\n import jq\n except ImportError:\n msg = \"jq is required for Path Selection. Install with: pip install jq\"\n raise ImportError(msg) from None\n\n try:\n if not self.data or not self.selected_key:\n msg = \"Missing input data or selected key.\"\n raise ValueError(msg)\n input_payload = self.data[0].data if isinstance(self.data, list) else self.data.data\n validate_jq_program(self.selected_key)\n compiled = jq.compile(self.selected_key)\n result = compiled.input(input_payload).first()\n if isinstance(result, dict):\n return Data(data=result)\n return Data(data={\"result\": result})\n except (ValueError, TypeError, KeyError) as e:\n self.status = f\"Error: {e!s}\"\n self.log(self.status)\n return Data(data={\"error\": str(e)})\n\n def json_query(self) -> Data:\n \"\"\"Run a JQ expression against the data.\"\"\"\n try:\n import jq\n except ImportError:\n msg = \"jq is required for JQ Expression. Install with: pip install jq\"\n raise ImportError(msg) from None\n\n if not self.query or not self.query.strip():\n msg = \"JSON Query is required and cannot be blank.\"\n raise ValueError(msg)\n raw_data = self.get_data_dict()\n try:\n input_str = json.dumps(raw_data)\n repaired = repair_json(input_str)\n data_json = json.loads(repaired)\n jq_input = data_json[\"data\"] if isinstance(data_json, dict) and \"data\" in data_json else data_json\n validate_jq_program(self.query)\n results = jq.compile(self.query).input(jq_input).all()\n if not results:\n msg = \"No result from JSON query.\"\n raise ValueError(msg)\n result = results[0] if len(results) == 1 else results\n if result is None or result == \"None\":\n msg = \"JSON query returned null/None. Check if the path exists in your data.\"\n raise ValueError(msg)\n if isinstance(result, dict):\n return Data(data=result)\n return Data(data={\"result\": result})\n except (ValueError, TypeError, KeyError, json.JSONDecodeError) as e:\n logger.error(f\"JSON Query failed: {e}\")\n msg = f\"JSON Query error: {e}\"\n raise ValueError(msg) from e\n\n # ==================================================================\n # Table operations\n # ==================================================================\n def _get_primary_dataframe(self) -> DataFrame:\n \"\"\"Get the first DataFrame from input (handles both single and list inputs).\"\"\"\n if isinstance(self.df, list):\n return self.df[0].copy() if self.df else DataFrame()\n return self.df.copy()\n\n def _run_table_operation(self, operation: str) -> DataFrame:\n # Merge and Concatenate use their own inputs, not the primary df.\n if operation == \"Merge\":\n return self.merge_dataframes()\n if operation == \"Concatenate\":\n return self.concatenate_dataframes()\n\n df_copy = self._get_primary_dataframe()\n table_handlers = {\n \"Filter\": self.filter_rows_by_value,\n \"Sort\": self.sort_by_column,\n \"Drop Column\": self.drop_column,\n \"Rename Column\": self.rename_column,\n \"Add Column\": self.add_column,\n \"Select Columns\": self.select_columns,\n \"Head\": self.head,\n \"Tail\": self.tail,\n \"Replace Value\": self.replace_values,\n \"Drop Duplicates\": self.drop_duplicates,\n }\n handler = table_handlers.get(operation)\n if handler is None:\n msg = f\"Unsupported operation: {operation}\"\n logger.error(msg)\n raise ValueError(msg)\n return handler(df_copy)\n\n def filter_rows_by_value(self, df: DataFrame) -> DataFrame:\n column = df[self.column_name]\n filter_value = self.filter_value\n operator = getattr(self, \"filter_operator\", \"equals\")\n\n if operator == \"equals\":\n mask = column == filter_value\n elif operator == \"not equals\":\n mask = column != filter_value\n elif operator == \"contains\":\n mask = column.astype(str).str.contains(str(filter_value), na=False)\n elif operator == \"not contains\":\n mask = ~column.astype(str).str.contains(str(filter_value), na=False)\n elif operator == \"starts with\":\n mask = column.astype(str).str.startswith(str(filter_value), na=False)\n elif operator == \"ends with\":\n mask = column.astype(str).str.endswith(str(filter_value), na=False)\n elif operator == \"greater than\":\n try:\n numeric_value = pd.to_numeric(filter_value)\n mask = column > numeric_value\n except (ValueError, TypeError):\n mask = column.astype(str) > str(filter_value)\n elif operator == \"less than\":\n try:\n numeric_value = pd.to_numeric(filter_value)\n mask = column < numeric_value\n except (ValueError, TypeError):\n mask = column.astype(str) < str(filter_value)\n else:\n mask = column == filter_value\n\n return DataFrame(df[mask])\n\n def sort_by_column(self, df: DataFrame) -> DataFrame:\n return DataFrame(df.sort_values(by=self.column_name, ascending=self.ascending))\n\n def drop_column(self, df: DataFrame) -> DataFrame:\n return DataFrame(df.drop(columns=[self.column_name]))\n\n def rename_column(self, df: DataFrame) -> DataFrame:\n return DataFrame(df.rename(columns={self.column_name: self.new_column_name}))\n\n def add_column(self, df: DataFrame) -> DataFrame:\n df[self.new_column_name] = [self.new_column_value] * len(df)\n return DataFrame(df)\n\n def select_columns(self, df: DataFrame) -> DataFrame:\n columns = [col.strip() for col in self.columns_to_select]\n return DataFrame(df[columns])\n\n def head(self, df: DataFrame) -> DataFrame:\n return DataFrame(df.head(self.num_rows))\n\n def tail(self, df: DataFrame) -> DataFrame:\n return DataFrame(df.tail(self.num_rows))\n\n def replace_values(self, df: DataFrame) -> DataFrame:\n df[self.column_name] = df[self.column_name].replace(self.replace_value, self.replacement_value)\n return DataFrame(df)\n\n def drop_duplicates(self, df: DataFrame) -> DataFrame:\n return DataFrame(df.drop_duplicates(subset=self.column_name))\n\n def concatenate_dataframes(self) -> DataFrame:\n \"\"\"Concatenate multiple DataFrames vertically (stack rows).\"\"\"\n if not isinstance(self.df, list) or len(self.df) == 0:\n return self.df.copy() if self.df is not None else DataFrame()\n\n if len(self.df) == 1:\n return self.df[0].copy()\n\n concatenated = pd.concat(self.df, ignore_index=True)\n return DataFrame(concatenated)\n\n def merge_dataframes(self) -> DataFrame:\n \"\"\"Merge two DataFrames based on a common column (join operation).\"\"\"\n left_df = getattr(self, \"left_dataframe\", None)\n right_df = getattr(self, \"right_dataframe\", None)\n\n if left_df is None:\n return DataFrame()\n if right_df is None:\n return left_df.copy()\n\n df_left = left_df.copy()\n df_right = right_df.copy()\n\n merge_on = getattr(self, \"merge_on_column\", None)\n merge_how = getattr(self, \"merge_how\", \"inner\")\n\n if merge_on:\n if merge_on not in df_left.columns:\n msg = f\"Column '{merge_on}' not found in left DataFrame. Available: {list(df_left.columns)}\"\n raise ValueError(msg)\n if merge_on not in df_right.columns:\n msg = f\"Column '{merge_on}' not found in right DataFrame. Available: {list(df_right.columns)}\"\n raise ValueError(msg)\n merged = df_left.merge(df_right, on=merge_on, how=merge_how, suffixes=(\"\", \"_right\"))\n else:\n merged = df_left.merge(df_right, left_index=True, right_index=True, how=merge_how, suffixes=(\"\", \"_right\"))\n\n cols_to_drop = []\n for col in merged.columns:\n if col.endswith(\"_right\"):\n original_col = col[:-6]\n if original_col in merged.columns:\n merged[original_col] = merged[original_col].combine_first(merged[col])\n cols_to_drop.append(col)\n\n if cols_to_drop:\n merged = merged.drop(columns=cols_to_drop)\n\n return DataFrame(merged)\n\n # ==================================================================\n # Text operations\n # ==================================================================\n def _run_text_operation(self) -> Any:\n \"\"\"Process text based on the selected operation (Message/Text outputs).\"\"\"\n text = getattr(self, \"text_input\", \"\")\n operation = self._operation_name()\n\n # Allow empty text for Text Join (second input may have content).\n if not text and operation != \"Text Join\":\n return None\n\n text_handlers = {\n \"Case Conversion\": self._case_conversion,\n \"Text Replace\": self._text_replace,\n \"Text Extract\": self._text_extract,\n \"Text Head\": self._text_head,\n \"Text Tail\": self._text_tail,\n \"Text Strip\": self._text_strip,\n \"Text Join\": self._text_join,\n \"Text Clean\": self._text_clean,\n }\n handler = text_handlers.get(operation)\n if handler:\n return handler(text)\n return text\n\n def _word_count_data(self) -> Data:\n \"\"\"Word Count operation result as a Data object.\"\"\"\n result = self._word_count(getattr(self, \"text_input\", \"\") or \"\")\n return Data(data=result)\n\n def _word_count(self, text: str) -> dict[str, Any]:\n \"\"\"Count words, characters, and lines in text.\"\"\"\n result: dict[str, Any] = {}\n text_str = str(text) if text else \"\"\n is_empty = not text_str or not text_str.strip()\n\n if getattr(self, \"count_words\", True):\n if is_empty:\n result[\"word_count\"] = 0\n result[\"unique_words\"] = 0\n else:\n words = text_str.split()\n result[\"word_count\"] = len(words)\n result[\"unique_words\"] = len(set(words))\n\n if getattr(self, \"count_characters\", True):\n if is_empty:\n result[\"character_count\"] = 0\n result[\"character_count_no_spaces\"] = 0\n else:\n result[\"character_count\"] = len(text_str)\n result[\"character_count_no_spaces\"] = len(text_str.replace(\" \", \"\"))\n\n if getattr(self, \"count_lines\", True):\n if is_empty:\n result[\"line_count\"] = 0\n result[\"non_empty_lines\"] = 0\n else:\n lines = text_str.split(\"\\n\")\n result[\"line_count\"] = len(lines)\n result[\"non_empty_lines\"] = len([line for line in lines if line.strip()])\n\n return result\n\n def _text_to_dataframe(self, text: str) -> DataFrame:\n \"\"\"Convert markdown-style table text to a DataFrame.\"\"\"\n lines = [line.strip() for line in text.strip().split(\"\\n\") if line.strip()]\n if not lines:\n return DataFrame(pd.DataFrame())\n\n separator = getattr(self, \"table_separator\", \"|\")\n has_header = getattr(self, \"has_header\", True)\n\n rows = self._parse_table_rows(lines, separator)\n if not rows:\n return DataFrame(pd.DataFrame())\n\n df = self._create_dataframe(rows, has_header=has_header)\n self._convert_numeric_columns(df)\n self.log(f\"Converted text to DataFrame: {len(df)} rows, {len(df.columns)} columns\")\n return DataFrame(df)\n\n def _parse_table_rows(self, lines: list[str], separator: str) -> list[list[str]]:\n rows = []\n for line in lines:\n cleaned_line = line.strip(separator)\n cells = [cell.strip() for cell in cleaned_line.split(separator)]\n rows.append(cells)\n return rows\n\n def _create_dataframe(self, rows: list[list[str]], *, has_header: bool) -> pd.DataFrame:\n if has_header and len(rows) > 1:\n header = rows[0]\n data_rows = rows[1:]\n header_col_count = len(header)\n for i, row in enumerate(data_rows):\n row_col_count = len(row)\n if row_col_count != header_col_count:\n msg = (\n f\"Header mismatch: {header_col_count} column(s) in header vs \"\n f\"{row_col_count} column(s) in data row {i + 1}. \"\n \"Please ensure the header has the same number of columns as your data.\"\n )\n raise ValueError(msg)\n return pd.DataFrame(data_rows, columns=header)\n\n max_cols = max(len(row) for row in rows) if rows else 0\n columns = [f\"col_{i}\" for i in range(max_cols)]\n return pd.DataFrame(rows, columns=columns)\n\n def _convert_numeric_columns(self, df: pd.DataFrame) -> None:\n for col in df.columns:\n with contextlib.suppress(ValueError, TypeError):\n df[col] = pd.to_numeric(df[col])\n\n def _case_conversion(self, text: str) -> str:\n case_type = getattr(self, \"case_type\", \"lowercase\")\n converter = CASE_CONVERTERS.get(case_type)\n return converter(text) if converter else text\n\n def _text_replace(self, text: str) -> str:\n search_pattern = getattr(self, \"search_pattern\", \"\")\n if not search_pattern:\n return text\n replacement_text = getattr(self, \"replacement_text\", \"\")\n use_regex = getattr(self, \"use_regex\", False)\n if use_regex:\n try:\n return re.sub(search_pattern, replacement_text, text)\n except re.error as e:\n self.log(f\"Invalid regex pattern: {e}\")\n return text\n return text.replace(search_pattern, replacement_text)\n\n def _text_extract(self, text: str) -> list[str]:\n extract_pattern = getattr(self, \"extract_pattern\", \"\")\n if not extract_pattern:\n return []\n max_matches = getattr(self, \"max_matches\", 10)\n try:\n matches = re.findall(extract_pattern, text)\n except re.error as e:\n msg = f\"Invalid regex pattern '{extract_pattern}': {e}\"\n raise ValueError(msg) from e\n return matches[:max_matches] if max_matches > 0 else matches\n\n def _text_head(self, text: str) -> str:\n head_characters = getattr(self, \"head_characters\", 100)\n if head_characters < 0:\n msg = f\"Characters from Start must be a non-negative integer, got {head_characters}\"\n raise ValueError(msg)\n if head_characters == 0:\n return \"\"\n return text[:head_characters]\n\n def _text_tail(self, text: str) -> str:\n tail_characters = getattr(self, \"tail_characters\", 100)\n if tail_characters < 0:\n msg = f\"Characters from End must be a non-negative integer, got {tail_characters}\"\n raise ValueError(msg)\n if tail_characters == 0:\n return \"\"\n return text[-tail_characters:]\n\n def _text_strip(self, text: str) -> str:\n strip_mode = getattr(self, \"strip_mode\", \"both\")\n strip_characters = getattr(self, \"strip_characters\", \"\")\n text_str = str(text) if text else \"\"\n chars_to_strip = strip_characters if strip_characters else None\n if strip_mode == \"left\":\n return text_str.lstrip(chars_to_strip)\n if strip_mode == \"right\":\n return text_str.rstrip(chars_to_strip)\n return text_str.strip(chars_to_strip)\n\n def _text_join(self, text: str) -> str:\n text_input_2 = getattr(self, \"text_input_2\", \"\")\n text1 = str(text) if text else \"\"\n text2 = str(text_input_2) if text_input_2 else \"\"\n if text1 and text2:\n return f\"{text1}\\n{text2}\"\n return text1 or text2\n\n def _text_clean(self, text: str) -> str:\n result = text\n if getattr(self, \"remove_extra_spaces\", True):\n # Collapse runs of horizontal whitespace but preserve newlines so\n # that remove_empty_lines stays effective when both are enabled.\n result = re.sub(r\"[^\\S\\n]+\", \" \", result)\n if getattr(self, \"remove_special_chars\", False):\n result = re.sub(r\"[^\\w\\s]\", \"\", result)\n if getattr(self, \"remove_empty_lines\", False):\n lines = [line for line in result.split(\"\\n\") if line.strip()]\n result = \"\\n\".join(lines)\n return result\n\n def _format_result_as_text(self, result: Any) -> str:\n if result is None:\n return \"\"\n if isinstance(result, list):\n return \"\\n\".join(str(item) for item in result)\n return str(result)\n"
+ "value": "\"\"\"Unified Operations component.\n\nBrings together the previously separate JSON, Table, and Text operation\ncomponents into a single component. An \"Input Type\" selector (Text / JSON /\nTable) drives everything: it filters the \"Operation\" picker to the operations\nthat apply to that type, reveals the matching input (Text / JSON / Table) and\nits operation-specific fields, and advertises the appropriate output type.\n\nThe three original components (JSON Operations, Table Operations, Text\nOperations) remain available as legacy components for backward compatibility\nwith existing flows.\n\"\"\"\n\nimport ast\nimport contextlib\nimport json\nimport re\nfrom typing import TYPE_CHECKING, Any\n\nimport pandas as pd\nfrom json_repair import repair_json\n\nfrom lfx.custom import Component\nfrom lfx.field_typing import RangeSpec\nfrom lfx.inputs import DictInput, SortableListInput, TabInput\nfrom lfx.io import (\n BoolInput,\n DataFrameInput,\n DataInput,\n DropdownInput,\n IntInput,\n MessageTextInput,\n MultilineInput,\n Output,\n StrInput,\n)\nfrom lfx.log.logger import logger\nfrom lfx.schema import Data\nfrom lfx.schema.dataframe import DataFrame\nfrom lfx.schema.dotdict import dotdict\nfrom lfx.schema.message import Message\nfrom lfx.utils.jq_security import validate_jq_program\n\nif TYPE_CHECKING:\n from collections.abc import Callable\n\n# The \"Input Type\" selector tabs. Each value maps a Langflow data type to the\n# operations, input, and output that belong to it.\nINPUT_TYPES = [\"Text\", \"JSON\", \"Table\"]\n\n# Operations grouped by input type, in display order, each with the icon shown\n# in the Operation picker. This is the single source of truth for the picker;\n# update_build_config swaps the picker's options to the selected type's list.\nOPERATIONS_BY_TYPE: dict[str, list[dict[str, str]]] = {\n \"Text\": [\n {\"name\": \"Word Count\", \"icon\": \"hash\"},\n {\"name\": \"Case Conversion\", \"icon\": \"type\"},\n {\"name\": \"Text Replace\", \"icon\": \"replace\"},\n {\"name\": \"Text Extract\", \"icon\": \"search\"},\n {\"name\": \"Text Head\", \"icon\": \"chevron-left\"},\n {\"name\": \"Text Tail\", \"icon\": \"chevron-right\"},\n {\"name\": \"Text Strip\", \"icon\": \"minus\"},\n {\"name\": \"Text Join\", \"icon\": \"link\"},\n {\"name\": \"Text Clean\", \"icon\": \"sparkles\"},\n {\"name\": \"Text to DataFrame\", \"icon\": \"table\"},\n ],\n \"JSON\": [\n {\"name\": \"Select Keys\", \"icon\": \"lasso-select\"},\n {\"name\": \"Literal Eval\", \"icon\": \"braces\"},\n {\"name\": \"Combine\", \"icon\": \"merge\"},\n {\"name\": \"Append or Update\", \"icon\": \"circle-plus\"},\n {\"name\": \"Remove Keys\", \"icon\": \"eraser\"},\n {\"name\": \"Rename Keys\", \"icon\": \"pencil-line\"},\n {\"name\": \"Path Selection\", \"icon\": \"mouse-pointer\"},\n {\"name\": \"JQ Expression\", \"icon\": \"terminal\"},\n ],\n \"Table\": [\n {\"name\": \"Add Column\", \"icon\": \"plus\"},\n {\"name\": \"Concatenate\", \"icon\": \"combine\"},\n {\"name\": \"Drop Column\", \"icon\": \"minus\"},\n {\"name\": \"Filter\", \"icon\": \"filter\"},\n {\"name\": \"Head\", \"icon\": \"arrow-up\"},\n {\"name\": \"Merge\", \"icon\": \"merge\"},\n {\"name\": \"Rename Column\", \"icon\": \"pencil\"},\n {\"name\": \"Replace Value\", \"icon\": \"replace\"},\n {\"name\": \"Select Columns\", \"icon\": \"columns\"},\n {\"name\": \"Sort\", \"icon\": \"arrow-up-down\"},\n {\"name\": \"Tail\", \"icon\": \"arrow-down\"},\n {\"name\": \"Drop Duplicates\", \"icon\": \"copy-x\"},\n ],\n}\n\n# Operation-name sets derived from the picker, used for dispatch and output\n# routing. Keeping them derived from OPERATIONS_BY_TYPE avoids any drift.\nJSON_OPERATIONS = {op[\"name\"] for op in OPERATIONS_BY_TYPE[\"JSON\"]}\nTABLE_OPERATIONS = {op[\"name\"] for op in OPERATIONS_BY_TYPE[\"Table\"]}\nTEXT_OPERATIONS = {op[\"name\"] for op in OPERATIONS_BY_TYPE[\"Text\"]}\n\n# Each input type maps to its main input field and its default output. \"Text\"\n# normally outputs a Message; \"JSON\" a Data; \"Table\" a DataFrame. A few text\n# operations override this (Word Count -> Data, Text to DataFrame -> DataFrame).\nINPUT_TYPE_TO_MAIN_INPUT = {\"Text\": \"text_input\", \"JSON\": \"data\", \"Table\": \"df\"}\n\n# Case conversions for the Text \"Case Conversion\" operation.\nCASE_CONVERTERS: dict[str, Any] = {\n \"uppercase\": str.upper,\n \"lowercase\": str.lower,\n \"title\": str.title,\n \"capitalize\": str.capitalize,\n \"swapcase\": str.swapcase,\n}\n\n# A markdown table's delimiter row (``|---|:--:|``) separates the header from the body.\nMARKDOWN_DELIMITER_CELL = re.compile(r\":?-+:?\")\n\n\nclass OperationsComponent(Component):\n display_name = \"Data Operations\"\n description = \"Perform operations on Text, JSON, and Tables from a single component.\"\n documentation: str = \"https://docs.langflow.org/components-processing#operations\"\n icon = \"wand-sparkles\"\n name = \"Operations\"\n metadata = {\n \"keywords\": [\n \"operations\",\n \"data operations\",\n \"json\",\n \"json operations\",\n \"table\",\n \"table operations\",\n \"dataframe\",\n \"dataframe operations\",\n \"text\",\n \"text operations\",\n \"select keys\",\n \"literal eval\",\n \"combine\",\n \"append or update\",\n \"remove keys\",\n \"rename keys\",\n \"path selection\",\n \"jq expression\",\n \"parse json\",\n \"add column\",\n \"concatenate\",\n \"drop column\",\n \"filter\",\n \"head\",\n \"merge\",\n \"rename column\",\n \"replace value\",\n \"select columns\",\n \"sort\",\n \"tail\",\n \"drop duplicates\",\n \"word count\",\n \"case conversion\",\n \"text replace\",\n \"text extract\",\n \"text join\",\n \"text clean\",\n \"text to dataframe\",\n \"data manipulation\",\n \"data transformation\",\n ],\n }\n\n # Operation -> operation-specific input fields to reveal when selected.\n OPERATION_FIELDS: dict[str, list[str]] = {\n # JSON\n \"Select Keys\": [\"select_keys_input\"],\n \"Literal Eval\": [],\n \"Combine\": [],\n \"Append or Update\": [\"append_update_data\"],\n \"Remove Keys\": [\"remove_keys_input\"],\n \"Rename Keys\": [\"rename_keys_input\"],\n \"Path Selection\": [\"mapped_json_display\", \"selected_key\"],\n \"JQ Expression\": [\"query\"],\n # Table\n \"Add Column\": [\"new_column_name\", \"new_column_value\"],\n \"Concatenate\": [],\n \"Drop Column\": [\"column_name\"],\n \"Filter\": [\"column_name\", \"filter_value\", \"filter_operator\"],\n \"Head\": [\"num_rows\"],\n \"Merge\": [\"left_dataframe\", \"right_dataframe\", \"merge_on_column\", \"merge_how\"],\n \"Rename Column\": [\"column_name\", \"new_column_name\"],\n \"Replace Value\": [\"column_name\", \"replace_value\", \"replacement_value\"],\n \"Select Columns\": [\"columns_to_select\"],\n \"Sort\": [\"column_name\", \"ascending\"],\n \"Tail\": [\"num_rows\"],\n \"Drop Duplicates\": [\"column_name\"],\n # Text\n \"Word Count\": [\"count_words\", \"count_characters\", \"count_lines\"],\n \"Case Conversion\": [\"case_type\"],\n \"Text Replace\": [\"search_pattern\", \"replacement_text\", \"use_regex\"],\n \"Text Extract\": [\"extract_pattern\", \"max_matches\"],\n \"Text Head\": [\"head_characters\"],\n \"Text Tail\": [\"tail_characters\"],\n \"Text Strip\": [\"strip_mode\", \"strip_characters\"],\n \"Text Join\": [\"text_input_2\"],\n \"Text Clean\": [\"remove_extra_spaces\", \"remove_special_chars\", \"remove_empty_lines\"],\n \"Text to DataFrame\": [\"table_separator\", \"has_header\"],\n }\n\n # The three main inputs (one per data type). They are never treated as\n # operation-specific fields; the input-type selector toggles them.\n MAIN_INPUTS = (\"text_input\", \"data\", \"df\")\n\n # Every operation-specific field (union of all the lists above), used to\n # hide and reset fields whenever the input type or operation changes.\n ALL_OPERATION_FIELDS: list[str] = [\n # JSON\n \"select_keys_input\",\n \"append_update_data\",\n \"remove_keys_input\",\n \"rename_keys_input\",\n \"mapped_json_display\",\n \"selected_key\",\n \"query\",\n # Table\n \"column_name\",\n \"filter_value\",\n \"filter_operator\",\n \"ascending\",\n \"new_column_name\",\n \"new_column_value\",\n \"columns_to_select\",\n \"num_rows\",\n \"replace_value\",\n \"replacement_value\",\n \"left_dataframe\",\n \"right_dataframe\",\n \"merge_on_column\",\n \"merge_how\",\n # Text\n \"table_separator\",\n \"has_header\",\n \"count_words\",\n \"count_characters\",\n \"count_lines\",\n \"case_type\",\n \"use_regex\",\n \"search_pattern\",\n \"replacement_text\",\n \"extract_pattern\",\n \"max_matches\",\n \"head_characters\",\n \"tail_characters\",\n \"strip_mode\",\n \"strip_characters\",\n \"text_input_2\",\n \"remove_extra_spaces\",\n \"remove_special_chars\",\n \"remove_empty_lines\",\n ]\n\n # Defaults applied to the JSON operation fields when the operation changes,\n # mirroring the JSON Operations component's reset behavior.\n OPERATION_FIELD_DEFAULTS: dict[str, Any] = {\n \"select_keys_input\": [],\n \"append_update_data\": {\"key\": \"value\"},\n \"remove_keys_input\": [],\n \"rename_keys_input\": {\"old_key\": \"new_key\"},\n \"mapped_json_display\": \"\",\n \"selected_key\": None,\n \"query\": \"\",\n }\n\n inputs = [\n # --- Input type selector: drives operations, input, and output ---\n TabInput(\n name=\"input_type\",\n display_name=\"Input Type\",\n options=INPUT_TYPES,\n value=\"Text\",\n info=\"Select the type of input to operate on.\",\n real_time_refresh=True,\n ),\n # --- Main inputs: one per data type, shown contextually ---\n MultilineInput(\n name=\"text_input\",\n display_name=\"Text\",\n info=\"The input text to process.\",\n show=True,\n ),\n DataInput(\n name=\"data\",\n display_name=\"JSON\",\n info=\"The JSON / Data object to operate on.\",\n is_list=True,\n show=False,\n ),\n DataFrameInput(\n name=\"df\",\n display_name=\"Table\",\n info=\"The input Table to operate on. Connect multiple Tables for merge or concatenate operations.\",\n is_list=True,\n show=False,\n ),\n # --- Operation picker (options are filtered by Input Type) ---\n SortableListInput(\n name=\"operation\",\n display_name=\"Operation\",\n placeholder=\"Select Operation\",\n info=\"Select the operation to perform. The matching fields and output appear once you choose one.\",\n options=OPERATIONS_BY_TYPE[\"Text\"],\n real_time_refresh=True,\n limit=1,\n ),\n # --- JSON operation fields ---\n MessageTextInput(\n name=\"select_keys_input\",\n display_name=\"Select Keys\",\n info=\"List of keys to select from the data. Only top-level keys can be selected.\",\n show=False,\n is_list=True,\n value=[],\n ),\n DictInput(\n name=\"append_update_data\",\n display_name=\"Append or Update\",\n info=\"Data to append or update the existing data with. Only top-level keys are checked.\",\n show=False,\n value={\"key\": \"value\"},\n is_list=True,\n ),\n MessageTextInput(\n name=\"remove_keys_input\",\n display_name=\"Remove Keys\",\n info=\"List of keys to remove from the data.\",\n show=False,\n is_list=True,\n value=[],\n ),\n DictInput(\n name=\"rename_keys_input\",\n display_name=\"Rename Keys\",\n info=\"List of keys to rename in the data.\",\n show=False,\n is_list=True,\n value={\"old_key\": \"new_key\"},\n ),\n MultilineInput(\n name=\"mapped_json_display\",\n display_name=\"JSON to Map\",\n info=\"Paste or preview your JSON here to explore its structure and select a path for extraction.\",\n required=False,\n refresh_button=True,\n real_time_refresh=True,\n placeholder=\"Add a JSON example.\",\n show=False,\n ),\n DropdownInput(\n name=\"selected_key\",\n display_name=\"Select Path\",\n options=[],\n required=False,\n dynamic=True,\n show=False,\n value=None,\n ),\n MessageTextInput(\n name=\"query\",\n display_name=\"JQ Expression\",\n info=\"JSON Query to filter the data. Used by Path Selection and JQ Expression operations.\",\n placeholder=\"e.g., .properties.id\",\n show=False,\n ),\n # --- Table operation fields ---\n StrInput(\n name=\"column_name\",\n display_name=\"Column Name\",\n info=\"The column name to use for the operation.\",\n dynamic=True,\n show=False,\n ),\n MessageTextInput(\n name=\"filter_value\",\n display_name=\"Filter Value\",\n info=\"The value to filter rows by.\",\n dynamic=True,\n show=False,\n ),\n DropdownInput(\n name=\"filter_operator\",\n display_name=\"Filter Operator\",\n options=[\n \"equals\",\n \"not equals\",\n \"contains\",\n \"not contains\",\n \"starts with\",\n \"ends with\",\n \"greater than\",\n \"less than\",\n ],\n value=\"equals\",\n info=\"The operator to apply for filtering rows.\",\n advanced=False,\n dynamic=True,\n show=False,\n ),\n BoolInput(\n name=\"ascending\",\n display_name=\"Sort Ascending\",\n info=\"Whether to sort in ascending order.\",\n dynamic=True,\n show=False,\n value=True,\n ),\n StrInput(\n name=\"new_column_name\",\n display_name=\"New Column Name\",\n info=\"The new column name when renaming or adding a column.\",\n dynamic=True,\n show=False,\n ),\n MessageTextInput(\n name=\"new_column_value\",\n display_name=\"New Column Value\",\n info=\"The value to populate the new column with.\",\n dynamic=True,\n show=False,\n ),\n StrInput(\n name=\"columns_to_select\",\n display_name=\"Columns to Select\",\n dynamic=True,\n is_list=True,\n show=False,\n ),\n IntInput(\n name=\"num_rows\",\n display_name=\"Number of Rows\",\n info=\"Number of rows to return (for head/tail).\",\n dynamic=True,\n show=False,\n value=5,\n ),\n MessageTextInput(\n name=\"replace_value\",\n display_name=\"Value to Replace\",\n info=\"The value to replace in the column.\",\n dynamic=True,\n show=False,\n ),\n MessageTextInput(\n name=\"replacement_value\",\n display_name=\"Replacement Value\",\n info=\"The value to replace with.\",\n dynamic=True,\n show=False,\n ),\n DataFrameInput(\n name=\"left_dataframe\",\n display_name=\"Left Table\",\n info=\"The left (primary) Table for merge operations. \"\n \"In a left merge, all rows from this table are preserved.\",\n dynamic=True,\n show=False,\n ),\n DataFrameInput(\n name=\"right_dataframe\",\n display_name=\"Right Table\",\n info=\"The right (secondary) Table for merge operations. \"\n \"In a right merge, all rows from this table are preserved.\",\n dynamic=True,\n show=False,\n ),\n StrInput(\n name=\"merge_on_column\",\n display_name=\"Merge On Column\",\n info=\"The column name to merge Tables on. Must exist in both Tables.\",\n dynamic=True,\n show=False,\n ),\n DropdownInput(\n name=\"merge_how\",\n display_name=\"Merge Type\",\n options=[\"inner\", \"outer\", \"left\", \"right\"],\n value=\"inner\",\n info=\"Type of merge: inner (intersection), outer (union), left, or right.\",\n dynamic=True,\n show=False,\n ),\n # --- Text operation fields ---\n StrInput(\n name=\"table_separator\",\n display_name=\"Table Separator\",\n info=\"Separator used in the table (default: '|').\",\n value=\"|\",\n dynamic=True,\n show=False,\n ),\n BoolInput(\n name=\"has_header\",\n display_name=\"Has Header\",\n info=\"Whether the table has a header row.\",\n value=True,\n dynamic=True,\n advanced=True,\n show=False,\n ),\n BoolInput(\n name=\"count_words\",\n display_name=\"Count Words\",\n info=\"Include word count in analysis.\",\n value=True,\n dynamic=True,\n advanced=True,\n show=False,\n ),\n BoolInput(\n name=\"count_characters\",\n display_name=\"Count Characters\",\n info=\"Include character count in analysis.\",\n value=True,\n dynamic=True,\n advanced=True,\n show=False,\n ),\n BoolInput(\n name=\"count_lines\",\n display_name=\"Count Lines\",\n info=\"Include line count in analysis.\",\n value=True,\n dynamic=True,\n advanced=True,\n show=False,\n ),\n DropdownInput(\n name=\"case_type\",\n display_name=\"Case Type\",\n options=[\"uppercase\", \"lowercase\", \"title\", \"capitalize\", \"swapcase\"],\n value=\"lowercase\",\n info=\"Type of case conversion to apply.\",\n dynamic=True,\n show=False,\n ),\n BoolInput(\n name=\"use_regex\",\n display_name=\"Use Regex\",\n info=\"Whether to treat search pattern as regex.\",\n value=False,\n dynamic=True,\n show=False,\n ),\n StrInput(\n name=\"search_pattern\",\n display_name=\"Search Pattern\",\n info=\"Text pattern to search for (supports regex).\",\n dynamic=True,\n show=False,\n ),\n StrInput(\n name=\"replacement_text\",\n display_name=\"Replacement Text\",\n info=\"Text to replace the search pattern with.\",\n dynamic=True,\n show=False,\n ),\n StrInput(\n name=\"extract_pattern\",\n display_name=\"Extract Pattern\",\n info=\"Regex pattern to extract from text.\",\n dynamic=True,\n show=False,\n ),\n IntInput(\n name=\"max_matches\",\n display_name=\"Max Matches\",\n info=\"Maximum number of matches to extract.\",\n value=10,\n dynamic=True,\n show=False,\n ),\n IntInput(\n name=\"head_characters\",\n display_name=\"Characters from Start\",\n info=\"Number of characters to extract from the beginning of text. Must be non-negative.\",\n value=100,\n dynamic=True,\n show=False,\n range_spec=RangeSpec(min=0, max=1000000, step=1, step_type=\"int\"),\n ),\n IntInput(\n name=\"tail_characters\",\n display_name=\"Characters from End\",\n info=\"Number of characters to extract from the end of text. Must be non-negative.\",\n value=100,\n dynamic=True,\n show=False,\n range_spec=RangeSpec(min=0, max=1000000, step=1, step_type=\"int\"),\n ),\n DropdownInput(\n name=\"strip_mode\",\n display_name=\"Strip Mode\",\n options=[\"both\", \"left\", \"right\"],\n value=\"both\",\n info=\"Which sides to strip whitespace from.\",\n dynamic=True,\n show=False,\n ),\n StrInput(\n name=\"strip_characters\",\n display_name=\"Characters to Strip\",\n info=\"Specific characters to remove (leave empty for whitespace).\",\n value=\"\",\n dynamic=True,\n show=False,\n ),\n MultilineInput(\n name=\"text_input_2\",\n display_name=\"Second Text Input\",\n info=\"Second text to join with the first text.\",\n dynamic=True,\n show=False,\n ),\n BoolInput(\n name=\"remove_extra_spaces\",\n display_name=\"Remove Extra Spaces\",\n info=\"Remove multiple consecutive spaces.\",\n value=True,\n dynamic=True,\n show=False,\n ),\n BoolInput(\n name=\"remove_special_chars\",\n display_name=\"Remove Special Characters\",\n info=\"Remove special characters except alphanumeric and spaces.\",\n value=False,\n dynamic=True,\n show=False,\n ),\n BoolInput(\n name=\"remove_empty_lines\",\n display_name=\"Remove Empty Lines\",\n info=\"Remove empty lines from text.\",\n value=False,\n dynamic=True,\n show=False,\n ),\n ]\n\n # Default output matches the default Input Type (\"Text\" -> Message).\n # update_outputs / update_frontend_node narrow it to the selected type and\n # operation.\n outputs = [Output(display_name=\"Message\", name=\"message_output\", method=\"as_message\")]\n\n # ------------------------------------------------------------------\n # Operation routing helpers\n # ------------------------------------------------------------------\n @staticmethod\n def _extract_operation_name(field_value: Any) -> str:\n \"\"\"Extract the operation name from a SortableListInput value.\"\"\"\n if isinstance(field_value, list) and len(field_value) > 0 and isinstance(field_value[0], dict):\n return field_value[0].get(\"name\", \"\")\n if isinstance(field_value, str):\n return field_value\n return \"\"\n\n def _operation_name(self) -> str:\n \"\"\"Get the currently selected operation name.\"\"\"\n return self._extract_operation_name(getattr(self, \"operation\", []))\n\n @staticmethod\n def _default_output_for_type(input_type: str) -> Output:\n \"\"\"Return the output advertised for an input type when no operation is selected yet.\"\"\"\n if input_type == \"JSON\":\n return Output(display_name=\"JSON\", name=\"data_output\", method=\"as_data\")\n if input_type == \"Table\":\n return Output(display_name=\"Table\", name=\"dataframe_output\", method=\"as_dataframe\")\n return Output(display_name=\"Message\", name=\"message_output\", method=\"as_message\")\n\n # ------------------------------------------------------------------\n # Dynamic UI\n # ------------------------------------------------------------------\n def _reset_operation_fields(self, build_config: dotdict) -> None:\n \"\"\"Hide every operation-specific field and restore its default value.\"\"\"\n for field in self.ALL_OPERATION_FIELDS:\n if field in build_config:\n build_config[field][\"show\"] = False\n if field in self.OPERATION_FIELD_DEFAULTS:\n build_config[field][\"value\"] = self.OPERATION_FIELD_DEFAULTS[field]\n\n def _show_main_input(self, build_config: dotdict, input_type: str, operation: str) -> None:\n \"\"\"Show only the main input that matches the input type; hide the others.\"\"\"\n for inp in self.MAIN_INPUTS:\n if inp in build_config:\n build_config[inp][\"show\"] = False\n build_config[inp][\"required\"] = False\n\n main_input = INPUT_TYPE_TO_MAIN_INPUT.get(input_type)\n if main_input and main_input in build_config:\n build_config[main_input][\"show\"] = True\n build_config[main_input][\"required\"] = True\n # The JSON \"Combine\" operation consumes a list of Data objects.\n if main_input == \"data\":\n build_config[\"data\"][\"is_list\"] = operation == \"Combine\"\n\n def update_build_config(self, build_config: dotdict, field_value: Any, field_name: str | None = None) -> dotdict:\n # Path Selection: refresh the available JSON paths from the pasted JSON.\n if field_name == \"mapped_json_display\":\n try:\n parsed_json = json.loads(field_value)\n keys = self.extract_all_paths(parsed_json)\n build_config[\"selected_key\"][\"options\"] = keys\n build_config[\"selected_key\"][\"show\"] = True\n except (json.JSONDecodeError, TypeError, ValueError) as e:\n logger.error(f\"Error parsing mapped JSON: {e}\")\n build_config[\"selected_key\"][\"show\"] = False\n return build_config\n\n # Input type changed: swap the operation list, clear the selection, and\n # show only the matching input. No operation-specific fields are shown\n # until an operation is picked.\n if field_name == \"input_type\":\n input_type = field_value if field_value in OPERATIONS_BY_TYPE else \"Text\"\n build_config[\"operation\"][\"options\"] = OPERATIONS_BY_TYPE[input_type]\n build_config[\"operation\"][\"value\"] = []\n self._reset_operation_fields(build_config)\n self._show_main_input(build_config, input_type, operation=\"\")\n return build_config\n\n # Operation changed: reset fields, show the input for the current type,\n # then reveal the operation-specific fields.\n if field_name == \"operation\":\n operation = self._extract_operation_name(field_value)\n self._reset_operation_fields(build_config)\n\n input_type = build_config.get(\"input_type\", {}).get(\"value\", \"Text\")\n self._show_main_input(build_config, input_type, operation)\n\n for field in self.OPERATION_FIELDS.get(operation, []):\n if field in build_config:\n build_config[field][\"show\"] = True\n\n return build_config\n\n return build_config\n\n def update_outputs(self, frontend_node: dict, field_name: str, field_value: Any) -> dict:\n \"\"\"Create the output(s) appropriate to the selected input type and operation.\"\"\"\n if field_name == \"input_type\":\n # Switching type clears the operation; advertise the type's default.\n input_type = field_value if field_value in OPERATIONS_BY_TYPE else \"Text\"\n frontend_node[\"outputs\"] = [self._default_output_for_type(input_type)]\n return frontend_node\n\n template = frontend_node.get(\"template\", {})\n input_type = template.get(\"input_type\", {}).get(\"value\", \"Text\")\n\n if field_name == \"operation\":\n operation = self._extract_operation_name(field_value)\n else:\n # Any other refresh (e.g. Path Selection's \"JSON to Map\" field)\n # reaches here on a freshly rebuilt node whose outputs were reset\n # to the class default (Message). Re-derive the output from the\n # saved operation so the refresh doesn't swap the real output type.\n operation = self._extract_operation_name(template.get(\"operation\", {}).get(\"value\", []))\n\n if not operation:\n # No operation selected: fall back to the input type's default output.\n frontend_node[\"outputs\"] = [self._default_output_for_type(input_type)]\n return frontend_node\n\n frontend_node[\"outputs\"] = []\n if operation in JSON_OPERATIONS or operation == \"Word Count\":\n frontend_node[\"outputs\"].append(Output(display_name=\"JSON\", name=\"data_output\", method=\"as_data\"))\n elif operation in TABLE_OPERATIONS or operation == \"Text to DataFrame\":\n frontend_node[\"outputs\"].append(\n Output(display_name=\"Table\", name=\"dataframe_output\", method=\"as_dataframe\")\n )\n elif operation == \"Text Join\":\n frontend_node[\"outputs\"].append(Output(display_name=\"Text\", name=\"text_output\", method=\"as_text\"))\n frontend_node[\"outputs\"].append(Output(display_name=\"Message\", name=\"message_output\", method=\"as_message\"))\n else:\n frontend_node[\"outputs\"].append(Output(display_name=\"Message\", name=\"message_output\", method=\"as_message\"))\n\n return frontend_node\n\n async def update_frontend_node(self, new_frontend_node: dict, current_frontend_node: dict) -> dict:\n \"\"\"Keep the operation options and outputs in sync with the saved input type on load.\"\"\"\n await super().update_frontend_node(new_frontend_node, current_frontend_node)\n\n template = new_frontend_node.get(\"template\", {})\n input_type = template.get(\"input_type\", {}).get(\"value\", \"Text\")\n if input_type not in OPERATIONS_BY_TYPE:\n input_type = \"Text\"\n\n # Filter the operation picker to the saved input type.\n if \"operation\" in template:\n template[\"operation\"][\"options\"] = OPERATIONS_BY_TYPE[input_type]\n\n # Re-derive the outputs from the saved input type + operation.\n operation_value = template.get(\"operation\", {}).get(\"value\", [])\n if self._extract_operation_name(operation_value):\n self.update_outputs(new_frontend_node, \"operation\", operation_value)\n else:\n self.update_outputs(new_frontend_node, \"input_type\", input_type)\n\n return new_frontend_node\n\n # ==================================================================\n # Output methods (referenced by update_outputs)\n # ==================================================================\n def as_data(self) -> Data:\n \"\"\"JSON-typed output: JSON operations and Word Count.\"\"\"\n operation = self._operation_name()\n if operation in JSON_OPERATIONS:\n handler = self._json_handlers().get(operation)\n if handler:\n try:\n return handler()\n except Exception as e:\n logger.error(f\"Error executing {operation}: {e!s}\")\n raise\n if operation == \"Word Count\":\n return self._word_count_data()\n return Data(data={})\n\n def as_dataframe(self) -> DataFrame:\n \"\"\"Table-typed output: Table operations and Text to DataFrame.\"\"\"\n operation = self._operation_name()\n if operation in TABLE_OPERATIONS:\n return self._run_table_operation(operation)\n if operation == \"Text to DataFrame\":\n return self._text_to_dataframe(getattr(self, \"text_input\", \"\") or \"\")\n return DataFrame(pd.DataFrame())\n\n def as_message(self) -> Message:\n \"\"\"Message-typed output: generic text operations (and Text Join).\"\"\"\n return Message(text=self._format_result_as_text(self._run_text_operation()))\n\n def as_text(self) -> Message:\n \"\"\"Text output for the Text Join operation.\"\"\"\n return self.as_message()\n\n # ==================================================================\n # JSON operations\n # ==================================================================\n @staticmethod\n def extract_all_paths(obj, path=\"\"):\n paths = []\n if isinstance(obj, dict):\n for k, v in obj.items():\n new_path = f\"{path}.{k}\" if path else f\".{k}\"\n paths.append(new_path)\n paths.extend(OperationsComponent.extract_all_paths(v, new_path))\n elif isinstance(obj, list) and obj:\n new_path = f\"{path}[0]\"\n paths.append(new_path)\n paths.extend(OperationsComponent.extract_all_paths(obj[0], new_path))\n return paths\n\n @staticmethod\n def remove_keys_recursive(obj, keys_to_remove):\n if isinstance(obj, dict):\n return {\n k: OperationsComponent.remove_keys_recursive(v, keys_to_remove)\n for k, v in obj.items()\n if k not in keys_to_remove\n }\n if isinstance(obj, list):\n return [OperationsComponent.remove_keys_recursive(item, keys_to_remove) for item in obj]\n return obj\n\n @staticmethod\n def rename_keys_recursive(obj, rename_map):\n if isinstance(obj, dict):\n return {\n rename_map.get(k, k): OperationsComponent.rename_keys_recursive(v, rename_map) for k, v in obj.items()\n }\n if isinstance(obj, list):\n return [OperationsComponent.rename_keys_recursive(item, rename_map) for item in obj]\n return obj\n\n def _json_handlers(self) -> \"dict[str, Callable[[], Data]]\":\n return {\n \"Select Keys\": self.select_keys,\n \"Literal Eval\": self.evaluate_data,\n \"Combine\": self.combine_data,\n \"Append or Update\": self.append_update,\n \"Remove Keys\": self.remove_keys,\n \"Rename Keys\": self.rename_keys,\n \"Path Selection\": self.json_path,\n \"JQ Expression\": self.json_query,\n }\n\n def get_data_dict(self) -> dict:\n \"\"\"Extract data dictionary from Data object.\"\"\"\n data = self.data[0] if isinstance(self.data, list) and len(self.data) == 1 else self.data\n return data.model_dump()\n\n def get_normalized_data(self) -> dict:\n \"\"\"Get normalized data dictionary, handling the 'data' key if present.\"\"\"\n data_dict = self.get_data_dict()\n return data_dict.get(\"data\", data_dict)\n\n def data_is_list(self) -> bool:\n \"\"\"Check if data contains multiple items.\"\"\"\n return isinstance(self.data, list) and len(self.data) > 1\n\n def validate_single_data(self, operation: str) -> None:\n \"\"\"Validate that the operation is being performed on a single data object.\"\"\"\n if self.data_is_list():\n msg = f\"{operation} operation is not supported for multiple data objects.\"\n raise ValueError(msg)\n\n def select_keys(self) -> Data:\n \"\"\"Select specific keys from the data dictionary.\"\"\"\n self.validate_single_data(\"Select Keys\")\n data_dict = self.get_normalized_data()\n filter_criteria: list[str] = self.select_keys_input\n\n if len(filter_criteria) == 1 and filter_criteria[0] == \"data\":\n filtered = data_dict[\"data\"]\n else:\n if not all(key in data_dict for key in filter_criteria):\n msg = f\"Select key not found in data. Available keys: {list(data_dict.keys())}\"\n raise ValueError(msg)\n filtered = {key: value for key, value in data_dict.items() if key in filter_criteria}\n\n return Data(data=filtered)\n\n def remove_keys(self) -> Data:\n \"\"\"Remove specified keys from the data dictionary, recursively.\"\"\"\n self.validate_single_data(\"Remove Keys\")\n data_dict = self.get_normalized_data()\n remove_keys_input: list[str] = self.remove_keys_input\n filtered = OperationsComponent.remove_keys_recursive(data_dict, set(remove_keys_input))\n return Data(data=filtered)\n\n def rename_keys(self) -> Data:\n \"\"\"Rename keys in the data dictionary, recursively.\"\"\"\n self.validate_single_data(\"Rename Keys\")\n data_dict = self.get_normalized_data()\n rename_keys_input: dict[str, str] = self.rename_keys_input\n renamed = OperationsComponent.rename_keys_recursive(data_dict, rename_keys_input)\n return Data(data=renamed)\n\n def recursive_eval(self, data: Any) -> Any:\n \"\"\"Recursively evaluate string values that look like Python literals.\"\"\"\n if isinstance(data, dict):\n return {k: self.recursive_eval(v) for k, v in data.items()}\n if isinstance(data, list):\n return [self.recursive_eval(item) for item in data]\n if isinstance(data, str):\n try:\n if (\n data.strip().startswith((\"{\", \"[\", \"(\", \"'\", '\"'))\n or data.strip().lower() in (\"true\", \"false\", \"none\")\n or data.strip().replace(\".\", \"\").isdigit()\n ):\n return ast.literal_eval(data)\n except (ValueError, SyntaxError, TypeError, MemoryError):\n return data\n else:\n return data\n return data\n\n def evaluate_data(self) -> Data:\n \"\"\"Evaluate string values in the data dictionary.\"\"\"\n self.validate_single_data(\"Literal Eval\")\n logger.info(\"evaluating data\")\n return Data(**self.recursive_eval(self.get_data_dict()))\n\n def combine_data(self) -> Data:\n \"\"\"Combine multiple data objects into one.\"\"\"\n logger.info(\"combining data\")\n if not self.data_is_list():\n return self.data[0] if self.data else Data(data={})\n\n data_dicts = [data.model_dump().get(\"data\", data.model_dump()) for data in self.data]\n combined_data: dict[str, Any] = {}\n\n for data_dict in data_dicts:\n for key, value in data_dict.items():\n if key not in combined_data:\n combined_data[key] = value\n elif isinstance(combined_data[key], list):\n if isinstance(value, list):\n combined_data[key].extend(value)\n else:\n combined_data[key].append(value)\n else:\n combined_data[key] = (\n [combined_data[key], value] if not isinstance(value, list) else [combined_data[key], *value]\n )\n\n return Data(**combined_data)\n\n def append_update(self) -> Data:\n \"\"\"Append or update the data with new key-value pairs.\"\"\"\n self.validate_single_data(\"Append or Update\")\n data_filtered = self.get_normalized_data()\n for key, value in self.append_update_data.items():\n data_filtered[key] = value\n return Data(**data_filtered)\n\n def json_path(self) -> Data:\n \"\"\"Extract a value from the data using the selected JQ path.\"\"\"\n try:\n import jq\n except ImportError:\n msg = \"jq is required for Path Selection. Install with: pip install jq\"\n raise ImportError(msg) from None\n\n try:\n if not self.data or not self.selected_key:\n msg = \"Missing input data or selected key.\"\n raise ValueError(msg)\n input_payload = self.data[0].data if isinstance(self.data, list) else self.data.data\n validate_jq_program(self.selected_key)\n compiled = jq.compile(self.selected_key)\n result = compiled.input(input_payload).first()\n if isinstance(result, dict):\n return Data(data=result)\n return Data(data={\"result\": result})\n except (ValueError, TypeError, KeyError) as e:\n self.status = f\"Error: {e!s}\"\n self.log(self.status)\n return Data(data={\"error\": str(e)})\n\n def json_query(self) -> Data:\n \"\"\"Run a JQ expression against the data.\"\"\"\n try:\n import jq\n except ImportError:\n msg = \"jq is required for JQ Expression. Install with: pip install jq\"\n raise ImportError(msg) from None\n\n if not self.query or not self.query.strip():\n msg = \"JSON Query is required and cannot be blank.\"\n raise ValueError(msg)\n raw_data = self.get_data_dict()\n try:\n input_str = json.dumps(raw_data)\n repaired = repair_json(input_str)\n data_json = json.loads(repaired)\n jq_input = data_json[\"data\"] if isinstance(data_json, dict) and \"data\" in data_json else data_json\n validate_jq_program(self.query)\n results = jq.compile(self.query).input(jq_input).all()\n if not results:\n msg = \"No result from JSON query.\"\n raise ValueError(msg)\n result = results[0] if len(results) == 1 else results\n if result is None or result == \"None\":\n msg = \"JSON query returned null/None. Check if the path exists in your data.\"\n raise ValueError(msg)\n if isinstance(result, dict):\n return Data(data=result)\n return Data(data={\"result\": result})\n except (ValueError, TypeError, KeyError, json.JSONDecodeError) as e:\n logger.error(f\"JSON Query failed: {e}\")\n msg = f\"JSON Query error: {e}\"\n raise ValueError(msg) from e\n\n # ==================================================================\n # Table operations\n # ==================================================================\n def _get_primary_dataframe(self) -> DataFrame:\n \"\"\"Get the first DataFrame from input (handles both single and list inputs).\"\"\"\n if isinstance(self.df, list):\n return self.df[0].copy() if self.df else DataFrame()\n return self.df.copy()\n\n def _run_table_operation(self, operation: str) -> DataFrame:\n # Merge and Concatenate use their own inputs, not the primary df.\n if operation == \"Merge\":\n return self.merge_dataframes()\n if operation == \"Concatenate\":\n return self.concatenate_dataframes()\n\n df_copy = self._get_primary_dataframe()\n table_handlers = {\n \"Filter\": self.filter_rows_by_value,\n \"Sort\": self.sort_by_column,\n \"Drop Column\": self.drop_column,\n \"Rename Column\": self.rename_column,\n \"Add Column\": self.add_column,\n \"Select Columns\": self.select_columns,\n \"Head\": self.head,\n \"Tail\": self.tail,\n \"Replace Value\": self.replace_values,\n \"Drop Duplicates\": self.drop_duplicates,\n }\n handler = table_handlers.get(operation)\n if handler is None:\n msg = f\"Unsupported operation: {operation}\"\n logger.error(msg)\n raise ValueError(msg)\n return handler(df_copy)\n\n @staticmethod\n def _comparable_filter_value(column: pd.Series, filter_value: Any) -> Any:\n \"\"\"Return a text input as a number when the column is numeric.\n\n Filter and Replace Value inputs arrive as text, and ``30 == \"30\"`` never matches in pandas.\n A blank input stays text: ``pd.to_numeric(\"\")`` is NaN, which would match missing cells.\n \"\"\"\n if filter_value in (None, \"\"):\n return filter_value\n if pd.api.types.is_numeric_dtype(column) and not pd.api.types.is_bool_dtype(column):\n try:\n return pd.to_numeric(filter_value)\n except (ValueError, TypeError):\n return filter_value\n return filter_value\n\n def filter_rows_by_value(self, df: DataFrame) -> DataFrame:\n column = df[self.column_name]\n filter_value = self.filter_value\n operator = getattr(self, \"filter_operator\", \"equals\")\n\n if operator == \"equals\":\n mask = column == self._comparable_filter_value(column, filter_value)\n elif operator == \"not equals\":\n mask = column != self._comparable_filter_value(column, filter_value)\n elif operator == \"contains\":\n mask = column.astype(str).str.contains(str(filter_value), na=False)\n elif operator == \"not contains\":\n mask = ~column.astype(str).str.contains(str(filter_value), na=False)\n elif operator == \"starts with\":\n mask = column.astype(str).str.startswith(str(filter_value), na=False)\n elif operator == \"ends with\":\n mask = column.astype(str).str.endswith(str(filter_value), na=False)\n elif operator == \"greater than\":\n try:\n numeric_value = pd.to_numeric(filter_value)\n mask = column > numeric_value\n except (ValueError, TypeError):\n mask = column.astype(str) > str(filter_value)\n elif operator == \"less than\":\n try:\n numeric_value = pd.to_numeric(filter_value)\n mask = column < numeric_value\n except (ValueError, TypeError):\n mask = column.astype(str) < str(filter_value)\n else:\n mask = column == self._comparable_filter_value(column, filter_value)\n\n return DataFrame(df[mask])\n\n def sort_by_column(self, df: DataFrame) -> DataFrame:\n return DataFrame(df.sort_values(by=self.column_name, ascending=self.ascending))\n\n def drop_column(self, df: DataFrame) -> DataFrame:\n return DataFrame(df.drop(columns=[self.column_name]))\n\n def rename_column(self, df: DataFrame) -> DataFrame:\n return DataFrame(df.rename(columns={self.column_name: self.new_column_name}))\n\n def add_column(self, df: DataFrame) -> DataFrame:\n df[self.new_column_name] = [self.new_column_value] * len(df)\n return DataFrame(df)\n\n def select_columns(self, df: DataFrame) -> DataFrame:\n columns = [col.strip() for col in self.columns_to_select]\n return DataFrame(df[columns])\n\n def head(self, df: DataFrame) -> DataFrame:\n return DataFrame(df.head(self.num_rows))\n\n def tail(self, df: DataFrame) -> DataFrame:\n return DataFrame(df.tail(self.num_rows))\n\n def replace_values(self, df: DataFrame) -> DataFrame:\n column = df[self.column_name]\n replace_val = self._comparable_filter_value(column, self.replace_value)\n replacement_val = self._comparable_filter_value(column, self.replacement_value)\n try:\n result = column.replace(replace_val, replacement_val)\n except TypeError:\n if not (\n isinstance(column.dtype, pd.api.extensions.ExtensionDtype)\n and pd.api.types.is_integer_dtype(column.dtype)\n ):\n raise\n # Nullable integers reject fractional/text replacements instead of widening like NumPy columns.\n widened = column.astype(\"Float64\" if pd.api.types.is_float(replacement_val) else object)\n # A float cannot represent every Int64 value. Preserve unrelated large integers exactly.\n if not widened.astype(object).equals(column.astype(object)):\n widened = column.astype(object)\n result = widened.mask(column.eq(replace_val).fillna(value=False), replacement_val)\n df[self.column_name] = result\n return DataFrame(df)\n\n def drop_duplicates(self, df: DataFrame) -> DataFrame:\n return DataFrame(df.drop_duplicates(subset=self.column_name))\n\n def concatenate_dataframes(self) -> DataFrame:\n \"\"\"Concatenate multiple DataFrames vertically (stack rows).\"\"\"\n if not isinstance(self.df, list) or len(self.df) == 0:\n return self.df.copy() if self.df is not None else DataFrame()\n\n if len(self.df) == 1:\n return self.df[0].copy()\n\n concatenated = pd.concat(self.df, ignore_index=True)\n return DataFrame(concatenated)\n\n def merge_dataframes(self) -> DataFrame:\n \"\"\"Merge two DataFrames based on a common column (join operation).\"\"\"\n left_df = getattr(self, \"left_dataframe\", None)\n right_df = getattr(self, \"right_dataframe\", None)\n\n if left_df is None:\n return DataFrame()\n if right_df is None:\n return left_df.copy()\n\n df_left = left_df.copy()\n df_right = right_df.copy()\n\n merge_on = getattr(self, \"merge_on_column\", None)\n merge_how = getattr(self, \"merge_how\", \"inner\")\n\n # Track only columns created by this merge, without colliding with input names.\n right_columns = {}\n used_columns = set(df_left.columns) | set(df_right.columns)\n for col in df_left.columns.intersection(df_right.columns):\n if merge_on and col == merge_on:\n continue\n right_col = f\"{col}_right\"\n while right_col in used_columns:\n right_col += \"_right\"\n right_columns[col] = right_col\n used_columns.add(right_col)\n df_right = df_right.rename(columns=right_columns)\n\n if merge_on:\n if merge_on not in df_left.columns:\n msg = f\"Column '{merge_on}' not found in left DataFrame. Available: {list(df_left.columns)}\"\n raise ValueError(msg)\n if merge_on not in df_right.columns:\n msg = f\"Column '{merge_on}' not found in right DataFrame. Available: {list(df_right.columns)}\"\n raise ValueError(msg)\n merged = df_left.merge(df_right, on=merge_on, how=merge_how)\n else:\n merged = df_left.merge(df_right, left_index=True, right_index=True, how=merge_how)\n\n cols_to_drop = []\n for col, right_col in right_columns.items():\n merged[col] = merged[col].combine_first(merged[right_col])\n cols_to_drop.append(right_col)\n\n if cols_to_drop:\n merged = merged.drop(columns=cols_to_drop)\n\n return DataFrame(merged)\n\n # ==================================================================\n # Text operations\n # ==================================================================\n def _run_text_operation(self) -> Any:\n \"\"\"Process text based on the selected operation (Message/Text outputs).\"\"\"\n text = getattr(self, \"text_input\", \"\")\n operation = self._operation_name()\n\n # Allow empty text for Text Join (second input may have content).\n if not text and operation != \"Text Join\":\n return None\n\n text_handlers = {\n \"Case Conversion\": self._case_conversion,\n \"Text Replace\": self._text_replace,\n \"Text Extract\": self._text_extract,\n \"Text Head\": self._text_head,\n \"Text Tail\": self._text_tail,\n \"Text Strip\": self._text_strip,\n \"Text Join\": self._text_join,\n \"Text Clean\": self._text_clean,\n }\n handler = text_handlers.get(operation)\n if handler:\n return handler(text)\n return text\n\n def _word_count_data(self) -> Data:\n \"\"\"Word Count operation result as a Data object.\"\"\"\n result = self._word_count(getattr(self, \"text_input\", \"\") or \"\")\n return Data(data=result)\n\n def _word_count(self, text: str) -> dict[str, Any]:\n \"\"\"Count words, characters, and lines in text.\"\"\"\n result: dict[str, Any] = {}\n text_str = str(text) if text else \"\"\n is_empty = not text_str or not text_str.strip()\n\n if getattr(self, \"count_words\", True):\n if is_empty:\n result[\"word_count\"] = 0\n result[\"unique_words\"] = 0\n else:\n words = text_str.split()\n result[\"word_count\"] = len(words)\n result[\"unique_words\"] = len(set(words))\n\n if getattr(self, \"count_characters\", True):\n if is_empty:\n result[\"character_count\"] = 0\n result[\"character_count_no_spaces\"] = 0\n else:\n result[\"character_count\"] = len(text_str)\n result[\"character_count_no_spaces\"] = len(text_str.replace(\" \", \"\"))\n\n if getattr(self, \"count_lines\", True):\n if is_empty:\n result[\"line_count\"] = 0\n result[\"non_empty_lines\"] = 0\n else:\n lines = text_str.split(\"\\n\")\n result[\"line_count\"] = len(lines)\n result[\"non_empty_lines\"] = len([line for line in lines if line.strip()])\n\n return result\n\n def _text_to_dataframe(self, text: str) -> DataFrame:\n \"\"\"Convert markdown-style table text to a DataFrame.\"\"\"\n lines = [line.strip() for line in text.strip().split(\"\\n\") if line.strip()]\n if not lines:\n return DataFrame(pd.DataFrame())\n\n separator = getattr(self, \"table_separator\", \"|\")\n has_header = getattr(self, \"has_header\", True)\n\n rows = self._parse_table_rows(lines, separator, has_header=has_header)\n if not rows:\n return DataFrame(pd.DataFrame())\n\n df = self._create_dataframe(rows, has_header=has_header)\n self._convert_numeric_columns(df)\n self.log(f\"Converted text to DataFrame: {len(df)} rows, {len(df.columns)} columns\")\n return DataFrame(df)\n\n def _parse_table_rows(self, lines: list[str], separator: str, *, has_header: bool = True) -> list[list[str]]:\n rows = []\n for index, line in enumerate(lines):\n cleaned_line = line.strip(separator)\n cells = [cell.strip() for cell in cleaned_line.split(separator)]\n # Skip the markdown delimiter row under the header instead of reading it as data.\n if has_header and index == 1 and all(MARKDOWN_DELIMITER_CELL.fullmatch(cell) for cell in cells):\n continue\n rows.append(cells)\n return rows\n\n def _create_dataframe(self, rows: list[list[str]], *, has_header: bool) -> pd.DataFrame:\n if has_header and rows:\n header = rows[0]\n data_rows = rows[1:]\n header_col_count = len(header)\n for i, row in enumerate(data_rows):\n row_col_count = len(row)\n if row_col_count != header_col_count:\n msg = (\n f\"Header mismatch: {header_col_count} column(s) in header vs \"\n f\"{row_col_count} column(s) in data row {i + 1}. \"\n \"Please ensure the header has the same number of columns as your data.\"\n )\n raise ValueError(msg)\n return pd.DataFrame(data_rows, columns=header)\n\n max_cols = max(len(row) for row in rows) if rows else 0\n columns = [f\"col_{i}\" for i in range(max_cols)]\n return pd.DataFrame(rows, columns=columns)\n\n def _convert_numeric_columns(self, df: pd.DataFrame) -> None:\n for col in df.columns:\n with contextlib.suppress(ValueError, TypeError):\n df[col] = pd.to_numeric(df[col])\n\n def _case_conversion(self, text: str) -> str:\n case_type = getattr(self, \"case_type\", \"lowercase\")\n converter = CASE_CONVERTERS.get(case_type)\n return converter(text) if converter else text\n\n def _text_replace(self, text: str) -> str:\n search_pattern = getattr(self, \"search_pattern\", \"\")\n if not search_pattern:\n return text\n replacement_text = getattr(self, \"replacement_text\", \"\")\n use_regex = getattr(self, \"use_regex\", False)\n if use_regex:\n try:\n return re.sub(search_pattern, replacement_text, text)\n except re.error as e:\n self.log(f\"Invalid regex pattern: {e}\")\n return text\n return text.replace(search_pattern, replacement_text)\n\n def _text_extract(self, text: str) -> list[str]:\n extract_pattern = getattr(self, \"extract_pattern\", \"\")\n if not extract_pattern:\n return []\n max_matches = getattr(self, \"max_matches\", 10)\n try:\n matches = re.findall(extract_pattern, text)\n except re.error as e:\n msg = f\"Invalid regex pattern '{extract_pattern}': {e}\"\n raise ValueError(msg) from e\n return matches[:max_matches] if max_matches > 0 else matches\n\n def _text_head(self, text: str) -> str:\n head_characters = getattr(self, \"head_characters\", 100)\n if head_characters < 0:\n msg = f\"Characters from Start must be a non-negative integer, got {head_characters}\"\n raise ValueError(msg)\n if head_characters == 0:\n return \"\"\n return text[:head_characters]\n\n def _text_tail(self, text: str) -> str:\n tail_characters = getattr(self, \"tail_characters\", 100)\n if tail_characters < 0:\n msg = f\"Characters from End must be a non-negative integer, got {tail_characters}\"\n raise ValueError(msg)\n if tail_characters == 0:\n return \"\"\n return text[-tail_characters:]\n\n def _text_strip(self, text: str) -> str:\n strip_mode = getattr(self, \"strip_mode\", \"both\")\n strip_characters = getattr(self, \"strip_characters\", \"\")\n text_str = str(text) if text else \"\"\n chars_to_strip = strip_characters if strip_characters else None\n if strip_mode == \"left\":\n return text_str.lstrip(chars_to_strip)\n if strip_mode == \"right\":\n return text_str.rstrip(chars_to_strip)\n return text_str.strip(chars_to_strip)\n\n def _text_join(self, text: str) -> str:\n text_input_2 = getattr(self, \"text_input_2\", \"\")\n text1 = str(text) if text else \"\"\n text2 = str(text_input_2) if text_input_2 else \"\"\n if text1 and text2:\n return f\"{text1}\\n{text2}\"\n return text1 or text2\n\n def _text_clean(self, text: str) -> str:\n result = text\n if getattr(self, \"remove_extra_spaces\", True):\n # Collapse runs of horizontal whitespace but preserve newlines so\n # that remove_empty_lines stays effective when both are enabled.\n result = re.sub(r\"[^\\S\\n]+\", \" \", result)\n if getattr(self, \"remove_special_chars\", False):\n result = re.sub(r\"[^\\w\\s]\", \"\", result)\n if getattr(self, \"remove_empty_lines\", False):\n lines = [line for line in result.split(\"\\n\") if line.strip()]\n result = \"\\n\".join(lines)\n return result\n\n def _format_result_as_text(self, result: Any) -> str:\n if result is None:\n return \"\"\n if isinstance(result, list):\n return \"\\n\".join(str(item) for item in result)\n return str(result)\n"
},
"column_name": {
"_input_type": "StrInput",
@@ -4015,13 +4013,9 @@
},
"dragging": false,
"id": "Operations-jsRu6",
- "measured": {
- "height": 52,
- "width": 192
- },
"position": {
- "x": 1393.4815933361858,
- "y": 1620.5940492140244
+ "x": 1416.6303034894079,
+ "y": 1626.38122675233
},
"selected": false,
"type": "genericNode"
@@ -4091,10 +4085,10 @@
],
"frozen": false,
"icon": "wand-sparkles",
- "last_updated": "2026-10-27T20:15:57.690Z",
+ "last_updated": "2026-10-29T18:15:01.221Z",
"legacy": false,
"metadata": {
- "code_hash": "f15ba610cfd0",
+ "code_hash": "6164f967d510",
"dependencies": {
"dependencies": [
{
@@ -4107,7 +4101,7 @@
},
{
"name": "lfx",
- "version": "1.12.3"
+ "version": "1.12.8"
},
{
"name": "jq",
@@ -4188,7 +4182,7 @@
"value": "72c3d17c-2dac-4a73-b48a-6518473d7830"
},
"_frontend_node_folder_id": {
- "value": "f3f8bf74-7a73-4ab3-9769-0d8a4ebbaec9"
+ "value": "afa57272-6d34-4d1c-bf31-27ffad110b3a"
},
"_type": "Component",
"append_update_data": {
@@ -4283,7 +4277,7 @@
"show": true,
"title_case": false,
"type": "code",
- "value": "\"\"\"Unified Operations component.\n\nBrings together the previously separate JSON, Table, and Text operation\ncomponents into a single component. An \"Input Type\" selector (Text / JSON /\nTable) drives everything: it filters the \"Operation\" picker to the operations\nthat apply to that type, reveals the matching input (Text / JSON / Table) and\nits operation-specific fields, and advertises the appropriate output type.\n\nThe three original components (JSON Operations, Table Operations, Text\nOperations) remain available as legacy components for backward compatibility\nwith existing flows.\n\"\"\"\n\nimport ast\nimport contextlib\nimport json\nimport re\nfrom typing import TYPE_CHECKING, Any\n\nimport pandas as pd\nfrom json_repair import repair_json\n\nfrom lfx.custom import Component\nfrom lfx.field_typing import RangeSpec\nfrom lfx.inputs import DictInput, SortableListInput, TabInput\nfrom lfx.io import (\n BoolInput,\n DataFrameInput,\n DataInput,\n DropdownInput,\n IntInput,\n MessageTextInput,\n MultilineInput,\n Output,\n StrInput,\n)\nfrom lfx.log.logger import logger\nfrom lfx.schema import Data\nfrom lfx.schema.dataframe import DataFrame\nfrom lfx.schema.dotdict import dotdict\nfrom lfx.schema.message import Message\nfrom lfx.utils.jq_security import validate_jq_program\n\nif TYPE_CHECKING:\n from collections.abc import Callable\n\n# The \"Input Type\" selector tabs. Each value maps a Langflow data type to the\n# operations, input, and output that belong to it.\nINPUT_TYPES = [\"Text\", \"JSON\", \"Table\"]\n\n# Operations grouped by input type, in display order, each with the icon shown\n# in the Operation picker. This is the single source of truth for the picker;\n# update_build_config swaps the picker's options to the selected type's list.\nOPERATIONS_BY_TYPE: dict[str, list[dict[str, str]]] = {\n \"Text\": [\n {\"name\": \"Word Count\", \"icon\": \"hash\"},\n {\"name\": \"Case Conversion\", \"icon\": \"type\"},\n {\"name\": \"Text Replace\", \"icon\": \"replace\"},\n {\"name\": \"Text Extract\", \"icon\": \"search\"},\n {\"name\": \"Text Head\", \"icon\": \"chevron-left\"},\n {\"name\": \"Text Tail\", \"icon\": \"chevron-right\"},\n {\"name\": \"Text Strip\", \"icon\": \"minus\"},\n {\"name\": \"Text Join\", \"icon\": \"link\"},\n {\"name\": \"Text Clean\", \"icon\": \"sparkles\"},\n {\"name\": \"Text to DataFrame\", \"icon\": \"table\"},\n ],\n \"JSON\": [\n {\"name\": \"Select Keys\", \"icon\": \"lasso-select\"},\n {\"name\": \"Literal Eval\", \"icon\": \"braces\"},\n {\"name\": \"Combine\", \"icon\": \"merge\"},\n {\"name\": \"Append or Update\", \"icon\": \"circle-plus\"},\n {\"name\": \"Remove Keys\", \"icon\": \"eraser\"},\n {\"name\": \"Rename Keys\", \"icon\": \"pencil-line\"},\n {\"name\": \"Path Selection\", \"icon\": \"mouse-pointer\"},\n {\"name\": \"JQ Expression\", \"icon\": \"terminal\"},\n ],\n \"Table\": [\n {\"name\": \"Add Column\", \"icon\": \"plus\"},\n {\"name\": \"Concatenate\", \"icon\": \"combine\"},\n {\"name\": \"Drop Column\", \"icon\": \"minus\"},\n {\"name\": \"Filter\", \"icon\": \"filter\"},\n {\"name\": \"Head\", \"icon\": \"arrow-up\"},\n {\"name\": \"Merge\", \"icon\": \"merge\"},\n {\"name\": \"Rename Column\", \"icon\": \"pencil\"},\n {\"name\": \"Replace Value\", \"icon\": \"replace\"},\n {\"name\": \"Select Columns\", \"icon\": \"columns\"},\n {\"name\": \"Sort\", \"icon\": \"arrow-up-down\"},\n {\"name\": \"Tail\", \"icon\": \"arrow-down\"},\n {\"name\": \"Drop Duplicates\", \"icon\": \"copy-x\"},\n ],\n}\n\n# Operation-name sets derived from the picker, used for dispatch and output\n# routing. Keeping them derived from OPERATIONS_BY_TYPE avoids any drift.\nJSON_OPERATIONS = {op[\"name\"] for op in OPERATIONS_BY_TYPE[\"JSON\"]}\nTABLE_OPERATIONS = {op[\"name\"] for op in OPERATIONS_BY_TYPE[\"Table\"]}\nTEXT_OPERATIONS = {op[\"name\"] for op in OPERATIONS_BY_TYPE[\"Text\"]}\n\n# Each input type maps to its main input field and its default output. \"Text\"\n# normally outputs a Message; \"JSON\" a Data; \"Table\" a DataFrame. A few text\n# operations override this (Word Count -> Data, Text to DataFrame -> DataFrame).\nINPUT_TYPE_TO_MAIN_INPUT = {\"Text\": \"text_input\", \"JSON\": \"data\", \"Table\": \"df\"}\n\n# Case conversions for the Text \"Case Conversion\" operation.\nCASE_CONVERTERS: dict[str, Any] = {\n \"uppercase\": str.upper,\n \"lowercase\": str.lower,\n \"title\": str.title,\n \"capitalize\": str.capitalize,\n \"swapcase\": str.swapcase,\n}\n\n\nclass OperationsComponent(Component):\n display_name = \"Data Operations\"\n description = \"Perform operations on Text, JSON, and Tables from a single component.\"\n documentation: str = \"https://docs.langflow.org/components-processing#operations\"\n icon = \"wand-sparkles\"\n name = \"Operations\"\n metadata = {\n \"keywords\": [\n \"operations\",\n \"data operations\",\n \"json\",\n \"json operations\",\n \"table\",\n \"table operations\",\n \"dataframe\",\n \"dataframe operations\",\n \"text\",\n \"text operations\",\n \"select keys\",\n \"literal eval\",\n \"combine\",\n \"append or update\",\n \"remove keys\",\n \"rename keys\",\n \"path selection\",\n \"jq expression\",\n \"parse json\",\n \"add column\",\n \"concatenate\",\n \"drop column\",\n \"filter\",\n \"head\",\n \"merge\",\n \"rename column\",\n \"replace value\",\n \"select columns\",\n \"sort\",\n \"tail\",\n \"drop duplicates\",\n \"word count\",\n \"case conversion\",\n \"text replace\",\n \"text extract\",\n \"text join\",\n \"text clean\",\n \"text to dataframe\",\n \"data manipulation\",\n \"data transformation\",\n ],\n }\n\n # Operation -> operation-specific input fields to reveal when selected.\n OPERATION_FIELDS: dict[str, list[str]] = {\n # JSON\n \"Select Keys\": [\"select_keys_input\"],\n \"Literal Eval\": [],\n \"Combine\": [],\n \"Append or Update\": [\"append_update_data\"],\n \"Remove Keys\": [\"remove_keys_input\"],\n \"Rename Keys\": [\"rename_keys_input\"],\n \"Path Selection\": [\"mapped_json_display\", \"selected_key\"],\n \"JQ Expression\": [\"query\"],\n # Table\n \"Add Column\": [\"new_column_name\", \"new_column_value\"],\n \"Concatenate\": [],\n \"Drop Column\": [\"column_name\"],\n \"Filter\": [\"column_name\", \"filter_value\", \"filter_operator\"],\n \"Head\": [\"num_rows\"],\n \"Merge\": [\"left_dataframe\", \"right_dataframe\", \"merge_on_column\", \"merge_how\"],\n \"Rename Column\": [\"column_name\", \"new_column_name\"],\n \"Replace Value\": [\"column_name\", \"replace_value\", \"replacement_value\"],\n \"Select Columns\": [\"columns_to_select\"],\n \"Sort\": [\"column_name\", \"ascending\"],\n \"Tail\": [\"num_rows\"],\n \"Drop Duplicates\": [\"column_name\"],\n # Text\n \"Word Count\": [\"count_words\", \"count_characters\", \"count_lines\"],\n \"Case Conversion\": [\"case_type\"],\n \"Text Replace\": [\"search_pattern\", \"replacement_text\", \"use_regex\"],\n \"Text Extract\": [\"extract_pattern\", \"max_matches\"],\n \"Text Head\": [\"head_characters\"],\n \"Text Tail\": [\"tail_characters\"],\n \"Text Strip\": [\"strip_mode\", \"strip_characters\"],\n \"Text Join\": [\"text_input_2\"],\n \"Text Clean\": [\"remove_extra_spaces\", \"remove_special_chars\", \"remove_empty_lines\"],\n \"Text to DataFrame\": [\"table_separator\", \"has_header\"],\n }\n\n # The three main inputs (one per data type). They are never treated as\n # operation-specific fields; the input-type selector toggles them.\n MAIN_INPUTS = (\"text_input\", \"data\", \"df\")\n\n # Every operation-specific field (union of all the lists above), used to\n # hide and reset fields whenever the input type or operation changes.\n ALL_OPERATION_FIELDS: list[str] = [\n # JSON\n \"select_keys_input\",\n \"append_update_data\",\n \"remove_keys_input\",\n \"rename_keys_input\",\n \"mapped_json_display\",\n \"selected_key\",\n \"query\",\n # Table\n \"column_name\",\n \"filter_value\",\n \"filter_operator\",\n \"ascending\",\n \"new_column_name\",\n \"new_column_value\",\n \"columns_to_select\",\n \"num_rows\",\n \"replace_value\",\n \"replacement_value\",\n \"left_dataframe\",\n \"right_dataframe\",\n \"merge_on_column\",\n \"merge_how\",\n # Text\n \"table_separator\",\n \"has_header\",\n \"count_words\",\n \"count_characters\",\n \"count_lines\",\n \"case_type\",\n \"use_regex\",\n \"search_pattern\",\n \"replacement_text\",\n \"extract_pattern\",\n \"max_matches\",\n \"head_characters\",\n \"tail_characters\",\n \"strip_mode\",\n \"strip_characters\",\n \"text_input_2\",\n \"remove_extra_spaces\",\n \"remove_special_chars\",\n \"remove_empty_lines\",\n ]\n\n # Defaults applied to the JSON operation fields when the operation changes,\n # mirroring the JSON Operations component's reset behavior.\n OPERATION_FIELD_DEFAULTS: dict[str, Any] = {\n \"select_keys_input\": [],\n \"append_update_data\": {\"key\": \"value\"},\n \"remove_keys_input\": [],\n \"rename_keys_input\": {\"old_key\": \"new_key\"},\n \"mapped_json_display\": \"\",\n \"selected_key\": None,\n \"query\": \"\",\n }\n\n inputs = [\n # --- Input type selector: drives operations, input, and output ---\n TabInput(\n name=\"input_type\",\n display_name=\"Input Type\",\n options=INPUT_TYPES,\n value=\"Text\",\n info=\"Select the type of input to operate on.\",\n real_time_refresh=True,\n ),\n # --- Main inputs: one per data type, shown contextually ---\n MultilineInput(\n name=\"text_input\",\n display_name=\"Text\",\n info=\"The input text to process.\",\n show=True,\n ),\n DataInput(\n name=\"data\",\n display_name=\"JSON\",\n info=\"The JSON / Data object to operate on.\",\n is_list=True,\n show=False,\n ),\n DataFrameInput(\n name=\"df\",\n display_name=\"Table\",\n info=\"The input Table to operate on. Connect multiple Tables for merge or concatenate operations.\",\n is_list=True,\n show=False,\n ),\n # --- Operation picker (options are filtered by Input Type) ---\n SortableListInput(\n name=\"operation\",\n display_name=\"Operation\",\n placeholder=\"Select Operation\",\n info=\"Select the operation to perform. The matching fields and output appear once you choose one.\",\n options=OPERATIONS_BY_TYPE[\"Text\"],\n real_time_refresh=True,\n limit=1,\n ),\n # --- JSON operation fields ---\n MessageTextInput(\n name=\"select_keys_input\",\n display_name=\"Select Keys\",\n info=\"List of keys to select from the data. Only top-level keys can be selected.\",\n show=False,\n is_list=True,\n value=[],\n ),\n DictInput(\n name=\"append_update_data\",\n display_name=\"Append or Update\",\n info=\"Data to append or update the existing data with. Only top-level keys are checked.\",\n show=False,\n value={\"key\": \"value\"},\n is_list=True,\n ),\n MessageTextInput(\n name=\"remove_keys_input\",\n display_name=\"Remove Keys\",\n info=\"List of keys to remove from the data.\",\n show=False,\n is_list=True,\n value=[],\n ),\n DictInput(\n name=\"rename_keys_input\",\n display_name=\"Rename Keys\",\n info=\"List of keys to rename in the data.\",\n show=False,\n is_list=True,\n value={\"old_key\": \"new_key\"},\n ),\n MultilineInput(\n name=\"mapped_json_display\",\n display_name=\"JSON to Map\",\n info=\"Paste or preview your JSON here to explore its structure and select a path for extraction.\",\n required=False,\n refresh_button=True,\n real_time_refresh=True,\n placeholder=\"Add a JSON example.\",\n show=False,\n ),\n DropdownInput(\n name=\"selected_key\",\n display_name=\"Select Path\",\n options=[],\n required=False,\n dynamic=True,\n show=False,\n value=None,\n ),\n MessageTextInput(\n name=\"query\",\n display_name=\"JQ Expression\",\n info=\"JSON Query to filter the data. Used by Path Selection and JQ Expression operations.\",\n placeholder=\"e.g., .properties.id\",\n show=False,\n ),\n # --- Table operation fields ---\n StrInput(\n name=\"column_name\",\n display_name=\"Column Name\",\n info=\"The column name to use for the operation.\",\n dynamic=True,\n show=False,\n ),\n MessageTextInput(\n name=\"filter_value\",\n display_name=\"Filter Value\",\n info=\"The value to filter rows by.\",\n dynamic=True,\n show=False,\n ),\n DropdownInput(\n name=\"filter_operator\",\n display_name=\"Filter Operator\",\n options=[\n \"equals\",\n \"not equals\",\n \"contains\",\n \"not contains\",\n \"starts with\",\n \"ends with\",\n \"greater than\",\n \"less than\",\n ],\n value=\"equals\",\n info=\"The operator to apply for filtering rows.\",\n advanced=False,\n dynamic=True,\n show=False,\n ),\n BoolInput(\n name=\"ascending\",\n display_name=\"Sort Ascending\",\n info=\"Whether to sort in ascending order.\",\n dynamic=True,\n show=False,\n value=True,\n ),\n StrInput(\n name=\"new_column_name\",\n display_name=\"New Column Name\",\n info=\"The new column name when renaming or adding a column.\",\n dynamic=True,\n show=False,\n ),\n MessageTextInput(\n name=\"new_column_value\",\n display_name=\"New Column Value\",\n info=\"The value to populate the new column with.\",\n dynamic=True,\n show=False,\n ),\n StrInput(\n name=\"columns_to_select\",\n display_name=\"Columns to Select\",\n dynamic=True,\n is_list=True,\n show=False,\n ),\n IntInput(\n name=\"num_rows\",\n display_name=\"Number of Rows\",\n info=\"Number of rows to return (for head/tail).\",\n dynamic=True,\n show=False,\n value=5,\n ),\n MessageTextInput(\n name=\"replace_value\",\n display_name=\"Value to Replace\",\n info=\"The value to replace in the column.\",\n dynamic=True,\n show=False,\n ),\n MessageTextInput(\n name=\"replacement_value\",\n display_name=\"Replacement Value\",\n info=\"The value to replace with.\",\n dynamic=True,\n show=False,\n ),\n DataFrameInput(\n name=\"left_dataframe\",\n display_name=\"Left Table\",\n info=\"The left (primary) Table for merge operations. \"\n \"In a left merge, all rows from this table are preserved.\",\n dynamic=True,\n show=False,\n ),\n DataFrameInput(\n name=\"right_dataframe\",\n display_name=\"Right Table\",\n info=\"The right (secondary) Table for merge operations. \"\n \"In a right merge, all rows from this table are preserved.\",\n dynamic=True,\n show=False,\n ),\n StrInput(\n name=\"merge_on_column\",\n display_name=\"Merge On Column\",\n info=\"The column name to merge Tables on. Must exist in both Tables.\",\n dynamic=True,\n show=False,\n ),\n DropdownInput(\n name=\"merge_how\",\n display_name=\"Merge Type\",\n options=[\"inner\", \"outer\", \"left\", \"right\"],\n value=\"inner\",\n info=\"Type of merge: inner (intersection), outer (union), left, or right.\",\n dynamic=True,\n show=False,\n ),\n # --- Text operation fields ---\n StrInput(\n name=\"table_separator\",\n display_name=\"Table Separator\",\n info=\"Separator used in the table (default: '|').\",\n value=\"|\",\n dynamic=True,\n show=False,\n ),\n BoolInput(\n name=\"has_header\",\n display_name=\"Has Header\",\n info=\"Whether the table has a header row.\",\n value=True,\n dynamic=True,\n advanced=True,\n show=False,\n ),\n BoolInput(\n name=\"count_words\",\n display_name=\"Count Words\",\n info=\"Include word count in analysis.\",\n value=True,\n dynamic=True,\n advanced=True,\n show=False,\n ),\n BoolInput(\n name=\"count_characters\",\n display_name=\"Count Characters\",\n info=\"Include character count in analysis.\",\n value=True,\n dynamic=True,\n advanced=True,\n show=False,\n ),\n BoolInput(\n name=\"count_lines\",\n display_name=\"Count Lines\",\n info=\"Include line count in analysis.\",\n value=True,\n dynamic=True,\n advanced=True,\n show=False,\n ),\n DropdownInput(\n name=\"case_type\",\n display_name=\"Case Type\",\n options=[\"uppercase\", \"lowercase\", \"title\", \"capitalize\", \"swapcase\"],\n value=\"lowercase\",\n info=\"Type of case conversion to apply.\",\n dynamic=True,\n show=False,\n ),\n BoolInput(\n name=\"use_regex\",\n display_name=\"Use Regex\",\n info=\"Whether to treat search pattern as regex.\",\n value=False,\n dynamic=True,\n show=False,\n ),\n StrInput(\n name=\"search_pattern\",\n display_name=\"Search Pattern\",\n info=\"Text pattern to search for (supports regex).\",\n dynamic=True,\n show=False,\n ),\n StrInput(\n name=\"replacement_text\",\n display_name=\"Replacement Text\",\n info=\"Text to replace the search pattern with.\",\n dynamic=True,\n show=False,\n ),\n StrInput(\n name=\"extract_pattern\",\n display_name=\"Extract Pattern\",\n info=\"Regex pattern to extract from text.\",\n dynamic=True,\n show=False,\n ),\n IntInput(\n name=\"max_matches\",\n display_name=\"Max Matches\",\n info=\"Maximum number of matches to extract.\",\n value=10,\n dynamic=True,\n show=False,\n ),\n IntInput(\n name=\"head_characters\",\n display_name=\"Characters from Start\",\n info=\"Number of characters to extract from the beginning of text. Must be non-negative.\",\n value=100,\n dynamic=True,\n show=False,\n range_spec=RangeSpec(min=0, max=1000000, step=1, step_type=\"int\"),\n ),\n IntInput(\n name=\"tail_characters\",\n display_name=\"Characters from End\",\n info=\"Number of characters to extract from the end of text. Must be non-negative.\",\n value=100,\n dynamic=True,\n show=False,\n range_spec=RangeSpec(min=0, max=1000000, step=1, step_type=\"int\"),\n ),\n DropdownInput(\n name=\"strip_mode\",\n display_name=\"Strip Mode\",\n options=[\"both\", \"left\", \"right\"],\n value=\"both\",\n info=\"Which sides to strip whitespace from.\",\n dynamic=True,\n show=False,\n ),\n StrInput(\n name=\"strip_characters\",\n display_name=\"Characters to Strip\",\n info=\"Specific characters to remove (leave empty for whitespace).\",\n value=\"\",\n dynamic=True,\n show=False,\n ),\n MultilineInput(\n name=\"text_input_2\",\n display_name=\"Second Text Input\",\n info=\"Second text to join with the first text.\",\n dynamic=True,\n show=False,\n ),\n BoolInput(\n name=\"remove_extra_spaces\",\n display_name=\"Remove Extra Spaces\",\n info=\"Remove multiple consecutive spaces.\",\n value=True,\n dynamic=True,\n show=False,\n ),\n BoolInput(\n name=\"remove_special_chars\",\n display_name=\"Remove Special Characters\",\n info=\"Remove special characters except alphanumeric and spaces.\",\n value=False,\n dynamic=True,\n show=False,\n ),\n BoolInput(\n name=\"remove_empty_lines\",\n display_name=\"Remove Empty Lines\",\n info=\"Remove empty lines from text.\",\n value=False,\n dynamic=True,\n show=False,\n ),\n ]\n\n # Default output matches the default Input Type (\"Text\" -> Message).\n # update_outputs / update_frontend_node narrow it to the selected type and\n # operation.\n outputs = [Output(display_name=\"Message\", name=\"message_output\", method=\"as_message\")]\n\n # ------------------------------------------------------------------\n # Operation routing helpers\n # ------------------------------------------------------------------\n @staticmethod\n def _extract_operation_name(field_value: Any) -> str:\n \"\"\"Extract the operation name from a SortableListInput value.\"\"\"\n if isinstance(field_value, list) and len(field_value) > 0 and isinstance(field_value[0], dict):\n return field_value[0].get(\"name\", \"\")\n if isinstance(field_value, str):\n return field_value\n return \"\"\n\n def _operation_name(self) -> str:\n \"\"\"Get the currently selected operation name.\"\"\"\n return self._extract_operation_name(getattr(self, \"operation\", []))\n\n @staticmethod\n def _default_output_for_type(input_type: str) -> Output:\n \"\"\"Return the output advertised for an input type when no operation is selected yet.\"\"\"\n if input_type == \"JSON\":\n return Output(display_name=\"JSON\", name=\"data_output\", method=\"as_data\")\n if input_type == \"Table\":\n return Output(display_name=\"Table\", name=\"dataframe_output\", method=\"as_dataframe\")\n return Output(display_name=\"Message\", name=\"message_output\", method=\"as_message\")\n\n # ------------------------------------------------------------------\n # Dynamic UI\n # ------------------------------------------------------------------\n def _reset_operation_fields(self, build_config: dotdict) -> None:\n \"\"\"Hide every operation-specific field and restore its default value.\"\"\"\n for field in self.ALL_OPERATION_FIELDS:\n if field in build_config:\n build_config[field][\"show\"] = False\n if field in self.OPERATION_FIELD_DEFAULTS:\n build_config[field][\"value\"] = self.OPERATION_FIELD_DEFAULTS[field]\n\n def _show_main_input(self, build_config: dotdict, input_type: str, operation: str) -> None:\n \"\"\"Show only the main input that matches the input type; hide the others.\"\"\"\n for inp in self.MAIN_INPUTS:\n if inp in build_config:\n build_config[inp][\"show\"] = False\n build_config[inp][\"required\"] = False\n\n main_input = INPUT_TYPE_TO_MAIN_INPUT.get(input_type)\n if main_input and main_input in build_config:\n build_config[main_input][\"show\"] = True\n build_config[main_input][\"required\"] = True\n # The JSON \"Combine\" operation consumes a list of Data objects.\n if main_input == \"data\":\n build_config[\"data\"][\"is_list\"] = operation == \"Combine\"\n\n def update_build_config(self, build_config: dotdict, field_value: Any, field_name: str | None = None) -> dotdict:\n # Path Selection: refresh the available JSON paths from the pasted JSON.\n if field_name == \"mapped_json_display\":\n try:\n parsed_json = json.loads(field_value)\n keys = self.extract_all_paths(parsed_json)\n build_config[\"selected_key\"][\"options\"] = keys\n build_config[\"selected_key\"][\"show\"] = True\n except (json.JSONDecodeError, TypeError, ValueError) as e:\n logger.error(f\"Error parsing mapped JSON: {e}\")\n build_config[\"selected_key\"][\"show\"] = False\n return build_config\n\n # Input type changed: swap the operation list, clear the selection, and\n # show only the matching input. No operation-specific fields are shown\n # until an operation is picked.\n if field_name == \"input_type\":\n input_type = field_value if field_value in OPERATIONS_BY_TYPE else \"Text\"\n build_config[\"operation\"][\"options\"] = OPERATIONS_BY_TYPE[input_type]\n build_config[\"operation\"][\"value\"] = []\n self._reset_operation_fields(build_config)\n self._show_main_input(build_config, input_type, operation=\"\")\n return build_config\n\n # Operation changed: reset fields, show the input for the current type,\n # then reveal the operation-specific fields.\n if field_name == \"operation\":\n operation = self._extract_operation_name(field_value)\n self._reset_operation_fields(build_config)\n\n input_type = build_config.get(\"input_type\", {}).get(\"value\", \"Text\")\n self._show_main_input(build_config, input_type, operation)\n\n for field in self.OPERATION_FIELDS.get(operation, []):\n if field in build_config:\n build_config[field][\"show\"] = True\n\n return build_config\n\n return build_config\n\n def update_outputs(self, frontend_node: dict, field_name: str, field_value: Any) -> dict:\n \"\"\"Create the output(s) appropriate to the selected input type and operation.\"\"\"\n if field_name == \"input_type\":\n # Switching type clears the operation; advertise the type's default.\n input_type = field_value if field_value in OPERATIONS_BY_TYPE else \"Text\"\n frontend_node[\"outputs\"] = [self._default_output_for_type(input_type)]\n return frontend_node\n\n template = frontend_node.get(\"template\", {})\n input_type = template.get(\"input_type\", {}).get(\"value\", \"Text\")\n\n if field_name == \"operation\":\n operation = self._extract_operation_name(field_value)\n else:\n # Any other refresh (e.g. Path Selection's \"JSON to Map\" field)\n # reaches here on a freshly rebuilt node whose outputs were reset\n # to the class default (Message). Re-derive the output from the\n # saved operation so the refresh doesn't swap the real output type.\n operation = self._extract_operation_name(template.get(\"operation\", {}).get(\"value\", []))\n\n if not operation:\n # No operation selected: fall back to the input type's default output.\n frontend_node[\"outputs\"] = [self._default_output_for_type(input_type)]\n return frontend_node\n\n frontend_node[\"outputs\"] = []\n if operation in JSON_OPERATIONS or operation == \"Word Count\":\n frontend_node[\"outputs\"].append(Output(display_name=\"JSON\", name=\"data_output\", method=\"as_data\"))\n elif operation in TABLE_OPERATIONS or operation == \"Text to DataFrame\":\n frontend_node[\"outputs\"].append(\n Output(display_name=\"Table\", name=\"dataframe_output\", method=\"as_dataframe\")\n )\n elif operation == \"Text Join\":\n frontend_node[\"outputs\"].append(Output(display_name=\"Text\", name=\"text_output\", method=\"as_text\"))\n frontend_node[\"outputs\"].append(Output(display_name=\"Message\", name=\"message_output\", method=\"as_message\"))\n else:\n frontend_node[\"outputs\"].append(Output(display_name=\"Message\", name=\"message_output\", method=\"as_message\"))\n\n return frontend_node\n\n async def update_frontend_node(self, new_frontend_node: dict, current_frontend_node: dict) -> dict:\n \"\"\"Keep the operation options and outputs in sync with the saved input type on load.\"\"\"\n await super().update_frontend_node(new_frontend_node, current_frontend_node)\n\n template = new_frontend_node.get(\"template\", {})\n input_type = template.get(\"input_type\", {}).get(\"value\", \"Text\")\n if input_type not in OPERATIONS_BY_TYPE:\n input_type = \"Text\"\n\n # Filter the operation picker to the saved input type.\n if \"operation\" in template:\n template[\"operation\"][\"options\"] = OPERATIONS_BY_TYPE[input_type]\n\n # Re-derive the outputs from the saved input type + operation.\n operation_value = template.get(\"operation\", {}).get(\"value\", [])\n if self._extract_operation_name(operation_value):\n self.update_outputs(new_frontend_node, \"operation\", operation_value)\n else:\n self.update_outputs(new_frontend_node, \"input_type\", input_type)\n\n return new_frontend_node\n\n # ==================================================================\n # Output methods (referenced by update_outputs)\n # ==================================================================\n def as_data(self) -> Data:\n \"\"\"JSON-typed output: JSON operations and Word Count.\"\"\"\n operation = self._operation_name()\n if operation in JSON_OPERATIONS:\n handler = self._json_handlers().get(operation)\n if handler:\n try:\n return handler()\n except Exception as e:\n logger.error(f\"Error executing {operation}: {e!s}\")\n raise\n if operation == \"Word Count\":\n return self._word_count_data()\n return Data(data={})\n\n def as_dataframe(self) -> DataFrame:\n \"\"\"Table-typed output: Table operations and Text to DataFrame.\"\"\"\n operation = self._operation_name()\n if operation in TABLE_OPERATIONS:\n return self._run_table_operation(operation)\n if operation == \"Text to DataFrame\":\n return self._text_to_dataframe(getattr(self, \"text_input\", \"\") or \"\")\n return DataFrame(pd.DataFrame())\n\n def as_message(self) -> Message:\n \"\"\"Message-typed output: generic text operations (and Text Join).\"\"\"\n return Message(text=self._format_result_as_text(self._run_text_operation()))\n\n def as_text(self) -> Message:\n \"\"\"Text output for the Text Join operation.\"\"\"\n return self.as_message()\n\n # ==================================================================\n # JSON operations\n # ==================================================================\n @staticmethod\n def extract_all_paths(obj, path=\"\"):\n paths = []\n if isinstance(obj, dict):\n for k, v in obj.items():\n new_path = f\"{path}.{k}\" if path else f\".{k}\"\n paths.append(new_path)\n paths.extend(OperationsComponent.extract_all_paths(v, new_path))\n elif isinstance(obj, list) and obj:\n new_path = f\"{path}[0]\"\n paths.append(new_path)\n paths.extend(OperationsComponent.extract_all_paths(obj[0], new_path))\n return paths\n\n @staticmethod\n def remove_keys_recursive(obj, keys_to_remove):\n if isinstance(obj, dict):\n return {\n k: OperationsComponent.remove_keys_recursive(v, keys_to_remove)\n for k, v in obj.items()\n if k not in keys_to_remove\n }\n if isinstance(obj, list):\n return [OperationsComponent.remove_keys_recursive(item, keys_to_remove) for item in obj]\n return obj\n\n @staticmethod\n def rename_keys_recursive(obj, rename_map):\n if isinstance(obj, dict):\n return {\n rename_map.get(k, k): OperationsComponent.rename_keys_recursive(v, rename_map) for k, v in obj.items()\n }\n if isinstance(obj, list):\n return [OperationsComponent.rename_keys_recursive(item, rename_map) for item in obj]\n return obj\n\n def _json_handlers(self) -> \"dict[str, Callable[[], Data]]\":\n return {\n \"Select Keys\": self.select_keys,\n \"Literal Eval\": self.evaluate_data,\n \"Combine\": self.combine_data,\n \"Append or Update\": self.append_update,\n \"Remove Keys\": self.remove_keys,\n \"Rename Keys\": self.rename_keys,\n \"Path Selection\": self.json_path,\n \"JQ Expression\": self.json_query,\n }\n\n def get_data_dict(self) -> dict:\n \"\"\"Extract data dictionary from Data object.\"\"\"\n data = self.data[0] if isinstance(self.data, list) and len(self.data) == 1 else self.data\n return data.model_dump()\n\n def get_normalized_data(self) -> dict:\n \"\"\"Get normalized data dictionary, handling the 'data' key if present.\"\"\"\n data_dict = self.get_data_dict()\n return data_dict.get(\"data\", data_dict)\n\n def data_is_list(self) -> bool:\n \"\"\"Check if data contains multiple items.\"\"\"\n return isinstance(self.data, list) and len(self.data) > 1\n\n def validate_single_data(self, operation: str) -> None:\n \"\"\"Validate that the operation is being performed on a single data object.\"\"\"\n if self.data_is_list():\n msg = f\"{operation} operation is not supported for multiple data objects.\"\n raise ValueError(msg)\n\n def select_keys(self) -> Data:\n \"\"\"Select specific keys from the data dictionary.\"\"\"\n self.validate_single_data(\"Select Keys\")\n data_dict = self.get_normalized_data()\n filter_criteria: list[str] = self.select_keys_input\n\n if len(filter_criteria) == 1 and filter_criteria[0] == \"data\":\n filtered = data_dict[\"data\"]\n else:\n if not all(key in data_dict for key in filter_criteria):\n msg = f\"Select key not found in data. Available keys: {list(data_dict.keys())}\"\n raise ValueError(msg)\n filtered = {key: value for key, value in data_dict.items() if key in filter_criteria}\n\n return Data(data=filtered)\n\n def remove_keys(self) -> Data:\n \"\"\"Remove specified keys from the data dictionary, recursively.\"\"\"\n self.validate_single_data(\"Remove Keys\")\n data_dict = self.get_normalized_data()\n remove_keys_input: list[str] = self.remove_keys_input\n filtered = OperationsComponent.remove_keys_recursive(data_dict, set(remove_keys_input))\n return Data(data=filtered)\n\n def rename_keys(self) -> Data:\n \"\"\"Rename keys in the data dictionary, recursively.\"\"\"\n self.validate_single_data(\"Rename Keys\")\n data_dict = self.get_normalized_data()\n rename_keys_input: dict[str, str] = self.rename_keys_input\n renamed = OperationsComponent.rename_keys_recursive(data_dict, rename_keys_input)\n return Data(data=renamed)\n\n def recursive_eval(self, data: Any) -> Any:\n \"\"\"Recursively evaluate string values that look like Python literals.\"\"\"\n if isinstance(data, dict):\n return {k: self.recursive_eval(v) for k, v in data.items()}\n if isinstance(data, list):\n return [self.recursive_eval(item) for item in data]\n if isinstance(data, str):\n try:\n if (\n data.strip().startswith((\"{\", \"[\", \"(\", \"'\", '\"'))\n or data.strip().lower() in (\"true\", \"false\", \"none\")\n or data.strip().replace(\".\", \"\").isdigit()\n ):\n return ast.literal_eval(data)\n except (ValueError, SyntaxError, TypeError, MemoryError):\n return data\n else:\n return data\n return data\n\n def evaluate_data(self) -> Data:\n \"\"\"Evaluate string values in the data dictionary.\"\"\"\n self.validate_single_data(\"Literal Eval\")\n logger.info(\"evaluating data\")\n return Data(**self.recursive_eval(self.get_data_dict()))\n\n def combine_data(self) -> Data:\n \"\"\"Combine multiple data objects into one.\"\"\"\n logger.info(\"combining data\")\n if not self.data_is_list():\n return self.data[0] if self.data else Data(data={})\n\n data_dicts = [data.model_dump().get(\"data\", data.model_dump()) for data in self.data]\n combined_data: dict[str, Any] = {}\n\n for data_dict in data_dicts:\n for key, value in data_dict.items():\n if key not in combined_data:\n combined_data[key] = value\n elif isinstance(combined_data[key], list):\n if isinstance(value, list):\n combined_data[key].extend(value)\n else:\n combined_data[key].append(value)\n else:\n combined_data[key] = (\n [combined_data[key], value] if not isinstance(value, list) else [combined_data[key], *value]\n )\n\n return Data(**combined_data)\n\n def append_update(self) -> Data:\n \"\"\"Append or update the data with new key-value pairs.\"\"\"\n self.validate_single_data(\"Append or Update\")\n data_filtered = self.get_normalized_data()\n for key, value in self.append_update_data.items():\n data_filtered[key] = value\n return Data(**data_filtered)\n\n def json_path(self) -> Data:\n \"\"\"Extract a value from the data using the selected JQ path.\"\"\"\n try:\n import jq\n except ImportError:\n msg = \"jq is required for Path Selection. Install with: pip install jq\"\n raise ImportError(msg) from None\n\n try:\n if not self.data or not self.selected_key:\n msg = \"Missing input data or selected key.\"\n raise ValueError(msg)\n input_payload = self.data[0].data if isinstance(self.data, list) else self.data.data\n validate_jq_program(self.selected_key)\n compiled = jq.compile(self.selected_key)\n result = compiled.input(input_payload).first()\n if isinstance(result, dict):\n return Data(data=result)\n return Data(data={\"result\": result})\n except (ValueError, TypeError, KeyError) as e:\n self.status = f\"Error: {e!s}\"\n self.log(self.status)\n return Data(data={\"error\": str(e)})\n\n def json_query(self) -> Data:\n \"\"\"Run a JQ expression against the data.\"\"\"\n try:\n import jq\n except ImportError:\n msg = \"jq is required for JQ Expression. Install with: pip install jq\"\n raise ImportError(msg) from None\n\n if not self.query or not self.query.strip():\n msg = \"JSON Query is required and cannot be blank.\"\n raise ValueError(msg)\n raw_data = self.get_data_dict()\n try:\n input_str = json.dumps(raw_data)\n repaired = repair_json(input_str)\n data_json = json.loads(repaired)\n jq_input = data_json[\"data\"] if isinstance(data_json, dict) and \"data\" in data_json else data_json\n validate_jq_program(self.query)\n results = jq.compile(self.query).input(jq_input).all()\n if not results:\n msg = \"No result from JSON query.\"\n raise ValueError(msg)\n result = results[0] if len(results) == 1 else results\n if result is None or result == \"None\":\n msg = \"JSON query returned null/None. Check if the path exists in your data.\"\n raise ValueError(msg)\n if isinstance(result, dict):\n return Data(data=result)\n return Data(data={\"result\": result})\n except (ValueError, TypeError, KeyError, json.JSONDecodeError) as e:\n logger.error(f\"JSON Query failed: {e}\")\n msg = f\"JSON Query error: {e}\"\n raise ValueError(msg) from e\n\n # ==================================================================\n # Table operations\n # ==================================================================\n def _get_primary_dataframe(self) -> DataFrame:\n \"\"\"Get the first DataFrame from input (handles both single and list inputs).\"\"\"\n if isinstance(self.df, list):\n return self.df[0].copy() if self.df else DataFrame()\n return self.df.copy()\n\n def _run_table_operation(self, operation: str) -> DataFrame:\n # Merge and Concatenate use their own inputs, not the primary df.\n if operation == \"Merge\":\n return self.merge_dataframes()\n if operation == \"Concatenate\":\n return self.concatenate_dataframes()\n\n df_copy = self._get_primary_dataframe()\n table_handlers = {\n \"Filter\": self.filter_rows_by_value,\n \"Sort\": self.sort_by_column,\n \"Drop Column\": self.drop_column,\n \"Rename Column\": self.rename_column,\n \"Add Column\": self.add_column,\n \"Select Columns\": self.select_columns,\n \"Head\": self.head,\n \"Tail\": self.tail,\n \"Replace Value\": self.replace_values,\n \"Drop Duplicates\": self.drop_duplicates,\n }\n handler = table_handlers.get(operation)\n if handler is None:\n msg = f\"Unsupported operation: {operation}\"\n logger.error(msg)\n raise ValueError(msg)\n return handler(df_copy)\n\n def filter_rows_by_value(self, df: DataFrame) -> DataFrame:\n column = df[self.column_name]\n filter_value = self.filter_value\n operator = getattr(self, \"filter_operator\", \"equals\")\n\n if operator == \"equals\":\n mask = column == filter_value\n elif operator == \"not equals\":\n mask = column != filter_value\n elif operator == \"contains\":\n mask = column.astype(str).str.contains(str(filter_value), na=False)\n elif operator == \"not contains\":\n mask = ~column.astype(str).str.contains(str(filter_value), na=False)\n elif operator == \"starts with\":\n mask = column.astype(str).str.startswith(str(filter_value), na=False)\n elif operator == \"ends with\":\n mask = column.astype(str).str.endswith(str(filter_value), na=False)\n elif operator == \"greater than\":\n try:\n numeric_value = pd.to_numeric(filter_value)\n mask = column > numeric_value\n except (ValueError, TypeError):\n mask = column.astype(str) > str(filter_value)\n elif operator == \"less than\":\n try:\n numeric_value = pd.to_numeric(filter_value)\n mask = column < numeric_value\n except (ValueError, TypeError):\n mask = column.astype(str) < str(filter_value)\n else:\n mask = column == filter_value\n\n return DataFrame(df[mask])\n\n def sort_by_column(self, df: DataFrame) -> DataFrame:\n return DataFrame(df.sort_values(by=self.column_name, ascending=self.ascending))\n\n def drop_column(self, df: DataFrame) -> DataFrame:\n return DataFrame(df.drop(columns=[self.column_name]))\n\n def rename_column(self, df: DataFrame) -> DataFrame:\n return DataFrame(df.rename(columns={self.column_name: self.new_column_name}))\n\n def add_column(self, df: DataFrame) -> DataFrame:\n df[self.new_column_name] = [self.new_column_value] * len(df)\n return DataFrame(df)\n\n def select_columns(self, df: DataFrame) -> DataFrame:\n columns = [col.strip() for col in self.columns_to_select]\n return DataFrame(df[columns])\n\n def head(self, df: DataFrame) -> DataFrame:\n return DataFrame(df.head(self.num_rows))\n\n def tail(self, df: DataFrame) -> DataFrame:\n return DataFrame(df.tail(self.num_rows))\n\n def replace_values(self, df: DataFrame) -> DataFrame:\n df[self.column_name] = df[self.column_name].replace(self.replace_value, self.replacement_value)\n return DataFrame(df)\n\n def drop_duplicates(self, df: DataFrame) -> DataFrame:\n return DataFrame(df.drop_duplicates(subset=self.column_name))\n\n def concatenate_dataframes(self) -> DataFrame:\n \"\"\"Concatenate multiple DataFrames vertically (stack rows).\"\"\"\n if not isinstance(self.df, list) or len(self.df) == 0:\n return self.df.copy() if self.df is not None else DataFrame()\n\n if len(self.df) == 1:\n return self.df[0].copy()\n\n concatenated = pd.concat(self.df, ignore_index=True)\n return DataFrame(concatenated)\n\n def merge_dataframes(self) -> DataFrame:\n \"\"\"Merge two DataFrames based on a common column (join operation).\"\"\"\n left_df = getattr(self, \"left_dataframe\", None)\n right_df = getattr(self, \"right_dataframe\", None)\n\n if left_df is None:\n return DataFrame()\n if right_df is None:\n return left_df.copy()\n\n df_left = left_df.copy()\n df_right = right_df.copy()\n\n merge_on = getattr(self, \"merge_on_column\", None)\n merge_how = getattr(self, \"merge_how\", \"inner\")\n\n if merge_on:\n if merge_on not in df_left.columns:\n msg = f\"Column '{merge_on}' not found in left DataFrame. Available: {list(df_left.columns)}\"\n raise ValueError(msg)\n if merge_on not in df_right.columns:\n msg = f\"Column '{merge_on}' not found in right DataFrame. Available: {list(df_right.columns)}\"\n raise ValueError(msg)\n merged = df_left.merge(df_right, on=merge_on, how=merge_how, suffixes=(\"\", \"_right\"))\n else:\n merged = df_left.merge(df_right, left_index=True, right_index=True, how=merge_how, suffixes=(\"\", \"_right\"))\n\n cols_to_drop = []\n for col in merged.columns:\n if col.endswith(\"_right\"):\n original_col = col[:-6]\n if original_col in merged.columns:\n merged[original_col] = merged[original_col].combine_first(merged[col])\n cols_to_drop.append(col)\n\n if cols_to_drop:\n merged = merged.drop(columns=cols_to_drop)\n\n return DataFrame(merged)\n\n # ==================================================================\n # Text operations\n # ==================================================================\n def _run_text_operation(self) -> Any:\n \"\"\"Process text based on the selected operation (Message/Text outputs).\"\"\"\n text = getattr(self, \"text_input\", \"\")\n operation = self._operation_name()\n\n # Allow empty text for Text Join (second input may have content).\n if not text and operation != \"Text Join\":\n return None\n\n text_handlers = {\n \"Case Conversion\": self._case_conversion,\n \"Text Replace\": self._text_replace,\n \"Text Extract\": self._text_extract,\n \"Text Head\": self._text_head,\n \"Text Tail\": self._text_tail,\n \"Text Strip\": self._text_strip,\n \"Text Join\": self._text_join,\n \"Text Clean\": self._text_clean,\n }\n handler = text_handlers.get(operation)\n if handler:\n return handler(text)\n return text\n\n def _word_count_data(self) -> Data:\n \"\"\"Word Count operation result as a Data object.\"\"\"\n result = self._word_count(getattr(self, \"text_input\", \"\") or \"\")\n return Data(data=result)\n\n def _word_count(self, text: str) -> dict[str, Any]:\n \"\"\"Count words, characters, and lines in text.\"\"\"\n result: dict[str, Any] = {}\n text_str = str(text) if text else \"\"\n is_empty = not text_str or not text_str.strip()\n\n if getattr(self, \"count_words\", True):\n if is_empty:\n result[\"word_count\"] = 0\n result[\"unique_words\"] = 0\n else:\n words = text_str.split()\n result[\"word_count\"] = len(words)\n result[\"unique_words\"] = len(set(words))\n\n if getattr(self, \"count_characters\", True):\n if is_empty:\n result[\"character_count\"] = 0\n result[\"character_count_no_spaces\"] = 0\n else:\n result[\"character_count\"] = len(text_str)\n result[\"character_count_no_spaces\"] = len(text_str.replace(\" \", \"\"))\n\n if getattr(self, \"count_lines\", True):\n if is_empty:\n result[\"line_count\"] = 0\n result[\"non_empty_lines\"] = 0\n else:\n lines = text_str.split(\"\\n\")\n result[\"line_count\"] = len(lines)\n result[\"non_empty_lines\"] = len([line for line in lines if line.strip()])\n\n return result\n\n def _text_to_dataframe(self, text: str) -> DataFrame:\n \"\"\"Convert markdown-style table text to a DataFrame.\"\"\"\n lines = [line.strip() for line in text.strip().split(\"\\n\") if line.strip()]\n if not lines:\n return DataFrame(pd.DataFrame())\n\n separator = getattr(self, \"table_separator\", \"|\")\n has_header = getattr(self, \"has_header\", True)\n\n rows = self._parse_table_rows(lines, separator)\n if not rows:\n return DataFrame(pd.DataFrame())\n\n df = self._create_dataframe(rows, has_header=has_header)\n self._convert_numeric_columns(df)\n self.log(f\"Converted text to DataFrame: {len(df)} rows, {len(df.columns)} columns\")\n return DataFrame(df)\n\n def _parse_table_rows(self, lines: list[str], separator: str) -> list[list[str]]:\n rows = []\n for line in lines:\n cleaned_line = line.strip(separator)\n cells = [cell.strip() for cell in cleaned_line.split(separator)]\n rows.append(cells)\n return rows\n\n def _create_dataframe(self, rows: list[list[str]], *, has_header: bool) -> pd.DataFrame:\n if has_header and len(rows) > 1:\n header = rows[0]\n data_rows = rows[1:]\n header_col_count = len(header)\n for i, row in enumerate(data_rows):\n row_col_count = len(row)\n if row_col_count != header_col_count:\n msg = (\n f\"Header mismatch: {header_col_count} column(s) in header vs \"\n f\"{row_col_count} column(s) in data row {i + 1}. \"\n \"Please ensure the header has the same number of columns as your data.\"\n )\n raise ValueError(msg)\n return pd.DataFrame(data_rows, columns=header)\n\n max_cols = max(len(row) for row in rows) if rows else 0\n columns = [f\"col_{i}\" for i in range(max_cols)]\n return pd.DataFrame(rows, columns=columns)\n\n def _convert_numeric_columns(self, df: pd.DataFrame) -> None:\n for col in df.columns:\n with contextlib.suppress(ValueError, TypeError):\n df[col] = pd.to_numeric(df[col])\n\n def _case_conversion(self, text: str) -> str:\n case_type = getattr(self, \"case_type\", \"lowercase\")\n converter = CASE_CONVERTERS.get(case_type)\n return converter(text) if converter else text\n\n def _text_replace(self, text: str) -> str:\n search_pattern = getattr(self, \"search_pattern\", \"\")\n if not search_pattern:\n return text\n replacement_text = getattr(self, \"replacement_text\", \"\")\n use_regex = getattr(self, \"use_regex\", False)\n if use_regex:\n try:\n return re.sub(search_pattern, replacement_text, text)\n except re.error as e:\n self.log(f\"Invalid regex pattern: {e}\")\n return text\n return text.replace(search_pattern, replacement_text)\n\n def _text_extract(self, text: str) -> list[str]:\n extract_pattern = getattr(self, \"extract_pattern\", \"\")\n if not extract_pattern:\n return []\n max_matches = getattr(self, \"max_matches\", 10)\n try:\n matches = re.findall(extract_pattern, text)\n except re.error as e:\n msg = f\"Invalid regex pattern '{extract_pattern}': {e}\"\n raise ValueError(msg) from e\n return matches[:max_matches] if max_matches > 0 else matches\n\n def _text_head(self, text: str) -> str:\n head_characters = getattr(self, \"head_characters\", 100)\n if head_characters < 0:\n msg = f\"Characters from Start must be a non-negative integer, got {head_characters}\"\n raise ValueError(msg)\n if head_characters == 0:\n return \"\"\n return text[:head_characters]\n\n def _text_tail(self, text: str) -> str:\n tail_characters = getattr(self, \"tail_characters\", 100)\n if tail_characters < 0:\n msg = f\"Characters from End must be a non-negative integer, got {tail_characters}\"\n raise ValueError(msg)\n if tail_characters == 0:\n return \"\"\n return text[-tail_characters:]\n\n def _text_strip(self, text: str) -> str:\n strip_mode = getattr(self, \"strip_mode\", \"both\")\n strip_characters = getattr(self, \"strip_characters\", \"\")\n text_str = str(text) if text else \"\"\n chars_to_strip = strip_characters if strip_characters else None\n if strip_mode == \"left\":\n return text_str.lstrip(chars_to_strip)\n if strip_mode == \"right\":\n return text_str.rstrip(chars_to_strip)\n return text_str.strip(chars_to_strip)\n\n def _text_join(self, text: str) -> str:\n text_input_2 = getattr(self, \"text_input_2\", \"\")\n text1 = str(text) if text else \"\"\n text2 = str(text_input_2) if text_input_2 else \"\"\n if text1 and text2:\n return f\"{text1}\\n{text2}\"\n return text1 or text2\n\n def _text_clean(self, text: str) -> str:\n result = text\n if getattr(self, \"remove_extra_spaces\", True):\n # Collapse runs of horizontal whitespace but preserve newlines so\n # that remove_empty_lines stays effective when both are enabled.\n result = re.sub(r\"[^\\S\\n]+\", \" \", result)\n if getattr(self, \"remove_special_chars\", False):\n result = re.sub(r\"[^\\w\\s]\", \"\", result)\n if getattr(self, \"remove_empty_lines\", False):\n lines = [line for line in result.split(\"\\n\") if line.strip()]\n result = \"\\n\".join(lines)\n return result\n\n def _format_result_as_text(self, result: Any) -> str:\n if result is None:\n return \"\"\n if isinstance(result, list):\n return \"\\n\".join(str(item) for item in result)\n return str(result)\n"
+ "value": "\"\"\"Unified Operations component.\n\nBrings together the previously separate JSON, Table, and Text operation\ncomponents into a single component. An \"Input Type\" selector (Text / JSON /\nTable) drives everything: it filters the \"Operation\" picker to the operations\nthat apply to that type, reveals the matching input (Text / JSON / Table) and\nits operation-specific fields, and advertises the appropriate output type.\n\nThe three original components (JSON Operations, Table Operations, Text\nOperations) remain available as legacy components for backward compatibility\nwith existing flows.\n\"\"\"\n\nimport ast\nimport contextlib\nimport json\nimport re\nfrom typing import TYPE_CHECKING, Any\n\nimport pandas as pd\nfrom json_repair import repair_json\n\nfrom lfx.custom import Component\nfrom lfx.field_typing import RangeSpec\nfrom lfx.inputs import DictInput, SortableListInput, TabInput\nfrom lfx.io import (\n BoolInput,\n DataFrameInput,\n DataInput,\n DropdownInput,\n IntInput,\n MessageTextInput,\n MultilineInput,\n Output,\n StrInput,\n)\nfrom lfx.log.logger import logger\nfrom lfx.schema import Data\nfrom lfx.schema.dataframe import DataFrame\nfrom lfx.schema.dotdict import dotdict\nfrom lfx.schema.message import Message\nfrom lfx.utils.jq_security import validate_jq_program\n\nif TYPE_CHECKING:\n from collections.abc import Callable\n\n# The \"Input Type\" selector tabs. Each value maps a Langflow data type to the\n# operations, input, and output that belong to it.\nINPUT_TYPES = [\"Text\", \"JSON\", \"Table\"]\n\n# Operations grouped by input type, in display order, each with the icon shown\n# in the Operation picker. This is the single source of truth for the picker;\n# update_build_config swaps the picker's options to the selected type's list.\nOPERATIONS_BY_TYPE: dict[str, list[dict[str, str]]] = {\n \"Text\": [\n {\"name\": \"Word Count\", \"icon\": \"hash\"},\n {\"name\": \"Case Conversion\", \"icon\": \"type\"},\n {\"name\": \"Text Replace\", \"icon\": \"replace\"},\n {\"name\": \"Text Extract\", \"icon\": \"search\"},\n {\"name\": \"Text Head\", \"icon\": \"chevron-left\"},\n {\"name\": \"Text Tail\", \"icon\": \"chevron-right\"},\n {\"name\": \"Text Strip\", \"icon\": \"minus\"},\n {\"name\": \"Text Join\", \"icon\": \"link\"},\n {\"name\": \"Text Clean\", \"icon\": \"sparkles\"},\n {\"name\": \"Text to DataFrame\", \"icon\": \"table\"},\n ],\n \"JSON\": [\n {\"name\": \"Select Keys\", \"icon\": \"lasso-select\"},\n {\"name\": \"Literal Eval\", \"icon\": \"braces\"},\n {\"name\": \"Combine\", \"icon\": \"merge\"},\n {\"name\": \"Append or Update\", \"icon\": \"circle-plus\"},\n {\"name\": \"Remove Keys\", \"icon\": \"eraser\"},\n {\"name\": \"Rename Keys\", \"icon\": \"pencil-line\"},\n {\"name\": \"Path Selection\", \"icon\": \"mouse-pointer\"},\n {\"name\": \"JQ Expression\", \"icon\": \"terminal\"},\n ],\n \"Table\": [\n {\"name\": \"Add Column\", \"icon\": \"plus\"},\n {\"name\": \"Concatenate\", \"icon\": \"combine\"},\n {\"name\": \"Drop Column\", \"icon\": \"minus\"},\n {\"name\": \"Filter\", \"icon\": \"filter\"},\n {\"name\": \"Head\", \"icon\": \"arrow-up\"},\n {\"name\": \"Merge\", \"icon\": \"merge\"},\n {\"name\": \"Rename Column\", \"icon\": \"pencil\"},\n {\"name\": \"Replace Value\", \"icon\": \"replace\"},\n {\"name\": \"Select Columns\", \"icon\": \"columns\"},\n {\"name\": \"Sort\", \"icon\": \"arrow-up-down\"},\n {\"name\": \"Tail\", \"icon\": \"arrow-down\"},\n {\"name\": \"Drop Duplicates\", \"icon\": \"copy-x\"},\n ],\n}\n\n# Operation-name sets derived from the picker, used for dispatch and output\n# routing. Keeping them derived from OPERATIONS_BY_TYPE avoids any drift.\nJSON_OPERATIONS = {op[\"name\"] for op in OPERATIONS_BY_TYPE[\"JSON\"]}\nTABLE_OPERATIONS = {op[\"name\"] for op in OPERATIONS_BY_TYPE[\"Table\"]}\nTEXT_OPERATIONS = {op[\"name\"] for op in OPERATIONS_BY_TYPE[\"Text\"]}\n\n# Each input type maps to its main input field and its default output. \"Text\"\n# normally outputs a Message; \"JSON\" a Data; \"Table\" a DataFrame. A few text\n# operations override this (Word Count -> Data, Text to DataFrame -> DataFrame).\nINPUT_TYPE_TO_MAIN_INPUT = {\"Text\": \"text_input\", \"JSON\": \"data\", \"Table\": \"df\"}\n\n# Case conversions for the Text \"Case Conversion\" operation.\nCASE_CONVERTERS: dict[str, Any] = {\n \"uppercase\": str.upper,\n \"lowercase\": str.lower,\n \"title\": str.title,\n \"capitalize\": str.capitalize,\n \"swapcase\": str.swapcase,\n}\n\n# A markdown table's delimiter row (``|---|:--:|``) separates the header from the body.\nMARKDOWN_DELIMITER_CELL = re.compile(r\":?-+:?\")\n\n\nclass OperationsComponent(Component):\n display_name = \"Data Operations\"\n description = \"Perform operations on Text, JSON, and Tables from a single component.\"\n documentation: str = \"https://docs.langflow.org/components-processing#operations\"\n icon = \"wand-sparkles\"\n name = \"Operations\"\n metadata = {\n \"keywords\": [\n \"operations\",\n \"data operations\",\n \"json\",\n \"json operations\",\n \"table\",\n \"table operations\",\n \"dataframe\",\n \"dataframe operations\",\n \"text\",\n \"text operations\",\n \"select keys\",\n \"literal eval\",\n \"combine\",\n \"append or update\",\n \"remove keys\",\n \"rename keys\",\n \"path selection\",\n \"jq expression\",\n \"parse json\",\n \"add column\",\n \"concatenate\",\n \"drop column\",\n \"filter\",\n \"head\",\n \"merge\",\n \"rename column\",\n \"replace value\",\n \"select columns\",\n \"sort\",\n \"tail\",\n \"drop duplicates\",\n \"word count\",\n \"case conversion\",\n \"text replace\",\n \"text extract\",\n \"text join\",\n \"text clean\",\n \"text to dataframe\",\n \"data manipulation\",\n \"data transformation\",\n ],\n }\n\n # Operation -> operation-specific input fields to reveal when selected.\n OPERATION_FIELDS: dict[str, list[str]] = {\n # JSON\n \"Select Keys\": [\"select_keys_input\"],\n \"Literal Eval\": [],\n \"Combine\": [],\n \"Append or Update\": [\"append_update_data\"],\n \"Remove Keys\": [\"remove_keys_input\"],\n \"Rename Keys\": [\"rename_keys_input\"],\n \"Path Selection\": [\"mapped_json_display\", \"selected_key\"],\n \"JQ Expression\": [\"query\"],\n # Table\n \"Add Column\": [\"new_column_name\", \"new_column_value\"],\n \"Concatenate\": [],\n \"Drop Column\": [\"column_name\"],\n \"Filter\": [\"column_name\", \"filter_value\", \"filter_operator\"],\n \"Head\": [\"num_rows\"],\n \"Merge\": [\"left_dataframe\", \"right_dataframe\", \"merge_on_column\", \"merge_how\"],\n \"Rename Column\": [\"column_name\", \"new_column_name\"],\n \"Replace Value\": [\"column_name\", \"replace_value\", \"replacement_value\"],\n \"Select Columns\": [\"columns_to_select\"],\n \"Sort\": [\"column_name\", \"ascending\"],\n \"Tail\": [\"num_rows\"],\n \"Drop Duplicates\": [\"column_name\"],\n # Text\n \"Word Count\": [\"count_words\", \"count_characters\", \"count_lines\"],\n \"Case Conversion\": [\"case_type\"],\n \"Text Replace\": [\"search_pattern\", \"replacement_text\", \"use_regex\"],\n \"Text Extract\": [\"extract_pattern\", \"max_matches\"],\n \"Text Head\": [\"head_characters\"],\n \"Text Tail\": [\"tail_characters\"],\n \"Text Strip\": [\"strip_mode\", \"strip_characters\"],\n \"Text Join\": [\"text_input_2\"],\n \"Text Clean\": [\"remove_extra_spaces\", \"remove_special_chars\", \"remove_empty_lines\"],\n \"Text to DataFrame\": [\"table_separator\", \"has_header\"],\n }\n\n # The three main inputs (one per data type). They are never treated as\n # operation-specific fields; the input-type selector toggles them.\n MAIN_INPUTS = (\"text_input\", \"data\", \"df\")\n\n # Every operation-specific field (union of all the lists above), used to\n # hide and reset fields whenever the input type or operation changes.\n ALL_OPERATION_FIELDS: list[str] = [\n # JSON\n \"select_keys_input\",\n \"append_update_data\",\n \"remove_keys_input\",\n \"rename_keys_input\",\n \"mapped_json_display\",\n \"selected_key\",\n \"query\",\n # Table\n \"column_name\",\n \"filter_value\",\n \"filter_operator\",\n \"ascending\",\n \"new_column_name\",\n \"new_column_value\",\n \"columns_to_select\",\n \"num_rows\",\n \"replace_value\",\n \"replacement_value\",\n \"left_dataframe\",\n \"right_dataframe\",\n \"merge_on_column\",\n \"merge_how\",\n # Text\n \"table_separator\",\n \"has_header\",\n \"count_words\",\n \"count_characters\",\n \"count_lines\",\n \"case_type\",\n \"use_regex\",\n \"search_pattern\",\n \"replacement_text\",\n \"extract_pattern\",\n \"max_matches\",\n \"head_characters\",\n \"tail_characters\",\n \"strip_mode\",\n \"strip_characters\",\n \"text_input_2\",\n \"remove_extra_spaces\",\n \"remove_special_chars\",\n \"remove_empty_lines\",\n ]\n\n # Defaults applied to the JSON operation fields when the operation changes,\n # mirroring the JSON Operations component's reset behavior.\n OPERATION_FIELD_DEFAULTS: dict[str, Any] = {\n \"select_keys_input\": [],\n \"append_update_data\": {\"key\": \"value\"},\n \"remove_keys_input\": [],\n \"rename_keys_input\": {\"old_key\": \"new_key\"},\n \"mapped_json_display\": \"\",\n \"selected_key\": None,\n \"query\": \"\",\n }\n\n inputs = [\n # --- Input type selector: drives operations, input, and output ---\n TabInput(\n name=\"input_type\",\n display_name=\"Input Type\",\n options=INPUT_TYPES,\n value=\"Text\",\n info=\"Select the type of input to operate on.\",\n real_time_refresh=True,\n ),\n # --- Main inputs: one per data type, shown contextually ---\n MultilineInput(\n name=\"text_input\",\n display_name=\"Text\",\n info=\"The input text to process.\",\n show=True,\n ),\n DataInput(\n name=\"data\",\n display_name=\"JSON\",\n info=\"The JSON / Data object to operate on.\",\n is_list=True,\n show=False,\n ),\n DataFrameInput(\n name=\"df\",\n display_name=\"Table\",\n info=\"The input Table to operate on. Connect multiple Tables for merge or concatenate operations.\",\n is_list=True,\n show=False,\n ),\n # --- Operation picker (options are filtered by Input Type) ---\n SortableListInput(\n name=\"operation\",\n display_name=\"Operation\",\n placeholder=\"Select Operation\",\n info=\"Select the operation to perform. The matching fields and output appear once you choose one.\",\n options=OPERATIONS_BY_TYPE[\"Text\"],\n real_time_refresh=True,\n limit=1,\n ),\n # --- JSON operation fields ---\n MessageTextInput(\n name=\"select_keys_input\",\n display_name=\"Select Keys\",\n info=\"List of keys to select from the data. Only top-level keys can be selected.\",\n show=False,\n is_list=True,\n value=[],\n ),\n DictInput(\n name=\"append_update_data\",\n display_name=\"Append or Update\",\n info=\"Data to append or update the existing data with. Only top-level keys are checked.\",\n show=False,\n value={\"key\": \"value\"},\n is_list=True,\n ),\n MessageTextInput(\n name=\"remove_keys_input\",\n display_name=\"Remove Keys\",\n info=\"List of keys to remove from the data.\",\n show=False,\n is_list=True,\n value=[],\n ),\n DictInput(\n name=\"rename_keys_input\",\n display_name=\"Rename Keys\",\n info=\"List of keys to rename in the data.\",\n show=False,\n is_list=True,\n value={\"old_key\": \"new_key\"},\n ),\n MultilineInput(\n name=\"mapped_json_display\",\n display_name=\"JSON to Map\",\n info=\"Paste or preview your JSON here to explore its structure and select a path for extraction.\",\n required=False,\n refresh_button=True,\n real_time_refresh=True,\n placeholder=\"Add a JSON example.\",\n show=False,\n ),\n DropdownInput(\n name=\"selected_key\",\n display_name=\"Select Path\",\n options=[],\n required=False,\n dynamic=True,\n show=False,\n value=None,\n ),\n MessageTextInput(\n name=\"query\",\n display_name=\"JQ Expression\",\n info=\"JSON Query to filter the data. Used by Path Selection and JQ Expression operations.\",\n placeholder=\"e.g., .properties.id\",\n show=False,\n ),\n # --- Table operation fields ---\n StrInput(\n name=\"column_name\",\n display_name=\"Column Name\",\n info=\"The column name to use for the operation.\",\n dynamic=True,\n show=False,\n ),\n MessageTextInput(\n name=\"filter_value\",\n display_name=\"Filter Value\",\n info=\"The value to filter rows by.\",\n dynamic=True,\n show=False,\n ),\n DropdownInput(\n name=\"filter_operator\",\n display_name=\"Filter Operator\",\n options=[\n \"equals\",\n \"not equals\",\n \"contains\",\n \"not contains\",\n \"starts with\",\n \"ends with\",\n \"greater than\",\n \"less than\",\n ],\n value=\"equals\",\n info=\"The operator to apply for filtering rows.\",\n advanced=False,\n dynamic=True,\n show=False,\n ),\n BoolInput(\n name=\"ascending\",\n display_name=\"Sort Ascending\",\n info=\"Whether to sort in ascending order.\",\n dynamic=True,\n show=False,\n value=True,\n ),\n StrInput(\n name=\"new_column_name\",\n display_name=\"New Column Name\",\n info=\"The new column name when renaming or adding a column.\",\n dynamic=True,\n show=False,\n ),\n MessageTextInput(\n name=\"new_column_value\",\n display_name=\"New Column Value\",\n info=\"The value to populate the new column with.\",\n dynamic=True,\n show=False,\n ),\n StrInput(\n name=\"columns_to_select\",\n display_name=\"Columns to Select\",\n dynamic=True,\n is_list=True,\n show=False,\n ),\n IntInput(\n name=\"num_rows\",\n display_name=\"Number of Rows\",\n info=\"Number of rows to return (for head/tail).\",\n dynamic=True,\n show=False,\n value=5,\n ),\n MessageTextInput(\n name=\"replace_value\",\n display_name=\"Value to Replace\",\n info=\"The value to replace in the column.\",\n dynamic=True,\n show=False,\n ),\n MessageTextInput(\n name=\"replacement_value\",\n display_name=\"Replacement Value\",\n info=\"The value to replace with.\",\n dynamic=True,\n show=False,\n ),\n DataFrameInput(\n name=\"left_dataframe\",\n display_name=\"Left Table\",\n info=\"The left (primary) Table for merge operations. \"\n \"In a left merge, all rows from this table are preserved.\",\n dynamic=True,\n show=False,\n ),\n DataFrameInput(\n name=\"right_dataframe\",\n display_name=\"Right Table\",\n info=\"The right (secondary) Table for merge operations. \"\n \"In a right merge, all rows from this table are preserved.\",\n dynamic=True,\n show=False,\n ),\n StrInput(\n name=\"merge_on_column\",\n display_name=\"Merge On Column\",\n info=\"The column name to merge Tables on. Must exist in both Tables.\",\n dynamic=True,\n show=False,\n ),\n DropdownInput(\n name=\"merge_how\",\n display_name=\"Merge Type\",\n options=[\"inner\", \"outer\", \"left\", \"right\"],\n value=\"inner\",\n info=\"Type of merge: inner (intersection), outer (union), left, or right.\",\n dynamic=True,\n show=False,\n ),\n # --- Text operation fields ---\n StrInput(\n name=\"table_separator\",\n display_name=\"Table Separator\",\n info=\"Separator used in the table (default: '|').\",\n value=\"|\",\n dynamic=True,\n show=False,\n ),\n BoolInput(\n name=\"has_header\",\n display_name=\"Has Header\",\n info=\"Whether the table has a header row.\",\n value=True,\n dynamic=True,\n advanced=True,\n show=False,\n ),\n BoolInput(\n name=\"count_words\",\n display_name=\"Count Words\",\n info=\"Include word count in analysis.\",\n value=True,\n dynamic=True,\n advanced=True,\n show=False,\n ),\n BoolInput(\n name=\"count_characters\",\n display_name=\"Count Characters\",\n info=\"Include character count in analysis.\",\n value=True,\n dynamic=True,\n advanced=True,\n show=False,\n ),\n BoolInput(\n name=\"count_lines\",\n display_name=\"Count Lines\",\n info=\"Include line count in analysis.\",\n value=True,\n dynamic=True,\n advanced=True,\n show=False,\n ),\n DropdownInput(\n name=\"case_type\",\n display_name=\"Case Type\",\n options=[\"uppercase\", \"lowercase\", \"title\", \"capitalize\", \"swapcase\"],\n value=\"lowercase\",\n info=\"Type of case conversion to apply.\",\n dynamic=True,\n show=False,\n ),\n BoolInput(\n name=\"use_regex\",\n display_name=\"Use Regex\",\n info=\"Whether to treat search pattern as regex.\",\n value=False,\n dynamic=True,\n show=False,\n ),\n StrInput(\n name=\"search_pattern\",\n display_name=\"Search Pattern\",\n info=\"Text pattern to search for (supports regex).\",\n dynamic=True,\n show=False,\n ),\n StrInput(\n name=\"replacement_text\",\n display_name=\"Replacement Text\",\n info=\"Text to replace the search pattern with.\",\n dynamic=True,\n show=False,\n ),\n StrInput(\n name=\"extract_pattern\",\n display_name=\"Extract Pattern\",\n info=\"Regex pattern to extract from text.\",\n dynamic=True,\n show=False,\n ),\n IntInput(\n name=\"max_matches\",\n display_name=\"Max Matches\",\n info=\"Maximum number of matches to extract.\",\n value=10,\n dynamic=True,\n show=False,\n ),\n IntInput(\n name=\"head_characters\",\n display_name=\"Characters from Start\",\n info=\"Number of characters to extract from the beginning of text. Must be non-negative.\",\n value=100,\n dynamic=True,\n show=False,\n range_spec=RangeSpec(min=0, max=1000000, step=1, step_type=\"int\"),\n ),\n IntInput(\n name=\"tail_characters\",\n display_name=\"Characters from End\",\n info=\"Number of characters to extract from the end of text. Must be non-negative.\",\n value=100,\n dynamic=True,\n show=False,\n range_spec=RangeSpec(min=0, max=1000000, step=1, step_type=\"int\"),\n ),\n DropdownInput(\n name=\"strip_mode\",\n display_name=\"Strip Mode\",\n options=[\"both\", \"left\", \"right\"],\n value=\"both\",\n info=\"Which sides to strip whitespace from.\",\n dynamic=True,\n show=False,\n ),\n StrInput(\n name=\"strip_characters\",\n display_name=\"Characters to Strip\",\n info=\"Specific characters to remove (leave empty for whitespace).\",\n value=\"\",\n dynamic=True,\n show=False,\n ),\n MultilineInput(\n name=\"text_input_2\",\n display_name=\"Second Text Input\",\n info=\"Second text to join with the first text.\",\n dynamic=True,\n show=False,\n ),\n BoolInput(\n name=\"remove_extra_spaces\",\n display_name=\"Remove Extra Spaces\",\n info=\"Remove multiple consecutive spaces.\",\n value=True,\n dynamic=True,\n show=False,\n ),\n BoolInput(\n name=\"remove_special_chars\",\n display_name=\"Remove Special Characters\",\n info=\"Remove special characters except alphanumeric and spaces.\",\n value=False,\n dynamic=True,\n show=False,\n ),\n BoolInput(\n name=\"remove_empty_lines\",\n display_name=\"Remove Empty Lines\",\n info=\"Remove empty lines from text.\",\n value=False,\n dynamic=True,\n show=False,\n ),\n ]\n\n # Default output matches the default Input Type (\"Text\" -> Message).\n # update_outputs / update_frontend_node narrow it to the selected type and\n # operation.\n outputs = [Output(display_name=\"Message\", name=\"message_output\", method=\"as_message\")]\n\n # ------------------------------------------------------------------\n # Operation routing helpers\n # ------------------------------------------------------------------\n @staticmethod\n def _extract_operation_name(field_value: Any) -> str:\n \"\"\"Extract the operation name from a SortableListInput value.\"\"\"\n if isinstance(field_value, list) and len(field_value) > 0 and isinstance(field_value[0], dict):\n return field_value[0].get(\"name\", \"\")\n if isinstance(field_value, str):\n return field_value\n return \"\"\n\n def _operation_name(self) -> str:\n \"\"\"Get the currently selected operation name.\"\"\"\n return self._extract_operation_name(getattr(self, \"operation\", []))\n\n @staticmethod\n def _default_output_for_type(input_type: str) -> Output:\n \"\"\"Return the output advertised for an input type when no operation is selected yet.\"\"\"\n if input_type == \"JSON\":\n return Output(display_name=\"JSON\", name=\"data_output\", method=\"as_data\")\n if input_type == \"Table\":\n return Output(display_name=\"Table\", name=\"dataframe_output\", method=\"as_dataframe\")\n return Output(display_name=\"Message\", name=\"message_output\", method=\"as_message\")\n\n # ------------------------------------------------------------------\n # Dynamic UI\n # ------------------------------------------------------------------\n def _reset_operation_fields(self, build_config: dotdict) -> None:\n \"\"\"Hide every operation-specific field and restore its default value.\"\"\"\n for field in self.ALL_OPERATION_FIELDS:\n if field in build_config:\n build_config[field][\"show\"] = False\n if field in self.OPERATION_FIELD_DEFAULTS:\n build_config[field][\"value\"] = self.OPERATION_FIELD_DEFAULTS[field]\n\n def _show_main_input(self, build_config: dotdict, input_type: str, operation: str) -> None:\n \"\"\"Show only the main input that matches the input type; hide the others.\"\"\"\n for inp in self.MAIN_INPUTS:\n if inp in build_config:\n build_config[inp][\"show\"] = False\n build_config[inp][\"required\"] = False\n\n main_input = INPUT_TYPE_TO_MAIN_INPUT.get(input_type)\n if main_input and main_input in build_config:\n build_config[main_input][\"show\"] = True\n build_config[main_input][\"required\"] = True\n # The JSON \"Combine\" operation consumes a list of Data objects.\n if main_input == \"data\":\n build_config[\"data\"][\"is_list\"] = operation == \"Combine\"\n\n def update_build_config(self, build_config: dotdict, field_value: Any, field_name: str | None = None) -> dotdict:\n # Path Selection: refresh the available JSON paths from the pasted JSON.\n if field_name == \"mapped_json_display\":\n try:\n parsed_json = json.loads(field_value)\n keys = self.extract_all_paths(parsed_json)\n build_config[\"selected_key\"][\"options\"] = keys\n build_config[\"selected_key\"][\"show\"] = True\n except (json.JSONDecodeError, TypeError, ValueError) as e:\n logger.error(f\"Error parsing mapped JSON: {e}\")\n build_config[\"selected_key\"][\"show\"] = False\n return build_config\n\n # Input type changed: swap the operation list, clear the selection, and\n # show only the matching input. No operation-specific fields are shown\n # until an operation is picked.\n if field_name == \"input_type\":\n input_type = field_value if field_value in OPERATIONS_BY_TYPE else \"Text\"\n build_config[\"operation\"][\"options\"] = OPERATIONS_BY_TYPE[input_type]\n build_config[\"operation\"][\"value\"] = []\n self._reset_operation_fields(build_config)\n self._show_main_input(build_config, input_type, operation=\"\")\n return build_config\n\n # Operation changed: reset fields, show the input for the current type,\n # then reveal the operation-specific fields.\n if field_name == \"operation\":\n operation = self._extract_operation_name(field_value)\n self._reset_operation_fields(build_config)\n\n input_type = build_config.get(\"input_type\", {}).get(\"value\", \"Text\")\n self._show_main_input(build_config, input_type, operation)\n\n for field in self.OPERATION_FIELDS.get(operation, []):\n if field in build_config:\n build_config[field][\"show\"] = True\n\n return build_config\n\n return build_config\n\n def update_outputs(self, frontend_node: dict, field_name: str, field_value: Any) -> dict:\n \"\"\"Create the output(s) appropriate to the selected input type and operation.\"\"\"\n if field_name == \"input_type\":\n # Switching type clears the operation; advertise the type's default.\n input_type = field_value if field_value in OPERATIONS_BY_TYPE else \"Text\"\n frontend_node[\"outputs\"] = [self._default_output_for_type(input_type)]\n return frontend_node\n\n template = frontend_node.get(\"template\", {})\n input_type = template.get(\"input_type\", {}).get(\"value\", \"Text\")\n\n if field_name == \"operation\":\n operation = self._extract_operation_name(field_value)\n else:\n # Any other refresh (e.g. Path Selection's \"JSON to Map\" field)\n # reaches here on a freshly rebuilt node whose outputs were reset\n # to the class default (Message). Re-derive the output from the\n # saved operation so the refresh doesn't swap the real output type.\n operation = self._extract_operation_name(template.get(\"operation\", {}).get(\"value\", []))\n\n if not operation:\n # No operation selected: fall back to the input type's default output.\n frontend_node[\"outputs\"] = [self._default_output_for_type(input_type)]\n return frontend_node\n\n frontend_node[\"outputs\"] = []\n if operation in JSON_OPERATIONS or operation == \"Word Count\":\n frontend_node[\"outputs\"].append(Output(display_name=\"JSON\", name=\"data_output\", method=\"as_data\"))\n elif operation in TABLE_OPERATIONS or operation == \"Text to DataFrame\":\n frontend_node[\"outputs\"].append(\n Output(display_name=\"Table\", name=\"dataframe_output\", method=\"as_dataframe\")\n )\n elif operation == \"Text Join\":\n frontend_node[\"outputs\"].append(Output(display_name=\"Text\", name=\"text_output\", method=\"as_text\"))\n frontend_node[\"outputs\"].append(Output(display_name=\"Message\", name=\"message_output\", method=\"as_message\"))\n else:\n frontend_node[\"outputs\"].append(Output(display_name=\"Message\", name=\"message_output\", method=\"as_message\"))\n\n return frontend_node\n\n async def update_frontend_node(self, new_frontend_node: dict, current_frontend_node: dict) -> dict:\n \"\"\"Keep the operation options and outputs in sync with the saved input type on load.\"\"\"\n await super().update_frontend_node(new_frontend_node, current_frontend_node)\n\n template = new_frontend_node.get(\"template\", {})\n input_type = template.get(\"input_type\", {}).get(\"value\", \"Text\")\n if input_type not in OPERATIONS_BY_TYPE:\n input_type = \"Text\"\n\n # Filter the operation picker to the saved input type.\n if \"operation\" in template:\n template[\"operation\"][\"options\"] = OPERATIONS_BY_TYPE[input_type]\n\n # Re-derive the outputs from the saved input type + operation.\n operation_value = template.get(\"operation\", {}).get(\"value\", [])\n if self._extract_operation_name(operation_value):\n self.update_outputs(new_frontend_node, \"operation\", operation_value)\n else:\n self.update_outputs(new_frontend_node, \"input_type\", input_type)\n\n return new_frontend_node\n\n # ==================================================================\n # Output methods (referenced by update_outputs)\n # ==================================================================\n def as_data(self) -> Data:\n \"\"\"JSON-typed output: JSON operations and Word Count.\"\"\"\n operation = self._operation_name()\n if operation in JSON_OPERATIONS:\n handler = self._json_handlers().get(operation)\n if handler:\n try:\n return handler()\n except Exception as e:\n logger.error(f\"Error executing {operation}: {e!s}\")\n raise\n if operation == \"Word Count\":\n return self._word_count_data()\n return Data(data={})\n\n def as_dataframe(self) -> DataFrame:\n \"\"\"Table-typed output: Table operations and Text to DataFrame.\"\"\"\n operation = self._operation_name()\n if operation in TABLE_OPERATIONS:\n return self._run_table_operation(operation)\n if operation == \"Text to DataFrame\":\n return self._text_to_dataframe(getattr(self, \"text_input\", \"\") or \"\")\n return DataFrame(pd.DataFrame())\n\n def as_message(self) -> Message:\n \"\"\"Message-typed output: generic text operations (and Text Join).\"\"\"\n return Message(text=self._format_result_as_text(self._run_text_operation()))\n\n def as_text(self) -> Message:\n \"\"\"Text output for the Text Join operation.\"\"\"\n return self.as_message()\n\n # ==================================================================\n # JSON operations\n # ==================================================================\n @staticmethod\n def extract_all_paths(obj, path=\"\"):\n paths = []\n if isinstance(obj, dict):\n for k, v in obj.items():\n new_path = f\"{path}.{k}\" if path else f\".{k}\"\n paths.append(new_path)\n paths.extend(OperationsComponent.extract_all_paths(v, new_path))\n elif isinstance(obj, list) and obj:\n new_path = f\"{path}[0]\"\n paths.append(new_path)\n paths.extend(OperationsComponent.extract_all_paths(obj[0], new_path))\n return paths\n\n @staticmethod\n def remove_keys_recursive(obj, keys_to_remove):\n if isinstance(obj, dict):\n return {\n k: OperationsComponent.remove_keys_recursive(v, keys_to_remove)\n for k, v in obj.items()\n if k not in keys_to_remove\n }\n if isinstance(obj, list):\n return [OperationsComponent.remove_keys_recursive(item, keys_to_remove) for item in obj]\n return obj\n\n @staticmethod\n def rename_keys_recursive(obj, rename_map):\n if isinstance(obj, dict):\n return {\n rename_map.get(k, k): OperationsComponent.rename_keys_recursive(v, rename_map) for k, v in obj.items()\n }\n if isinstance(obj, list):\n return [OperationsComponent.rename_keys_recursive(item, rename_map) for item in obj]\n return obj\n\n def _json_handlers(self) -> \"dict[str, Callable[[], Data]]\":\n return {\n \"Select Keys\": self.select_keys,\n \"Literal Eval\": self.evaluate_data,\n \"Combine\": self.combine_data,\n \"Append or Update\": self.append_update,\n \"Remove Keys\": self.remove_keys,\n \"Rename Keys\": self.rename_keys,\n \"Path Selection\": self.json_path,\n \"JQ Expression\": self.json_query,\n }\n\n def get_data_dict(self) -> dict:\n \"\"\"Extract data dictionary from Data object.\"\"\"\n data = self.data[0] if isinstance(self.data, list) and len(self.data) == 1 else self.data\n return data.model_dump()\n\n def get_normalized_data(self) -> dict:\n \"\"\"Get normalized data dictionary, handling the 'data' key if present.\"\"\"\n data_dict = self.get_data_dict()\n return data_dict.get(\"data\", data_dict)\n\n def data_is_list(self) -> bool:\n \"\"\"Check if data contains multiple items.\"\"\"\n return isinstance(self.data, list) and len(self.data) > 1\n\n def validate_single_data(self, operation: str) -> None:\n \"\"\"Validate that the operation is being performed on a single data object.\"\"\"\n if self.data_is_list():\n msg = f\"{operation} operation is not supported for multiple data objects.\"\n raise ValueError(msg)\n\n def select_keys(self) -> Data:\n \"\"\"Select specific keys from the data dictionary.\"\"\"\n self.validate_single_data(\"Select Keys\")\n data_dict = self.get_normalized_data()\n filter_criteria: list[str] = self.select_keys_input\n\n if len(filter_criteria) == 1 and filter_criteria[0] == \"data\":\n filtered = data_dict[\"data\"]\n else:\n if not all(key in data_dict for key in filter_criteria):\n msg = f\"Select key not found in data. Available keys: {list(data_dict.keys())}\"\n raise ValueError(msg)\n filtered = {key: value for key, value in data_dict.items() if key in filter_criteria}\n\n return Data(data=filtered)\n\n def remove_keys(self) -> Data:\n \"\"\"Remove specified keys from the data dictionary, recursively.\"\"\"\n self.validate_single_data(\"Remove Keys\")\n data_dict = self.get_normalized_data()\n remove_keys_input: list[str] = self.remove_keys_input\n filtered = OperationsComponent.remove_keys_recursive(data_dict, set(remove_keys_input))\n return Data(data=filtered)\n\n def rename_keys(self) -> Data:\n \"\"\"Rename keys in the data dictionary, recursively.\"\"\"\n self.validate_single_data(\"Rename Keys\")\n data_dict = self.get_normalized_data()\n rename_keys_input: dict[str, str] = self.rename_keys_input\n renamed = OperationsComponent.rename_keys_recursive(data_dict, rename_keys_input)\n return Data(data=renamed)\n\n def recursive_eval(self, data: Any) -> Any:\n \"\"\"Recursively evaluate string values that look like Python literals.\"\"\"\n if isinstance(data, dict):\n return {k: self.recursive_eval(v) for k, v in data.items()}\n if isinstance(data, list):\n return [self.recursive_eval(item) for item in data]\n if isinstance(data, str):\n try:\n if (\n data.strip().startswith((\"{\", \"[\", \"(\", \"'\", '\"'))\n or data.strip().lower() in (\"true\", \"false\", \"none\")\n or data.strip().replace(\".\", \"\").isdigit()\n ):\n return ast.literal_eval(data)\n except (ValueError, SyntaxError, TypeError, MemoryError):\n return data\n else:\n return data\n return data\n\n def evaluate_data(self) -> Data:\n \"\"\"Evaluate string values in the data dictionary.\"\"\"\n self.validate_single_data(\"Literal Eval\")\n logger.info(\"evaluating data\")\n return Data(**self.recursive_eval(self.get_data_dict()))\n\n def combine_data(self) -> Data:\n \"\"\"Combine multiple data objects into one.\"\"\"\n logger.info(\"combining data\")\n if not self.data_is_list():\n return self.data[0] if self.data else Data(data={})\n\n data_dicts = [data.model_dump().get(\"data\", data.model_dump()) for data in self.data]\n combined_data: dict[str, Any] = {}\n\n for data_dict in data_dicts:\n for key, value in data_dict.items():\n if key not in combined_data:\n combined_data[key] = value\n elif isinstance(combined_data[key], list):\n if isinstance(value, list):\n combined_data[key].extend(value)\n else:\n combined_data[key].append(value)\n else:\n combined_data[key] = (\n [combined_data[key], value] if not isinstance(value, list) else [combined_data[key], *value]\n )\n\n return Data(**combined_data)\n\n def append_update(self) -> Data:\n \"\"\"Append or update the data with new key-value pairs.\"\"\"\n self.validate_single_data(\"Append or Update\")\n data_filtered = self.get_normalized_data()\n for key, value in self.append_update_data.items():\n data_filtered[key] = value\n return Data(**data_filtered)\n\n def json_path(self) -> Data:\n \"\"\"Extract a value from the data using the selected JQ path.\"\"\"\n try:\n import jq\n except ImportError:\n msg = \"jq is required for Path Selection. Install with: pip install jq\"\n raise ImportError(msg) from None\n\n try:\n if not self.data or not self.selected_key:\n msg = \"Missing input data or selected key.\"\n raise ValueError(msg)\n input_payload = self.data[0].data if isinstance(self.data, list) else self.data.data\n validate_jq_program(self.selected_key)\n compiled = jq.compile(self.selected_key)\n result = compiled.input(input_payload).first()\n if isinstance(result, dict):\n return Data(data=result)\n return Data(data={\"result\": result})\n except (ValueError, TypeError, KeyError) as e:\n self.status = f\"Error: {e!s}\"\n self.log(self.status)\n return Data(data={\"error\": str(e)})\n\n def json_query(self) -> Data:\n \"\"\"Run a JQ expression against the data.\"\"\"\n try:\n import jq\n except ImportError:\n msg = \"jq is required for JQ Expression. Install with: pip install jq\"\n raise ImportError(msg) from None\n\n if not self.query or not self.query.strip():\n msg = \"JSON Query is required and cannot be blank.\"\n raise ValueError(msg)\n raw_data = self.get_data_dict()\n try:\n input_str = json.dumps(raw_data)\n repaired = repair_json(input_str)\n data_json = json.loads(repaired)\n jq_input = data_json[\"data\"] if isinstance(data_json, dict) and \"data\" in data_json else data_json\n validate_jq_program(self.query)\n results = jq.compile(self.query).input(jq_input).all()\n if not results:\n msg = \"No result from JSON query.\"\n raise ValueError(msg)\n result = results[0] if len(results) == 1 else results\n if result is None or result == \"None\":\n msg = \"JSON query returned null/None. Check if the path exists in your data.\"\n raise ValueError(msg)\n if isinstance(result, dict):\n return Data(data=result)\n return Data(data={\"result\": result})\n except (ValueError, TypeError, KeyError, json.JSONDecodeError) as e:\n logger.error(f\"JSON Query failed: {e}\")\n msg = f\"JSON Query error: {e}\"\n raise ValueError(msg) from e\n\n # ==================================================================\n # Table operations\n # ==================================================================\n def _get_primary_dataframe(self) -> DataFrame:\n \"\"\"Get the first DataFrame from input (handles both single and list inputs).\"\"\"\n if isinstance(self.df, list):\n return self.df[0].copy() if self.df else DataFrame()\n return self.df.copy()\n\n def _run_table_operation(self, operation: str) -> DataFrame:\n # Merge and Concatenate use their own inputs, not the primary df.\n if operation == \"Merge\":\n return self.merge_dataframes()\n if operation == \"Concatenate\":\n return self.concatenate_dataframes()\n\n df_copy = self._get_primary_dataframe()\n table_handlers = {\n \"Filter\": self.filter_rows_by_value,\n \"Sort\": self.sort_by_column,\n \"Drop Column\": self.drop_column,\n \"Rename Column\": self.rename_column,\n \"Add Column\": self.add_column,\n \"Select Columns\": self.select_columns,\n \"Head\": self.head,\n \"Tail\": self.tail,\n \"Replace Value\": self.replace_values,\n \"Drop Duplicates\": self.drop_duplicates,\n }\n handler = table_handlers.get(operation)\n if handler is None:\n msg = f\"Unsupported operation: {operation}\"\n logger.error(msg)\n raise ValueError(msg)\n return handler(df_copy)\n\n @staticmethod\n def _comparable_filter_value(column: pd.Series, filter_value: Any) -> Any:\n \"\"\"Return a text input as a number when the column is numeric.\n\n Filter and Replace Value inputs arrive as text, and ``30 == \"30\"`` never matches in pandas.\n A blank input stays text: ``pd.to_numeric(\"\")`` is NaN, which would match missing cells.\n \"\"\"\n if filter_value in (None, \"\"):\n return filter_value\n if pd.api.types.is_numeric_dtype(column) and not pd.api.types.is_bool_dtype(column):\n try:\n return pd.to_numeric(filter_value)\n except (ValueError, TypeError):\n return filter_value\n return filter_value\n\n def filter_rows_by_value(self, df: DataFrame) -> DataFrame:\n column = df[self.column_name]\n filter_value = self.filter_value\n operator = getattr(self, \"filter_operator\", \"equals\")\n\n if operator == \"equals\":\n mask = column == self._comparable_filter_value(column, filter_value)\n elif operator == \"not equals\":\n mask = column != self._comparable_filter_value(column, filter_value)\n elif operator == \"contains\":\n mask = column.astype(str).str.contains(str(filter_value), na=False)\n elif operator == \"not contains\":\n mask = ~column.astype(str).str.contains(str(filter_value), na=False)\n elif operator == \"starts with\":\n mask = column.astype(str).str.startswith(str(filter_value), na=False)\n elif operator == \"ends with\":\n mask = column.astype(str).str.endswith(str(filter_value), na=False)\n elif operator == \"greater than\":\n try:\n numeric_value = pd.to_numeric(filter_value)\n mask = column > numeric_value\n except (ValueError, TypeError):\n mask = column.astype(str) > str(filter_value)\n elif operator == \"less than\":\n try:\n numeric_value = pd.to_numeric(filter_value)\n mask = column < numeric_value\n except (ValueError, TypeError):\n mask = column.astype(str) < str(filter_value)\n else:\n mask = column == self._comparable_filter_value(column, filter_value)\n\n return DataFrame(df[mask])\n\n def sort_by_column(self, df: DataFrame) -> DataFrame:\n return DataFrame(df.sort_values(by=self.column_name, ascending=self.ascending))\n\n def drop_column(self, df: DataFrame) -> DataFrame:\n return DataFrame(df.drop(columns=[self.column_name]))\n\n def rename_column(self, df: DataFrame) -> DataFrame:\n return DataFrame(df.rename(columns={self.column_name: self.new_column_name}))\n\n def add_column(self, df: DataFrame) -> DataFrame:\n df[self.new_column_name] = [self.new_column_value] * len(df)\n return DataFrame(df)\n\n def select_columns(self, df: DataFrame) -> DataFrame:\n columns = [col.strip() for col in self.columns_to_select]\n return DataFrame(df[columns])\n\n def head(self, df: DataFrame) -> DataFrame:\n return DataFrame(df.head(self.num_rows))\n\n def tail(self, df: DataFrame) -> DataFrame:\n return DataFrame(df.tail(self.num_rows))\n\n def replace_values(self, df: DataFrame) -> DataFrame:\n column = df[self.column_name]\n replace_val = self._comparable_filter_value(column, self.replace_value)\n replacement_val = self._comparable_filter_value(column, self.replacement_value)\n try:\n result = column.replace(replace_val, replacement_val)\n except TypeError:\n if not (\n isinstance(column.dtype, pd.api.extensions.ExtensionDtype)\n and pd.api.types.is_integer_dtype(column.dtype)\n ):\n raise\n # Nullable integers reject fractional/text replacements instead of widening like NumPy columns.\n widened = column.astype(\"Float64\" if pd.api.types.is_float(replacement_val) else object)\n # A float cannot represent every Int64 value. Preserve unrelated large integers exactly.\n if not widened.astype(object).equals(column.astype(object)):\n widened = column.astype(object)\n result = widened.mask(column.eq(replace_val).fillna(value=False), replacement_val)\n df[self.column_name] = result\n return DataFrame(df)\n\n def drop_duplicates(self, df: DataFrame) -> DataFrame:\n return DataFrame(df.drop_duplicates(subset=self.column_name))\n\n def concatenate_dataframes(self) -> DataFrame:\n \"\"\"Concatenate multiple DataFrames vertically (stack rows).\"\"\"\n if not isinstance(self.df, list) or len(self.df) == 0:\n return self.df.copy() if self.df is not None else DataFrame()\n\n if len(self.df) == 1:\n return self.df[0].copy()\n\n concatenated = pd.concat(self.df, ignore_index=True)\n return DataFrame(concatenated)\n\n def merge_dataframes(self) -> DataFrame:\n \"\"\"Merge two DataFrames based on a common column (join operation).\"\"\"\n left_df = getattr(self, \"left_dataframe\", None)\n right_df = getattr(self, \"right_dataframe\", None)\n\n if left_df is None:\n return DataFrame()\n if right_df is None:\n return left_df.copy()\n\n df_left = left_df.copy()\n df_right = right_df.copy()\n\n merge_on = getattr(self, \"merge_on_column\", None)\n merge_how = getattr(self, \"merge_how\", \"inner\")\n\n # Track only columns created by this merge, without colliding with input names.\n right_columns = {}\n used_columns = set(df_left.columns) | set(df_right.columns)\n for col in df_left.columns.intersection(df_right.columns):\n if merge_on and col == merge_on:\n continue\n right_col = f\"{col}_right\"\n while right_col in used_columns:\n right_col += \"_right\"\n right_columns[col] = right_col\n used_columns.add(right_col)\n df_right = df_right.rename(columns=right_columns)\n\n if merge_on:\n if merge_on not in df_left.columns:\n msg = f\"Column '{merge_on}' not found in left DataFrame. Available: {list(df_left.columns)}\"\n raise ValueError(msg)\n if merge_on not in df_right.columns:\n msg = f\"Column '{merge_on}' not found in right DataFrame. Available: {list(df_right.columns)}\"\n raise ValueError(msg)\n merged = df_left.merge(df_right, on=merge_on, how=merge_how)\n else:\n merged = df_left.merge(df_right, left_index=True, right_index=True, how=merge_how)\n\n cols_to_drop = []\n for col, right_col in right_columns.items():\n merged[col] = merged[col].combine_first(merged[right_col])\n cols_to_drop.append(right_col)\n\n if cols_to_drop:\n merged = merged.drop(columns=cols_to_drop)\n\n return DataFrame(merged)\n\n # ==================================================================\n # Text operations\n # ==================================================================\n def _run_text_operation(self) -> Any:\n \"\"\"Process text based on the selected operation (Message/Text outputs).\"\"\"\n text = getattr(self, \"text_input\", \"\")\n operation = self._operation_name()\n\n # Allow empty text for Text Join (second input may have content).\n if not text and operation != \"Text Join\":\n return None\n\n text_handlers = {\n \"Case Conversion\": self._case_conversion,\n \"Text Replace\": self._text_replace,\n \"Text Extract\": self._text_extract,\n \"Text Head\": self._text_head,\n \"Text Tail\": self._text_tail,\n \"Text Strip\": self._text_strip,\n \"Text Join\": self._text_join,\n \"Text Clean\": self._text_clean,\n }\n handler = text_handlers.get(operation)\n if handler:\n return handler(text)\n return text\n\n def _word_count_data(self) -> Data:\n \"\"\"Word Count operation result as a Data object.\"\"\"\n result = self._word_count(getattr(self, \"text_input\", \"\") or \"\")\n return Data(data=result)\n\n def _word_count(self, text: str) -> dict[str, Any]:\n \"\"\"Count words, characters, and lines in text.\"\"\"\n result: dict[str, Any] = {}\n text_str = str(text) if text else \"\"\n is_empty = not text_str or not text_str.strip()\n\n if getattr(self, \"count_words\", True):\n if is_empty:\n result[\"word_count\"] = 0\n result[\"unique_words\"] = 0\n else:\n words = text_str.split()\n result[\"word_count\"] = len(words)\n result[\"unique_words\"] = len(set(words))\n\n if getattr(self, \"count_characters\", True):\n if is_empty:\n result[\"character_count\"] = 0\n result[\"character_count_no_spaces\"] = 0\n else:\n result[\"character_count\"] = len(text_str)\n result[\"character_count_no_spaces\"] = len(text_str.replace(\" \", \"\"))\n\n if getattr(self, \"count_lines\", True):\n if is_empty:\n result[\"line_count\"] = 0\n result[\"non_empty_lines\"] = 0\n else:\n lines = text_str.split(\"\\n\")\n result[\"line_count\"] = len(lines)\n result[\"non_empty_lines\"] = len([line for line in lines if line.strip()])\n\n return result\n\n def _text_to_dataframe(self, text: str) -> DataFrame:\n \"\"\"Convert markdown-style table text to a DataFrame.\"\"\"\n lines = [line.strip() for line in text.strip().split(\"\\n\") if line.strip()]\n if not lines:\n return DataFrame(pd.DataFrame())\n\n separator = getattr(self, \"table_separator\", \"|\")\n has_header = getattr(self, \"has_header\", True)\n\n rows = self._parse_table_rows(lines, separator, has_header=has_header)\n if not rows:\n return DataFrame(pd.DataFrame())\n\n df = self._create_dataframe(rows, has_header=has_header)\n self._convert_numeric_columns(df)\n self.log(f\"Converted text to DataFrame: {len(df)} rows, {len(df.columns)} columns\")\n return DataFrame(df)\n\n def _parse_table_rows(self, lines: list[str], separator: str, *, has_header: bool = True) -> list[list[str]]:\n rows = []\n for index, line in enumerate(lines):\n cleaned_line = line.strip(separator)\n cells = [cell.strip() for cell in cleaned_line.split(separator)]\n # Skip the markdown delimiter row under the header instead of reading it as data.\n if has_header and index == 1 and all(MARKDOWN_DELIMITER_CELL.fullmatch(cell) for cell in cells):\n continue\n rows.append(cells)\n return rows\n\n def _create_dataframe(self, rows: list[list[str]], *, has_header: bool) -> pd.DataFrame:\n if has_header and rows:\n header = rows[0]\n data_rows = rows[1:]\n header_col_count = len(header)\n for i, row in enumerate(data_rows):\n row_col_count = len(row)\n if row_col_count != header_col_count:\n msg = (\n f\"Header mismatch: {header_col_count} column(s) in header vs \"\n f\"{row_col_count} column(s) in data row {i + 1}. \"\n \"Please ensure the header has the same number of columns as your data.\"\n )\n raise ValueError(msg)\n return pd.DataFrame(data_rows, columns=header)\n\n max_cols = max(len(row) for row in rows) if rows else 0\n columns = [f\"col_{i}\" for i in range(max_cols)]\n return pd.DataFrame(rows, columns=columns)\n\n def _convert_numeric_columns(self, df: pd.DataFrame) -> None:\n for col in df.columns:\n with contextlib.suppress(ValueError, TypeError):\n df[col] = pd.to_numeric(df[col])\n\n def _case_conversion(self, text: str) -> str:\n case_type = getattr(self, \"case_type\", \"lowercase\")\n converter = CASE_CONVERTERS.get(case_type)\n return converter(text) if converter else text\n\n def _text_replace(self, text: str) -> str:\n search_pattern = getattr(self, \"search_pattern\", \"\")\n if not search_pattern:\n return text\n replacement_text = getattr(self, \"replacement_text\", \"\")\n use_regex = getattr(self, \"use_regex\", False)\n if use_regex:\n try:\n return re.sub(search_pattern, replacement_text, text)\n except re.error as e:\n self.log(f\"Invalid regex pattern: {e}\")\n return text\n return text.replace(search_pattern, replacement_text)\n\n def _text_extract(self, text: str) -> list[str]:\n extract_pattern = getattr(self, \"extract_pattern\", \"\")\n if not extract_pattern:\n return []\n max_matches = getattr(self, \"max_matches\", 10)\n try:\n matches = re.findall(extract_pattern, text)\n except re.error as e:\n msg = f\"Invalid regex pattern '{extract_pattern}': {e}\"\n raise ValueError(msg) from e\n return matches[:max_matches] if max_matches > 0 else matches\n\n def _text_head(self, text: str) -> str:\n head_characters = getattr(self, \"head_characters\", 100)\n if head_characters < 0:\n msg = f\"Characters from Start must be a non-negative integer, got {head_characters}\"\n raise ValueError(msg)\n if head_characters == 0:\n return \"\"\n return text[:head_characters]\n\n def _text_tail(self, text: str) -> str:\n tail_characters = getattr(self, \"tail_characters\", 100)\n if tail_characters < 0:\n msg = f\"Characters from End must be a non-negative integer, got {tail_characters}\"\n raise ValueError(msg)\n if tail_characters == 0:\n return \"\"\n return text[-tail_characters:]\n\n def _text_strip(self, text: str) -> str:\n strip_mode = getattr(self, \"strip_mode\", \"both\")\n strip_characters = getattr(self, \"strip_characters\", \"\")\n text_str = str(text) if text else \"\"\n chars_to_strip = strip_characters if strip_characters else None\n if strip_mode == \"left\":\n return text_str.lstrip(chars_to_strip)\n if strip_mode == \"right\":\n return text_str.rstrip(chars_to_strip)\n return text_str.strip(chars_to_strip)\n\n def _text_join(self, text: str) -> str:\n text_input_2 = getattr(self, \"text_input_2\", \"\")\n text1 = str(text) if text else \"\"\n text2 = str(text_input_2) if text_input_2 else \"\"\n if text1 and text2:\n return f\"{text1}\\n{text2}\"\n return text1 or text2\n\n def _text_clean(self, text: str) -> str:\n result = text\n if getattr(self, \"remove_extra_spaces\", True):\n # Collapse runs of horizontal whitespace but preserve newlines so\n # that remove_empty_lines stays effective when both are enabled.\n result = re.sub(r\"[^\\S\\n]+\", \" \", result)\n if getattr(self, \"remove_special_chars\", False):\n result = re.sub(r\"[^\\w\\s]\", \"\", result)\n if getattr(self, \"remove_empty_lines\", False):\n lines = [line for line in result.split(\"\\n\") if line.strip()]\n result = \"\\n\".join(lines)\n return result\n\n def _format_result_as_text(self, result: Any) -> str:\n if result is None:\n return \"\"\n if isinstance(result, list):\n return \"\\n\".join(str(item) for item in result)\n return str(result)\n"
},
"column_name": {
"_input_type": "StrInput",
@@ -5383,13 +5377,9 @@
},
"dragging": false,
"id": "Operations-fX1Im",
- "measured": {
- "height": 52,
- "width": 192
- },
"position": {
- "x": 1701.888054410499,
- "y": 1622.9090207014667
+ "x": 1696.1008768721936,
+ "y": 1631.0110692550945
},
"selected": false,
"type": "genericNode"
@@ -5589,10 +5579,6 @@
},
"dragging": false,
"id": "OpenAICompatibleEmbedding-aIHce",
- "measured": {
- "height": 52,
- "width": 192
- },
"position": {
"x": 2026.2607693884997,
"y": 1754.074435768159
@@ -6515,10 +6501,6 @@
},
"dragging": false,
"id": "OpenSearchVectorStoreComponentMultimodalMultiEmbedding-dihKf",
- "measured": {
- "height": 188,
- "width": 192
- },
"position": {
"x": 2376.807670689636,
"y": 1551.0689633093473
@@ -6795,10 +6777,6 @@
},
"dragging": false,
"id": "ext:openrag:OpenRAGSplitTextComponent@extra-tutKN",
- "measured": {
- "height": 80,
- "width": 192
- },
"position": {
"x": 2035.3566968494886,
"y": 1554.1985641894335
@@ -6808,16 +6786,16 @@
}
],
"viewport": {
- "x": -600.99465524025,
- "y": -544.8939772193618,
- "zoom": 0.5452796392357185
+ "x": -831.1883903909913,
+ "y": -745.811554662029,
+ "zoom": 0.6547736597321486
}
},
"description": "This flow is to ingest the URL to open search.",
"endpoint_name": null,
"id": "72c3d17c-2dac-4a73-b48a-6518473d7830",
"is_component": false,
- "last_tested_version": "1.12.3",
+ "last_tested_version": "1.12.8",
"mcp_enabled": true,
"locked": true,
"name": "OpenSearch URL Ingestion Flow",
diff --git a/tests/integration/core/test_mcp_url_ingest.py b/tests/integration/core/test_mcp_url_ingest.py
index 1c4d8b66f..2124557ee 100644
--- a/tests/integration/core/test_mcp_url_ingest.py
+++ b/tests/integration/core/test_mcp_url_ingest.py
@@ -6,6 +6,7 @@ import pytest
OPENRAG_MCP_SERVER_NAME = "lf-starter_project"
LANGFLOW_GLOBAL_VAR_PREFIX = "x-langflow-global-var-"
+MCP_CREDENTIAL_MASK = "********"
async def _wait_for_langflow_client(timeout_s: float = 60.0):
@@ -63,12 +64,13 @@ def _extract_server_headers(server_config: dict[str, Any]) -> dict[str, str]:
return headers
-def _assert_has_required_global_headers(headers: dict[str, str]) -> None:
+def _assert_has_redacted_required_global_headers(headers: dict[str, str]) -> None:
from services.langflow_mcp_service import REQUIRED_MCP_HEADERS
- for key, expected_val in REQUIRED_MCP_HEADERS.items():
- assert headers.get(key) == expected_val, (
- f"Expected header {key}={expected_val!r} in MCP server headers, got {headers.get(key)!r}"
+ for key in REQUIRED_MCP_HEADERS:
+ assert headers.get(key) == MCP_CREDENTIAL_MASK, (
+ f"Expected required MCP header {key} to be redacted in the Langflow response, "
+ f"got {headers.get(key)!r}"
)
@@ -102,7 +104,7 @@ async def test_openrag_mcp_server_url_is_patched_without_persisting_request_glob
f"MCP server URLs were not rewritten to LANGFLOW_URL={expected_base!r}: {urls}"
)
- _assert_has_required_global_headers(_extract_server_headers(server_config))
+ _assert_has_redacted_required_global_headers(_extract_server_headers(server_config))
@pytest.mark.asyncio