Skip to content

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

Python

fix: update flows to latest version, update url ingestion (#1742)

Lucas Oliveira3b2c8fd27cd3
diff --git a/Makefile b/Makefile
index d8ce272b4..b565f9d09 100644
--- a/Makefile
+++ b/Makefile
@@ -428,7 +428,7 @@ dev-cpu: ensure-langflow-data ensure-backend-volumes ## Start full stack with CP
dev-local: ensure-langflow-data ensure-backend-volumes ## Start infrastructure for local development
@echo "$(YELLOW)Starting infrastructure only (for local development)...$(NC)"
- $(COMPOSE_CMD) -f docker-compose.yml -f docker-compose.gpu.yml up -d opensearch openrag-backend dashboards langflow
+ $(COMPOSE_CMD) -f docker-compose.yml -f docker-compose.gpu.yml -f docker-compose.host-backend.yml up -d opensearch openrag-backend dashboards langflow
@echo "$(PURPLE)Infrastructure started!$(NC)"
@echo " $(CYAN)Backend:$(NC) http://openrag-backend"
@echo " $(CYAN)Langflow:$(NC) http://localhost:7860"
@@ -439,7 +439,7 @@ dev-local: ensure-langflow-data ensure-backend-volumes ## Start infrastructure f
dev-local-cpu: ensure-langflow-data ensure-backend-volumes ## Start infrastructure for local development, with CPU only
@echo "$(YELLOW)Starting infrastructure only (for local development)...$(NC)"
- $(COMPOSE_CMD) up -d opensearch openrag-backend dashboards langflow
+ $(COMPOSE_CMD) -f docker-compose.yml -f docker-compose.host-backend.yml up -d opensearch openrag-backend dashboards langflow
@echo "$(PURPLE)Infrastructure started!$(NC)"
@echo " $(CYAN)Backend:$(NC) http://openrag-backend"
@echo " $(CYAN)Langflow:$(NC) http://localhost:7860"
@@ -452,7 +452,7 @@ dev-local-build-lf: ensure-langflow-data ensure-backend-volumes ## Start infrast
@echo "$(YELLOW)Building Langflow image...$(NC)"
$(COMPOSE_CMD) -f docker-compose.yml -f docker-compose.gpu.yml build langflow
@echo "$(YELLOW)Starting infrastructure only (for local development)...$(NC)"
- $(COMPOSE_CMD) -f docker-compose.yml -f docker-compose.gpu.yml up -d opensearch openrag-backend dashboards langflow
+ $(COMPOSE_CMD) -f docker-compose.yml -f docker-compose.gpu.yml -f docker-compose.host-backend.yml up -d opensearch openrag-backend dashboards langflow
@echo "$(PURPLE)Infrastructure started!$(NC)"
@echo " $(CYAN)Backend:$(NC) http://openrag-backend"
@echo " $(CYAN)Langflow:$(NC) http://localhost:7860"
@@ -463,9 +463,9 @@ dev-local-build-lf: ensure-langflow-data ensure-backend-volumes ## Start infrast
dev-local-build-lf-cpu: ensure-langflow-data ensure-backend-volumes ## Start infrastructure for local development, building only Langflow image with CPU only
@echo "$(YELLOW)Building Langflow image (CPU)...$(NC)"
- $(COMPOSE_CMD) build langflow
+ $(COMPOSE_CMD) -f docker-compose.yml -f docker-compose.host-backend.yml build langflow
@echo "$(YELLOW)Starting infrastructure only (for local development)...$(NC)"
- $(COMPOSE_CMD) up -d opensearch openrag-backend dashboards langflow
+ $(COMPOSE_CMD) -f docker-compose.yml -f docker-compose.host-backend.yml up -d opensearch openrag-backend dashboards langflow
@echo "$(PURPLE)Infrastructure started!$(NC)"
@echo " $(CYAN)Backend:$(NC) http://openrag-backend"
@echo " $(CYAN)Langflow:$(NC) http://localhost:7860"
diff --git a/flows/ingestion_flow.json b/flows/ingestion_flow.json
index 5fc809c84..e48ed7be1 100644
--- a/flows/ingestion_flow.json
+++ b/flows/ingestion_flow.json
@@ -579,6 +579,7 @@
],
"frozen": false,
"icon": "Docling",
+ "last_updated": "2026-06-02T20:40:57.828Z",
"legacy": false,
"metadata": {
"code_hash": "dcf9aeedd059",
@@ -629,6 +630,12 @@
],
"pinned": false,
"template": {
+ "_frontend_node_flow_id": {
+ "value": "5488df7c-b93f-4f87-a446-b67028bc0813"
+ },
+ "_frontend_node_folder_id": {
+ "value": "dcac372c-a803-4877-8e1a-83e9adcd2972"
+ },
"_type": "Component",
"api_headers": {
"_input_type": "TableInput",
@@ -676,10 +683,16 @@
"type": "table",
"value": [
{
+ "__load_from_db_fields": {
+ "value": true
+ },
"key": "Authorization",
"value": "JWT"
},
{
+ "__load_from_db_fields": {
+ "value": true
+ },
"key": "X-Tenant-Id",
"value": "OWNER"
}
@@ -772,7 +785,7 @@
"do_picture_classification": false,
"do_picture_description": false,
"do_table_structure": true,
- "ocr_engine": "ocrmac",
+ "ocr_engine": "easyocr",
"picture_description_local": {
"prompt": "Describe this image in a few sentences.",
"repo_id": "HuggingFaceTB/SmolVLM-256M-Instruct"
@@ -843,6 +856,7 @@
"type": "bool",
"value": true
},
+ "is_refresh": false,
"max_concurrency": {
"_input_type": "IntInput",
"advanced": true,
@@ -4022,7 +4036,7 @@
"value": "5488df7c-b93f-4f87-a446-b67028bc0813"
},
"_frontend_node_folder_id": {
- "value": "2be9efb3-6f08-4dee-9d08-1747bd9c33ee"
+ "value": "dcac372c-a803-4877-8e1a-83e9adcd2972"
},
"_type": "Component",
"api_base": {
@@ -4550,7 +4564,7 @@
"value": "5488df7c-b93f-4f87-a446-b67028bc0813"
},
"_frontend_node_folder_id": {
- "value": "2be9efb3-6f08-4dee-9d08-1747bd9c33ee"
+ "value": "dcac372c-a803-4877-8e1a-83e9adcd2972"
},
"_type": "Component",
"api_base": {
@@ -5078,7 +5092,7 @@
"value": "5488df7c-b93f-4f87-a446-b67028bc0813"
},
"_frontend_node_folder_id": {
- "value": "2be9efb3-6f08-4dee-9d08-1747bd9c33ee"
+ "value": "dcac372c-a803-4877-8e1a-83e9adcd2972"
},
"_type": "Component",
"api_base": {
@@ -5530,16 +5544,16 @@
}
],
"viewport": {
- "x": 88.5162499041611,
- "y": -383.79779651448473,
- "zoom": 0.39626280960074645
+ "x": 91.09392360442735,
+ "y": -726.3579579832333,
+ "zoom": 0.6220209268560802
}
},
"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": "1.9.0",
+ "last_tested_version": "1.9.6",
"locked": true,
"name": "OpenSearch Ingestion Flow",
"tags": [
diff --git a/flows/openrag_agent.json b/flows/openrag_agent.json
index da40458ff..0d7622ec4 100644
--- a/flows/openrag_agent.json
+++ b/flows/openrag_agent.json
@@ -984,10 +984,10 @@
],
"frozen": false,
"icon": "bot",
- "last_updated": "2026-04-17T22:36:44.494Z",
+ "last_updated": "2026-06-02T20:39:35.580Z",
"legacy": false,
"metadata": {
- "code_hash": "154c71cf7441",
+ "code_hash": "3c0fdab9e061",
"dependencies": {
"dependencies": [
{
@@ -996,11 +996,11 @@
},
{
"name": "lfx",
- "version": "0.4.0"
+ "version": "0.4.6"
},
{
"name": "langchain_core",
- "version": "1.2.29"
+ "version": "1.4.0"
}
],
"total_dependencies": 3
@@ -1037,7 +1037,7 @@
},
"_frontend_node_folder_id": {
"input_types": [],
- "value": "ef261332-778a-4347-96bc-99b4207d86b1"
+ "value": "38bb3005-a7d5-4eac-8a7f-433d69e4ad1e"
},
"_type": "Component",
"add_current_date_tool": {
@@ -1161,7 +1161,7 @@
"show": true,
"title_case": false,
"type": "code",
- "value": "from __future__ import annotations\n\nimport json\nimport re\nfrom typing import TYPE_CHECKING\n\nfrom pydantic import ValidationError\n\nfrom lfx.components.models_and_agents.memory import MemoryComponent\n\nif TYPE_CHECKING:\n from langchain_core.tools import Tool\n\nfrom lfx.base.agents.agent import LCToolsAgentComponent\nfrom lfx.base.agents.events import ExceptionWithMessageError\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 CurrentDateComponent\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.helpers.base_model import build_model_from_schema\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.schema.data import Data\nfrom lfx.schema.dotdict import dotdict\nfrom lfx.schema.message import Message\nfrom lfx.schema.table import EditMode\n\n\ndef set_advanced_true(component_input):\n component_input.advanced = True\n return component_input\n\n\nclass AgentComponent(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 ),\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=\"System Prompt: Initial instructions and context provided to guide the agent's behavior.\",\n value=\"You are a helpful assistant that can use tools to answer questions and perform tasks.\",\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. Field name varies by provider.\",\n advanced=True,\n range_spec=RangeSpec(min=1, 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 *LCToolsAgentComponent.get_base_inputs(),\n # removed memory inputs from agent component\n # *memory_inputs,\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 ]\n outputs = [\n Output(name=\"response\", display_name=\"Response\", method=\"message_response\"),\n ]\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 return get_llm(\n model=self.model,\n user_id=self.user_id,\n api_key=getattr(self, \"api_key\", None),\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 )\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 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 self.tools.append(current_date_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 async def message_response(self) -> Message:\n try:\n llm_model, self.chat_history, self.tools = await self.get_agent_requirements()\n # Set up and run agent\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.system_prompt,\n )\n agent = self.create_agent_runnable()\n result = await self.run_agent(agent)\n\n # Store result for potential JSON output\n self._agent_result = result\n\n except (ValueError, TypeError, KeyError) as e:\n await logger.aerror(f\"{type(e).__name__}: {e!s}\")\n raise\n except ExceptionWithMessageError as e:\n await logger.aerror(f\"ExceptionWithMessageError occurred: {e}\")\n raise\n # Avoid catching blind Exception; let truly unexpected exceptions propagate\n except Exception as e:\n await logger.aerror(f\"Unexpected error: {e!s}\")\n raise\n else:\n return result\n\n def _preprocess_schema(self, schema):\n \"\"\"Preprocess schema to ensure correct data types for build_model_from_schema.\"\"\"\n processed_schema = []\n for field in schema:\n processed_field = {\n \"name\": str(field.get(\"name\", \"field\")),\n \"type\": str(field.get(\"type\", \"str\")),\n \"description\": str(field.get(\"description\", \"\")),\n \"multiple\": field.get(\"multiple\", False),\n }\n # Ensure multiple is handled correctly\n if isinstance(processed_field[\"multiple\"], str):\n processed_field[\"multiple\"] = processed_field[\"multiple\"].lower() in [\n \"true\",\n \"1\",\n \"t\",\n \"y\",\n \"yes\",\n ]\n processed_schema.append(processed_field)\n return processed_schema\n\n async def build_structured_output_base(self, content: str):\n \"\"\"Build structured output with optional BaseModel validation.\"\"\"\n json_pattern = r\"\\{.*\\}\"\n schema_error_msg = \"Try setting an output schema\"\n\n # Try to parse content as JSON first\n json_data = None\n try:\n json_data = json.loads(content)\n except json.JSONDecodeError:\n json_match = re.search(json_pattern, content, re.DOTALL)\n if json_match:\n try:\n json_data = json.loads(json_match.group())\n except json.JSONDecodeError:\n return {\"content\": content, \"error\": schema_error_msg}\n else:\n return {\"content\": content, \"error\": schema_error_msg}\n\n # If no output schema provided, return parsed JSON without validation\n if not hasattr(self, \"output_schema\") or not self.output_schema or len(self.output_schema) == 0:\n return json_data\n\n # Use BaseModel validation with schema\n try:\n processed_schema = self._preprocess_schema(self.output_schema)\n output_model = build_model_from_schema(processed_schema)\n\n # Validate against the schema\n if isinstance(json_data, list):\n # Multiple objects\n validated_objects = []\n for item in json_data:\n try:\n validated_obj = output_model.model_validate(item)\n validated_objects.append(validated_obj.model_dump())\n except ValidationError as e:\n await logger.aerror(f\"Validation error for item: {e}\")\n # Include invalid items with error info\n validated_objects.append({\"data\": item, \"validation_error\": str(e)})\n return validated_objects\n\n # Single object\n try:\n validated_obj = output_model.model_validate(json_data)\n return [validated_obj.model_dump()] # Return as list for consistency\n except ValidationError as e:\n await logger.aerror(f\"Validation error: {e}\")\n return [{\"data\": json_data, \"validation_error\": str(e)}]\n\n except (TypeError, ValueError) as e:\n await logger.aerror(f\"Error building structured output: {e}\")\n # Fallback to parsed JSON without validation\n return json_data\n\n async def json_response(self) -> Data:\n \"\"\"Convert agent response to structured JSON Data output with schema validation.\"\"\"\n # Always use structured chat agent for JSON response mode for better JSON formatting\n try:\n system_components = []\n\n # 1. Agent Instructions (system_prompt)\n agent_instructions = getattr(self, \"system_prompt\", \"\") or \"\"\n if agent_instructions:\n system_components.append(f\"{agent_instructions}\")\n\n # 2. Format Instructions\n format_instructions = getattr(self, \"format_instructions\", \"\") or \"\"\n if format_instructions:\n system_components.append(f\"Format instructions: {format_instructions}\")\n\n # 3. Schema Information from BaseModel\n if hasattr(self, \"output_schema\") and self.output_schema and len(self.output_schema) > 0:\n try:\n processed_schema = self._preprocess_schema(self.output_schema)\n output_model = build_model_from_schema(processed_schema)\n schema_dict = output_model.model_json_schema()\n schema_info = (\n \"You are given some text that may include format instructions, \"\n \"explanations, or other content alongside a JSON schema.\\n\\n\"\n \"Your task:\\n\"\n \"- Extract only the JSON schema.\\n\"\n \"- Return it as valid JSON.\\n\"\n \"- Do not include format instructions, explanations, or extra text.\\n\\n\"\n \"Input:\\n\"\n f\"{json.dumps(schema_dict, indent=2)}\\n\\n\"\n \"Output (only JSON schema):\"\n )\n system_components.append(schema_info)\n except (ValidationError, ValueError, TypeError, KeyError) as e:\n await logger.aerror(f\"Could not build schema for prompt: {e}\", exc_info=True)\n\n # Combine all components\n combined_instructions = \"\\n\\n\".join(system_components) if system_components 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=combined_instructions,\n )\n\n # Create and run structured chat agent\n try:\n structured_agent = self.create_agent_runnable()\n except (NotImplementedError, ValueError, TypeError) as e:\n await logger.aerror(f\"Error with structured chat agent: {e}\")\n raise\n try:\n result = await self.run_agent(structured_agent)\n except (\n ExceptionWithMessageError,\n ValueError,\n TypeError,\n RuntimeError,\n ) as e:\n await logger.aerror(f\"Error with structured agent result: {e}\")\n raise\n # Extract content from structured agent result\n if hasattr(result, \"content\"):\n content = result.content\n elif hasattr(result, \"text\"):\n content = result.text\n else:\n content = str(result)\n\n except (\n ExceptionWithMessageError,\n ValueError,\n TypeError,\n NotImplementedError,\n AttributeError,\n ) as e:\n await logger.aerror(f\"Error with structured chat agent: {e}\")\n # Fallback to regular agent\n content_str = \"No content returned from agent\"\n return Data(data={\"content\": content_str, \"error\": str(e)})\n\n # Process with structured output validation\n try:\n structured_output = await self.build_structured_output_base(content)\n\n # Handle different output formats\n if isinstance(structured_output, list) and structured_output:\n if len(structured_output) == 1:\n return Data(data=structured_output[0])\n return Data(data={\"results\": structured_output})\n if isinstance(structured_output, dict):\n return Data(data=structured_output)\n return Data(data={\"content\": content})\n\n except (ValueError, TypeError) as e:\n await logger.aerror(f\"Error in structured output processing: {e}\")\n return Data(data={\"content\": content, \"error\": str(e)})\n\n async def get_memory_data(self):\n # TODO: This is a temporary fix to avoid message duplication. We should develop a function for this.\n messages = (\n await MemoryComponent(**self.get_base_args())\n .set(\n session_id=self.graph.session_id,\n context_id=self.context_id,\n order=\"Ascending\",\n n_messages=self.n_messages,\n )\n .retrieve_messages()\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 # Update model options with caching (for all field changes)\n # Agents require tool calling, so filter for only tool-calling capable models\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 cache_key_prefix=\"language_model_options_tool_calling\",\n get_options_func=lambda user_id=None: get_language_model_options(user_id=user_id, tool_calling=True),\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\n default_keys = [\n \"code\",\n \"_type\",\n \"model\",\n \"tools\",\n \"input_value\",\n \"add_current_date_tool\",\n \"system_prompt\",\n \"agent_description\",\n \"max_iterations\",\n \"handle_parsing_errors\",\n \"verbose\",\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 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 tools_names = self._build_tools_names()\n agent_description = self.get_tool_description()\n # TODO: Agent Description Depreciated Feature to be removed\n description = f\"{agent_description}{tools_names}\"\n\n tools = component_toolkit(component=self).get_tools(\n tool_name=\"Call_Agent\",\n tool_description=description,\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 json\nimport re\nfrom typing import TYPE_CHECKING\n\nfrom pydantic import ValidationError\n\nfrom lfx.components.models_and_agents.memory import MemoryComponent\n\nif TYPE_CHECKING:\n from langchain_core.tools import Tool\n\nfrom lfx.base.agents.agent import LCToolsAgentComponent\nfrom lfx.base.agents.events import ExceptionWithMessageError\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 CurrentDateComponent\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.helpers.base_model import build_model_from_schema\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.schema.data import Data\nfrom lfx.schema.dotdict import dotdict\nfrom lfx.schema.message import Message\nfrom lfx.schema.table import EditMode\n\n\ndef set_advanced_true(component_input):\n component_input.advanced = True\n return component_input\n\n\nclass AgentComponent(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 ),\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=\"System Prompt: Initial instructions and context provided to guide the agent's behavior.\",\n value=\"You are a helpful assistant that can use tools to answer questions and perform tasks.\",\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. Field name varies by provider.\",\n advanced=True,\n range_spec=RangeSpec(min=1, 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 *LCToolsAgentComponent.get_base_inputs(),\n # removed memory inputs from agent component\n # *memory_inputs,\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 ]\n outputs = [\n Output(name=\"response\", display_name=\"Response\", method=\"message_response\"),\n ]\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 # Streaming is mandatory for the Agent: runnable.astream_events() only emits\n # on_chat_model_stream chunks when the underlying chat model is instantiated\n # with streaming=True. Unlike the LanguageModel component (where stream is a\n # user toggle), the Agent always streams so the Playground/API surface\n # receives tokens incrementally.\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 )\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 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 self.tools.append(current_date_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 async def message_response(self) -> Message:\n try:\n llm_model, self.chat_history, self.tools = await self.get_agent_requirements()\n # Set up and run agent\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.system_prompt,\n )\n agent = self.create_agent_runnable()\n result = await self.run_agent(agent)\n\n # Store result for potential JSON output\n self._agent_result = result\n\n except (ValueError, TypeError, KeyError) as e:\n await logger.aerror(f\"{type(e).__name__}: {e!s}\")\n raise\n except ExceptionWithMessageError as e:\n await logger.aerror(f\"ExceptionWithMessageError occurred: {e}\")\n raise\n # Avoid catching blind Exception; let truly unexpected exceptions propagate\n except Exception as e:\n await logger.aerror(f\"Unexpected error: {e!s}\")\n raise\n else:\n return result\n\n def _preprocess_schema(self, schema):\n \"\"\"Preprocess schema to ensure correct data types for build_model_from_schema.\"\"\"\n processed_schema = []\n for field in schema:\n processed_field = {\n \"name\": str(field.get(\"name\", \"field\")),\n \"type\": str(field.get(\"type\", \"str\")),\n \"description\": str(field.get(\"description\", \"\")),\n \"multiple\": field.get(\"multiple\", False),\n }\n # Ensure multiple is handled correctly\n if isinstance(processed_field[\"multiple\"], str):\n processed_field[\"multiple\"] = processed_field[\"multiple\"].lower() in [\n \"true\",\n \"1\",\n \"t\",\n \"y\",\n \"yes\",\n ]\n processed_schema.append(processed_field)\n return processed_schema\n\n async def build_structured_output_base(self, content: str):\n \"\"\"Build structured output with optional BaseModel validation.\"\"\"\n json_pattern = r\"\\{.*\\}\"\n schema_error_msg = \"Try setting an output schema\"\n\n # Try to parse content as JSON first\n json_data = None\n try:\n json_data = json.loads(content)\n except json.JSONDecodeError:\n json_match = re.search(json_pattern, content, re.DOTALL)\n if json_match:\n try:\n json_data = json.loads(json_match.group())\n except json.JSONDecodeError:\n return {\"content\": content, \"error\": schema_error_msg}\n else:\n return {\"content\": content, \"error\": schema_error_msg}\n\n # If no output schema provided, return parsed JSON without validation\n if not hasattr(self, \"output_schema\") or not self.output_schema or len(self.output_schema) == 0:\n return json_data\n\n # Use BaseModel validation with schema\n try:\n processed_schema = self._preprocess_schema(self.output_schema)\n output_model = build_model_from_schema(processed_schema)\n\n # Validate against the schema\n if isinstance(json_data, list):\n # Multiple objects\n validated_objects = []\n for item in json_data:\n try:\n validated_obj = output_model.model_validate(item)\n validated_objects.append(validated_obj.model_dump())\n except ValidationError as e:\n await logger.aerror(f\"Validation error for item: {e}\")\n # Include invalid items with error info\n validated_objects.append({\"data\": item, \"validation_error\": str(e)})\n return validated_objects\n\n # Single object\n try:\n validated_obj = output_model.model_validate(json_data)\n return [validated_obj.model_dump()] # Return as list for consistency\n except ValidationError as e:\n await logger.aerror(f\"Validation error: {e}\")\n return [{\"data\": json_data, \"validation_error\": str(e)}]\n\n except (TypeError, ValueError) as e:\n await logger.aerror(f\"Error building structured output: {e}\")\n # Fallback to parsed JSON without validation\n return json_data\n\n async def json_response(self) -> Data:\n \"\"\"Convert agent response to structured JSON Data output with schema validation.\"\"\"\n # Always use structured chat agent for JSON response mode for better JSON formatting\n try:\n system_components = []\n\n # 1. Agent Instructions (system_prompt)\n agent_instructions = getattr(self, \"system_prompt\", \"\") or \"\"\n if agent_instructions:\n system_components.append(f\"{agent_instructions}\")\n\n # 2. Format Instructions\n format_instructions = getattr(self, \"format_instructions\", \"\") or \"\"\n if format_instructions:\n system_components.append(f\"Format instructions: {format_instructions}\")\n\n # 3. Schema Information from BaseModel\n if hasattr(self, \"output_schema\") and self.output_schema and len(self.output_schema) > 0:\n try:\n processed_schema = self._preprocess_schema(self.output_schema)\n output_model = build_model_from_schema(processed_schema)\n schema_dict = output_model.model_json_schema()\n schema_info = (\n \"You are given some text that may include format instructions, \"\n \"explanations, or other content alongside a JSON schema.\\n\\n\"\n \"Your task:\\n\"\n \"- Extract only the JSON schema.\\n\"\n \"- Return it as valid JSON.\\n\"\n \"- Do not include format instructions, explanations, or extra text.\\n\\n\"\n \"Input:\\n\"\n f\"{json.dumps(schema_dict, indent=2)}\\n\\n\"\n \"Output (only JSON schema):\"\n )\n system_components.append(schema_info)\n except (ValidationError, ValueError, TypeError, KeyError) as e:\n await logger.aerror(f\"Could not build schema for prompt: {e}\", exc_info=True)\n\n # Combine all components\n combined_instructions = \"\\n\\n\".join(system_components) if system_components 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=combined_instructions,\n )\n\n # Create and run structured chat agent\n try:\n structured_agent = self.create_agent_runnable()\n except (NotImplementedError, ValueError, TypeError) as e:\n await logger.aerror(f\"Error with structured chat agent: {e}\")\n raise\n try:\n result = await self.run_agent(structured_agent)\n except (\n ExceptionWithMessageError,\n ValueError,\n TypeError,\n RuntimeError,\n ) as e:\n await logger.aerror(f\"Error with structured agent result: {e}\")\n raise\n # Extract content from structured agent result\n if hasattr(result, \"content\"):\n content = result.content\n elif hasattr(result, \"text\"):\n content = result.text\n else:\n content = str(result)\n\n except (\n ExceptionWithMessageError,\n ValueError,\n TypeError,\n NotImplementedError,\n AttributeError,\n ) as e:\n await logger.aerror(f\"Error with structured chat agent: {e}\")\n # Fallback to regular agent\n content_str = \"No content returned from agent\"\n return Data(data={\"content\": content_str, \"error\": str(e)})\n\n # Process with structured output validation\n try:\n structured_output = await self.build_structured_output_base(content)\n\n # Handle different output formats\n if isinstance(structured_output, list) and structured_output:\n if len(structured_output) == 1:\n return Data(data=structured_output[0])\n return Data(data={\"results\": structured_output})\n if isinstance(structured_output, dict):\n return Data(data=structured_output)\n return Data(data={\"content\": content})\n\n except (ValueError, TypeError) as e:\n await logger.aerror(f\"Error in structured output processing: {e}\")\n return Data(data={\"content\": content, \"error\": str(e)})\n\n async def get_memory_data(self):\n # TODO: This is a temporary fix to avoid message duplication. We should develop a function for this.\n messages = (\n await MemoryComponent(**self.get_base_args())\n .set(\n session_id=self.graph.session_id,\n context_id=self.context_id,\n order=\"Ascending\",\n n_messages=self.n_messages,\n )\n .retrieve_messages()\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 # Update model options with caching (for all field changes)\n # Agents require tool calling, so filter for only tool-calling capable models\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 cache_key_prefix=\"language_model_options_tool_calling\",\n get_options_func=lambda user_id=None: get_language_model_options(user_id=user_id, tool_calling=True),\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\n default_keys = [\n \"code\",\n \"_type\",\n \"model\",\n \"tools\",\n \"input_value\",\n \"add_current_date_tool\",\n \"system_prompt\",\n \"agent_description\",\n \"max_iterations\",\n \"handle_parsing_errors\",\n \"verbose\",\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 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 tools_names = self._build_tools_names()\n agent_description = self.get_tool_description()\n # TODO: Agent Description Depreciated Feature to be removed\n description = f\"{agent_description}{tools_names}\"\n\n tools = component_toolkit(component=self).get_tools(\n tool_name=\"Call_Agent\",\n tool_description=description,\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",
@@ -1683,6 +1683,7 @@
],
"frozen": false,
"icon": "calculator",
+ "last_updated": "2026-06-03T19:37:43.198Z",
"legacy": false,
"metadata": {
"code_hash": "d0b2936e74fa",
@@ -1721,6 +1722,12 @@
],
"pinned": false,
"template": {
+ "_frontend_node_flow_id": {
+ "value": "1098eea1-6649-4e1d-aed1-b77249fb8dd0"
+ },
+ "_frontend_node_folder_id": {
+ "value": "38bb3005-a7d5-4eac-8a7f-433d69e4ad1e"
+ },
"_type": "Component",
"code": {
"advanced": true,
@@ -1765,6 +1772,7 @@
"type": "str",
"value": ""
},
+ "is_refresh": false,
"tools_metadata": {
"_input_type": "ToolsInput",
"advanced": false,
@@ -1903,7 +1911,7 @@
"value": "1098eea1-6649-4e1d-aed1-b77249fb8dd0"
},
"_frontend_node_folder_id": {
- "value": "ef261332-778a-4347-96bc-99b4207d86b1"
+ "value": "38bb3005-a7d5-4eac-8a7f-433d69e4ad1e"
},
"_type": "Component",
"api_base": {
@@ -2372,9 +2380,11 @@
"description": "Store and search documents using OpenSearch with multi-model hybrid semantic and keyword search. To search use the tools search_documents and raw_search. Search documents takes a query for vector search, for example\n {search_query: \"components in openrag\"}",
"display_name": "OpenSearch (Multi-Model Multi-Embedding)",
"documentation": "",
- "edited": false,
+ "edited": true,
"field_order": [
"docs_metadata",
+ "openrag_ingest_token",
+ "openrag_ingest_run_id",
"opensearch_url",
"index_name",
"engine",
@@ -2399,31 +2409,38 @@
"use_ssl",
"verify_certs",
"request_timeout",
- "max_retries"
+ "max_retries",
+ "openrag_ingest_url",
+ "openrag_ingest_token",
+ "openrag_ingest_run_id",
+ "openrag_ingest_batch_size"
],
"frozen": false,
"icon": "OpenSearch",
- "last_updated": "2026-05-18T18:15:01.796Z",
+ "last_updated": "2026-06-03T19:37:43.198Z",
"legacy": false,
- "lf_version": "1.9.0",
"metadata": {
- "code_hash": "4a05432fb489",
+ "code_hash": "220fbf21a963",
"dependencies": {
"dependencies": [
{
- "name": "opensearchpy",
- "version": "2.8.0"
+ "name": "httpx",
+ "version": "0.28.1"
},
{
"name": "lfx",
- "version": null
+ "version": "0.4.6"
+ },
+ {
+ "name": "opensearchpy",
+ "version": "2.8.0"
},
{
"name": "tenacity",
"version": "8.5.0"
}
],
- "total_dependencies": 3
+ "total_dependencies": 4
},
"module": "custom_components.opensearch_multimodel_multiembedding"
},
@@ -2455,7 +2472,7 @@
"value": "1098eea1-6649-4e1d-aed1-b77249fb8dd0"
},
"_frontend_node_folder_id": {
- "value": "ef261332-778a-4347-96bc-99b4207d86b1"
+ "value": "38bb3005-a7d5-4eac-8a7f-433d69e4ad1e"
},
"_type": "Component",
"auth_mode": {
@@ -2466,11 +2483,13 @@
"display_name": "Authentication Mode",
"dynamic": false,
"external_options": {},
- "info": "Authentication method: 'basic' for username/password authentication, or 'jwt' for JSON Web Token (Bearer) authentication.",
+ "info": "Authentication method: 'basic' for username/password authentication, 'jwt' for JSON Web Token (Bearer) authentication, or 'openrag' to delegate writes to the OpenRAG backend ingest callback (no direct OpenSearch credentials required — only OPENRAG_* fields).",
+ "load_from_db": false,
"name": "auth_mode",
"options": [
"basic",
- "jwt"
+ "jwt",
+ "openrag"
],
"options_metadata": [],
"override_skip": false,
@@ -2767,7 +2786,7 @@
"override_skip": false,
"password": true,
"placeholder": "",
- "required": true,
+ "required": false,
"show": true,
"title_case": false,
"track_in_telemetry": false,
@@ -2855,6 +2874,101 @@
"type": "int",
"value": 10
},
+ "openrag_ingest_batch_size": {
+ "_input_type": "IntInput",
+ "advanced": true,
+ "display_name": "OpenRAG Ingest Batch Size",
+ "dynamic": false,
+ "info": "",
+ "list": false,
+ "list_add_label": "Add More",
+ "name": "openrag_ingest_batch_size",
+ "override_skip": false,
+ "placeholder": "",
+ "required": false,
+ "show": true,
+ "title_case": false,
+ "tool_mode": false,
+ "trace_as_metadata": true,
+ "track_in_telemetry": true,
+ "type": "int",
+ "value": 100
+ },
+ "openrag_ingest_run_id": {
+ "_input_type": "StrInput",
+ "advanced": true,
+ "display_name": "OpenRAG Ingest Run ID",
+ "dynamic": false,
+ "info": "",
+ "input_types": [
+ "Text",
+ "Message"
+ ],
+ "list": false,
+ "list_add_label": "Add More",
+ "load_from_db": true,
+ "name": "openrag_ingest_run_id",
+ "override_skip": false,
+ "placeholder": "",
+ "required": false,
+ "show": true,
+ "title_case": false,
+ "tool_mode": false,
+ "trace_as_metadata": true,
+ "track_in_telemetry": false,
+ "type": "str",
+ "value": "OPENRAG_INGEST_RUN_ID"
+ },
+ "openrag_ingest_token": {
+ "_input_type": "StrInput",
+ "advanced": true,
+ "display_name": "OpenRAG Ingest Token",
+ "dynamic": false,
+ "info": "Short-lived token used only for OpenRAG ingest callbacks.",
+ "input_types": [
+ "Text",
+ "Message"
+ ],
+ "list": false,
+ "list_add_label": "Add More",
+ "load_from_db": true,
+ "name": "openrag_ingest_token",
+ "override_skip": false,
+ "placeholder": "",
+ "required": false,
+ "show": true,
+ "title_case": false,
+ "tool_mode": false,
+ "trace_as_metadata": true,
+ "track_in_telemetry": false,
+ "type": "str",
+ "value": "OPENRAG_INGEST_TOKEN"
+ },
+ "openrag_ingest_url": {
+ "_input_type": "StrInput",
+ "advanced": true,
+ "display_name": "OpenRAG Ingest URL",
+ "dynamic": false,
+ "info": "Internal OpenRAG callback URL for backend-owned document indexing.",
+ "input_types": [
+ "Text",
+ "Message"
+ ],
+ "list": false,
+ "list_add_label": "Add More",
+ "load_from_db": true,
+ "name": "openrag_ingest_url",
+ "override_skip": false,
+ "placeholder": "",
+ "required": false,
+ "show": true,
+ "title_case": false,
+ "tool_mode": false,
+ "trace_as_metadata": true,
+ "track_in_telemetry": false,
+ "type": "str",
+ "value": "OPENRAG_INGEST_URL"
+ },
"opensearch_url": {
"_input_type": "StrInput",
"advanced": false,
@@ -3253,7 +3367,7 @@
"value": "1098eea1-6649-4e1d-aed1-b77249fb8dd0"
},
"_frontend_node_folder_id": {
- "value": "ef261332-778a-4347-96bc-99b4207d86b1"
+ "value": "38bb3005-a7d5-4eac-8a7f-433d69e4ad1e"
},
"_type": "Component",
"api_base": {
@@ -3783,7 +3897,7 @@
"value": "1098eea1-6649-4e1d-aed1-b77249fb8dd0"
},
"_frontend_node_folder_id": {
- "value": "ef261332-778a-4347-96bc-99b4207d86b1"
+ "value": "38bb3005-a7d5-4eac-8a7f-433d69e4ad1e"
},
"_type": "Component",
"api_base": {
@@ -4628,7 +4742,7 @@
],
"frozen": false,
"icon": "Mcp",
- "last_updated": "2026-05-18T18:15:01.797Z",
+ "last_updated": "2026-06-03T19:37:43.205Z",
"legacy": false,
"metadata": {
"code_hash": "ccd98ac0a0fb",
@@ -4679,7 +4793,7 @@
"value": "1098eea1-6649-4e1d-aed1-b77249fb8dd0"
},
"_frontend_node_folder_id": {
- "value": "ef261332-778a-4347-96bc-99b4207d86b1"
+ "value": "38bb3005-a7d5-4eac-8a7f-433d69e4ad1e"
},
"_type": "Component",
"code": {
@@ -4746,48 +4860,81 @@
"value": [
{
"": "",
+ "__load_from_db_fields": {
+ "value": true
+ },
"key": "X-Langflow-Global-Var-JWT",
"value": "JWT"
},
{
+ "__load_from_db_fields": {
+ "value": true
+ },
"key": "X-Langflow-Global-Var-OPENAI_API_KEY",
"value": "OPENAI_API_KEY"
},
{
+ "__load_from_db_fields": {
+ "value": true
+ },
"key": "X-Langflow-Global-Var-OPENSEARCH_URL",
"value": "OPENSEARCH_URL"
},
{
- "key": "X-Langflow-Global-Var-OWNER",
- "value": "OWNER"
- },
- {
- "key": "X-Langflow-Global-Var-OWNER_NAME",
- "value": "OWNER_NAME"
- },
- {
- "key": "X-Langflow-Global-Var-OWNER_EMAIL",
- "value": "OWNER_EMAIL"
- },
- {
- "key": "X-Langflow-Global-Var-CONNECTOR_TYPE",
- "value": "CONNECTOR_TYPE"
- },
- {
+ "__load_from_db_fields": {
+ "value": true
+ },
"key": "X-Langflow-Global-Var-OPENSEARCH_INDEX_NAME",
"value": "OPENSEARCH_INDEX_NAME"
},
{
+ "__load_from_db_fields": {
+ "value": true
+ },
"key": "X-Langflow-Global-Var-WATSONX_PROJECT_ID",
"value": "WATSONX_PROJECT_ID"
},
{
+ "__load_from_db_fields": {
+ "value": true
+ },
"key": "X-Langflow-Global-Var-WATSONX_APIKEY",
"value": "WATSONX_APIKEY"
},
{
+ "__load_from_db_fields": {
+ "value": true
+ },
"key": "X-Langflow-Global-Var-SELECTED_EMBEDDING_MODEL",
"value": "SELECTED_EMBEDDING_MODEL"
+ },
+ {
+ "__load_from_db_fields": {
+ "value": true
+ },
+ "key": "X-Langflow-Global-Var-OPENRAG_INGEST_URL",
+ "value": "OPENRAG_INGEST_URL"
+ },
+ {
+ "__load_from_db_fields": {
+ "value": true
+ },
+ "key": "X-Langflow-Global-Var-OPENRAG_INGEST_RUN_ID",
+ "value": "OPENRAG_INGEST_RUN_ID"
+ },
+ {
+ "__load_from_db_fields": {
+ "value": true
+ },
+ "key": "X-Langflow-Global-Var-OPENRAG_INGEST_BATCH_SIZE",
+ "value": "OPENRAG_INGEST_BATCH_SIZE"
+ },
+ {
+ "__load_from_db_fields": {
+ "value": true
+ },
+ "key": "X-Langflow-Global-Var-OPENRAG_INGEST_TOKEN",
+ "value": "OPENRAG_INGEST_TOKEN"
}
]
},
@@ -4985,11 +5132,11 @@
"endpoint_name": null,
"id": "1098eea1-6649-4e1d-aed1-b77249fb8dd0",
"is_component": false,
- "last_tested_version": "1.9.3",
+ "last_tested_version": "1.9.6",
"locked": true,
"name": "OpenRAG OpenSearch Agent Flow",
"tags": [
"assistants",
"agents"
]
-}
+}
\ No newline at end of file
diff --git a/flows/openrag_nudges.json b/flows/openrag_nudges.json
index 764bd39d5..c1d332e2e 100644
--- a/flows/openrag_nudges.json
+++ b/flows/openrag_nudges.json
@@ -1177,7 +1177,7 @@
"value": "ebc01d31-1976-46ce-a385-b0240327226c"
},
"_frontend_node_folder_id": {
- "value": "79f95013-41e9-4a4f-af49-f07ec1fac77a"
+ "value": "38bb3005-a7d5-4eac-8a7f-433d69e4ad1e"
},
"_type": "Component",
"api_key": {
@@ -1409,81 +1409,6 @@
"name": "gpt-5.2",
"provider": "OpenAI"
},
- {
- "category": "IBM WatsonX",
- "icon": "WatsonxAI",
- "metadata": {
- "api_key_param": "apikey",
- "context_length": 128000,
- "max_tokens_field_name": "max_tokens",
- "model_class": "ChatWatsonx",
- "model_name_param": "model_id",
- "project_id_param": "project_id",
- "url_param": "url"
- },
- "name": "ibm/granite-4-h-small",
- "provider": "IBM WatsonX"
- },
- {
- "category": "IBM WatsonX",
- "icon": "WatsonxAI",
- "metadata": {
- "api_key_param": "apikey",
- "context_length": 128000,
- "max_tokens_field_name": "max_tokens",
- "model_class": "ChatWatsonx",
- "model_name_param": "model_id",
- "project_id_param": "project_id",
- "url_param": "url"
- },
- "name": "ibm/granite-8b-code-instruct",
- "provider": "IBM WatsonX"
- },
- {
- "category": "IBM WatsonX",
- "icon": "WatsonxAI",
- "metadata": {
- "api_key_param": "apikey",
- "context_length": 128000,
- "max_tokens_field_name": "max_tokens",
- "model_class": "ChatWatsonx",
- "model_name_param": "model_id",
- "project_id_param": "project_id",
- "url_param": "url"
- },
- "name": "ibm/granite-guardian-3-8b",
- "provider": "IBM WatsonX"
- },
- {
- "category": "IBM WatsonX",
- "icon": "WatsonxAI",
- "metadata": {
- "api_key_param": "apikey",
- "context_length": 128000,
- "max_tokens_field_name": "max_tokens",
- "model_class": "ChatWatsonx",
- "model_name_param": "model_id",
- "project_id_param": "project_id",
- "url_param": "url"
- },
- "name": "meta-llama/llama-3-2-11b-vision-instruct",
- "provider": "IBM WatsonX"
- },
- {
- "category": "IBM WatsonX",
- "icon": "WatsonxAI",
- "metadata": {
- "api_key_param": "apikey",
- "context_length": 128000,
- "max_tokens_field_name": "max_tokens",
- "model_class": "ChatWatsonx",
- "model_name_param": "model_id",
- "project_id_param": "project_id",
- "url_param": "url"
- },
- "name": "meta-llama/llama-3-3-70b-instruct",
- "provider": "IBM WatsonX"
- },
{
"category": "OpenAI",
"icon": "OpenAI",
@@ -1492,8 +1417,7 @@
"context_length": 128000,
"max_tokens_field_name": "max_tokens",
"model_class": "ChatOpenAI",
- "model_name_param": "model",
- "not_enabled_locally": true
+ "model_name_param": "model"
},
"name": "gpt-4o",
"provider": "OpenAI"
@@ -1746,7 +1670,7 @@
"value": "ebc01d31-1976-46ce-a385-b0240327226c"
},
"_frontend_node_folder_id": {
- "value": "79f95013-41e9-4a4f-af49-f07ec1fac77a"
+ "value": "38bb3005-a7d5-4eac-8a7f-433d69e4ad1e"
},
"_type": "Component",
"api_base": {
@@ -1906,7 +1830,7 @@
"type": "bool",
"value": true
},
- "is_refresh": false,
+ "is_refresh": true,
"max_retries": {
"_input_type": "IntInput",
"advanced": true,
@@ -2015,96 +1939,6 @@
},
"name": "text-embedding-ada-002",
"provider": "OpenAI"
- },
- {
- "category": "IBM WatsonX",
- "icon": "WatsonxAI",
- "metadata": {
- "embedding_class": "WatsonxEmbeddings",
- "model_type": "embeddings",
- "param_mapping": {
- "api_key": "apikey",
- "model_id": "model_id",
- "project_id": "project_id",
- "request_timeout": "request_timeout",
- "space_id": "space_id",
- "url": "url"
- }
- },
- "name": "ibm/granite-embedding-278m-multilingual",
- "provider": "IBM WatsonX"
- },
- {
- "category": "IBM WatsonX",
- "icon": "WatsonxAI",
- "metadata": {
- "embedding_class": "WatsonxEmbeddings",
- "model_type": "embeddings",
- "param_mapping": {
- "api_key": "apikey",
- "model_id": "model_id",
- "project_id": "project_id",
- "request_timeout": "request_timeout",
- "space_id": "space_id",
- "url": "url"
- }
- },
- "name": "ibm/slate-125m-english-rtrvr-v2",
- "provider": "IBM WatsonX"
- },
- {
- "category": "IBM WatsonX",
- "icon": "WatsonxAI",
- "metadata": {
- "embedding_class": "WatsonxEmbeddings",
- "model_type": "embeddings",
- "param_mapping": {
- "api_key": "apikey",
- "model_id": "model_id",
- "project_id": "project_id",
- "request_timeout": "request_timeout",
- "space_id": "space_id",
- "url": "url"
- }
- },
- "name": "ibm/slate-30m-english-rtrvr-v2",
- "provider": "IBM WatsonX"
- },
- {
- "category": "IBM WatsonX",
- "icon": "WatsonxAI",
- "metadata": {
- "embedding_class": "WatsonxEmbeddings",
- "model_type": "embeddings",
- "param_mapping": {
- "api_key": "apikey",
- "model_id": "model_id",
- "project_id": "project_id",
- "request_timeout": "request_timeout",
- "space_id": "space_id",
- "url": "url"
- }
- },
- "name": "intfloat/multilingual-e5-large",
- "provider": "IBM WatsonX"
- },
- {
- "category": "IBM WatsonX",
- "icon": "WatsonxAI",
- "metadata": {
- "embedding_class": "WatsonxEmbeddings",
- "model_type": "embeddings",
- "param_mapping": {
- "api_key": "apikey",
- "model_id": "model_id",
- "project_id": "project_id",
- "request_timeout": "request_timeout",
- "space_id": "space_id",
- "url": "url"
- }
- },
- "name": "sentence-transformers/all-minilm-l6-v2",
- "provider": "IBM WatsonX"
}
],
"override_skip": false,
@@ -2120,6 +1954,7 @@
"type": "model",
"value": [
{
+ "category": "OpenAI",
"icon": "OpenAI",
"metadata": {
"embedding_class": "OpenAIEmbeddings",
@@ -2284,7 +2119,7 @@
"x": -326.63616916760816,
"y": 1367.3460258727496
},
- "selected": true,
+ "selected": false,
"type": "genericNode"
},
{
@@ -2304,9 +2139,11 @@
"description": "Store and search documents using OpenSearch with multi-model hybrid semantic and keyword search. To search use the tools search_documents and raw_search. Search documents takes a query for vector search, for example\n {search_query: \"components in openrag\"}",
"display_name": "OpenSearch (Multi-Model Multi-Embedding)",
"documentation": "",
- "edited": false,
+ "edited": true,
"field_order": [
"docs_metadata",
+ "openrag_ingest_token",
+ "openrag_ingest_run_id",
"opensearch_url",
"index_name",
"engine",
@@ -2331,30 +2168,38 @@
"use_ssl",
"verify_certs",
"request_timeout",
- "max_retries"
+ "max_retries",
+ "openrag_ingest_url",
+ "openrag_ingest_token",
+ "openrag_ingest_run_id",
+ "openrag_ingest_batch_size"
],
"frozen": false,
"icon": "OpenSearch",
- "last_updated": "2026-04-07T18:43:59.369Z",
+ "last_updated": "2026-06-03T19:37:14.327Z",
"legacy": false,
"metadata": {
- "code_hash": "4a05432fb489",
+ "code_hash": "220fbf21a963",
"dependencies": {
"dependencies": [
{
- "name": "opensearchpy",
- "version": "2.8.0"
+ "name": "httpx",
+ "version": "0.28.1"
},
{
"name": "lfx",
- "version": null
+ "version": "0.4.6"
+ },
+ {
+ "name": "opensearchpy",
+ "version": "2.8.0"
},
{
"name": "tenacity",
"version": "8.5.0"
}
],
- "total_dependencies": 3
+ "total_dependencies": 4
},
"module": "custom_components.opensearch_multimodel_multiembedding"
},
@@ -2422,7 +2267,7 @@
"value": "ebc01d31-1976-46ce-a385-b0240327226c"
},
"_frontend_node_folder_id": {
- "value": "3832f035-bbe8-40c4-ba61-8f760b613bdb"
+ "value": "38bb3005-a7d5-4eac-8a7f-433d69e4ad1e"
},
"_type": "Component",
"auth_mode": {
@@ -2433,11 +2278,13 @@
"display_name": "Authentication Mode",
"dynamic": false,
"external_options": {},
- "info": "Authentication method: 'basic' for username/password authentication, or 'jwt' for JSON Web Token (Bearer) authentication.",
+ "info": "Authentication method: 'basic' for username/password authentication, 'jwt' for JSON Web Token (Bearer) authentication, or 'openrag' to delegate writes to the OpenRAG backend ingest callback (no direct OpenSearch credentials required — only OPENRAG_* fields).",
+ "load_from_db": false,
"name": "auth_mode",
"options": [
"basic",
- "jwt"
+ "jwt",
+ "openrag"
],
"options_metadata": [],
"override_skip": false,
@@ -2734,7 +2581,7 @@
"override_skip": false,
"password": true,
"placeholder": "",
- "required": true,
+ "required": false,
"show": true,
"title_case": false,
"track_in_telemetry": false,
@@ -2822,6 +2669,101 @@
"type": "int",
"value": 10
},
+ "openrag_ingest_batch_size": {
+ "_input_type": "IntInput",
+ "advanced": true,
+ "display_name": "OpenRAG Ingest Batch Size",
+ "dynamic": false,
+ "info": "",
+ "list": false,
+ "list_add_label": "Add More",
+ "name": "openrag_ingest_batch_size",
+ "override_skip": false,
+ "placeholder": "",
+ "required": false,
+ "show": true,
+ "title_case": false,
+ "tool_mode": false,
+ "trace_as_metadata": true,
+ "track_in_telemetry": true,
+ "type": "int",
+ "value": 100
+ },
+ "openrag_ingest_run_id": {
+ "_input_type": "StrInput",
+ "advanced": true,
+ "display_name": "OpenRAG Ingest Run ID",
+ "dynamic": false,
+ "info": "",
+ "input_types": [
+ "Text",
+ "Message"
+ ],
+ "list": false,
+ "list_add_label": "Add More",
+ "load_from_db": true,
+ "name": "openrag_ingest_run_id",
+ "override_skip": false,
+ "placeholder": "",
+ "required": false,
+ "show": true,
+ "title_case": false,
+ "tool_mode": false,
+ "trace_as_metadata": true,
+ "track_in_telemetry": false,
+ "type": "str",
+ "value": "OPENRAG_INGEST_RUN_ID"
+ },
+ "openrag_ingest_token": {
+ "_input_type": "StrInput",
+ "advanced": true,
+ "display_name": "OpenRAG Ingest Token",
+ "dynamic": false,
+ "info": "Short-lived token used only for OpenRAG ingest callbacks.",
+ "input_types": [
+ "Text",
+ "Message"
+ ],
+ "list": false,
+ "list_add_label": "Add More",
+ "load_from_db": true,
+ "name": "openrag_ingest_token",
+ "override_skip": false,
+ "placeholder": "",
+ "required": false,
+ "show": true,
+ "title_case": false,
+ "tool_mode": false,
+ "trace_as_metadata": true,
+ "track_in_telemetry": false,
+ "type": "str",
+ "value": "OPENRAG_INGEST_TOKEN"
+ },
+ "openrag_ingest_url": {
+ "_input_type": "StrInput",
+ "advanced": true,
+ "display_name": "OpenRAG Ingest URL",
+ "dynamic": false,
+ "info": "Internal OpenRAG callback URL for backend-owned document indexing.",
+ "input_types": [
+ "Text",
+ "Message"
+ ],
+ "list": false,
+ "list_add_label": "Add More",
+ "load_from_db": true,
+ "name": "openrag_ingest_url",
+ "override_skip": false,
+ "placeholder": "",
+ "required": false,
+ "show": true,
+ "title_case": false,
+ "tool_mode": false,
+ "trace_as_metadata": true,
+ "track_in_telemetry": false,
+ "type": "str",
+ "value": "OPENRAG_INGEST_URL"
+ },
"opensearch_url": {
"_input_type": "StrInput",
"advanced": false,
@@ -3138,7 +3080,7 @@
"value": "ebc01d31-1976-46ce-a385-b0240327226c"
},
"_frontend_node_folder_id": {
- "value": "79f95013-41e9-4a4f-af49-f07ec1fac77a"
+ "value": "38bb3005-a7d5-4eac-8a7f-433d69e4ad1e"
},
"_type": "Component",
"api_base": {
@@ -3298,7 +3240,7 @@
"type": "bool",
"value": true
},
- "is_refresh": false,
+ "is_refresh": true,
"max_retries": {
"_input_type": "IntInput",
"advanced": true,
@@ -3407,96 +3349,6 @@
},
"name": "text-embedding-ada-002",
"provider": "OpenAI"
- },
- {
- "category": "IBM WatsonX",
- "icon": "WatsonxAI",
- "metadata": {
- "embedding_class": "WatsonxEmbeddings",
- "model_type": "embeddings",
- "param_mapping": {
- "api_key": "apikey",
- "model_id": "model_id",
- "project_id": "project_id",
- "request_timeout": "request_timeout",
- "space_id": "space_id",
- "url": "url"
- }
- },
- "name": "ibm/granite-embedding-278m-multilingual",
- "provider": "IBM WatsonX"
- },
- {
- "category": "IBM WatsonX",
- "icon": "WatsonxAI",
- "metadata": {
- "embedding_class": "WatsonxEmbeddings",
- "model_type": "embeddings",
- "param_mapping": {
- "api_key": "apikey",
- "model_id": "model_id",
- "project_id": "project_id",
- "request_timeout": "request_timeout",
- "space_id": "space_id",
- "url": "url"
- }
- },
- "name": "ibm/slate-125m-english-rtrvr-v2",
- "provider": "IBM WatsonX"
- },
- {
- "category": "IBM WatsonX",
- "icon": "WatsonxAI",
- "metadata": {
- "embedding_class": "WatsonxEmbeddings",
- "model_type": "embeddings",
- "param_mapping": {
- "api_key": "apikey",
- "model_id": "model_id",
- "project_id": "project_id",
- "request_timeout": "request_timeout",
- "space_id": "space_id",
- "url": "url"
- }
- },
- "name": "ibm/slate-30m-english-rtrvr-v2",
- "provider": "IBM WatsonX"
- },
- {
- "category": "IBM WatsonX",
- "icon": "WatsonxAI",
- "metadata": {
- "embedding_class": "WatsonxEmbeddings",
- "model_type": "embeddings",
- "param_mapping": {
- "api_key": "apikey",
- "model_id": "model_id",
- "project_id": "project_id",
- "request_timeout": "request_timeout",
- "space_id": "space_id",
- "url": "url"
- }
- },
- "name": "intfloat/multilingual-e5-large",
- "provider": "IBM WatsonX"
- },
- {
- "category": "IBM WatsonX",
- "icon": "WatsonxAI",
- "metadata": {
- "embedding_class": "WatsonxEmbeddings",
- "model_type": "embeddings",
- "param_mapping": {
- "api_key": "apikey",
- "model_id": "model_id",
- "project_id": "project_id",
- "request_timeout": "request_timeout",
- "space_id": "space_id",
- "url": "url"
- }
- },
- "name": "sentence-transformers/all-minilm-l6-v2",
- "provider": "IBM WatsonX"
}
],
"override_skip": false,
@@ -3512,6 +3364,7 @@
"type": "model",
"value": [
{
+ "category": "OpenAI",
"icon": "OpenAI",
"metadata": {
"embedding_class": "OpenAIEmbeddings",
@@ -3757,7 +3610,7 @@
"value": "ebc01d31-1976-46ce-a385-b0240327226c"
},
"_frontend_node_folder_id": {
- "value": "79f95013-41e9-4a4f-af49-f07ec1fac77a"
+ "value": "38bb3005-a7d5-4eac-8a7f-433d69e4ad1e"
},
"_type": "Component",
"api_base": {
@@ -3917,7 +3770,7 @@
"type": "bool",
"value": true
},
- "is_refresh": false,
+ "is_refresh": true,
"max_retries": {
"_input_type": "IntInput",
"advanced": true,
@@ -4026,96 +3879,6 @@
},
"name": "text-embedding-ada-002",
"provider": "OpenAI"
- },
- {
- "category": "IBM WatsonX",
- "icon": "WatsonxAI",
- "metadata": {
- "embedding_class": "WatsonxEmbeddings",
- "model_type": "embeddings",
- "param_mapping": {
- "api_key": "apikey",
- "model_id": "model_id",
- "project_id": "project_id",
- "request_timeout": "request_timeout",
- "space_id": "space_id",
- "url": "url"
- }
- },
- "name": "ibm/granite-embedding-278m-multilingual",
- "provider": "IBM WatsonX"
- },
- {
- "category": "IBM WatsonX",
- "icon": "WatsonxAI",
- "metadata": {
- "embedding_class": "WatsonxEmbeddings",
- "model_type": "embeddings",
- "param_mapping": {
- "api_key": "apikey",
- "model_id": "model_id",
- "project_id": "project_id",
- "request_timeout": "request_timeout",
- "space_id": "space_id",
- "url": "url"
- }
- },
- "name": "ibm/slate-125m-english-rtrvr-v2",
- "provider": "IBM WatsonX"
- },
- {
- "category": "IBM WatsonX",
- "icon": "WatsonxAI",
- "metadata": {
- "embedding_class": "WatsonxEmbeddings",
- "model_type": "embeddings",
- "param_mapping": {
- "api_key": "apikey",
- "model_id": "model_id",
- "project_id": "project_id",
- "request_timeout": "request_timeout",
- "space_id": "space_id",
- "url": "url"
- }
- },
- "name": "ibm/slate-30m-english-rtrvr-v2",
- "provider": "IBM WatsonX"
- },
- {
- "category": "IBM WatsonX",
- "icon": "WatsonxAI",
- "metadata": {
- "embedding_class": "WatsonxEmbeddings",
- "model_type": "embeddings",
- "param_mapping": {
- "api_key": "apikey",
- "model_id": "model_id",
- "project_id": "project_id",
- "request_timeout": "request_timeout",
- "space_id": "space_id",
- "url": "url"
- }
- },
- "name": "intfloat/multilingual-e5-large",
- "provider": "IBM WatsonX"
- },
- {
- "category": "IBM WatsonX",
- "icon": "WatsonxAI",
- "metadata": {
- "embedding_class": "WatsonxEmbeddings",
- "model_type": "embeddings",
- "param_mapping": {
- "api_key": "apikey",
- "model_id": "model_id",
- "project_id": "project_id",
- "request_timeout": "request_timeout",
- "space_id": "space_id",
- "url": "url"
- }
- },
- "name": "sentence-transformers/all-minilm-l6-v2",
- "provider": "IBM WatsonX"
}
],
"override_skip": false,
@@ -4131,6 +3894,7 @@
"type": "model",
"value": [
{
+ "category": "OpenAI",
"icon": "OpenAI",
"metadata": {
"embedding_class": "OpenAIEmbeddings",
@@ -4656,7 +4420,7 @@
],
"viewport": {
"x": 219.98802613623758,
- "y": -187.42019049039925,
+ "y": -149.42019049039925,
"zoom": 0.4738353067326915
}
},
@@ -4664,11 +4428,11 @@
"endpoint_name": null,
"id": "ebc01d31-1976-46ce-a385-b0240327226c",
"is_component": false,
- "last_tested_version": "1.9.0",
+ "last_tested_version": "1.9.6",
"locked": true,
"name": "OpenRAG OpenSearch Nudges Flow",
"tags": [
"assistants",
"agents"
]
-}
+}
\ No newline at end of file
diff --git a/flows/openrag_url_mcp.json b/flows/openrag_url_mcp.json
index ec34cd3aa..9fcbd0893 100644
--- a/flows/openrag_url_mcp.json
+++ b/flows/openrag_url_mcp.json
@@ -29,122 +29,6 @@
"target": "URLComponent-lnA0q",
"targetHandle": "{œfieldNameœ:œurlsœ,œidœ:œURLComponent-lnA0qœ,œinputTypesœ:[œMessageœ],œtypeœ:œstrœ}"
},
- {
- "animated": false,
- "className": "",
- "data": {
- "sourceHandle": {
- "dataType": "TextInput",
- "id": "TextInput-tahMb",
- "name": "text",
- "output_types": [
- "Message"
- ]
- },
- "targetHandle": {
- "fieldName": "dynamic_owner_name",
- "id": "AdvancedDynamicFormBuilder-ziCu4",
- "inputTypes": [
- "Text",
- "Message"
- ],
- "type": "str"
- }
- },
- "id": "xy-edge__TextInput-tahMb{œdataTypeœ:œTextInputœ,œidœ:œTextInput-tahMbœ,œnameœ:œtextœ,œoutput_typesœ:[œMessageœ]}-AdvancedDynamicFormBuilder-ziCu4{œfieldNameœ:œdynamic_owner_nameœ,œidœ:œAdvancedDynamicFormBuilder-ziCu4œ,œinputTypesœ:[œTextœ,œMessageœ],œtypeœ:œstrœ}",
- "selected": false,
- "source": "TextInput-tahMb",
- "sourceHandle": "{œdataTypeœ:œTextInputœ,œidœ:œTextInput-tahMbœ,œnameœ:œtextœ,œoutput_typesœ:[œMessageœ]}",
- "target": "AdvancedDynamicFormBuilder-ziCu4",
- "targetHandle": "{œfieldNameœ:œdynamic_owner_nameœ,œidœ:œAdvancedDynamicFormBuilder-ziCu4œ,œinputTypesœ:[œTextœ,œMessageœ],œtypeœ:œstrœ}"
- },
- {
- "animated": false,
- "className": "",
- "data": {
- "sourceHandle": {
- "dataType": "TextInput",
- "id": "TextInput-Rm9YX",
- "name": "text",
- "output_types": [
- "Message"
- ]
- },
- "targetHandle": {
- "fieldName": "dynamic_owner_email",
- "id": "AdvancedDynamicFormBuilder-ziCu4",
- "inputTypes": [
- "Text",
- "Message"
- ],
- "type": "str"
- }
- },
- "id": "xy-edge__TextInput-Rm9YX{œdataTypeœ:œTextInputœ,œidœ:œTextInput-Rm9YXœ,œnameœ:œtextœ,œoutput_typesœ:[œMessageœ]}-AdvancedDynamicFormBuilder-ziCu4{œfieldNameœ:œdynamic_owner_emailœ,œidœ:œAdvancedDynamicFormBuilder-ziCu4œ,œinputTypesœ:[œTextœ,œMessageœ],œtypeœ:œstrœ}",
- "selected": false,
- "source": "TextInput-Rm9YX",
- "sourceHandle": "{œdataTypeœ:œTextInputœ,œidœ:œTextInput-Rm9YXœ,œnameœ:œtextœ,œoutput_typesœ:[œMessageœ]}",
- "target": "AdvancedDynamicFormBuilder-ziCu4",
- "targetHandle": "{œfieldNameœ:œdynamic_owner_emailœ,œidœ:œAdvancedDynamicFormBuilder-ziCu4œ,œinputTypesœ:[œTextœ,œMessageœ],œtypeœ:œstrœ}"
- },
- {
- "animated": false,
- "className": "",
- "data": {
- "sourceHandle": {
- "dataType": "TextInput",
- "id": "TextInput-G5CiZ",
- "name": "text",
- "output_types": [
- "Message"
- ]
- },
- "targetHandle": {
- "fieldName": "dynamic_owner",
- "id": "AdvancedDynamicFormBuilder-ziCu4",
- "inputTypes": [
- "Text",
- "Message"
- ],
- "type": "str"
- }
- },
- "id": "xy-edge__TextInput-G5CiZ{œdataTypeœ:œTextInputœ,œidœ:œTextInput-G5CiZœ,œnameœ:œtextœ,œoutput_typesœ:[œMessageœ]}-AdvancedDynamicFormBuilder-ziCu4{œfieldNameœ:œdynamic_ownerœ,œidœ:œAdvancedDynamicFormBuilder-ziCu4œ,œinputTypesœ:[œTextœ,œMessageœ],œtypeœ:œstrœ}",
- "selected": false,
- "source": "TextInput-G5CiZ",
- "sourceHandle": "{œdataTypeœ:œTextInputœ,œidœ:œTextInput-G5CiZœ,œnameœ:œtextœ,œoutput_typesœ:[œMessageœ]}",
- "target": "AdvancedDynamicFormBuilder-ziCu4",
- "targetHandle": "{œfieldNameœ:œdynamic_ownerœ,œidœ:œAdvancedDynamicFormBuilder-ziCu4œ,œinputTypesœ:[œTextœ,œMessageœ],œtypeœ:œstrœ}"
- },
- {
- "animated": false,
- "className": "",
- "data": {
- "sourceHandle": {
- "dataType": "TextInput",
- "id": "TextInput-OPyEf",
- "name": "text",
- "output_types": [
- "Message"
- ]
- },
- "targetHandle": {
- "fieldName": "dynamic_connector_type",
- "id": "AdvancedDynamicFormBuilder-ziCu4",
- "inputTypes": [
- "Text",
- "Message"
- ],
- "type": "str"
- }
- },
- "id": "xy-edge__TextInput-OPyEf{œdataTypeœ:œTextInputœ,œidœ:œTextInput-OPyEfœ,œnameœ:œtextœ,œoutput_typesœ:[œMessageœ]}-AdvancedDynamicFormBuilder-ziCu4{œfieldNameœ:œdynamic_connector_typeœ,œidœ:œAdvancedDynamicFormBuilder-ziCu4œ,œinputTypesœ:[œTextœ,œMessageœ],œtypeœ:œstrœ}",
- "selected": false,
- "source": "TextInput-OPyEf",
- "sourceHandle": "{œdataTypeœ:œTextInputœ,œidœ:œTextInput-OPyEfœ,œnameœ:œtextœ,œoutput_typesœ:[œMessageœ]}",
- "target": "AdvancedDynamicFormBuilder-ziCu4",
- "targetHandle": "{œfieldNameœ:œdynamic_connector_typeœ,œidœ:œAdvancedDynamicFormBuilder-ziCu4œ,œinputTypesœ:[œTextœ,œMessageœ],œtypeœ:œstrœ}"
- },
{
"animated": false,
"className": "",
@@ -468,35 +352,6 @@
"target": "DataFrameOperations-RhKoe",
"targetHandle": "{œfieldNameœ:œdfœ,œidœ:œDataFrameOperations-RhKoeœ,œinputTypesœ:[œDataFrameœ,œTableœ],œtypeœ:œotherœ}"
},
- {
- "animated": false,
- "className": "",
- "data": {
- "sourceHandle": {
- "dataType": "AdvancedDynamicFormBuilder",
- "id": "AdvancedDynamicFormBuilder-ziCu4",
- "name": "form_data",
- "output_types": [
- "JSON"
- ]
- },
- "targetHandle": {
- "fieldName": "docs_metadata",
- "id": "OpenSearchVectorStoreComponentMultimodalMultiEmbedding-PMGGV",
- "inputTypes": [
- "Data",
- "JSON"
- ],
- "type": "table"
- }
- },
- "id": "xy-edge__AdvancedDynamicFormBuilder-ziCu4{œdataTypeœ:œAdvancedDynamicFormBuilderœ,œidœ:œAdvancedDynamicFormBuilder-ziCu4œ,œnameœ:œform_dataœ,œoutput_typesœ:[œJSONœ]}-OpenSearchVectorStoreComponentMultimodalMultiEmbedding-PMGGV{œfieldNameœ:œdocs_metadataœ,œidœ:œOpenSearchVectorStoreComponentMultimodalMultiEmbedding-PMGGVœ,œinputTypesœ:[œDataœ,œJSONœ],œtypeœ:œtableœ}",
- "selected": false,
- "source": "AdvancedDynamicFormBuilder-ziCu4",
- "sourceHandle": "{œdataTypeœ:œAdvancedDynamicFormBuilderœ,œidœ:œAdvancedDynamicFormBuilder-ziCu4œ,œnameœ:œform_dataœ,œoutput_typesœ:[œJSONœ]}",
- "target": "OpenSearchVectorStoreComponentMultimodalMultiEmbedding-PMGGV",
- "targetHandle": "{œfieldNameœ:œdocs_metadataœ,œidœ:œOpenSearchVectorStoreComponentMultimodalMultiEmbedding-PMGGVœ,œinputTypesœ:[œDataœ,œJSONœ],œtypeœ:œtableœ}"
- },
{
"animated": false,
"className": "",
@@ -526,93 +381,6 @@
"sourceHandle": "{œdataTypeœ:œSplitTextœ,œidœ:œSplitText-QIKhgœ,œnameœ:œdataframeœ,œoutput_typesœ:[œTableœ]}",
"target": "OpenSearchVectorStoreComponentMultimodalMultiEmbedding-PMGGV",
"targetHandle": "{œfieldNameœ:œingest_dataœ,œidœ:œOpenSearchVectorStoreComponentMultimodalMultiEmbedding-PMGGVœ,œinputTypesœ:[œDataœ,œDataFrameœ,œTableœ],œtypeœ:œotherœ}"
- },
- {
- "animated": false,
- "className": "",
- "data": {
- "sourceHandle": {
- "dataType": "TextInput",
- "id": "TextInput-OpenRAGIngest-url",
- "name": "text",
- "output_types": [
- "Message"
- ]
- },
- "targetHandle": {
- "fieldName": "openrag_ingest_url",
- "id": "OpenSearchVectorStoreComponentMultimodalMultiEmbedding-PMGGV",
- "inputTypes": [
- "Text",
- "Message"
- ],
- "type": "str"
- }
- },
- "id": "xy-edge__TextInput-OpenRAGIngest-url{œdataTypeœ:œTextInputœ,œidœ:œTextInput-OpenRAGIngest-urlœ,œnameœ:œtextœ,œoutput_typesœ:[œMessageœ]}-OpenSearchVectorStoreComponentMultimodalMultiEmbedding-PMGGV{œfieldNameœ:œopenrag_ingest_urlœ,œidœ:œOpenSearchVectorStoreComponentMultimodalMultiEmbedding-PMGGVœ,œinputTypesœ:[œTextœ,œMessageœ],œtypeœ:œstrœ}",
- "selected": false,
- "source": "TextInput-OpenRAGIngest-url",
- "sourceHandle": "{œdataTypeœ:œTextInputœ,œidœ:œTextInput-OpenRAGIngest-urlœ,œnameœ:œtextœ,œoutput_typesœ:[œMessageœ]}",
- "target": "OpenSearchVectorStoreComponentMultimodalMultiEmbedding-PMGGV",
- "targetHandle": "{œfieldNameœ:œopenrag_ingest_urlœ,œidœ:œOpenSearchVectorStoreComponentMultimodalMultiEmbedding-PMGGVœ,œinputTypesœ:[œTextœ,œMessageœ],œtypeœ:œstrœ}"
- },
- {
- "animated": false,
- "className": "",
- "data": {
- "sourceHandle": {
- "dataType": "TextInput",
- "id": "TextInput-OpenRAGIngest-token",
- "name": "text",
- "output_types": [
- "Message"
- ]
- },
- "targetHandle": {
- "fieldName": "openrag_ingest_token",
- "id": "OpenSearchVectorStoreComponentMultimodalMultiEmbedding-PMGGV",
- "inputTypes": [
- "Text",
- "Message"
- ],
- "type": "str"
- }
- },
- "id": "xy-edge__TextInput-OpenRAGIngest-token{œdataTypeœ:œTextInputœ,œidœ:œTextInput-OpenRAGIngest-tokenœ,œnameœ:œtextœ,œoutput_typesœ:[œMessageœ]}-OpenSearchVectorStoreComponentMultimodalMultiEmbedding-PMGGV{œfieldNameœ:œopenrag_ingest_tokenœ,œidœ:œOpenSearchVectorStoreComponentMultimodalMultiEmbedding-PMGGVœ,œinputTypesœ:[œTextœ,œMessageœ],œtypeœ:œstrœ}",
- "selected": false,
- "source": "TextInput-OpenRAGIngest-token",
- "sourceHandle": "{œdataTypeœ:œTextInputœ,œidœ:œTextInput-OpenRAGIngest-tokenœ,œnameœ:œtextœ,œoutput_typesœ:[œMessageœ]}",
- "target": "OpenSearchVectorStoreComponentMultimodalMultiEmbedding-PMGGV",
- "targetHandle": "{œfieldNameœ:œopenrag_ingest_tokenœ,œidœ:œOpenSearchVectorStoreComponentMultimodalMultiEmbedding-PMGGVœ,œinputTypesœ:[œTextœ,œMessageœ],œtypeœ:œstrœ}"
- },
- {
- "animated": false,
- "className": "",
- "data": {
- "sourceHandle": {
- "dataType": "TextInput",
- "id": "TextInput-OpenRAGIngest-run_id",
- "name": "text",
- "output_types": [
- "Message"
- ]
- },
- "targetHandle": {
- "fieldName": "openrag_ingest_run_id",
- "id": "OpenSearchVectorStoreComponentMultimodalMultiEmbedding-PMGGV",
- "inputTypes": [
- "Text",
- "Message"
- ],
- "type": "str"
- }
- },
- "id": "xy-edge__TextInput-OpenRAGIngest-run_id{œdataTypeœ:œTextInputœ,œidœ:œTextInput-OpenRAGIngest-run_idœ,œnameœ:œtextœ,œoutput_typesœ:[œMessageœ]}-OpenSearchVectorStoreComponentMultimodalMultiEmbedding-PMGGV{œfieldNameœ:œopenrag_ingest_run_idœ,œidœ:œOpenSearchVectorStoreComponentMultimodalMultiEmbedding-PMGGVœ,œinputTypesœ:[œTextœ,œMessageœ],œtypeœ:œstrœ}",
- "selected": false,
- "source": "TextInput-OpenRAGIngest-run_id",
- "sourceHandle": "{œdataTypeœ:œTextInputœ,œidœ:œTextInput-OpenRAGIngest-run_idœ,œnameœ:œtextœ,œoutput_typesœ:[œMessageœ]}",
- "target": "OpenSearchVectorStoreComponentMultimodalMultiEmbedding-PMGGV",
- "targetHandle": "{œfieldNameœ:œopenrag_ingest_run_idœ,œidœ:œOpenSearchVectorStoreComponentMultimodalMultiEmbedding-PMGGVœ,œinputTypesœ:[œTextœ,œMessageœ],œtypeœ:œstrœ}"
}
],
"nodes": [
@@ -3664,9 +3432,11 @@
"description": "Store and search documents using OpenSearch with multi-model hybrid semantic and keyword search. To search use the tools search_documents and raw_search. Search documents takes a query for vector search, for example\n {search_query: \"components in openrag\"}",
"display_name": "OpenSearch (Multi-Model Multi-Embedding)",
"documentation": "",
- "edited": false,
+ "edited": true,
"field_order": [
"docs_metadata",
+ "openrag_ingest_token",
+ "openrag_ingest_run_id",
"opensearch_url",
"index_name",
"engine",
@@ -3691,30 +3461,38 @@
"use_ssl",
"verify_certs",
"request_timeout",
- "max_retries"
+ "max_retries",
+ "openrag_ingest_url",
+ "openrag_ingest_token",
+ "openrag_ingest_run_id",
+ "openrag_ingest_batch_size"
],
"frozen": false,
"icon": "OpenSearch",
- "last_updated": "2026-04-07T18:51:06.910Z",
+ "last_updated": "2026-06-02T20:38:12.785Z",
"legacy": false,
"metadata": {
- "code_hash": "4a05432fb489",
+ "code_hash": "220fbf21a963",
"dependencies": {
"dependencies": [
{
- "name": "opensearchpy",
- "version": "2.8.0"
+ "name": "httpx",
+ "version": "0.28.1"
},
{
"name": "lfx",
- "version": null
+ "version": "0.4.6"
+ },
+ {
+ "name": "opensearchpy",
+ "version": "2.8.0"
},
{
"name": "tenacity",
"version": "8.5.0"
}
],
- "total_dependencies": 3
+ "total_dependencies": 4
},
"module": "custom_components.opensearch_multimodel_multiembedding"
},
@@ -3782,7 +3560,7 @@
"value": "72c3d17c-2dac-4a73-b48a-6518473d7830"
},
"_frontend_node_folder_id": {
- "value": "3832f035-bbe8-40c4-ba61-8f760b613bdb"
+ "value": "dcac372c-a803-4877-8e1a-83e9adcd2972"
},
"_type": "Component",
"auth_mode": {
@@ -3793,11 +3571,13 @@
"display_name": "Authentication Mode",
"dynamic": false,
"external_options": {},
- "info": "Authentication method: 'basic' for username/password authentication, or 'jwt' for JSON Web Token (Bearer) authentication.",
+ "info": "Authentication method: 'basic' for username/password authentication, 'jwt' for JSON Web Token (Bearer) authentication, or 'openrag' to delegate writes to the OpenRAG backend ingest callback (no direct OpenSearch credentials required — only OPENRAG_* fields).",
+ "load_from_db": false,
"name": "auth_mode",
"options": [
"basic",
- "jwt"
+ "jwt",
+ "openrag"
],
"options_metadata": [],
"override_skip": false,
@@ -3811,7 +3591,7 @@
"trace_as_metadata": true,
"track_in_telemetry": true,
"type": "str",
- "value": "jwt"
+ "value": "openrag"
},
"bearer_prefix": {
"_input_type": "BoolInput",
@@ -3825,7 +3605,7 @@
"override_skip": false,
"placeholder": "",
"required": false,
- "show": true,
+ "show": false,
"title_case": false,
"tool_mode": false,
"trace_as_metadata": true,
@@ -4073,8 +3853,8 @@
"name": "jwt_header",
"override_skip": false,
"placeholder": "",
- "required": true,
- "show": true,
+ "required": false,
+ "show": false,
"title_case": false,
"tool_mode": false,
"trace_as_metadata": true,
@@ -4089,17 +3869,17 @@
"dynamic": false,
"info": "Valid JSON Web Token for authentication. Will be sent in the Authorization header (with optional 'Bearer ' prefix).",
"input_types": [],
- "load_from_db": true,
+ "load_from_db": false,
"name": "jwt_token",
"override_skip": false,
"password": true,
"placeholder": "",
- "required": true,
- "show": true,
+ "required": false,
+ "show": false,
"title_case": false,
"track_in_telemetry": false,
"type": "str",
- "value": "JWT"
+ "value": ""
},
"m": {
"_input_type": "IntInput",
@@ -4182,16 +3962,15 @@
"type": "int",
"value": 10
},
- "opensearch_url": {
- "_input_type": "StrInput",
+ "openrag_ingest_batch_size": {
+ "_input_type": "IntInput",
"advanced": false,
- "display_name": "OpenSearch URL",
+ "display_name": "OpenRAG Ingest Batch Size",
"dynamic": false,
- "info": "The connection URL for your OpenSearch cluster (e.g., http://localhost:9200 for local development or your cloud endpoint).",
+ "info": "",
"list": false,
"list_add_label": "Add More",
- "load_from_db": true,
- "name": "opensearch_url",
+ "name": "openrag_ingest_batch_size",
"override_skip": false,
"placeholder": "",
"required": false,
@@ -4199,67 +3978,163 @@
"title_case": false,
"tool_mode": false,
"trace_as_metadata": true,
- "track_in_telemetry": false,
- "type": "str",
- "value": "OPENSEARCH_URL"
+ "track_in_telemetry": true,
+ "type": "int",
+ "value": 100
},
- "password": {
- "_input_type": "SecretStrInput",
+ "openrag_ingest_run_id": {
+ "_input_type": "StrInput",
"advanced": false,
- "display_name": "OpenSearch Password",
+ "display_name": "OpenRAG Ingest Run ID",
"dynamic": false,
"info": "",
- "input_types": [],
- "load_from_db": false,
- "name": "password",
+ "input_types": [
+ "Text",
+ "Message"
+ ],
+ "list": false,
+ "list_add_label": "Add More",
+ "load_from_db": true,
+ "name": "openrag_ingest_run_id",
"override_skip": false,
- "password": true,
"placeholder": "",
- "required": false,
- "show": false,
+ "required": true,
+ "show": true,
"title_case": false,
+ "tool_mode": false,
+ "trace_as_metadata": true,
"track_in_telemetry": false,
"type": "str",
- "value": ""
+ "value": "OPENRAG_INGEST_RUN_ID"
},
- "request_timeout": {
+ "openrag_ingest_token": {
"_input_type": "StrInput",
- "advanced": true,
- "display_name": "Request Timeout (seconds)",
+ "advanced": false,
+ "display_name": "OpenRAG Ingest Token",
"dynamic": false,
- "info": "Time in seconds to wait for a response from OpenSearch. Increase for large bulk ingestion or complex hybrid queries.",
+ "info": "Short-lived token used only for OpenRAG ingest callbacks.",
+ "input_types": [
+ "Text",
+ "Message"
+ ],
"list": false,
"list_add_label": "Add More",
- "load_from_db": false,
- "name": "request_timeout",
+ "load_from_db": true,
+ "name": "openrag_ingest_token",
"override_skip": false,
"placeholder": "",
- "required": false,
+ "required": true,
"show": true,
"title_case": false,
"tool_mode": false,
"trace_as_metadata": true,
"track_in_telemetry": false,
"type": "str",
- "value": "60"
+ "value": "OPENRAG_INGEST_TOKEN"
},
- "search_query": {
- "_input_type": "QueryInput",
+ "openrag_ingest_url": {
+ "_input_type": "StrInput",
"advanced": false,
- "display_name": "Search Query",
+ "display_name": "OpenRAG Ingest URL",
"dynamic": false,
- "info": "Enter a query to run a similarity search.",
+ "info": "Internal OpenRAG callback URL for backend-owned document indexing.",
"input_types": [
+ "Text",
"Message"
],
"list": false,
"list_add_label": "Add More",
- "load_from_db": false,
- "name": "search_query",
+ "load_from_db": true,
+ "name": "openrag_ingest_url",
"override_skip": false,
- "placeholder": "Enter a query...",
- "required": false,
- "show": true,
+ "placeholder": "",
+ "required": true,
+ "show": true,
+ "title_case": false,
+ "tool_mode": false,
+ "trace_as_metadata": true,
+ "track_in_telemetry": false,
+ "type": "str",
+ "value": "OPENRAG_INGEST_URL"
+ },
+ "opensearch_url": {
+ "_input_type": "StrInput",
+ "advanced": false,
+ "display_name": "OpenSearch URL",
+ "dynamic": false,
+ "info": "The connection URL for your OpenSearch cluster (e.g., http://localhost:9200 for local development or your cloud endpoint).",
+ "list": false,
+ "list_add_label": "Add More",
+ "load_from_db": true,
+ "name": "opensearch_url",
+ "override_skip": false,
+ "placeholder": "",
+ "required": false,
+ "show": true,
+ "title_case": false,
+ "tool_mode": false,
+ "trace_as_metadata": true,
+ "track_in_telemetry": false,
+ "type": "str",
+ "value": "OPENSEARCH_URL"
+ },
+ "password": {
+ "_input_type": "SecretStrInput",
+ "advanced": false,
+ "display_name": "OpenSearch Password",
+ "dynamic": false,
+ "info": "",
+ "input_types": [],
+ "load_from_db": false,
+ "name": "password",
+ "override_skip": false,
+ "password": true,
+ "placeholder": "",
+ "required": false,
+ "show": false,
+ "title_case": false,
+ "track_in_telemetry": false,
+ "type": "str",
+ "value": ""
+ },
+ "request_timeout": {
+ "_input_type": "StrInput",
+ "advanced": true,
+ "display_name": "Request Timeout (seconds)",
+ "dynamic": false,
+ "info": "Time in seconds to wait for a response from OpenSearch. Increase for large bulk ingestion or complex hybrid queries.",
+ "list": false,
+ "list_add_label": "Add More",
+ "load_from_db": false,
+ "name": "request_timeout",
+ "override_skip": false,
+ "placeholder": "",
+ "required": false,
+ "show": true,
+ "title_case": false,
+ "tool_mode": false,
+ "trace_as_metadata": true,
+ "track_in_telemetry": false,
+ "type": "str",
+ "value": "60"
+ },
+ "search_query": {
+ "_input_type": "QueryInput",
+ "advanced": false,
+ "display_name": "Search Query",
+ "dynamic": false,
+ "info": "Enter a query to run a similarity search.",
+ "input_types": [
+ "Message"
+ ],
+ "list": false,
+ "list_add_label": "Add More",
+ "load_from_db": false,
+ "name": "search_query",
+ "override_skip": false,
+ "placeholder": "Enter a query...",
+ "required": false,
+ "show": true,
"title_case": false,
"tool_mode": true,
"trace_as_input": true,
@@ -4399,99 +4274,6 @@
"track_in_telemetry": true,
"type": "bool",
"value": false
- },
- "openrag_ingest_url": {
- "_input_type": "StrInput",
- "advanced": true,
- "display_name": "OpenRAG Ingest URL",
- "dynamic": false,
- "info": "Internal OpenRAG callback URL for backend-owned document indexing.",
- "list": false,
- "list_add_label": "Add More",
- "load_from_db": true,
- "name": "openrag_ingest_url",
- "override_skip": false,
- "placeholder": "",
- "required": false,
- "show": false,
- "title_case": false,
- "tool_mode": false,
- "trace_as_metadata": true,
- "track_in_telemetry": false,
- "type": "str",
- "value": "OPENRAG_INGEST_URL",
- "input_types": [
- "Text",
- "Message"
- ]
- },
- "openrag_ingest_token": {
- "_input_type": "StrInput",
- "advanced": true,
- "display_name": "OpenRAG Ingest Token",
- "dynamic": false,
- "info": "Short-lived token used only for OpenRAG ingest callbacks.",
- "input_types": [
- "Text",
- "Message"
- ],
- "load_from_db": true,
- "name": "openrag_ingest_token",
- "override_skip": false,
- "password": true,
- "placeholder": "",
- "required": false,
- "show": false,
- "title_case": false,
- "track_in_telemetry": false,
- "type": "str",
- "value": "OPENRAG_INGEST_TOKEN"
- },
- "openrag_ingest_run_id": {
- "_input_type": "StrInput",
- "advanced": true,
- "display_name": "OpenRAG Ingest Run ID",
- "dynamic": false,
- "info": "",
- "list": false,
- "list_add_label": "Add More",
- "load_from_db": true,
- "name": "openrag_ingest_run_id",
- "override_skip": false,
- "placeholder": "",
- "required": false,
- "show": false,
- "title_case": false,
- "tool_mode": false,
- "trace_as_metadata": true,
- "track_in_telemetry": false,
- "type": "str",
- "value": "OPENRAG_INGEST_RUN_ID",
- "input_types": [
- "Text",
- "Message"
- ]
- },
- "openrag_ingest_batch_size": {
- "_input_type": "IntInput",
- "advanced": true,
- "display_name": "OpenRAG Ingest Batch Size",
- "dynamic": false,
- "info": "",
- "list": false,
- "list_add_label": "Add More",
- "load_from_db": false,
- "name": "openrag_ingest_batch_size",
- "override_skip": false,
- "placeholder": "",
- "required": false,
- "show": false,
- "title_case": false,
- "tool_mode": false,
- "trace_as_metadata": true,
- "track_in_telemetry": false,
- "type": "int",
- "value": 100
}
},
"tool_mode": false
@@ -4503,77 +4285,104 @@
"dragging": false,
"id": "OpenSearchVectorStoreComponentMultimodalMultiEmbedding-PMGGV",
"measured": {
- "height": 967,
+ "height": 1213,
"width": 320
},
"position": {
"x": 2729.318175939116,
"y": 1398.252846147518
},
- "selected": false,
+ "selected": true,
"type": "genericNode"
},
{
"data": {
- "id": "AdvancedDynamicFormBuilder-ziCu4",
+ "description": "Perform various operations on a Table.",
+ "display_name": "Table Operations",
+ "id": "DataFrameOperations-NpdW5",
"node": {
"base_classes": [
- "Data",
- "Message"
+ "Table"
],
"beta": false,
"conditional_paths": [],
"custom_fields": {},
- "description": "Creates dynamic input fields that can receive data from other components or manual input.",
- "display_name": "Create Data",
- "documentation": "",
- "edited": true,
+ "description": "Perform various operations on a Table.",
+ "display_name": "Table Operations",
+ "documentation": "https://docs.langflow.org/dataframe-operations",
+ "edited": false,
"field_order": [
- "form_fields",
- "include_metadata"
+ "df",
+ "operation",
+ "column_name",
+ "filter_value",
+ "filter_operator",
+ "ascending",
+ "new_column_name",
+ "new_column_value",
+ "columns_to_select",
+ "num_rows",
+ "replace_value",
+ "replacement_value",
+ "left_dataframe",
+ "right_dataframe",
+ "merge_on_column",
+ "merge_how"
],
"frozen": false,
- "icon": "braces",
- "last_updated": "2026-04-17T22:34:51.074Z",
+ "icon": "table",
+ "last_updated": "2026-04-07T16:59:34.492Z",
"legacy": false,
- "lf_version": "1.8.0",
- "metadata": {},
+ "metadata": {
+ "code_hash": "4df73846bdd3",
+ "dependencies": {
+ "dependencies": [
+ {
+ "name": "pandas",
+ "version": "2.2.3"
+ },
+ {
+ "name": "lfx",
+ "version": null
+ }
+ ],
+ "total_dependencies": 2
+ },
+ "keywords": [
+ "dataframe",
+ "dataframe operations",
+ "table",
+ "table operations",
+ "filter",
+ "sort",
+ "merge",
+ "concatenate",
+ "drop column",
+ "rename column",
+ "add column",
+ "select columns",
+ "replace value",
+ "drop duplicates"
+ ],
+ "module": "custom_components.table_operations"
+ },
"minimized": false,
"output_types": [],
"outputs": [
{
"allows_loop": false,
"cache": true,
- "display_name": "Data",
+ "display_name": "Table",
"group_outputs": false,
- "hidden": null,
"loop_types": null,
- "method": "process_form",
- "name": "form_data",
+ "method": "perform_operation",
+ "name": "output",
"options": null,
"required_inputs": null,
- "selected": "JSON",
+ "selected": "Table",
"tool_mode": true,
"types": [
- "JSON"
- ],
- "value": "__UNDEFINED__"
- },
- {
- "allows_loop": false,
- "cache": true,
- "display_name": "Message",
- "group_outputs": false,
- "hidden": null,
- "loop_types": null,
- "method": "get_message",
- "name": "message",
- "options": null,
- "required_inputs": null,
- "selected": "Message",
- "tool_mode": true,
- "types": [
- "Message"
+ "Table"
],
"value": "__UNDEFINED__"
}
@@ -4584,9 +4393,29 @@
"value": "72c3d17c-2dac-4a73-b48a-6518473d7830"
},
"_frontend_node_folder_id": {
- "value": "79f95013-41e9-4a4f-af49-f07ec1fac77a"
+ "value": "3430da17-6e18-48e1-ad5c-9589db1b95d6"
},
"_type": "Component",
+ "ascending": {
+ "_input_type": "BoolInput",
+ "advanced": false,
+ "display_name": "Sort Ascending",
+ "dynamic": true,
+ "info": "Whether to sort in ascending order.",
+ "list": false,
+ "list_add_label": "Add More",
+ "name": "ascending",
+ "override_skip": false,
+ "placeholder": "",
+ "required": false,
+ "show": false,
+ "title_case": false,
+ "tool_mode": false,
+ "trace_as_metadata": true,
+ "track_in_telemetry": true,
+ "type": "bool",
+ "value": true
+ },
"code": {
"advanced": true,
"dynamic": true,
@@ -4603,102 +4432,127 @@
"show": true,
"title_case": false,
"type": "code",
- "value": "from typing import Any\r\n\r\nfrom langflow.custom import Component\r\nfrom langflow.io import (\r\n BoolInput,\r\n FloatInput,\r\n HandleInput,\r\n IntInput,\r\n MultilineInput,\r\n Output,\r\n StrInput,\r\n TableInput,\r\n)\r\nfrom langflow.schema.data import Data\r\nfrom langflow.schema.message import Message\r\n\r\n\r\nclass CrateData(Component):\r\n \"\"\"Dynamic Form Component\r\n\r\n This component creates dynamic inputs that can receive data from other components\r\n or be filled manually. It demonstrates advanced dynamic input functionality with\r\n component connectivity.\r\n\r\n ## Features\r\n - **Dynamic Input Generation**: Create inputs based on table configuration\r\n - **Component Connectivity**: Inputs can receive data from other components\r\n - **Multiple Input Types**: Support for text, number, boolean, and handle inputs\r\n - **Flexible Data Sources**: Manual input OR component connections\r\n - **Real-time Updates**: Form fields update immediately when table changes\r\n - **Multiple Output Formats**: Data and formatted Message outputs\r\n - **JSON Output**: Collects all dynamic inputs into a structured JSON response\r\n\r\n ## Use Cases\r\n - Dynamic API parameter collection from multiple sources\r\n - Variable data aggregation from different components\r\n - Flexible pipeline configuration\r\n - Multi-source data processing\r\n\r\n ## Field Types Available\r\n - **text**: Single-line text input (can connect to Text/String outputs)\r\n - **multiline**: Multi-line text input (can connect to Text outputs)\r\n - **number**: Integer input (can connect to Number outputs)\r\n - **float**: Decimal number input (can connect to Number outputs)\r\n - **boolean**: True/false checkbox (can connect to Boolean outputs)\r\n - **handle**: Generic data input (can connect to any component output)\r\n - **data**: Structured data input (can connect to Data outputs)\r\n\r\n ## Input Types for Connections\r\n - **Text**: Text/String data from components\r\n - **Data**: Structured data objects\r\n - **Message**: Message objects with text content\r\n - **Number**: Numeric values\r\n - **Boolean**: True/false values\r\n - **Any**: Accepts any type of connection\r\n - **Combinations**: Text,Message | Data,Text | Text,Data,Message | etc.\r\n \"\"\"\r\n\r\n display_name = \"Create Data\"\r\n description = \"Creates dynamic input fields that can receive data from other components or manual input.\"\r\n icon = \"braces\"\r\n name = \"AdvancedDynamicFormBuilder\"\r\n\r\n def __init__(self, **kwargs):\r\n super().__init__(**kwargs)\r\n self._dynamic_inputs = {}\r\n\r\n inputs = [\r\n TableInput(\r\n name=\"form_fields\",\r\n display_name=\"Input Configuration\",\r\n info=\"Define the dynamic form fields. Each row creates a new input field that can connect to other components.\",\r\n table_schema=[\r\n {\r\n \"name\": \"field_name\",\r\n \"display_name\": \"Field Name\",\r\n \"type\": \"str\",\r\n \"description\": \"Name for the field (used as both internal name and display label)\",\r\n },\r\n {\r\n \"name\": \"field_type\",\r\n \"display_name\": \"Field Type\",\r\n \"type\": \"str\",\r\n \"description\": \"Type of input field to create\",\r\n \"options\": [\"Text\", \"Data\", \"Number\", \"Handle\", \"Boolean\"],\r\n \"value\": \"Text\",\r\n },\r\n ],\r\n value=[{\"field_name\": \"field_name\", \"field_type\": \"Text\"}],\r\n real_time_refresh=True,\r\n ),\r\n BoolInput(\r\n name=\"include_metadata\",\r\n display_name=\"Include Metadata\",\r\n info=\"Include form configuration metadata in the output.\",\r\n value=False,\r\n advanced=True,\r\n ),\r\n ]\r\n\r\n outputs = [\r\n Output(display_name=\"Data\", name=\"form_data\", method=\"process_form\"),\r\n Output(display_name=\"Message\", name=\"message\", method=\"get_message\"),\r\n ]\r\n\r\n def update_build_config(self, build_config: dict, field_value: Any, field_name: str = None) -> dict:\r\n \"\"\"Update build configuration to add dynamic inputs that can connect to other components.\"\"\"\r\n if field_name == \"form_fields\":\r\n # Store current values before clearing dynamic inputs\r\n current_values = {}\r\n keys_to_remove = [key for key in build_config if key.startswith(\"dynamic_\")]\r\n for key in keys_to_remove:\r\n # Preserve the current value before deletion\r\n if hasattr(self, key):\r\n current_values[key] = getattr(self, key)\r\n del build_config[key]\r\n\r\n # Add dynamic inputs based on table configuration\r\n # Safety check to ensure field_value is not None and is iterable\r\n if field_value is None:\r\n field_value = []\r\n\r\n for i, field_config in enumerate(field_value):\r\n # Safety check to ensure field_config is not None\r\n if field_config is None:\r\n continue\r\n\r\n field_name = field_config.get(\"field_name\", f\"field_{i}\")\r\n display_name = field_name # Use field_name as display_name\r\n field_type_option = field_config.get(\"field_type\", \"Text\")\r\n default_value = \"\" # All fields have empty default value\r\n required = False # All fields are optional by default\r\n help_text = \"\" # All fields have empty help text\r\n\r\n # Map field type options to actual field types and input types\r\n field_type_mapping = {\r\n \"Text\": {\"field_type\": \"multiline\", \"input_types\": [\"Text\", \"Message\"]},\r\n \"Data\": {\"field_type\": \"data\", \"input_types\": [\"Data\"]},\r\n \"Number\": {\"field_type\": \"number\", \"input_types\": [\"Text\", \"Message\"]},\r\n \"Handle\": {\"field_type\": \"handle\", \"input_types\": [\"Text\", \"Data\", \"Message\"]},\r\n \"Boolean\": {\"field_type\": \"boolean\", \"input_types\": None},\r\n }\r\n\r\n field_config_mapped = field_type_mapping.get(\r\n field_type_option, {\"field_type\": \"text\", \"input_types\": []}\r\n )\r\n field_type = field_config_mapped[\"field_type\"]\r\n input_types_list = field_config_mapped[\"input_types\"]\r\n\r\n # Create the appropriate input type based on field_type\r\n dynamic_input_name = f\"dynamic_{field_name}\"\r\n\r\n if field_type == \"text\":\r\n # Use preserved value if available, otherwise use default\r\n current_value = current_values.get(dynamic_input_name, default_value)\r\n if current_value is None:\r\n current_value = default_value\r\n \r\n if input_types_list:\r\n build_config[dynamic_input_name] = StrInput(\r\n name=dynamic_input_name,\r\n display_name=display_name,\r\n info=f\"{help_text} (Can connect to: {', '.join(input_types_list)})\",\r\n value=current_value,\r\n required=required,\r\n input_types=input_types_list,\r\n )\r\n else:\r\n build_config[dynamic_input_name] = StrInput(\r\n name=dynamic_input_name,\r\n display_name=display_name,\r\n info=help_text,\r\n value=current_value,\r\n required=required,\r\n )\r\n\r\n elif field_type == \"multiline\":\r\n # Use preserved value if available, otherwise use default\r\n current_value = current_values.get(dynamic_input_name, default_value)\r\n if current_value is None:\r\n current_value = default_value\r\n \r\n if input_types_list:\r\n build_config[dynamic_input_name] = MultilineInput(\r\n name=dynamic_input_name,\r\n display_name=display_name,\r\n info=f\"{help_text} (Can connect to: {', '.join(input_types_list)})\",\r\n value=current_value,\r\n required=required,\r\n input_types=input_types_list,\r\n )\r\n else:\r\n build_config[dynamic_input_name] = MultilineInput(\r\n name=dynamic_input_name,\r\n display_name=display_name,\r\n info=help_text,\r\n value=current_value,\r\n required=required,\r\n )\r\n\r\n elif field_type == \"number\":\r\n # Use preserved value if available, otherwise use default\r\n current_value = current_values.get(dynamic_input_name, default_value)\r\n if current_value is None:\r\n current_value = default_value\r\n \r\n try:\r\n if current_value:\r\n current_int = int(current_value)\r\n else:\r\n current_int = 0\r\n except (ValueError, TypeError):\r\n try:\r\n current_int = int(default_value) if default_value else 0\r\n except ValueError:\r\n current_int = 0\r\n\r\n if input_types_list:\r\n build_config[dynamic_input_name] = IntInput(\r\n name=dynamic_input_name,\r\n display_name=display_name,\r\n info=f\"{help_text} (Can connect to: {', '.join(input_types_list)})\",\r\n value=current_int,\r\n required=required,\r\n input_types=input_types_list,\r\n )\r\n else:\r\n build_config[dynamic_input_name] = IntInput(\r\n name=dynamic_input_name,\r\n display_name=display_name,\r\n info=help_text,\r\n value=current_int,\r\n required=required,\r\n )\r\n\r\n elif field_type == \"float\":\r\n # Use preserved value if available, otherwise use default\r\n current_value = current_values.get(dynamic_input_name, default_value)\r\n if current_value is None:\r\n current_value = default_value\r\n \r\n try:\r\n if current_value:\r\n current_float = float(current_value)\r\n else:\r\n current_float = 0.0\r\n except (ValueError, TypeError):\r\n try:\r\n current_float = float(default_value) if default_value else 0.0\r\n except ValueError:\r\n current_float = 0.0\r\n\r\n if input_types_list:\r\n build_config[dynamic_input_name] = FloatInput(\r\n name=dynamic_input_name,\r\n display_name=display_name,\r\n info=f\"{help_text} (Can connect to: {', '.join(input_types_list)})\",\r\n value=current_float,\r\n required=required,\r\n input_types=input_types_list,\r\n )\r\n else:\r\n build_config[dynamic_input_name] = FloatInput(\r\n name=dynamic_input_name,\r\n display_name=display_name,\r\n info=help_text,\r\n value=current_float,\r\n required=required,\r\n )\r\n\r\n elif field_type == \"boolean\":\r\n # Use preserved value if available, otherwise use default\r\n current_value = current_values.get(dynamic_input_name, default_value)\r\n if current_value is None:\r\n current_value = default_value\r\n \r\n # Convert current value to boolean\r\n if isinstance(current_value, bool):\r\n current_bool = current_value\r\n else:\r\n current_bool = str(current_value).lower() in [\"true\", \"1\", \"yes\"] if current_value else False\r\n\r\n # Boolean fields don't use input_types parameter to avoid errors\r\n build_config[dynamic_input_name] = BoolInput(\r\n name=dynamic_input_name,\r\n display_name=display_name,\r\n info=help_text,\r\n value=current_bool,\r\n input_types=[],\r\n required=required,\r\n )\r\n\r\n elif field_type == \"handle\":\r\n # HandleInput for generic data connections\r\n build_config[dynamic_input_name] = HandleInput(\r\n name=dynamic_input_name,\r\n display_name=display_name,\r\n info=f\"{help_text} (Accepts: {', '.join(input_types_list) if input_types_list else 'Any'})\",\r\n input_types=input_types_list if input_types_list else [\"Data\", \"Text\", \"Message\"],\r\n required=required,\r\n )\r\n\r\n elif field_type == \"data\":\r\n # Specialized for Data type connections\r\n build_config[dynamic_input_name] = HandleInput(\r\n name=dynamic_input_name,\r\n display_name=display_name,\r\n info=f\"{help_text} (Data input)\",\r\n input_types=[\"Data\"] if not input_types_list else input_types_list,\r\n required=required,\r\n )\r\n\r\n else:\r\n # Default to text input for unknown types\r\n # Use preserved value if available, otherwise use default\r\n current_value = current_values.get(dynamic_input_name, default_value)\r\n if current_value is None:\r\n current_value = default_value\r\n \r\n build_config[dynamic_input_name] = StrInput(\r\n name=dynamic_input_name,\r\n display_name=display_name,\r\n info=f\"{help_text} (Unknown type '{field_type}', defaulting to text)\",\r\n value=current_value,\r\n required=required,\r\n )\r\n\r\n return build_config\r\n\r\n def get_dynamic_values(self) -> dict[str, Any]:\r\n \"\"\"Extract simple values from all dynamic inputs, handling both manual and connected inputs.\"\"\"\r\n dynamic_values = {}\r\n connection_info = {}\r\n form_fields = getattr(self, \"form_fields\", [])\r\n\r\n for field_config in form_fields:\r\n # Safety check to ensure field_config is not None\r\n if field_config is None:\r\n continue\r\n\r\n field_name = field_config.get(\"field_name\", \"\")\r\n if field_name:\r\n dynamic_input_name = f\"dynamic_{field_name}\"\r\n value = getattr(self, dynamic_input_name, None)\r\n\r\n # Extract simple values from connections or manual input\r\n if value is not None:\r\n try:\r\n extracted_value = self._extract_simple_value(value)\r\n dynamic_values[field_name] = extracted_value\r\n\r\n # Determine connection type for status\r\n if hasattr(value, \"text\") and hasattr(value, \"timestamp\"):\r\n connection_info[field_name] = \"Connected (Message)\"\r\n elif hasattr(value, \"data\"):\r\n connection_info[field_name] = \"Connected (Data)\"\r\n elif isinstance(value, (str, int, float, bool, list, dict)):\r\n connection_info[field_name] = \"Manual input\"\r\n else:\r\n connection_info[field_name] = \"Connected (Object)\"\r\n\r\n except Exception:\r\n # Fallback to string representation if all else fails\r\n dynamic_values[field_name] = str(value)\r\n connection_info[field_name] = \"Error\"\r\n else:\r\n # Use empty default value if nothing connected\r\n dynamic_values[field_name] = \"\"\r\n connection_info[field_name] = \"Empty default\"\r\n\r\n # Store connection info for status output\r\n self._connection_info = connection_info\r\n return dynamic_values\r\n\r\n def _extract_simple_value(self, value: Any) -> Any:\r\n \"\"\"Extract the simplest, most useful value from any input type.\"\"\"\r\n # Handle None\r\n if value is None:\r\n return None\r\n\r\n # Handle simple types directly\r\n if isinstance(value, (str, int, float, bool)):\r\n return value\r\n\r\n # Handle lists and tuples - keep simple\r\n if isinstance(value, (list, tuple)):\r\n return [self._extract_simple_value(item) for item in value]\r\n\r\n # Handle dictionaries - keep simple\r\n if isinstance(value, dict):\r\n return {str(k): self._extract_simple_value(v) for k, v in value.items()}\r\n\r\n # Handle Message objects - extract only the text\r\n if hasattr(value, \"text\"):\r\n return str(value.text) if value.text is not None else \"\"\r\n\r\n # Handle Data objects - extract the data content\r\n if hasattr(value, \"data\") and value.data is not None:\r\n return self._extract_simple_value(value.data)\r\n\r\n # For any other object, convert to string\r\n return str(value)\r\n\r\n def process_form(self) -> Data:\r\n \"\"\"Process all dynamic form inputs and return clean data with just field values.\"\"\"\r\n # Get all dynamic values (just the key:value pairs)\r\n dynamic_values = self.get_dynamic_values()\r\n\r\n # Update status with connection info\r\n connected_fields = len([v for v in getattr(self, \"_connection_info\", {}).values() if \"Connected\" in v])\r\n total_fields = len(dynamic_values)\r\n\r\n self.status = f\"Form processed successfully. {connected_fields}/{total_fields} fields connected to components.\"\r\n\r\n # Return clean Data object with just the field values\r\n return Data(data=dynamic_values)\r\n\r\n def get_message(self) -> Message:\r\n \"\"\"Return form data as a formatted text message.\"\"\"\r\n # Get all dynamic values\r\n dynamic_values = self.get_dynamic_values()\r\n\r\n if not dynamic_values:\r\n return Message(text=\"No form data available\")\r\n\r\n # Format as text message\r\n message_lines = [\"📋 Form Data:\"]\r\n message_lines.append(\"=\" * 40)\r\n\r\n for field_name, value in dynamic_values.items():\r\n # Use field_name as display_name\r\n display_name = field_name\r\n\r\n message_lines.append(f\"• {display_name}: {value}\")\r\n\r\n message_lines.append(\"=\" * 40)\r\n message_lines.append(f\"Total fields: {len(dynamic_values)}\")\r\n\r\n message_text = \"\\n\".join(message_lines)\r\n self.status = f\"Message formatted with {len(dynamic_values)} fields\"\r\n\r\n return Message(text=message_text)"
+ "value": "import pandas as pd\n\nfrom lfx.custom.custom_component.component import Component\nfrom lfx.inputs import SortableListInput\nfrom lfx.io import BoolInput, DataFrameInput, DropdownInput, IntInput, MessageTextInput, Output, StrInput\nfrom lfx.log.logger import logger\nfrom lfx.schema.dataframe import DataFrame\n\n\nclass DataFrameOperationsComponent(Component):\n display_name = \"Table Operations\"\n description = \"Perform various operations on a Table.\"\n documentation: str = \"https://docs.langflow.org/dataframe-operations\"\n icon = \"table\"\n name = \"DataFrameOperations\"\n metadata = {\n \"keywords\": [\n \"dataframe\",\n \"dataframe operations\",\n \"table\",\n \"table operations\",\n \"filter\",\n \"sort\",\n \"merge\",\n \"concatenate\",\n \"drop column\",\n \"rename column\",\n \"add column\",\n \"select columns\",\n \"replace value\",\n \"drop duplicates\",\n ],\n }\n\n OPERATION_CHOICES = [\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 ]\n\n inputs = [\n DataFrameInput(\n name=\"df\",\n display_name=\"Table\",\n info=\"The input DataFrame to operate on. Connect multiple DataFrames for merge or concatenate operations.\",\n required=True,\n is_list=True,\n ),\n SortableListInput(\n name=\"operation\",\n display_name=\"Operation\",\n placeholder=\"Select Operation\",\n info=\"Select the DataFrame operation to perform.\",\n options=[\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 real_time_refresh=True,\n limit=1,\n ),\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) DataFrame 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) DataFrame 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 DataFrames on. Must exist in both DataFrames.\",\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 ]\n\n outputs = [\n Output(\n display_name=\"Table\",\n name=\"output\",\n method=\"perform_operation\",\n info=\"The resulting DataFrame after the operation.\",\n )\n ]\n\n def update_build_config(self, build_config, field_value, field_name=None):\n dynamic_fields = [\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 ]\n for field in dynamic_fields:\n build_config[field][\"show\"] = False\n\n if field_name == \"operation\":\n # Handle SortableListInput format\n if isinstance(field_value, list):\n operation_name = field_value[0].get(\"name\", \"\") if field_value else \"\"\n else:\n operation_name = field_value or \"\"\n\n # If no operation selected, all dynamic fields stay hidden (already set to False above)\n if not operation_name:\n return build_config\n\n if operation_name == \"Filter\":\n build_config[\"column_name\"][\"show\"] = True\n build_config[\"filter_value\"][\"show\"] = True\n build_config[\"filter_operator\"][\"show\"] = True\n elif operation_name == \"Sort\":\n build_config[\"column_name\"][\"show\"] = True\n build_config[\"ascending\"][\"show\"] = True\n elif operation_name == \"Drop Column\":\n build_config[\"column_name\"][\"show\"] = True\n elif operation_name == \"Rename Column\":\n build_config[\"column_name\"][\"show\"] = True\n build_config[\"new_column_name\"][\"show\"] = True\n elif operation_name == \"Add Column\":\n build_config[\"new_column_name\"][\"show\"] = True\n build_config[\"new_column_value\"][\"show\"] = True\n elif operation_name == \"Select Columns\":\n build_config[\"columns_to_select\"][\"show\"] = True\n elif operation_name in {\"Head\", \"Tail\"}:\n build_config[\"num_rows\"][\"show\"] = True\n elif operation_name == \"Replace Value\":\n build_config[\"column_name\"][\"show\"] = True\n build_config[\"replace_value\"][\"show\"] = True\n build_config[\"replacement_value\"][\"show\"] = True\n elif operation_name == \"Drop Duplicates\":\n build_config[\"column_name\"][\"show\"] = True\n elif operation_name == \"Merge\":\n build_config[\"left_dataframe\"][\"show\"] = True\n build_config[\"right_dataframe\"][\"show\"] = True\n build_config[\"merge_on_column\"][\"show\"] = True\n build_config[\"merge_how\"][\"show\"] = True\n\n return build_config\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 perform_operation(self) -> DataFrame:\n # Handle SortableListInput format for operation (also supports legacy string format)\n operation_input = getattr(self, \"operation\", [])\n if isinstance(operation_input, list):\n op = operation_input[0].get(\"name\", \"\") if operation_input else \"\"\n else:\n op = operation_input or \"\"\n\n # Merge and Concatenate use their own inputs, not the primary df\n if op == \"Merge\":\n return self.merge_dataframes()\n if op == \"Concatenate\":\n return self.concatenate_dataframes()\n\n df_copy = self._get_primary_dataframe()\n\n # If no operation selected, return original DataFrame\n if not op:\n return df_copy\n\n if op == \"Filter\":\n return self.filter_rows_by_value(df_copy)\n if op == \"Sort\":\n return self.sort_by_column(df_copy)\n if op == \"Drop Column\":\n return self.drop_column(df_copy)\n if op == \"Rename Column\":\n return self.rename_column(df_copy)\n if op == \"Add Column\":\n return self.add_column(df_copy)\n if op == \"Select Columns\":\n return self.select_columns(df_copy)\n if op == \"Head\":\n return self.head(df_copy)\n if op == \"Tail\":\n return self.tail(df_copy)\n if op == \"Replace Value\":\n return self.replace_values(df_copy)\n if op == \"Drop Duplicates\":\n return self.drop_duplicates(df_copy)\n msg = f\"Unsupported operation: {op}\"\n logger.error(msg)\n raise ValueError(msg)\n\n def filter_rows_by_value(self, df: DataFrame) -> DataFrame:\n column = df[self.column_name]\n filter_value = self.filter_value\n\n # Handle regular DropdownInput format (just a string value)\n operator = getattr(self, \"filter_operator\", \"equals\") # Default to equals for backward compatibility\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 # Try to convert filter_value to numeric for comparison\n numeric_value = pd.to_numeric(filter_value)\n mask = column > numeric_value\n except (ValueError, TypeError):\n # If conversion fails, compare as strings\n mask = column.astype(str) > str(filter_value)\n elif operator == \"less than\":\n try:\n # Try to convert filter_value to numeric for comparison\n numeric_value = pd.to_numeric(filter_value)\n mask = column < numeric_value\n except (ValueError, TypeError):\n # If conversion fails, compare as strings\n mask = column.astype(str) < str(filter_value)\n else:\n mask = column == filter_value # Fallback to equals\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 only one DataFrame, return it\n if len(self.df) == 1:\n return self.df[0].copy()\n\n # Concatenate all DataFrames vertically\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\n Uses explicit left_dataframe and right_dataframe inputs to give the user\n deterministic control over which DataFrame is primary (left) and which\n is secondary (right) in the merge.\n \"\"\"\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\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\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 # Combine duplicate columns: use left value if exists, otherwise right value\n cols_to_drop = []\n for col in merged.columns:\n if col.endswith(\"_right\"):\n original_col = col[:-6] # Remove \"_right\" suffix\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"
},
- "dynamic_connector_type": {
- "_input_type": "MultilineInput",
+ "column_name": {
+ "_input_type": "StrInput",
"advanced": false,
- "ai_enabled": false,
- "copy_field": false,
- "display_name": "connector_type",
- "dynamic": false,
- "helper_text": null,
- "info": " (Can connect to: Text, Message)",
- "input_types": [
- "Text",
- "Message"
- ],
+ "display_name": "Column Name",
+ "dynamic": true,
+ "info": "The column name to use for the operation.",
"list": false,
"list_add_label": "Add More",
"load_from_db": false,
- "multiline": true,
- "name": "dynamic_connector_type",
+ "name": "column_name",
"override_skip": false,
- "password": false,
"placeholder": "",
- "real_time_refresh": null,
- "refresh_button": null,
- "refresh_button_text": null,
"required": false,
- "show": true,
+ "show": false,
"title_case": false,
"tool_mode": false,
- "trace_as_input": true,
"trace_as_metadata": true,
"track_in_telemetry": false,
"type": "str",
"value": ""
},
- "dynamic_owner": {
- "_input_type": "MultilineInput",
+ "columns_to_select": {
+ "_input_type": "StrInput",
"advanced": false,
- "ai_enabled": false,
- "copy_field": false,
- "display_name": "owner",
+ "display_name": "Columns to Select",
+ "dynamic": true,
+ "info": "",
+ "list": true,
+ "list_add_label": "Add More",
+ "load_from_db": false,
+ "name": "columns_to_select",
+ "override_skip": false,
+ "placeholder": "",
+ "required": false,
+ "show": true,
+ "title_case": false,
+ "tool_mode": false,
+ "trace_as_metadata": true,
+ "track_in_telemetry": false,
+ "type": "str",
+ "value": [
+ "title"
+ ]
+ },
+ "df": {
+ "_input_type": "DataFrameInput",
+ "advanced": false,
+ "display_name": "Table",
"dynamic": false,
- "helper_text": null,
- "info": " (Can connect to: Text, Message)",
+ "info": "The input DataFrame to operate on. Connect multiple DataFrames for merge or concatenate operations.",
"input_types": [
- "Text",
- "Message"
+ "DataFrame",
+ "Table"
],
- "list": false,
+ "list": true,
"list_add_label": "Add More",
- "load_from_db": false,
- "multiline": true,
- "name": "dynamic_owner",
+ "name": "df",
"override_skip": false,
- "password": false,
"placeholder": "",
- "real_time_refresh": null,
- "refresh_button": null,
- "refresh_button_text": null,
- "required": false,
+ "required": true,
"show": true,
"title_case": false,
"tool_mode": false,
"trace_as_input": true,
"trace_as_metadata": true,
"track_in_telemetry": false,
- "type": "str",
+ "type": "other",
"value": ""
},
- "dynamic_owner_email": {
- "_input_type": "MultilineInput",
+ "filter_operator": {
+ "_input_type": "DropdownInput",
"advanced": false,
- "ai_enabled": false,
- "copy_field": false,
- "display_name": "owner_email",
- "dynamic": false,
- "helper_text": null,
- "info": " (Can connect to: Text, Message)",
+ "combobox": false,
+ "dialog_inputs": {},
+ "display_name": "Filter Operator",
+ "dynamic": true,
+ "external_options": {},
+ "info": "The operator to apply for filtering rows.",
+ "name": "filter_operator",
+ "options": [
+ "equals",
+ "not equals",
+ "contains",
+ "not contains",
+ "starts with",
+ "ends with",
+ "greater than",
+ "less than"
+ ],
+ "options_metadata": [],
+ "override_skip": false,
+ "placeholder": "",
+ "required": false,
+ "show": false,
+ "title_case": false,
+ "toggle": false,
+ "tool_mode": false,
+ "trace_as_metadata": true,
+ "track_in_telemetry": true,
+ "type": "str",
+ "value": "equals"
+ },
+ "filter_value": {
+ "_input_type": "MessageTextInput",
+ "advanced": false,
+ "display_name": "Filter Value",
+ "dynamic": true,
+ "info": "The value to filter rows by.",
"input_types": [
- "Text",
"Message"
],
"list": false,
"list_add_label": "Add More",
"load_from_db": false,
- "multiline": true,
- "name": "dynamic_owner_email",
+ "name": "filter_value",
"override_skip": false,
- "password": false,
"placeholder": "",
- "real_time_refresh": null,
- "refresh_button": null,
- "refresh_button_text": null,
"required": false,
- "show": true,
+ "show": false,
"title_case": false,
"tool_mode": false,
"trace_as_input": true,
@@ -4707,525 +4561,109 @@
"type": "str",
"value": ""
},
- "dynamic_owner_name": {
- "_input_type": "MultilineInput",
+ "is_refresh": false,
+ "left_dataframe": {
+ "_input_type": "DataFrameInput",
"advanced": false,
- "ai_enabled": false,
- "copy_field": false,
- "display_name": "owner_name",
- "dynamic": false,
- "helper_text": null,
- "info": " (Can connect to: Text, Message)",
+ "display_name": "Left Table",
+ "dynamic": true,
+ "info": "The left (primary) DataFrame for merge operations. In a left merge, all rows from this table are preserved.",
"input_types": [
- "Text",
- "Message"
+ "DataFrame",
+ "Table"
],
"list": false,
"list_add_label": "Add More",
- "load_from_db": false,
- "multiline": true,
- "name": "dynamic_owner_name",
+ "name": "left_dataframe",
"override_skip": false,
- "password": false,
"placeholder": "",
- "real_time_refresh": null,
- "refresh_button": null,
- "refresh_button_text": null,
"required": false,
- "show": true,
+ "show": false,
"title_case": false,
"tool_mode": false,
"trace_as_input": true,
"trace_as_metadata": true,
"track_in_telemetry": false,
- "type": "str",
+ "type": "other",
"value": ""
},
- "form_fields": {
- "_input_type": "TableInput",
+ "merge_how": {
+ "_input_type": "DropdownInput",
"advanced": false,
- "display_name": "Input Configuration",
- "dynamic": false,
- "info": "Define the dynamic form fields. Each row creates a new input field that can connect to other components.",
- "is_list": true,
+ "combobox": false,
+ "dialog_inputs": {},
+ "display_name": "Merge Type",
+ "dynamic": true,
+ "external_options": {},
+ "info": "Type of merge: inner (intersection), outer (union), left, or right.",
+ "name": "merge_how",
+ "options": [
+ "inner",
+ "outer",
+ "left",
+ "right"
+ ],
+ "options_metadata": [],
+ "override_skip": false,
+ "placeholder": "",
+ "required": false,
+ "show": false,
+ "title_case": false,
+ "toggle": false,
+ "tool_mode": false,
+ "trace_as_metadata": true,
+ "track_in_telemetry": true,
+ "type": "str",
+ "value": "inner"
+ },
+ "merge_on_column": {
+ "_input_type": "StrInput",
+ "advanced": false,
+ "display_name": "Merge On Column",
+ "dynamic": true,
+ "info": "The column name to merge DataFrames on. Must exist in both DataFrames.",
+ "list": false,
"list_add_label": "Add More",
"load_from_db": false,
- "name": "form_fields",
+ "name": "merge_on_column",
+ "override_skip": false,
"placeholder": "",
- "real_time_refresh": true,
"required": false,
- "show": true,
- "table_icon": "Table",
- "table_schema": {
- "columns": [
- {
- "default": "None",
- "description": "Name for the field (used as both internal name and display label)",
- "disable_edit": false,
- "display_name": "Field Name",
- "edit_mode": "popover",
- "filterable": true,
- "formatter": "text",
- "hidden": false,
- "name": "field_name",
- "sortable": true,
- "type": "str"
- },
- {
- "default": "None",
- "description": "Type of input field to create",
- "disable_edit": false,
- "display_name": "Field Type",
- "edit_mode": "popover",
- "filterable": true,
- "formatter": "text",
- "hidden": false,
- "name": "field_type",
- "options": [
- "Text",
- "Data",
- "Number",
- "Handle",
- "Boolean"
- ],
- "sortable": true,
- "type": "str"
- }
- ]
- },
+ "show": false,
"title_case": false,
"tool_mode": false,
"trace_as_metadata": true,
- "trigger_icon": "Table",
- "trigger_text": "Open table",
- "type": "table",
- "value": [
- {
- "field_name": "owner",
- "field_type": "Text"
- },
- {
- "field_name": "owner_name",
- "field_type": "Text"
- },
- {
- "field_name": "owner_email",
- "field_type": "Text"
- },
- {
- "field_name": "connector_type",
- "field_type": "Text"
- }
- ]
+ "track_in_telemetry": false,
+ "type": "str",
+ "value": ""
},
- "include_metadata": {
- "_input_type": "BoolInput",
- "advanced": true,
- "display_name": "Include Metadata",
- "dynamic": false,
- "info": "Include form configuration metadata in the output.",
+ "new_column_name": {
+ "_input_type": "StrInput",
+ "advanced": false,
+ "display_name": "New Column Name",
+ "dynamic": true,
+ "info": "The new column name when renaming or adding a column.",
"list": false,
"list_add_label": "Add More",
- "name": "include_metadata",
+ "load_from_db": false,
+ "name": "new_column_name",
+ "override_skip": false,
"placeholder": "",
"required": false,
- "show": true,
+ "show": false,
"title_case": false,
"tool_mode": false,
"trace_as_metadata": true,
- "type": "bool",
- "value": false
+ "track_in_telemetry": false,
+ "type": "str",
+ "value": "filename"
},
- "is_refresh": false
- },
- "tool_mode": false
- },
- "selected_output": "form_data",
- "showNode": true,
- "type": "AdvancedDynamicFormBuilder"
- },
- "dragging": false,
- "id": "AdvancedDynamicFormBuilder-ziCu4",
- "measured": {
- "height": 553,
- "width": 320
- },
- "position": {
- "x": 2344.490839041331,
- "y": 830.665770502212
- },
- "selected": false,
- "type": "genericNode"
- },
- {
- "data": {
- "description": "Perform various operations on a Table.",
- "display_name": "Table Operations",
- "id": "DataFrameOperations-NpdW5",
- "node": {
- "base_classes": [
- "Table"
- ],
- "beta": false,
- "conditional_paths": [],
- "custom_fields": {},
- "description": "Perform various operations on a Table.",
- "display_name": "Table Operations",
- "documentation": "https://docs.langflow.org/dataframe-operations",
- "edited": false,
- "field_order": [
- "df",
- "operation",
- "column_name",
- "filter_value",
- "filter_operator",
- "ascending",
- "new_column_name",
- "new_column_value",
- "columns_to_select",
- "num_rows",
- "replace_value",
- "replacement_value",
- "left_dataframe",
- "right_dataframe",
- "merge_on_column",
- "merge_how"
- ],
- "frozen": false,
- "icon": "table",
- "last_updated": "2026-04-07T16:59:34.492Z",
- "legacy": false,
- "metadata": {
- "code_hash": "4df73846bdd3",
- "dependencies": {
- "dependencies": [
- {
- "name": "pandas",
- "version": "2.2.3"
- },
- {
- "name": "lfx",
- "version": null
- }
- ],
- "total_dependencies": 2
- },
- "keywords": [
- "dataframe",
- "dataframe operations",
- "table",
- "table operations",
- "filter",
- "sort",
- "merge",
- "concatenate",
- "drop column",
- "rename column",
- "add column",
- "select columns",
- "replace value",
- "drop duplicates"
- ],
- "module": "custom_components.table_operations"
- },
- "minimized": false,
- "output_types": [],
- "outputs": [
- {
- "allows_loop": false,
- "cache": true,
- "display_name": "Table",
- "group_outputs": false,
- "loop_types": null,
- "method": "perform_operation",
- "name": "output",
- "options": null,
- "required_inputs": null,
- "selected": "Table",
- "tool_mode": true,
- "types": [
- "Table"
- ],
- "value": "__UNDEFINED__"
- }
- ],
- "pinned": false,
- "template": {
- "_frontend_node_flow_id": {
- "value": "72c3d17c-2dac-4a73-b48a-6518473d7830"
- },
- "_frontend_node_folder_id": {
- "value": "3430da17-6e18-48e1-ad5c-9589db1b95d6"
- },
- "_type": "Component",
- "ascending": {
- "_input_type": "BoolInput",
- "advanced": false,
- "display_name": "Sort Ascending",
- "dynamic": true,
- "info": "Whether to sort in ascending order.",
- "list": false,
- "list_add_label": "Add More",
- "name": "ascending",
- "override_skip": false,
- "placeholder": "",
- "required": false,
- "show": false,
- "title_case": false,
- "tool_mode": false,
- "trace_as_metadata": true,
- "track_in_telemetry": true,
- "type": "bool",
- "value": true
- },
- "code": {
- "advanced": true,
- "dynamic": true,
- "fileTypes": [],
- "file_path": "",
- "info": "",
- "list": false,
- "load_from_db": false,
- "multiline": true,
- "name": "code",
- "password": false,
- "placeholder": "",
- "required": true,
- "show": true,
- "title_case": false,
- "type": "code",
- "value": "import pandas as pd\n\nfrom lfx.custom.custom_component.component import Component\nfrom lfx.inputs import SortableListInput\nfrom lfx.io import BoolInput, DataFrameInput, DropdownInput, IntInput, MessageTextInput, Output, StrInput\nfrom lfx.log.logger import logger\nfrom lfx.schema.dataframe import DataFrame\n\n\nclass DataFrameOperationsComponent(Component):\n display_name = \"Table Operations\"\n description = \"Perform various operations on a Table.\"\n documentation: str = \"https://docs.langflow.org/dataframe-operations\"\n icon = \"table\"\n name = \"DataFrameOperations\"\n metadata = {\n \"keywords\": [\n \"dataframe\",\n \"dataframe operations\",\n \"table\",\n \"table operations\",\n \"filter\",\n \"sort\",\n \"merge\",\n \"concatenate\",\n \"drop column\",\n \"rename column\",\n \"add column\",\n \"select columns\",\n \"replace value\",\n \"drop duplicates\",\n ],\n }\n\n OPERATION_CHOICES = [\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 ]\n\n inputs = [\n DataFrameInput(\n name=\"df\",\n display_name=\"Table\",\n info=\"The input DataFrame to operate on. Connect multiple DataFrames for merge or concatenate operations.\",\n required=True,\n is_list=True,\n ),\n SortableListInput(\n name=\"operation\",\n display_name=\"Operation\",\n placeholder=\"Select Operation\",\n info=\"Select the DataFrame operation to perform.\",\n options=[\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 real_time_refresh=True,\n limit=1,\n ),\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) DataFrame 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) DataFrame 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 DataFrames on. Must exist in both DataFrames.\",\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 ]\n\n outputs = [\n Output(\n display_name=\"Table\",\n name=\"output\",\n method=\"perform_operation\",\n info=\"The resulting DataFrame after the operation.\",\n )\n ]\n\n def update_build_config(self, build_config, field_value, field_name=None):\n dynamic_fields = [\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 ]\n for field in dynamic_fields:\n build_config[field][\"show\"] = False\n\n if field_name == \"operation\":\n # Handle SortableListInput format\n if isinstance(field_value, list):\n operation_name = field_value[0].get(\"name\", \"\") if field_value else \"\"\n else:\n operation_name = field_value or \"\"\n\n # If no operation selected, all dynamic fields stay hidden (already set to False above)\n if not operation_name:\n return build_config\n\n if operation_name == \"Filter\":\n build_config[\"column_name\"][\"show\"] = True\n build_config[\"filter_value\"][\"show\"] = True\n build_config[\"filter_operator\"][\"show\"] = True\n elif operation_name == \"Sort\":\n build_config[\"column_name\"][\"show\"] = True\n build_config[\"ascending\"][\"show\"] = True\n elif operation_name == \"Drop Column\":\n build_config[\"column_name\"][\"show\"] = True\n elif operation_name == \"Rename Column\":\n build_config[\"column_name\"][\"show\"] = True\n build_config[\"new_column_name\"][\"show\"] = True\n elif operation_name == \"Add Column\":\n build_config[\"new_column_name\"][\"show\"] = True\n build_config[\"new_column_value\"][\"show\"] = True\n elif operation_name == \"Select Columns\":\n build_config[\"columns_to_select\"][\"show\"] = True\n elif operation_name in {\"Head\", \"Tail\"}:\n build_config[\"num_rows\"][\"show\"] = True\n elif operation_name == \"Replace Value\":\n build_config[\"column_name\"][\"show\"] = True\n build_config[\"replace_value\"][\"show\"] = True\n build_config[\"replacement_value\"][\"show\"] = True\n elif operation_name == \"Drop Duplicates\":\n build_config[\"column_name\"][\"show\"] = True\n elif operation_name == \"Merge\":\n build_config[\"left_dataframe\"][\"show\"] = True\n build_config[\"right_dataframe\"][\"show\"] = True\n build_config[\"merge_on_column\"][\"show\"] = True\n build_config[\"merge_how\"][\"show\"] = True\n\n return build_config\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 perform_operation(self) -> DataFrame:\n # Handle SortableListInput format for operation (also supports legacy string format)\n operation_input = getattr(self, \"operation\", [])\n if isinstance(operation_input, list):\n op = operation_input[0].get(\"name\", \"\") if operation_input else \"\"\n else:\n op = operation_input or \"\"\n\n # Merge and Concatenate use their own inputs, not the primary df\n if op == \"Merge\":\n return self.merge_dataframes()\n if op == \"Concatenate\":\n return self.concatenate_dataframes()\n\n df_copy = self._get_primary_dataframe()\n\n # If no operation selected, return original DataFrame\n if not op:\n return df_copy\n\n if op == \"Filter\":\n return self.filter_rows_by_value(df_copy)\n if op == \"Sort\":\n return self.sort_by_column(df_copy)\n if op == \"Drop Column\":\n return self.drop_column(df_copy)\n if op == \"Rename Column\":\n return self.rename_column(df_copy)\n if op == \"Add Column\":\n return self.add_column(df_copy)\n if op == \"Select Columns\":\n return self.select_columns(df_copy)\n if op == \"Head\":\n return self.head(df_copy)\n if op == \"Tail\":\n return self.tail(df_copy)\n if op == \"Replace Value\":\n return self.replace_values(df_copy)\n if op == \"Drop Duplicates\":\n return self.drop_duplicates(df_copy)\n msg = f\"Unsupported operation: {op}\"\n logger.error(msg)\n raise ValueError(msg)\n\n def filter_rows_by_value(self, df: DataFrame) -> DataFrame:\n column = df[self.column_name]\n filter_value = self.filter_value\n\n # Handle regular DropdownInput format (just a string value)\n operator = getattr(self, \"filter_operator\", \"equals\") # Default to equals for backward compatibility\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 # Try to convert filter_value to numeric for comparison\n numeric_value = pd.to_numeric(filter_value)\n mask = column > numeric_value\n except (ValueError, TypeError):\n # If conversion fails, compare as strings\n mask = column.astype(str) > str(filter_value)\n elif operator == \"less than\":\n try:\n # Try to convert filter_value to numeric for comparison\n numeric_value = pd.to_numeric(filter_value)\n mask = column < numeric_value\n except (ValueError, TypeError):\n # If conversion fails, compare as strings\n mask = column.astype(str) < str(filter_value)\n else:\n mask = column == filter_value # Fallback to equals\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 only one DataFrame, return it\n if len(self.df) == 1:\n return self.df[0].copy()\n\n # Concatenate all DataFrames vertically\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\n Uses explicit left_dataframe and right_dataframe inputs to give the user\n deterministic control over which DataFrame is primary (left) and which\n is secondary (right) in the merge.\n \"\"\"\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\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\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 # Combine duplicate columns: use left value if exists, otherwise right value\n cols_to_drop = []\n for col in merged.columns:\n if col.endswith(\"_right\"):\n original_col = col[:-6] # Remove \"_right\" suffix\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"
- },
- "column_name": {
- "_input_type": "StrInput",
- "advanced": false,
- "display_name": "Column Name",
- "dynamic": true,
- "info": "The column name to use for the operation.",
- "list": false,
- "list_add_label": "Add More",
- "load_from_db": false,
- "name": "column_name",
- "override_skip": false,
- "placeholder": "",
- "required": false,
- "show": false,
- "title_case": false,
- "tool_mode": false,
- "trace_as_metadata": true,
- "track_in_telemetry": false,
- "type": "str",
- "value": ""
- },
- "columns_to_select": {
- "_input_type": "StrInput",
- "advanced": false,
- "display_name": "Columns to Select",
- "dynamic": true,
- "info": "",
- "list": true,
- "list_add_label": "Add More",
- "load_from_db": false,
- "name": "columns_to_select",
- "override_skip": false,
- "placeholder": "",
- "required": false,
- "show": true,
- "title_case": false,
- "tool_mode": false,
- "trace_as_metadata": true,
- "track_in_telemetry": false,
- "type": "str",
- "value": [
- "title"
- ]
- },
- "df": {
- "_input_type": "DataFrameInput",
- "advanced": false,
- "display_name": "Table",
- "dynamic": false,
- "info": "The input DataFrame to operate on. Connect multiple DataFrames for merge or concatenate operations.",
- "input_types": [
- "DataFrame",
- "Table"
- ],
- "list": true,
- "list_add_label": "Add More",
- "name": "df",
- "override_skip": false,
- "placeholder": "",
- "required": true,
- "show": true,
- "title_case": false,
- "tool_mode": false,
- "trace_as_input": true,
- "trace_as_metadata": true,
- "track_in_telemetry": false,
- "type": "other",
- "value": ""
- },
- "filter_operator": {
- "_input_type": "DropdownInput",
- "advanced": false,
- "combobox": false,
- "dialog_inputs": {},
- "display_name": "Filter Operator",
- "dynamic": true,
- "external_options": {},
- "info": "The operator to apply for filtering rows.",
- "name": "filter_operator",
- "options": [
- "equals",
- "not equals",
- "contains",
- "not contains",
- "starts with",
- "ends with",
- "greater than",
- "less than"
- ],
- "options_metadata": [],
- "override_skip": false,
- "placeholder": "",
- "required": false,
- "show": false,
- "title_case": false,
- "toggle": false,
- "tool_mode": false,
- "trace_as_metadata": true,
- "track_in_telemetry": true,
- "type": "str",
- "value": "equals"
- },
- "filter_value": {
+ "new_column_value": {
"_input_type": "MessageTextInput",
"advanced": false,
- "display_name": "Filter Value",
+ "display_name": "New Column Value",
"dynamic": true,
- "info": "The value to filter rows by.",
- "input_types": [
- "Message"
- ],
- "list": false,
- "list_add_label": "Add More",
- "load_from_db": false,
- "name": "filter_value",
- "override_skip": false,
- "placeholder": "",
- "required": false,
- "show": false,
- "title_case": false,
- "tool_mode": false,
- "trace_as_input": true,
- "trace_as_metadata": true,
- "track_in_telemetry": false,
- "type": "str",
- "value": ""
- },
- "is_refresh": false,
- "left_dataframe": {
- "_input_type": "DataFrameInput",
- "advanced": false,
- "display_name": "Left Table",
- "dynamic": true,
- "info": "The left (primary) DataFrame for merge operations. In a left merge, all rows from this table are preserved.",
- "input_types": [
- "DataFrame",
- "Table"
- ],
- "list": false,
- "list_add_label": "Add More",
- "name": "left_dataframe",
- "override_skip": false,
- "placeholder": "",
- "required": false,
- "show": false,
- "title_case": false,
- "tool_mode": false,
- "trace_as_input": true,
- "trace_as_metadata": true,
- "track_in_telemetry": false,
- "type": "other",
- "value": ""
- },
- "merge_how": {
- "_input_type": "DropdownInput",
- "advanced": false,
- "combobox": false,
- "dialog_inputs": {},
- "display_name": "Merge Type",
- "dynamic": true,
- "external_options": {},
- "info": "Type of merge: inner (intersection), outer (union), left, or right.",
- "name": "merge_how",
- "options": [
- "inner",
- "outer",
- "left",
- "right"
- ],
- "options_metadata": [],
- "override_skip": false,
- "placeholder": "",
- "required": false,
- "show": false,
- "title_case": false,
- "toggle": false,
- "tool_mode": false,
- "trace_as_metadata": true,
- "track_in_telemetry": true,
- "type": "str",
- "value": "inner"
- },
- "merge_on_column": {
- "_input_type": "StrInput",
- "advanced": false,
- "display_name": "Merge On Column",
- "dynamic": true,
- "info": "The column name to merge DataFrames on. Must exist in both DataFrames.",
- "list": false,
- "list_add_label": "Add More",
- "load_from_db": false,
- "name": "merge_on_column",
- "override_skip": false,
- "placeholder": "",
- "required": false,
- "show": false,
- "title_case": false,
- "tool_mode": false,
- "trace_as_metadata": true,
- "track_in_telemetry": false,
- "type": "str",
- "value": ""
- },
- "new_column_name": {
- "_input_type": "StrInput",
- "advanced": false,
- "display_name": "New Column Name",
- "dynamic": true,
- "info": "The new column name when renaming or adding a column.",
- "list": false,
- "list_add_label": "Add More",
- "load_from_db": false,
- "name": "new_column_name",
- "override_skip": false,
- "placeholder": "",
- "required": false,
- "show": false,
- "title_case": false,
- "tool_mode": false,
- "trace_as_metadata": true,
- "track_in_telemetry": false,
- "type": "str",
- "value": "filename"
- },
- "new_column_value": {
- "_input_type": "MessageTextInput",
- "advanced": false,
- "display_name": "New Column Value",
- "dynamic": true,
- "info": "The value to populate the new column with.",
+ "info": "The value to populate the new column with.",
"input_types": [
"Message"
],
@@ -5236,871 +4674,213 @@
"override_skip": false,
"placeholder": "",
"required": false,
- "show": false,
- "title_case": false,
- "tool_mode": false,
- "trace_as_input": true,
- "trace_as_metadata": true,
- "track_in_telemetry": false,
- "type": "str",
- "value": ""
- },
- "num_rows": {
- "_input_type": "IntInput",
- "advanced": false,
- "display_name": "Number of Rows",
- "dynamic": true,
- "info": "Number of rows to return (for head/tail).",
- "list": false,
- "list_add_label": "Add More",
- "name": "num_rows",
- "override_skip": false,
- "placeholder": "",
- "required": false,
- "show": false,
- "title_case": false,
- "tool_mode": false,
- "trace_as_metadata": true,
- "track_in_telemetry": true,
- "type": "int",
- "value": 5
- },
- "operation": {
- "_input_type": "SortableListInput",
- "advanced": false,
- "display_name": "Operation",
- "dynamic": false,
- "info": "Select the DataFrame operation to perform.",
- "limit": 1,
- "load_from_db": false,
- "name": "operation",
- "options": [
- {
- "icon": "plus",
- "name": "Add Column"
- },
- {
- "icon": "combine",
- "name": "Concatenate"
- },
- {
- "icon": "minus",
- "name": "Drop Column"
- },
- {
- "icon": "filter",
- "name": "Filter"
- },
- {
- "icon": "arrow-up",
- "name": "Head"
- },
- {
- "icon": "merge",
- "name": "Merge"
- },
- {
- "icon": "pencil",
- "name": "Rename Column"
- },
- {
- "icon": "replace",
- "name": "Replace Value"
- },
- {
- "icon": "columns",
- "name": "Select Columns"
- },
- {
- "icon": "arrow-up-down",
- "name": "Sort"
- },
- {
- "icon": "arrow-down",
- "name": "Tail"
- },
- {
- "icon": "copy-x",
- "name": "Drop Duplicates"
- }
- ],
- "override_skip": false,
- "placeholder": "Select Operation",
- "real_time_refresh": true,
- "required": false,
- "search_category": [],
- "show": true,
- "title_case": false,
- "tool_mode": false,
- "trace_as_metadata": true,
- "track_in_telemetry": false,
- "type": "sortableList",
- "value": [
- {
- "chosen": false,
- "icon": "columns",
- "name": "Select Columns",
- "selected": false
- }
- ]
- },
- "replace_value": {
- "_input_type": "MessageTextInput",
- "advanced": false,
- "display_name": "Value to Replace",
- "dynamic": true,
- "info": "The value to replace in the column.",
- "input_types": [
- "Message"
- ],
- "list": false,
- "list_add_label": "Add More",
- "load_from_db": false,
- "name": "replace_value",
- "override_skip": false,
- "placeholder": "",
- "required": false,
- "show": false,
- "title_case": false,
- "tool_mode": false,
- "trace_as_input": true,
- "trace_as_metadata": true,
- "track_in_telemetry": false,
- "type": "str",
- "value": ""
- },
- "replacement_value": {
- "_input_type": "MessageTextInput",
- "advanced": false,
- "display_name": "Replacement Value",
- "dynamic": true,
- "info": "The value to replace with.",
- "input_types": [
- "Message"
- ],
- "list": false,
- "list_add_label": "Add More",
- "load_from_db": false,
- "name": "replacement_value",
- "override_skip": false,
- "placeholder": "",
- "required": false,
- "show": false,
- "title_case": false,
- "tool_mode": false,
- "trace_as_input": true,
- "trace_as_metadata": true,
- "track_in_telemetry": false,
- "type": "str",
- "value": ""
- },
- "right_dataframe": {
- "_input_type": "DataFrameInput",
- "advanced": false,
- "display_name": "Right Table",
- "dynamic": true,
- "info": "The right (secondary) DataFrame for merge operations. In a right merge, all rows from this table are preserved.",
- "input_types": [
- "DataFrame",
- "Table"
- ],
- "list": false,
- "list_add_label": "Add More",
- "name": "right_dataframe",
- "override_skip": false,
- "placeholder": "",
- "required": false,
- "show": false,
- "title_case": false,
- "tool_mode": false,
- "trace_as_input": true,
- "trace_as_metadata": true,
- "track_in_telemetry": false,
- "type": "other",
- "value": ""
- }
- },
- "tool_mode": false
- },
- "showNode": true,
- "type": "DataFrameOperations"
- },
- "dragging": false,
- "id": "DataFrameOperations-NpdW5",
- "measured": {
- "height": 319,
- "width": 320
- },
- "position": {
- "x": 825.4722512847663,
- "y": 1474.884927217593
- },
- "selected": false,
- "type": "genericNode"
- },
- {
- "data": {
- "description": "Extracts text using a template.",
- "display_name": "Parser",
- "id": "ParserComponent-1eim1",
- "node": {
- "base_classes": [
- "Message"
- ],
- "beta": false,
- "conditional_paths": [],
- "custom_fields": {},
- "description": "Extracts text using a template.",
- "display_name": "Parser",
- "documentation": "https://docs.langflow.org/parser",
- "edited": false,
- "field_order": [
- "input_data",
- "mode",
- "pattern",
- "sep"
- ],
- "frozen": false,
- "icon": "braces",
- "legacy": false,
- "metadata": {
- "code_hash": "cda7b997a730",
- "dependencies": {
- "dependencies": [
- {
- "name": "lfx",
- "version": null
- }
- ],
- "total_dependencies": 1
- },
- "module": "custom_components.parser"
- },
- "minimized": false,
- "output_types": [],
- "outputs": [
- {
- "allows_loop": false,
- "cache": true,
- "display_name": "Parsed Text",
- "group_outputs": false,
- "loop_types": null,
- "method": "parse_combined_text",
- "name": "parsed_text",
- "options": null,
- "required_inputs": null,
- "selected": "Message",
- "tool_mode": true,
- "types": [
- "Message"
- ],
- "value": "__UNDEFINED__"
- }
- ],
- "pinned": false,
- "template": {
- "_type": "Component",
- "code": {
- "advanced": true,
- "dynamic": true,
- "fileTypes": [],
- "file_path": "",
- "info": "",
- "list": false,
- "load_from_db": false,
- "multiline": true,
- "name": "code",
- "password": false,
- "placeholder": "",
- "required": true,
- "show": true,
- "title_case": false,
- "type": "code",
- "value": "from lfx.custom.custom_component.component import Component\nfrom lfx.helpers.data import safe_convert\nfrom lfx.inputs.inputs import BoolInput, HandleInput, MessageTextInput, MultilineInput, TabInput\nfrom lfx.schema.data import Data\nfrom lfx.schema.dataframe import DataFrame\nfrom lfx.schema.message import Message\nfrom lfx.template.field.base import Output\n\n\nclass ParserComponent(Component):\n display_name = \"Parser\"\n description = \"Extracts text using a template.\"\n documentation: str = \"https://docs.langflow.org/parser\"\n icon = \"braces\"\n\n inputs = [\n HandleInput(\n name=\"input_data\",\n display_name=\"JSON or Table\",\n input_types=[\"DataFrame\", \"Table\", \"Data\", \"JSON\"],\n info=\"Accepts either a DataFrame or a Data object.\",\n required=True,\n ),\n TabInput(\n name=\"mode\",\n display_name=\"Mode\",\n options=[\"Parser\", \"Stringify\"],\n value=\"Parser\",\n info=\"Convert into raw string instead of using a template.\",\n real_time_refresh=True,\n ),\n MultilineInput(\n name=\"pattern\",\n display_name=\"Template\",\n info=(\n \"Use variables within curly brackets to extract column values for DataFrames \"\n \"or key values for Data.\"\n \"For example: `Name: {Name}, Age: {Age}, Country: {Country}`\"\n ),\n value=\"Text: {text}\", # Example default\n dynamic=True,\n show=True,\n required=True,\n ),\n MessageTextInput(\n name=\"sep\",\n display_name=\"Separator\",\n advanced=True,\n value=\"\\n\",\n info=\"String used to separate rows/items.\",\n ),\n ]\n\n outputs = [\n Output(\n display_name=\"Parsed Text\",\n name=\"parsed_text\",\n info=\"Formatted text output.\",\n method=\"parse_combined_text\",\n ),\n ]\n\n def update_build_config(self, build_config, field_value, field_name=None):\n \"\"\"Dynamically hide/show `template` and enforce requirement based on `stringify`.\"\"\"\n if field_name == \"mode\":\n build_config[\"pattern\"][\"show\"] = self.mode == \"Parser\"\n build_config[\"pattern\"][\"required\"] = self.mode == \"Parser\"\n if field_value:\n clean_data = BoolInput(\n name=\"clean_data\",\n display_name=\"Clean Data\",\n info=(\n \"Enable to clean the data by removing empty rows and lines \"\n \"in each cell of the DataFrame/ Data object.\"\n ),\n value=True,\n advanced=True,\n required=False,\n )\n build_config[\"clean_data\"] = clean_data.to_dict()\n else:\n build_config.pop(\"clean_data\", None)\n\n return build_config\n\n def _clean_args(self):\n \"\"\"Prepare arguments based on input type.\"\"\"\n input_data = self.input_data\n\n match input_data:\n case list() if all(isinstance(item, Data) for item in input_data):\n msg = \"List of Data objects is not supported.\"\n raise ValueError(msg)\n case DataFrame():\n return input_data, None\n case Data():\n return None, input_data\n case dict() if \"data\" in input_data:\n try:\n if \"columns\" in input_data: # Likely a DataFrame\n return DataFrame.from_dict(input_data), None\n # Likely a Data object\n return None, Data(**input_data)\n except (TypeError, ValueError, KeyError) as e:\n msg = f\"Invalid structured input provided: {e!s}\"\n raise ValueError(msg) from e\n case _:\n msg = f\"Unsupported input type: {type(input_data)}. Expected DataFrame or Data.\"\n raise ValueError(msg)\n\n def parse_combined_text(self) -> Message:\n \"\"\"Parse all rows/items into a single text or convert input to string if `stringify` is enabled.\"\"\"\n # Early return for stringify option\n if self.mode == \"Stringify\":\n return self.convert_to_string()\n\n df, data = self._clean_args()\n\n lines = []\n if df is not None:\n for _, row in df.iterrows():\n formatted_text = self.pattern.format(**row.to_dict())\n lines.append(formatted_text)\n elif data is not None:\n # Use format_map with a dict that returns default_value for missing keys\n class DefaultDict(dict):\n def __missing__(self, key):\n return data.default_value or \"\"\n\n formatted_text = self.pattern.format_map(DefaultDict(data.data))\n lines.append(formatted_text)\n\n combined_text = self.sep.join(lines)\n self.status = combined_text\n return Message(text=combined_text)\n\n def convert_to_string(self) -> Message:\n \"\"\"Convert input data to string with proper error handling.\"\"\"\n result = \"\"\n if isinstance(self.input_data, list):\n result = \"\\n\".join([safe_convert(item, clean_data=self.clean_data or False) for item in self.input_data])\n else:\n result = safe_convert(self.input_data or False)\n self.log(f\"Converted to string with length: {len(result)}\")\n\n message = Message(text=result)\n self.status = message\n return message\n"
- },
- "input_data": {
- "_input_type": "HandleInput",
- "advanced": false,
- "display_name": "JSON or Table",
- "dynamic": false,
- "info": "Accepts either a DataFrame or a Data object.",
- "input_types": [
- "DataFrame",
- "Table",
- "Data",
- "JSON"
- ],
- "list": false,
- "list_add_label": "Add More",
- "name": "input_data",
- "override_skip": false,
- "placeholder": "",
- "required": true,
- "show": true,
- "title_case": false,
- "trace_as_metadata": true,
- "track_in_telemetry": false,
- "type": "other",
- "value": ""
- },
- "mode": {
- "_input_type": "TabInput",
- "advanced": false,
- "display_name": "Mode",
- "dynamic": false,
- "info": "Convert into raw string instead of using a template.",
- "name": "mode",
- "options": [
- "Parser",
- "Stringify"
- ],
- "override_skip": false,
- "placeholder": "",
- "real_time_refresh": true,
- "required": false,
- "show": true,
- "title_case": false,
- "tool_mode": false,
- "trace_as_metadata": true,
- "track_in_telemetry": true,
- "type": "tab",
- "value": "Parser"
- },
- "pattern": {
- "_input_type": "MultilineInput",
- "advanced": false,
- "ai_enabled": false,
- "copy_field": false,
- "display_name": "Template",
- "dynamic": true,
- "info": "Use variables within curly brackets to extract column values for DataFrames or key values for Data.For example: `Name: {Name}, Age: {Age}, Country: {Country}`",
- "input_types": [
- "Message"
- ],
- "list": false,
- "list_add_label": "Add More",
- "load_from_db": false,
- "multiline": true,
- "name": "pattern",
- "override_skip": false,
- "password": false,
- "placeholder": "",
- "required": true,
- "show": true,
- "title_case": false,
- "tool_mode": false,
- "trace_as_input": true,
- "trace_as_metadata": true,
- "track_in_telemetry": false,
- "type": "str",
- "value": "{title}"
- },
- "sep": {
- "_input_type": "MessageTextInput",
- "advanced": true,
- "display_name": "Separator",
- "dynamic": false,
- "info": "String used to separate rows/items.",
- "input_types": [
- "Message"
- ],
- "list": false,
- "list_add_label": "Add More",
- "load_from_db": false,
- "name": "sep",
- "override_skip": false,
- "placeholder": "",
- "required": false,
- "show": true,
- "title_case": false,
- "tool_mode": false,
- "trace_as_input": true,
- "trace_as_metadata": true,
- "track_in_telemetry": false,
- "type": "str",
- "value": "\n"
- }
- },
- "tool_mode": false
- },
- "showNode": true,
- "type": "ParserComponent"
- },
- "dragging": false,
- "id": "ParserComponent-1eim1",
- "measured": {
- "height": 331,
- "width": 320
- },
- "position": {
- "x": 1197.404962798599,
- "y": 1479.7759648749616
- },
- "selected": false,
- "type": "genericNode"
- },
- {
- "data": {
- "id": "TextInput-OPyEf",
- "node": {
- "base_classes": [
- "Message"
- ],
- "beta": false,
- "conditional_paths": [],
- "custom_fields": {},
- "description": "Get user text inputs.",
- "display_name": "Text Input",
- "documentation": "https://docs.langflow.org/text-input-and-output",
- "edited": false,
- "field_order": [
- "input_value",
- "use_global_variable"
- ],
- "frozen": false,
- "icon": "type",
- "last_updated": "2026-03-05T16:40:36.785Z",
- "legacy": false,
- "metadata": {
- "code_hash": "518f16485886",
- "dependencies": {
- "dependencies": [
- {
- "name": "lfx",
- "version": null
- }
- ],
- "total_dependencies": 1
- },
- "module": "lfx.components.input_output.text.TextInputComponent"
- },
- "minimized": false,
- "output_types": [],
- "outputs": [
- {
- "allows_loop": false,
- "cache": true,
- "display_name": "Output Text",
- "group_outputs": false,
- "loop_types": null,
- "method": "text_response",
- "name": "text",
- "options": null,
- "required_inputs": null,
- "selected": "Message",
- "tool_mode": true,
- "types": [
- "Message"
- ],
- "value": "__UNDEFINED__"
- }
- ],
- "pinned": false,
- "template": {
- "_frontend_node_flow_id": {
- "value": "72c3d17c-2dac-4a73-b48a-6518473d7830"
- },
- "_frontend_node_folder_id": {
- "value": "7a54b33c-ad03-4c78-b61b-f95adbb74e17"
- },
- "_type": "Component",
- "code": {
- "advanced": true,
- "dynamic": true,
- "fileTypes": [],
- "file_path": "",
- "info": "",
- "list": false,
- "load_from_db": false,
- "multiline": true,
- "name": "code",
- "password": false,
- "placeholder": "",
- "required": true,
- "show": true,
- "title_case": false,
- "type": "code",
- "value": "from typing import Any\n\nfrom lfx.base.io.text import TextComponent\nfrom lfx.io import BoolInput, MultilineInput, Output\nfrom lfx.schema.message import Message\n\n\nclass TextInputComponent(TextComponent):\n display_name = \"Text Input\"\n description = \"Get user text inputs.\"\n documentation: str = \"https://docs.langflow.org/text-input-and-output\"\n icon = \"type\"\n name = \"TextInput\"\n\n inputs = [\n MultilineInput(\n name=\"input_value\",\n display_name=\"Text\",\n info=\"Text to be passed as input.\",\n ),\n BoolInput(\n name=\"use_global_variable\",\n display_name=\"Use Global Variable\",\n info=\"Enable to select from global variables (shows globe icon). Disables multiline editing.\",\n value=False,\n advanced=True,\n real_time_refresh=True,\n ),\n ]\n outputs = [\n Output(display_name=\"Output Text\", name=\"text\", method=\"text_response\"),\n ]\n\n def update_build_config(self, build_config: dict, field_value: Any, field_name: str | None = None) -> dict:\n if field_name == \"use_global_variable\":\n if field_value:\n # Enable global variable mode: single-line with password masking and globe dropdown\n build_config[\"input_value\"][\"multiline\"] = False\n build_config[\"input_value\"][\"password\"] = True\n else:\n # Default mode: multiline text editing\n build_config[\"input_value\"][\"multiline\"] = True\n build_config[\"input_value\"][\"password\"] = False\n return build_config\n\n def text_response(self) -> Message:\n return Message(\n text=self.input_value,\n )\n"
- },
- "input_value": {
- "_input_type": "MultilineInput",
- "advanced": false,
- "ai_enabled": false,
- "copy_field": false,
- "display_name": "Text",
- "dynamic": false,
- "info": "Text to be passed as input.",
- "input_types": [
- "Message"
- ],
- "list": false,
- "list_add_label": "Add More",
- "load_from_db": true,
- "multiline": false,
- "name": "input_value",
- "override_skip": false,
- "password": true,
- "placeholder": "",
- "required": false,
- "show": true,
- "title_case": false,
- "tool_mode": false,
- "trace_as_input": true,
- "trace_as_metadata": true,
- "track_in_telemetry": false,
- "type": "str",
- "value": "CONNECTOR_TYPE"
- },
- "is_refresh": false,
- "use_global_variable": {
- "_input_type": "BoolInput",
- "advanced": true,
- "display_name": "Use Global Variable",
- "dynamic": false,
- "info": "Enable to select from global variables (shows globe icon). Disables multiline editing.",
- "list": false,
- "list_add_label": "Add More",
- "name": "use_global_variable",
- "override_skip": false,
- "placeholder": "",
- "real_time_refresh": true,
- "required": false,
- "show": true,
- "title_case": false,
- "tool_mode": false,
- "trace_as_metadata": true,
- "track_in_telemetry": true,
- "type": "bool",
- "value": true
- }
- },
- "tool_mode": false
- },
- "showNode": false,
- "type": "TextInput"
- },
- "dragging": false,
- "id": "TextInput-OPyEf",
- "measured": {
- "height": 52,
- "width": 192
- },
- "position": {
- "x": 2046.1686011821303,
- "y": 1025.3287669019733
- },
- "selected": false,
- "type": "genericNode"
- },
- {
- "data": {
- "id": "TextInput-G5CiZ",
- "node": {
- "base_classes": [
- "Message"
- ],
- "beta": false,
- "conditional_paths": [],
- "custom_fields": {},
- "description": "Get user text inputs.",
- "display_name": "Text Input",
- "documentation": "https://docs.langflow.org/text-input-and-output",
- "edited": false,
- "field_order": [
- "input_value",
- "use_global_variable"
- ],
- "frozen": false,
- "icon": "type",
- "last_updated": "2026-03-05T16:40:36.785Z",
- "legacy": false,
- "metadata": {
- "code_hash": "518f16485886",
- "dependencies": {
- "dependencies": [
- {
- "name": "lfx",
- "version": null
- }
- ],
- "total_dependencies": 1
- },
- "module": "lfx.components.input_output.text.TextInputComponent"
- },
- "minimized": false,
- "output_types": [],
- "outputs": [
- {
- "allows_loop": false,
- "cache": true,
- "display_name": "Output Text",
- "group_outputs": false,
- "loop_types": null,
- "method": "text_response",
- "name": "text",
- "options": null,
- "required_inputs": null,
- "selected": "Message",
- "tool_mode": true,
- "types": [
- "Message"
- ],
- "value": "__UNDEFINED__"
- }
- ],
- "pinned": false,
- "template": {
- "_frontend_node_flow_id": {
- "value": "72c3d17c-2dac-4a73-b48a-6518473d7830"
- },
- "_frontend_node_folder_id": {
- "value": "7a54b33c-ad03-4c78-b61b-f95adbb74e17"
- },
- "_type": "Component",
- "code": {
- "advanced": true,
- "dynamic": true,
- "fileTypes": [],
- "file_path": "",
- "info": "",
- "list": false,
- "load_from_db": false,
- "multiline": true,
- "name": "code",
- "password": false,
- "placeholder": "",
- "required": true,
- "show": true,
- "title_case": false,
- "type": "code",
- "value": "from typing import Any\n\nfrom lfx.base.io.text import TextComponent\nfrom lfx.io import BoolInput, MultilineInput, Output\nfrom lfx.schema.message import Message\n\n\nclass TextInputComponent(TextComponent):\n display_name = \"Text Input\"\n description = \"Get user text inputs.\"\n documentation: str = \"https://docs.langflow.org/text-input-and-output\"\n icon = \"type\"\n name = \"TextInput\"\n\n inputs = [\n MultilineInput(\n name=\"input_value\",\n display_name=\"Text\",\n info=\"Text to be passed as input.\",\n ),\n BoolInput(\n name=\"use_global_variable\",\n display_name=\"Use Global Variable\",\n info=\"Enable to select from global variables (shows globe icon). Disables multiline editing.\",\n value=False,\n advanced=True,\n real_time_refresh=True,\n ),\n ]\n outputs = [\n Output(display_name=\"Output Text\", name=\"text\", method=\"text_response\"),\n ]\n\n def update_build_config(self, build_config: dict, field_value: Any, field_name: str | None = None) -> dict:\n if field_name == \"use_global_variable\":\n if field_value:\n # Enable global variable mode: single-line with password masking and globe dropdown\n build_config[\"input_value\"][\"multiline\"] = False\n build_config[\"input_value\"][\"password\"] = True\n else:\n # Default mode: multiline text editing\n build_config[\"input_value\"][\"multiline\"] = True\n build_config[\"input_value\"][\"password\"] = False\n return build_config\n\n def text_response(self) -> Message:\n return Message(\n text=self.input_value,\n )\n"
- },
- "input_value": {
- "_input_type": "MultilineInput",
- "advanced": false,
- "ai_enabled": false,
- "copy_field": false,
- "display_name": "Text",
- "dynamic": false,
- "info": "Text to be passed as input.",
- "input_types": [
- "Message"
- ],
- "list": false,
- "list_add_label": "Add More",
- "load_from_db": true,
- "multiline": false,
- "name": "input_value",
- "override_skip": false,
- "password": true,
- "placeholder": "",
- "required": false,
- "show": true,
+ "show": false,
"title_case": false,
"tool_mode": false,
"trace_as_input": true,
"trace_as_metadata": true,
"track_in_telemetry": false,
"type": "str",
- "value": "OWNER"
+ "value": ""
},
- "is_refresh": false,
- "use_global_variable": {
- "_input_type": "BoolInput",
- "advanced": true,
- "display_name": "Use Global Variable",
- "dynamic": false,
- "info": "Enable to select from global variables (shows globe icon). Disables multiline editing.",
+ "num_rows": {
+ "_input_type": "IntInput",
+ "advanced": false,
+ "display_name": "Number of Rows",
+ "dynamic": true,
+ "info": "Number of rows to return (for head/tail).",
"list": false,
"list_add_label": "Add More",
- "name": "use_global_variable",
+ "name": "num_rows",
"override_skip": false,
"placeholder": "",
- "real_time_refresh": true,
"required": false,
- "show": true,
+ "show": false,
"title_case": false,
"tool_mode": false,
"trace_as_metadata": true,
"track_in_telemetry": true,
- "type": "bool",
- "value": true
- }
- },
- "tool_mode": false
- },
- "showNode": false,
- "type": "TextInput"
- },
- "dragging": false,
- "id": "TextInput-G5CiZ",
- "measured": {
- "height": 52,
- "width": 192
- },
- "position": {
- "x": 2047.7721855431944,
- "y": 1107.9760140854928
- },
- "selected": false,
- "type": "genericNode"
- },
- {
- "data": {
- "id": "TextInput-Rm9YX",
- "node": {
- "base_classes": [
- "Message"
- ],
- "beta": false,
- "conditional_paths": [],
- "custom_fields": {},
- "description": "Get user text inputs.",
- "display_name": "Text Input",
- "documentation": "https://docs.langflow.org/text-input-and-output",
- "edited": false,
- "field_order": [
- "input_value",
- "use_global_variable"
- ],
- "frozen": false,
- "icon": "type",
- "last_updated": "2026-03-05T16:40:36.785Z",
- "legacy": false,
- "metadata": {
- "code_hash": "518f16485886",
- "dependencies": {
- "dependencies": [
+ "type": "int",
+ "value": 5
+ },
+ "operation": {
+ "_input_type": "SortableListInput",
+ "advanced": false,
+ "display_name": "Operation",
+ "dynamic": false,
+ "info": "Select the DataFrame operation to perform.",
+ "limit": 1,
+ "load_from_db": false,
+ "name": "operation",
+ "options": [
{
- "name": "lfx",
- "version": null
+ "icon": "plus",
+ "name": "Add Column"
+ },
+ {
+ "icon": "combine",
+ "name": "Concatenate"
+ },
+ {
+ "icon": "minus",
+ "name": "Drop Column"
+ },
+ {
+ "icon": "filter",
+ "name": "Filter"
+ },
+ {
+ "icon": "arrow-up",
+ "name": "Head"
+ },
+ {
+ "icon": "merge",
+ "name": "Merge"
+ },
+ {
+ "icon": "pencil",
+ "name": "Rename Column"
+ },
+ {
+ "icon": "replace",
+ "name": "Replace Value"
+ },
+ {
+ "icon": "columns",
+ "name": "Select Columns"
+ },
+ {
+ "icon": "arrow-up-down",
+ "name": "Sort"
+ },
+ {
+ "icon": "arrow-down",
+ "name": "Tail"
+ },
+ {
+ "icon": "copy-x",
+ "name": "Drop Duplicates"
}
],
- "total_dependencies": 1
+ "override_skip": false,
+ "placeholder": "Select Operation",
+ "real_time_refresh": true,
+ "required": false,
+ "search_category": [],
+ "show": true,
+ "title_case": false,
+ "tool_mode": false,
+ "trace_as_metadata": true,
+ "track_in_telemetry": false,
+ "type": "sortableList",
+ "value": [
+ {
+ "chosen": false,
+ "icon": "columns",
+ "name": "Select Columns",
+ "selected": false
+ }
+ ]
},
- "module": "lfx.components.input_output.text.TextInputComponent"
- },
- "minimized": false,
- "output_types": [],
- "outputs": [
- {
- "allows_loop": false,
- "cache": true,
- "display_name": "Output Text",
- "group_outputs": false,
- "loop_types": null,
- "method": "text_response",
- "name": "text",
- "options": null,
- "required_inputs": null,
- "selected": "Message",
- "tool_mode": true,
- "types": [
+ "replace_value": {
+ "_input_type": "MessageTextInput",
+ "advanced": false,
+ "display_name": "Value to Replace",
+ "dynamic": true,
+ "info": "The value to replace in the column.",
+ "input_types": [
"Message"
],
- "value": "__UNDEFINED__"
- }
- ],
- "pinned": false,
- "template": {
- "_frontend_node_flow_id": {
- "value": "72c3d17c-2dac-4a73-b48a-6518473d7830"
- },
- "_frontend_node_folder_id": {
- "value": "7a54b33c-ad03-4c78-b61b-f95adbb74e17"
- },
- "_type": "Component",
- "code": {
- "advanced": true,
- "dynamic": true,
- "fileTypes": [],
- "file_path": "",
- "info": "",
"list": false,
+ "list_add_label": "Add More",
"load_from_db": false,
- "multiline": true,
- "name": "code",
- "password": false,
+ "name": "replace_value",
+ "override_skip": false,
"placeholder": "",
- "required": true,
- "show": true,
+ "required": false,
+ "show": false,
"title_case": false,
- "type": "code",
- "value": "from typing import Any\n\nfrom lfx.base.io.text import TextComponent\nfrom lfx.io import BoolInput, MultilineInput, Output\nfrom lfx.schema.message import Message\n\n\nclass TextInputComponent(TextComponent):\n display_name = \"Text Input\"\n description = \"Get user text inputs.\"\n documentation: str = \"https://docs.langflow.org/text-input-and-output\"\n icon = \"type\"\n name = \"TextInput\"\n\n inputs = [\n MultilineInput(\n name=\"input_value\",\n display_name=\"Text\",\n info=\"Text to be passed as input.\",\n ),\n BoolInput(\n name=\"use_global_variable\",\n display_name=\"Use Global Variable\",\n info=\"Enable to select from global variables (shows globe icon). Disables multiline editing.\",\n value=False,\n advanced=True,\n real_time_refresh=True,\n ),\n ]\n outputs = [\n Output(display_name=\"Output Text\", name=\"text\", method=\"text_response\"),\n ]\n\n def update_build_config(self, build_config: dict, field_value: Any, field_name: str | None = None) -> dict:\n if field_name == \"use_global_variable\":\n if field_value:\n # Enable global variable mode: single-line with password masking and globe dropdown\n build_config[\"input_value\"][\"multiline\"] = False\n build_config[\"input_value\"][\"password\"] = True\n else:\n # Default mode: multiline text editing\n build_config[\"input_value\"][\"multiline\"] = True\n build_config[\"input_value\"][\"password\"] = False\n return build_config\n\n def text_response(self) -> Message:\n return Message(\n text=self.input_value,\n )\n"
+ "tool_mode": false,
+ "trace_as_input": true,
+ "trace_as_metadata": true,
+ "track_in_telemetry": false,
+ "type": "str",
+ "value": ""
},
- "input_value": {
- "_input_type": "MultilineInput",
+ "replacement_value": {
+ "_input_type": "MessageTextInput",
"advanced": false,
- "ai_enabled": false,
- "copy_field": false,
- "display_name": "Text",
- "dynamic": false,
- "info": "Text to be passed as input.",
+ "display_name": "Replacement Value",
+ "dynamic": true,
+ "info": "The value to replace with.",
"input_types": [
"Message"
],
"list": false,
"list_add_label": "Add More",
- "load_from_db": true,
- "multiline": false,
- "name": "input_value",
+ "load_from_db": false,
+ "name": "replacement_value",
"override_skip": false,
- "password": true,
"placeholder": "",
"required": false,
- "show": true,
+ "show": false,
"title_case": false,
"tool_mode": false,
"trace_as_input": true,
"trace_as_metadata": true,
"track_in_telemetry": false,
"type": "str",
- "value": "OWNER_EMAIL"
+ "value": ""
},
- "is_refresh": false,
- "use_global_variable": {
- "_input_type": "BoolInput",
- "advanced": true,
- "display_name": "Use Global Variable",
- "dynamic": false,
- "info": "Enable to select from global variables (shows globe icon). Disables multiline editing.",
+ "right_dataframe": {
+ "_input_type": "DataFrameInput",
+ "advanced": false,
+ "display_name": "Right Table",
+ "dynamic": true,
+ "info": "The right (secondary) DataFrame for merge operations. In a right merge, all rows from this table are preserved.",
+ "input_types": [
+ "DataFrame",
+ "Table"
+ ],
"list": false,
"list_add_label": "Add More",
- "name": "use_global_variable",
+ "name": "right_dataframe",
"override_skip": false,
"placeholder": "",
- "real_time_refresh": true,
"required": false,
- "show": true,
+ "show": false,
"title_case": false,
"tool_mode": false,
+ "trace_as_input": true,
"trace_as_metadata": true,
- "track_in_telemetry": true,
- "type": "bool",
- "value": true
+ "track_in_telemetry": false,
+ "type": "other",
+ "value": ""
}
},
"tool_mode": false
},
- "showNode": false,
- "type": "TextInput"
+ "showNode": true,
+ "type": "DataFrameOperations"
},
"dragging": false,
- "id": "TextInput-Rm9YX",
+ "id": "DataFrameOperations-NpdW5",
"measured": {
- "height": 52,
- "width": 192
+ "height": 319,
+ "width": 320
},
"position": {
- "x": 2046.9016349798983,
- "y": 1190.6783175986243
+ "x": 825.4722512847663,
+ "y": 1474.884927217593
},
"selected": false,
"type": "genericNode"
},
{
"data": {
- "id": "TextInput-tahMb",
+ "description": "Extracts text using a template.",
+ "display_name": "Parser",
+ "id": "ParserComponent-1eim1",
"node": {
"base_classes": [
"Message"
@@ -6108,20 +4888,21 @@
"beta": false,
"conditional_paths": [],
"custom_fields": {},
- "description": "Get user text inputs.",
- "display_name": "Text Input",
- "documentation": "https://docs.langflow.org/text-input-and-output",
+ "description": "Extracts text using a template.",
+ "display_name": "Parser",
+ "documentation": "https://docs.langflow.org/parser",
"edited": false,
"field_order": [
- "input_value",
- "use_global_variable"
+ "input_data",
+ "mode",
+ "pattern",
+ "sep"
],
"frozen": false,
- "icon": "type",
- "last_updated": "2026-03-05T16:40:36.785Z",
+ "icon": "braces",
"legacy": false,
"metadata": {
- "code_hash": "518f16485886",
+ "code_hash": "cda7b997a730",
"dependencies": {
"dependencies": [
{
@@ -6131,7 +4912,7 @@
],
"total_dependencies": 1
},
- "module": "lfx.components.input_output.text.TextInputComponent"
+ "module": "custom_components.parser"
},
"minimized": false,
"output_types": [],
@@ -6139,11 +4920,11 @@
{
"allows_loop": false,
"cache": true,
- "display_name": "Output Text",
+ "display_name": "Parsed Text",
"group_outputs": false,
"loop_types": null,
- "method": "text_response",
- "name": "text",
+ "method": "parse_combined_text",
+ "name": "parsed_text",
"options": null,
"required_inputs": null,
"selected": "Message",
@@ -6156,12 +4937,6 @@
],
"pinned": false,
"template": {
- "_frontend_node_flow_id": {
- "value": "72c3d17c-2dac-4a73-b48a-6518473d7830"
- },
- "_frontend_node_folder_id": {
- "value": "7a54b33c-ad03-4c78-b61b-f95adbb74e17"
- },
"_type": "Component",
"code": {
"advanced": true,
@@ -6179,28 +4954,76 @@
"show": true,
"title_case": false,
"type": "code",
- "value": "from typing import Any\n\nfrom lfx.base.io.text import TextComponent\nfrom lfx.io import BoolInput, MultilineInput, Output\nfrom lfx.schema.message import Message\n\n\nclass TextInputComponent(TextComponent):\n display_name = \"Text Input\"\n description = \"Get user text inputs.\"\n documentation: str = \"https://docs.langflow.org/text-input-and-output\"\n icon = \"type\"\n name = \"TextInput\"\n\n inputs = [\n MultilineInput(\n name=\"input_value\",\n display_name=\"Text\",\n info=\"Text to be passed as input.\",\n ),\n BoolInput(\n name=\"use_global_variable\",\n display_name=\"Use Global Variable\",\n info=\"Enable to select from global variables (shows globe icon). Disables multiline editing.\",\n value=False,\n advanced=True,\n real_time_refresh=True,\n ),\n ]\n outputs = [\n Output(display_name=\"Output Text\", name=\"text\", method=\"text_response\"),\n ]\n\n def update_build_config(self, build_config: dict, field_value: Any, field_name: str | None = None) -> dict:\n if field_name == \"use_global_variable\":\n if field_value:\n # Enable global variable mode: single-line with password masking and globe dropdown\n build_config[\"input_value\"][\"multiline\"] = False\n build_config[\"input_value\"][\"password\"] = True\n else:\n # Default mode: multiline text editing\n build_config[\"input_value\"][\"multiline\"] = True\n build_config[\"input_value\"][\"password\"] = False\n return build_config\n\n def text_response(self) -> Message:\n return Message(\n text=self.input_value,\n )\n"
+ "value": "from lfx.custom.custom_component.component import Component\nfrom lfx.helpers.data import safe_convert\nfrom lfx.inputs.inputs import BoolInput, HandleInput, MessageTextInput, MultilineInput, TabInput\nfrom lfx.schema.data import Data\nfrom lfx.schema.dataframe import DataFrame\nfrom lfx.schema.message import Message\nfrom lfx.template.field.base import Output\n\n\nclass ParserComponent(Component):\n display_name = \"Parser\"\n description = \"Extracts text using a template.\"\n documentation: str = \"https://docs.langflow.org/parser\"\n icon = \"braces\"\n\n inputs = [\n HandleInput(\n name=\"input_data\",\n display_name=\"JSON or Table\",\n input_types=[\"DataFrame\", \"Table\", \"Data\", \"JSON\"],\n info=\"Accepts either a DataFrame or a Data object.\",\n required=True,\n ),\n TabInput(\n name=\"mode\",\n display_name=\"Mode\",\n options=[\"Parser\", \"Stringify\"],\n value=\"Parser\",\n info=\"Convert into raw string instead of using a template.\",\n real_time_refresh=True,\n ),\n MultilineInput(\n name=\"pattern\",\n display_name=\"Template\",\n info=(\n \"Use variables within curly brackets to extract column values for DataFrames \"\n \"or key values for Data.\"\n \"For example: `Name: {Name}, Age: {Age}, Country: {Country}`\"\n ),\n value=\"Text: {text}\", # Example default\n dynamic=True,\n show=True,\n required=True,\n ),\n MessageTextInput(\n name=\"sep\",\n display_name=\"Separator\",\n advanced=True,\n value=\"\\n\",\n info=\"String used to separate rows/items.\",\n ),\n ]\n\n outputs = [\n Output(\n display_name=\"Parsed Text\",\n name=\"parsed_text\",\n info=\"Formatted text output.\",\n method=\"parse_combined_text\",\n ),\n ]\n\n def update_build_config(self, build_config, field_value, field_name=None):\n \"\"\"Dynamically hide/show `template` and enforce requirement based on `stringify`.\"\"\"\n if field_name == \"mode\":\n build_config[\"pattern\"][\"show\"] = self.mode == \"Parser\"\n build_config[\"pattern\"][\"required\"] = self.mode == \"Parser\"\n if field_value:\n clean_data = BoolInput(\n name=\"clean_data\",\n display_name=\"Clean Data\",\n info=(\n \"Enable to clean the data by removing empty rows and lines \"\n \"in each cell of the DataFrame/ Data object.\"\n ),\n value=True,\n advanced=True,\n required=False,\n )\n build_config[\"clean_data\"] = clean_data.to_dict()\n else:\n build_config.pop(\"clean_data\", None)\n\n return build_config\n\n def _clean_args(self):\n \"\"\"Prepare arguments based on input type.\"\"\"\n input_data = self.input_data\n\n match input_data:\n case list() if all(isinstance(item, Data) for item in input_data):\n msg = \"List of Data objects is not supported.\"\n raise ValueError(msg)\n case DataFrame():\n return input_data, None\n case Data():\n return None, input_data\n case dict() if \"data\" in input_data:\n try:\n if \"columns\" in input_data: # Likely a DataFrame\n return DataFrame.from_dict(input_data), None\n # Likely a Data object\n return None, Data(**input_data)\n except (TypeError, ValueError, KeyError) as e:\n msg = f\"Invalid structured input provided: {e!s}\"\n raise ValueError(msg) from e\n case _:\n msg = f\"Unsupported input type: {type(input_data)}. Expected DataFrame or Data.\"\n raise ValueError(msg)\n\n def parse_combined_text(self) -> Message:\n \"\"\"Parse all rows/items into a single text or convert input to string if `stringify` is enabled.\"\"\"\n # Early return for stringify option\n if self.mode == \"Stringify\":\n return self.convert_to_string()\n\n df, data = self._clean_args()\n\n lines = []\n if df is not None:\n for _, row in df.iterrows():\n formatted_text = self.pattern.format(**row.to_dict())\n lines.append(formatted_text)\n elif data is not None:\n # Use format_map with a dict that returns default_value for missing keys\n class DefaultDict(dict):\n def __missing__(self, key):\n return data.default_value or \"\"\n\n formatted_text = self.pattern.format_map(DefaultDict(data.data))\n lines.append(formatted_text)\n\n combined_text = self.sep.join(lines)\n self.status = combined_text\n return Message(text=combined_text)\n\n def convert_to_string(self) -> Message:\n \"\"\"Convert input data to string with proper error handling.\"\"\"\n result = \"\"\n if isinstance(self.input_data, list):\n result = \"\\n\".join([safe_convert(item, clean_data=self.clean_data or False) for item in self.input_data])\n else:\n result = safe_convert(self.input_data or False)\n self.log(f\"Converted to string with length: {len(result)}\")\n\n message = Message(text=result)\n self.status = message\n return message\n"
},
- "input_value": {
+ "input_data": {
+ "_input_type": "HandleInput",
+ "advanced": false,
+ "display_name": "JSON or Table",
+ "dynamic": false,
+ "info": "Accepts either a DataFrame or a Data object.",
+ "input_types": [
+ "DataFrame",
+ "Table",
+ "Data",
+ "JSON"
+ ],
+ "list": false,
+ "list_add_label": "Add More",
+ "name": "input_data",
+ "override_skip": false,
+ "placeholder": "",
+ "required": true,
+ "show": true,
+ "title_case": false,
+ "trace_as_metadata": true,
+ "track_in_telemetry": false,
+ "type": "other",
+ "value": ""
+ },
+ "mode": {
+ "_input_type": "TabInput",
+ "advanced": false,
+ "display_name": "Mode",
+ "dynamic": false,
+ "info": "Convert into raw string instead of using a template.",
+ "name": "mode",
+ "options": [
+ "Parser",
+ "Stringify"
+ ],
+ "override_skip": false,
+ "placeholder": "",
+ "real_time_refresh": true,
+ "required": false,
+ "show": true,
+ "title_case": false,
+ "tool_mode": false,
+ "trace_as_metadata": true,
+ "track_in_telemetry": true,
+ "type": "tab",
+ "value": "Parser"
+ },
+ "pattern": {
"_input_type": "MultilineInput",
"advanced": false,
"ai_enabled": false,
"copy_field": false,
- "display_name": "Text",
- "dynamic": false,
- "info": "Text to be passed as input.",
+ "display_name": "Template",
+ "dynamic": true,
+ "info": "Use variables within curly brackets to extract column values for DataFrames or key values for Data.For example: `Name: {Name}, Age: {Age}, Country: {Country}`",
"input_types": [
"Message"
],
"list": false,
"list_add_label": "Add More",
- "load_from_db": true,
- "multiline": false,
- "name": "input_value",
+ "load_from_db": false,
+ "multiline": true,
+ "name": "pattern",
"override_skip": false,
- "password": true,
+ "password": false,
"placeholder": "",
- "required": false,
+ "required": true,
"show": true,
"title_case": false,
"tool_mode": false,
@@ -6208,45 +5031,48 @@
"trace_as_metadata": true,
"track_in_telemetry": false,
"type": "str",
- "value": "OWNER_NAME"
+ "value": "{title}"
},
- "is_refresh": false,
- "use_global_variable": {
- "_input_type": "BoolInput",
+ "sep": {
+ "_input_type": "MessageTextInput",
"advanced": true,
- "display_name": "Use Global Variable",
+ "display_name": "Separator",
"dynamic": false,
- "info": "Enable to select from global variables (shows globe icon). Disables multiline editing.",
+ "info": "String used to separate rows/items.",
+ "input_types": [
+ "Message"
+ ],
"list": false,
"list_add_label": "Add More",
- "name": "use_global_variable",
+ "load_from_db": false,
+ "name": "sep",
"override_skip": false,
"placeholder": "",
- "real_time_refresh": true,
"required": false,
"show": true,
"title_case": false,
"tool_mode": false,
+ "trace_as_input": true,
"trace_as_metadata": true,
- "track_in_telemetry": true,
- "type": "bool",
- "value": true
+ "track_in_telemetry": false,
+ "type": "str",
+ "value": "\n"
}
},
"tool_mode": false
},
- "showNode": false,
- "type": "TextInput"
+ "showNode": true,
+ "type": "ParserComponent"
},
"dragging": false,
- "id": "TextInput-tahMb",
+ "id": "ParserComponent-1eim1",
"measured": {
- "height": 52,
- "width": 192
+ "height": 331,
+ "width": 320
},
"position": {
- "x": 2046.9016349798978,
- "y": 1271.6395199851643
+ "x": 1197.404962798599,
+ "y": 1479.7759648749616
},
"selected": false,
"type": "genericNode"
@@ -6329,7 +5155,7 @@
"value": "72c3d17c-2dac-4a73-b48a-6518473d7830"
},
"_frontend_node_folder_id": {
- "value": "79f95013-41e9-4a4f-af49-f07ec1fac77a"
+ "value": "dcac372c-a803-4877-8e1a-83e9adcd2972"
},
"_type": "Component",
"api_base": {
@@ -6408,7 +5234,7 @@
"trace_as_metadata": true,
"track_in_telemetry": true,
"type": "str",
- "value": "https://us-south.ml.cloud.ibm.com"
+ "value": ""
},
"chunk_size": {
"_input_type": "IntInput",
@@ -6488,7 +5314,7 @@
"type": "bool",
"value": true
},
- "is_refresh": false,
+ "is_refresh": true,
"max_retries": {
"_input_type": "IntInput",
"advanced": true,
@@ -6597,96 +5423,6 @@
},
"name": "text-embedding-ada-002",
"provider": "OpenAI"
- },
- {
- "category": "IBM WatsonX",
- "icon": "WatsonxAI",
- "metadata": {
- "embedding_class": "WatsonxEmbeddings",
- "model_type": "embeddings",
- "param_mapping": {
- "api_key": "apikey",
- "model_id": "model_id",
- "project_id": "project_id",
- "request_timeout": "request_timeout",
- "space_id": "space_id",
- "url": "url"
- }
- },
- "name": "ibm/granite-embedding-278m-multilingual",
- "provider": "IBM WatsonX"
- },
- {
- "category": "IBM WatsonX",
- "icon": "WatsonxAI",
- "metadata": {
- "embedding_class": "WatsonxEmbeddings",
- "model_type": "embeddings",
- "param_mapping": {
- "api_key": "apikey",
- "model_id": "model_id",
- "project_id": "project_id",
- "request_timeout": "request_timeout",
- "space_id": "space_id",
- "url": "url"
- }
- },
- "name": "ibm/slate-125m-english-rtrvr-v2",
- "provider": "IBM WatsonX"
- },
- {
- "category": "IBM WatsonX",
- "icon": "WatsonxAI",
- "metadata": {
- "embedding_class": "WatsonxEmbeddings",
- "model_type": "embeddings",
- "param_mapping": {
- "api_key": "apikey",
- "model_id": "model_id",
- "project_id": "project_id",
- "request_timeout": "request_timeout",
- "space_id": "space_id",
- "url": "url"
- }
- },
- "name": "ibm/slate-30m-english-rtrvr-v2",
- "provider": "IBM WatsonX"
- },
- {
- "category": "IBM WatsonX",
- "icon": "WatsonxAI",
- "metadata": {
- "embedding_class": "WatsonxEmbeddings",
- "model_type": "embeddings",
- "param_mapping": {
- "api_key": "apikey",
- "model_id": "model_id",
- "project_id": "project_id",
- "request_timeout": "request_timeout",
- "space_id": "space_id",
- "url": "url"
- }
- },
- "name": "intfloat/multilingual-e5-large",
- "provider": "IBM WatsonX"
- },
- {
- "category": "IBM WatsonX",
- "icon": "WatsonxAI",
- "metadata": {
- "embedding_class": "WatsonxEmbeddings",
- "model_type": "embeddings",
- "param_mapping": {
- "api_key": "apikey",
- "model_id": "model_id",
- "project_id": "project_id",
- "request_timeout": "request_timeout",
- "space_id": "space_id",
- "url": "url"
- }
- },
- "name": "sentence-transformers/all-minilm-l6-v2",
- "provider": "IBM WatsonX"
}
],
"override_skip": false,
@@ -6702,6 +5438,7 @@
"type": "model",
"value": [
{
+ "category": "OpenAI",
"icon": "OpenAI",
"metadata": {
"embedding_class": "OpenAIEmbeddings",
@@ -6776,7 +5513,7 @@
],
"list": false,
"list_add_label": "Add More",
- "load_from_db": true,
+ "load_from_db": false,
"name": "project_id",
"override_skip": false,
"placeholder": "",
@@ -6788,7 +5525,7 @@
"trace_as_metadata": true,
"track_in_telemetry": false,
"type": "str",
- "value": "WATSONX_PROJECT_ID"
+ "value": ""
},
"request_timeout": {
"_input_type": "FloatInput",
@@ -6947,7 +5684,7 @@
"value": "72c3d17c-2dac-4a73-b48a-6518473d7830"
},
"_frontend_node_folder_id": {
- "value": "79f95013-41e9-4a4f-af49-f07ec1fac77a"
+ "value": "dcac372c-a803-4877-8e1a-83e9adcd2972"
},
"_type": "Component",
"api_base": {
@@ -7026,7 +5763,7 @@
"trace_as_metadata": true,
"track_in_telemetry": true,
"type": "str",
- "value": "https://us-south.ml.cloud.ibm.com"
+ "value": ""
},
"chunk_size": {
"_input_type": "IntInput",
@@ -7106,7 +5843,7 @@
"type": "bool",
"value": true
},
- "is_refresh": false,
+ "is_refresh": true,
"max_retries": {
"_input_type": "IntInput",
"advanced": true,
@@ -7215,96 +5952,6 @@
},
"name": "text-embedding-ada-002",
"provider": "OpenAI"
- },
- {
- "category": "IBM WatsonX",
- "icon": "WatsonxAI",
- "metadata": {
- "embedding_class": "WatsonxEmbeddings",
- "model_type": "embeddings",
- "param_mapping": {
- "api_key": "apikey",
- "model_id": "model_id",
- "project_id": "project_id",
- "request_timeout": "request_timeout",
- "space_id": "space_id",
- "url": "url"
- }
- },
- "name": "ibm/granite-embedding-278m-multilingual",
- "provider": "IBM WatsonX"
- },
- {
- "category": "IBM WatsonX",
- "icon": "WatsonxAI",
- "metadata": {
- "embedding_class": "WatsonxEmbeddings",
- "model_type": "embeddings",
- "param_mapping": {
- "api_key": "apikey",
- "model_id": "model_id",
- "project_id": "project_id",
- "request_timeout": "request_timeout",
- "space_id": "space_id",
- "url": "url"
- }
- },
- "name": "ibm/slate-125m-english-rtrvr-v2",
- "provider": "IBM WatsonX"
- },
- {
- "category": "IBM WatsonX",
- "icon": "WatsonxAI",
- "metadata": {
- "embedding_class": "WatsonxEmbeddings",
- "model_type": "embeddings",
- "param_mapping": {
- "api_key": "apikey",
- "model_id": "model_id",
- "project_id": "project_id",
- "request_timeout": "request_timeout",
- "space_id": "space_id",
- "url": "url"
- }
- },
- "name": "ibm/slate-30m-english-rtrvr-v2",
- "provider": "IBM WatsonX"
- },
- {
- "category": "IBM WatsonX",
- "icon": "WatsonxAI",
- "metadata": {
- "embedding_class": "WatsonxEmbeddings",
- "model_type": "embeddings",
- "param_mapping": {
- "api_key": "apikey",
- "model_id": "model_id",
- "project_id": "project_id",
- "request_timeout": "request_timeout",
- "space_id": "space_id",
- "url": "url"
- }
- },
- "name": "intfloat/multilingual-e5-large",
- "provider": "IBM WatsonX"
- },
- {
- "category": "IBM WatsonX",
- "icon": "WatsonxAI",
- "metadata": {
- "embedding_class": "WatsonxEmbeddings",
- "model_type": "embeddings",
- "param_mapping": {
- "api_key": "apikey",
- "model_id": "model_id",
- "project_id": "project_id",
- "request_timeout": "request_timeout",
- "space_id": "space_id",
- "url": "url"
- }
- },
- "name": "sentence-transformers/all-minilm-l6-v2",
- "provider": "IBM WatsonX"
}
],
"override_skip": false,
@@ -7320,6 +5967,7 @@
"type": "model",
"value": [
{
+ "category": "OpenAI",
"icon": "OpenAI",
"metadata": {
"embedding_class": "OpenAIEmbeddings",
@@ -7394,7 +6042,7 @@
],
"list": false,
"list_add_label": "Add More",
- "load_from_db": true,
+ "load_from_db": false,
"name": "project_id",
"override_skip": false,
"placeholder": "",
@@ -7406,7 +6054,7 @@
"trace_as_metadata": true,
"track_in_telemetry": false,
"type": "str",
- "value": "WATSONX_PROJECT_ID"
+ "value": ""
},
"request_timeout": {
"_input_type": "FloatInput",
@@ -7565,7 +6213,7 @@
"value": "72c3d17c-2dac-4a73-b48a-6518473d7830"
},
"_frontend_node_folder_id": {
- "value": "79f95013-41e9-4a4f-af49-f07ec1fac77a"
+ "value": "dcac372c-a803-4877-8e1a-83e9adcd2972"
},
"_type": "Component",
"api_base": {
@@ -7644,7 +6292,7 @@
"trace_as_metadata": true,
"track_in_telemetry": true,
"type": "str",
- "value": "https://us-south.ml.cloud.ibm.com"
+ "value": ""
},
"chunk_size": {
"_input_type": "IntInput",
@@ -7724,7 +6372,7 @@
"type": "bool",
"value": true
},
- "is_refresh": false,
+ "is_refresh": true,
"max_retries": {
"_input_type": "IntInput",
"advanced": true,
@@ -7783,146 +6431,56 @@
"chunk_size": "chunk_size",
"dimensions": "dimensions",
"max_retries": "max_retries",
- "model": "model",
- "model_kwargs": "model_kwargs",
- "request_timeout": "timeout",
- "show_progress_bar": "show_progress_bar"
- }
- },
- "name": "text-embedding-3-small",
- "provider": "OpenAI"
- },
- {
- "category": "OpenAI",
- "icon": "OpenAI",
- "metadata": {
- "embedding_class": "OpenAIEmbeddings",
- "model_type": "embeddings",
- "param_mapping": {
- "api_base": "base_url",
- "api_key": "api_key",
- "chunk_size": "chunk_size",
- "dimensions": "dimensions",
- "max_retries": "max_retries",
- "model": "model",
- "model_kwargs": "model_kwargs",
- "request_timeout": "timeout",
- "show_progress_bar": "show_progress_bar"
- }
- },
- "name": "text-embedding-3-large",
- "provider": "OpenAI"
- },
- {
- "category": "OpenAI",
- "icon": "OpenAI",
- "metadata": {
- "embedding_class": "OpenAIEmbeddings",
- "model_type": "embeddings",
- "param_mapping": {
- "api_base": "base_url",
- "api_key": "api_key",
- "chunk_size": "chunk_size",
- "dimensions": "dimensions",
- "max_retries": "max_retries",
- "model": "model",
- "model_kwargs": "model_kwargs",
- "request_timeout": "timeout",
- "show_progress_bar": "show_progress_bar"
- }
- },
- "name": "text-embedding-ada-002",
- "provider": "OpenAI"
- },
- {
- "category": "IBM WatsonX",
- "icon": "WatsonxAI",
- "metadata": {
- "embedding_class": "WatsonxEmbeddings",
- "model_type": "embeddings",
- "param_mapping": {
- "api_key": "apikey",
- "model_id": "model_id",
- "project_id": "project_id",
- "request_timeout": "request_timeout",
- "space_id": "space_id",
- "url": "url"
- }
- },
- "name": "ibm/granite-embedding-278m-multilingual",
- "provider": "IBM WatsonX"
- },
- {
- "category": "IBM WatsonX",
- "icon": "WatsonxAI",
- "metadata": {
- "embedding_class": "WatsonxEmbeddings",
- "model_type": "embeddings",
- "param_mapping": {
- "api_key": "apikey",
- "model_id": "model_id",
- "project_id": "project_id",
- "request_timeout": "request_timeout",
- "space_id": "space_id",
- "url": "url"
- }
- },
- "name": "ibm/slate-125m-english-rtrvr-v2",
- "provider": "IBM WatsonX"
- },
- {
- "category": "IBM WatsonX",
- "icon": "WatsonxAI",
- "metadata": {
- "embedding_class": "WatsonxEmbeddings",
- "model_type": "embeddings",
- "param_mapping": {
- "api_key": "apikey",
- "model_id": "model_id",
- "project_id": "project_id",
- "request_timeout": "request_timeout",
- "space_id": "space_id",
- "url": "url"
+ "model": "model",
+ "model_kwargs": "model_kwargs",
+ "request_timeout": "timeout",
+ "show_progress_bar": "show_progress_bar"
}
},
- "name": "ibm/slate-30m-english-rtrvr-v2",
- "provider": "IBM WatsonX"
+ "name": "text-embedding-3-small",
+ "provider": "OpenAI"
},
{
- "category": "IBM WatsonX",
- "icon": "WatsonxAI",
+ "category": "OpenAI",
+ "icon": "OpenAI",
"metadata": {
- "embedding_class": "WatsonxEmbeddings",
+ "embedding_class": "OpenAIEmbeddings",
"model_type": "embeddings",
"param_mapping": {
- "api_key": "apikey",
- "model_id": "model_id",
- "project_id": "project_id",
- "request_timeout": "request_timeout",
- "space_id": "space_id",
- "url": "url"
+ "api_base": "base_url",
+ "api_key": "api_key",
+ "chunk_size": "chunk_size",
+ "dimensions": "dimensions",
+ "max_retries": "max_retries",
+ "model": "model",
+ "model_kwargs": "model_kwargs",
+ "request_timeout": "timeout",
+ "show_progress_bar": "show_progress_bar"
}
},
- "name": "intfloat/multilingual-e5-large",
- "provider": "IBM WatsonX"
+ "name": "text-embedding-3-large",
+ "provider": "OpenAI"
},
{
- "category": "IBM WatsonX",
- "icon": "WatsonxAI",
+ "category": "OpenAI",
+ "icon": "OpenAI",
"metadata": {
- "embedding_class": "WatsonxEmbeddings",
+ "embedding_class": "OpenAIEmbeddings",
"model_type": "embeddings",
"param_mapping": {
- "api_key": "apikey",
- "model_id": "model_id",
- "project_id": "project_id",
- "request_timeout": "request_timeout",
- "space_id": "space_id",
- "url": "url"
+ "api_base": "base_url",
+ "api_key": "api_key",
+ "chunk_size": "chunk_size",
+ "dimensions": "dimensions",
+ "max_retries": "max_retries",
+ "model": "model",
+ "model_kwargs": "model_kwargs",
+ "request_timeout": "timeout",
+ "show_progress_bar": "show_progress_bar"
}
},
- "name": "sentence-transformers/all-minilm-l6-v2",
- "provider": "IBM WatsonX"
+ "name": "text-embedding-ada-002",
+ "provider": "OpenAI"
}
],
"override_skip": false,
@@ -7938,6 +6496,7 @@
"type": "model",
"value": [
{
+ "category": "OpenAI",
"icon": "OpenAI",
"metadata": {
"embedding_class": "OpenAIEmbeddings",
@@ -7981,601 +6540,142 @@
},
"ollama_base_url": {
"_input_type": "StrInput",
- "advanced": false,
- "display_name": "Ollama API URL",
- "dynamic": false,
- "info": "Endpoint of the Ollama API (Ollama only). Defaults to http://localhost:11434",
- "list": false,
- "list_add_label": "Add More",
- "load_from_db": false,
- "name": "ollama_base_url",
- "override_skip": false,
- "placeholder": "",
- "real_time_refresh": true,
- "required": false,
- "show": false,
- "title_case": false,
- "tool_mode": false,
- "trace_as_metadata": true,
- "track_in_telemetry": false,
- "type": "str",
- "value": ""
- },
- "project_id": {
- "_input_type": "MessageTextInput",
- "advanced": true,
- "display_name": "Project ID",
- "dynamic": false,
- "info": "Falls back to WATSONX_PROJECT_ID environment variable",
- "input_types": [
- "Message"
- ],
- "list": false,
- "list_add_label": "Add More",
- "load_from_db": true,
- "name": "project_id",
- "override_skip": false,
- "placeholder": "",
- "required": false,
- "show": false,
- "title_case": false,
- "tool_mode": false,
- "trace_as_input": true,
- "trace_as_metadata": true,
- "track_in_telemetry": false,
- "type": "str",
- "value": "WATSONX_PROJECT_ID"
- },
- "request_timeout": {
- "_input_type": "FloatInput",
- "advanced": true,
- "display_name": "Request Timeout",
- "dynamic": false,
- "info": "",
- "list": false,
- "list_add_label": "Add More",
- "name": "request_timeout",
- "override_skip": false,
- "placeholder": "",
- "required": false,
- "show": true,
- "title_case": false,
- "tool_mode": false,
- "trace_as_metadata": true,
- "track_in_telemetry": true,
- "type": "float",
- "value": ""
- },
- "show_progress_bar": {
- "_input_type": "BoolInput",
- "advanced": true,
- "display_name": "Show Progress Bar",
- "dynamic": false,
- "info": "",
- "list": false,
- "list_add_label": "Add More",
- "name": "show_progress_bar",
- "override_skip": false,
- "placeholder": "",
- "required": false,
- "show": true,
- "title_case": false,
- "tool_mode": false,
- "trace_as_metadata": true,
- "track_in_telemetry": true,
- "type": "bool",
- "value": false
- },
- "truncate_input_tokens": {
- "_input_type": "IntInput",
- "advanced": true,
- "display_name": "Truncate Input Tokens",
- "dynamic": false,
- "info": "",
- "list": false,
- "list_add_label": "Add More",
- "name": "truncate_input_tokens",
- "override_skip": false,
- "placeholder": "",
- "required": false,
- "show": false,
- "title_case": false,
- "tool_mode": false,
- "trace_as_metadata": true,
- "track_in_telemetry": true,
- "type": "int",
- "value": 200
- }
- },
- "tool_mode": false
- },
- "showNode": true,
- "type": "EmbeddingModel"
- },
- "dragging": false,
- "id": "EmbeddingModel-qb5S3",
- "measured": {
- "height": 207,
- "width": 320
- },
- "position": {
- "x": 2183.7808538410127,
- "y": 2095.003494871439
- },
- "selected": true,
- "type": "genericNode"
- },
- {
- "data": {
- "id": "TextInput-OpenRAGIngest-url",
- "node": {
- "base_classes": [
- "Message"
- ],
- "beta": false,
- "conditional_paths": [],
- "custom_fields": {},
- "description": "Get user text inputs.",
- "display_name": "Text Input",
- "documentation": "https://docs.langflow.org/text-input-and-output",
- "edited": false,
- "field_order": [
- "input_value",
- "use_global_variable"
- ],
- "frozen": false,
- "icon": "type",
- "last_updated": "2026-03-05T16:40:36.785Z",
- "legacy": false,
- "metadata": {
- "code_hash": "518f16485886",
- "dependencies": {
- "dependencies": [
- {
- "name": "lfx",
- "version": null
- }
- ],
- "total_dependencies": 1
- },
- "module": "lfx.components.input_output.text.TextInputComponent"
- },
- "minimized": false,
- "output_types": [],
- "outputs": [
- {
- "allows_loop": false,
- "cache": true,
- "display_name": "Output Text",
- "group_outputs": false,
- "loop_types": null,
- "method": "text_response",
- "name": "text",
- "options": null,
- "required_inputs": null,
- "selected": "Message",
- "tool_mode": true,
- "types": [
- "Message"
- ],
- "value": "__UNDEFINED__"
- }
- ],
- "pinned": false,
- "template": {
- "_frontend_node_flow_id": {
- "value": "72c3d17c-2dac-4a73-b48a-6518473d7830"
- },
- "_frontend_node_folder_id": {
- "value": "7a54b33c-ad03-4c78-b61b-f95adbb74e17"
- },
- "_type": "Component",
- "code": {
- "advanced": true,
- "dynamic": true,
- "fileTypes": [],
- "file_path": "",
- "info": "",
- "list": false,
- "load_from_db": false,
- "multiline": true,
- "name": "code",
- "password": false,
- "placeholder": "",
- "required": true,
- "show": true,
- "title_case": false,
- "type": "code",
- "value": "from typing import Any\n\nfrom lfx.base.io.text import TextComponent\nfrom lfx.io import BoolInput, MultilineInput, Output\nfrom lfx.schema.message import Message\n\n\nclass TextInputComponent(TextComponent):\n display_name = \"Text Input\"\n description = \"Get user text inputs.\"\n documentation: str = \"https://docs.langflow.org/text-input-and-output\"\n icon = \"type\"\n name = \"TextInput\"\n\n inputs = [\n MultilineInput(\n name=\"input_value\",\n display_name=\"Text\",\n info=\"Text to be passed as input.\",\n ),\n BoolInput(\n name=\"use_global_variable\",\n display_name=\"Use Global Variable\",\n info=\"Enable to select from global variables (shows globe icon). Disables multiline editing.\",\n value=False,\n advanced=True,\n real_time_refresh=True,\n ),\n ]\n outputs = [\n Output(display_name=\"Output Text\", name=\"text\", method=\"text_response\"),\n ]\n\n def update_build_config(self, build_config: dict, field_value: Any, field_name: str | None = None) -> dict:\n if field_name == \"use_global_variable\":\n if field_value:\n # Enable global variable mode: single-line with password masking and globe dropdown\n build_config[\"input_value\"][\"multiline\"] = False\n build_config[\"input_value\"][\"password\"] = True\n else:\n # Default mode: multiline text editing\n build_config[\"input_value\"][\"multiline\"] = True\n build_config[\"input_value\"][\"password\"] = False\n return build_config\n\n def text_response(self) -> Message:\n return Message(\n text=self.input_value,\n )\n"
- },
- "input_value": {
- "_input_type": "MultilineInput",
- "advanced": false,
- "ai_enabled": false,
- "copy_field": false,
- "display_name": "Text",
- "dynamic": false,
- "info": "Text to be passed as input.",
- "input_types": [
- "Message"
- ],
- "list": false,
- "list_add_label": "Add More",
- "load_from_db": true,
- "multiline": false,
- "name": "input_value",
- "override_skip": false,
- "password": true,
- "placeholder": "",
- "required": false,
- "show": true,
- "title_case": false,
- "tool_mode": false,
- "trace_as_input": true,
- "trace_as_metadata": true,
- "track_in_telemetry": false,
- "type": "str",
- "value": "OPENRAG_INGEST_URL"
- },
- "is_refresh": false,
- "use_global_variable": {
- "_input_type": "BoolInput",
- "advanced": true,
- "display_name": "Use Global Variable",
+ "advanced": false,
+ "display_name": "Ollama API URL",
"dynamic": false,
- "info": "Enable to select from global variables (shows globe icon). Disables multiline editing.",
+ "info": "Endpoint of the Ollama API (Ollama only). Defaults to http://localhost:11434",
"list": false,
"list_add_label": "Add More",
- "name": "use_global_variable",
+ "load_from_db": false,
+ "name": "ollama_base_url",
"override_skip": false,
"placeholder": "",
"real_time_refresh": true,
"required": false,
- "show": true,
+ "show": false,
"title_case": false,
"tool_mode": false,
"trace_as_metadata": true,
- "track_in_telemetry": true,
- "type": "bool",
- "value": true
- }
- },
- "tool_mode": false
- },
- "showNode": false,
- "type": "TextInput"
- },
- "dragging": false,
- "id": "TextInput-OpenRAGIngest-url",
- "measured": {
- "height": 52,
- "width": 192
- },
- "position": {
- "x": 2009.318175939116,
- "y": 1153.252846147518
- },
- "selected": false,
- "type": "genericNode"
- },
- {
- "data": {
- "id": "TextInput-OpenRAGIngest-token",
- "node": {
- "base_classes": [
- "Message"
- ],
- "beta": false,
- "conditional_paths": [],
- "custom_fields": {},
- "description": "Get user text inputs.",
- "display_name": "Text Input",
- "documentation": "https://docs.langflow.org/text-input-and-output",
- "edited": false,
- "field_order": [
- "input_value",
- "use_global_variable"
- ],
- "frozen": false,
- "icon": "type",
- "last_updated": "2026-03-05T16:40:36.785Z",
- "legacy": false,
- "metadata": {
- "code_hash": "518f16485886",
- "dependencies": {
- "dependencies": [
- {
- "name": "lfx",
- "version": null
- }
- ],
- "total_dependencies": 1
- },
- "module": "lfx.components.input_output.text.TextInputComponent"
- },
- "minimized": false,
- "output_types": [],
- "outputs": [
- {
- "allows_loop": false,
- "cache": true,
- "display_name": "Output Text",
- "group_outputs": false,
- "loop_types": null,
- "method": "text_response",
- "name": "text",
- "options": null,
- "required_inputs": null,
- "selected": "Message",
- "tool_mode": true,
- "types": [
- "Message"
- ],
- "value": "__UNDEFINED__"
- }
- ],
- "pinned": false,
- "template": {
- "_frontend_node_flow_id": {
- "value": "72c3d17c-2dac-4a73-b48a-6518473d7830"
- },
- "_frontend_node_folder_id": {
- "value": "7a54b33c-ad03-4c78-b61b-f95adbb74e17"
+ "track_in_telemetry": false,
+ "type": "str",
+ "value": ""
},
- "_type": "Component",
- "code": {
+ "project_id": {
+ "_input_type": "MessageTextInput",
"advanced": true,
- "dynamic": true,
- "fileTypes": [],
- "file_path": "",
- "info": "",
- "list": false,
- "load_from_db": false,
- "multiline": true,
- "name": "code",
- "password": false,
- "placeholder": "",
- "required": true,
- "show": true,
- "title_case": false,
- "type": "code",
- "value": "from typing import Any\n\nfrom lfx.base.io.text import TextComponent\nfrom lfx.io import BoolInput, MultilineInput, Output\nfrom lfx.schema.message import Message\n\n\nclass TextInputComponent(TextComponent):\n display_name = \"Text Input\"\n description = \"Get user text inputs.\"\n documentation: str = \"https://docs.langflow.org/text-input-and-output\"\n icon = \"type\"\n name = \"TextInput\"\n\n inputs = [\n MultilineInput(\n name=\"input_value\",\n display_name=\"Text\",\n info=\"Text to be passed as input.\",\n ),\n BoolInput(\n name=\"use_global_variable\",\n display_name=\"Use Global Variable\",\n info=\"Enable to select from global variables (shows globe icon). Disables multiline editing.\",\n value=False,\n advanced=True,\n real_time_refresh=True,\n ),\n ]\n outputs = [\n Output(display_name=\"Output Text\", name=\"text\", method=\"text_response\"),\n ]\n\n def update_build_config(self, build_config: dict, field_value: Any, field_name: str | None = None) -> dict:\n if field_name == \"use_global_variable\":\n if field_value:\n # Enable global variable mode: single-line with password masking and globe dropdown\n build_config[\"input_value\"][\"multiline\"] = False\n build_config[\"input_value\"][\"password\"] = True\n else:\n # Default mode: multiline text editing\n build_config[\"input_value\"][\"multiline\"] = True\n build_config[\"input_value\"][\"password\"] = False\n return build_config\n\n def text_response(self) -> Message:\n return Message(\n text=self.input_value,\n )\n"
- },
- "input_value": {
- "_input_type": "MultilineInput",
- "advanced": false,
- "ai_enabled": false,
- "copy_field": false,
- "display_name": "Text",
+ "display_name": "Project ID",
"dynamic": false,
- "info": "Text to be passed as input.",
+ "info": "Falls back to WATSONX_PROJECT_ID environment variable",
"input_types": [
"Message"
],
"list": false,
"list_add_label": "Add More",
- "load_from_db": true,
- "multiline": false,
- "name": "input_value",
+ "load_from_db": false,
+ "name": "project_id",
"override_skip": false,
- "password": true,
"placeholder": "",
"required": false,
- "show": true,
+ "show": false,
"title_case": false,
"tool_mode": false,
"trace_as_input": true,
"trace_as_metadata": true,
"track_in_telemetry": false,
"type": "str",
- "value": "OPENRAG_INGEST_TOKEN"
+ "value": ""
},
- "is_refresh": false,
- "use_global_variable": {
- "_input_type": "BoolInput",
+ "request_timeout": {
+ "_input_type": "FloatInput",
"advanced": true,
- "display_name": "Use Global Variable",
+ "display_name": "Request Timeout",
"dynamic": false,
- "info": "Enable to select from global variables (shows globe icon). Disables multiline editing.",
+ "info": "",
"list": false,
"list_add_label": "Add More",
- "name": "use_global_variable",
+ "name": "request_timeout",
"override_skip": false,
"placeholder": "",
- "real_time_refresh": true,
"required": false,
"show": true,
"title_case": false,
"tool_mode": false,
"trace_as_metadata": true,
"track_in_telemetry": true,
- "type": "bool",
- "value": true
- }
- },
- "tool_mode": false
- },
- "showNode": false,
- "type": "TextInput"
- },
- "dragging": false,
- "id": "TextInput-OpenRAGIngest-token",
- "measured": {
- "height": 52,
- "width": 192
- },
- "position": {
- "x": 2009.318175939116,
- "y": 1235.252846147518
- },
- "selected": false,
- "type": "genericNode"
- },
- {
- "data": {
- "id": "TextInput-OpenRAGIngest-run_id",
- "node": {
- "base_classes": [
- "Message"
- ],
- "beta": false,
- "conditional_paths": [],
- "custom_fields": {},
- "description": "Get user text inputs.",
- "display_name": "Text Input",
- "documentation": "https://docs.langflow.org/text-input-and-output",
- "edited": false,
- "field_order": [
- "input_value",
- "use_global_variable"
- ],
- "frozen": false,
- "icon": "type",
- "last_updated": "2026-03-05T16:40:36.785Z",
- "legacy": false,
- "metadata": {
- "code_hash": "518f16485886",
- "dependencies": {
- "dependencies": [
- {
- "name": "lfx",
- "version": null
- }
- ],
- "total_dependencies": 1
- },
- "module": "lfx.components.input_output.text.TextInputComponent"
- },
- "minimized": false,
- "output_types": [],
- "outputs": [
- {
- "allows_loop": false,
- "cache": true,
- "display_name": "Output Text",
- "group_outputs": false,
- "loop_types": null,
- "method": "text_response",
- "name": "text",
- "options": null,
- "required_inputs": null,
- "selected": "Message",
- "tool_mode": true,
- "types": [
- "Message"
- ],
- "value": "__UNDEFINED__"
- }
- ],
- "pinned": false,
- "template": {
- "_frontend_node_flow_id": {
- "value": "72c3d17c-2dac-4a73-b48a-6518473d7830"
- },
- "_frontend_node_folder_id": {
- "value": "7a54b33c-ad03-4c78-b61b-f95adbb74e17"
+ "type": "float",
+ "value": ""
},
- "_type": "Component",
- "code": {
+ "show_progress_bar": {
+ "_input_type": "BoolInput",
"advanced": true,
- "dynamic": true,
- "fileTypes": [],
- "file_path": "",
- "info": "",
- "list": false,
- "load_from_db": false,
- "multiline": true,
- "name": "code",
- "password": false,
- "placeholder": "",
- "required": true,
- "show": true,
- "title_case": false,
- "type": "code",
- "value": "from typing import Any\n\nfrom lfx.base.io.text import TextComponent\nfrom lfx.io import BoolInput, MultilineInput, Output\nfrom lfx.schema.message import Message\n\n\nclass TextInputComponent(TextComponent):\n display_name = \"Text Input\"\n description = \"Get user text inputs.\"\n documentation: str = \"https://docs.langflow.org/text-input-and-output\"\n icon = \"type\"\n name = \"TextInput\"\n\n inputs = [\n MultilineInput(\n name=\"input_value\",\n display_name=\"Text\",\n info=\"Text to be passed as input.\",\n ),\n BoolInput(\n name=\"use_global_variable\",\n display_name=\"Use Global Variable\",\n info=\"Enable to select from global variables (shows globe icon). Disables multiline editing.\",\n value=False,\n advanced=True,\n real_time_refresh=True,\n ),\n ]\n outputs = [\n Output(display_name=\"Output Text\", name=\"text\", method=\"text_response\"),\n ]\n\n def update_build_config(self, build_config: dict, field_value: Any, field_name: str | None = None) -> dict:\n if field_name == \"use_global_variable\":\n if field_value:\n # Enable global variable mode: single-line with password masking and globe dropdown\n build_config[\"input_value\"][\"multiline\"] = False\n build_config[\"input_value\"][\"password\"] = True\n else:\n # Default mode: multiline text editing\n build_config[\"input_value\"][\"multiline\"] = True\n build_config[\"input_value\"][\"password\"] = False\n return build_config\n\n def text_response(self) -> Message:\n return Message(\n text=self.input_value,\n )\n"
- },
- "input_value": {
- "_input_type": "MultilineInput",
- "advanced": false,
- "ai_enabled": false,
- "copy_field": false,
- "display_name": "Text",
+ "display_name": "Show Progress Bar",
"dynamic": false,
- "info": "Text to be passed as input.",
- "input_types": [
- "Message"
- ],
+ "info": "",
"list": false,
"list_add_label": "Add More",
- "load_from_db": true,
- "multiline": false,
- "name": "input_value",
+ "name": "show_progress_bar",
"override_skip": false,
- "password": true,
"placeholder": "",
"required": false,
"show": true,
"title_case": false,
"tool_mode": false,
- "trace_as_input": true,
"trace_as_metadata": true,
- "track_in_telemetry": false,
- "type": "str",
- "value": "OPENRAG_INGEST_RUN_ID"
+ "track_in_telemetry": true,
+ "type": "bool",
+ "value": false
},
- "is_refresh": false,
- "use_global_variable": {
- "_input_type": "BoolInput",
+ "truncate_input_tokens": {
+ "_input_type": "IntInput",
"advanced": true,
- "display_name": "Use Global Variable",
+ "display_name": "Truncate Input Tokens",
"dynamic": false,
- "info": "Enable to select from global variables (shows globe icon). Disables multiline editing.",
+ "info": "",
"list": false,
"list_add_label": "Add More",
- "name": "use_global_variable",
+ "name": "truncate_input_tokens",
"override_skip": false,
"placeholder": "",
- "real_time_refresh": true,
"required": false,
- "show": true,
+ "show": false,
"title_case": false,
"tool_mode": false,
"trace_as_metadata": true,
"track_in_telemetry": true,
- "type": "bool",
- "value": true
+ "type": "int",
+ "value": 200
}
},
"tool_mode": false
},
- "showNode": false,
- "type": "TextInput"
+ "showNode": true,
+ "type": "EmbeddingModel"
},
"dragging": false,
- "id": "TextInput-OpenRAGIngest-run_id",
+ "id": "EmbeddingModel-qb5S3",
"measured": {
- "height": 52,
- "width": 192
+ "height": 207,
+ "width": 320
},
"position": {
- "x": 2009.318175939116,
- "y": 1317.252846147518
+ "x": 2183.7808538410127,
+ "y": 2095.003494871439
},
"selected": false,
"type": "genericNode"
}
],
"viewport": {
- "x": -798.5646284783511,
- "y": -1114.1894840221698,
- "zoom": 0.7194800700371419
+ "x": -1539.087785115923,
+ "y": -1068.8202149715655,
+ "zoom": 0.7829687481507004
}
},
"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": "1.9.0",
+ "last_tested_version": "1.9.6",
"locked": true,
"mcp_enabled": true,
"name": "OpenSearch URL Ingestion Flow",
@@ -8585,4 +6685,4 @@
"rag",
"q-a"
]
-}
+}
\ No newline at end of file
diff --git a/frontend/package-lock.json b/frontend/package-lock.json
index 692ad121c..2128508bb 100644
--- a/frontend/package-lock.json
+++ b/frontend/package-lock.json
@@ -1103,6 +1103,7 @@
"integrity": "sha512-6TyEnHgd6SArQO8UO2OMTxshln3QMWBtPGrOCgs3wVEmQmwyuNtB10IZMfmYDE0riwNR1cu4q+pPcxMVtaG3TA==",
"devOptional": true,
"license": "Apache-2.0",
+ "peer": true,
"dependencies": {
"playwright": "1.57.0"
},
@@ -3041,6 +3042,7 @@
"integrity": "sha512-yCAeZl7a0DxgNVteXFHt9+uyFbqXGy/ShC4BlcHkoE0AfGXYv/BUiplV72DjMYXHDBXFjhvr6DD1NiRVfB4j8g==",
"dev": true,
"license": "MIT",
+ "peer": true,
"dependencies": {
"undici-types": "~6.21.0"
}
@@ -3056,6 +3058,7 @@
"resolved": "https://registry.npmjs.org/@types/react/-/react-19.1.12.tgz",
"integrity": "sha512-cMoR+FoAf/Jyq6+Df2/Z41jISvGZZ2eTlnsaJRptmZ76Caldwy1odD4xTr/gNV9VLj0AWgg/nmkevIyUfIIq5w==",
"license": "MIT",
+ "peer": true,
"dependencies": {
"csstype": "^3.0.2"
}
@@ -3066,6 +3069,7 @@
"integrity": "sha512-qXRuZaOsAdXKFyOhRBg6Lqqc0yay13vN7KrIg4L7N4aaHN68ma9OK3NE1BoDFgFOTfM7zg+3/8+2n8rLUH3OKQ==",
"devOptional": true,
"license": "MIT",
+ "peer": true,
"peerDependencies": {
"@types/react": "^19.0.0"
}
@@ -3130,6 +3134,7 @@
"integrity": "sha512-klQbnPAAiGYFyI02+znpBRLyjL4/BrBd0nyWkdC0s/6xFLkXYQ8OoRrSkqacS1ddVxf/LDyODIKbQ5TgKAf/Fg==",
"dev": true,
"license": "MIT",
+ "peer": true,
"dependencies": {
"@typescript-eslint/scope-manager": "8.56.1",
"@typescript-eslint/types": "8.56.1",
@@ -3718,6 +3723,7 @@
"integrity": "sha512-UVJyE9MttOsBQIDKw1skb9nAwQuR5wuGD3+82K6JgJlm/Y+KI92oNsMNGZCYdDsVtRHSak0pcV5Dno5+4jh9sw==",
"dev": true,
"license": "MIT",
+ "peer": true,
"bin": {
"acorn": "bin/acorn"
},
@@ -4220,6 +4226,7 @@
}
],
"license": "MIT",
+ "peer": true,
"dependencies": {
"caniuse-lite": "^1.0.30001737",
"electron-to-chromium": "^1.5.211",
@@ -5068,6 +5075,7 @@
"integrity": "sha512-VmQ+sifHUbI/IcSopBCF/HO3YiHQx/AVd3UVyYL6weuwW+HvON9VYn5l6Zl1WZzPWXPNZrSQpxwkkZ/VuvJZzg==",
"dev": true,
"license": "MIT",
+ "peer": true,
"dependencies": {
"@eslint-community/eslint-utils": "^4.8.0",
"@eslint-community/regexpp": "^4.12.1",
@@ -5241,6 +5249,7 @@
"integrity": "sha512-whOE1HFo/qJDyX4SnXzP4N6zOWn79WhnCUY/iDR0mPfQZO8wcYE4JClzI2oZrhBnnMUCBCHZhO6VQyoBU95mZA==",
"dev": true,
"license": "MIT",
+ "peer": true,
"dependencies": {
"@rtsao/scc": "^1.1.0",
"array-includes": "^3.1.9",
@@ -7024,6 +7033,7 @@
"resolved": "https://registry.npmjs.org/jiti/-/jiti-1.21.7.tgz",
"integrity": "sha512-/imKNG4EbWNrVjoNC/1H5/9GFy+tqjGBHCaSsN+P2RnPqjsLmv6UD3Ej+Kj8nBWaRAwyk7kK5ZUc+OEatnTR3A==",
"license": "MIT",
+ "peer": true,
"bin": {
"jiti": "bin/jiti.js"
}
@@ -9144,6 +9154,7 @@
"resolved": "https://registry.npmjs.org/picomatch/-/picomatch-4.0.4.tgz",
"integrity": "sha512-QP88BAKvMam/3NxH6vj2o21R6MjxZUAd6nlwAS/pnGvN9IVLocLHxGYIzFhg6fUQ+5th6P4dv4eW9jX3DSIj7A==",
"license": "MIT",
+ "peer": true,
"engines": {
"node": ">=12"
},
@@ -9257,6 +9268,7 @@
}
],
"license": "MIT",
+ "peer": true,
"dependencies": {
"nanoid": "^3.3.12",
"picocolors": "^1.1.1",
@@ -9551,6 +9563,7 @@
"resolved": "https://registry.npmjs.org/react/-/react-19.1.1.tgz",
"integrity": "sha512-w8nqGImo45dmMIfljjMwOGtbmC/mk4CMYhWIicdSflH91J9TyCyczcPFXJzrZ/ZXcgGRFeP6BU0BEJTw6tZdfQ==",
"license": "MIT",
+ "peer": true,
"engines": {
"node": ">=0.10.0"
}
@@ -9560,6 +9573,7 @@
"resolved": "https://registry.npmjs.org/react-dom/-/react-dom-19.1.1.tgz",
"integrity": "sha512-Dlq/5LAZgF0Gaz6yiqZCf6VCcZs1ghAJyrsu84Q/GT0gV+mCxbfmKNoGRKBYMJ8IEdGPqu49YWXD02GCknEDkw==",
"license": "MIT",
+ "peer": true,
"dependencies": {
"scheduler": "^0.26.0"
},
@@ -10753,6 +10767,7 @@
"resolved": "https://registry.npmjs.org/tailwindcss/-/tailwindcss-3.4.17.tgz",
"integrity": "sha512-w33E2aCvSDP0tW9RZuNXadXlkHXqFzSkQew/aIa2i/Sj8fThxwovwlXHSPXTbAHwEIhBFXAedUhP2tueAKP8Og==",
"license": "MIT",
+ "peer": true,
"dependencies": {
"@alloc/quick-lru": "^5.2.0",
"arg": "^5.0.2",
@@ -11098,6 +11113,7 @@
"integrity": "sha512-CWBzXQrc/qOkhidw1OzBTQuYRbfyxDXJMVJ1XNwUHGROVmuaeiEm3OslpZ1RV96d7SKKjZKrSJu3+t/xlw3R9A==",
"dev": true,
"license": "Apache-2.0",
+ "peer": true,
"bin": {
"tsc": "bin/tsc",
"tsserver": "bin/tsserver"
diff --git a/src/services/chat_service.py b/src/services/chat_service.py
index f43121345..57a1e2265 100644
--- a/src/services/chat_service.py
+++ b/src/services/chat_service.py
@@ -1,7 +1,9 @@
import json
-from config.settings import NUDGES_FLOW_ID, clients, LANGFLOW_URL, LANGFLOW_CHAT_FLOW_ID
-from agent import async_chat, async_langflow, async_chat_stream
+from typing import Any
+
+from agent import async_chat, async_chat_stream, async_langflow
from auth_context import set_auth_context
+from config.settings import LANGFLOW_CHAT_FLOW_ID, LANGFLOW_URL, NUDGES_FLOW_ID, clients
from utils.logging_config import get_logger
logger = get_logger(__name__)
@@ -75,24 +77,65 @@ class ChatService:
)
# Prepare extra headers for JWT authentication and embedding model
- extra_headers = {
- "X-Langflow-Global-Var-OWNER": str(owner) if owner else "",
- "X-Langflow-Global-Var-OWNER_NAME": str(owner_name) if owner_name else "",
- "X-Langflow-Global-Var-OWNER_EMAIL": str(owner_email) if owner_email else "",
- }
+ extra_headers = {}
if jwt_token:
extra_headers["X-LANGFLOW-GLOBAL-VAR-JWT"] = jwt_token
# Pass the selected embedding model as a global variable
from config.settings import get_openrag_config
from utils.langflow_headers import add_provider_credentials_to_headers
-
+
config = get_openrag_config()
embedding_model = config.knowledge.embedding_model
extra_headers["X-LANGFLOW-GLOBAL-VAR-SELECTED_EMBEDDING_MODEL"] = embedding_model
-
+
+ # Configure ingest callback credentials/vars like ingestion does
+ import uuid
+
+ from config.settings import (
+ LANGFLOW_INGEST_CALLBACK_BATCH_SIZE,
+ get_index_name,
+ get_ingest_callback_url,
+ )
+ from services.document_index_writer import DocumentIndexContext
+ from services.langflow_ingest_token_service import LangflowIngestTokenService
+
+ doc_id = str(uuid.uuid4())
+ ingest_run_id = f"{doc_id}-{uuid.uuid4().hex}"
+ context = DocumentIndexContext(
+ document_id=doc_id,
+ filename="",
+ mimetype="",
+ embedding_model=embedding_model,
+ owner=None,
+ owner_name=None,
+ owner_email=None,
+ file_size=0,
+ connector_type="url",
+ source_url=None,
+ allowed_users=[],
+ allowed_groups=[],
+ allowed_principals=[],
+ allowed_principal_labels=[],
+ ingest_run_id=ingest_run_id,
+ is_sample_data=False,
+ index_name=get_index_name(),
+ )
+ token_service = LangflowIngestTokenService()
+ ingest_token = token_service.create_token(context)
+
+ extra_headers["X-Langflow-Global-Var-OPENRAG_INGEST_URL"] = get_ingest_callback_url()
+ extra_headers["X-Langflow-Global-Var-OPENRAG_INGEST_TOKEN"] = ingest_token
+ extra_headers["X-Langflow-Global-Var-OPENRAG_INGEST_RUN_ID"] = ingest_run_id
+ extra_headers["X-Langflow-Global-Var-OPENRAG_INGEST_BATCH_SIZE"] = str(
+ LANGFLOW_INGEST_CALLBACK_BATCH_SIZE
+ )
+ extra_headers["X-Langflow-Global-Var-CONNECTOR_TYPE"] = "url"
+
# Add provider credentials to headers
- await add_provider_credentials_to_headers(extra_headers, config, flows_service=self.flows_service, jwt_token=jwt_token)
+ await add_provider_credentials_to_headers(
+ extra_headers, config, flows_service=self.flows_service, jwt_token=jwt_token
+ )
# Get context variables for filters, limit, and threshold
from auth_context import (
get_score_threshold,
@@ -105,7 +148,7 @@ class ChatService:
score_threshold = get_score_threshold()
# Build the complete filter expression like the search service does
- filter_expression = {}
+ filter_expression: dict[str, Any] = {}
if filters:
filter_clauses = []
# Map frontend filter names to backend field names
@@ -143,10 +186,10 @@ class ChatService:
"Sending OpenRAG query filter to Langflow",
filter_expression=filter_expression,
)
- extra_headers["X-LANGFLOW-GLOBAL-VAR-OPENRAG-QUERY-FILTER"] = json.dumps(
- filter_expression
+ extra_headers["X-LANGFLOW-GLOBAL-VAR-OPENRAG-QUERY-FILTER"] = json.dumps(filter_expression)
+ logger.info(
+ "[CHAT] Langflow chat request", stream=stream, filters_applied=bool(filter_expression)
)
- logger.info("[CHAT] Langflow chat request", stream=stream, filters_applied=bool(filter_expression))
# Ensure the Langflow client exists; try lazy init if needed
langflow_client = await clients.ensure_langflow_client()
if not langflow_client:
@@ -154,7 +197,6 @@ class ChatService:
"Langflow client not initialized. Ensure LANGFLOW is reachable or set LANGFLOW_KEY."
)
-
if stream:
from agent import async_langflow_chat_stream
@@ -200,9 +242,7 @@ class ChatService:
conversation_user_id = storage_user_id or user_id
if not LANGFLOW_URL or not NUDGES_FLOW_ID:
- raise ValueError(
- "LANGFLOW_URL and NUDGES_FLOW_ID environment variables are required"
- )
+ raise ValueError("LANGFLOW_URL and NUDGES_FLOW_ID environment variables are required")
# Prepare extra headers for JWT authentication and embedding model
extra_headers = {}
@@ -212,16 +252,18 @@ class ChatService:
# Pass the selected embedding model as a global variable
from config.settings import get_openrag_config
from utils.langflow_headers import add_provider_credentials_to_headers
-
+
config = get_openrag_config()
embedding_model = config.knowledge.embedding_model
extra_headers["X-LANGFLOW-GLOBAL-VAR-SELECTED_EMBEDDING_MODEL"] = embedding_model
-
+
# Add provider credentials to headers
- await add_provider_credentials_to_headers(extra_headers, config, flows_service=self.flows_service, jwt_token=jwt_token)
+ await add_provider_credentials_to_headers(
+ extra_headers, config, flows_service=self.flows_service, jwt_token=jwt_token
+ )
# Build the complete filter expression like the chat service does
- filter_expression = {}
+ filter_expression: dict[str, Any] = {}
has_user_filters = False
filter_clauses = []
@@ -252,13 +294,7 @@ class ChatService:
# If no user filters are active, exclude sample data from nudges
if not has_user_filters:
# Add a bool query with must_not to exclude sample data
- filter_clauses.append({
- "bool": {
- "must_not": [
- {"term": {"is_sample_data": "true"}}
- ]
- }
- })
+ filter_clauses.append({"bool": {"must_not": [{"term": {"is_sample_data": "true"}}]}})
logger.info("Excluding sample data from nudges (no user filters active)")
# Set the filter clauses if we have any
@@ -273,9 +309,7 @@ class ChatService:
filter_expression["score_threshold"] = score_threshold
# Pass the complete filter expression as a single header to Langflow (only if we have something to send)
- extra_headers["X-LANGFLOW-GLOBAL-VAR-OPENRAG-QUERY-FILTER"] = json.dumps(
- filter_expression
- )
+ extra_headers["X-LANGFLOW-GLOBAL-VAR-OPENRAG-QUERY-FILTER"] = json.dumps(filter_expression)
logger.info("[CHAT] Nudges request", filters_applied=bool(filter_expression))
# Ensure the Langflow client exists; try lazy init if needed
@@ -303,7 +337,6 @@ class ChatService:
from agent import async_langflow_chat
-
response_text, response_id, _sources = await async_langflow_chat(
langflow_client,
NUDGES_FLOW_ID,
@@ -336,25 +369,66 @@ class ChatService:
if endpoint == "langflow":
# Prepare extra headers for JWT authentication and embedding model
- extra_headers = {
- "X-Langflow-Global-Var-OWNER": str(owner) if owner else "",
- "X-Langflow-Global-Var-OWNER_NAME": str(owner_name) if owner_name else "",
- "X-Langflow-Global-Var-OWNER_EMAIL": str(owner_email) if owner_email else "",
- }
+ extra_headers = {}
if jwt_token:
extra_headers["X-LANGFLOW-GLOBAL-VAR-JWT"] = jwt_token
# Pass the selected embedding model as a global variable
from config.settings import get_openrag_config
from utils.langflow_headers import add_provider_credentials_to_headers
-
+
config = get_openrag_config()
embedding_model = config.knowledge.embedding_model
extra_headers["X-LANGFLOW-GLOBAL-VAR-SELECTED_EMBEDDING_MODEL"] = embedding_model
-
+
+ # Configure ingest callback credentials/vars like ingestion does
+ import uuid
+
+ from config.settings import (
+ LANGFLOW_INGEST_CALLBACK_BATCH_SIZE,
+ get_index_name,
+ get_ingest_callback_url,
+ )
+ from services.document_index_writer import DocumentIndexContext
+ from services.langflow_ingest_token_service import LangflowIngestTokenService
+
+ doc_id = str(uuid.uuid4())
+ ingest_run_id = f"{doc_id}-{uuid.uuid4().hex}"
+ context = DocumentIndexContext(
+ document_id=doc_id,
+ filename="",
+ mimetype="",
+ embedding_model=embedding_model,
+ owner=None,
+ owner_name=None,
+ owner_email=None,
+ file_size=0,
+ connector_type="url",
+ source_url=None,
+ allowed_users=[],
+ allowed_groups=[],
+ allowed_principals=[],
+ allowed_principal_labels=[],
+ ingest_run_id=ingest_run_id,
+ is_sample_data=False,
+ index_name=get_index_name(),
+ )
+ token_service = LangflowIngestTokenService()
+ ingest_token = token_service.create_token(context)
+
+ extra_headers["X-Langflow-Global-Var-OPENRAG_INGEST_URL"] = get_ingest_callback_url()
+ extra_headers["X-Langflow-Global-Var-OPENRAG_INGEST_TOKEN"] = ingest_token
+ extra_headers["X-Langflow-Global-Var-OPENRAG_INGEST_RUN_ID"] = ingest_run_id
+ extra_headers["X-Langflow-Global-Var-OPENRAG_INGEST_BATCH_SIZE"] = str(
+ LANGFLOW_INGEST_CALLBACK_BATCH_SIZE
+ )
+ extra_headers["X-Langflow-Global-Var-CONNECTOR_TYPE"] = "url"
+
# Add provider credentials to headers
- await add_provider_credentials_to_headers(extra_headers, config, flows_service=self.flows_service, jwt_token=jwt_token)
-
+ await add_provider_credentials_to_headers(
+ extra_headers, config, flows_service=self.flows_service, jwt_token=jwt_token
+ )
+
# Ensure the Langflow client exists; try lazy init if needed
langflow_client = await clients.ensure_langflow_client()
if not langflow_client:
@@ -431,9 +505,7 @@ class ChatService:
if messages: # Only include conversations with actual messages
# Generate title from first user message
- first_user_msg = next(
- (msg for msg in messages if msg["role"] == "user"), None
- )
+ first_user_msg = next((msg for msg in messages if msg["role"] == "user"), None)
title = (
first_user_msg["content"][:50] + "..."
if first_user_msg and len(first_user_msg["content"]) > 50
@@ -451,14 +523,10 @@ class ChatService:
"created_at": conversation_state.get("created_at").isoformat()
if conversation_state.get("created_at")
else None,
- "last_activity": conversation_state.get(
- "last_activity"
- ).isoformat()
+ "last_activity": conversation_state.get("last_activity").isoformat()
if conversation_state.get("last_activity")
else None,
- "previous_response_id": conversation_state.get(
- "previous_response_id"
- ),
+ "previous_response_id": conversation_state.get("previous_response_id"),
"filter_id": conversation_state.get("filter_id"),
"total_messages": len(messages),
"source": "in_memory",
@@ -515,10 +583,8 @@ class ChatService:
# 2. Get actual conversations from Langflow database (source of truth for messages)
logger.debug(f"Attempting to fetch Langflow history for user: {user_id}")
- langflow_history = (
- await langflow_history_service.get_user_conversation_history(
- user_id, flow_id=LANGFLOW_CHAT_FLOW_ID
- )
+ langflow_history = await langflow_history_service.get_user_conversation_history(
+ user_id, flow_id=LANGFLOW_CHAT_FLOW_ID
)
if langflow_history.get("conversations"):
@@ -561,8 +627,7 @@ class ChatService:
)
title = (
first_user_msg["content"][:50] + "..."
- if first_user_msg
- and len(first_user_msg["content"]) > 50
+ if first_user_msg and len(first_user_msg["content"]) > 50
else first_user_msg["content"]
if first_user_msg
else "Langflow chat"
@@ -624,6 +689,7 @@ class ChatService:
try:
# Delete from local conversation storage
from agent import delete_user_conversation
+
local_deleted = await delete_user_conversation(user_id, session_id)
if not local_deleted:
@@ -645,17 +711,13 @@ class ChatService:
except Exception as e:
logger.error(f"Error deleting session {session_id} for user {user_id}: {e}")
- return {
- "success": False,
- "error": str(e)
- }
+ return {"success": False, "error": str(e)}
async def _delete_langflow_session(self, session_id: str):
"""Delete a session from Langflow using the monitor API"""
try:
response = await clients.langflow_request(
- "DELETE",
- f"/api/v1/monitor/messages/session/{session_id}"
+ "DELETE", f"/api/v1/monitor/messages/session/{session_id}"
)
if response.status_code == 200 or response.status_code == 204:
@@ -678,14 +740,14 @@ class ChatService:
conversations = await get_user_conversations(user_id)
session_ids = list(conversations.keys())
-
+
results = []
for session_id in session_ids:
result = await self.delete_session(user_id, session_id)
results.append(result)
-
+
return {
"success": True,
"deleted_count": len([r for r in results if r.get("success")]),
- "total_count": len(session_ids)
+ "total_count": len(session_ids),
}
diff --git a/src/services/default_docs_service.py b/src/services/default_docs_service.py
index a28f6271e..7202a6bcd 100644
--- a/src/services/default_docs_service.py
+++ b/src/services/default_docs_service.py
@@ -150,7 +150,7 @@ async def ingest_default_documents_when_ready(
task_service,
file_paths,
existing_task_id=task_id,
- connector_type="openrag_docs",
+ connector_type="local",
jwt_token=jwt_token,
)
task_id = new_task_id or task_id
@@ -161,7 +161,7 @@ async def ingest_default_documents_when_ready(
task_service,
file_paths,
existing_task_id=task_id,
- connector_type="openrag_docs",
+ connector_type="local",
jwt_token=jwt_token,
)
task_id = new_task_id or task_id
diff --git a/tests/integration/core/test_mcp_url_ingest.py b/tests/integration/core/test_mcp_url_ingest.py
index 73e1695aa..5bd00bc4c 100644
--- a/tests/integration/core/test_mcp_url_ingest.py
+++ b/tests/integration/core/test_mcp_url_ingest.py
@@ -5,7 +5,6 @@ from typing import Any
import pytest
-
OPENRAG_MCP_SERVER_NAME = "lf-starter_project"
LANGFLOW_GLOBAL_VAR_PREFIX = "x-langflow-global-var-"
@@ -38,8 +37,7 @@ def _extract_server_urls(server_config: dict[str, Any]) -> list[str]:
urls.extend(
arg
for arg in args
- if isinstance(arg, str)
- and (arg.startswith("http://") or arg.startswith("https://"))
+ if isinstance(arg, str) and (arg.startswith("http://") or arg.startswith("https://"))
)
return urls
@@ -50,11 +48,7 @@ def _extract_server_headers(server_config: dict[str, Any]) -> dict[str, str]:
raw_headers = server_config.get("headers")
if isinstance(raw_headers, dict):
headers.update(
- {
- str(key): str(value)
- for key, value in raw_headers.items()
- if value is not None
- }
+ {str(key): str(value) for key, value in raw_headers.items() if value is not None}
)
args = server_config.get("args", [])
@@ -97,8 +91,7 @@ async def test_openrag_mcp_server_url_is_patched_without_persisting_request_glob
servers = await mcp_service.list_mcp_servers()
server_names = [_server_name(server) for server in servers]
assert OPENRAG_MCP_SERVER_NAME in server_names, (
- f"Expected OpenRAG MCP server {OPENRAG_MCP_SERVER_NAME!r}; "
- f"found {server_names}"
+ f"Expected OpenRAG MCP server {OPENRAG_MCP_SERVER_NAME!r}; found {server_names}"
)
server_config = await mcp_service.get_mcp_server(OPENRAG_MCP_SERVER_NAME)
@@ -108,8 +101,7 @@ async def test_openrag_mcp_server_url_is_patched_without_persisting_request_glob
expected_base = (LANGFLOW_URL or os.environ.get("LANGFLOW_URL", "")).rstrip("/")
if expected_base and "localhost" not in expected_base:
assert any(url.startswith(expected_base) for url in urls), (
- f"MCP server URLs were not rewritten to LANGFLOW_URL={expected_base!r}: "
- f"{urls}"
+ f"MCP server URLs were not rewritten to LANGFLOW_URL={expected_base!r}: {urls}"
)
_assert_no_persisted_langflow_globals(_extract_server_headers(server_config))
@@ -141,13 +133,13 @@ async def test_loaded_agent_flow_routes_request_globals_into_mcp_headers():
"JWT",
"OPENAI_API_KEY",
"OPENSEARCH_URL",
- "OWNER",
- "OWNER_EMAIL",
- "OWNER_NAME",
"SELECTED_EMBEDDING_MODEL",
"WATSONX_APIKEY",
"WATSONX_PROJECT_ID",
"OPENSEARCH_INDEX_NAME",
- "CONNECTOR_TYPE",
+ "OPENRAG_INGEST_URL",
+ "OPENRAG_INGEST_TOKEN",
+ "OPENRAG_INGEST_RUN_ID",
+ "OPENRAG_INGEST_BATCH_SIZE",
]:
assert f"X-Langflow-Global-Var-{global_var_name}" in flow_text
diff --git a/tests/integration/core/test_onboarding_sample_docs.py b/tests/integration/core/test_onboarding_sample_docs.py
index ea68b3812..1b1befd7e 100644
--- a/tests/integration/core/test_onboarding_sample_docs.py
+++ b/tests/integration/core/test_onboarding_sample_docs.py
@@ -214,8 +214,7 @@ async def test_onboarding_ingests_sample_docs_and_creates_openrag_docs_filter(
"query": {
"bool": {
"filter": [
- {"term": {"connector_type": "openrag_docs"}},
- {"term": {"is_sample_data": "true"}},
+ {"term": {"connector_type": "local"}},
]
}
},