Skip to content

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

Python
467 KB
Raw Blame
{
  "data": {
    "edges": [
      {
        "animated": false,
        "className": "",
        "data": {
          "sourceHandle": {
            "dataType": "DoclingRemote",
            "id": "DoclingRemote-Dp3PX",
            "name": "dataframe",
            "output_types": [
              "Table"
            ]
          },
          "targetHandle": {
            "fieldName": "data_inputs",
            "id": "ExportDoclingDocument-zZdRg",
            "inputTypes": [
              "Data",
              "JSON",
              "DataFrame",
              "Table"
            ],
            "type": "other"
          }
        },
        "id": "reactflow__edge-DoclingRemote-Dp3PX{œdataTypeœ:œDoclingRemoteœ,œidœ:œDoclingRemote-Dp3PXœ,œnameœ:œdataframeœ,œoutput_typesœ:[œTableœ]}-ExportDoclingDocument-zZdRg{œfieldNameœ:œdata_inputsœ,œidœ:œExportDoclingDocument-zZdRgœ,œinputTypesœ:[œDataœ,œJSONœ,œDataFrameœ,œTableœ],œtypeœ:œotherœ}",
        "selected": false,
        "source": "DoclingRemote-Dp3PX",
        "sourceHandle": "{œdataTypeœ:œDoclingRemoteœ,œidœ:œDoclingRemote-Dp3PXœ,œnameœ:œdataframeœ,œoutput_typesœ:[œTableœ]}",
        "target": "ExportDoclingDocument-zZdRg",
        "targetHandle": "{œfieldNameœ:œdata_inputsœ,œidœ:œExportDoclingDocument-zZdRgœ,œinputTypesœ:[œDataœ,œJSONœ,œDataFrameœ,œTableœ],œtypeœ:œotherœ}"
      },
      {
        "animated": false,
        "className": "",
        "data": {
          "sourceHandle": {
            "dataType": "OpenAICompatibleEmbedding",
            "id": "OpenAICompatibleEmbedding-MloZd",
            "name": "embeddings",
            "output_types": [
              "Embeddings"
            ]
          },
          "targetHandle": {
            "fieldName": "embedding",
            "id": "OpenSearchVectorStoreComponentMultimodalMultiEmbedding-WaE28",
            "inputTypes": [
              "Embeddings"
            ],
            "type": "other"
          }
        },
        "id": "xy-edge__OpenAICompatibleEmbedding-MloZd{œdataTypeœ:œOpenAICompatibleEmbeddingœ,œidœ:œOpenAICompatibleEmbedding-MloZdœ,œnameœ:œembeddingsœ,œoutput_typesœ:[œEmbeddingsœ]}-OpenSearchVectorStoreComponentMultimodalMultiEmbedding-WaE28{œfieldNameœ:œembeddingœ,œidœ:œOpenSearchVectorStoreComponentMultimodalMultiEmbedding-WaE28œ,œinputTypesœ:[œEmbeddingsœ],œtypeœ:œotherœ}",
        "selected": false,
        "source": "OpenAICompatibleEmbedding-MloZd",
        "sourceHandle": "{œdataTypeœ:œOpenAICompatibleEmbeddingœ,œidœ:œOpenAICompatibleEmbedding-MloZdœ,œnameœ:œembeddingsœ,œoutput_typesœ:[œEmbeddingsœ]}",
        "target": "OpenSearchVectorStoreComponentMultimodalMultiEmbedding-WaE28",
        "targetHandle": "{œfieldNameœ:œembeddingœ,œidœ:œOpenSearchVectorStoreComponentMultimodalMultiEmbedding-WaE28œ,œinputTypesœ:[œEmbeddingsœ],œtypeœ:œotherœ}"
      },
      {
        "animated": false,
        "className": "",
        "data": {
          "sourceHandle": {
            "dataType": "Operations",
            "id": "Operations-VUCJC",
            "name": "dataframe_output",
            "output_types": [
              "Table"
            ]
          },
          "targetHandle": {
            "fieldName": "data_inputs",
            "id": "ext:openrag:OpenRAGSplitTextComponent@extra-0ttMH",
            "inputTypes": [
              "Data",
              "JSON",
              "DataFrame",
              "Table",
              "Message"
            ],
            "type": "other"
          }
        },
        "id": "xy-edge__Operations-VUCJC{œdataTypeœ:œOperationsœ,œidœ:œOperations-VUCJCœ,œnameœ:œdataframe_outputœ,œoutput_typesœ:[œTableœ]}-ext:openrag:OpenRAGSplitTextComponent@extra-0ttMH{œfieldNameœ:œdata_inputsœ,œidœ:œext:openrag:OpenRAGSplitTextComponent@extra-0ttMHœ,œinputTypesœ:[œDataœ,œJSONœ,œDataFrameœ,œTableœ,œMessageœ],œtypeœ:œotherœ}",
        "selected": false,
        "source": "Operations-VUCJC",
        "sourceHandle": "{œdataTypeœ:œOperationsœ,œidœ:œOperations-VUCJCœ,œnameœ:œdataframe_outputœ,œoutput_typesœ:[œTableœ]}",
        "target": "ext:openrag:OpenRAGSplitTextComponent@extra-0ttMH",
        "targetHandle": "{œfieldNameœ:œdata_inputsœ,œidœ:œext:openrag:OpenRAGSplitTextComponent@extra-0ttMHœ,œinputTypesœ:[œDataœ,œJSONœ,œDataFrameœ,œTableœ,œMessageœ],œtypeœ:œotherœ}"
      },
      {
        "animated": false,
        "className": "",
        "data": {
          "sourceHandle": {
            "dataType": "ext:openrag:OpenRAGSplitTextComponent@extra",
            "id": "ext:openrag:OpenRAGSplitTextComponent@extra-0ttMH",
            "name": "dataframe",
            "output_types": [
              "Table"
            ]
          },
          "targetHandle": {
            "fieldName": "ingest_data",
            "id": "OpenSearchVectorStoreComponentMultimodalMultiEmbedding-WaE28",
            "inputTypes": [
              "Data",
              "DataFrame",
              "Table"
            ],
            "type": "other"
          }
        },
        "id": "xy-edge__ext:openrag:OpenRAGSplitTextComponent@extra-0ttMH{œdataTypeœ:œext:openrag:OpenRAGSplitTextComponent@extraœ,œidœ:œext:openrag:OpenRAGSplitTextComponent@extra-0ttMHœ,œnameœ:œdataframeœ,œoutput_typesœ:[œTableœ]}-OpenSearchVectorStoreComponentMultimodalMultiEmbedding-WaE28{œfieldNameœ:œingest_dataœ,œidœ:œOpenSearchVectorStoreComponentMultimodalMultiEmbedding-WaE28œ,œinputTypesœ:[œDataœ,œDataFrameœ,œTableœ],œtypeœ:œotherœ}",
        "selected": false,
        "source": "ext:openrag:OpenRAGSplitTextComponent@extra-0ttMH",
        "sourceHandle": "{œdataTypeœ:œext:openrag:OpenRAGSplitTextComponent@extraœ,œidœ:œext:openrag:OpenRAGSplitTextComponent@extra-0ttMHœ,œnameœ:œdataframeœ,œoutput_typesœ:[œTableœ]}",
        "target": "OpenSearchVectorStoreComponentMultimodalMultiEmbedding-WaE28",
        "targetHandle": "{œfieldNameœ:œingest_dataœ,œidœ:œOpenSearchVectorStoreComponentMultimodalMultiEmbedding-WaE28œ,œinputTypesœ:[œDataœ,œDataFrameœ,œTableœ],œtypeœ:œotherœ}"
      },
      {
        "animated": false,
        "className": "",
        "data": {
          "sourceHandle": {
            "dataType": "ExportDoclingDocument",
            "id": "ExportDoclingDocument-zZdRg",
            "name": "dataframe",
            "output_types": [
              "Table"
            ]
          },
          "targetHandle": {
            "fieldName": "df",
            "id": "Operations-IC6CD",
            "inputTypes": [
              "DataFrame",
              "Table"
            ],
            "type": "other"
          }
        },
        "id": "xy-edge__ExportDoclingDocument-zZdRg{œdataTypeœ:œExportDoclingDocumentœ,œidœ:œExportDoclingDocument-zZdRgœ,œnameœ:œdataframeœ,œoutput_typesœ:[œTableœ]}-Operations-IC6CD{œfieldNameœ:œdfœ,œidœ:œOperations-IC6CDœ,œinputTypesœ:[œDataFrameœ,œTableœ],œtypeœ:œotherœ}",
        "selected": false,
        "source": "ExportDoclingDocument-zZdRg",
        "sourceHandle": "{œdataTypeœ:œExportDoclingDocumentœ,œidœ:œExportDoclingDocument-zZdRgœ,œnameœ:œdataframeœ,œoutput_typesœ:[œTableœ]}",
        "target": "Operations-IC6CD",
        "targetHandle": "{œfieldNameœ:œdfœ,œidœ:œOperations-IC6CDœ,œinputTypesœ:[œDataFrameœ,œTableœ],œtypeœ:œotherœ}"
      },
      {
        "animated": false,
        "className": "",
        "data": {
          "sourceHandle": {
            "dataType": "Operations",
            "id": "Operations-IC6CD",
            "name": "dataframe_output",
            "output_types": [
              "Table"
            ]
          },
          "targetHandle": {
            "fieldName": "df",
            "id": "Operations-VUCJC",
            "inputTypes": [
              "DataFrame",
              "Table"
            ],
            "type": "other"
          }
        },
        "id": "xy-edge__Operations-IC6CD{œdataTypeœ:œOperationsœ,œidœ:œOperations-IC6CDœ,œnameœ:œdataframe_outputœ,œoutput_typesœ:[œTableœ]}-Operations-VUCJC{œfieldNameœ:œdfœ,œidœ:œOperations-VUCJCœ,œinputTypesœ:[œDataFrameœ,œTableœ],œtypeœ:œotherœ}",
        "selected": false,
        "source": "Operations-IC6CD",
        "sourceHandle": "{œdataTypeœ:œOperationsœ,œidœ:œOperations-IC6CDœ,œnameœ:œdataframe_outputœ,œoutput_typesœ:[œTableœ]}",
        "target": "Operations-VUCJC",
        "targetHandle": "{œfieldNameœ:œdfœ,œidœ:œOperations-VUCJCœ,œinputTypesœ:[œDataFrameœ,œTableœ],œtypeœ:œotherœ}"
      }
    ],
    "nodes": [
      {
        "data": {
          "description": "Uses Docling to process input documents connecting to your instance of Docling Serve.",
          "display_name": "Docling Serve",
          "id": "DoclingRemote-Dp3PX",
          "node": {
            "base_classes": [
              "Table"
            ],
            "beta": false,
            "conditional_paths": [],
            "custom_fields": {},
            "description": "Uses Docling to process input documents connecting to your instance of Docling Serve.",
            "display_name": "Docling Serve",
            "documentation": "https://docling-project.github.io/docling/",
            "edited": true,
            "field_order": [
              "path",
              "file_path",
              "separator",
              "silent_errors",
              "delete_server_file_after_processing",
              "ignore_unsupported_extensions",
              "ignore_unspecified_files",
              "api_url",
              "task_id",
              "max_concurrency",
              "max_poll_timeout",
              "api_headers",
              "docling_serve_opts",
              "verify_ssl"
            ],
            "frozen": false,
            "icon": "Docling",
            "last_updated": "2026-06-02T20:40:57.828Z",
            "legacy": false,
            "metadata": {
              "code_hash": "7b3186b7fe33",
              "dependencies": {
                "dependencies": [
                  {
                    "name": "httpx",
                    "version": "0.28.1"
                  },
                  {
                    "name": "docling_core",
                    "version": "2.74.1"
                  },
                  {
                    "name": "pydantic",
                    "version": "2.12.5"
                  },
                  {
                    "name": "lfx",
                    "version": "0.4.3"
                  }
                ],
                "total_dependencies": 4
              },
              "module": "custom_components.docling_serve"
            },
            "minimized": false,
            "output_types": [],
            "outputs": [
              {
                "allows_loop": false,
                "cache": true,
                "display_name": "Files",
                "group_outputs": false,
                "hidden": null,
                "loop_types": null,
                "method": "load_files",
                "name": "dataframe",
                "options": null,
                "required_inputs": null,
                "selected": "Table",
                "tool_mode": true,
                "types": [
                  "Table"
                ],
                "value": "__UNDEFINED__"
              }
            ],
            "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",
                "advanced": true,
                "display_name": "HTTP headers",
                "dynamic": false,
                "info": "Optional headers required for connecting to Docling Serve.",
                "input_types": [
                  "Data",
                  "JSON"
                ],
                "is_list": true,
                "list_add_label": "Add More",
                "load_from_db": false,
                "name": "api_headers",
                "override_skip": false,
                "placeholder": "",
                "real_time_refresh": true,
                "required": false,
                "show": true,
                "table_icon": "Table",
                "table_schema": [
                  {
                    "description": "Key name",
                    "display_name": "Key",
                    "formatter": "text",
                    "name": "key",
                    "type": "string"
                  },
                  {
                    "description": "Value of the header",
                    "display_name": "Value",
                    "formatter": "text",
                    "load_from_db": true,
                    "name": "value",
                    "type": "string"
                  }
                ],
                "title_case": false,
                "tool_mode": false,
                "trace_as_metadata": true,
                "track_in_telemetry": false,
                "trigger_icon": "Table",
                "trigger_text": "Open table",
                "type": "table",
                "value": [
                  {
                    "__load_from_db_fields": {
                      "value": true
                    },
                    "key": "Authorization",
                    "value": "JWT"
                  }
                ]
              },
              "api_url": {
                "_input_type": "StrInput",
                "advanced": false,
                "display_name": "Server address",
                "dynamic": false,
                "info": "URL of the Docling Serve instance.",
                "list": false,
                "list_add_label": "Add More",
                "load_from_db": true,
                "name": "api_url",
                "override_skip": false,
                "placeholder": "",
                "required": true,
                "show": true,
                "title_case": false,
                "tool_mode": false,
                "trace_as_metadata": true,
                "track_in_telemetry": false,
                "type": "str",
                "value": "DOCLING_SERVE_URL"
              },
              "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 __future__ import annotations\n\nimport base64\nimport json\nimport time\nfrom concurrent.futures import Future, ThreadPoolExecutor\nfrom pathlib import Path  # noqa: TC003\nfrom typing import Any\n\nimport httpx\nfrom docling_core.types.doc import DoclingDocument\nfrom lfx.base.data import BaseFileComponent\nfrom lfx.inputs import IntInput, NestedDictInput, StrInput, TableInput\nfrom lfx.inputs.inputs import FloatInput\nfrom lfx.schema import Data, dotdict\nfrom lfx.utils.util import transform_localhost_url\nfrom pydantic import ValidationError\n\n\nclass DoclingRemoteComponent(BaseFileComponent):\n    display_name = \"Docling Serve\"\n    description = (\n        \"Uses Docling to process input documents connecting to your instance of Docling Serve.\"\n    )\n    documentation = \"https://docling-project.github.io/docling/\"\n    trace_type = \"tool\"\n    icon = \"Docling\"\n    name = \"DoclingRemote\"\n\n    MAX_500_RETRIES = 5\n\n    # https://docling-project.github.io/docling/usage/supported_formats/\n    VALID_EXTENSIONS = [\n        \"adoc\",\n        \"asciidoc\",\n        \"asc\",\n        \"bmp\",\n        \"csv\",\n        \"dotx\",\n        \"dotm\",\n        \"docm\",\n        \"docx\",\n        \"htm\",\n        \"html\",\n        \"jpeg\",\n        \"jpg\",\n        \"json\",\n        \"md\",\n        \"pdf\",\n        \"png\",\n        \"potx\",\n        \"ppsx\",\n        \"pptm\",\n        \"potm\",\n        \"ppsm\",\n        \"pptx\",\n        \"tiff\",\n        \"txt\",\n        \"xls\",\n        \"xlsx\",\n        \"xhtml\",\n        \"xml\",\n        \"webp\",\n    ]\n\n    inputs = [\n        *BaseFileComponent.get_base_inputs(),\n        StrInput(\n            name=\"api_url\",\n            display_name=\"Server address\",\n            info=\"URL of the Docling Serve instance.\",\n            required=True,\n        ),\n        StrInput(\n            name=\"task_id\",\n            display_name=\"Task ID\",\n            info=(\n                \"Optional task ID from a previous Docling Serve upload. \"\n                \"If provided, file input is ignored and the component polls for this task's results.\"\n            ),\n            required=False,\n        ),\n        IntInput(\n            name=\"max_concurrency\",\n            display_name=\"Concurrency\",\n            info=\"Maximum number of concurrent requests for the server.\",\n            advanced=True,\n            value=2,\n            input_types=[\"Message\"],\n        ),\n        FloatInput(\n            name=\"max_poll_timeout\",\n            display_name=\"Maximum poll time\",\n            info=\"Maximum waiting time for the document conversion to complete.\",\n            advanced=True,\n            value=3600,\n            input_types=[\"Message\"],\n        ),\n        TableInput(\n            name=\"api_headers\",\n            display_name=\"HTTP headers\",\n            advanced=True,\n            required=False,\n            info=(\"Optional headers required for connecting to Docling Serve.\"),\n            table_schema=[\n                {\n                    \"name\": \"key\",\n                    \"display_name\": \"Key\",\n                    \"type\": \"string\",\n                    \"description\": \"Key name\",\n                },\n                {\n                    \"name\": \"value\",\n                    \"display_name\": \"Value\",\n                    \"load_from_db\": True,\n                    \"type\": \"string\",\n                    \"description\": \"Value of the header\",\n                },\n            ],\n            value=[],\n            real_time_refresh=True,\n            input_types=[\"Data\", \"JSON\"],\n        ),\n        NestedDictInput(\n            name=\"docling_serve_opts\",\n            display_name=\"Docling options\",\n            advanced=True,\n            required=False,\n            info=(\n                \"Optional dictionary of additional options. \"\n                \"See https://github.com/docling-project/docling-serve/blob/main/docs/usage.md for more information.\"\n            ),\n            input_types=[\"Message\"],\n        ),\n        StrInput(\n            name=\"verify_ssl\",\n            display_name=\"Verify SSL\",\n            info=\"Whether to verify SSL certificates for Docling Serve.\",\n            value=\"DOCLING_SERVE_VERIFY_SSL\",\n            load_from_db=True,\n            required=False,\n            advanced=True,\n        ),\n    ]\n\n    outputs = [\n        *BaseFileComponent.get_base_outputs(),\n    ]\n\n    def _process_headers(self) -> dict[str, str]:\n        \"\"\"Process the headers input into a valid dictionary.\"\"\"\n        if not self.api_headers:\n            return {}\n\n        component_headers_dict = {}\n        # TableInput normalizes to list\n        items = self.api_headers if isinstance(self.api_headers, list) else [self.api_headers]\n\n        for item in items:\n            if not item:\n                continue\n\n            # Case 1: Data object\n            if hasattr(item, \"data\") and isinstance(item.data, dict):\n                data = item.data\n                if \"key\" in data and \"value\" in data:\n                    component_headers_dict[str(data[\"key\"])] = str(data[\"value\"])\n                else:\n                    # Fallback: merge all keys from Data object\n                    for k, v in data.items():\n                        if k not in (\"text_key\", \"default_value\"):\n                            component_headers_dict[str(k)] = str(v)\n\n            # Case 2: Dictionary (Table row)\n            elif isinstance(item, dict):\n                if \"key\" in item and \"value\" in item:\n                    component_headers_dict[str(item[\"key\"])] = str(item[\"value\"])\n                else:\n                    # Fallback: merge all keys\n                    for k, v in item.items():\n                        component_headers_dict[str(k)] = str(v)\n\n            # Case 3: Message object\n            elif hasattr(item, \"text\") and isinstance(item.text, str):\n                try:\n                    parsed = json.loads(item.text)\n                    if isinstance(parsed, dict):\n                        for k, v in parsed.items():\n                            component_headers_dict[str(k)] = str(v)\n                except json.JSONDecodeError:\n                    pass\n\n        return component_headers_dict\n\n    def update_build_config(\n        self, build_config: dotdict, field_value: Any, field_name: str | None = None\n    ) -> dotdict:\n        if field_name == \"api_headers\":\n            if isinstance(field_value, dict):\n                # If it's a dict, convert to list of {key, value} pairs for TableInput\n                # This handles migration from NestedDictInput to TableInput\n                new_value = [{\"key\": k, \"value\": v} for k, v in field_value.items()]\n                build_config[\"api_headers\"][\"value\"] = new_value\n                return build_config\n            if field_value is None:\n                build_config[\"api_headers\"][\"value\"] = []\n                return build_config\n\n        # Default behavior\n        return super().update_build_config(build_config, field_value, field_name)\n\n    def _raise_if_task_missing(self, response: httpx.Response, task_id: str) -> None:\n        \"\"\"Raise a clear error when Docling Serve no longer knows the task.\n\n        Docling Serve deletes a finished task some minutes after its result is\n        first fetched, and forgets every task when it restarts. Polling such a\n        task returns 404, which would otherwise surface as a bare HTTP error.\n        \"\"\"\n        if response.status_code != httpx.codes.NOT_FOUND:\n            return\n        msg = (\n            f\"Docling task {task_id} was not found on the Docling Serve server. Its result \"\n            \"may have expired (Docling Serve deletes finished results after a delay) or the \"\n            \"server restarted. Re-ingest the file.\"\n        )\n        self.log(msg)\n        raise RuntimeError(msg)\n\n    def _poll_and_fetch_result(\n        self, client: httpx.Client, base_url: str, task_id: str, file_path: str | None = None\n    ) -> Data | None:\n        \"\"\"Poll for task completion and fetch the result.\n\n        Args:\n            client: The HTTP client to use for requests.\n            base_url: The base URL of the Docling Serve API.\n            task_id: The task ID to poll for.\n            file_path: Optional file path to include in the result data.\n\n        Returns:\n            Data object with the DoclingDocument, or None if processing failed.\n        \"\"\"\n        http_failures = 0\n        retry_status_start = 500\n        retry_status_end = 600\n        start_wait_time = time.monotonic()\n\n        response = client.get(f\"{base_url}/status/poll/{task_id}\")\n        self._raise_if_task_missing(response, task_id)\n        response.raise_for_status()\n        task = response.json()\n\n        while task[\"task_status\"] not in (\"success\", \"failure\"):\n            processing_time = time.monotonic() - start_wait_time\n            if processing_time >= self.max_poll_timeout:\n                msg = (\n                    f\"Processing time {processing_time=} exceeds the maximum poll timeout {self.max_poll_timeout=}.\"\n                    \"Please increase the max_poll_timeout parameter or review why the processing \"\n                    \"takes long on the server.\"\n                )\n                self.log(msg)\n                raise RuntimeError(msg)\n\n            time.sleep(2)\n            response = client.get(f\"{base_url}/status/poll/{task_id}\")\n\n            if retry_status_start <= response.status_code < retry_status_end:\n                http_failures += 1\n                if http_failures > self.MAX_500_RETRIES:\n                    self.log(\n                        f\"The status requests got a http response {response.status_code} too many times.\"\n                    )\n                    return None\n                continue\n\n            self._raise_if_task_missing(response, task_id)\n            response.raise_for_status()\n            task = response.json()\n\n        result_resp = client.get(f\"{base_url}/result/{task_id}\")\n        result_resp.raise_for_status()\n        result = result_resp.json()\n\n        if result.get(\"status\") == \"failure\" or result.get(\"errors\"):\n            errors = result.get(\"errors\", [])\n            err_msg_list = []\n            for err in errors:\n                if isinstance(err, dict) and \"error_message\" in err:\n                    err_msg_list.append(err[\"error_message\"])\n                elif isinstance(err, str):\n                    err_msg_list.append(err)\n\n            err_details = (\n                \"; \".join(err_msg_list) if err_msg_list else \"Unknown Docling processing error\"\n            )\n\n            msg = f\"Docling processing failed: {err_details}\"\n            raise ValueError(msg)\n\n        if \"json_content\" not in result[\"document\"] or result[\"document\"][\"json_content\"] is None:\n            self.log(\"No JSON DoclingDocument found in the result.\")\n            return None\n\n        try:\n            doc = DoclingDocument.model_validate(result[\"document\"][\"json_content\"])\n            data_dict: dict[str, Any] = {\"doc\": doc}\n            if file_path:\n                data_dict[\"file_path\"] = file_path\n            return Data(data=data_dict)\n        except ValidationError as e:\n            self.log(f\"Error validating the document. {e}\")\n            return None\n\n    def _get_verify_ssl(self) -> bool:\n        \"\"\"Determine whether to verify SSL certificates for Docling Serve.\n\n        Returns:\n            bool: True if SSL verification should be enforced, False otherwise.\n        \"\"\"\n        verify = getattr(self, \"verify_ssl\", None)\n        if hasattr(verify, \"get_secret_value\"):\n            verify = verify.get_secret_value()\n        if hasattr(verify, \"text\"):\n            verify = verify.text\n        if isinstance(verify, bool):\n            return verify\n        val_str = str(verify or \"\").strip().lower()\n        if val_str in (\"false\", \"0\", \"no\"):\n            return False\n        return True\n\n    def _process_task_id(self) -> list[Data]:\n        \"\"\"Process an existing task by polling for status and retrieving results.\n\n        Returns:\n            List containing the result Data object, or empty list if processing failed.\n        \"\"\"\n        transformed_url = transform_localhost_url(self.api_url)\n        base_url = f\"{transformed_url}/v1\"\n\n        with httpx.Client(headers=self._process_headers(), verify=self._get_verify_ssl()) as client:\n            result = self._poll_and_fetch_result(client, base_url, self.task_id)\n            return [result] if result else []\n\n    def load_files_base(self) -> list[Data]:\n        \"\"\"Load and process files, or poll an existing task if task_id is provided.\n\n        Returns:\n            list[Data]: Parsed data from the processed files or task.\n        \"\"\"\n        if self.task_id:\n            return self._process_task_id()\n        return super().load_files_base()\n\n    def process_files(\n        self, file_list: list[BaseFileComponent.BaseFile]\n    ) -> list[BaseFileComponent.BaseFile]:\n        transformed_url = transform_localhost_url(self.api_url)\n        base_url = f\"{transformed_url}/v1\"\n\n        def _convert_document(\n            client: httpx.Client, file_path: Path, options: dict[str, Any]\n        ) -> Data | None:\n            encoded_doc = base64.b64encode(file_path.read_bytes()).decode()\n            payload = {\n                \"options\": options,\n                \"sources\": [\n                    {\"kind\": \"file\", \"base64_string\": encoded_doc, \"filename\": file_path.name}\n                ],\n            }\n\n            response = client.post(f\"{base_url}/convert/source/async\", json=payload)\n            response.raise_for_status()\n            task = response.json()\n\n            return self._poll_and_fetch_result(client, base_url, task[\"task_id\"], str(file_path))\n\n        docling_options = {\n            \"to_formats\": [\"json\"],\n            \"image_export_mode\": \"placeholder\",\n            **(self.docling_serve_opts or {}),\n        }\n\n        processed_data: list[Data | None] = [None] * len(file_list)\n        with (\n            httpx.Client(headers=self._process_headers(), verify=self._get_verify_ssl()) as client,\n            ThreadPoolExecutor(max_workers=self.max_concurrency) as executor,\n        ):\n            futures: list[tuple[int, Future]] = []\n            for i, file in enumerate(file_list):\n                if file.path is not None:\n                    futures.append(\n                        (i, executor.submit(_convert_document, client, file.path, docling_options))\n                    )\n\n            for idx, future in futures:\n                try:\n                    processed_data[idx] = future.result()\n                except (httpx.HTTPStatusError, httpx.RequestError, KeyError, ValueError) as exc:\n                    self.log(f\"Docling remote processing failed: {exc}\")\n                    raise\n\n        return self.rollup_data(file_list, processed_data)\n"
              },
              "delete_server_file_after_processing": {
                "_input_type": "BoolInput",
                "advanced": true,
                "display_name": "Delete Server File After Processing",
                "dynamic": false,
                "info": "If true, the Server File Path will be deleted after processing.",
                "list": false,
                "list_add_label": "Add More",
                "name": "delete_server_file_after_processing",
                "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": true
              },
              "docling_serve_opts": {
                "_input_type": "NestedDictInput",
                "advanced": true,
                "display_name": "Docling options",
                "dynamic": false,
                "info": "Optional dictionary of additional options. See https://github.com/docling-project/docling-serve/blob/main/docs/usage.md for more information.",
                "input_types": [
                  "Message"
                ],
                "list": false,
                "list_add_label": "Add More",
                "load_from_db": false,
                "name": "docling_serve_opts",
                "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": "NestedDict",
                "value": {
                  "do_ocr": false,
                  "do_picture_classification": false,
                  "do_picture_description": false,
                  "do_table_structure": true,
                  "ocr_engine": "ocrmac"
                }
              },
              "file_path": {
                "_input_type": "HandleInput",
                "advanced": true,
                "display_name": "Server File Path",
                "dynamic": false,
                "info": "Data object with a 'file_path' property pointing to server file or a Message object with a path to the file. Supercedes 'Path' but supports same file types.",
                "input_types": [
                  "Data",
                  "JSON",
                  "Message"
                ],
                "list": true,
                "list_add_label": "Add More",
                "name": "file_path",
                "override_skip": false,
                "placeholder": "",
                "required": false,
                "show": true,
                "title_case": false,
                "trace_as_metadata": true,
                "track_in_telemetry": false,
                "type": "other",
                "value": ""
              },
              "ignore_unspecified_files": {
                "_input_type": "BoolInput",
                "advanced": true,
                "display_name": "Ignore Unspecified Files",
                "dynamic": false,
                "info": "If true, Data with no 'file_path' property will be ignored.",
                "list": false,
                "list_add_label": "Add More",
                "name": "ignore_unspecified_files",
                "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
              },
              "ignore_unsupported_extensions": {
                "_input_type": "BoolInput",
                "advanced": true,
                "display_name": "Ignore Unsupported Extensions",
                "dynamic": false,
                "info": "If true, files with unsupported extensions will not be processed.",
                "list": false,
                "list_add_label": "Add More",
                "name": "ignore_unsupported_extensions",
                "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": true
              },
              "is_refresh": false,
              "max_concurrency": {
                "_input_type": "IntInput",
                "advanced": true,
                "display_name": "Concurrency",
                "dynamic": false,
                "info": "Maximum number of concurrent requests for the server.",
                "input_types": [
                  "Message"
                ],
                "list": false,
                "list_add_label": "Add More",
                "name": "max_concurrency",
                "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": 2
              },
              "max_poll_timeout": {
                "_input_type": "FloatInput",
                "advanced": true,
                "display_name": "Maximum poll time",
                "dynamic": false,
                "info": "Maximum waiting time for the document conversion to complete.",
                "input_types": [
                  "Message"
                ],
                "list": false,
                "list_add_label": "Add More",
                "name": "max_poll_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": 3600
              },
              "path": {
                "_input_type": "FileInput",
                "advanced": false,
                "display_name": "Files",
                "dynamic": false,
                "fileTypes": [
                  "adoc",
                  "asciidoc",
                  "asc",
                  "bmp",
                  "csv",
                  "dotx",
                  "dotm",
                  "docm",
                  "docx",
                  "htm",
                  "html",
                  "jpeg",
                  "jpg",
                  "json",
                  "md",
                  "pdf",
                  "png",
                  "potx",
                  "ppsx",
                  "pptm",
                  "potm",
                  "ppsm",
                  "pptx",
                  "tiff",
                  "txt",
                  "xls",
                  "xlsx",
                  "xhtml",
                  "xml",
                  "webp",
                  "zip",
                  "tar",
                  "tgz",
                  "bz2",
                  "gz"
                ],
                "file_path": [],
                "info": "Supported file extensions: adoc, asciidoc, asc, bmp, csv, dotx, dotm, docm, docx, htm, html, jpeg, jpg, json, md, pdf, png, potx, ppsx, pptm, potm, ppsm, pptx, tiff, txt, xls, xlsx, xhtml, xml, webp; optionally bundled in file extensions: zip, tar, tgz, bz2, gz",
                "list": true,
                "list_add_label": "Add More",
                "name": "path",
                "override_skip": false,
                "placeholder": "",
                "required": false,
                "show": true,
                "temp_file": false,
                "title_case": false,
                "tool_mode": true,
                "trace_as_metadata": true,
                "track_in_telemetry": false,
                "type": "file",
                "value": ""
              },
              "separator": {
                "_input_type": "StrInput",
                "advanced": true,
                "display_name": "Separator",
                "dynamic": false,
                "info": "Specify the separator to use between multiple outputs in Message format.",
                "list": false,
                "list_add_label": "Add More",
                "load_from_db": false,
                "name": "separator",
                "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": "\n\n"
              },
              "silent_errors": {
                "_input_type": "BoolInput",
                "advanced": true,
                "display_name": "Silent Errors",
                "dynamic": false,
                "info": "If true, errors will not raise an exception.",
                "list": false,
                "list_add_label": "Add More",
                "name": "silent_errors",
                "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
              },
              "task_id": {
                "_input_type": "StrInput",
                "advanced": false,
                "display_name": "Task ID",
                "dynamic": false,
                "info": "Optional task ID from a previous Docling Serve upload. If provided, file input is ignored and the component polls for this task's results.",
                "list": false,
                "list_add_label": "Add More",
                "load_from_db": true,
                "name": "task_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": "DOCLING_TASK_ID"
              },
              "verify_ssl": {
                "_input_type": "StrInput",
                "advanced": true,
                "display_name": "Verify SSL",
                "dynamic": false,
                "info": "Whether to verify SSL certificates for Docling Serve.",
                "list": false,
                "list_add_label": "Add More",
                "load_from_db": true,
                "name": "verify_ssl",
                "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": "DOCLING_SERVE_VERIFY_SSL"
              }
            },
            "tool_mode": false
          },
          "showNode": false,
          "type": "DoclingRemote"
        },
        "dragging": false,
        "id": "DoclingRemote-Dp3PX",
        "position": {
          "x": 377.3513331245854,
          "y": 1841.1174193072818
        },
        "selected": false,
        "type": "genericNode"
      },
      {
        "data": {
          "description": "Export DoclingDocument to markdown, html or other formats.",
          "display_name": "Export DoclingDocument",
          "id": "ExportDoclingDocument-zZdRg",
          "node": {
            "base_classes": [
              "JSON",
              "Table"
            ],
            "beta": false,
            "conditional_paths": [],
            "custom_fields": {},
            "description": "Export DoclingDocument to markdown, html or other formats.",
            "display_name": "Export DoclingDocument",
            "documentation": "https://docling-project.github.io/docling/",
            "edited": false,
            "field_order": [
              "data_inputs",
              "export_format",
              "image_mode",
              "md_image_placeholder",
              "md_page_break_placeholder",
              "doc_key"
            ],
            "frozen": false,
            "icon": "Docling",
            "legacy": false,
            "metadata": {
              "code_hash": "a63df6f05725",
              "dependencies": {
                "dependencies": [
                  {
                    "name": "lfx",
                    "version": "1.11.2"
                  }
                ],
                "total_dependencies": 1
              },
              "module": "custom_components.export_doclingdocument"
            },
            "minimized": false,
            "output_types": [],
            "outputs": [
              {
                "allows_loop": false,
                "cache": true,
                "display_name": "Exported data",
                "group_outputs": false,
                "loop_types": null,
                "method": "export_document",
                "name": "data",
                "options": null,
                "required_inputs": null,
                "selected": "JSON",
                "tool_mode": true,
                "types": [
                  "JSON"
                ],
                "value": "__UNDEFINED__"
              },
              {
                "allows_loop": false,
                "cache": true,
                "display_name": "Table",
                "group_outputs": false,
                "loop_types": null,
                "method": "as_dataframe",
                "name": "dataframe",
                "options": null,
                "required_inputs": null,
                "selected": "Table",
                "tool_mode": true,
                "types": [
                  "Table"
                ],
                "value": "__UNDEFINED__"
              }
            ],
            "pinned": false,
            "template": {
              "_type": "Component",
              "code": {
                "advanced": true,
                "api_editable": false,
                "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 inspect\nfrom typing import Any\n\nfrom lfx.base.data.docling_utils import (\n    coerce_docling_document,\n    extract_docling_documents,\n    get_docling_image_ref_mode,\n)\nfrom lfx.custom import Component\nfrom lfx.io import DropdownInput, HandleInput, MessageTextInput, Output, StrInput\nfrom lfx.schema import Data, DataFrame\n\n\ndef traverse_pictures_kwargs(export_fn) -> dict[str, Any]:\n    \"\"\"Ask export_to_markdown to serialize text nested under pictures, when it can.\n\n    Scanned/image pages come back from Docling with all their OCR text attached\n    as children of a PictureItem rather than to the document body. Markdown\n    export skips picture children by default, which silently drops every OCR'd\n    word and leaves only the image placeholder.\n\n    Older docling-core releases have no `traverse_pictures` parameter and raise\n    TypeError if it is passed, so probe the signature rather than assume.\n    \"\"\"\n    try:\n        parameters = inspect.signature(export_fn).parameters\n    except (TypeError, ValueError):\n        # Some callables (C builtins, exotic wrappers) have no inspectable\n        # signature. Omitting the flag keeps the old behaviour rather than\n        # risking a TypeError that would fail the whole export.\n        return {}\n    if \"traverse_pictures\" in parameters:\n        return {\"traverse_pictures\": True}\n    return {}\n\n\nclass ExportDoclingDocumentComponent(Component):\n    display_name: str = \"Export DoclingDocument\"\n    description: str = \"Export DoclingDocument to markdown, html or other formats.\"\n    documentation = \"https://docling-project.github.io/docling/\"\n    icon = \"Docling\"\n    name = \"ExportDoclingDocument\"\n\n    inputs = [\n        HandleInput(\n            name=\"data_inputs\",\n            display_name=\"JSON or Table\",\n            info=\"The data with documents to export.\",\n            input_types=[\"Data\", \"JSON\", \"DataFrame\", \"Table\"],\n            required=True,\n        ),\n        DropdownInput(\n            name=\"export_format\",\n            display_name=\"Export format\",\n            options=[\"Markdown\", \"HTML\", \"Plaintext\", \"DocTags\"],\n            info=\"Select the export format to convert the input.\",\n            value=\"Markdown\",\n            real_time_refresh=True,\n        ),\n        DropdownInput(\n            name=\"image_mode\",\n            display_name=\"Image export mode\",\n            options=[\"placeholder\", \"embedded\"],\n            info=(\n                \"Specify how images are exported in the output. Placeholder will replace the images with a string, \"\n                \"whereas Embedded will include them as base64 encoded images.\"\n            ),\n            value=\"placeholder\",\n        ),\n        StrInput(\n            name=\"md_image_placeholder\",\n            display_name=\"Image placeholder\",\n            info=\"Specify the image placeholder for markdown exports.\",\n            value=\"<!-- image -->\",\n            advanced=True,\n        ),\n        StrInput(\n            name=\"md_page_break_placeholder\",\n            display_name=\"Page break placeholder\",\n            info=\"Add this placeholder between pages in the markdown output.\",\n            value=\"\",\n            advanced=True,\n        ),\n        MessageTextInput(\n            name=\"doc_key\",\n            display_name=\"Doc Key\",\n            info=\"The key to use for the DoclingDocument column.\",\n            value=\"doc\",\n            advanced=True,\n        ),\n    ]\n\n    outputs = [\n        Output(display_name=\"Exported data\", name=\"data\", method=\"export_document\"),\n        Output(display_name=\"Table\", name=\"dataframe\", method=\"as_dataframe\"),\n    ]\n\n    def update_build_config(\n        self, build_config: dict, field_value: Any, field_name: str | None = None\n    ) -> dict:\n        if field_name == \"export_format\" and field_value == \"Markdown\":\n            build_config[\"md_image_placeholder\"][\"show\"] = True\n            build_config[\"md_page_break_placeholder\"][\"show\"] = True\n            build_config[\"image_mode\"][\"show\"] = True\n        elif field_name == \"export_format\" and field_value == \"HTML\":\n            build_config[\"md_image_placeholder\"][\"show\"] = False\n            build_config[\"md_page_break_placeholder\"][\"show\"] = False\n            build_config[\"image_mode\"][\"show\"] = True\n        elif field_name == \"export_format\" and field_value in {\"Plaintext\", \"DocTags\"}:\n            build_config[\"md_image_placeholder\"][\"show\"] = False\n            build_config[\"md_page_break_placeholder\"][\"show\"] = False\n            build_config[\"image_mode\"][\"show\"] = False\n\n        return build_config\n\n    def _get_image_mode(self) -> Any:\n        return get_docling_image_ref_mode(self.image_mode)\n\n    @staticmethod\n    def _coerce_exportable_document(doc: Any) -> Any:\n        return coerce_docling_document(doc)\n\n    def _base_metadata(self, doc) -> dict:\n        \"\"\"Build shared metadata from a DoclingDocument.\"\"\"\n        metadata: dict = {\"export_format\": self.export_format}\n        if hasattr(doc, \"name\") and doc.name:\n            metadata[\"name\"] = doc.name\n        if hasattr(doc, \"origin\") and doc.origin is not None:\n            if hasattr(doc.origin, \"filename\") and doc.origin.filename:\n                metadata[\"filename\"] = doc.origin.filename\n            if hasattr(doc.origin, \"binary_hash\") and doc.origin.binary_hash:\n                metadata[\"document_id\"] = str(doc.origin.binary_hash)\n            if hasattr(doc.origin, \"mimetype\") and doc.origin.mimetype:\n                metadata[\"mimetype\"] = doc.origin.mimetype\n        return metadata\n\n    def _export_per_page_markdown(self, doc, image_mode: Any, base_meta: dict) -> list[Data]:\n        \"\"\"Export one Data chunk per page, tagging each with page=N.\n\n        Uses DoclingDocument.pages (ordered dict of page_no -> PageItem) to\n        iterate pages.\n        \"\"\"\n        pages_dict = getattr(doc, \"pages\", None)\n        if not pages_dict:\n            return []\n\n        results: list[Data] = []\n        for page_no in sorted(pages_dict.keys()):\n            try:\n                try:\n                    # Try standard page_no first (docling-core 2.x+)\n                    page_content = doc.export_to_markdown(\n                        image_mode=image_mode,\n                        image_placeholder=self.md_image_placeholder,\n                        page_no=page_no,\n                        **traverse_pictures_kwargs(doc.export_to_markdown),\n                    )\n                except TypeError:\n                    # Fallback to from_page/to_page parameters\n                    page_content = doc.export_to_markdown(\n                        image_mode=image_mode,\n                        image_placeholder=self.md_image_placeholder,\n                        from_page=page_no,\n                        to_page=page_no,\n                        **traverse_pictures_kwargs(doc.export_to_markdown),\n                    )\n            except Exception:\n                # Any exception from either attempt: fall back to whole-document export\n                return []\n\n            if page_content and page_content.strip():\n                meta = {**base_meta, \"page\": int(page_no)}\n                results.append(Data(text=page_content, data={\"text\": page_content, **meta}))\n\n        return results\n\n    def export_document(self) -> list[Data]:\n        documents, warning = extract_docling_documents(self.data_inputs, self.doc_key)\n        if warning:\n            self.status = warning\n\n        results: list[Data] = []\n        try:\n            image_mode = self._get_image_mode()\n            for raw_doc in documents:\n                doc = self._coerce_exportable_document(raw_doc)\n                base_meta = self._base_metadata(doc)\n\n                # For Markdown: attempt per-page export so downstream chunks\n                # carry an accurate page number (used by the chat citation UI).\n                if self.export_format == \"Markdown\":\n                    per_page = self._export_per_page_markdown(doc, image_mode, base_meta)\n                    if per_page:\n                        results.extend(per_page)\n                        continue\n\n                    # Fall back to whole-document export (no page granularity)\n                    try:\n                        content = doc.export_to_markdown(\n                            image_mode=image_mode,\n                            image_placeholder=self.md_image_placeholder,\n                            page_break_placeholder=self.md_page_break_placeholder,\n                            **traverse_pictures_kwargs(doc.export_to_markdown),\n                        )\n                    except TypeError:\n                        # Older docling-core versions lack page_break_placeholder\n                        content = doc.export_to_markdown(\n                            image_mode=image_mode,\n                            image_placeholder=self.md_image_placeholder,\n                            **traverse_pictures_kwargs(doc.export_to_markdown),\n                        )\n                elif self.export_format == \"HTML\":\n                    content = doc.export_to_html(image_mode=image_mode)\n                elif self.export_format == \"Plaintext\":\n                    content = doc.export_to_text()\n                elif self.export_format == \"DocTags\":\n                    content = doc.export_to_doctags()\n                else:\n                    content = \"\"\n\n                results.append(Data(text=content, data={\"text\": content, **base_meta}))\n\n        except Exception as e:\n            msg = f\"Error exporting document: {e}\"\n            raise TypeError(msg) from e\n\n        return results\n\n    def as_dataframe(self) -> DataFrame:\n        return DataFrame(self.export_document())\n"
              },
              "data_inputs": {
                "_input_type": "HandleInput",
                "advanced": false,
                "api_editable": false,
                "display_name": "JSON or Table",
                "dynamic": false,
                "info": "The data with documents to export.",
                "input_types": [
                  "Data",
                  "JSON",
                  "DataFrame",
                  "Table"
                ],
                "list": false,
                "list_add_label": "Add More",
                "name": "data_inputs",
                "override_skip": false,
                "placeholder": "",
                "required": true,
                "show": true,
                "title_case": false,
                "trace_as_metadata": true,
                "track_in_telemetry": false,
                "type": "other",
                "value": ""
              },
              "doc_key": {
                "_input_type": "MessageTextInput",
                "advanced": true,
                "api_editable": false,
                "display_name": "Doc Key",
                "dynamic": false,
                "info": "The key to use for the DoclingDocument column.",
                "input_types": [
                  "Message"
                ],
                "list": false,
                "list_add_label": "Add More",
                "load_from_db": false,
                "name": "doc_key",
                "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": "doc"
              },
              "export_format": {
                "_input_type": "DropdownInput",
                "advanced": false,
                "api_editable": false,
                "combobox": false,
                "dialog_inputs": {},
                "display_name": "Export format",
                "dynamic": false,
                "external_options": {},
                "info": "Select the export format to convert the input.",
                "name": "export_format",
                "options": [
                  "Markdown",
                  "HTML",
                  "Plaintext",
                  "DocTags"
                ],
                "options_metadata": [],
                "override_skip": false,
                "placeholder": "",
                "real_time_refresh": true,
                "required": false,
                "show": true,
                "title_case": false,
                "toggle": false,
                "tool_mode": false,
                "trace_as_metadata": true,
                "track_in_telemetry": true,
                "type": "str",
                "value": "Markdown"
              },
              "image_mode": {
                "_input_type": "DropdownInput",
                "advanced": false,
                "api_editable": false,
                "combobox": false,
                "dialog_inputs": {},
                "display_name": "Image export mode",
                "dynamic": false,
                "external_options": {},
                "info": "Specify how images are exported in the output. Placeholder will replace the images with a string, whereas Embedded will include them as base64 encoded images.",
                "name": "image_mode",
                "options": [
                  "placeholder",
                  "embedded"
                ],
                "options_metadata": [],
                "override_skip": false,
                "placeholder": "",
                "required": false,
                "show": true,
                "title_case": false,
                "toggle": false,
                "tool_mode": false,
                "trace_as_metadata": true,
                "track_in_telemetry": true,
                "type": "str",
                "value": "placeholder"
              },
              "md_image_placeholder": {
                "_input_type": "StrInput",
                "advanced": true,
                "api_editable": false,
                "display_name": "Image placeholder",
                "dynamic": false,
                "info": "Specify the image placeholder for markdown exports.",
                "list": false,
                "list_add_label": "Add More",
                "load_from_db": false,
                "name": "md_image_placeholder",
                "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": "<!-- image -->"
              },
              "md_page_break_placeholder": {
                "_input_type": "StrInput",
                "advanced": true,
                "api_editable": false,
                "display_name": "Page break placeholder",
                "dynamic": false,
                "info": "Add this placeholder between pages in the markdown output.",
                "list": false,
                "list_add_label": "Add More",
                "load_from_db": false,
                "name": "md_page_break_placeholder",
                "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": ""
              }
            },
            "tool_mode": false
          },
          "selected_output": "dataframe",
          "showNode": false,
          "type": "ExportDoclingDocument"
        },
        "dragging": false,
        "id": "ExportDoclingDocument-zZdRg",
        "position": {
          "x": 648.3765412475954,
          "y": 1839.7464467523132
        },
        "selected": false,
        "type": "genericNode"
      },
      {
        "data": {
          "id": "note-DCu9M",
          "node": {
            "description": "## README\n\nThis flow transforms raw documents into searchable knowledge stored in an OpenSearch vector database.\nThis [knowledge](https://docs.openr.ag/knowledge) serves as context that your [agents](https://docs.openr.ag/agents) draw upon to answer questions and perform tasks.\n\n* Data sources: This flow ingests data from OAuth connectors or can load from your local machine. For more, see [Ingest Knowledge](https://docs.openr.ag/knowledge#ingest-knowledge).\n* Docling ingestion: The [**Docling Serve** component](https://docs.openr.ag/ingestion) processes input documents by connecting to your instance of Docling serve. For more, see [Docling Ingestion](https://docs.openr.ag/ingestion).\n* Processing: The flow adds metadata through three [**DataFrame Operations** components](https://docs.langflow.org/components-processing#dataframe-operations) that add `filename`, `file_size`, and `mimetype` columns.\nThe **Split Text** component then splits the processed text into uniform, easily searchable chunks.\n* Embedding generation:The [**Embedding Model** component](https://docs.langflow.org/components-embedding-models) generates vector embeddings with the model you selected at [Application onboarding](https://docs.openr.ag/install#application-onboarding), and the [**OpenSearch** component](https://docs.langflow.org/bundles-elastic#opensearch) stores the processed documents and their embeddings in the documents index.\n* Metadata and ownership: The **Secret Input** components provide user context that is stored as metadata in OpenSearch. These fields are populated from OAuth configuration values, and enable multi-tenant document isolation in OpenSearch, so each user's documents remain private and traceable.\n\nFor more information, see the [OpenRAG docs](https://docs.openr.ag/ingestion#knowledge-ingestion-flows).\n",
            "display_name": "",
            "documentation": "",
            "template": {}
          },
          "type": "note"
        },
        "dragging": false,
        "height": 439,
        "id": "note-DCu9M",
        "measured": {
          "height": 439,
          "width": 1000
        },
        "position": {
          "x": 397.85175902629203,
          "y": 1366.975190474015
        },
        "resizing": true,
        "selected": false,
        "type": "noteNode",
        "width": 1000
      },
      {
        "data": {
          "description": "Perform operations on Text, JSON, and Tables from a single component.",
          "display_name": "Data Operations",
          "id": "Operations-IC6CD",
          "node": {
            "base_classes": [
              "Message"
            ],
            "beta": false,
            "conditional_paths": [],
            "custom_fields": {},
            "description": "Perform operations on Text, JSON, and Tables from a single component.",
            "display_name": "Data Operations",
            "documentation": "https://docs.langflow.org/components-processing#operations",
            "edited": false,
            "field_order": [
              "input_type",
              "text_input",
              "data",
              "df",
              "operation",
              "select_keys_input",
              "append_update_data",
              "remove_keys_input",
              "rename_keys_input",
              "mapped_json_display",
              "selected_key",
              "query",
              "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",
              "table_separator",
              "has_header",
              "count_words",
              "count_characters",
              "count_lines",
              "case_type",
              "use_regex",
              "search_pattern",
              "replacement_text",
              "extract_pattern",
              "max_matches",
              "head_characters",
              "tail_characters",
              "strip_mode",
              "strip_characters",
              "text_input_2",
              "remove_extra_spaces",
              "remove_special_chars",
              "remove_empty_lines"
            ],
            "frozen": false,
            "icon": "wand-sparkles",
            "last_updated": "2026-10-29T18:16:38.729Z",
            "legacy": false,
            "metadata": {
              "code_hash": "6164f967d510",
              "dependencies": {
                "dependencies": [
                  {
                    "name": "pandas",
                    "version": "2.3.3"
                  },
                  {
                    "name": "json_repair",
                    "version": "0.61.7"
                  },
                  {
                    "name": "lfx",
                    "version": "1.12.8"
                  },
                  {
                    "name": "jq",
                    "version": "1.12.0"
                  }
                ],
                "total_dependencies": 4
              },
              "keywords": [
                "operations",
                "data operations",
                "json",
                "json operations",
                "table",
                "table operations",
                "dataframe",
                "dataframe operations",
                "text",
                "text operations",
                "select keys",
                "literal eval",
                "combine",
                "append or update",
                "remove keys",
                "rename keys",
                "path selection",
                "jq expression",
                "parse json",
                "add column",
                "concatenate",
                "drop column",
                "filter",
                "head",
                "merge",
                "rename column",
                "replace value",
                "select columns",
                "sort",
                "tail",
                "drop duplicates",
                "word count",
                "case conversion",
                "text replace",
                "text extract",
                "text join",
                "text clean",
                "text to dataframe",
                "data manipulation",
                "data transformation"
              ],
              "module": "custom_components.data_operations"
            },
            "minimized": false,
            "output_types": [],
            "outputs": [
              {
                "allows_loop": false,
                "cache": true,
                "display_name": "Table",
                "group_outputs": false,
                "hidden": null,
                "loop_types": null,
                "method": "as_dataframe",
                "name": "dataframe_output",
                "options": null,
                "required_inputs": null,
                "selected": "Table",
                "tool_mode": true,
                "types": [
                  "Table"
                ],
                "value": "__UNDEFINED__"
              }
            ],
            "pinned": false,
            "template": {
              "_frontend_node_flow_id": {
                "value": "5488df7c-b93f-4f87-a446-b67028bc0813"
              },
              "_frontend_node_folder_id": {
                "value": "afa57272-6d34-4d1c-bf31-27ffad110b3a"
              },
              "_type": "Component",
              "append_update_data": {
                "_input_type": "DictInput",
                "advanced": false,
                "api_editable": false,
                "display_name": "Append or Update",
                "dynamic": false,
                "info": "Data to append or update the existing data with. Only top-level keys are checked.",
                "list": true,
                "list_add_label": "Add More",
                "name": "append_update_data",
                "override_skip": false,
                "placeholder": "",
                "required": false,
                "show": false,
                "title_case": false,
                "tool_mode": false,
                "trace_as_input": true,
                "track_in_telemetry": false,
                "type": "dict",
                "value": {
                  "key": "value"
                }
              },
              "ascending": {
                "_input_type": "BoolInput",
                "advanced": false,
                "api_editable": 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
              },
              "case_type": {
                "_input_type": "DropdownInput",
                "advanced": false,
                "api_editable": false,
                "combobox": false,
                "dialog_inputs": {},
                "display_name": "Case Type",
                "dynamic": true,
                "external_options": {},
                "info": "Type of case conversion to apply.",
                "name": "case_type",
                "options": [
                  "uppercase",
                  "lowercase",
                  "title",
                  "capitalize",
                  "swapcase"
                ],
                "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": "lowercase"
              },
              "code": {
                "advanced": true,
                "api_editable": false,
                "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": "\"\"\"Unified Operations component.\n\nBrings together the previously separate JSON, Table, and Text operation\ncomponents into a single component. An \"Input Type\" selector (Text / JSON /\nTable) drives everything: it filters the \"Operation\" picker to the operations\nthat apply to that type, reveals the matching input (Text / JSON / Table) and\nits operation-specific fields, and advertises the appropriate output type.\n\nThe three original components (JSON Operations, Table Operations, Text\nOperations) remain available as legacy components for backward compatibility\nwith existing flows.\n\"\"\"\n\nimport ast\nimport contextlib\nimport json\nimport re\nfrom typing import TYPE_CHECKING, Any\n\nimport pandas as pd\nfrom json_repair import repair_json\n\nfrom lfx.custom import Component\nfrom lfx.field_typing import RangeSpec\nfrom lfx.inputs import DictInput, SortableListInput, TabInput\nfrom lfx.io import (\n    BoolInput,\n    DataFrameInput,\n    DataInput,\n    DropdownInput,\n    IntInput,\n    MessageTextInput,\n    MultilineInput,\n    Output,\n    StrInput,\n)\nfrom lfx.log.logger import logger\nfrom lfx.schema import Data\nfrom lfx.schema.dataframe import DataFrame\nfrom lfx.schema.dotdict import dotdict\nfrom lfx.schema.message import Message\nfrom lfx.utils.jq_security import validate_jq_program\n\nif TYPE_CHECKING:\n    from collections.abc import Callable\n\n# The \"Input Type\" selector tabs. Each value maps a Langflow data type to the\n# operations, input, and output that belong to it.\nINPUT_TYPES = [\"Text\", \"JSON\", \"Table\"]\n\n# Operations grouped by input type, in display order, each with the icon shown\n# in the Operation picker. This is the single source of truth for the picker;\n# update_build_config swaps the picker's options to the selected type's list.\nOPERATIONS_BY_TYPE: dict[str, list[dict[str, str]]] = {\n    \"Text\": [\n        {\"name\": \"Word Count\", \"icon\": \"hash\"},\n        {\"name\": \"Case Conversion\", \"icon\": \"type\"},\n        {\"name\": \"Text Replace\", \"icon\": \"replace\"},\n        {\"name\": \"Text Extract\", \"icon\": \"search\"},\n        {\"name\": \"Text Head\", \"icon\": \"chevron-left\"},\n        {\"name\": \"Text Tail\", \"icon\": \"chevron-right\"},\n        {\"name\": \"Text Strip\", \"icon\": \"minus\"},\n        {\"name\": \"Text Join\", \"icon\": \"link\"},\n        {\"name\": \"Text Clean\", \"icon\": \"sparkles\"},\n        {\"name\": \"Text to DataFrame\", \"icon\": \"table\"},\n    ],\n    \"JSON\": [\n        {\"name\": \"Select Keys\", \"icon\": \"lasso-select\"},\n        {\"name\": \"Literal Eval\", \"icon\": \"braces\"},\n        {\"name\": \"Combine\", \"icon\": \"merge\"},\n        {\"name\": \"Append or Update\", \"icon\": \"circle-plus\"},\n        {\"name\": \"Remove Keys\", \"icon\": \"eraser\"},\n        {\"name\": \"Rename Keys\", \"icon\": \"pencil-line\"},\n        {\"name\": \"Path Selection\", \"icon\": \"mouse-pointer\"},\n        {\"name\": \"JQ Expression\", \"icon\": \"terminal\"},\n    ],\n    \"Table\": [\n        {\"name\": \"Add Column\", \"icon\": \"plus\"},\n        {\"name\": \"Concatenate\", \"icon\": \"combine\"},\n        {\"name\": \"Drop Column\", \"icon\": \"minus\"},\n        {\"name\": \"Filter\", \"icon\": \"filter\"},\n        {\"name\": \"Head\", \"icon\": \"arrow-up\"},\n        {\"name\": \"Merge\", \"icon\": \"merge\"},\n        {\"name\": \"Rename Column\", \"icon\": \"pencil\"},\n        {\"name\": \"Replace Value\", \"icon\": \"replace\"},\n        {\"name\": \"Select Columns\", \"icon\": \"columns\"},\n        {\"name\": \"Sort\", \"icon\": \"arrow-up-down\"},\n        {\"name\": \"Tail\", \"icon\": \"arrow-down\"},\n        {\"name\": \"Drop Duplicates\", \"icon\": \"copy-x\"},\n    ],\n}\n\n# Operation-name sets derived from the picker, used for dispatch and output\n# routing. Keeping them derived from OPERATIONS_BY_TYPE avoids any drift.\nJSON_OPERATIONS = {op[\"name\"] for op in OPERATIONS_BY_TYPE[\"JSON\"]}\nTABLE_OPERATIONS = {op[\"name\"] for op in OPERATIONS_BY_TYPE[\"Table\"]}\nTEXT_OPERATIONS = {op[\"name\"] for op in OPERATIONS_BY_TYPE[\"Text\"]}\n\n# Each input type maps to its main input field and its default output. \"Text\"\n# normally outputs a Message; \"JSON\" a Data; \"Table\" a DataFrame. A few text\n# operations override this (Word Count -> Data, Text to DataFrame -> DataFrame).\nINPUT_TYPE_TO_MAIN_INPUT = {\"Text\": \"text_input\", \"JSON\": \"data\", \"Table\": \"df\"}\n\n# Case conversions for the Text \"Case Conversion\" operation.\nCASE_CONVERTERS: dict[str, Any] = {\n    \"uppercase\": str.upper,\n    \"lowercase\": str.lower,\n    \"title\": str.title,\n    \"capitalize\": str.capitalize,\n    \"swapcase\": str.swapcase,\n}\n\n# A markdown table's delimiter row (``|---|:--:|``) separates the header from the body.\nMARKDOWN_DELIMITER_CELL = re.compile(r\":?-+:?\")\n\n\nclass OperationsComponent(Component):\n    display_name = \"Data Operations\"\n    description = \"Perform operations on Text, JSON, and Tables from a single component.\"\n    documentation: str = \"https://docs.langflow.org/components-processing#operations\"\n    icon = \"wand-sparkles\"\n    name = \"Operations\"\n    metadata = {\n        \"keywords\": [\n            \"operations\",\n            \"data operations\",\n            \"json\",\n            \"json operations\",\n            \"table\",\n            \"table operations\",\n            \"dataframe\",\n            \"dataframe operations\",\n            \"text\",\n            \"text operations\",\n            \"select keys\",\n            \"literal eval\",\n            \"combine\",\n            \"append or update\",\n            \"remove keys\",\n            \"rename keys\",\n            \"path selection\",\n            \"jq expression\",\n            \"parse json\",\n            \"add column\",\n            \"concatenate\",\n            \"drop column\",\n            \"filter\",\n            \"head\",\n            \"merge\",\n            \"rename column\",\n            \"replace value\",\n            \"select columns\",\n            \"sort\",\n            \"tail\",\n            \"drop duplicates\",\n            \"word count\",\n            \"case conversion\",\n            \"text replace\",\n            \"text extract\",\n            \"text join\",\n            \"text clean\",\n            \"text to dataframe\",\n            \"data manipulation\",\n            \"data transformation\",\n        ],\n    }\n\n    # Operation -> operation-specific input fields to reveal when selected.\n    OPERATION_FIELDS: dict[str, list[str]] = {\n        # JSON\n        \"Select Keys\": [\"select_keys_input\"],\n        \"Literal Eval\": [],\n        \"Combine\": [],\n        \"Append or Update\": [\"append_update_data\"],\n        \"Remove Keys\": [\"remove_keys_input\"],\n        \"Rename Keys\": [\"rename_keys_input\"],\n        \"Path Selection\": [\"mapped_json_display\", \"selected_key\"],\n        \"JQ Expression\": [\"query\"],\n        # Table\n        \"Add Column\": [\"new_column_name\", \"new_column_value\"],\n        \"Concatenate\": [],\n        \"Drop Column\": [\"column_name\"],\n        \"Filter\": [\"column_name\", \"filter_value\", \"filter_operator\"],\n        \"Head\": [\"num_rows\"],\n        \"Merge\": [\"left_dataframe\", \"right_dataframe\", \"merge_on_column\", \"merge_how\"],\n        \"Rename Column\": [\"column_name\", \"new_column_name\"],\n        \"Replace Value\": [\"column_name\", \"replace_value\", \"replacement_value\"],\n        \"Select Columns\": [\"columns_to_select\"],\n        \"Sort\": [\"column_name\", \"ascending\"],\n        \"Tail\": [\"num_rows\"],\n        \"Drop Duplicates\": [\"column_name\"],\n        # Text\n        \"Word Count\": [\"count_words\", \"count_characters\", \"count_lines\"],\n        \"Case Conversion\": [\"case_type\"],\n        \"Text Replace\": [\"search_pattern\", \"replacement_text\", \"use_regex\"],\n        \"Text Extract\": [\"extract_pattern\", \"max_matches\"],\n        \"Text Head\": [\"head_characters\"],\n        \"Text Tail\": [\"tail_characters\"],\n        \"Text Strip\": [\"strip_mode\", \"strip_characters\"],\n        \"Text Join\": [\"text_input_2\"],\n        \"Text Clean\": [\"remove_extra_spaces\", \"remove_special_chars\", \"remove_empty_lines\"],\n        \"Text to DataFrame\": [\"table_separator\", \"has_header\"],\n    }\n\n    # The three main inputs (one per data type). They are never treated as\n    # operation-specific fields; the input-type selector toggles them.\n    MAIN_INPUTS = (\"text_input\", \"data\", \"df\")\n\n    # Every operation-specific field (union of all the lists above), used to\n    # hide and reset fields whenever the input type or operation changes.\n    ALL_OPERATION_FIELDS: list[str] = [\n        # JSON\n        \"select_keys_input\",\n        \"append_update_data\",\n        \"remove_keys_input\",\n        \"rename_keys_input\",\n        \"mapped_json_display\",\n        \"selected_key\",\n        \"query\",\n        # Table\n        \"column_name\",\n        \"filter_value\",\n        \"filter_operator\",\n        \"ascending\",\n        \"new_column_name\",\n        \"new_column_value\",\n        \"columns_to_select\",\n        \"num_rows\",\n        \"replace_value\",\n        \"replacement_value\",\n        \"left_dataframe\",\n        \"right_dataframe\",\n        \"merge_on_column\",\n        \"merge_how\",\n        # Text\n        \"table_separator\",\n        \"has_header\",\n        \"count_words\",\n        \"count_characters\",\n        \"count_lines\",\n        \"case_type\",\n        \"use_regex\",\n        \"search_pattern\",\n        \"replacement_text\",\n        \"extract_pattern\",\n        \"max_matches\",\n        \"head_characters\",\n        \"tail_characters\",\n        \"strip_mode\",\n        \"strip_characters\",\n        \"text_input_2\",\n        \"remove_extra_spaces\",\n        \"remove_special_chars\",\n        \"remove_empty_lines\",\n    ]\n\n    # Defaults applied to the JSON operation fields when the operation changes,\n    # mirroring the JSON Operations component's reset behavior.\n    OPERATION_FIELD_DEFAULTS: dict[str, Any] = {\n        \"select_keys_input\": [],\n        \"append_update_data\": {\"key\": \"value\"},\n        \"remove_keys_input\": [],\n        \"rename_keys_input\": {\"old_key\": \"new_key\"},\n        \"mapped_json_display\": \"\",\n        \"selected_key\": None,\n        \"query\": \"\",\n    }\n\n    inputs = [\n        # --- Input type selector: drives operations, input, and output ---\n        TabInput(\n            name=\"input_type\",\n            display_name=\"Input Type\",\n            options=INPUT_TYPES,\n            value=\"Text\",\n            info=\"Select the type of input to operate on.\",\n            real_time_refresh=True,\n        ),\n        # --- Main inputs: one per data type, shown contextually ---\n        MultilineInput(\n            name=\"text_input\",\n            display_name=\"Text\",\n            info=\"The input text to process.\",\n            show=True,\n        ),\n        DataInput(\n            name=\"data\",\n            display_name=\"JSON\",\n            info=\"The JSON / Data object to operate on.\",\n            is_list=True,\n            show=False,\n        ),\n        DataFrameInput(\n            name=\"df\",\n            display_name=\"Table\",\n            info=\"The input Table to operate on. Connect multiple Tables for merge or concatenate operations.\",\n            is_list=True,\n            show=False,\n        ),\n        # --- Operation picker (options are filtered by Input Type) ---\n        SortableListInput(\n            name=\"operation\",\n            display_name=\"Operation\",\n            placeholder=\"Select Operation\",\n            info=\"Select the operation to perform. The matching fields and output appear once you choose one.\",\n            options=OPERATIONS_BY_TYPE[\"Text\"],\n            real_time_refresh=True,\n            limit=1,\n        ),\n        # --- JSON operation fields ---\n        MessageTextInput(\n            name=\"select_keys_input\",\n            display_name=\"Select Keys\",\n            info=\"List of keys to select from the data. Only top-level keys can be selected.\",\n            show=False,\n            is_list=True,\n            value=[],\n        ),\n        DictInput(\n            name=\"append_update_data\",\n            display_name=\"Append or Update\",\n            info=\"Data to append or update the existing data with. Only top-level keys are checked.\",\n            show=False,\n            value={\"key\": \"value\"},\n            is_list=True,\n        ),\n        MessageTextInput(\n            name=\"remove_keys_input\",\n            display_name=\"Remove Keys\",\n            info=\"List of keys to remove from the data.\",\n            show=False,\n            is_list=True,\n            value=[],\n        ),\n        DictInput(\n            name=\"rename_keys_input\",\n            display_name=\"Rename Keys\",\n            info=\"List of keys to rename in the data.\",\n            show=False,\n            is_list=True,\n            value={\"old_key\": \"new_key\"},\n        ),\n        MultilineInput(\n            name=\"mapped_json_display\",\n            display_name=\"JSON to Map\",\n            info=\"Paste or preview your JSON here to explore its structure and select a path for extraction.\",\n            required=False,\n            refresh_button=True,\n            real_time_refresh=True,\n            placeholder=\"Add a JSON example.\",\n            show=False,\n        ),\n        DropdownInput(\n            name=\"selected_key\",\n            display_name=\"Select Path\",\n            options=[],\n            required=False,\n            dynamic=True,\n            show=False,\n            value=None,\n        ),\n        MessageTextInput(\n            name=\"query\",\n            display_name=\"JQ Expression\",\n            info=\"JSON Query to filter the data. Used by Path Selection and JQ Expression operations.\",\n            placeholder=\"e.g., .properties.id\",\n            show=False,\n        ),\n        # --- Table operation fields ---\n        StrInput(\n            name=\"column_name\",\n            display_name=\"Column Name\",\n            info=\"The column name to use for the operation.\",\n            dynamic=True,\n            show=False,\n        ),\n        MessageTextInput(\n            name=\"filter_value\",\n            display_name=\"Filter Value\",\n            info=\"The value to filter rows by.\",\n            dynamic=True,\n            show=False,\n        ),\n        DropdownInput(\n            name=\"filter_operator\",\n            display_name=\"Filter Operator\",\n            options=[\n                \"equals\",\n                \"not equals\",\n                \"contains\",\n                \"not contains\",\n                \"starts with\",\n                \"ends with\",\n                \"greater than\",\n                \"less than\",\n            ],\n            value=\"equals\",\n            info=\"The operator to apply for filtering rows.\",\n            advanced=False,\n            dynamic=True,\n            show=False,\n        ),\n        BoolInput(\n            name=\"ascending\",\n            display_name=\"Sort Ascending\",\n            info=\"Whether to sort in ascending order.\",\n            dynamic=True,\n            show=False,\n            value=True,\n        ),\n        StrInput(\n            name=\"new_column_name\",\n            display_name=\"New Column Name\",\n            info=\"The new column name when renaming or adding a column.\",\n            dynamic=True,\n            show=False,\n        ),\n        MessageTextInput(\n            name=\"new_column_value\",\n            display_name=\"New Column Value\",\n            info=\"The value to populate the new column with.\",\n            dynamic=True,\n            show=False,\n        ),\n        StrInput(\n            name=\"columns_to_select\",\n            display_name=\"Columns to Select\",\n            dynamic=True,\n            is_list=True,\n            show=False,\n        ),\n        IntInput(\n            name=\"num_rows\",\n            display_name=\"Number of Rows\",\n            info=\"Number of rows to return (for head/tail).\",\n            dynamic=True,\n            show=False,\n            value=5,\n        ),\n        MessageTextInput(\n            name=\"replace_value\",\n            display_name=\"Value to Replace\",\n            info=\"The value to replace in the column.\",\n            dynamic=True,\n            show=False,\n        ),\n        MessageTextInput(\n            name=\"replacement_value\",\n            display_name=\"Replacement Value\",\n            info=\"The value to replace with.\",\n            dynamic=True,\n            show=False,\n        ),\n        DataFrameInput(\n            name=\"left_dataframe\",\n            display_name=\"Left Table\",\n            info=\"The left (primary) Table for merge operations. \"\n            \"In a left merge, all rows from this table are preserved.\",\n            dynamic=True,\n            show=False,\n        ),\n        DataFrameInput(\n            name=\"right_dataframe\",\n            display_name=\"Right Table\",\n            info=\"The right (secondary) Table for merge operations. \"\n            \"In a right merge, all rows from this table are preserved.\",\n            dynamic=True,\n            show=False,\n        ),\n        StrInput(\n            name=\"merge_on_column\",\n            display_name=\"Merge On Column\",\n            info=\"The column name to merge Tables on. Must exist in both Tables.\",\n            dynamic=True,\n            show=False,\n        ),\n        DropdownInput(\n            name=\"merge_how\",\n            display_name=\"Merge Type\",\n            options=[\"inner\", \"outer\", \"left\", \"right\"],\n            value=\"inner\",\n            info=\"Type of merge: inner (intersection), outer (union), left, or right.\",\n            dynamic=True,\n            show=False,\n        ),\n        # --- Text operation fields ---\n        StrInput(\n            name=\"table_separator\",\n            display_name=\"Table Separator\",\n            info=\"Separator used in the table (default: '|').\",\n            value=\"|\",\n            dynamic=True,\n            show=False,\n        ),\n        BoolInput(\n            name=\"has_header\",\n            display_name=\"Has Header\",\n            info=\"Whether the table has a header row.\",\n            value=True,\n            dynamic=True,\n            advanced=True,\n            show=False,\n        ),\n        BoolInput(\n            name=\"count_words\",\n            display_name=\"Count Words\",\n            info=\"Include word count in analysis.\",\n            value=True,\n            dynamic=True,\n            advanced=True,\n            show=False,\n        ),\n        BoolInput(\n            name=\"count_characters\",\n            display_name=\"Count Characters\",\n            info=\"Include character count in analysis.\",\n            value=True,\n            dynamic=True,\n            advanced=True,\n            show=False,\n        ),\n        BoolInput(\n            name=\"count_lines\",\n            display_name=\"Count Lines\",\n            info=\"Include line count in analysis.\",\n            value=True,\n            dynamic=True,\n            advanced=True,\n            show=False,\n        ),\n        DropdownInput(\n            name=\"case_type\",\n            display_name=\"Case Type\",\n            options=[\"uppercase\", \"lowercase\", \"title\", \"capitalize\", \"swapcase\"],\n            value=\"lowercase\",\n            info=\"Type of case conversion to apply.\",\n            dynamic=True,\n            show=False,\n        ),\n        BoolInput(\n            name=\"use_regex\",\n            display_name=\"Use Regex\",\n            info=\"Whether to treat search pattern as regex.\",\n            value=False,\n            dynamic=True,\n            show=False,\n        ),\n        StrInput(\n            name=\"search_pattern\",\n            display_name=\"Search Pattern\",\n            info=\"Text pattern to search for (supports regex).\",\n            dynamic=True,\n            show=False,\n        ),\n        StrInput(\n            name=\"replacement_text\",\n            display_name=\"Replacement Text\",\n            info=\"Text to replace the search pattern with.\",\n            dynamic=True,\n            show=False,\n        ),\n        StrInput(\n            name=\"extract_pattern\",\n            display_name=\"Extract Pattern\",\n            info=\"Regex pattern to extract from text.\",\n            dynamic=True,\n            show=False,\n        ),\n        IntInput(\n            name=\"max_matches\",\n            display_name=\"Max Matches\",\n            info=\"Maximum number of matches to extract.\",\n            value=10,\n            dynamic=True,\n            show=False,\n        ),\n        IntInput(\n            name=\"head_characters\",\n            display_name=\"Characters from Start\",\n            info=\"Number of characters to extract from the beginning of text. Must be non-negative.\",\n            value=100,\n            dynamic=True,\n            show=False,\n            range_spec=RangeSpec(min=0, max=1000000, step=1, step_type=\"int\"),\n        ),\n        IntInput(\n            name=\"tail_characters\",\n            display_name=\"Characters from End\",\n            info=\"Number of characters to extract from the end of text. Must be non-negative.\",\n            value=100,\n            dynamic=True,\n            show=False,\n            range_spec=RangeSpec(min=0, max=1000000, step=1, step_type=\"int\"),\n        ),\n        DropdownInput(\n            name=\"strip_mode\",\n            display_name=\"Strip Mode\",\n            options=[\"both\", \"left\", \"right\"],\n            value=\"both\",\n            info=\"Which sides to strip whitespace from.\",\n            dynamic=True,\n            show=False,\n        ),\n        StrInput(\n            name=\"strip_characters\",\n            display_name=\"Characters to Strip\",\n            info=\"Specific characters to remove (leave empty for whitespace).\",\n            value=\"\",\n            dynamic=True,\n            show=False,\n        ),\n        MultilineInput(\n            name=\"text_input_2\",\n            display_name=\"Second Text Input\",\n            info=\"Second text to join with the first text.\",\n            dynamic=True,\n            show=False,\n        ),\n        BoolInput(\n            name=\"remove_extra_spaces\",\n            display_name=\"Remove Extra Spaces\",\n            info=\"Remove multiple consecutive spaces.\",\n            value=True,\n            dynamic=True,\n            show=False,\n        ),\n        BoolInput(\n            name=\"remove_special_chars\",\n            display_name=\"Remove Special Characters\",\n            info=\"Remove special characters except alphanumeric and spaces.\",\n            value=False,\n            dynamic=True,\n            show=False,\n        ),\n        BoolInput(\n            name=\"remove_empty_lines\",\n            display_name=\"Remove Empty Lines\",\n            info=\"Remove empty lines from text.\",\n            value=False,\n            dynamic=True,\n            show=False,\n        ),\n    ]\n\n    # Default output matches the default Input Type (\"Text\" -> Message).\n    # update_outputs / update_frontend_node narrow it to the selected type and\n    # operation.\n    outputs = [Output(display_name=\"Message\", name=\"message_output\", method=\"as_message\")]\n\n    # ------------------------------------------------------------------\n    # Operation routing helpers\n    # ------------------------------------------------------------------\n    @staticmethod\n    def _extract_operation_name(field_value: Any) -> str:\n        \"\"\"Extract the operation name from a SortableListInput value.\"\"\"\n        if isinstance(field_value, list) and len(field_value) > 0 and isinstance(field_value[0], dict):\n            return field_value[0].get(\"name\", \"\")\n        if isinstance(field_value, str):\n            return field_value\n        return \"\"\n\n    def _operation_name(self) -> str:\n        \"\"\"Get the currently selected operation name.\"\"\"\n        return self._extract_operation_name(getattr(self, \"operation\", []))\n\n    @staticmethod\n    def _default_output_for_type(input_type: str) -> Output:\n        \"\"\"Return the output advertised for an input type when no operation is selected yet.\"\"\"\n        if input_type == \"JSON\":\n            return Output(display_name=\"JSON\", name=\"data_output\", method=\"as_data\")\n        if input_type == \"Table\":\n            return Output(display_name=\"Table\", name=\"dataframe_output\", method=\"as_dataframe\")\n        return Output(display_name=\"Message\", name=\"message_output\", method=\"as_message\")\n\n    # ------------------------------------------------------------------\n    # Dynamic UI\n    # ------------------------------------------------------------------\n    def _reset_operation_fields(self, build_config: dotdict) -> None:\n        \"\"\"Hide every operation-specific field and restore its default value.\"\"\"\n        for field in self.ALL_OPERATION_FIELDS:\n            if field in build_config:\n                build_config[field][\"show\"] = False\n                if field in self.OPERATION_FIELD_DEFAULTS:\n                    build_config[field][\"value\"] = self.OPERATION_FIELD_DEFAULTS[field]\n\n    def _show_main_input(self, build_config: dotdict, input_type: str, operation: str) -> None:\n        \"\"\"Show only the main input that matches the input type; hide the others.\"\"\"\n        for inp in self.MAIN_INPUTS:\n            if inp in build_config:\n                build_config[inp][\"show\"] = False\n                build_config[inp][\"required\"] = False\n\n        main_input = INPUT_TYPE_TO_MAIN_INPUT.get(input_type)\n        if main_input and main_input in build_config:\n            build_config[main_input][\"show\"] = True\n            build_config[main_input][\"required\"] = True\n            # The JSON \"Combine\" operation consumes a list of Data objects.\n            if main_input == \"data\":\n                build_config[\"data\"][\"is_list\"] = operation == \"Combine\"\n\n    def update_build_config(self, build_config: dotdict, field_value: Any, field_name: str | None = None) -> dotdict:\n        # Path Selection: refresh the available JSON paths from the pasted JSON.\n        if field_name == \"mapped_json_display\":\n            try:\n                parsed_json = json.loads(field_value)\n                keys = self.extract_all_paths(parsed_json)\n                build_config[\"selected_key\"][\"options\"] = keys\n                build_config[\"selected_key\"][\"show\"] = True\n            except (json.JSONDecodeError, TypeError, ValueError) as e:\n                logger.error(f\"Error parsing mapped JSON: {e}\")\n                build_config[\"selected_key\"][\"show\"] = False\n            return build_config\n\n        # Input type changed: swap the operation list, clear the selection, and\n        # show only the matching input. No operation-specific fields are shown\n        # until an operation is picked.\n        if field_name == \"input_type\":\n            input_type = field_value if field_value in OPERATIONS_BY_TYPE else \"Text\"\n            build_config[\"operation\"][\"options\"] = OPERATIONS_BY_TYPE[input_type]\n            build_config[\"operation\"][\"value\"] = []\n            self._reset_operation_fields(build_config)\n            self._show_main_input(build_config, input_type, operation=\"\")\n            return build_config\n\n        # Operation changed: reset fields, show the input for the current type,\n        # then reveal the operation-specific fields.\n        if field_name == \"operation\":\n            operation = self._extract_operation_name(field_value)\n            self._reset_operation_fields(build_config)\n\n            input_type = build_config.get(\"input_type\", {}).get(\"value\", \"Text\")\n            self._show_main_input(build_config, input_type, operation)\n\n            for field in self.OPERATION_FIELDS.get(operation, []):\n                if field in build_config:\n                    build_config[field][\"show\"] = True\n\n            return build_config\n\n        return build_config\n\n    def update_outputs(self, frontend_node: dict, field_name: str, field_value: Any) -> dict:\n        \"\"\"Create the output(s) appropriate to the selected input type and operation.\"\"\"\n        if field_name == \"input_type\":\n            # Switching type clears the operation; advertise the type's default.\n            input_type = field_value if field_value in OPERATIONS_BY_TYPE else \"Text\"\n            frontend_node[\"outputs\"] = [self._default_output_for_type(input_type)]\n            return frontend_node\n\n        template = frontend_node.get(\"template\", {})\n        input_type = template.get(\"input_type\", {}).get(\"value\", \"Text\")\n\n        if field_name == \"operation\":\n            operation = self._extract_operation_name(field_value)\n        else:\n            # Any other refresh (e.g. Path Selection's \"JSON to Map\" field)\n            # reaches here on a freshly rebuilt node whose outputs were reset\n            # to the class default (Message). Re-derive the output from the\n            # saved operation so the refresh doesn't swap the real output type.\n            operation = self._extract_operation_name(template.get(\"operation\", {}).get(\"value\", []))\n\n        if not operation:\n            # No operation selected: fall back to the input type's default output.\n            frontend_node[\"outputs\"] = [self._default_output_for_type(input_type)]\n            return frontend_node\n\n        frontend_node[\"outputs\"] = []\n        if operation in JSON_OPERATIONS or operation == \"Word Count\":\n            frontend_node[\"outputs\"].append(Output(display_name=\"JSON\", name=\"data_output\", method=\"as_data\"))\n        elif operation in TABLE_OPERATIONS or operation == \"Text to DataFrame\":\n            frontend_node[\"outputs\"].append(\n                Output(display_name=\"Table\", name=\"dataframe_output\", method=\"as_dataframe\")\n            )\n        elif operation == \"Text Join\":\n            frontend_node[\"outputs\"].append(Output(display_name=\"Text\", name=\"text_output\", method=\"as_text\"))\n            frontend_node[\"outputs\"].append(Output(display_name=\"Message\", name=\"message_output\", method=\"as_message\"))\n        else:\n            frontend_node[\"outputs\"].append(Output(display_name=\"Message\", name=\"message_output\", method=\"as_message\"))\n\n        return frontend_node\n\n    async def update_frontend_node(self, new_frontend_node: dict, current_frontend_node: dict) -> dict:\n        \"\"\"Keep the operation options and outputs in sync with the saved input type on load.\"\"\"\n        await super().update_frontend_node(new_frontend_node, current_frontend_node)\n\n        template = new_frontend_node.get(\"template\", {})\n        input_type = template.get(\"input_type\", {}).get(\"value\", \"Text\")\n        if input_type not in OPERATIONS_BY_TYPE:\n            input_type = \"Text\"\n\n        # Filter the operation picker to the saved input type.\n        if \"operation\" in template:\n            template[\"operation\"][\"options\"] = OPERATIONS_BY_TYPE[input_type]\n\n        # Re-derive the outputs from the saved input type + operation.\n        operation_value = template.get(\"operation\", {}).get(\"value\", [])\n        if self._extract_operation_name(operation_value):\n            self.update_outputs(new_frontend_node, \"operation\", operation_value)\n        else:\n            self.update_outputs(new_frontend_node, \"input_type\", input_type)\n\n        return new_frontend_node\n\n    # ==================================================================\n    # Output methods (referenced by update_outputs)\n    # ==================================================================\n    def as_data(self) -> Data:\n        \"\"\"JSON-typed output: JSON operations and Word Count.\"\"\"\n        operation = self._operation_name()\n        if operation in JSON_OPERATIONS:\n            handler = self._json_handlers().get(operation)\n            if handler:\n                try:\n                    return handler()\n                except Exception as e:\n                    logger.error(f\"Error executing {operation}: {e!s}\")\n                    raise\n        if operation == \"Word Count\":\n            return self._word_count_data()\n        return Data(data={})\n\n    def as_dataframe(self) -> DataFrame:\n        \"\"\"Table-typed output: Table operations and Text to DataFrame.\"\"\"\n        operation = self._operation_name()\n        if operation in TABLE_OPERATIONS:\n            return self._run_table_operation(operation)\n        if operation == \"Text to DataFrame\":\n            return self._text_to_dataframe(getattr(self, \"text_input\", \"\") or \"\")\n        return DataFrame(pd.DataFrame())\n\n    def as_message(self) -> Message:\n        \"\"\"Message-typed output: generic text operations (and Text Join).\"\"\"\n        return Message(text=self._format_result_as_text(self._run_text_operation()))\n\n    def as_text(self) -> Message:\n        \"\"\"Text output for the Text Join operation.\"\"\"\n        return self.as_message()\n\n    # ==================================================================\n    # JSON operations\n    # ==================================================================\n    @staticmethod\n    def extract_all_paths(obj, path=\"\"):\n        paths = []\n        if isinstance(obj, dict):\n            for k, v in obj.items():\n                new_path = f\"{path}.{k}\" if path else f\".{k}\"\n                paths.append(new_path)\n                paths.extend(OperationsComponent.extract_all_paths(v, new_path))\n        elif isinstance(obj, list) and obj:\n            new_path = f\"{path}[0]\"\n            paths.append(new_path)\n            paths.extend(OperationsComponent.extract_all_paths(obj[0], new_path))\n        return paths\n\n    @staticmethod\n    def remove_keys_recursive(obj, keys_to_remove):\n        if isinstance(obj, dict):\n            return {\n                k: OperationsComponent.remove_keys_recursive(v, keys_to_remove)\n                for k, v in obj.items()\n                if k not in keys_to_remove\n            }\n        if isinstance(obj, list):\n            return [OperationsComponent.remove_keys_recursive(item, keys_to_remove) for item in obj]\n        return obj\n\n    @staticmethod\n    def rename_keys_recursive(obj, rename_map):\n        if isinstance(obj, dict):\n            return {\n                rename_map.get(k, k): OperationsComponent.rename_keys_recursive(v, rename_map) for k, v in obj.items()\n            }\n        if isinstance(obj, list):\n            return [OperationsComponent.rename_keys_recursive(item, rename_map) for item in obj]\n        return obj\n\n    def _json_handlers(self) -> \"dict[str, Callable[[], Data]]\":\n        return {\n            \"Select Keys\": self.select_keys,\n            \"Literal Eval\": self.evaluate_data,\n            \"Combine\": self.combine_data,\n            \"Append or Update\": self.append_update,\n            \"Remove Keys\": self.remove_keys,\n            \"Rename Keys\": self.rename_keys,\n            \"Path Selection\": self.json_path,\n            \"JQ Expression\": self.json_query,\n        }\n\n    def get_data_dict(self) -> dict:\n        \"\"\"Extract data dictionary from Data object.\"\"\"\n        data = self.data[0] if isinstance(self.data, list) and len(self.data) == 1 else self.data\n        return data.model_dump()\n\n    def get_normalized_data(self) -> dict:\n        \"\"\"Get normalized data dictionary, handling the 'data' key if present.\"\"\"\n        data_dict = self.get_data_dict()\n        return data_dict.get(\"data\", data_dict)\n\n    def data_is_list(self) -> bool:\n        \"\"\"Check if data contains multiple items.\"\"\"\n        return isinstance(self.data, list) and len(self.data) > 1\n\n    def validate_single_data(self, operation: str) -> None:\n        \"\"\"Validate that the operation is being performed on a single data object.\"\"\"\n        if self.data_is_list():\n            msg = f\"{operation} operation is not supported for multiple data objects.\"\n            raise ValueError(msg)\n\n    def select_keys(self) -> Data:\n        \"\"\"Select specific keys from the data dictionary.\"\"\"\n        self.validate_single_data(\"Select Keys\")\n        data_dict = self.get_normalized_data()\n        filter_criteria: list[str] = self.select_keys_input\n\n        if len(filter_criteria) == 1 and filter_criteria[0] == \"data\":\n            filtered = data_dict[\"data\"]\n        else:\n            if not all(key in data_dict for key in filter_criteria):\n                msg = f\"Select key not found in data. Available keys: {list(data_dict.keys())}\"\n                raise ValueError(msg)\n            filtered = {key: value for key, value in data_dict.items() if key in filter_criteria}\n\n        return Data(data=filtered)\n\n    def remove_keys(self) -> Data:\n        \"\"\"Remove specified keys from the data dictionary, recursively.\"\"\"\n        self.validate_single_data(\"Remove Keys\")\n        data_dict = self.get_normalized_data()\n        remove_keys_input: list[str] = self.remove_keys_input\n        filtered = OperationsComponent.remove_keys_recursive(data_dict, set(remove_keys_input))\n        return Data(data=filtered)\n\n    def rename_keys(self) -> Data:\n        \"\"\"Rename keys in the data dictionary, recursively.\"\"\"\n        self.validate_single_data(\"Rename Keys\")\n        data_dict = self.get_normalized_data()\n        rename_keys_input: dict[str, str] = self.rename_keys_input\n        renamed = OperationsComponent.rename_keys_recursive(data_dict, rename_keys_input)\n        return Data(data=renamed)\n\n    def recursive_eval(self, data: Any) -> Any:\n        \"\"\"Recursively evaluate string values that look like Python literals.\"\"\"\n        if isinstance(data, dict):\n            return {k: self.recursive_eval(v) for k, v in data.items()}\n        if isinstance(data, list):\n            return [self.recursive_eval(item) for item in data]\n        if isinstance(data, str):\n            try:\n                if (\n                    data.strip().startswith((\"{\", \"[\", \"(\", \"'\", '\"'))\n                    or data.strip().lower() in (\"true\", \"false\", \"none\")\n                    or data.strip().replace(\".\", \"\").isdigit()\n                ):\n                    return ast.literal_eval(data)\n            except (ValueError, SyntaxError, TypeError, MemoryError):\n                return data\n            else:\n                return data\n        return data\n\n    def evaluate_data(self) -> Data:\n        \"\"\"Evaluate string values in the data dictionary.\"\"\"\n        self.validate_single_data(\"Literal Eval\")\n        logger.info(\"evaluating data\")\n        return Data(**self.recursive_eval(self.get_data_dict()))\n\n    def combine_data(self) -> Data:\n        \"\"\"Combine multiple data objects into one.\"\"\"\n        logger.info(\"combining data\")\n        if not self.data_is_list():\n            return self.data[0] if self.data else Data(data={})\n\n        data_dicts = [data.model_dump().get(\"data\", data.model_dump()) for data in self.data]\n        combined_data: dict[str, Any] = {}\n\n        for data_dict in data_dicts:\n            for key, value in data_dict.items():\n                if key not in combined_data:\n                    combined_data[key] = value\n                elif isinstance(combined_data[key], list):\n                    if isinstance(value, list):\n                        combined_data[key].extend(value)\n                    else:\n                        combined_data[key].append(value)\n                else:\n                    combined_data[key] = (\n                        [combined_data[key], value] if not isinstance(value, list) else [combined_data[key], *value]\n                    )\n\n        return Data(**combined_data)\n\n    def append_update(self) -> Data:\n        \"\"\"Append or update the data with new key-value pairs.\"\"\"\n        self.validate_single_data(\"Append or Update\")\n        data_filtered = self.get_normalized_data()\n        for key, value in self.append_update_data.items():\n            data_filtered[key] = value\n        return Data(**data_filtered)\n\n    def json_path(self) -> Data:\n        \"\"\"Extract a value from the data using the selected JQ path.\"\"\"\n        try:\n            import jq\n        except ImportError:\n            msg = \"jq is required for Path Selection. Install with: pip install jq\"\n            raise ImportError(msg) from None\n\n        try:\n            if not self.data or not self.selected_key:\n                msg = \"Missing input data or selected key.\"\n                raise ValueError(msg)\n            input_payload = self.data[0].data if isinstance(self.data, list) else self.data.data\n            validate_jq_program(self.selected_key)\n            compiled = jq.compile(self.selected_key)\n            result = compiled.input(input_payload).first()\n            if isinstance(result, dict):\n                return Data(data=result)\n            return Data(data={\"result\": result})\n        except (ValueError, TypeError, KeyError) as e:\n            self.status = f\"Error: {e!s}\"\n            self.log(self.status)\n            return Data(data={\"error\": str(e)})\n\n    def json_query(self) -> Data:\n        \"\"\"Run a JQ expression against the data.\"\"\"\n        try:\n            import jq\n        except ImportError:\n            msg = \"jq is required for JQ Expression. Install with: pip install jq\"\n            raise ImportError(msg) from None\n\n        if not self.query or not self.query.strip():\n            msg = \"JSON Query is required and cannot be blank.\"\n            raise ValueError(msg)\n        raw_data = self.get_data_dict()\n        try:\n            input_str = json.dumps(raw_data)\n            repaired = repair_json(input_str)\n            data_json = json.loads(repaired)\n            jq_input = data_json[\"data\"] if isinstance(data_json, dict) and \"data\" in data_json else data_json\n            validate_jq_program(self.query)\n            results = jq.compile(self.query).input(jq_input).all()\n            if not results:\n                msg = \"No result from JSON query.\"\n                raise ValueError(msg)\n            result = results[0] if len(results) == 1 else results\n            if result is None or result == \"None\":\n                msg = \"JSON query returned null/None. Check if the path exists in your data.\"\n                raise ValueError(msg)\n            if isinstance(result, dict):\n                return Data(data=result)\n            return Data(data={\"result\": result})\n        except (ValueError, TypeError, KeyError, json.JSONDecodeError) as e:\n            logger.error(f\"JSON Query failed: {e}\")\n            msg = f\"JSON Query error: {e}\"\n            raise ValueError(msg) from e\n\n    # ==================================================================\n    # Table operations\n    # ==================================================================\n    def _get_primary_dataframe(self) -> DataFrame:\n        \"\"\"Get the first DataFrame from input (handles both single and list inputs).\"\"\"\n        if isinstance(self.df, list):\n            return self.df[0].copy() if self.df else DataFrame()\n        return self.df.copy()\n\n    def _run_table_operation(self, operation: str) -> DataFrame:\n        # Merge and Concatenate use their own inputs, not the primary df.\n        if operation == \"Merge\":\n            return self.merge_dataframes()\n        if operation == \"Concatenate\":\n            return self.concatenate_dataframes()\n\n        df_copy = self._get_primary_dataframe()\n        table_handlers = {\n            \"Filter\": self.filter_rows_by_value,\n            \"Sort\": self.sort_by_column,\n            \"Drop Column\": self.drop_column,\n            \"Rename Column\": self.rename_column,\n            \"Add Column\": self.add_column,\n            \"Select Columns\": self.select_columns,\n            \"Head\": self.head,\n            \"Tail\": self.tail,\n            \"Replace Value\": self.replace_values,\n            \"Drop Duplicates\": self.drop_duplicates,\n        }\n        handler = table_handlers.get(operation)\n        if handler is None:\n            msg = f\"Unsupported operation: {operation}\"\n            logger.error(msg)\n            raise ValueError(msg)\n        return handler(df_copy)\n\n    @staticmethod\n    def _comparable_filter_value(column: pd.Series, filter_value: Any) -> Any:\n        \"\"\"Return a text input as a number when the column is numeric.\n\n        Filter and Replace Value inputs arrive as text, and ``30 == \"30\"`` never matches in pandas.\n        A blank input stays text: ``pd.to_numeric(\"\")`` is NaN, which would match missing cells.\n        \"\"\"\n        if filter_value in (None, \"\"):\n            return filter_value\n        if pd.api.types.is_numeric_dtype(column) and not pd.api.types.is_bool_dtype(column):\n            try:\n                return pd.to_numeric(filter_value)\n            except (ValueError, TypeError):\n                return filter_value\n        return filter_value\n\n    def filter_rows_by_value(self, df: DataFrame) -> DataFrame:\n        column = df[self.column_name]\n        filter_value = self.filter_value\n        operator = getattr(self, \"filter_operator\", \"equals\")\n\n        if operator == \"equals\":\n            mask = column == self._comparable_filter_value(column, filter_value)\n        elif operator == \"not equals\":\n            mask = column != self._comparable_filter_value(column, filter_value)\n        elif operator == \"contains\":\n            mask = column.astype(str).str.contains(str(filter_value), na=False)\n        elif operator == \"not contains\":\n            mask = ~column.astype(str).str.contains(str(filter_value), na=False)\n        elif operator == \"starts with\":\n            mask = column.astype(str).str.startswith(str(filter_value), na=False)\n        elif operator == \"ends with\":\n            mask = column.astype(str).str.endswith(str(filter_value), na=False)\n        elif operator == \"greater than\":\n            try:\n                numeric_value = pd.to_numeric(filter_value)\n                mask = column > numeric_value\n            except (ValueError, TypeError):\n                mask = column.astype(str) > str(filter_value)\n        elif operator == \"less than\":\n            try:\n                numeric_value = pd.to_numeric(filter_value)\n                mask = column < numeric_value\n            except (ValueError, TypeError):\n                mask = column.astype(str) < str(filter_value)\n        else:\n            mask = column == self._comparable_filter_value(column, filter_value)\n\n        return DataFrame(df[mask])\n\n    def sort_by_column(self, df: DataFrame) -> DataFrame:\n        return DataFrame(df.sort_values(by=self.column_name, ascending=self.ascending))\n\n    def drop_column(self, df: DataFrame) -> DataFrame:\n        return DataFrame(df.drop(columns=[self.column_name]))\n\n    def rename_column(self, df: DataFrame) -> DataFrame:\n        return DataFrame(df.rename(columns={self.column_name: self.new_column_name}))\n\n    def add_column(self, df: DataFrame) -> DataFrame:\n        df[self.new_column_name] = [self.new_column_value] * len(df)\n        return DataFrame(df)\n\n    def select_columns(self, df: DataFrame) -> DataFrame:\n        columns = [col.strip() for col in self.columns_to_select]\n        return DataFrame(df[columns])\n\n    def head(self, df: DataFrame) -> DataFrame:\n        return DataFrame(df.head(self.num_rows))\n\n    def tail(self, df: DataFrame) -> DataFrame:\n        return DataFrame(df.tail(self.num_rows))\n\n    def replace_values(self, df: DataFrame) -> DataFrame:\n        column = df[self.column_name]\n        replace_val = self._comparable_filter_value(column, self.replace_value)\n        replacement_val = self._comparable_filter_value(column, self.replacement_value)\n        try:\n            result = column.replace(replace_val, replacement_val)\n        except TypeError:\n            if not (\n                isinstance(column.dtype, pd.api.extensions.ExtensionDtype)\n                and pd.api.types.is_integer_dtype(column.dtype)\n            ):\n                raise\n            # Nullable integers reject fractional/text replacements instead of widening like NumPy columns.\n            widened = column.astype(\"Float64\" if pd.api.types.is_float(replacement_val) else object)\n            # A float cannot represent every Int64 value. Preserve unrelated large integers exactly.\n            if not widened.astype(object).equals(column.astype(object)):\n                widened = column.astype(object)\n            result = widened.mask(column.eq(replace_val).fillna(value=False), replacement_val)\n        df[self.column_name] = result\n        return DataFrame(df)\n\n    def drop_duplicates(self, df: DataFrame) -> DataFrame:\n        return DataFrame(df.drop_duplicates(subset=self.column_name))\n\n    def concatenate_dataframes(self) -> DataFrame:\n        \"\"\"Concatenate multiple DataFrames vertically (stack rows).\"\"\"\n        if not isinstance(self.df, list) or len(self.df) == 0:\n            return self.df.copy() if self.df is not None else DataFrame()\n\n        if len(self.df) == 1:\n            return self.df[0].copy()\n\n        concatenated = pd.concat(self.df, ignore_index=True)\n        return DataFrame(concatenated)\n\n    def merge_dataframes(self) -> DataFrame:\n        \"\"\"Merge two DataFrames based on a common column (join operation).\"\"\"\n        left_df = getattr(self, \"left_dataframe\", None)\n        right_df = getattr(self, \"right_dataframe\", None)\n\n        if left_df is None:\n            return DataFrame()\n        if right_df is None:\n            return left_df.copy()\n\n        df_left = left_df.copy()\n        df_right = right_df.copy()\n\n        merge_on = getattr(self, \"merge_on_column\", None)\n        merge_how = getattr(self, \"merge_how\", \"inner\")\n\n        # Track only columns created by this merge, without colliding with input names.\n        right_columns = {}\n        used_columns = set(df_left.columns) | set(df_right.columns)\n        for col in df_left.columns.intersection(df_right.columns):\n            if merge_on and col == merge_on:\n                continue\n            right_col = f\"{col}_right\"\n            while right_col in used_columns:\n                right_col += \"_right\"\n            right_columns[col] = right_col\n            used_columns.add(right_col)\n        df_right = df_right.rename(columns=right_columns)\n\n        if merge_on:\n            if merge_on not in df_left.columns:\n                msg = f\"Column '{merge_on}' not found in left DataFrame. Available: {list(df_left.columns)}\"\n                raise ValueError(msg)\n            if merge_on not in df_right.columns:\n                msg = f\"Column '{merge_on}' not found in right DataFrame. Available: {list(df_right.columns)}\"\n                raise ValueError(msg)\n            merged = df_left.merge(df_right, on=merge_on, how=merge_how)\n        else:\n            merged = df_left.merge(df_right, left_index=True, right_index=True, how=merge_how)\n\n        cols_to_drop = []\n        for col, right_col in right_columns.items():\n            merged[col] = merged[col].combine_first(merged[right_col])\n            cols_to_drop.append(right_col)\n\n        if cols_to_drop:\n            merged = merged.drop(columns=cols_to_drop)\n\n        return DataFrame(merged)\n\n    # ==================================================================\n    # Text operations\n    # ==================================================================\n    def _run_text_operation(self) -> Any:\n        \"\"\"Process text based on the selected operation (Message/Text outputs).\"\"\"\n        text = getattr(self, \"text_input\", \"\")\n        operation = self._operation_name()\n\n        # Allow empty text for Text Join (second input may have content).\n        if not text and operation != \"Text Join\":\n            return None\n\n        text_handlers = {\n            \"Case Conversion\": self._case_conversion,\n            \"Text Replace\": self._text_replace,\n            \"Text Extract\": self._text_extract,\n            \"Text Head\": self._text_head,\n            \"Text Tail\": self._text_tail,\n            \"Text Strip\": self._text_strip,\n            \"Text Join\": self._text_join,\n            \"Text Clean\": self._text_clean,\n        }\n        handler = text_handlers.get(operation)\n        if handler:\n            return handler(text)\n        return text\n\n    def _word_count_data(self) -> Data:\n        \"\"\"Word Count operation result as a Data object.\"\"\"\n        result = self._word_count(getattr(self, \"text_input\", \"\") or \"\")\n        return Data(data=result)\n\n    def _word_count(self, text: str) -> dict[str, Any]:\n        \"\"\"Count words, characters, and lines in text.\"\"\"\n        result: dict[str, Any] = {}\n        text_str = str(text) if text else \"\"\n        is_empty = not text_str or not text_str.strip()\n\n        if getattr(self, \"count_words\", True):\n            if is_empty:\n                result[\"word_count\"] = 0\n                result[\"unique_words\"] = 0\n            else:\n                words = text_str.split()\n                result[\"word_count\"] = len(words)\n                result[\"unique_words\"] = len(set(words))\n\n        if getattr(self, \"count_characters\", True):\n            if is_empty:\n                result[\"character_count\"] = 0\n                result[\"character_count_no_spaces\"] = 0\n            else:\n                result[\"character_count\"] = len(text_str)\n                result[\"character_count_no_spaces\"] = len(text_str.replace(\" \", \"\"))\n\n        if getattr(self, \"count_lines\", True):\n            if is_empty:\n                result[\"line_count\"] = 0\n                result[\"non_empty_lines\"] = 0\n            else:\n                lines = text_str.split(\"\\n\")\n                result[\"line_count\"] = len(lines)\n                result[\"non_empty_lines\"] = len([line for line in lines if line.strip()])\n\n        return result\n\n    def _text_to_dataframe(self, text: str) -> DataFrame:\n        \"\"\"Convert markdown-style table text to a DataFrame.\"\"\"\n        lines = [line.strip() for line in text.strip().split(\"\\n\") if line.strip()]\n        if not lines:\n            return DataFrame(pd.DataFrame())\n\n        separator = getattr(self, \"table_separator\", \"|\")\n        has_header = getattr(self, \"has_header\", True)\n\n        rows = self._parse_table_rows(lines, separator, has_header=has_header)\n        if not rows:\n            return DataFrame(pd.DataFrame())\n\n        df = self._create_dataframe(rows, has_header=has_header)\n        self._convert_numeric_columns(df)\n        self.log(f\"Converted text to DataFrame: {len(df)} rows, {len(df.columns)} columns\")\n        return DataFrame(df)\n\n    def _parse_table_rows(self, lines: list[str], separator: str, *, has_header: bool = True) -> list[list[str]]:\n        rows = []\n        for index, line in enumerate(lines):\n            cleaned_line = line.strip(separator)\n            cells = [cell.strip() for cell in cleaned_line.split(separator)]\n            # Skip the markdown delimiter row under the header instead of reading it as data.\n            if has_header and index == 1 and all(MARKDOWN_DELIMITER_CELL.fullmatch(cell) for cell in cells):\n                continue\n            rows.append(cells)\n        return rows\n\n    def _create_dataframe(self, rows: list[list[str]], *, has_header: bool) -> pd.DataFrame:\n        if has_header and rows:\n            header = rows[0]\n            data_rows = rows[1:]\n            header_col_count = len(header)\n            for i, row in enumerate(data_rows):\n                row_col_count = len(row)\n                if row_col_count != header_col_count:\n                    msg = (\n                        f\"Header mismatch: {header_col_count} column(s) in header vs \"\n                        f\"{row_col_count} column(s) in data row {i + 1}. \"\n                        \"Please ensure the header has the same number of columns as your data.\"\n                    )\n                    raise ValueError(msg)\n            return pd.DataFrame(data_rows, columns=header)\n\n        max_cols = max(len(row) for row in rows) if rows else 0\n        columns = [f\"col_{i}\" for i in range(max_cols)]\n        return pd.DataFrame(rows, columns=columns)\n\n    def _convert_numeric_columns(self, df: pd.DataFrame) -> None:\n        for col in df.columns:\n            with contextlib.suppress(ValueError, TypeError):\n                df[col] = pd.to_numeric(df[col])\n\n    def _case_conversion(self, text: str) -> str:\n        case_type = getattr(self, \"case_type\", \"lowercase\")\n        converter = CASE_CONVERTERS.get(case_type)\n        return converter(text) if converter else text\n\n    def _text_replace(self, text: str) -> str:\n        search_pattern = getattr(self, \"search_pattern\", \"\")\n        if not search_pattern:\n            return text\n        replacement_text = getattr(self, \"replacement_text\", \"\")\n        use_regex = getattr(self, \"use_regex\", False)\n        if use_regex:\n            try:\n                return re.sub(search_pattern, replacement_text, text)\n            except re.error as e:\n                self.log(f\"Invalid regex pattern: {e}\")\n                return text\n        return text.replace(search_pattern, replacement_text)\n\n    def _text_extract(self, text: str) -> list[str]:\n        extract_pattern = getattr(self, \"extract_pattern\", \"\")\n        if not extract_pattern:\n            return []\n        max_matches = getattr(self, \"max_matches\", 10)\n        try:\n            matches = re.findall(extract_pattern, text)\n        except re.error as e:\n            msg = f\"Invalid regex pattern '{extract_pattern}': {e}\"\n            raise ValueError(msg) from e\n        return matches[:max_matches] if max_matches > 0 else matches\n\n    def _text_head(self, text: str) -> str:\n        head_characters = getattr(self, \"head_characters\", 100)\n        if head_characters < 0:\n            msg = f\"Characters from Start must be a non-negative integer, got {head_characters}\"\n            raise ValueError(msg)\n        if head_characters == 0:\n            return \"\"\n        return text[:head_characters]\n\n    def _text_tail(self, text: str) -> str:\n        tail_characters = getattr(self, \"tail_characters\", 100)\n        if tail_characters < 0:\n            msg = f\"Characters from End must be a non-negative integer, got {tail_characters}\"\n            raise ValueError(msg)\n        if tail_characters == 0:\n            return \"\"\n        return text[-tail_characters:]\n\n    def _text_strip(self, text: str) -> str:\n        strip_mode = getattr(self, \"strip_mode\", \"both\")\n        strip_characters = getattr(self, \"strip_characters\", \"\")\n        text_str = str(text) if text else \"\"\n        chars_to_strip = strip_characters if strip_characters else None\n        if strip_mode == \"left\":\n            return text_str.lstrip(chars_to_strip)\n        if strip_mode == \"right\":\n            return text_str.rstrip(chars_to_strip)\n        return text_str.strip(chars_to_strip)\n\n    def _text_join(self, text: str) -> str:\n        text_input_2 = getattr(self, \"text_input_2\", \"\")\n        text1 = str(text) if text else \"\"\n        text2 = str(text_input_2) if text_input_2 else \"\"\n        if text1 and text2:\n            return f\"{text1}\\n{text2}\"\n        return text1 or text2\n\n    def _text_clean(self, text: str) -> str:\n        result = text\n        if getattr(self, \"remove_extra_spaces\", True):\n            # Collapse runs of horizontal whitespace but preserve newlines so\n            # that remove_empty_lines stays effective when both are enabled.\n            result = re.sub(r\"[^\\S\\n]+\", \" \", result)\n        if getattr(self, \"remove_special_chars\", False):\n            result = re.sub(r\"[^\\w\\s]\", \"\", result)\n        if getattr(self, \"remove_empty_lines\", False):\n            lines = [line for line in result.split(\"\\n\") if line.strip()]\n            result = \"\\n\".join(lines)\n        return result\n\n    def _format_result_as_text(self, result: Any) -> str:\n        if result is None:\n            return \"\"\n        if isinstance(result, list):\n            return \"\\n\".join(str(item) for item in result)\n        return str(result)\n"
              },
              "column_name": {
                "_input_type": "StrInput",
                "advanced": false,
                "api_editable": 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,
                "api_editable": 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": false,
                "title_case": false,
                "tool_mode": false,
                "trace_as_metadata": true,
                "track_in_telemetry": false,
                "type": "str",
                "value": ""
              },
              "count_characters": {
                "_input_type": "BoolInput",
                "advanced": true,
                "api_editable": false,
                "display_name": "Count Characters",
                "dynamic": true,
                "info": "Include character count in analysis.",
                "list": false,
                "list_add_label": "Add More",
                "name": "count_characters",
                "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
              },
              "count_lines": {
                "_input_type": "BoolInput",
                "advanced": true,
                "api_editable": false,
                "display_name": "Count Lines",
                "dynamic": true,
                "info": "Include line count in analysis.",
                "list": false,
                "list_add_label": "Add More",
                "name": "count_lines",
                "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
              },
              "count_words": {
                "_input_type": "BoolInput",
                "advanced": true,
                "api_editable": false,
                "display_name": "Count Words",
                "dynamic": true,
                "info": "Include word count in analysis.",
                "list": false,
                "list_add_label": "Add More",
                "name": "count_words",
                "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
              },
              "data": {
                "_input_type": "JSONInput",
                "advanced": false,
                "api_editable": false,
                "display_name": "JSON",
                "dynamic": false,
                "info": "The JSON / Data object to operate on.",
                "input_types": [
                  "Data",
                  "JSON"
                ],
                "list": true,
                "list_add_label": "Add More",
                "name": "data",
                "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": ""
              },
              "df": {
                "_input_type": "DataFrameInput",
                "advanced": false,
                "api_editable": false,
                "display_name": "Table",
                "dynamic": false,
                "info": "The input Table to operate on. Connect multiple Tables 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": ""
              },
              "extract_pattern": {
                "_input_type": "StrInput",
                "advanced": false,
                "api_editable": false,
                "display_name": "Extract Pattern",
                "dynamic": true,
                "info": "Regex pattern to extract from text.",
                "list": false,
                "list_add_label": "Add More",
                "load_from_db": false,
                "name": "extract_pattern",
                "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": ""
              },
              "filter_operator": {
                "_input_type": "DropdownInput",
                "advanced": false,
                "api_editable": 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": {
                "_input_type": "MessageTextInput",
                "advanced": false,
                "api_editable": false,
                "display_name": "Filter 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": ""
              },
              "has_header": {
                "_input_type": "BoolInput",
                "advanced": true,
                "api_editable": false,
                "display_name": "Has Header",
                "dynamic": true,
                "info": "Whether the table has a header row.",
                "list": false,
                "list_add_label": "Add More",
                "name": "has_header",
                "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
              },
              "head_characters": {
                "_input_type": "IntInput",
                "advanced": false,
                "api_editable": false,
                "display_name": "Characters from Start",
                "dynamic": true,
                "info": "Number of characters to extract from the beginning of text. Must be non-negative.",
                "list": false,
                "list_add_label": "Add More",
                "name": "head_characters",
                "override_skip": false,
                "placeholder": "",
                "range_spec": {
                  "max": 1000000,
                  "min": 0,
                  "step": 1,
                  "step_type": "int"
                },
                "required": false,
                "show": false,
                "title_case": false,
                "tool_mode": false,
                "trace_as_metadata": true,
                "track_in_telemetry": true,
                "type": "int",
                "value": 100
              },
              "input_type": {
                "_input_type": "TabInput",
                "advanced": false,
                "api_editable": false,
                "display_name": "Input Type",
                "dynamic": false,
                "info": "Select the type of input to operate on.",
                "load_from_db": false,
                "name": "input_type",
                "options": [
                  "Text",
                  "JSON",
                  "Table"
                ],
                "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": "Table"
              },
              "is_refresh": false,
              "left_dataframe": {
                "_input_type": "DataFrameInput",
                "advanced": false,
                "api_editable": false,
                "display_name": "Left Table",
                "dynamic": true,
                "info": "The left (primary) Table 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": ""
              },
              "mapped_json_display": {
                "_input_type": "MultilineInput",
                "advanced": false,
                "ai_enabled": false,
                "api_editable": false,
                "copy_field": false,
                "display_name": "JSON to Map",
                "dynamic": false,
                "info": "Paste or preview your JSON here to explore its structure and select a path for extraction.",
                "input_types": [
                  "Message"
                ],
                "list": false,
                "list_add_label": "Add More",
                "load_from_db": false,
                "multiline": true,
                "name": "mapped_json_display",
                "override_skip": false,
                "password": false,
                "placeholder": "Add a JSON example.",
                "real_time_refresh": true,
                "refresh_button": true,
                "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": ""
              },
              "max_matches": {
                "_input_type": "IntInput",
                "advanced": false,
                "api_editable": false,
                "display_name": "Max Matches",
                "dynamic": true,
                "info": "Maximum number of matches to extract.",
                "list": false,
                "list_add_label": "Add More",
                "name": "max_matches",
                "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": 10
              },
              "merge_how": {
                "_input_type": "DropdownInput",
                "advanced": false,
                "api_editable": 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,
                "api_editable": false,
                "display_name": "Merge On Column",
                "dynamic": true,
                "info": "The column name to merge Tables on. Must exist in both Tables.",
                "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,
                "api_editable": 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": true,
                "title_case": false,
                "tool_mode": false,
                "trace_as_metadata": true,
                "track_in_telemetry": false,
                "type": "str",
                "value": "file_size"
              },
              "new_column_value": {
                "_input_type": "MessageTextInput",
                "advanced": false,
                "api_editable": false,
                "display_name": "New Column Value",
                "dynamic": true,
                "info": "The value to populate the new column with.",
                "input_types": [
                  "Message"
                ],
                "list": false,
                "list_add_label": "Add More",
                "load_from_db": true,
                "name": "new_column_value",
                "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": "FILESIZE"
              },
              "num_rows": {
                "_input_type": "IntInput",
                "advanced": false,
                "api_editable": 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,
                "api_editable": false,
                "display_name": "Operation",
                "dynamic": false,
                "info": "Select the operation to perform. The matching fields and output appear once you choose one.",
                "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": "plus",
                    "name": "Add Column",
                    "selected": false
                  }
                ]
              },
              "query": {
                "_input_type": "MessageTextInput",
                "advanced": false,
                "api_editable": false,
                "display_name": "JQ Expression",
                "dynamic": false,
                "info": "JSON Query to filter the data. Used by Path Selection and JQ Expression operations.",
                "input_types": [
                  "Message"
                ],
                "list": false,
                "list_add_label": "Add More",
                "load_from_db": false,
                "name": "query",
                "override_skip": false,
                "placeholder": "e.g., .properties.id",
                "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": ""
              },
              "remove_empty_lines": {
                "_input_type": "BoolInput",
                "advanced": false,
                "api_editable": false,
                "display_name": "Remove Empty Lines",
                "dynamic": true,
                "info": "Remove empty lines from text.",
                "list": false,
                "list_add_label": "Add More",
                "name": "remove_empty_lines",
                "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": false
              },
              "remove_extra_spaces": {
                "_input_type": "BoolInput",
                "advanced": false,
                "api_editable": false,
                "display_name": "Remove Extra Spaces",
                "dynamic": true,
                "info": "Remove multiple consecutive spaces.",
                "list": false,
                "list_add_label": "Add More",
                "name": "remove_extra_spaces",
                "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
              },
              "remove_keys_input": {
                "_input_type": "MessageTextInput",
                "advanced": false,
                "api_editable": false,
                "display_name": "Remove Keys",
                "dynamic": false,
                "info": "List of keys to remove from the data.",
                "input_types": [
                  "Message"
                ],
                "list": true,
                "list_add_label": "Add More",
                "load_from_db": false,
                "name": "remove_keys_input",
                "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": []
              },
              "remove_special_chars": {
                "_input_type": "BoolInput",
                "advanced": false,
                "api_editable": false,
                "display_name": "Remove Special Characters",
                "dynamic": true,
                "info": "Remove special characters except alphanumeric and spaces.",
                "list": false,
                "list_add_label": "Add More",
                "name": "remove_special_chars",
                "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": false
              },
              "rename_keys_input": {
                "_input_type": "DictInput",
                "advanced": false,
                "api_editable": false,
                "display_name": "Rename Keys",
                "dynamic": false,
                "info": "List of keys to rename in the data.",
                "list": true,
                "list_add_label": "Add More",
                "name": "rename_keys_input",
                "override_skip": false,
                "placeholder": "",
                "required": false,
                "show": false,
                "title_case": false,
                "tool_mode": false,
                "trace_as_input": true,
                "track_in_telemetry": false,
                "type": "dict",
                "value": {
                  "old_key": "new_key"
                }
              },
              "replace_value": {
                "_input_type": "MessageTextInput",
                "advanced": false,
                "api_editable": 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_text": {
                "_input_type": "StrInput",
                "advanced": false,
                "api_editable": false,
                "display_name": "Replacement Text",
                "dynamic": true,
                "info": "Text to replace the search pattern with.",
                "list": false,
                "list_add_label": "Add More",
                "load_from_db": false,
                "name": "replacement_text",
                "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": ""
              },
              "replacement_value": {
                "_input_type": "MessageTextInput",
                "advanced": false,
                "api_editable": 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,
                "api_editable": false,
                "display_name": "Right Table",
                "dynamic": true,
                "info": "The right (secondary) Table 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": ""
              },
              "search_pattern": {
                "_input_type": "StrInput",
                "advanced": false,
                "api_editable": false,
                "display_name": "Search Pattern",
                "dynamic": true,
                "info": "Text pattern to search for (supports regex).",
                "list": false,
                "list_add_label": "Add More",
                "load_from_db": false,
                "name": "search_pattern",
                "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": ""
              },
              "select_keys_input": {
                "_input_type": "MessageTextInput",
                "advanced": false,
                "api_editable": false,
                "display_name": "Select Keys",
                "dynamic": false,
                "info": "List of keys to select from the data. Only top-level keys can be selected.",
                "input_types": [
                  "Message"
                ],
                "list": true,
                "list_add_label": "Add More",
                "load_from_db": false,
                "name": "select_keys_input",
                "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": []
              },
              "selected_key": {
                "_input_type": "DropdownInput",
                "advanced": false,
                "api_editable": false,
                "combobox": false,
                "dialog_inputs": {},
                "display_name": "Select Path",
                "dynamic": true,
                "external_options": {},
                "info": "",
                "name": "selected_key",
                "options": [],
                "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": null
              },
              "strip_characters": {
                "_input_type": "StrInput",
                "advanced": false,
                "api_editable": false,
                "display_name": "Characters to Strip",
                "dynamic": true,
                "info": "Specific characters to remove (leave empty for whitespace).",
                "list": false,
                "list_add_label": "Add More",
                "load_from_db": false,
                "name": "strip_characters",
                "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": ""
              },
              "strip_mode": {
                "_input_type": "DropdownInput",
                "advanced": false,
                "api_editable": false,
                "combobox": false,
                "dialog_inputs": {},
                "display_name": "Strip Mode",
                "dynamic": true,
                "external_options": {},
                "info": "Which sides to strip whitespace from.",
                "name": "strip_mode",
                "options": [
                  "both",
                  "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": "both"
              },
              "table_separator": {
                "_input_type": "StrInput",
                "advanced": false,
                "api_editable": false,
                "display_name": "Table Separator",
                "dynamic": true,
                "info": "Separator used in the table (default: '|').",
                "list": false,
                "list_add_label": "Add More",
                "load_from_db": false,
                "name": "table_separator",
                "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": "|"
              },
              "tail_characters": {
                "_input_type": "IntInput",
                "advanced": false,
                "api_editable": false,
                "display_name": "Characters from End",
                "dynamic": true,
                "info": "Number of characters to extract from the end of text. Must be non-negative.",
                "list": false,
                "list_add_label": "Add More",
                "name": "tail_characters",
                "override_skip": false,
                "placeholder": "",
                "range_spec": {
                  "max": 1000000,
                  "min": 0,
                  "step": 1,
                  "step_type": "int"
                },
                "required": false,
                "show": false,
                "title_case": false,
                "tool_mode": false,
                "trace_as_metadata": true,
                "track_in_telemetry": true,
                "type": "int",
                "value": 100
              },
              "text_input": {
                "_input_type": "MultilineInput",
                "advanced": false,
                "ai_enabled": false,
                "api_editable": false,
                "copy_field": false,
                "display_name": "Text",
                "dynamic": false,
                "info": "The input text to process.",
                "input_types": [
                  "Message"
                ],
                "list": false,
                "list_add_label": "Add More",
                "load_from_db": false,
                "multiline": true,
                "name": "text_input",
                "override_skip": false,
                "password": 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": ""
              },
              "text_input_2": {
                "_input_type": "MultilineInput",
                "advanced": false,
                "ai_enabled": false,
                "api_editable": false,
                "copy_field": false,
                "display_name": "Second Text Input",
                "dynamic": true,
                "info": "Second text to join with the first text.",
                "input_types": [
                  "Message"
                ],
                "list": false,
                "list_add_label": "Add More",
                "load_from_db": false,
                "multiline": true,
                "name": "text_input_2",
                "override_skip": false,
                "password": 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": ""
              },
              "use_regex": {
                "_input_type": "BoolInput",
                "advanced": false,
                "api_editable": false,
                "display_name": "Use Regex",
                "dynamic": true,
                "info": "Whether to treat search pattern as regex.",
                "list": false,
                "list_add_label": "Add More",
                "name": "use_regex",
                "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": false
              }
            },
            "tool_mode": false
          },
          "showNode": false,
          "type": "Operations"
        },
        "dragging": false,
        "id": "Operations-IC6CD",
        "position": {
          "x": 922.8558031751697,
          "y": 1830.0439761689086
        },
        "selected": false,
        "type": "genericNode"
      },
      {
        "data": {
          "description": "Perform operations on Text, JSON, and Tables from a single component.",
          "display_name": "Data Operations",
          "id": "Operations-VUCJC",
          "node": {
            "base_classes": [
              "Message"
            ],
            "beta": false,
            "conditional_paths": [],
            "custom_fields": {},
            "description": "Perform operations on Text, JSON, and Tables from a single component.",
            "display_name": "Data Operations",
            "documentation": "https://docs.langflow.org/components-processing#operations",
            "edited": false,
            "field_order": [
              "input_type",
              "text_input",
              "data",
              "df",
              "operation",
              "select_keys_input",
              "append_update_data",
              "remove_keys_input",
              "rename_keys_input",
              "mapped_json_display",
              "selected_key",
              "query",
              "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",
              "table_separator",
              "has_header",
              "count_words",
              "count_characters",
              "count_lines",
              "case_type",
              "use_regex",
              "search_pattern",
              "replacement_text",
              "extract_pattern",
              "max_matches",
              "head_characters",
              "tail_characters",
              "strip_mode",
              "strip_characters",
              "text_input_2",
              "remove_extra_spaces",
              "remove_special_chars",
              "remove_empty_lines"
            ],
            "frozen": false,
            "icon": "wand-sparkles",
            "last_updated": "2026-10-29T18:16:47.706Z",
            "legacy": false,
            "metadata": {
              "code_hash": "6164f967d510",
              "dependencies": {
                "dependencies": [
                  {
                    "name": "pandas",
                    "version": "2.3.3"
                  },
                  {
                    "name": "json_repair",
                    "version": "0.61.7"
                  },
                  {
                    "name": "lfx",
                    "version": "1.12.8"
                  },
                  {
                    "name": "jq",
                    "version": "1.12.0"
                  }
                ],
                "total_dependencies": 4
              },
              "keywords": [
                "operations",
                "data operations",
                "json",
                "json operations",
                "table",
                "table operations",
                "dataframe",
                "dataframe operations",
                "text",
                "text operations",
                "select keys",
                "literal eval",
                "combine",
                "append or update",
                "remove keys",
                "rename keys",
                "path selection",
                "jq expression",
                "parse json",
                "add column",
                "concatenate",
                "drop column",
                "filter",
                "head",
                "merge",
                "rename column",
                "replace value",
                "select columns",
                "sort",
                "tail",
                "drop duplicates",
                "word count",
                "case conversion",
                "text replace",
                "text extract",
                "text join",
                "text clean",
                "text to dataframe",
                "data manipulation",
                "data transformation"
              ],
              "module": "custom_components.data_operations"
            },
            "minimized": false,
            "output_types": [],
            "outputs": [
              {
                "allows_loop": false,
                "cache": true,
                "display_name": "Table",
                "group_outputs": false,
                "hidden": null,
                "loop_types": null,
                "method": "as_dataframe",
                "name": "dataframe_output",
                "options": null,
                "required_inputs": null,
                "selected": "Table",
                "tool_mode": true,
                "types": [
                  "Table"
                ],
                "value": "__UNDEFINED__"
              }
            ],
            "pinned": false,
            "template": {
              "_frontend_node_flow_id": {
                "value": "5488df7c-b93f-4f87-a446-b67028bc0813"
              },
              "_frontend_node_folder_id": {
                "value": "afa57272-6d34-4d1c-bf31-27ffad110b3a"
              },
              "_type": "Component",
              "append_update_data": {
                "_input_type": "DictInput",
                "advanced": false,
                "api_editable": false,
                "display_name": "Append or Update",
                "dynamic": false,
                "info": "Data to append or update the existing data with. Only top-level keys are checked.",
                "list": true,
                "list_add_label": "Add More",
                "name": "append_update_data",
                "override_skip": false,
                "placeholder": "",
                "required": false,
                "show": false,
                "title_case": false,
                "tool_mode": false,
                "trace_as_input": true,
                "track_in_telemetry": false,
                "type": "dict",
                "value": {
                  "key": "value"
                }
              },
              "ascending": {
                "_input_type": "BoolInput",
                "advanced": false,
                "api_editable": 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
              },
              "case_type": {
                "_input_type": "DropdownInput",
                "advanced": false,
                "api_editable": false,
                "combobox": false,
                "dialog_inputs": {},
                "display_name": "Case Type",
                "dynamic": true,
                "external_options": {},
                "info": "Type of case conversion to apply.",
                "name": "case_type",
                "options": [
                  "uppercase",
                  "lowercase",
                  "title",
                  "capitalize",
                  "swapcase"
                ],
                "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": "lowercase"
              },
              "code": {
                "advanced": true,
                "api_editable": false,
                "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": "\"\"\"Unified Operations component.\n\nBrings together the previously separate JSON, Table, and Text operation\ncomponents into a single component. An \"Input Type\" selector (Text / JSON /\nTable) drives everything: it filters the \"Operation\" picker to the operations\nthat apply to that type, reveals the matching input (Text / JSON / Table) and\nits operation-specific fields, and advertises the appropriate output type.\n\nThe three original components (JSON Operations, Table Operations, Text\nOperations) remain available as legacy components for backward compatibility\nwith existing flows.\n\"\"\"\n\nimport ast\nimport contextlib\nimport json\nimport re\nfrom typing import TYPE_CHECKING, Any\n\nimport pandas as pd\nfrom json_repair import repair_json\n\nfrom lfx.custom import Component\nfrom lfx.field_typing import RangeSpec\nfrom lfx.inputs import DictInput, SortableListInput, TabInput\nfrom lfx.io import (\n    BoolInput,\n    DataFrameInput,\n    DataInput,\n    DropdownInput,\n    IntInput,\n    MessageTextInput,\n    MultilineInput,\n    Output,\n    StrInput,\n)\nfrom lfx.log.logger import logger\nfrom lfx.schema import Data\nfrom lfx.schema.dataframe import DataFrame\nfrom lfx.schema.dotdict import dotdict\nfrom lfx.schema.message import Message\nfrom lfx.utils.jq_security import validate_jq_program\n\nif TYPE_CHECKING:\n    from collections.abc import Callable\n\n# The \"Input Type\" selector tabs. Each value maps a Langflow data type to the\n# operations, input, and output that belong to it.\nINPUT_TYPES = [\"Text\", \"JSON\", \"Table\"]\n\n# Operations grouped by input type, in display order, each with the icon shown\n# in the Operation picker. This is the single source of truth for the picker;\n# update_build_config swaps the picker's options to the selected type's list.\nOPERATIONS_BY_TYPE: dict[str, list[dict[str, str]]] = {\n    \"Text\": [\n        {\"name\": \"Word Count\", \"icon\": \"hash\"},\n        {\"name\": \"Case Conversion\", \"icon\": \"type\"},\n        {\"name\": \"Text Replace\", \"icon\": \"replace\"},\n        {\"name\": \"Text Extract\", \"icon\": \"search\"},\n        {\"name\": \"Text Head\", \"icon\": \"chevron-left\"},\n        {\"name\": \"Text Tail\", \"icon\": \"chevron-right\"},\n        {\"name\": \"Text Strip\", \"icon\": \"minus\"},\n        {\"name\": \"Text Join\", \"icon\": \"link\"},\n        {\"name\": \"Text Clean\", \"icon\": \"sparkles\"},\n        {\"name\": \"Text to DataFrame\", \"icon\": \"table\"},\n    ],\n    \"JSON\": [\n        {\"name\": \"Select Keys\", \"icon\": \"lasso-select\"},\n        {\"name\": \"Literal Eval\", \"icon\": \"braces\"},\n        {\"name\": \"Combine\", \"icon\": \"merge\"},\n        {\"name\": \"Append or Update\", \"icon\": \"circle-plus\"},\n        {\"name\": \"Remove Keys\", \"icon\": \"eraser\"},\n        {\"name\": \"Rename Keys\", \"icon\": \"pencil-line\"},\n        {\"name\": \"Path Selection\", \"icon\": \"mouse-pointer\"},\n        {\"name\": \"JQ Expression\", \"icon\": \"terminal\"},\n    ],\n    \"Table\": [\n        {\"name\": \"Add Column\", \"icon\": \"plus\"},\n        {\"name\": \"Concatenate\", \"icon\": \"combine\"},\n        {\"name\": \"Drop Column\", \"icon\": \"minus\"},\n        {\"name\": \"Filter\", \"icon\": \"filter\"},\n        {\"name\": \"Head\", \"icon\": \"arrow-up\"},\n        {\"name\": \"Merge\", \"icon\": \"merge\"},\n        {\"name\": \"Rename Column\", \"icon\": \"pencil\"},\n        {\"name\": \"Replace Value\", \"icon\": \"replace\"},\n        {\"name\": \"Select Columns\", \"icon\": \"columns\"},\n        {\"name\": \"Sort\", \"icon\": \"arrow-up-down\"},\n        {\"name\": \"Tail\", \"icon\": \"arrow-down\"},\n        {\"name\": \"Drop Duplicates\", \"icon\": \"copy-x\"},\n    ],\n}\n\n# Operation-name sets derived from the picker, used for dispatch and output\n# routing. Keeping them derived from OPERATIONS_BY_TYPE avoids any drift.\nJSON_OPERATIONS = {op[\"name\"] for op in OPERATIONS_BY_TYPE[\"JSON\"]}\nTABLE_OPERATIONS = {op[\"name\"] for op in OPERATIONS_BY_TYPE[\"Table\"]}\nTEXT_OPERATIONS = {op[\"name\"] for op in OPERATIONS_BY_TYPE[\"Text\"]}\n\n# Each input type maps to its main input field and its default output. \"Text\"\n# normally outputs a Message; \"JSON\" a Data; \"Table\" a DataFrame. A few text\n# operations override this (Word Count -> Data, Text to DataFrame -> DataFrame).\nINPUT_TYPE_TO_MAIN_INPUT = {\"Text\": \"text_input\", \"JSON\": \"data\", \"Table\": \"df\"}\n\n# Case conversions for the Text \"Case Conversion\" operation.\nCASE_CONVERTERS: dict[str, Any] = {\n    \"uppercase\": str.upper,\n    \"lowercase\": str.lower,\n    \"title\": str.title,\n    \"capitalize\": str.capitalize,\n    \"swapcase\": str.swapcase,\n}\n\n# A markdown table's delimiter row (``|---|:--:|``) separates the header from the body.\nMARKDOWN_DELIMITER_CELL = re.compile(r\":?-+:?\")\n\n\nclass OperationsComponent(Component):\n    display_name = \"Data Operations\"\n    description = \"Perform operations on Text, JSON, and Tables from a single component.\"\n    documentation: str = \"https://docs.langflow.org/components-processing#operations\"\n    icon = \"wand-sparkles\"\n    name = \"Operations\"\n    metadata = {\n        \"keywords\": [\n            \"operations\",\n            \"data operations\",\n            \"json\",\n            \"json operations\",\n            \"table\",\n            \"table operations\",\n            \"dataframe\",\n            \"dataframe operations\",\n            \"text\",\n            \"text operations\",\n            \"select keys\",\n            \"literal eval\",\n            \"combine\",\n            \"append or update\",\n            \"remove keys\",\n            \"rename keys\",\n            \"path selection\",\n            \"jq expression\",\n            \"parse json\",\n            \"add column\",\n            \"concatenate\",\n            \"drop column\",\n            \"filter\",\n            \"head\",\n            \"merge\",\n            \"rename column\",\n            \"replace value\",\n            \"select columns\",\n            \"sort\",\n            \"tail\",\n            \"drop duplicates\",\n            \"word count\",\n            \"case conversion\",\n            \"text replace\",\n            \"text extract\",\n            \"text join\",\n            \"text clean\",\n            \"text to dataframe\",\n            \"data manipulation\",\n            \"data transformation\",\n        ],\n    }\n\n    # Operation -> operation-specific input fields to reveal when selected.\n    OPERATION_FIELDS: dict[str, list[str]] = {\n        # JSON\n        \"Select Keys\": [\"select_keys_input\"],\n        \"Literal Eval\": [],\n        \"Combine\": [],\n        \"Append or Update\": [\"append_update_data\"],\n        \"Remove Keys\": [\"remove_keys_input\"],\n        \"Rename Keys\": [\"rename_keys_input\"],\n        \"Path Selection\": [\"mapped_json_display\", \"selected_key\"],\n        \"JQ Expression\": [\"query\"],\n        # Table\n        \"Add Column\": [\"new_column_name\", \"new_column_value\"],\n        \"Concatenate\": [],\n        \"Drop Column\": [\"column_name\"],\n        \"Filter\": [\"column_name\", \"filter_value\", \"filter_operator\"],\n        \"Head\": [\"num_rows\"],\n        \"Merge\": [\"left_dataframe\", \"right_dataframe\", \"merge_on_column\", \"merge_how\"],\n        \"Rename Column\": [\"column_name\", \"new_column_name\"],\n        \"Replace Value\": [\"column_name\", \"replace_value\", \"replacement_value\"],\n        \"Select Columns\": [\"columns_to_select\"],\n        \"Sort\": [\"column_name\", \"ascending\"],\n        \"Tail\": [\"num_rows\"],\n        \"Drop Duplicates\": [\"column_name\"],\n        # Text\n        \"Word Count\": [\"count_words\", \"count_characters\", \"count_lines\"],\n        \"Case Conversion\": [\"case_type\"],\n        \"Text Replace\": [\"search_pattern\", \"replacement_text\", \"use_regex\"],\n        \"Text Extract\": [\"extract_pattern\", \"max_matches\"],\n        \"Text Head\": [\"head_characters\"],\n        \"Text Tail\": [\"tail_characters\"],\n        \"Text Strip\": [\"strip_mode\", \"strip_characters\"],\n        \"Text Join\": [\"text_input_2\"],\n        \"Text Clean\": [\"remove_extra_spaces\", \"remove_special_chars\", \"remove_empty_lines\"],\n        \"Text to DataFrame\": [\"table_separator\", \"has_header\"],\n    }\n\n    # The three main inputs (one per data type). They are never treated as\n    # operation-specific fields; the input-type selector toggles them.\n    MAIN_INPUTS = (\"text_input\", \"data\", \"df\")\n\n    # Every operation-specific field (union of all the lists above), used to\n    # hide and reset fields whenever the input type or operation changes.\n    ALL_OPERATION_FIELDS: list[str] = [\n        # JSON\n        \"select_keys_input\",\n        \"append_update_data\",\n        \"remove_keys_input\",\n        \"rename_keys_input\",\n        \"mapped_json_display\",\n        \"selected_key\",\n        \"query\",\n        # Table\n        \"column_name\",\n        \"filter_value\",\n        \"filter_operator\",\n        \"ascending\",\n        \"new_column_name\",\n        \"new_column_value\",\n        \"columns_to_select\",\n        \"num_rows\",\n        \"replace_value\",\n        \"replacement_value\",\n        \"left_dataframe\",\n        \"right_dataframe\",\n        \"merge_on_column\",\n        \"merge_how\",\n        # Text\n        \"table_separator\",\n        \"has_header\",\n        \"count_words\",\n        \"count_characters\",\n        \"count_lines\",\n        \"case_type\",\n        \"use_regex\",\n        \"search_pattern\",\n        \"replacement_text\",\n        \"extract_pattern\",\n        \"max_matches\",\n        \"head_characters\",\n        \"tail_characters\",\n        \"strip_mode\",\n        \"strip_characters\",\n        \"text_input_2\",\n        \"remove_extra_spaces\",\n        \"remove_special_chars\",\n        \"remove_empty_lines\",\n    ]\n\n    # Defaults applied to the JSON operation fields when the operation changes,\n    # mirroring the JSON Operations component's reset behavior.\n    OPERATION_FIELD_DEFAULTS: dict[str, Any] = {\n        \"select_keys_input\": [],\n        \"append_update_data\": {\"key\": \"value\"},\n        \"remove_keys_input\": [],\n        \"rename_keys_input\": {\"old_key\": \"new_key\"},\n        \"mapped_json_display\": \"\",\n        \"selected_key\": None,\n        \"query\": \"\",\n    }\n\n    inputs = [\n        # --- Input type selector: drives operations, input, and output ---\n        TabInput(\n            name=\"input_type\",\n            display_name=\"Input Type\",\n            options=INPUT_TYPES,\n            value=\"Text\",\n            info=\"Select the type of input to operate on.\",\n            real_time_refresh=True,\n        ),\n        # --- Main inputs: one per data type, shown contextually ---\n        MultilineInput(\n            name=\"text_input\",\n            display_name=\"Text\",\n            info=\"The input text to process.\",\n            show=True,\n        ),\n        DataInput(\n            name=\"data\",\n            display_name=\"JSON\",\n            info=\"The JSON / Data object to operate on.\",\n            is_list=True,\n            show=False,\n        ),\n        DataFrameInput(\n            name=\"df\",\n            display_name=\"Table\",\n            info=\"The input Table to operate on. Connect multiple Tables for merge or concatenate operations.\",\n            is_list=True,\n            show=False,\n        ),\n        # --- Operation picker (options are filtered by Input Type) ---\n        SortableListInput(\n            name=\"operation\",\n            display_name=\"Operation\",\n            placeholder=\"Select Operation\",\n            info=\"Select the operation to perform. The matching fields and output appear once you choose one.\",\n            options=OPERATIONS_BY_TYPE[\"Text\"],\n            real_time_refresh=True,\n            limit=1,\n        ),\n        # --- JSON operation fields ---\n        MessageTextInput(\n            name=\"select_keys_input\",\n            display_name=\"Select Keys\",\n            info=\"List of keys to select from the data. Only top-level keys can be selected.\",\n            show=False,\n            is_list=True,\n            value=[],\n        ),\n        DictInput(\n            name=\"append_update_data\",\n            display_name=\"Append or Update\",\n            info=\"Data to append or update the existing data with. Only top-level keys are checked.\",\n            show=False,\n            value={\"key\": \"value\"},\n            is_list=True,\n        ),\n        MessageTextInput(\n            name=\"remove_keys_input\",\n            display_name=\"Remove Keys\",\n            info=\"List of keys to remove from the data.\",\n            show=False,\n            is_list=True,\n            value=[],\n        ),\n        DictInput(\n            name=\"rename_keys_input\",\n            display_name=\"Rename Keys\",\n            info=\"List of keys to rename in the data.\",\n            show=False,\n            is_list=True,\n            value={\"old_key\": \"new_key\"},\n        ),\n        MultilineInput(\n            name=\"mapped_json_display\",\n            display_name=\"JSON to Map\",\n            info=\"Paste or preview your JSON here to explore its structure and select a path for extraction.\",\n            required=False,\n            refresh_button=True,\n            real_time_refresh=True,\n            placeholder=\"Add a JSON example.\",\n            show=False,\n        ),\n        DropdownInput(\n            name=\"selected_key\",\n            display_name=\"Select Path\",\n            options=[],\n            required=False,\n            dynamic=True,\n            show=False,\n            value=None,\n        ),\n        MessageTextInput(\n            name=\"query\",\n            display_name=\"JQ Expression\",\n            info=\"JSON Query to filter the data. Used by Path Selection and JQ Expression operations.\",\n            placeholder=\"e.g., .properties.id\",\n            show=False,\n        ),\n        # --- Table operation fields ---\n        StrInput(\n            name=\"column_name\",\n            display_name=\"Column Name\",\n            info=\"The column name to use for the operation.\",\n            dynamic=True,\n            show=False,\n        ),\n        MessageTextInput(\n            name=\"filter_value\",\n            display_name=\"Filter Value\",\n            info=\"The value to filter rows by.\",\n            dynamic=True,\n            show=False,\n        ),\n        DropdownInput(\n            name=\"filter_operator\",\n            display_name=\"Filter Operator\",\n            options=[\n                \"equals\",\n                \"not equals\",\n                \"contains\",\n                \"not contains\",\n                \"starts with\",\n                \"ends with\",\n                \"greater than\",\n                \"less than\",\n            ],\n            value=\"equals\",\n            info=\"The operator to apply for filtering rows.\",\n            advanced=False,\n            dynamic=True,\n            show=False,\n        ),\n        BoolInput(\n            name=\"ascending\",\n            display_name=\"Sort Ascending\",\n            info=\"Whether to sort in ascending order.\",\n            dynamic=True,\n            show=False,\n            value=True,\n        ),\n        StrInput(\n            name=\"new_column_name\",\n            display_name=\"New Column Name\",\n            info=\"The new column name when renaming or adding a column.\",\n            dynamic=True,\n            show=False,\n        ),\n        MessageTextInput(\n            name=\"new_column_value\",\n            display_name=\"New Column Value\",\n            info=\"The value to populate the new column with.\",\n            dynamic=True,\n            show=False,\n        ),\n        StrInput(\n            name=\"columns_to_select\",\n            display_name=\"Columns to Select\",\n            dynamic=True,\n            is_list=True,\n            show=False,\n        ),\n        IntInput(\n            name=\"num_rows\",\n            display_name=\"Number of Rows\",\n            info=\"Number of rows to return (for head/tail).\",\n            dynamic=True,\n            show=False,\n            value=5,\n        ),\n        MessageTextInput(\n            name=\"replace_value\",\n            display_name=\"Value to Replace\",\n            info=\"The value to replace in the column.\",\n            dynamic=True,\n            show=False,\n        ),\n        MessageTextInput(\n            name=\"replacement_value\",\n            display_name=\"Replacement Value\",\n            info=\"The value to replace with.\",\n            dynamic=True,\n            show=False,\n        ),\n        DataFrameInput(\n            name=\"left_dataframe\",\n            display_name=\"Left Table\",\n            info=\"The left (primary) Table for merge operations. \"\n            \"In a left merge, all rows from this table are preserved.\",\n            dynamic=True,\n            show=False,\n        ),\n        DataFrameInput(\n            name=\"right_dataframe\",\n            display_name=\"Right Table\",\n            info=\"The right (secondary) Table for merge operations. \"\n            \"In a right merge, all rows from this table are preserved.\",\n            dynamic=True,\n            show=False,\n        ),\n        StrInput(\n            name=\"merge_on_column\",\n            display_name=\"Merge On Column\",\n            info=\"The column name to merge Tables on. Must exist in both Tables.\",\n            dynamic=True,\n            show=False,\n        ),\n        DropdownInput(\n            name=\"merge_how\",\n            display_name=\"Merge Type\",\n            options=[\"inner\", \"outer\", \"left\", \"right\"],\n            value=\"inner\",\n            info=\"Type of merge: inner (intersection), outer (union), left, or right.\",\n            dynamic=True,\n            show=False,\n        ),\n        # --- Text operation fields ---\n        StrInput(\n            name=\"table_separator\",\n            display_name=\"Table Separator\",\n            info=\"Separator used in the table (default: '|').\",\n            value=\"|\",\n            dynamic=True,\n            show=False,\n        ),\n        BoolInput(\n            name=\"has_header\",\n            display_name=\"Has Header\",\n            info=\"Whether the table has a header row.\",\n            value=True,\n            dynamic=True,\n            advanced=True,\n            show=False,\n        ),\n        BoolInput(\n            name=\"count_words\",\n            display_name=\"Count Words\",\n            info=\"Include word count in analysis.\",\n            value=True,\n            dynamic=True,\n            advanced=True,\n            show=False,\n        ),\n        BoolInput(\n            name=\"count_characters\",\n            display_name=\"Count Characters\",\n            info=\"Include character count in analysis.\",\n            value=True,\n            dynamic=True,\n            advanced=True,\n            show=False,\n        ),\n        BoolInput(\n            name=\"count_lines\",\n            display_name=\"Count Lines\",\n            info=\"Include line count in analysis.\",\n            value=True,\n            dynamic=True,\n            advanced=True,\n            show=False,\n        ),\n        DropdownInput(\n            name=\"case_type\",\n            display_name=\"Case Type\",\n            options=[\"uppercase\", \"lowercase\", \"title\", \"capitalize\", \"swapcase\"],\n            value=\"lowercase\",\n            info=\"Type of case conversion to apply.\",\n            dynamic=True,\n            show=False,\n        ),\n        BoolInput(\n            name=\"use_regex\",\n            display_name=\"Use Regex\",\n            info=\"Whether to treat search pattern as regex.\",\n            value=False,\n            dynamic=True,\n            show=False,\n        ),\n        StrInput(\n            name=\"search_pattern\",\n            display_name=\"Search Pattern\",\n            info=\"Text pattern to search for (supports regex).\",\n            dynamic=True,\n            show=False,\n        ),\n        StrInput(\n            name=\"replacement_text\",\n            display_name=\"Replacement Text\",\n            info=\"Text to replace the search pattern with.\",\n            dynamic=True,\n            show=False,\n        ),\n        StrInput(\n            name=\"extract_pattern\",\n            display_name=\"Extract Pattern\",\n            info=\"Regex pattern to extract from text.\",\n            dynamic=True,\n            show=False,\n        ),\n        IntInput(\n            name=\"max_matches\",\n            display_name=\"Max Matches\",\n            info=\"Maximum number of matches to extract.\",\n            value=10,\n            dynamic=True,\n            show=False,\n        ),\n        IntInput(\n            name=\"head_characters\",\n            display_name=\"Characters from Start\",\n            info=\"Number of characters to extract from the beginning of text. Must be non-negative.\",\n            value=100,\n            dynamic=True,\n            show=False,\n            range_spec=RangeSpec(min=0, max=1000000, step=1, step_type=\"int\"),\n        ),\n        IntInput(\n            name=\"tail_characters\",\n            display_name=\"Characters from End\",\n            info=\"Number of characters to extract from the end of text. Must be non-negative.\",\n            value=100,\n            dynamic=True,\n            show=False,\n            range_spec=RangeSpec(min=0, max=1000000, step=1, step_type=\"int\"),\n        ),\n        DropdownInput(\n            name=\"strip_mode\",\n            display_name=\"Strip Mode\",\n            options=[\"both\", \"left\", \"right\"],\n            value=\"both\",\n            info=\"Which sides to strip whitespace from.\",\n            dynamic=True,\n            show=False,\n        ),\n        StrInput(\n            name=\"strip_characters\",\n            display_name=\"Characters to Strip\",\n            info=\"Specific characters to remove (leave empty for whitespace).\",\n            value=\"\",\n            dynamic=True,\n            show=False,\n        ),\n        MultilineInput(\n            name=\"text_input_2\",\n            display_name=\"Second Text Input\",\n            info=\"Second text to join with the first text.\",\n            dynamic=True,\n            show=False,\n        ),\n        BoolInput(\n            name=\"remove_extra_spaces\",\n            display_name=\"Remove Extra Spaces\",\n            info=\"Remove multiple consecutive spaces.\",\n            value=True,\n            dynamic=True,\n            show=False,\n        ),\n        BoolInput(\n            name=\"remove_special_chars\",\n            display_name=\"Remove Special Characters\",\n            info=\"Remove special characters except alphanumeric and spaces.\",\n            value=False,\n            dynamic=True,\n            show=False,\n        ),\n        BoolInput(\n            name=\"remove_empty_lines\",\n            display_name=\"Remove Empty Lines\",\n            info=\"Remove empty lines from text.\",\n            value=False,\n            dynamic=True,\n            show=False,\n        ),\n    ]\n\n    # Default output matches the default Input Type (\"Text\" -> Message).\n    # update_outputs / update_frontend_node narrow it to the selected type and\n    # operation.\n    outputs = [Output(display_name=\"Message\", name=\"message_output\", method=\"as_message\")]\n\n    # ------------------------------------------------------------------\n    # Operation routing helpers\n    # ------------------------------------------------------------------\n    @staticmethod\n    def _extract_operation_name(field_value: Any) -> str:\n        \"\"\"Extract the operation name from a SortableListInput value.\"\"\"\n        if isinstance(field_value, list) and len(field_value) > 0 and isinstance(field_value[0], dict):\n            return field_value[0].get(\"name\", \"\")\n        if isinstance(field_value, str):\n            return field_value\n        return \"\"\n\n    def _operation_name(self) -> str:\n        \"\"\"Get the currently selected operation name.\"\"\"\n        return self._extract_operation_name(getattr(self, \"operation\", []))\n\n    @staticmethod\n    def _default_output_for_type(input_type: str) -> Output:\n        \"\"\"Return the output advertised for an input type when no operation is selected yet.\"\"\"\n        if input_type == \"JSON\":\n            return Output(display_name=\"JSON\", name=\"data_output\", method=\"as_data\")\n        if input_type == \"Table\":\n            return Output(display_name=\"Table\", name=\"dataframe_output\", method=\"as_dataframe\")\n        return Output(display_name=\"Message\", name=\"message_output\", method=\"as_message\")\n\n    # ------------------------------------------------------------------\n    # Dynamic UI\n    # ------------------------------------------------------------------\n    def _reset_operation_fields(self, build_config: dotdict) -> None:\n        \"\"\"Hide every operation-specific field and restore its default value.\"\"\"\n        for field in self.ALL_OPERATION_FIELDS:\n            if field in build_config:\n                build_config[field][\"show\"] = False\n                if field in self.OPERATION_FIELD_DEFAULTS:\n                    build_config[field][\"value\"] = self.OPERATION_FIELD_DEFAULTS[field]\n\n    def _show_main_input(self, build_config: dotdict, input_type: str, operation: str) -> None:\n        \"\"\"Show only the main input that matches the input type; hide the others.\"\"\"\n        for inp in self.MAIN_INPUTS:\n            if inp in build_config:\n                build_config[inp][\"show\"] = False\n                build_config[inp][\"required\"] = False\n\n        main_input = INPUT_TYPE_TO_MAIN_INPUT.get(input_type)\n        if main_input and main_input in build_config:\n            build_config[main_input][\"show\"] = True\n            build_config[main_input][\"required\"] = True\n            # The JSON \"Combine\" operation consumes a list of Data objects.\n            if main_input == \"data\":\n                build_config[\"data\"][\"is_list\"] = operation == \"Combine\"\n\n    def update_build_config(self, build_config: dotdict, field_value: Any, field_name: str | None = None) -> dotdict:\n        # Path Selection: refresh the available JSON paths from the pasted JSON.\n        if field_name == \"mapped_json_display\":\n            try:\n                parsed_json = json.loads(field_value)\n                keys = self.extract_all_paths(parsed_json)\n                build_config[\"selected_key\"][\"options\"] = keys\n                build_config[\"selected_key\"][\"show\"] = True\n            except (json.JSONDecodeError, TypeError, ValueError) as e:\n                logger.error(f\"Error parsing mapped JSON: {e}\")\n                build_config[\"selected_key\"][\"show\"] = False\n            return build_config\n\n        # Input type changed: swap the operation list, clear the selection, and\n        # show only the matching input. No operation-specific fields are shown\n        # until an operation is picked.\n        if field_name == \"input_type\":\n            input_type = field_value if field_value in OPERATIONS_BY_TYPE else \"Text\"\n            build_config[\"operation\"][\"options\"] = OPERATIONS_BY_TYPE[input_type]\n            build_config[\"operation\"][\"value\"] = []\n            self._reset_operation_fields(build_config)\n            self._show_main_input(build_config, input_type, operation=\"\")\n            return build_config\n\n        # Operation changed: reset fields, show the input for the current type,\n        # then reveal the operation-specific fields.\n        if field_name == \"operation\":\n            operation = self._extract_operation_name(field_value)\n            self._reset_operation_fields(build_config)\n\n            input_type = build_config.get(\"input_type\", {}).get(\"value\", \"Text\")\n            self._show_main_input(build_config, input_type, operation)\n\n            for field in self.OPERATION_FIELDS.get(operation, []):\n                if field in build_config:\n                    build_config[field][\"show\"] = True\n\n            return build_config\n\n        return build_config\n\n    def update_outputs(self, frontend_node: dict, field_name: str, field_value: Any) -> dict:\n        \"\"\"Create the output(s) appropriate to the selected input type and operation.\"\"\"\n        if field_name == \"input_type\":\n            # Switching type clears the operation; advertise the type's default.\n            input_type = field_value if field_value in OPERATIONS_BY_TYPE else \"Text\"\n            frontend_node[\"outputs\"] = [self._default_output_for_type(input_type)]\n            return frontend_node\n\n        template = frontend_node.get(\"template\", {})\n        input_type = template.get(\"input_type\", {}).get(\"value\", \"Text\")\n\n        if field_name == \"operation\":\n            operation = self._extract_operation_name(field_value)\n        else:\n            # Any other refresh (e.g. Path Selection's \"JSON to Map\" field)\n            # reaches here on a freshly rebuilt node whose outputs were reset\n            # to the class default (Message). Re-derive the output from the\n            # saved operation so the refresh doesn't swap the real output type.\n            operation = self._extract_operation_name(template.get(\"operation\", {}).get(\"value\", []))\n\n        if not operation:\n            # No operation selected: fall back to the input type's default output.\n            frontend_node[\"outputs\"] = [self._default_output_for_type(input_type)]\n            return frontend_node\n\n        frontend_node[\"outputs\"] = []\n        if operation in JSON_OPERATIONS or operation == \"Word Count\":\n            frontend_node[\"outputs\"].append(Output(display_name=\"JSON\", name=\"data_output\", method=\"as_data\"))\n        elif operation in TABLE_OPERATIONS or operation == \"Text to DataFrame\":\n            frontend_node[\"outputs\"].append(\n                Output(display_name=\"Table\", name=\"dataframe_output\", method=\"as_dataframe\")\n            )\n        elif operation == \"Text Join\":\n            frontend_node[\"outputs\"].append(Output(display_name=\"Text\", name=\"text_output\", method=\"as_text\"))\n            frontend_node[\"outputs\"].append(Output(display_name=\"Message\", name=\"message_output\", method=\"as_message\"))\n        else:\n            frontend_node[\"outputs\"].append(Output(display_name=\"Message\", name=\"message_output\", method=\"as_message\"))\n\n        return frontend_node\n\n    async def update_frontend_node(self, new_frontend_node: dict, current_frontend_node: dict) -> dict:\n        \"\"\"Keep the operation options and outputs in sync with the saved input type on load.\"\"\"\n        await super().update_frontend_node(new_frontend_node, current_frontend_node)\n\n        template = new_frontend_node.get(\"template\", {})\n        input_type = template.get(\"input_type\", {}).get(\"value\", \"Text\")\n        if input_type not in OPERATIONS_BY_TYPE:\n            input_type = \"Text\"\n\n        # Filter the operation picker to the saved input type.\n        if \"operation\" in template:\n            template[\"operation\"][\"options\"] = OPERATIONS_BY_TYPE[input_type]\n\n        # Re-derive the outputs from the saved input type + operation.\n        operation_value = template.get(\"operation\", {}).get(\"value\", [])\n        if self._extract_operation_name(operation_value):\n            self.update_outputs(new_frontend_node, \"operation\", operation_value)\n        else:\n            self.update_outputs(new_frontend_node, \"input_type\", input_type)\n\n        return new_frontend_node\n\n    # ==================================================================\n    # Output methods (referenced by update_outputs)\n    # ==================================================================\n    def as_data(self) -> Data:\n        \"\"\"JSON-typed output: JSON operations and Word Count.\"\"\"\n        operation = self._operation_name()\n        if operation in JSON_OPERATIONS:\n            handler = self._json_handlers().get(operation)\n            if handler:\n                try:\n                    return handler()\n                except Exception as e:\n                    logger.error(f\"Error executing {operation}: {e!s}\")\n                    raise\n        if operation == \"Word Count\":\n            return self._word_count_data()\n        return Data(data={})\n\n    def as_dataframe(self) -> DataFrame:\n        \"\"\"Table-typed output: Table operations and Text to DataFrame.\"\"\"\n        operation = self._operation_name()\n        if operation in TABLE_OPERATIONS:\n            return self._run_table_operation(operation)\n        if operation == \"Text to DataFrame\":\n            return self._text_to_dataframe(getattr(self, \"text_input\", \"\") or \"\")\n        return DataFrame(pd.DataFrame())\n\n    def as_message(self) -> Message:\n        \"\"\"Message-typed output: generic text operations (and Text Join).\"\"\"\n        return Message(text=self._format_result_as_text(self._run_text_operation()))\n\n    def as_text(self) -> Message:\n        \"\"\"Text output for the Text Join operation.\"\"\"\n        return self.as_message()\n\n    # ==================================================================\n    # JSON operations\n    # ==================================================================\n    @staticmethod\n    def extract_all_paths(obj, path=\"\"):\n        paths = []\n        if isinstance(obj, dict):\n            for k, v in obj.items():\n                new_path = f\"{path}.{k}\" if path else f\".{k}\"\n                paths.append(new_path)\n                paths.extend(OperationsComponent.extract_all_paths(v, new_path))\n        elif isinstance(obj, list) and obj:\n            new_path = f\"{path}[0]\"\n            paths.append(new_path)\n            paths.extend(OperationsComponent.extract_all_paths(obj[0], new_path))\n        return paths\n\n    @staticmethod\n    def remove_keys_recursive(obj, keys_to_remove):\n        if isinstance(obj, dict):\n            return {\n                k: OperationsComponent.remove_keys_recursive(v, keys_to_remove)\n                for k, v in obj.items()\n                if k not in keys_to_remove\n            }\n        if isinstance(obj, list):\n            return [OperationsComponent.remove_keys_recursive(item, keys_to_remove) for item in obj]\n        return obj\n\n    @staticmethod\n    def rename_keys_recursive(obj, rename_map):\n        if isinstance(obj, dict):\n            return {\n                rename_map.get(k, k): OperationsComponent.rename_keys_recursive(v, rename_map) for k, v in obj.items()\n            }\n        if isinstance(obj, list):\n            return [OperationsComponent.rename_keys_recursive(item, rename_map) for item in obj]\n        return obj\n\n    def _json_handlers(self) -> \"dict[str, Callable[[], Data]]\":\n        return {\n            \"Select Keys\": self.select_keys,\n            \"Literal Eval\": self.evaluate_data,\n            \"Combine\": self.combine_data,\n            \"Append or Update\": self.append_update,\n            \"Remove Keys\": self.remove_keys,\n            \"Rename Keys\": self.rename_keys,\n            \"Path Selection\": self.json_path,\n            \"JQ Expression\": self.json_query,\n        }\n\n    def get_data_dict(self) -> dict:\n        \"\"\"Extract data dictionary from Data object.\"\"\"\n        data = self.data[0] if isinstance(self.data, list) and len(self.data) == 1 else self.data\n        return data.model_dump()\n\n    def get_normalized_data(self) -> dict:\n        \"\"\"Get normalized data dictionary, handling the 'data' key if present.\"\"\"\n        data_dict = self.get_data_dict()\n        return data_dict.get(\"data\", data_dict)\n\n    def data_is_list(self) -> bool:\n        \"\"\"Check if data contains multiple items.\"\"\"\n        return isinstance(self.data, list) and len(self.data) > 1\n\n    def validate_single_data(self, operation: str) -> None:\n        \"\"\"Validate that the operation is being performed on a single data object.\"\"\"\n        if self.data_is_list():\n            msg = f\"{operation} operation is not supported for multiple data objects.\"\n            raise ValueError(msg)\n\n    def select_keys(self) -> Data:\n        \"\"\"Select specific keys from the data dictionary.\"\"\"\n        self.validate_single_data(\"Select Keys\")\n        data_dict = self.get_normalized_data()\n        filter_criteria: list[str] = self.select_keys_input\n\n        if len(filter_criteria) == 1 and filter_criteria[0] == \"data\":\n            filtered = data_dict[\"data\"]\n        else:\n            if not all(key in data_dict for key in filter_criteria):\n                msg = f\"Select key not found in data. Available keys: {list(data_dict.keys())}\"\n                raise ValueError(msg)\n            filtered = {key: value for key, value in data_dict.items() if key in filter_criteria}\n\n        return Data(data=filtered)\n\n    def remove_keys(self) -> Data:\n        \"\"\"Remove specified keys from the data dictionary, recursively.\"\"\"\n        self.validate_single_data(\"Remove Keys\")\n        data_dict = self.get_normalized_data()\n        remove_keys_input: list[str] = self.remove_keys_input\n        filtered = OperationsComponent.remove_keys_recursive(data_dict, set(remove_keys_input))\n        return Data(data=filtered)\n\n    def rename_keys(self) -> Data:\n        \"\"\"Rename keys in the data dictionary, recursively.\"\"\"\n        self.validate_single_data(\"Rename Keys\")\n        data_dict = self.get_normalized_data()\n        rename_keys_input: dict[str, str] = self.rename_keys_input\n        renamed = OperationsComponent.rename_keys_recursive(data_dict, rename_keys_input)\n        return Data(data=renamed)\n\n    def recursive_eval(self, data: Any) -> Any:\n        \"\"\"Recursively evaluate string values that look like Python literals.\"\"\"\n        if isinstance(data, dict):\n            return {k: self.recursive_eval(v) for k, v in data.items()}\n        if isinstance(data, list):\n            return [self.recursive_eval(item) for item in data]\n        if isinstance(data, str):\n            try:\n                if (\n                    data.strip().startswith((\"{\", \"[\", \"(\", \"'\", '\"'))\n                    or data.strip().lower() in (\"true\", \"false\", \"none\")\n                    or data.strip().replace(\".\", \"\").isdigit()\n                ):\n                    return ast.literal_eval(data)\n            except (ValueError, SyntaxError, TypeError, MemoryError):\n                return data\n            else:\n                return data\n        return data\n\n    def evaluate_data(self) -> Data:\n        \"\"\"Evaluate string values in the data dictionary.\"\"\"\n        self.validate_single_data(\"Literal Eval\")\n        logger.info(\"evaluating data\")\n        return Data(**self.recursive_eval(self.get_data_dict()))\n\n    def combine_data(self) -> Data:\n        \"\"\"Combine multiple data objects into one.\"\"\"\n        logger.info(\"combining data\")\n        if not self.data_is_list():\n            return self.data[0] if self.data else Data(data={})\n\n        data_dicts = [data.model_dump().get(\"data\", data.model_dump()) for data in self.data]\n        combined_data: dict[str, Any] = {}\n\n        for data_dict in data_dicts:\n            for key, value in data_dict.items():\n                if key not in combined_data:\n                    combined_data[key] = value\n                elif isinstance(combined_data[key], list):\n                    if isinstance(value, list):\n                        combined_data[key].extend(value)\n                    else:\n                        combined_data[key].append(value)\n                else:\n                    combined_data[key] = (\n                        [combined_data[key], value] if not isinstance(value, list) else [combined_data[key], *value]\n                    )\n\n        return Data(**combined_data)\n\n    def append_update(self) -> Data:\n        \"\"\"Append or update the data with new key-value pairs.\"\"\"\n        self.validate_single_data(\"Append or Update\")\n        data_filtered = self.get_normalized_data()\n        for key, value in self.append_update_data.items():\n            data_filtered[key] = value\n        return Data(**data_filtered)\n\n    def json_path(self) -> Data:\n        \"\"\"Extract a value from the data using the selected JQ path.\"\"\"\n        try:\n            import jq\n        except ImportError:\n            msg = \"jq is required for Path Selection. Install with: pip install jq\"\n            raise ImportError(msg) from None\n\n        try:\n            if not self.data or not self.selected_key:\n                msg = \"Missing input data or selected key.\"\n                raise ValueError(msg)\n            input_payload = self.data[0].data if isinstance(self.data, list) else self.data.data\n            validate_jq_program(self.selected_key)\n            compiled = jq.compile(self.selected_key)\n            result = compiled.input(input_payload).first()\n            if isinstance(result, dict):\n                return Data(data=result)\n            return Data(data={\"result\": result})\n        except (ValueError, TypeError, KeyError) as e:\n            self.status = f\"Error: {e!s}\"\n            self.log(self.status)\n            return Data(data={\"error\": str(e)})\n\n    def json_query(self) -> Data:\n        \"\"\"Run a JQ expression against the data.\"\"\"\n        try:\n            import jq\n        except ImportError:\n            msg = \"jq is required for JQ Expression. Install with: pip install jq\"\n            raise ImportError(msg) from None\n\n        if not self.query or not self.query.strip():\n            msg = \"JSON Query is required and cannot be blank.\"\n            raise ValueError(msg)\n        raw_data = self.get_data_dict()\n        try:\n            input_str = json.dumps(raw_data)\n            repaired = repair_json(input_str)\n            data_json = json.loads(repaired)\n            jq_input = data_json[\"data\"] if isinstance(data_json, dict) and \"data\" in data_json else data_json\n            validate_jq_program(self.query)\n            results = jq.compile(self.query).input(jq_input).all()\n            if not results:\n                msg = \"No result from JSON query.\"\n                raise ValueError(msg)\n            result = results[0] if len(results) == 1 else results\n            if result is None or result == \"None\":\n                msg = \"JSON query returned null/None. Check if the path exists in your data.\"\n                raise ValueError(msg)\n            if isinstance(result, dict):\n                return Data(data=result)\n            return Data(data={\"result\": result})\n        except (ValueError, TypeError, KeyError, json.JSONDecodeError) as e:\n            logger.error(f\"JSON Query failed: {e}\")\n            msg = f\"JSON Query error: {e}\"\n            raise ValueError(msg) from e\n\n    # ==================================================================\n    # Table operations\n    # ==================================================================\n    def _get_primary_dataframe(self) -> DataFrame:\n        \"\"\"Get the first DataFrame from input (handles both single and list inputs).\"\"\"\n        if isinstance(self.df, list):\n            return self.df[0].copy() if self.df else DataFrame()\n        return self.df.copy()\n\n    def _run_table_operation(self, operation: str) -> DataFrame:\n        # Merge and Concatenate use their own inputs, not the primary df.\n        if operation == \"Merge\":\n            return self.merge_dataframes()\n        if operation == \"Concatenate\":\n            return self.concatenate_dataframes()\n\n        df_copy = self._get_primary_dataframe()\n        table_handlers = {\n            \"Filter\": self.filter_rows_by_value,\n            \"Sort\": self.sort_by_column,\n            \"Drop Column\": self.drop_column,\n            \"Rename Column\": self.rename_column,\n            \"Add Column\": self.add_column,\n            \"Select Columns\": self.select_columns,\n            \"Head\": self.head,\n            \"Tail\": self.tail,\n            \"Replace Value\": self.replace_values,\n            \"Drop Duplicates\": self.drop_duplicates,\n        }\n        handler = table_handlers.get(operation)\n        if handler is None:\n            msg = f\"Unsupported operation: {operation}\"\n            logger.error(msg)\n            raise ValueError(msg)\n        return handler(df_copy)\n\n    @staticmethod\n    def _comparable_filter_value(column: pd.Series, filter_value: Any) -> Any:\n        \"\"\"Return a text input as a number when the column is numeric.\n\n        Filter and Replace Value inputs arrive as text, and ``30 == \"30\"`` never matches in pandas.\n        A blank input stays text: ``pd.to_numeric(\"\")`` is NaN, which would match missing cells.\n        \"\"\"\n        if filter_value in (None, \"\"):\n            return filter_value\n        if pd.api.types.is_numeric_dtype(column) and not pd.api.types.is_bool_dtype(column):\n            try:\n                return pd.to_numeric(filter_value)\n            except (ValueError, TypeError):\n                return filter_value\n        return filter_value\n\n    def filter_rows_by_value(self, df: DataFrame) -> DataFrame:\n        column = df[self.column_name]\n        filter_value = self.filter_value\n        operator = getattr(self, \"filter_operator\", \"equals\")\n\n        if operator == \"equals\":\n            mask = column == self._comparable_filter_value(column, filter_value)\n        elif operator == \"not equals\":\n            mask = column != self._comparable_filter_value(column, filter_value)\n        elif operator == \"contains\":\n            mask = column.astype(str).str.contains(str(filter_value), na=False)\n        elif operator == \"not contains\":\n            mask = ~column.astype(str).str.contains(str(filter_value), na=False)\n        elif operator == \"starts with\":\n            mask = column.astype(str).str.startswith(str(filter_value), na=False)\n        elif operator == \"ends with\":\n            mask = column.astype(str).str.endswith(str(filter_value), na=False)\n        elif operator == \"greater than\":\n            try:\n                numeric_value = pd.to_numeric(filter_value)\n                mask = column > numeric_value\n            except (ValueError, TypeError):\n                mask = column.astype(str) > str(filter_value)\n        elif operator == \"less than\":\n            try:\n                numeric_value = pd.to_numeric(filter_value)\n                mask = column < numeric_value\n            except (ValueError, TypeError):\n                mask = column.astype(str) < str(filter_value)\n        else:\n            mask = column == self._comparable_filter_value(column, filter_value)\n\n        return DataFrame(df[mask])\n\n    def sort_by_column(self, df: DataFrame) -> DataFrame:\n        return DataFrame(df.sort_values(by=self.column_name, ascending=self.ascending))\n\n    def drop_column(self, df: DataFrame) -> DataFrame:\n        return DataFrame(df.drop(columns=[self.column_name]))\n\n    def rename_column(self, df: DataFrame) -> DataFrame:\n        return DataFrame(df.rename(columns={self.column_name: self.new_column_name}))\n\n    def add_column(self, df: DataFrame) -> DataFrame:\n        df[self.new_column_name] = [self.new_column_value] * len(df)\n        return DataFrame(df)\n\n    def select_columns(self, df: DataFrame) -> DataFrame:\n        columns = [col.strip() for col in self.columns_to_select]\n        return DataFrame(df[columns])\n\n    def head(self, df: DataFrame) -> DataFrame:\n        return DataFrame(df.head(self.num_rows))\n\n    def tail(self, df: DataFrame) -> DataFrame:\n        return DataFrame(df.tail(self.num_rows))\n\n    def replace_values(self, df: DataFrame) -> DataFrame:\n        column = df[self.column_name]\n        replace_val = self._comparable_filter_value(column, self.replace_value)\n        replacement_val = self._comparable_filter_value(column, self.replacement_value)\n        try:\n            result = column.replace(replace_val, replacement_val)\n        except TypeError:\n            if not (\n                isinstance(column.dtype, pd.api.extensions.ExtensionDtype)\n                and pd.api.types.is_integer_dtype(column.dtype)\n            ):\n                raise\n            # Nullable integers reject fractional/text replacements instead of widening like NumPy columns.\n            widened = column.astype(\"Float64\" if pd.api.types.is_float(replacement_val) else object)\n            # A float cannot represent every Int64 value. Preserve unrelated large integers exactly.\n            if not widened.astype(object).equals(column.astype(object)):\n                widened = column.astype(object)\n            result = widened.mask(column.eq(replace_val).fillna(value=False), replacement_val)\n        df[self.column_name] = result\n        return DataFrame(df)\n\n    def drop_duplicates(self, df: DataFrame) -> DataFrame:\n        return DataFrame(df.drop_duplicates(subset=self.column_name))\n\n    def concatenate_dataframes(self) -> DataFrame:\n        \"\"\"Concatenate multiple DataFrames vertically (stack rows).\"\"\"\n        if not isinstance(self.df, list) or len(self.df) == 0:\n            return self.df.copy() if self.df is not None else DataFrame()\n\n        if len(self.df) == 1:\n            return self.df[0].copy()\n\n        concatenated = pd.concat(self.df, ignore_index=True)\n        return DataFrame(concatenated)\n\n    def merge_dataframes(self) -> DataFrame:\n        \"\"\"Merge two DataFrames based on a common column (join operation).\"\"\"\n        left_df = getattr(self, \"left_dataframe\", None)\n        right_df = getattr(self, \"right_dataframe\", None)\n\n        if left_df is None:\n            return DataFrame()\n        if right_df is None:\n            return left_df.copy()\n\n        df_left = left_df.copy()\n        df_right = right_df.copy()\n\n        merge_on = getattr(self, \"merge_on_column\", None)\n        merge_how = getattr(self, \"merge_how\", \"inner\")\n\n        # Track only columns created by this merge, without colliding with input names.\n        right_columns = {}\n        used_columns = set(df_left.columns) | set(df_right.columns)\n        for col in df_left.columns.intersection(df_right.columns):\n            if merge_on and col == merge_on:\n                continue\n            right_col = f\"{col}_right\"\n            while right_col in used_columns:\n                right_col += \"_right\"\n            right_columns[col] = right_col\n            used_columns.add(right_col)\n        df_right = df_right.rename(columns=right_columns)\n\n        if merge_on:\n            if merge_on not in df_left.columns:\n                msg = f\"Column '{merge_on}' not found in left DataFrame. Available: {list(df_left.columns)}\"\n                raise ValueError(msg)\n            if merge_on not in df_right.columns:\n                msg = f\"Column '{merge_on}' not found in right DataFrame. Available: {list(df_right.columns)}\"\n                raise ValueError(msg)\n            merged = df_left.merge(df_right, on=merge_on, how=merge_how)\n        else:\n            merged = df_left.merge(df_right, left_index=True, right_index=True, how=merge_how)\n\n        cols_to_drop = []\n        for col, right_col in right_columns.items():\n            merged[col] = merged[col].combine_first(merged[right_col])\n            cols_to_drop.append(right_col)\n\n        if cols_to_drop:\n            merged = merged.drop(columns=cols_to_drop)\n\n        return DataFrame(merged)\n\n    # ==================================================================\n    # Text operations\n    # ==================================================================\n    def _run_text_operation(self) -> Any:\n        \"\"\"Process text based on the selected operation (Message/Text outputs).\"\"\"\n        text = getattr(self, \"text_input\", \"\")\n        operation = self._operation_name()\n\n        # Allow empty text for Text Join (second input may have content).\n        if not text and operation != \"Text Join\":\n            return None\n\n        text_handlers = {\n            \"Case Conversion\": self._case_conversion,\n            \"Text Replace\": self._text_replace,\n            \"Text Extract\": self._text_extract,\n            \"Text Head\": self._text_head,\n            \"Text Tail\": self._text_tail,\n            \"Text Strip\": self._text_strip,\n            \"Text Join\": self._text_join,\n            \"Text Clean\": self._text_clean,\n        }\n        handler = text_handlers.get(operation)\n        if handler:\n            return handler(text)\n        return text\n\n    def _word_count_data(self) -> Data:\n        \"\"\"Word Count operation result as a Data object.\"\"\"\n        result = self._word_count(getattr(self, \"text_input\", \"\") or \"\")\n        return Data(data=result)\n\n    def _word_count(self, text: str) -> dict[str, Any]:\n        \"\"\"Count words, characters, and lines in text.\"\"\"\n        result: dict[str, Any] = {}\n        text_str = str(text) if text else \"\"\n        is_empty = not text_str or not text_str.strip()\n\n        if getattr(self, \"count_words\", True):\n            if is_empty:\n                result[\"word_count\"] = 0\n                result[\"unique_words\"] = 0\n            else:\n                words = text_str.split()\n                result[\"word_count\"] = len(words)\n                result[\"unique_words\"] = len(set(words))\n\n        if getattr(self, \"count_characters\", True):\n            if is_empty:\n                result[\"character_count\"] = 0\n                result[\"character_count_no_spaces\"] = 0\n            else:\n                result[\"character_count\"] = len(text_str)\n                result[\"character_count_no_spaces\"] = len(text_str.replace(\" \", \"\"))\n\n        if getattr(self, \"count_lines\", True):\n            if is_empty:\n                result[\"line_count\"] = 0\n                result[\"non_empty_lines\"] = 0\n            else:\n                lines = text_str.split(\"\\n\")\n                result[\"line_count\"] = len(lines)\n                result[\"non_empty_lines\"] = len([line for line in lines if line.strip()])\n\n        return result\n\n    def _text_to_dataframe(self, text: str) -> DataFrame:\n        \"\"\"Convert markdown-style table text to a DataFrame.\"\"\"\n        lines = [line.strip() for line in text.strip().split(\"\\n\") if line.strip()]\n        if not lines:\n            return DataFrame(pd.DataFrame())\n\n        separator = getattr(self, \"table_separator\", \"|\")\n        has_header = getattr(self, \"has_header\", True)\n\n        rows = self._parse_table_rows(lines, separator, has_header=has_header)\n        if not rows:\n            return DataFrame(pd.DataFrame())\n\n        df = self._create_dataframe(rows, has_header=has_header)\n        self._convert_numeric_columns(df)\n        self.log(f\"Converted text to DataFrame: {len(df)} rows, {len(df.columns)} columns\")\n        return DataFrame(df)\n\n    def _parse_table_rows(self, lines: list[str], separator: str, *, has_header: bool = True) -> list[list[str]]:\n        rows = []\n        for index, line in enumerate(lines):\n            cleaned_line = line.strip(separator)\n            cells = [cell.strip() for cell in cleaned_line.split(separator)]\n            # Skip the markdown delimiter row under the header instead of reading it as data.\n            if has_header and index == 1 and all(MARKDOWN_DELIMITER_CELL.fullmatch(cell) for cell in cells):\n                continue\n            rows.append(cells)\n        return rows\n\n    def _create_dataframe(self, rows: list[list[str]], *, has_header: bool) -> pd.DataFrame:\n        if has_header and rows:\n            header = rows[0]\n            data_rows = rows[1:]\n            header_col_count = len(header)\n            for i, row in enumerate(data_rows):\n                row_col_count = len(row)\n                if row_col_count != header_col_count:\n                    msg = (\n                        f\"Header mismatch: {header_col_count} column(s) in header vs \"\n                        f\"{row_col_count} column(s) in data row {i + 1}. \"\n                        \"Please ensure the header has the same number of columns as your data.\"\n                    )\n                    raise ValueError(msg)\n            return pd.DataFrame(data_rows, columns=header)\n\n        max_cols = max(len(row) for row in rows) if rows else 0\n        columns = [f\"col_{i}\" for i in range(max_cols)]\n        return pd.DataFrame(rows, columns=columns)\n\n    def _convert_numeric_columns(self, df: pd.DataFrame) -> None:\n        for col in df.columns:\n            with contextlib.suppress(ValueError, TypeError):\n                df[col] = pd.to_numeric(df[col])\n\n    def _case_conversion(self, text: str) -> str:\n        case_type = getattr(self, \"case_type\", \"lowercase\")\n        converter = CASE_CONVERTERS.get(case_type)\n        return converter(text) if converter else text\n\n    def _text_replace(self, text: str) -> str:\n        search_pattern = getattr(self, \"search_pattern\", \"\")\n        if not search_pattern:\n            return text\n        replacement_text = getattr(self, \"replacement_text\", \"\")\n        use_regex = getattr(self, \"use_regex\", False)\n        if use_regex:\n            try:\n                return re.sub(search_pattern, replacement_text, text)\n            except re.error as e:\n                self.log(f\"Invalid regex pattern: {e}\")\n                return text\n        return text.replace(search_pattern, replacement_text)\n\n    def _text_extract(self, text: str) -> list[str]:\n        extract_pattern = getattr(self, \"extract_pattern\", \"\")\n        if not extract_pattern:\n            return []\n        max_matches = getattr(self, \"max_matches\", 10)\n        try:\n            matches = re.findall(extract_pattern, text)\n        except re.error as e:\n            msg = f\"Invalid regex pattern '{extract_pattern}': {e}\"\n            raise ValueError(msg) from e\n        return matches[:max_matches] if max_matches > 0 else matches\n\n    def _text_head(self, text: str) -> str:\n        head_characters = getattr(self, \"head_characters\", 100)\n        if head_characters < 0:\n            msg = f\"Characters from Start must be a non-negative integer, got {head_characters}\"\n            raise ValueError(msg)\n        if head_characters == 0:\n            return \"\"\n        return text[:head_characters]\n\n    def _text_tail(self, text: str) -> str:\n        tail_characters = getattr(self, \"tail_characters\", 100)\n        if tail_characters < 0:\n            msg = f\"Characters from End must be a non-negative integer, got {tail_characters}\"\n            raise ValueError(msg)\n        if tail_characters == 0:\n            return \"\"\n        return text[-tail_characters:]\n\n    def _text_strip(self, text: str) -> str:\n        strip_mode = getattr(self, \"strip_mode\", \"both\")\n        strip_characters = getattr(self, \"strip_characters\", \"\")\n        text_str = str(text) if text else \"\"\n        chars_to_strip = strip_characters if strip_characters else None\n        if strip_mode == \"left\":\n            return text_str.lstrip(chars_to_strip)\n        if strip_mode == \"right\":\n            return text_str.rstrip(chars_to_strip)\n        return text_str.strip(chars_to_strip)\n\n    def _text_join(self, text: str) -> str:\n        text_input_2 = getattr(self, \"text_input_2\", \"\")\n        text1 = str(text) if text else \"\"\n        text2 = str(text_input_2) if text_input_2 else \"\"\n        if text1 and text2:\n            return f\"{text1}\\n{text2}\"\n        return text1 or text2\n\n    def _text_clean(self, text: str) -> str:\n        result = text\n        if getattr(self, \"remove_extra_spaces\", True):\n            # Collapse runs of horizontal whitespace but preserve newlines so\n            # that remove_empty_lines stays effective when both are enabled.\n            result = re.sub(r\"[^\\S\\n]+\", \" \", result)\n        if getattr(self, \"remove_special_chars\", False):\n            result = re.sub(r\"[^\\w\\s]\", \"\", result)\n        if getattr(self, \"remove_empty_lines\", False):\n            lines = [line for line in result.split(\"\\n\") if line.strip()]\n            result = \"\\n\".join(lines)\n        return result\n\n    def _format_result_as_text(self, result: Any) -> str:\n        if result is None:\n            return \"\"\n        if isinstance(result, list):\n            return \"\\n\".join(str(item) for item in result)\n        return str(result)\n"
              },
              "column_name": {
                "_input_type": "StrInput",
                "advanced": false,
                "api_editable": 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,
                "api_editable": 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": false,
                "title_case": false,
                "tool_mode": false,
                "trace_as_metadata": true,
                "track_in_telemetry": false,
                "type": "str",
                "value": ""
              },
              "count_characters": {
                "_input_type": "BoolInput",
                "advanced": true,
                "api_editable": false,
                "display_name": "Count Characters",
                "dynamic": true,
                "info": "Include character count in analysis.",
                "list": false,
                "list_add_label": "Add More",
                "name": "count_characters",
                "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
              },
              "count_lines": {
                "_input_type": "BoolInput",
                "advanced": true,
                "api_editable": false,
                "display_name": "Count Lines",
                "dynamic": true,
                "info": "Include line count in analysis.",
                "list": false,
                "list_add_label": "Add More",
                "name": "count_lines",
                "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
              },
              "count_words": {
                "_input_type": "BoolInput",
                "advanced": true,
                "api_editable": false,
                "display_name": "Count Words",
                "dynamic": true,
                "info": "Include word count in analysis.",
                "list": false,
                "list_add_label": "Add More",
                "name": "count_words",
                "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
              },
              "data": {
                "_input_type": "JSONInput",
                "advanced": false,
                "api_editable": false,
                "display_name": "JSON",
                "dynamic": false,
                "info": "The JSON / Data object to operate on.",
                "input_types": [
                  "Data",
                  "JSON"
                ],
                "list": true,
                "list_add_label": "Add More",
                "name": "data",
                "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": ""
              },
              "df": {
                "_input_type": "DataFrameInput",
                "advanced": false,
                "api_editable": false,
                "display_name": "Table",
                "dynamic": false,
                "info": "The input Table to operate on. Connect multiple Tables 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": ""
              },
              "extract_pattern": {
                "_input_type": "StrInput",
                "advanced": false,
                "api_editable": false,
                "display_name": "Extract Pattern",
                "dynamic": true,
                "info": "Regex pattern to extract from text.",
                "list": false,
                "list_add_label": "Add More",
                "load_from_db": false,
                "name": "extract_pattern",
                "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": ""
              },
              "filter_operator": {
                "_input_type": "DropdownInput",
                "advanced": false,
                "api_editable": 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": {
                "_input_type": "MessageTextInput",
                "advanced": false,
                "api_editable": false,
                "display_name": "Filter 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": ""
              },
              "has_header": {
                "_input_type": "BoolInput",
                "advanced": true,
                "api_editable": false,
                "display_name": "Has Header",
                "dynamic": true,
                "info": "Whether the table has a header row.",
                "list": false,
                "list_add_label": "Add More",
                "name": "has_header",
                "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
              },
              "head_characters": {
                "_input_type": "IntInput",
                "advanced": false,
                "api_editable": false,
                "display_name": "Characters from Start",
                "dynamic": true,
                "info": "Number of characters to extract from the beginning of text. Must be non-negative.",
                "list": false,
                "list_add_label": "Add More",
                "name": "head_characters",
                "override_skip": false,
                "placeholder": "",
                "range_spec": {
                  "max": 1000000,
                  "min": 0,
                  "step": 1,
                  "step_type": "int"
                },
                "required": false,
                "show": false,
                "title_case": false,
                "tool_mode": false,
                "trace_as_metadata": true,
                "track_in_telemetry": true,
                "type": "int",
                "value": 100
              },
              "input_type": {
                "_input_type": "TabInput",
                "advanced": false,
                "api_editable": false,
                "display_name": "Input Type",
                "dynamic": false,
                "info": "Select the type of input to operate on.",
                "load_from_db": false,
                "name": "input_type",
                "options": [
                  "Text",
                  "JSON",
                  "Table"
                ],
                "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": "Table"
              },
              "is_refresh": false,
              "left_dataframe": {
                "_input_type": "DataFrameInput",
                "advanced": false,
                "api_editable": false,
                "display_name": "Left Table",
                "dynamic": true,
                "info": "The left (primary) Table 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": ""
              },
              "mapped_json_display": {
                "_input_type": "MultilineInput",
                "advanced": false,
                "ai_enabled": false,
                "api_editable": false,
                "copy_field": false,
                "display_name": "JSON to Map",
                "dynamic": false,
                "info": "Paste or preview your JSON here to explore its structure and select a path for extraction.",
                "input_types": [
                  "Message"
                ],
                "list": false,
                "list_add_label": "Add More",
                "load_from_db": false,
                "multiline": true,
                "name": "mapped_json_display",
                "override_skip": false,
                "password": false,
                "placeholder": "Add a JSON example.",
                "real_time_refresh": true,
                "refresh_button": true,
                "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": ""
              },
              "max_matches": {
                "_input_type": "IntInput",
                "advanced": false,
                "api_editable": false,
                "display_name": "Max Matches",
                "dynamic": true,
                "info": "Maximum number of matches to extract.",
                "list": false,
                "list_add_label": "Add More",
                "name": "max_matches",
                "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": 10
              },
              "merge_how": {
                "_input_type": "DropdownInput",
                "advanced": false,
                "api_editable": 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,
                "api_editable": false,
                "display_name": "Merge On Column",
                "dynamic": true,
                "info": "The column name to merge Tables on. Must exist in both Tables.",
                "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,
                "api_editable": 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": true,
                "title_case": false,
                "tool_mode": false,
                "trace_as_metadata": true,
                "track_in_telemetry": false,
                "type": "str",
                "value": "mimetype"
              },
              "new_column_value": {
                "_input_type": "MessageTextInput",
                "advanced": false,
                "api_editable": false,
                "display_name": "New Column Value",
                "dynamic": true,
                "info": "The value to populate the new column with.",
                "input_types": [
                  "Message"
                ],
                "list": false,
                "list_add_label": "Add More",
                "load_from_db": true,
                "name": "new_column_value",
                "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": "MIMETYPE"
              },
              "num_rows": {
                "_input_type": "IntInput",
                "advanced": false,
                "api_editable": 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,
                "api_editable": false,
                "display_name": "Operation",
                "dynamic": false,
                "info": "Select the operation to perform. The matching fields and output appear once you choose one.",
                "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": "plus",
                    "name": "Add Column",
                    "selected": false
                  }
                ]
              },
              "query": {
                "_input_type": "MessageTextInput",
                "advanced": false,
                "api_editable": false,
                "display_name": "JQ Expression",
                "dynamic": false,
                "info": "JSON Query to filter the data. Used by Path Selection and JQ Expression operations.",
                "input_types": [
                  "Message"
                ],
                "list": false,
                "list_add_label": "Add More",
                "load_from_db": false,
                "name": "query",
                "override_skip": false,
                "placeholder": "e.g., .properties.id",
                "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": ""
              },
              "remove_empty_lines": {
                "_input_type": "BoolInput",
                "advanced": false,
                "api_editable": false,
                "display_name": "Remove Empty Lines",
                "dynamic": true,
                "info": "Remove empty lines from text.",
                "list": false,
                "list_add_label": "Add More",
                "name": "remove_empty_lines",
                "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": false
              },
              "remove_extra_spaces": {
                "_input_type": "BoolInput",
                "advanced": false,
                "api_editable": false,
                "display_name": "Remove Extra Spaces",
                "dynamic": true,
                "info": "Remove multiple consecutive spaces.",
                "list": false,
                "list_add_label": "Add More",
                "name": "remove_extra_spaces",
                "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
              },
              "remove_keys_input": {
                "_input_type": "MessageTextInput",
                "advanced": false,
                "api_editable": false,
                "display_name": "Remove Keys",
                "dynamic": false,
                "info": "List of keys to remove from the data.",
                "input_types": [
                  "Message"
                ],
                "list": true,
                "list_add_label": "Add More",
                "load_from_db": false,
                "name": "remove_keys_input",
                "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": []
              },
              "remove_special_chars": {
                "_input_type": "BoolInput",
                "advanced": false,
                "api_editable": false,
                "display_name": "Remove Special Characters",
                "dynamic": true,
                "info": "Remove special characters except alphanumeric and spaces.",
                "list": false,
                "list_add_label": "Add More",
                "name": "remove_special_chars",
                "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": false
              },
              "rename_keys_input": {
                "_input_type": "DictInput",
                "advanced": false,
                "api_editable": false,
                "display_name": "Rename Keys",
                "dynamic": false,
                "info": "List of keys to rename in the data.",
                "list": true,
                "list_add_label": "Add More",
                "name": "rename_keys_input",
                "override_skip": false,
                "placeholder": "",
                "required": false,
                "show": false,
                "title_case": false,
                "tool_mode": false,
                "trace_as_input": true,
                "track_in_telemetry": false,
                "type": "dict",
                "value": {
                  "old_key": "new_key"
                }
              },
              "replace_value": {
                "_input_type": "MessageTextInput",
                "advanced": false,
                "api_editable": 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_text": {
                "_input_type": "StrInput",
                "advanced": false,
                "api_editable": false,
                "display_name": "Replacement Text",
                "dynamic": true,
                "info": "Text to replace the search pattern with.",
                "list": false,
                "list_add_label": "Add More",
                "load_from_db": false,
                "name": "replacement_text",
                "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": ""
              },
              "replacement_value": {
                "_input_type": "MessageTextInput",
                "advanced": false,
                "api_editable": 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,
                "api_editable": false,
                "display_name": "Right Table",
                "dynamic": true,
                "info": "The right (secondary) Table 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": ""
              },
              "search_pattern": {
                "_input_type": "StrInput",
                "advanced": false,
                "api_editable": false,
                "display_name": "Search Pattern",
                "dynamic": true,
                "info": "Text pattern to search for (supports regex).",
                "list": false,
                "list_add_label": "Add More",
                "load_from_db": false,
                "name": "search_pattern",
                "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": ""
              },
              "select_keys_input": {
                "_input_type": "MessageTextInput",
                "advanced": false,
                "api_editable": false,
                "display_name": "Select Keys",
                "dynamic": false,
                "info": "List of keys to select from the data. Only top-level keys can be selected.",
                "input_types": [
                  "Message"
                ],
                "list": true,
                "list_add_label": "Add More",
                "load_from_db": false,
                "name": "select_keys_input",
                "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": []
              },
              "selected_key": {
                "_input_type": "DropdownInput",
                "advanced": false,
                "api_editable": false,
                "combobox": false,
                "dialog_inputs": {},
                "display_name": "Select Path",
                "dynamic": true,
                "external_options": {},
                "info": "",
                "name": "selected_key",
                "options": [],
                "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": null
              },
              "strip_characters": {
                "_input_type": "StrInput",
                "advanced": false,
                "api_editable": false,
                "display_name": "Characters to Strip",
                "dynamic": true,
                "info": "Specific characters to remove (leave empty for whitespace).",
                "list": false,
                "list_add_label": "Add More",
                "load_from_db": false,
                "name": "strip_characters",
                "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": ""
              },
              "strip_mode": {
                "_input_type": "DropdownInput",
                "advanced": false,
                "api_editable": false,
                "combobox": false,
                "dialog_inputs": {},
                "display_name": "Strip Mode",
                "dynamic": true,
                "external_options": {},
                "info": "Which sides to strip whitespace from.",
                "name": "strip_mode",
                "options": [
                  "both",
                  "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": "both"
              },
              "table_separator": {
                "_input_type": "StrInput",
                "advanced": false,
                "api_editable": false,
                "display_name": "Table Separator",
                "dynamic": true,
                "info": "Separator used in the table (default: '|').",
                "list": false,
                "list_add_label": "Add More",
                "load_from_db": false,
                "name": "table_separator",
                "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": "|"
              },
              "tail_characters": {
                "_input_type": "IntInput",
                "advanced": false,
                "api_editable": false,
                "display_name": "Characters from End",
                "dynamic": true,
                "info": "Number of characters to extract from the end of text. Must be non-negative.",
                "list": false,
                "list_add_label": "Add More",
                "name": "tail_characters",
                "override_skip": false,
                "placeholder": "",
                "range_spec": {
                  "max": 1000000,
                  "min": 0,
                  "step": 1,
                  "step_type": "int"
                },
                "required": false,
                "show": false,
                "title_case": false,
                "tool_mode": false,
                "trace_as_metadata": true,
                "track_in_telemetry": true,
                "type": "int",
                "value": 100
              },
              "text_input": {
                "_input_type": "MultilineInput",
                "advanced": false,
                "ai_enabled": false,
                "api_editable": false,
                "copy_field": false,
                "display_name": "Text",
                "dynamic": false,
                "info": "The input text to process.",
                "input_types": [
                  "Message"
                ],
                "list": false,
                "list_add_label": "Add More",
                "load_from_db": false,
                "multiline": true,
                "name": "text_input",
                "override_skip": false,
                "password": 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": ""
              },
              "text_input_2": {
                "_input_type": "MultilineInput",
                "advanced": false,
                "ai_enabled": false,
                "api_editable": false,
                "copy_field": false,
                "display_name": "Second Text Input",
                "dynamic": true,
                "info": "Second text to join with the first text.",
                "input_types": [
                  "Message"
                ],
                "list": false,
                "list_add_label": "Add More",
                "load_from_db": false,
                "multiline": true,
                "name": "text_input_2",
                "override_skip": false,
                "password": 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": ""
              },
              "use_regex": {
                "_input_type": "BoolInput",
                "advanced": false,
                "api_editable": false,
                "display_name": "Use Regex",
                "dynamic": true,
                "info": "Whether to treat search pattern as regex.",
                "list": false,
                "list_add_label": "Add More",
                "name": "use_regex",
                "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": false
              }
            },
            "tool_mode": false
          },
          "showNode": false,
          "type": "Operations"
        },
        "dragging": false,
        "id": "Operations-VUCJC",
        "position": {
          "x": 1209.814890352602,
          "y": 1833.3550221261078
        },
        "selected": false,
        "type": "genericNode"
      },
      {
        "data": {
          "id": "OpenAICompatibleEmbedding-MloZd",
          "node": {
            "base_classes": [
              "Embeddings"
            ],
            "beta": false,
            "conditional_paths": [],
            "custom_fields": {},
            "description": "Embeddings via OpenRAG's OpenAI-compatible /v1 proxy. Uses the same base URL and hop token as the chat component.",
            "display_name": "OpenRAG Embeddings",
            "documentation": "",
            "edited": false,
            "field_order": [
              "model_name",
              "api_key",
              "api_base",
              "dimensions",
              "chunk_size"
            ],
            "frozen": false,
            "icon": "OpenRAG",
            "legacy": false,
            "metadata": {
              "code_hash": "d4b6a5d67c0b",
              "dependencies": {
                "dependencies": [
                  {
                    "name": "langchain_openai",
                    "version": "1.5.2"
                  },
                  {
                    "name": "lfx",
                    "version": "1.11.2"
                  }
                ],
                "total_dependencies": 2
              },
              "module": "custom_components.openrag_embeddings"
            },
            "minimized": false,
            "output_types": [],
            "outputs": [
              {
                "allows_loop": false,
                "cache": true,
                "display_name": "Embedding Model",
                "group_outputs": false,
                "method": "build_embeddings",
                "name": "embeddings",
                "selected": "Embeddings",
                "tool_mode": true,
                "types": [
                  "Embeddings"
                ],
                "value": "__UNDEFINED__"
              }
            ],
            "pinned": false,
            "template": {
              "_type": "Component",
              "api_base": {
                "_input_type": "StrInput",
                "advanced": false,
                "api_editable": false,
                "display_name": "OpenAI API Base",
                "dynamic": false,
                "info": "Bound to OPENRAG_LLM_BASE_URL at runtime. It is either the public /v1 base or the private router base. Same URL as chat.",
                "list": false,
                "list_add_label": "Add More",
                "load_from_db": true,
                "name": "api_base",
                "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_LLM_BASE_URL"
              },
              "api_key": {
                "_input_type": "SecretStrInput",
                "advanced": false,
                "api_editable": false,
                "display_name": "OpenRAG LLM Token",
                "dynamic": false,
                "info": "Hop token from OPENRAG_LLM_TOKEN. Same token as the chat component.",
                "input_types": [],
                "load_from_db": true,
                "name": "api_key",
                "override_skip": false,
                "password": true,
                "placeholder": "",
                "required": false,
                "show": true,
                "title_case": false,
                "track_in_telemetry": false,
                "type": "str",
                "value": "OPENRAG_LLM_TOKEN"
              },
              "chunk_size": {
                "_input_type": "IntInput",
                "advanced": true,
                "api_editable": false,
                "display_name": "Chunk Size",
                "dynamic": false,
                "info": "",
                "list": false,
                "list_add_label": "Add More",
                "name": "chunk_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": 1000
              },
              "code": {
                "advanced": true,
                "api_editable": false,
                "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": "\"\"\"OpenAI-compatible embeddings that talk to the OpenRAG LLM proxy.\n\nEmbeddings work the same way as chat: Langflow never holds upstream vendor\nkeys. At runtime OpenRAG injects:\n\n- ``OPENRAG_LLM_TOKEN`` — the same short-lived hop token as chat\n- ``OPENRAG_LLM_BASE_URL`` — the backend's ``/v1`` base or the router's\n  private unversioned base\n- ``SELECTED_EMBEDDING_MODEL`` — configured embedding model id\n\n``OpenAIEmbeddings`` posts to ``{base_url}/embeddings``. The backend gateway\nroutes by the configured embedding provider (which can differ from the chat\nprovider).\n\"\"\"\n\nfrom __future__ import annotations\n\nfrom typing import Any\n\nfrom langchain_core.embeddings import Embeddings\nfrom langchain_openai import OpenAIEmbeddings\nfrom lfx.base.embeddings.model import LCEmbeddingsModel\nfrom lfx.io import IntInput, SecretStrInput, StrInput\n\n# Names must match src/api/settings/langflow_sync.py + src/utils/langflow_headers.py\nOPENRAG_LLM_BASE_URL_VAR = \"OPENRAG_LLM_BASE_URL\"\nOPENRAG_LLM_TOKEN_VAR = \"OPENRAG_LLM_TOKEN\"\nSELECTED_EMBEDDING_MODEL_VAR = \"SELECTED_EMBEDDING_MODEL\"\nSELECTED_EMBEDDING_PROVIDER_VAR = \"SELECTED_EMBEDDING_PROVIDER\"\nLEGACY_EMBEDDING_ROUTE_PREFIX = \"legacy:\"\nINDEXED_EMBEDDING_ROUTE_PREFIX = \"space:\"\n\n\ndef _as_str(value: object) -> str | None:\n    if value is None:\n        return None\n    getter = getattr(value, \"get_secret_value\", None)\n    if callable(getter):\n        value = getter()\n    text = str(value).strip()\n    return text or None\n\n\ndef _embedding_route_identity(route: str) -> tuple[str | None, str]:\n    \"\"\"Return the provider and model identity encoded in a retrieval route.\"\"\"\n    if route.startswith(LEGACY_EMBEDDING_ROUTE_PREFIX):\n        return None, route.removeprefix(LEGACY_EMBEDDING_ROUTE_PREFIX)\n    if route.startswith(INDEXED_EMBEDDING_ROUTE_PREFIX):\n        qualified = route.removeprefix(INDEXED_EMBEDDING_ROUTE_PREFIX)\n        provider, separator, model_name = qualified.partition(\":\")\n        if separator and provider and model_name:\n            return provider.lower(), model_name\n        return None, qualified\n    return None, route\n\n\nclass OpenRAGEmbeddings(Embeddings):\n    \"\"\"One immutable model route plus a factory for other retrieval routes.\"\"\"\n\n    def __init__(\n        self,\n        *,\n        model_name: str,\n        api_key: str | None,\n        api_base: str | None,\n        provider_name: str | None = None,\n        chunk_size: int | None = None,\n        dimensions: int | None = None,\n    ) -> None:\n        self.model = model_name\n        self.deployment = model_name\n        self._api_key = api_key\n        self._api_base = api_base\n        self._provider_name = (provider_name or \"openai\").strip().lower()\n        self._chunk_size = chunk_size\n        self._dimensions = dimensions\n\n        kwargs: dict[str, Any] = {\n            \"model\": self.model,\n            # Keep identity aligned with ``model``. LangChain otherwise exposes\n            # its ada-002 class default as the deployment for every instance.\n            \"deployment\": self.model_name,\n            \"api_key\": api_key,\n            \"base_url\": api_base,\n            \"check_embedding_ctx_length\": False,\n        }\n        if chunk_size:\n            kwargs[\"chunk_size\"] = chunk_size\n        if dimensions:\n            kwargs[\"dimensions\"] = dimensions\n        self._delegate = OpenAIEmbeddings(**kwargs)\n\n    @property\n    def model_name(self) -> str:\n        return self.model\n\n    def for_model(self, model_name: str) -> Embeddings:\n        \"\"\"Return a dedicated adapter; never mutate the selected ingestion model.\"\"\"\n        route = (model_name or \"\").strip()\n        if not route:\n            raise ValueError(\"Embedding model route is required\")\n        route_provider, route_model = _embedding_route_identity(route)\n        is_selected_route = route_provider == self._provider_name and route_model == self.model_name\n        dimensions = self._dimensions if is_selected_route else None\n        return OpenRAGEmbeddings(\n            model_name=route,\n            api_key=self._api_key,\n            api_base=self._api_base,\n            provider_name=self._provider_name,\n            chunk_size=self._chunk_size,\n            dimensions=dimensions,\n        )\n\n    def embed_documents(self, texts: list[str]) -> list[list[float]]:\n        return self._delegate.embed_documents(texts)\n\n    def embed_query(self, text: str) -> list[float]:\n        return self._delegate.embed_query(text)\n\n    async def aembed_documents(self, texts: list[str]) -> list[list[float]]:\n        return await self._delegate.aembed_documents(texts)\n\n    async def aembed_query(self, text: str) -> list[float]:\n        return await self._delegate.aembed_query(text)\n\n\nclass OpenAICompatibleEmbeddingComponent(LCEmbeddingsModel):\n    display_name = \"OpenRAG Embeddings\"\n    description = (\n        \"Embeddings via OpenRAG's OpenAI-compatible proxy. \"\n        \"Uses the same base URL and hop token as the chat component.\"\n    )\n    icon = \"OpenRAG\"\n    name = \"OpenAICompatibleEmbedding\"\n\n    inputs = [\n        StrInput(\n            name=\"model_name\",\n            display_name=\"Model Name\",\n            info=\"Embedding model id. Bound to SELECTED_EMBEDDING_MODEL at runtime.\",\n            value=SELECTED_EMBEDDING_MODEL_VAR,\n            load_from_db=True,\n        ),\n        StrInput(\n            name=\"provider_name\",\n            display_name=\"Provider Name\",\n            info=\"Embedding provider id. Bound to SELECTED_EMBEDDING_PROVIDER at runtime.\",\n            value=SELECTED_EMBEDDING_PROVIDER_VAR,\n            load_from_db=True,\n        ),\n        SecretStrInput(\n            name=\"api_key\",\n            display_name=\"OpenRAG LLM Token\",\n            info=\"Hop token from OPENRAG_LLM_TOKEN. Same token as the chat component.\",\n            value=OPENRAG_LLM_TOKEN_VAR,\n            required=False,\n            load_from_db=True,\n        ),\n        StrInput(\n            name=\"api_base\",\n            display_name=\"OpenAI API Base\",\n            info=(\n                \"Bound to OPENRAG_LLM_BASE_URL at runtime. It is either the public \"\n                \"/v1 base or the private router base. Same URL as chat.\"\n            ),\n            value=OPENRAG_LLM_BASE_URL_VAR,\n            load_from_db=True,\n        ),\n        IntInput(\n            name=\"dimensions\",\n            display_name=\"Dimensions\",\n            info=\"Output dimensions when the embedding model supports it.\",\n            advanced=True,\n        ),\n        IntInput(\n            name=\"chunk_size\",\n            display_name=\"Chunk Size\",\n            advanced=True,\n            value=1000,\n        ),\n    ]\n\n    def build_embeddings(self) -> Embeddings:\n        api_key = _as_str(self.api_key)\n        api_base = _as_str(self.api_base)\n        if api_base:\n            api_base = api_base.rstrip(\"/\")\n        return OpenRAGEmbeddings(\n            model_name=self.model_name,\n            api_key=api_key,\n            api_base=api_base,\n            provider_name=getattr(self, \"provider_name\", None),\n            chunk_size=getattr(self, \"chunk_size\", None),\n            dimensions=getattr(self, \"dimensions\", None),\n        )\n"
              },
              "dimensions": {
                "_input_type": "IntInput",
                "advanced": true,
                "api_editable": false,
                "display_name": "Dimensions",
                "dynamic": false,
                "info": "Output dimensions when the embedding model supports it.",
                "list": false,
                "list_add_label": "Add More",
                "name": "dimensions",
                "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": 0
              },
              "model_name": {
                "_input_type": "StrInput",
                "advanced": false,
                "api_editable": false,
                "display_name": "Model Name",
                "dynamic": false,
                "info": "Embedding model id. Bound to SELECTED_EMBEDDING_MODEL at runtime.",
                "list": false,
                "list_add_label": "Add More",
                "load_from_db": true,
                "name": "model_name",
                "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": "SELECTED_EMBEDDING_MODEL"
              }
            },
            "tool_mode": false
          },
          "showNode": false,
          "type": "OpenAICompatibleEmbedding"
        },
        "dragging": false,
        "id": "OpenAICompatibleEmbedding-MloZd",
        "position": {
          "x": 1481.2824937463324,
          "y": 1946.082713977874
        },
        "selected": false,
        "type": "genericNode"
      },
      {
        "data": {
          "id": "OpenSearchVectorStoreComponentMultimodalMultiEmbedding-WaE28",
          "node": {
            "base_classes": [
              "JSON",
              "VectorStore"
            ],
            "beta": false,
            "conditional_paths": [],
            "custom_fields": {},
            "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,
            "field_order": [
              "docs_metadata",
              "opensearch_url",
              "index_name",
              "engine",
              "space_type",
              "ef_construction",
              "m",
              "num_candidates",
              "ingest_data",
              "search_query",
              "should_cache_vector_store",
              "embedding",
              "embedding_model_name",
              "vector_field",
              "number_of_results",
              "filter_expression",
              "auth_mode",
              "username",
              "password",
              "jwt_token",
              "jwt_header",
              "bearer_prefix",
              "use_ssl",
              "verify_certs",
              "request_timeout",
              "max_retries",
              "openrag_ingest_url",
              "openrag_ingest_token",
              "openrag_ingest_run_id",
              "openrag_ingest_batch_size"
            ],
            "frozen": false,
            "icon": "OpenSearch",
            "last_updated": "2026-08-18T22:46:55.693Z",
            "legacy": false,
            "metadata": {
              "code_hash": "3a48ccb54b9d",
              "dependencies": {
                "dependencies": [
                  {
                    "name": "httpx",
                    "version": "0.28.1"
                  },
                  {
                    "name": "lfx",
                    "version": "1.11.2"
                  },
                  {
                    "name": "opensearchpy",
                    "version": "3.2.0"
                  },
                  {
                    "name": "config",
                    "version": null
                  },
                  {
                    "name": "tenacity",
                    "version": "8.5.0"
                  }
                ],
                "total_dependencies": 5
              },
              "module": "_lfx_ext.extra.openrag.opensearch_multimodal"
            },
            "minimized": false,
            "output_types": [],
            "outputs": [
              {
                "allows_loop": false,
                "cache": true,
                "display_name": "Search Results",
                "group_outputs": false,
                "loop_types": null,
                "method": "search_documents",
                "name": "search_results",
                "options": null,
                "required_inputs": null,
                "selected": "JSON",
                "tool_mode": true,
                "types": [
                  "JSON"
                ],
                "value": "__UNDEFINED__"
              },
              {
                "allows_loop": false,
                "cache": true,
                "display_name": "Raw Search",
                "group_outputs": false,
                "loop_types": null,
                "method": "raw_search",
                "name": "raw_search",
                "options": null,
                "required_inputs": null,
                "selected": "JSON",
                "tool_mode": true,
                "types": [
                  "JSON"
                ],
                "value": "__UNDEFINED__"
              },
              {
                "allows_loop": false,
                "cache": true,
                "display_name": "Vector Store Connection",
                "group_outputs": false,
                "hidden": false,
                "loop_types": null,
                "method": "as_vector_store",
                "name": "vectorstoreconnection",
                "options": null,
                "required_inputs": null,
                "selected": "VectorStore",
                "tool_mode": true,
                "types": [
                  "VectorStore"
                ],
                "value": "__UNDEFINED__"
              }
            ],
            "pinned": false,
            "template": {
              "_frontend_node_flow_id": {
                "value": "5488df7c-b93f-4f87-a446-b67028bc0813"
              },
              "_frontend_node_folder_id": {
                "value": "e861a230-a49b-41ef-82de-5f825ea9ab51"
              },
              "_type": "Component",
              "auth_mode": {
                "_input_type": "DropdownInput",
                "advanced": false,
                "api_editable": false,
                "combobox": false,
                "dialog_inputs": {},
                "display_name": "Authentication Mode",
                "dynamic": false,
                "external_options": {},
                "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).",
                "name": "auth_mode",
                "options": [
                  "basic",
                  "jwt",
                  "openrag"
                ],
                "options_metadata": [],
                "override_skip": false,
                "placeholder": "",
                "real_time_refresh": true,
                "required": false,
                "show": true,
                "title_case": false,
                "toggle": false,
                "tool_mode": false,
                "trace_as_metadata": true,
                "track_in_telemetry": true,
                "type": "str",
                "value": "openrag"
              },
              "bearer_prefix": {
                "_input_type": "BoolInput",
                "advanced": true,
                "api_editable": false,
                "display_name": "Prefix 'Bearer '",
                "dynamic": false,
                "info": "",
                "list": false,
                "list_add_label": "Add More",
                "name": "bearer_prefix",
                "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": false
              },
              "code": {
                "advanced": true,
                "api_editable": false,
                "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 __future__ import annotations\n\nimport copy\nimport json\nimport unicodedata\nimport uuid\nfrom concurrent.futures import ThreadPoolExecutor, as_completed\nfrom dataclasses import dataclass\nfrom typing import Any\n\nimport httpx\nfrom lfx.base.vectorstores.model import LCVectorStoreComponent, check_cached_vector_store\nfrom lfx.base.vectorstores.vector_store_connection_decorator import vector_store_connection\nfrom lfx.io import (\n    BoolInput,\n    DropdownInput,\n    HandleInput,\n    IntInput,\n    MultilineInput,\n    Output,\n    SecretStrInput,\n    StrInput,\n    TableInput,\n)\nfrom lfx.log import logger\nfrom lfx.schema.data import Data\nfrom opensearchpy import OpenSearch, helpers\nfrom opensearchpy.exceptions import OpenSearchException, RequestError\n\nREQUEST_TIMEOUT = 60\nMAX_RETRIES = 5\nEMBEDDING_SPACE_PAGE_SIZE = 100\nSELECTED_EMBEDDING_PROVIDER_VAR = \"SELECTED_EMBEDDING_PROVIDER\"\nLEGACY_EMBEDDING_ROUTE_PREFIX = \"legacy:\"\nINDEXED_EMBEDDING_ROUTE_PREFIX = \"space:\"\n\n# Some PDF fonts map common kanji (日, 月, 木, 金, 土, ...) to the look-alike\n# Kangxi Radical code points in their /ToUnicode CMap, and Docling copies them\n# through unchanged. Map just those blocks back to CJK Unified Ideographs;\n# full NFKC would also rewrite full-width digits, ㈱, ①, half-width katakana.\n# Mirrors normalize_cjk_radicals in src/utils/document_processing.py.\nCJK_RADICAL_TABLE = {\n    cp: unicodedata.normalize(\"NFKC\", chr(cp))\n    for cp in range(0x2E80, 0x2FE0)  # CJK Radicals Supplement + Kangxi Radicals\n    if unicodedata.normalize(\"NFKC\", chr(cp)) != chr(cp)\n}\n\n\n@dataclass(frozen=True)\nclass EmbeddingSpace:\n    \"\"\"One indexed vector space and the model route needed to query it.\"\"\"\n\n    space_id: str\n    route_model: str\n    field_identity: str\n    legacy: bool = False\n\n\ndef build_embedding_space_aggregation(\n    *,\n    size: int,\n    qualified_after: dict[str, Any] | None = None,\n    legacy_after: dict[str, Any] | None = None,\n    include_qualified: bool = True,\n    include_legacy: bool = True,\n) -> dict[str, Any]:\n    \"\"\"Build pageable discovery aggregations for exact and legacy vector spaces.\"\"\"\n    aggregations: dict[str, Any] = {}\n    if include_qualified:\n        composite: dict[str, Any] = {\n            \"size\": size,\n            \"sources\": [{\"space_id\": {\"terms\": {\"field\": \"embedding_space_id\"}}}],\n        }\n        if qualified_after:\n            composite[\"after\"] = qualified_after\n        aggregations[\"embedding_spaces\"] = {\"composite\": composite}\n\n    if include_legacy:\n        composite = {\n            \"size\": size,\n            \"sources\": [{\"model\": {\"terms\": {\"field\": \"embedding_model\"}}}],\n        }\n        if legacy_after:\n            composite[\"after\"] = legacy_after\n        aggregations[\"legacy_embedding_models\"] = {\"composite\": composite}\n    return aggregations\n\n\ndef embedding_space_after_keys(\n    result: dict[str, Any],\n) -> tuple[dict[str, Any] | None, dict[str, Any] | None]:\n    \"\"\"Return composite pagination cursors for exact and legacy aggregations.\"\"\"\n    aggregations = result.get(\"aggregations\", {})\n    qualified_after = aggregations.get(\"embedding_spaces\", {}).get(\"after_key\")\n    legacy_after = aggregations.get(\"legacy_embedding_models\", {}).get(\"after_key\")\n    return qualified_after, legacy_after\n\n\ndef embedding_spaces_from_aggregation(result: dict[str, Any]) -> list[EmbeddingSpace]:\n    \"\"\"Convert an OpenSearch aggregation response into stable retrieval identities.\"\"\"\n    aggregations = result.get(\"aggregations\", {})\n    qualified_buckets = aggregations.get(\"embedding_spaces\", {}).get(\"buckets\", [])\n    legacy_buckets = aggregations.get(\"legacy_embedding_models\", {}).get(\"buckets\", [])\n\n    spaces: list[EmbeddingSpace] = []\n    seen: set[str] = set()\n    for bucket in qualified_buckets:\n        key = bucket.get(\"key\")\n        raw_space_id = key.get(\"space_id\") if isinstance(key, dict) else key\n        space_id = str(raw_space_id or \"\").strip()\n        if not space_id or space_id in seen:\n            continue\n        seen.add(space_id)\n        spaces.append(\n            EmbeddingSpace(\n                space_id=space_id,\n                route_model=f\"{INDEXED_EMBEDDING_ROUTE_PREFIX}{space_id}\",\n                field_identity=space_id,\n            )\n        )\n\n    for bucket in legacy_buckets:\n        key = bucket.get(\"key\")\n        raw_model = key.get(\"model\") if isinstance(key, dict) else key\n        model = str(raw_model or \"\").strip()\n        space_id = f\"{LEGACY_EMBEDDING_ROUTE_PREFIX}{model}\"\n        if not model or space_id in seen:\n            continue\n        seen.add(space_id)\n        spaces.append(\n            EmbeddingSpace(\n                space_id=space_id,\n                route_model=space_id,\n                field_identity=model,\n                legacy=True,\n            )\n        )\n    return spaces\n\n\n# watsonx.ai surfaces rate-limit state via these (mostly non-standard) response\n# headers. The IBM SDK acts on the x-requests-limit-* family directly; we log\n# them on a failed embedding call to aid plan/region tuning.\n_WATSONX_RATE_LIMIT_HEADERS = (\n    \"x-requests-limit-rate\",\n    \"x-requests-limit-remaining\",\n    \"x-requests-limit-reset\",\n    \"Retry-After\",\n)\n\n\ndef _log_watsonx_rate_limit_headers(error: Exception) -> None:\n    \"\"\"Best-effort diagnostic: log watsonx rate-limit headers from a failed call.\n\n    The watsonx SDK raises ``ApiRequestFailure``, which carries the originating\n    httpx/requests ``Response`` as ``.response``. On a 429 exhaustion we surface\n    the documented rate-limit headers so operators can tune throughput.\n    \"\"\"\n    try:\n        response = getattr(error, \"response\", None)\n        headers = getattr(response, \"headers\", None)\n        if not headers:\n            return\n        status = getattr(response, \"status_code\", \"unknown\")\n        observed = {\n            h: headers.get(h) for h in _WATSONX_RATE_LIMIT_HEADERS if headers.get(h) is not None\n        }\n        if str(status) == \"429\" or observed:\n            logger.warning(f\"watsonx rate-limit response (status={status}): {observed}\")\n    except Exception as log_error:  # never let diagnostics mask the real error\n        logger.debug(f\"Could not extract watsonx rate-limit headers: {log_error}\")\n\n\ndef normalize_model_name(model_name: str) -> str:\n    \"\"\"Normalize embedding model name for use as field suffix.\n\n    Converts model names to valid OpenSearch field names by replacing\n    special characters and ensuring alphanumeric format.\n\n    Args:\n        model_name: Original embedding model name (e.g., \"text-embedding-3-small\")\n\n    Returns:\n        Normalized field suffix (e.g., \"text_embedding_3_small\")\n    \"\"\"\n    normalized = model_name.lower()\n    # Replace common separators with underscores\n    normalized = normalized.replace(\"-\", \"_\").replace(\":\", \"_\").replace(\"/\", \"_\").replace(\".\", \"_\")\n    # Remove any non-alphanumeric characters except underscores\n    normalized = \"\".join(c if c.isalnum() or c == \"_\" else \"_\" for c in normalized)\n    # Remove duplicate underscores\n    while \"__\" in normalized:\n        normalized = normalized.replace(\"__\", \"_\")\n    return normalized.strip(\"_\")\n\n\ndef get_embedding_field_name(model_name: str) -> str:\n    \"\"\"Get the dynamic embedding field name for a model.\n\n    Args:\n        model_name: Embedding model name\n\n    Returns:\n        Field name in format: chunk_embedding_{normalized_model_name}\n    \"\"\"\n    logger.info(f\"chunk_embedding_{normalize_model_name(model_name)}\")\n    return f\"chunk_embedding_{normalize_model_name(model_name)}\"\n\n\nUNTRUSTED_CHUNK_FENCE_START = \"<<<UNTRUSTED_DOC_CHUNK>>>\"\nUNTRUSTED_CHUNK_FENCE_END = \"<<<END_UNTRUSTED_DOC_CHUNK>>>\"\n\n\ndef fence_untrusted_text(text: str) -> str:\n    \"\"\"Wrap retrieved document text in delimiters marking it as untrusted data.\n\n    Retrieved chunk text can contain attacker-controlled natural-language\n    instructions (indirect prompt injection, VULN-13906). Fencing it lets the\n    system prompt tell the LLM to treat anything between these markers as\n    data only, never as instructions or tool directives.\n\n    Any literal fence markers already present in `text` are escaped first, so\n    a poisoned chunk can't embed a fake end-of-fence marker to break out of\n    the untrusted section and have its continuation misread as trusted.\n    \"\"\"\n    if not text:\n        return text\n    escaped = text.replace(UNTRUSTED_CHUNK_FENCE_START, \"\\\\\" + UNTRUSTED_CHUNK_FENCE_START).replace(\n        UNTRUSTED_CHUNK_FENCE_END, \"\\\\\" + UNTRUSTED_CHUNK_FENCE_END\n    )\n    return f\"{UNTRUSTED_CHUNK_FENCE_START}\\n{escaped}\\n{UNTRUSTED_CHUNK_FENCE_END}\"\n\n\n@vector_store_connection\nclass OpenSearchVectorStoreComponentMultimodalMultiEmbedding(LCVectorStoreComponent):\n    \"\"\"OpenSearch Vector Store Component with Multi-Model Hybrid Search Capabilities.\n\n    This component provides vector storage and retrieval using OpenSearch, combining semantic\n    similarity search (KNN) with keyword-based search for optimal results. It supports:\n    - Multiple embedding models per index with dynamic field names\n    - Automatic detection and querying of all available embedding models\n    - Parallel embedding generation for multi-model search\n    - Document ingestion with model tracking\n    - Advanced filtering and aggregations\n    - Flexible authentication options\n\n    Features:\n    - Multi-model vector storage with dynamic fields (chunk_embedding_{model_name})\n    - Hybrid search combining multiple KNN queries (dis_max) + keyword matching\n    - Auto-detection of available models in the index\n    - Parallel query embedding generation for all detected models\n    - Vector storage with configurable engines (jvector, nmslib, faiss, lucene)\n    - Flexible authentication (Basic auth, JWT tokens)\n\n    Model Name Resolution:\n    - Priority: deployment > model > model_name attributes\n    - This ensures correct matching between embedding objects and index fields\n    - When multiple embeddings are provided, specify embedding_model_name to select which one to use\n    - During search, each detected model in the index is matched to its corresponding embedding object\n    \"\"\"\n\n    display_name: str = \"OpenSearch (Multi-Model Multi-Embedding)\"\n    icon: str = \"OpenSearch\"\n    description: str = (\n        \"Store and search documents using OpenSearch with multi-model hybrid semantic and keyword search. \"\n        \"To search use the tools search_documents and raw_search. \"\n        \"Search documents takes a query for vector search, for example\\n\"\n        '  {search_query: \"components in openrag\"}'\n    )\n\n    # Keys we consider baseline\n    default_keys: list[str] = [\n        \"opensearch_url\",\n        \"index_name\",\n        *[i.name for i in LCVectorStoreComponent.inputs],  # search_query, add_documents, etc.\n        \"embedding\",\n        \"embedding_model_name\",\n        \"embedding_provider_name\",\n        \"vector_field\",\n        \"number_of_results\",\n        \"auth_mode\",\n        \"username\",\n        \"password\",\n        \"jwt_token\",\n        \"jwt_header\",\n        \"bearer_prefix\",\n        \"use_ssl\",\n        \"verify_certs\",\n        \"filter_expression\",\n        \"engine\",\n        \"space_type\",\n        \"ef_construction\",\n        \"m\",\n        \"num_candidates\",\n        \"docs_metadata\",\n        \"request_timeout\",\n        \"max_retries\",\n        \"openrag_ingest_url\",\n        \"openrag_ingest_token\",\n        \"openrag_ingest_run_id\",\n        \"openrag_ingest_batch_size\",\n    ]\n    _openrag_ingest_global_placeholders = {\n        \"openrag_ingest_url\": \"OPENRAG_INGEST_URL\",\n        \"openrag_ingest_token\": \"OPENRAG_INGEST_TOKEN\",\n        \"openrag_ingest_run_id\": \"OPENRAG_INGEST_RUN_ID\",\n    }\n\n    inputs = [\n        TableInput(\n            name=\"docs_metadata\",\n            display_name=\"Document Metadata\",\n            info=(\n                \"Additional metadata key-value pairs to be added to all ingested documents. \"\n                \"Useful for tagging documents with source information, categories, or other custom attributes.\"\n            ),\n            table_schema=[\n                {\n                    \"name\": \"key\",\n                    \"display_name\": \"Key\",\n                    \"type\": \"str\",\n                    \"description\": \"Key name\",\n                },\n                {\n                    \"name\": \"value\",\n                    \"display_name\": \"Value\",\n                    \"type\": \"str\",\n                    \"description\": \"Value of the metadata\",\n                },\n            ],\n            value=[],\n            input_types=[\"Data\", \"JSON\"],\n        ),\n        StrInput(\n            name=\"opensearch_url\",\n            display_name=\"OpenSearch URL\",\n            value=\"http://localhost:9200\",\n            info=(\n                \"The connection URL for your OpenSearch cluster \"\n                \"(e.g., http://localhost:9200 for local development or your cloud endpoint).\"\n            ),\n        ),\n        StrInput(\n            name=\"index_name\",\n            display_name=\"Index Name\",\n            value=\"langflow\",\n            info=(\n                \"The OpenSearch index name where documents will be stored and searched. \"\n                \"Will be created automatically if it doesn't exist.\"\n            ),\n        ),\n        DropdownInput(\n            name=\"engine\",\n            display_name=\"Vector Engine\",\n            options=[\"nmslib\", \"faiss\", \"lucene\", \"jvector\"],\n            value=\"jvector\",\n            info=(\n                \"Vector search engine for similarity calculations. 'nmslib' works with standard \"\n                \"OpenSearch. 'jvector' requires OpenSearch 2.9+. 'lucene' requires index.knn: true. \"\n                \"Amazon OpenSearch Serverless only supports 'nmslib' or 'faiss'.\"\n            ),\n            advanced=True,\n        ),\n        DropdownInput(\n            name=\"space_type\",\n            display_name=\"Distance Metric\",\n            options=[\"l2\", \"l1\", \"cosinesimil\", \"linf\", \"innerproduct\"],\n            value=\"l2\",\n            info=(\n                \"Distance metric for calculating vector similarity. 'l2' (Euclidean) is most common, \"\n                \"'cosinesimil' for cosine similarity, 'innerproduct' for dot product.\"\n            ),\n            advanced=True,\n        ),\n        IntInput(\n            name=\"ef_construction\",\n            display_name=\"EF Construction\",\n            value=512,\n            info=(\n                \"Size of the dynamic candidate list during index construction. \"\n                \"Higher values improve recall but increase indexing time and memory usage.\"\n            ),\n            advanced=True,\n        ),\n        IntInput(\n            name=\"m\",\n            display_name=\"M Parameter\",\n            value=16,\n            info=(\n                \"Number of bidirectional connections for each vector in the HNSW graph. \"\n                \"Higher values improve search quality but increase memory usage and indexing time.\"\n            ),\n            advanced=True,\n        ),\n        IntInput(\n            name=\"num_candidates\",\n            display_name=\"Candidate Pool Size\",\n            value=1000,\n            info=(\n                \"Number of approximate neighbors to consider for each KNN query. \"\n                \"Some OpenSearch deployments do not support this parameter; set to 0 to disable.\"\n            ),\n            advanced=True,\n        ),\n        *LCVectorStoreComponent.inputs,  # includes search_query, add_documents, etc.\n        HandleInput(\n            name=\"embedding\", display_name=\"Embedding\", input_types=[\"Embeddings\"], is_list=True\n        ),\n        StrInput(\n            name=\"embedding_model_name\",\n            display_name=\"Embedding Model Name\",\n            value=\"\",\n            info=(\n                \"Name of the embedding model to use for ingestion. This selects which embedding from the list \"\n                \"will be used to embed documents. Matches on deployment, model, model_id, or model_name. \"\n                \"For duplicate deployments, use combined format: 'deployment:model' \"\n                \"(e.g., 'text-embedding-ada-002:text-embedding-3-large'). \"\n                \"Leave empty to use the first embedding. Error message will show all available identifiers.\"\n            ),\n            advanced=False,\n        ),\n        StrInput(\n            name=\"embedding_provider_name\",\n            display_name=\"Embedding Provider\",\n            value=SELECTED_EMBEDDING_PROVIDER_VAR,\n            info=(\n                \"Exact OpenRAG provider key used for new ingestion metadata and vector fields. \"\n                \"Bound to SELECTED_EMBEDDING_PROVIDER in managed OpenRAG flows.\"\n            ),\n            load_from_db=True,\n            advanced=True,\n        ),\n        StrInput(\n            name=\"vector_field\",\n            display_name=\"Legacy Vector Field Name\",\n            value=\"chunk_embedding\",\n            advanced=True,\n            info=(\n                \"Legacy field name for backward compatibility. New documents use dynamic fields \"\n                \"(chunk_embedding_{model_name}) based on the embedding_model_name.\"\n            ),\n        ),\n        IntInput(\n            name=\"number_of_results\",\n            display_name=\"Default Result Limit\",\n            value=10,\n            advanced=True,\n            info=(\n                \"Default maximum number of search results to return when no limit is \"\n                \"specified in the filter expression.\"\n            ),\n        ),\n        MultilineInput(\n            name=\"filter_expression\",\n            display_name=\"Search Filters (JSON)\",\n            value=\"\",\n            info=(\n                \"Optional JSON configuration for search filtering, result limits, and score thresholds.\\n\\n\"\n                \"Format 1 - Explicit filters:\\n\"\n                '{\"filter\": [{\"term\": {\"filename\":\"doc.pdf\"}}, '\n                '{\"terms\":{\"owner\":[\"user1\",\"user2\"]}}], \"limit\": 10, \"score_threshold\": 1.6}\\n\\n'\n                \"Format 2 - Context-style mapping:\\n\"\n                '{\"data_sources\":[\"file.pdf\"], \"document_types\":[\"application/pdf\"], \"owners\":[\"user123\"]}\\n\\n'\n                \"Use __IMPOSSIBLE_VALUE__ as placeholder to ignore specific filters.\"\n            ),\n        ),\n        # ----- Auth controls (dynamic) -----\n        DropdownInput(\n            name=\"auth_mode\",\n            display_name=\"Authentication Mode\",\n            value=\"openrag\",\n            options=[\"basic\", \"jwt\", \"openrag\"],\n            info=(\n                \"Authentication method: 'basic' for username/password authentication, \"\n                \"'jwt' for JSON Web Token (Bearer) authentication, or 'openrag' to \"\n                \"delegate writes to the OpenRAG backend ingest callback (no direct \"\n                \"OpenSearch credentials required — only OPENRAG_* fields).\"\n            ),\n            real_time_refresh=True,\n            advanced=False,\n        ),\n        StrInput(\n            name=\"username\",\n            display_name=\"Username\",\n            value=\"admin\",\n            show=True,\n        ),\n        SecretStrInput(\n            name=\"password\",\n            display_name=\"OpenSearch Password\",\n            value=\"OPENSEARCH_PASSWORD\",\n            load_from_db=True,\n            show=True,\n        ),\n        SecretStrInput(\n            name=\"jwt_token\",\n            display_name=\"JWT Token\",\n            value=\"JWT\",\n            load_from_db=False,\n            show=False,\n            info=(\n                \"Valid JSON Web Token for authentication. \"\n                \"Will be sent in the Authorization header (with optional 'Bearer ' prefix).\"\n            ),\n            required=False,\n        ),\n        StrInput(\n            name=\"jwt_header\",\n            display_name=\"JWT Header Name\",\n            value=\"Authorization\",\n            show=False,\n            advanced=True,\n        ),\n        BoolInput(\n            name=\"bearer_prefix\",\n            display_name=\"Prefix 'Bearer '\",\n            value=False,\n            show=False,\n            advanced=True,\n        ),\n        # ----- TLS -----\n        BoolInput(\n            name=\"use_ssl\",\n            display_name=\"Use SSL/TLS\",\n            value=True,\n            advanced=True,\n            info=\"Enable SSL/TLS encryption for secure connections to OpenSearch.\",\n        ),\n        BoolInput(\n            name=\"verify_certs\",\n            display_name=\"Verify SSL Certificates\",\n            value=False,\n            advanced=True,\n            info=(\n                \"Verify SSL certificates when connecting. \"\n                \"Disable for self-signed certificates in development environments.\"\n            ),\n        ),\n        # ----- Timeout / Retry -----\n        StrInput(\n            name=\"request_timeout\",\n            display_name=\"Request Timeout (seconds)\",\n            value=\"60\",\n            advanced=True,\n            info=(\n                \"Time in seconds to wait for a response from OpenSearch. \"\n                \"Increase for large bulk ingestion or complex hybrid queries.\"\n            ),\n        ),\n        StrInput(\n            name=\"max_retries\",\n            display_name=\"Max Retries\",\n            value=\"3\",\n            advanced=True,\n            info=\"Number of retries for failed connections before raising an error.\",\n        ),\n        StrInput(\n            name=\"openrag_ingest_url\",\n            display_name=\"OpenRAG Ingest URL\",\n            value=\"OPENRAG_INGEST_URL\",\n            load_from_db=True,\n            input_types=[\"Text\", \"Message\"],\n            advanced=True,\n            info=\"Internal OpenRAG callback URL for backend-owned document indexing.\",\n        ),\n        SecretStrInput(\n            name=\"openrag_ingest_token\",\n            display_name=\"OpenRAG Ingest Token\",\n            value=\"OPENRAG_INGEST_TOKEN\",\n            load_from_db=True,\n            input_types=[\"Text\", \"Message\"],\n            advanced=True,\n            info=\"Short-lived token used only for OpenRAG ingest callbacks.\",\n        ),\n        StrInput(\n            name=\"openrag_ingest_run_id\",\n            display_name=\"OpenRAG Ingest Run ID\",\n            value=\"OPENRAG_INGEST_RUN_ID\",\n            load_from_db=True,\n            input_types=[\"Text\", \"Message\"],\n            advanced=True,\n        ),\n        IntInput(\n            name=\"openrag_ingest_batch_size\",\n            display_name=\"OpenRAG Ingest Batch Size\",\n            value=100,\n            advanced=True,\n        ),\n    ]\n    outputs = [\n        Output(\n            display_name=\"Search Results\",\n            name=\"search_results\",\n            method=\"search_documents\",\n        ),\n        Output(display_name=\"Raw Search\", name=\"raw_search\", method=\"raw_search\"),\n    ]\n\n    def raw_search(self, query: str | dict | None = None) -> Data:\n        \"\"\"Execute a raw OpenSearch query against the target index.\n\n        Args:\n            query (dict[str, Any]): The OpenSearch query DSL dictionary.\n\n        Returns:\n            Data: Search results as a Data object.\n\n        Raises:\n            ValueError: If 'query' is not a valid OpenSearch query (must be a non-empty dict).\n        \"\"\"\n        raw_query = query if query is not None else self.search_query\n\n        if raw_query is None or (isinstance(raw_query, str) and not raw_query.strip()):\n            self.log(\"No query provided for raw search - returning empty results\")\n            return Data(data={})\n\n        if isinstance(raw_query, dict):\n            query_body = copy.deepcopy(raw_query)\n        elif isinstance(raw_query, str):\n            s = raw_query.strip()\n\n            # First, optimistically try to parse as JSON DSL\n            try:\n                query_body = json.loads(s)\n            except json.JSONDecodeError:\n                # Fallback: treat as a basic text query over common fields\n                query_body = {\n                    \"query\": {\n                        \"multi_match\": {\n                            \"query\": s,\n                            \"fields\": [\"text^2\", \"filename^1.5\"],\n                            \"type\": \"best_fields\",\n                            \"fuzziness\": \"AUTO\",\n                        }\n                    }\n                }\n        else:\n            msg = f\"Unsupported raw_search query type: {type(raw_query)!r}\"\n            raise TypeError(msg)\n\n        filter_obj = self._parse_filter_expression()\n        filter_clauses = self._coerce_filter_clauses(filter_obj)\n\n        if filter_clauses:\n            if \"query\" in query_body:\n                original_query = query_body[\"query\"]\n                query_body[\"query\"] = {\n                    \"bool\": {\n                        \"must\": [original_query],\n                        \"filter\": filter_clauses,\n                    }\n                }\n            else:\n                query_body[\"query\"] = {\n                    \"bool\": {\n                        \"must\": [{\"match_all\": {}}],\n                        \"filter\": filter_clauses,\n                    }\n                }\n\n        if filter_obj:\n            # Apply limit if not already set in the raw query\n            if \"size\" not in query_body:\n                limit = self._resolve_limit(filter_obj, default_limit=None)\n                if limit is not None:\n                    query_body[\"size\"] = limit\n\n            # Apply score_threshold / scoreThreshold as min_score if not already set\n            if \"min_score\" not in query_body:\n                score_threshold = self._resolve_score_threshold(filter_obj)\n                if score_threshold is not None:\n                    query_body[\"min_score\"] = score_threshold\n\n        client = self.build_client()\n        logger.info(f\"query: {query_body}\")\n        resp = client.search(\n            index=self.index_name,\n            body=query_body,\n            params={\"terminate_after\": 0},\n        )\n        # Remove any _source keys whose value is a list of floats (embedding vectors)\n        # Minimum length threshold to identify embedding vectors\n        min_vector_length = 100\n\n        def is_vector(val):\n            # Accepts if it's a list of numbers (float or int) and has reasonable vector length\n            return (\n                isinstance(val, list)\n                and len(val) > min_vector_length\n                and all(isinstance(x, (float, int)) for x in val)\n            )\n\n        if \"hits\" in resp and \"hits\" in resp[\"hits\"]:\n            for hit in resp[\"hits\"][\"hits\"]:\n                source = hit.get(\"_source\")\n                if isinstance(source, dict):\n                    keys_to_remove = [k for k, v in source.items() if is_vector(v)]\n                    for k in keys_to_remove:\n                        source.pop(k)\n                    if \"text\" in source:\n                        source[\"text\"] = fence_untrusted_text(source[\"text\"])\n        logger.info(f\"Raw search response (all embedding vectors removed): {resp}\")\n        return Data(**resp)\n\n    def _get_embedding_model_name(self, embedding_obj=None) -> str:\n        \"\"\"Get the embedding model name from component config or embedding object.\n\n        Priority: deployment > model > model_id > model_name\n        This ensures we use the actual model being deployed, not just the configured model.\n        Supports multiple embedding providers (OpenAI, Watsonx, Cohere, etc.)\n\n        Args:\n            embedding_obj: Specific embedding object to get name from (optional)\n\n        Returns:\n            Embedding model name\n\n        Raises:\n            ValueError: If embedding model name cannot be determined\n        \"\"\"\n        # First try explicit embedding_model_name input\n        if hasattr(self, \"embedding_model_name\") and self.embedding_model_name:\n            return self.embedding_model_name.strip()\n\n        # Try to get from provided embedding object\n        if embedding_obj:\n            # Priority: deployment > model > model_id > model_name\n            if hasattr(embedding_obj, \"deployment\") and embedding_obj.deployment:\n                return str(embedding_obj.deployment)\n            if hasattr(embedding_obj, \"model\") and embedding_obj.model:\n                return str(embedding_obj.model)\n            if hasattr(embedding_obj, \"model_id\") and embedding_obj.model_id:\n                return str(embedding_obj.model_id)\n            if hasattr(embedding_obj, \"model_name\") and embedding_obj.model_name:\n                return str(embedding_obj.model_name)\n\n        # Try to get from embedding component (legacy single embedding)\n        if hasattr(self, \"embedding\") and self.embedding:\n            # Handle list of embeddings\n            if isinstance(self.embedding, list) and len(self.embedding) > 0:\n                first_emb = self.embedding[0]\n                if hasattr(first_emb, \"deployment\") and first_emb.deployment:\n                    return str(first_emb.deployment)\n                if hasattr(first_emb, \"model\") and first_emb.model:\n                    return str(first_emb.model)\n                if hasattr(first_emb, \"model_id\") and first_emb.model_id:\n                    return str(first_emb.model_id)\n                if hasattr(first_emb, \"model_name\") and first_emb.model_name:\n                    return str(first_emb.model_name)\n            # Handle single embedding\n            elif not isinstance(self.embedding, list):\n                if hasattr(self.embedding, \"deployment\") and self.embedding.deployment:\n                    return str(self.embedding.deployment)\n                if hasattr(self.embedding, \"model\") and self.embedding.model:\n                    return str(self.embedding.model)\n                if hasattr(self.embedding, \"model_id\") and self.embedding.model_id:\n                    return str(self.embedding.model_id)\n                if hasattr(self.embedding, \"model_name\") and self.embedding.model_name:\n                    return str(self.embedding.model_name)\n\n        msg = (\n            \"Could not determine embedding model name. \"\n            \"Please set the 'embedding_model_name' field or ensure the embedding component \"\n            \"has a 'deployment', 'model', 'model_id', or 'model_name' attribute.\"\n        )\n        raise ValueError(msg)\n\n    # ---------- helper functions for index management ----------\n    def _default_text_mapping(\n        self,\n        dim: int,\n        engine: str = \"jvector\",\n        space_type: str = \"l2\",\n        ef_search: int = 512,\n        ef_construction: int = 100,\n        m: int = 16,\n        vector_field: str = \"vector_field\",\n    ) -> dict[str, Any]:\n        \"\"\"Create the default OpenSearch index mapping for vector search.\n\n        This method generates the index configuration with k-NN settings optimized\n        for approximate nearest neighbor search using the specified vector engine.\n        Includes the embedding_model keyword field for tracking which model was used.\n\n        Args:\n            dim: Dimensionality of the vector embeddings\n            engine: Vector search engine (jvector, nmslib, faiss, lucene)\n            space_type: Distance metric for similarity calculation\n            ef_search: Size of dynamic list used during search\n            ef_construction: Size of dynamic list used during index construction\n            m: Number of bidirectional links for each vector\n            vector_field: Name of the field storing vector embeddings\n\n        Returns:\n            Dictionary containing OpenSearch index mapping configuration\n        \"\"\"\n        return {\n            \"settings\": {\"index\": {\"knn\": True, \"knn.algo_param.ef_search\": ef_search}},\n            \"mappings\": {\n                \"properties\": {\n                    vector_field: {\n                        \"type\": \"knn_vector\",\n                        \"dimension\": dim,\n                        \"method\": {\n                            \"name\": \"disk_ann\",\n                            \"space_type\": space_type,\n                            \"engine\": engine,\n                            \"parameters\": {\"ef_construction\": ef_construction, \"m\": m},\n                        },\n                    },\n                    \"embedding_model\": {\"type\": \"keyword\"},  # Track which model was used\n                    \"embedding_provider\": {\"type\": \"keyword\"},\n                    \"embedding_space_id\": {\"type\": \"keyword\"},\n                    \"embedding_dimensions\": {\"type\": \"integer\"},\n                }\n            },\n        }\n\n    def _ensure_embedding_field_mapping(\n        self,\n        client: OpenSearch,\n        index_name: str,\n        field_name: str,\n        dim: int,\n        engine: str,\n        space_type: str,\n        ef_construction: int,\n        m: int,\n    ) -> None:\n        \"\"\"Lazily add a dynamic embedding field to the index if it doesn't exist.\n\n        This allows adding new embedding models without recreating the entire index.\n        Also ensures the embedding_model tracking field exists.\n\n        Note: Some OpenSearch versions/configurations have issues with dynamically adding\n        knn_vector mappings (NullPointerException). This method checks if the field\n        already exists before attempting to add it, and gracefully skips if the field\n        is already properly configured.\n\n        Args:\n            client: OpenSearch client instance\n            index_name: Target index name\n            field_name: Dynamic field name for this embedding model\n            dim: Vector dimensionality\n            engine: Vector search engine\n            space_type: Distance metric\n            ef_construction: Construction parameter\n            m: HNSW parameter\n        \"\"\"\n        # First, check if the field already exists and is properly mapped\n        properties = self._get_index_properties(client)\n        if self._is_knn_vector_field(properties, field_name):\n            # Field already exists as knn_vector - verify dimensions match\n            existing_dim = self._get_field_dimension(properties, field_name)\n            if existing_dim is not None and existing_dim != dim:\n                logger.warning(\n                    f\"Field '{field_name}' exists with dimension {existing_dim}, \"\n                    f\"but current embedding has dimension {dim}. Using existing mapping.\"\n                )\n            else:\n                logger.info(\n                    f\"[OpenSearchMultimodel] Field '{field_name}' already exists\"\n                    f\"as knn_vector with matching dimensions - skipping mapping update\"\n                )\n            return\n\n        # Field doesn't exist, try to add the mapping\n        try:\n            mapping = {\n                \"properties\": {\n                    field_name: {\n                        \"type\": \"knn_vector\",\n                        \"dimension\": dim,\n                        \"method\": {\n                            \"name\": \"disk_ann\",\n                            \"space_type\": space_type,\n                            \"engine\": engine,\n                            \"parameters\": {\"ef_construction\": ef_construction, \"m\": m},\n                        },\n                    },\n                    # Also ensure the embedding_model tracking field exists as keyword\n                    \"embedding_model\": {\"type\": \"keyword\"},\n                    \"embedding_provider\": {\"type\": \"keyword\"},\n                    \"embedding_space_id\": {\"type\": \"keyword\"},\n                    \"embedding_dimensions\": {\"type\": \"integer\"},\n                }\n            }\n            client.indices.put_mapping(index=index_name, body=mapping)\n            logger.info(f\"Added/updated embedding field mapping: {field_name}\")\n        except RequestError as e:\n            error_str = str(e).lower()\n            if \"invalid engine\" in error_str and \"jvector\" in error_str:\n                msg = (\n                    \"The 'jvector' engine is not available in your OpenSearch installation. \"\n                    \"Use 'nmslib' or 'faiss' for standard OpenSearch, or upgrade to OpenSearch 2.9+.\"\n                )\n                raise ValueError(msg) from e\n            if \"index.knn\" in error_str:\n                msg = (\n                    \"The index has index.knn: false. Delete the existing index and let the \"\n                    \"component recreate it, or create a new index with a different name.\"\n                )\n                raise ValueError(msg) from e\n            raise\n        except Exception as e:\n            # Check if this is the known OpenSearch k-NN NullPointerException issue\n            error_str = str(e).lower()\n            if \"null\" in error_str or \"nullpointerexception\" in error_str:\n                logger.warning(\n                    f\"[OpenSearchMultimodel] Could not add embedding field mapping for {field_name}\"\n                    f\"due to OpenSearch k-NN plugin issue: {e}. \"\n                    f\"This is a known issue with some OpenSearch versions. \"\n                    f\"[OpenSearchMultimodel] Skipping mapping update. \"\n                    f\"Please ensure the index has the correct mapping for KNN search to work.\"\n                )\n                # Skip and continue - ingestion will proceed, but KNN search may fail if mapping doesn't exist\n                return\n            logger.warning(\n                f\"[OpenSearchMultimodel] Could not add embedding field mapping for {field_name}: {e}\"\n            )\n            raise\n\n        # Verify the field was added correctly\n        properties = self._get_index_properties(client)\n        if not self._is_knn_vector_field(properties, field_name):\n            msg = f\"Field '{field_name}' is not mapped as knn_vector. Current mapping: {properties.get(field_name)}\"\n            logger.error(msg)\n            raise ValueError(msg)\n\n    def _validate_aoss_with_engines(self, *, is_aoss: bool, engine: str) -> None:\n        \"\"\"Validate engine compatibility with Amazon OpenSearch Serverless (AOSS).\n\n        Amazon OpenSearch Serverless has restrictions on which vector engines\n        can be used. This method ensures the selected engine is compatible.\n\n        Args:\n            is_aoss: Whether the connection is to Amazon OpenSearch Serverless\n            engine: The selected vector search engine\n\n        Raises:\n            ValueError: If AOSS is used with an incompatible engine\n        \"\"\"\n        if is_aoss and engine not in {\"nmslib\", \"faiss\"}:\n            msg = \"Amazon OpenSearch Service Serverless only supports `nmslib` or `faiss` engines\"\n            raise ValueError(msg)\n\n    def _is_aoss_enabled(self, http_auth: Any) -> bool:\n        \"\"\"Determine if Amazon OpenSearch Serverless (AOSS) is being used.\n\n        Args:\n            http_auth: The HTTP authentication object\n\n        Returns:\n            True if AOSS is enabled, False otherwise\n        \"\"\"\n        return (\n            http_auth is not None and hasattr(http_auth, \"service\") and http_auth.service == \"aoss\"\n        )\n\n    @staticmethod\n    def _openrag_input_to_str(value: Any) -> str:\n        if value is None:\n            return \"\"\n        if hasattr(value, \"get_secret_value\"):\n            value = value.get_secret_value()\n        if hasattr(value, \"text\"):\n            value = value.text\n        return str(value or \"\").strip()\n\n    def _openrag_callback_value(self, attr_name: str) -> str:\n        value = self._openrag_input_to_str(getattr(self, attr_name, \"\"))\n        if value == self._openrag_ingest_global_placeholders.get(attr_name):\n            return \"\"\n        return value\n\n    def _openrag_ingest_callback_config(self) -> tuple[str, str, str] | None:\n        url = self._openrag_callback_value(\"openrag_ingest_url\")\n        token = self._openrag_callback_value(\"openrag_ingest_token\")\n        ingest_run_id = self._openrag_callback_value(\"openrag_ingest_run_id\")\n\n        if not url and not token and not ingest_run_id:\n            return None\n        if not url or not token or not ingest_run_id:\n            msg = \"OpenRAG ingest callback requires url, token, and ingest_run_id.\"\n            raise ValueError(msg)\n\n        logger.debug(\n            \"[OpenRAG callback config] configured for ingest_run_id=%s (url_len=%d, token_len=%d)\",\n            ingest_run_id,\n            len(url),\n            len(token),\n        )\n        return url, token, ingest_run_id\n\n    def _post_openrag_ingest_batches(\n        self,\n        *,\n        requests: list[dict],\n        vector_field: str,\n        text_field: str,\n    ) -> None:\n        callback_config = self._openrag_ingest_callback_config()\n        if callback_config is None:\n            return\n\n        url, token, ingest_run_id = callback_config\n        batch_size = max(self._parse_int_param(\"openrag_ingest_batch_size\", 100), 1)\n        timeout = self._parse_int_param(\"request_timeout\", REQUEST_TIMEOUT)\n        headers = {\"Authorization\": f\"Bearer {token}\"}\n\n        logger.debug(\n            f\"[OpenRAG ingest POST] total_chunks={len(requests)} batch_size={batch_size} timeout_s={timeout}\"\n        )\n\n        with httpx.Client(timeout=timeout) as client:\n            total_batches = (len(requests) + batch_size - 1) // batch_size\n            for batch_number, start in enumerate(range(0, len(requests), batch_size), start=1):\n                batch = requests[start : start + batch_size]\n                final = batch_number == total_batches\n                payload = {\n                    \"ingest_run_id\": ingest_run_id,\n                    \"batch_id\": batch_number,\n                    \"final\": final,\n                    \"chunks\": [\n                        self._openrag_chunk_payload(\n                            request,\n                            vector_field=vector_field,\n                            text_field=text_field,\n                        )\n                        for request in batch\n                    ],\n                }\n                logger.debug(\n                    f\"[OpenRAG ingest POST] -> batch={batch_number}/{total_batches} \"\n                    f\"chunks={len(payload['chunks'])} final={final}\"\n                )\n                response = client.post(url, json=payload, headers=headers)\n                logger.debug(\n                    f\"[OpenRAG ingest POST resp] batch={batch_number} status={response.status_code}\"\n                )\n                if response.status_code >= 400:\n                    msg = (\n                        \"OpenRAG ingest callback failed \"\n                        f\"(batch={batch_number}, status={response.status_code})\"\n                    )\n                    logger.warning(msg)\n                    raise RuntimeError(msg)\n\n        logger.debug(f\"Posted {len(requests)} chunks to OpenRAG backend ingest callback.\")\n\n    @staticmethod\n    def _openrag_chunk_payload(\n        request: dict,\n        *,\n        vector_field: str,\n        text_field: str,\n    ) -> dict:\n        metadata = {\n            key: value\n            for key, value in request.items()\n            if key not in {\"_op_type\", \"_index\", \"_id\", \"id\", vector_field, text_field}\n        }\n        page = metadata.get(\"page\")\n        if isinstance(page, str) and page.isdigit():\n            page = int(page)\n        return {\n            \"id\": request.get(\"_id\") or request.get(\"id\"),\n            \"text\": request.get(text_field, \"\"),\n            \"vector\": request[vector_field],\n            \"page\": page if isinstance(page, int) else None,\n            \"metadata\": metadata,\n        }\n\n    def _bulk_ingest_embeddings(\n        self,\n        client: OpenSearch,\n        index_name: str,\n        embeddings: list[list[float]],\n        texts: list[str],\n        metadatas: list[dict] | None = None,\n        ids: list[str] | None = None,\n        vector_field: str = \"vector_field\",\n        text_field: str = \"text\",\n        embedding_model: str = \"unknown\",\n        embedding_provider: str | None = None,\n        embedding_space_id: str | None = None,\n        mapping: dict | None = None,\n        max_chunk_bytes: int | None = 1 * 1024 * 1024,\n        *,\n        is_aoss: bool = False,\n    ) -> list[str]:\n        \"\"\"Efficiently ingest multiple documents with embeddings into OpenSearch.\n\n        This method uses bulk operations to insert documents with their vector\n        embeddings and metadata into the specified OpenSearch index. Each document\n        is tagged with the embedding_model name for tracking.\n\n        Args:\n            client: OpenSearch client instance\n            index_name: Target index for document storage\n            embeddings: List of vector embeddings for each document\n            texts: List of document texts\n            metadatas: Optional metadata dictionaries for each document\n            ids: Optional document IDs (UUIDs generated if not provided)\n            vector_field: Field name for storing vector embeddings\n            text_field: Field name for storing document text\n            embedding_model: Name of the embedding model used\n            embedding_provider: Exact provider key, when known\n            embedding_space_id: Provider-qualified vector-space identity\n            mapping: Optional index mapping configuration\n            max_chunk_bytes: Maximum size per bulk request chunk\n            is_aoss: Whether using Amazon OpenSearch Serverless\n\n        Returns:\n            List of document IDs that were successfully ingested\n        \"\"\"\n        logger.debug(f\"[OpenSearchMultimodel] Bulk ingesting embeddings for {index_name}\")\n        if not mapping:\n            mapping = {}\n\n        requests = []\n        return_ids = []\n        vector_dimensions = len(embeddings[0]) if embeddings else None\n\n        for i, text in enumerate(texts):\n            metadata = metadatas[i] if metadatas else {}\n            if vector_dimensions is not None and \"embedding_dimensions\" not in metadata:\n                metadata = {**metadata, \"embedding_dimensions\": vector_dimensions}\n\n            # Normalize ACL fields that may arrive as JSON strings from flows\n            for key in (\"allowed_users\", \"allowed_groups\", \"allowed_principals\"):\n                value = metadata.get(key)\n                if isinstance(value, str):\n                    try:\n                        parsed = json.loads(value)\n                        if isinstance(parsed, list):\n                            metadata[key] = parsed\n                    except (json.JSONDecodeError, TypeError):\n                        # Leave value as-is if it isn't valid JSON\n                        pass\n\n            metadata_document_id = str(metadata.get(\"document_id\") or \"\").strip()\n            if metadata_document_id and metadata_document_id.lower() != \"none\":\n                generated_id = f\"{metadata_document_id}_{i}\"\n            else:\n                generated_id = str(uuid.uuid4())\n            _id = ids[i] if ids else generated_id\n            request = {\n                \"_op_type\": \"index\",\n                \"_index\": index_name,\n                vector_field: embeddings[i],\n                text_field: text,\n                \"embedding_model\": embedding_model,  # Track which model was used\n                **metadata,\n            }\n            if embedding_provider:\n                request[\"embedding_provider\"] = embedding_provider\n            if embedding_space_id:\n                request[\"embedding_space_id\"] = embedding_space_id\n            if is_aoss:\n                request[\"id\"] = _id\n            else:\n                request[\"_id\"] = _id\n            requests.append(request)\n            return_ids.append(_id)\n        if metadatas:\n            self.log(f\"Sample metadata: {metadatas[0] if metadatas else {}}\")\n        if self._openrag_ingest_callback_config() is not None:\n            self._post_openrag_ingest_batches(\n                requests=requests,\n                vector_field=vector_field,\n                text_field=text_field,\n            )\n            return return_ids\n        try:\n            helpers.bulk(client, requests, max_chunk_bytes=max_chunk_bytes)\n        except Exception as bulk_error:\n            if \"Unsupported request type for filter level DLS\" not in str(bulk_error):\n                raise\n            logger.warning(\n                \"[OpenSearchMultimodel] Bulk ingest is blocked by filter-level DLS; \"\n                \"falling back to per-document index requests.\"\n            )\n            self._index_embeddings_individually(client, requests)\n        return return_ids\n\n    def _index_embeddings_individually(\n        self,\n        client: OpenSearch,\n        requests: list[dict],\n    ) -> None:\n        \"\"\"Index documents one at a time when OpenSearch DLS rejects bulk writes.\"\"\"\n        for request in requests:\n            document_id = request.get(\"_id\") or request.get(\"id\")\n            body = {\n                key: value\n                for key, value in request.items()\n                if key not in {\"_op_type\", \"_index\", \"_id\", \"id\"}\n            }\n            client.index(index=request[\"_index\"], id=document_id, body=body)\n\n    def _log_index_admin_skip(self, operation: str, error: Exception) -> None:\n        \"\"\"Log index-admin operations that may be blocked under filter-level DLS.\"\"\"\n        logger.warning(\n            f\"[OpenSearchMultimodel] Could not run index-admin operation '{operation}': {error}. \"\n            \"Assuming the backend pre-created the required index/mapping and continuing.\"\n        )\n\n    # ---------- param helpers ----------\n    def _parse_int_param(self, attr_name: str, default: int) -> int:\n        \"\"\"Parse a string attribute to int, returning *default* on failure.\"\"\"\n        raw = getattr(self, attr_name, None)\n        if raw is None or str(raw).strip() == \"\":\n            return default\n        try:\n            value = int(str(raw).strip())\n        except ValueError:\n            logger.warning(\n                f\"Invalid integer value '{raw}' for {attr_name}, using default {default}\"\n            )\n            return default\n\n        if value < 0:\n            logger.warning(f\"Negative value '{raw}' for {attr_name}, using default {default}\")\n            return default\n\n        return value\n\n    # ---------- auth / client ----------\n    def _build_auth_kwargs(self) -> dict[str, Any]:\n        \"\"\"Build authentication configuration for OpenSearch client.\n\n        Constructs the appropriate authentication parameters based on the\n        selected auth mode (basic username/password or JWT token).\n\n        Returns:\n            Dictionary containing authentication configuration\n\n        Raises:\n            ValueError: If required authentication parameters are missing\n        \"\"\"\n        mode = (self.auth_mode or \"basic\").strip().lower()\n        if mode == \"jwt\":\n            token = (self.jwt_token or \"\").strip()\n            if not token:\n                msg = \"Auth Mode is 'jwt' but no jwt_token was provided.\"\n                raise ValueError(msg)\n            header_name = (self.jwt_header or \"Authorization\").strip()\n            header_value = f\"Bearer {token}\" if self.bearer_prefix else token\n            return {\"headers\": {header_name: header_value}}\n        if mode == \"openrag\":\n            # Writes are delegated to the OpenRAG backend ingest callback,\n            # so no direct OpenSearch credentials are needed. Only the\n            # OPENRAG_* fields are required for ingestion to function.\n            url = self._openrag_callback_value(\"openrag_ingest_url\")\n            token = self._openrag_callback_value(\"openrag_ingest_token\")\n            ingest_run_id = self._openrag_callback_value(\"openrag_ingest_run_id\")\n            missing = [\n                name\n                for name, value in (\n                    (\"openrag_ingest_url\", url),\n                    (\"openrag_ingest_token\", token),\n                    (\"openrag_ingest_run_id\", ingest_run_id),\n                )\n                if not (value or \"\").strip()\n            ]\n            if missing:\n                msg = (\n                    \"Auth Mode is 'openrag' but required OPENRAG_* fields are \"\n                    f\"missing: {', '.join(missing)}.\"\n                )\n                raise ValueError(msg)\n            return {}\n        user = (self.username or \"\").strip()\n        pwd = (self._openrag_input_to_str(self.password) or \"\").strip()\n        if pwd == \"OPENSEARCH_PASSWORD\" or not pwd:\n            from config.settings import get_opensearch_password\n\n            pwd = get_opensearch_password() or \"\"\n        if not user or not pwd:\n            msg = \"Auth Mode is 'basic' but username/password are missing.\"\n            raise ValueError(msg)\n        return {\"http_auth\": (user, pwd)}\n\n    def build_client(self) -> OpenSearch:\n        \"\"\"Create and configure an OpenSearch client instance.\n\n        Returns:\n            Configured OpenSearch client ready for operations\n        \"\"\"\n        logger.debug(\"[OpenSearchMultimodel] Building OpenSearch client\")\n        auth_kwargs = self._build_auth_kwargs()\n        return OpenSearch(\n            hosts=[self.opensearch_url],\n            use_ssl=self.use_ssl,\n            verify_certs=self.verify_certs,\n            ssl_assert_hostname=False,\n            ssl_show_warn=False,\n            timeout=self._parse_int_param(\"request_timeout\", REQUEST_TIMEOUT),\n            max_retries=self._parse_int_param(\"max_retries\", MAX_RETRIES),\n            retry_on_timeout=True,\n            **auth_kwargs,\n        )\n\n    @check_cached_vector_store\n    def build_vector_store(self) -> OpenSearch:\n        # Return raw OpenSearch client as our \"vector store.\"\n        client = self.build_client()\n\n        # Check if we're in ingestion-only mode (no search query)\n        has_search_query = bool((self.search_query or \"\").strip())\n        if not has_search_query:\n            logger.debug(\n                \"[OpenSearchMultimodel] Ingestion-only mode activated: search operations will be skipped\"\n            )\n            logger.debug(\"[OpenSearchMultimodel] Starting ingestion mode...\")\n\n        logger.debug(f\"[OpenSearchMultimodel] Embedding: {self.embedding}\")\n        self._add_documents_to_vector_store(client=client)\n        return client\n\n    # ---------- ingest ----------\n    def _add_documents_to_vector_store(self, client: OpenSearch) -> None:\n        \"\"\"Process and ingest documents into the OpenSearch vector store.\n\n        This method handles the complete document ingestion pipeline:\n        - Prepares document data and metadata\n        - Generates vector embeddings using the selected model\n        - Creates appropriate index mappings with dynamic field names\n        - Bulk inserts documents with vectors and model tracking\n\n        Args:\n            client: OpenSearch client for performing operations\n        \"\"\"\n        logger.debug(\"[OpenSearchMultimodel][INGESTION] _add_documents_to_vector_store called\")\n        # Convert DataFrame to Data if needed using parent's method\n        self.ingest_data = self._prepare_ingest_data()\n\n        logger.debug(\n            f\"[OpenSearchMultimodel][INGESTION] ingest_data type: \"\n            f\"{type(self.ingest_data)}, length: {len(self.ingest_data) if self.ingest_data else 0}\"\n        )\n        logger.debug(\n            f\"[OpenSearchMultimodel][INGESTION] ingest_data content: \"\n            f\"{self.ingest_data[:2] if self.ingest_data and len(self.ingest_data) > 0 else 'empty'}\"\n        )\n\n        docs = self.ingest_data or []\n        if not docs:\n            logger.debug(\"Ingestion complete: No documents provided\")\n            return\n\n        if not self.embedding:\n            msg = \"Embedding handle is required to embed documents.\"\n            raise ValueError(msg)\n\n        # Normalize embedding to list first\n        embeddings_list = self.embedding if isinstance(self.embedding, list) else [self.embedding]\n\n        # Filter out None values (fail-safe mode) - do this BEFORE checking if empty\n        embeddings_list = [e for e in embeddings_list if e is not None]\n\n        # NOW check if we have any valid embeddings left after filtering\n        if not embeddings_list:\n            logger.warning(\n                \"All embeddings returned None (fail-safe mode enabled). Skipping document ingestion.\"\n            )\n            self.log(\n                \"Embedding returned None (fail-safe mode enabled). Skipping document ingestion.\"\n            )\n            return\n\n        logger.debug(\n            f\"[OpenSearchMultimodel][INGESTION] Valid embeddings after filtering: {len(embeddings_list)}\"\n        )\n        self.log(\n            f\"[OpenSearchMultimodel][INGESTION] Available embedding models: {len(embeddings_list)}\"\n        )\n\n        # Select the embedding to use for ingestion\n        selected_embedding = None\n        embedding_model = None\n\n        # If embedding_model_name is specified, find matching embedding\n        if (\n            hasattr(self, \"embedding_model_name\")\n            and self.embedding_model_name\n            and self.embedding_model_name.strip()\n        ):\n            target_model_name = self.embedding_model_name.strip()\n            self.log(f\"Looking for embedding model: {target_model_name}\")\n\n            for emb_obj in embeddings_list:\n                # Check all possible model identifiers (deployment, model, model_id, model_name)\n                # Also check available_models list from EmbeddingsWithModels\n                possible_names = []\n                deployment = getattr(emb_obj, \"deployment\", None)\n                model = getattr(emb_obj, \"model\", None)\n                model_id = getattr(emb_obj, \"model_id\", None)\n                model_name = getattr(emb_obj, \"model_name\", None)\n                available_models_attr = getattr(emb_obj, \"available_models\", None)\n\n                if deployment:\n                    possible_names.append(str(deployment))\n                if model:\n                    possible_names.append(str(model))\n                if model_id:\n                    possible_names.append(str(model_id))\n                if model_name:\n                    possible_names.append(str(model_name))\n\n                # Also add combined identifier\n                if deployment and model and deployment != model:\n                    possible_names.append(f\"{deployment}:{model}\")\n\n                # Add all models from available_models dict\n                if available_models_attr and isinstance(available_models_attr, dict):\n                    possible_names.extend(\n                        str(model_key).strip()\n                        for model_key in available_models_attr\n                        if model_key and str(model_key).strip()\n                    )\n\n                # Match if target matches any of the possible names\n                if target_model_name in possible_names:\n                    # Check if target is in available_models dict - use dedicated instance\n                    if (\n                        available_models_attr\n                        and isinstance(available_models_attr, dict)\n                        and target_model_name in available_models_attr\n                    ):\n                        # Use the dedicated embedding instance from the dict\n                        selected_embedding = available_models_attr[target_model_name]\n                        embedding_model = target_model_name\n                        self.log(\n                            f\"Found dedicated embedding instance for '{embedding_model}' in available_models dict\"\n                        )\n                    else:\n                        # Traditional identifier match\n                        selected_embedding = emb_obj\n                        embedding_model = self._get_embedding_model_name(emb_obj)\n                        self.log(\n                            f\"Found matching embedding model: {embedding_model} (matched on: {target_model_name})\"\n                        )\n                    break\n\n            if not selected_embedding:\n                # Build detailed list of available embeddings with all their identifiers\n                available_info = []\n                for idx, emb in enumerate(embeddings_list):\n                    emb_type = type(emb).__name__\n                    identifiers = []\n                    deployment = getattr(emb, \"deployment\", None)\n                    model = getattr(emb, \"model\", None)\n                    model_id = getattr(emb, \"model_id\", None)\n                    model_name = getattr(emb, \"model_name\", None)\n                    available_models_attr = getattr(emb, \"available_models\", None)\n\n                    if deployment:\n                        identifiers.append(f\"deployment='{deployment}'\")\n                    if model:\n                        identifiers.append(f\"model='{model}'\")\n                    if model_id:\n                        identifiers.append(f\"model_id='{model_id}'\")\n                    if model_name:\n                        identifiers.append(f\"model_name='{model_name}'\")\n\n                    # Add combined identifier as an option\n                    if deployment and model and deployment != model:\n                        identifiers.append(f\"combined='{deployment}:{model}'\")\n\n                    # Add available_models dict if present\n                    if available_models_attr and isinstance(available_models_attr, dict):\n                        identifiers.append(f\"available_models={list(available_models_attr.keys())}\")\n\n                    available_info.append(\n                        f\"  [{idx}] {emb_type}: {', '.join(identifiers) if identifiers else 'No identifiers'}\"\n                    )\n\n                msg = (\n                    f\"Embedding model '{target_model_name}' not found in available embeddings.\\n\\n\"\n                    f\"Available embeddings:\\n\" + \"\\n\".join(available_info) + \"\\n\\n\"\n                    \"Please set 'embedding_model_name' to one of the identifier values shown above \"\n                    \"(use the value after the '=' sign, without quotes).\\n\"\n                    \"For duplicate deployments, use the 'combined' format.\\n\"\n                    \"Or leave it empty to use the first embedding.\"\n                )\n                raise ValueError(msg)\n        else:\n            # Use first embedding if no model name specified\n            selected_embedding = embeddings_list[0]\n            embedding_model = self._get_embedding_model_name(selected_embedding)\n            self.log(f\"No embedding_model_name specified, using first embedding: {embedding_model}\")\n\n        embedding_provider = self._openrag_input_to_str(\n            getattr(self, \"embedding_provider_name\", \"\")\n        ).lower()\n        if embedding_provider == SELECTED_EMBEDDING_PROVIDER_VAR.lower():\n            embedding_provider = \"\"\n        embedding_space_id = (\n            f\"{embedding_provider}:{embedding_model}\" if embedding_provider else None\n        )\n        dynamic_field_name = get_embedding_field_name(embedding_space_id or embedding_model)\n\n        logger.info(f\"Selected embedding model for ingestion: '{embedding_model}'\")\n        self.log(f\"Using embedding model for ingestion: {embedding_model}\")\n        self.log(f\"Dynamic vector field: {dynamic_field_name}\")\n\n        # Log embedding details for debugging\n        if hasattr(selected_embedding, \"deployment\"):\n            logger.info(f\"Embedding deployment: {selected_embedding.deployment}\")\n        if hasattr(selected_embedding, \"model\"):\n            logger.info(f\"Embedding model: {selected_embedding.model}\")\n        if hasattr(selected_embedding, \"model_id\"):\n            logger.info(f\"Embedding model_id: {selected_embedding.model_id}\")\n        if hasattr(selected_embedding, \"dimensions\"):\n            logger.info(f\"Embedding dimensions: {selected_embedding.dimensions}\")\n        if hasattr(selected_embedding, \"available_models\"):\n            logger.info(f\"Embedding available_models: {selected_embedding.available_models}\")\n\n        # No model switching needed - each model in available_models has its own dedicated instance\n        # The selected_embedding is already configured correctly for the target model\n        logger.info(\n            f\"Using embedding instance for '{embedding_model}' - pre-configured and ready to use\"\n        )\n\n        # Extract texts and metadata from documents\n        texts = []\n        metadatas = []\n        # Process docs_metadata table input into a dict\n        additional_metadata = {}\n        logger.debug(f\"[LF] Docs metadata {self.docs_metadata}\")\n        if hasattr(self, \"docs_metadata\") and self.docs_metadata:\n            logger.info(f\"[LF] Docs metadata {self.docs_metadata}\")\n            if isinstance(self.docs_metadata[-1], Data):\n                logger.info(f\"[LF] Docs metadata is a Data object {self.docs_metadata}\")\n                self.docs_metadata = self.docs_metadata[-1].data\n                logger.info(f\"[LF] Docs metadata is a Data object {self.docs_metadata}\")\n                additional_metadata.update(self.docs_metadata)\n            else:\n                for item in self.docs_metadata:\n                    if isinstance(item, dict) and \"key\" in item and \"value\" in item:\n                        additional_metadata[item[\"key\"]] = item[\"value\"]\n        # Replace string \"None\" values with actual None\n        for key, value in additional_metadata.items():\n            if value == \"None\":\n                additional_metadata[key] = None\n        logger.info(f\"[LF] Additional metadata {additional_metadata}\")\n        for doc_obj in docs:\n            data_copy = json.loads(doc_obj.model_dump_json())\n            text = data_copy.pop(doc_obj.text_key, doc_obj.default_value)\n            if isinstance(text, str):\n                text = text.translate(CJK_RADICAL_TABLE)\n            texts.append(text)\n\n            # Merge additional metadata from table input\n            data_copy.update(additional_metadata)\n\n            metadatas.append(data_copy)\n        self.log(metadatas)\n\n        # Determine whether the selected embedding is watsonx/IBM. The watsonx\n        # SDK ships its own rate-limit machinery (input batching, proactive\n        # x-requests-limit-* TokenBucket throttling, and jittered exponential\n        # backoff on 429), so we lean on it instead of retrying on top of it.\n        # The type-name check also covers watsonx-hosted, non-\"ibm/\" models\n        # (e.g. intfloat/multilingual-e5-large).\n        is_ibm = (embedding_model and \"ibm\" in str(embedding_model).lower()) or (\n            selected_embedding and \"watsonx\" in type(selected_embedding).__name__.lower()\n        )\n        logger.debug(f\"Is IBM/watsonx embedding: {is_ibm}\")\n\n        failed: set[int] = set()\n\n        if is_ibm:\n            # Hand the full batch to the SDK and let it batch/throttle/retry.\n            # Retry attempts and base backoff are tunable via the SDK's own\n            # WATSONX_MAX_RETRIES / WATSONX_DELAY_TIME environment variables.\n            logger.info(\n                f\"Embedding {len(texts)} chunks via watsonx SDK batch (SDK-managed throttle + 429 retry)\"\n            )\n            try:\n                vectors: list[list[float]] = selected_embedding.embed_documents(texts)\n                logger.info(f\"Successfully embedded {len(vectors)} chunks via watsonx SDK\")\n            except Exception as embed_error:\n                _log_watsonx_rate_limit_headers(embed_error)\n                logger.error(\n                    f\"Failed to embed {len(texts)} chunks via watsonx SDK. Error: {embed_error}\",\n                )\n                raise\n\n        else:\n            # Non-watsonx providers (OpenAI, Ollama) lack the watsonx SDK's\n            # built-in rate-limit handling, so embed per chunk in parallel with\n            # a generic rate-limit-aware tenacity retry.\n            vectors: list[list[float]] = [None] * len(texts)\n            from tenacity import (\n                retry,\n                retry_if_exception,\n                stop_after_attempt,\n                wait_exponential,\n            )\n\n            def is_rate_limit_error(exception: Exception) -> bool:\n                \"\"\"Check if exception is a rate limit error (429).\"\"\"\n                error_str = str(exception).lower()\n                return \"429\" in error_str or \"rate_limit\" in error_str or \"rate limit\" in error_str\n\n            def is_other_retryable_error(exception: Exception) -> bool:\n                \"\"\"Check if exception is a transient network error worth retrying.\"\"\"\n                if is_rate_limit_error(exception):\n                    return False\n                return isinstance(exception, (ConnectionError, TimeoutError, OSError))\n\n            # Retry decorator for rate limit errors (longer backoff)\n            retry_on_rate_limit = retry(\n                retry=retry_if_exception(is_rate_limit_error),\n                stop=stop_after_attempt(5),\n                wait=wait_exponential(multiplier=2, min=2, max=30),\n                reraise=True,\n                before_sleep=lambda retry_state: logger.warning(\n                    f\"Rate limit hit for chunk (attempt {retry_state.attempt_number}/5), \"\n                    f\"backing off for {retry_state.next_action.sleep:.1f}s\"\n                ),\n            )\n\n            # Retry decorator for other errors (shorter backoff)\n            retry_on_other_errors = retry(\n                retry=retry_if_exception(is_other_retryable_error),\n                stop=stop_after_attempt(3),\n                wait=wait_exponential(multiplier=1, min=1, max=8),\n                reraise=True,\n                before_sleep=lambda retry_state: logger.warning(\n                    f\"Error embedding chunk (attempt {retry_state.attempt_number}/3), \"\n                    f\"retrying in {retry_state.next_action.sleep:.1f}s: {retry_state.outcome.exception()}\"\n                ),\n            )\n\n            def embed_chunk_with_retry(chunk_text: str, chunk_idx: int) -> list[float]:\n                \"\"\"Embed a single chunk with rate-limit-aware retry logic.\"\"\"\n\n                @retry_on_rate_limit\n                @retry_on_other_errors\n                def _embed(text: str) -> list[float]:\n                    return selected_embedding.embed_documents([text])[0]\n\n                try:\n                    return _embed(chunk_text)\n                except Exception as e:\n                    logger.error(\n                        f\"Failed to embed chunk {chunk_idx} after all retries: {e}\",\n                        error=str(e),\n                    )\n                    raise\n\n            max_workers = min(max(len(texts), 1), 8)\n            logger.debug(f\"Using parallel processing with {max_workers} workers\")\n\n            with ThreadPoolExecutor(max_workers=max_workers) as executor:\n                futures = {\n                    executor.submit(embed_chunk_with_retry, chunk, idx): idx\n                    for idx, chunk in enumerate(texts)\n                }\n                for future in as_completed(futures):\n                    idx = futures[future]\n                    try:\n                        vectors[idx] = future.result()\n                    except Exception as e:  # noqa: BLE001\n                        logger.error(\n                            f\"Embedding failed for chunk {idx}, skipping: {e}\",\n                            error=str(e),\n                        )\n                        failed.add(idx)\n\n            if failed:\n                # Abort before any write. Direct writes carry no ingest_run_id,\n                # so backend cleanup could not remove survivors, and a partial\n                # document would stay searchable and be mistaken for a duplicate.\n                msg = (\n                    f\"Embedding failed for {len(failed)} of {len(texts)} chunks with model \"\n                    f\"'{embedding_model}' (chunk indices: {sorted(failed)}); \"\n                    \"aborting ingestion so no partial document is indexed.\"\n                )\n                self.log(msg)\n                raise RuntimeError(msg)\n\n        if not vectors:\n            # Empty input batch — nothing to ingest, return normally.\n            self.log(f\"No vectors generated from documents for model {embedding_model}.\")\n            return\n\n        # Get vector dimension for mapping\n        dim = len(vectors[0]) if vectors else 768  # default fallback\n        use_openrag_ingest_callback = self._openrag_ingest_callback_config() is not None\n\n        is_aoss = False\n        mapping: dict | None = None\n\n        engine = getattr(self, \"engine\", \"jvector\")\n\n        if use_openrag_ingest_callback:\n            self.log(\"Using OpenRAG backend ingest callback; skipping direct OpenSearch writes.\")\n        else:\n            # Check for AOSS\n            auth_kwargs = self._build_auth_kwargs()\n            is_aoss = self._is_aoss_enabled(auth_kwargs.get(\"http_auth\"))\n\n            # Validate engine with AOSS\n            self._validate_aoss_with_engines(is_aoss=is_aoss, engine=engine)\n\n            # Create mapping with proper KNN settings\n            space_type = getattr(self, \"space_type\", \"l2\")\n            ef_construction = getattr(self, \"ef_construction\", 512)\n            m = getattr(self, \"m\", 16)\n\n            mapping = self._default_text_mapping(\n                dim=dim,\n                engine=engine,\n                space_type=space_type,\n                ef_construction=ef_construction,\n                m=m,\n                vector_field=dynamic_field_name,  # Use dynamic field name\n            )\n\n            # Ensure index exists with baseline mapping (index.knn: true is required for vector search)\n            index_exists = True\n            try:\n                index_exists = bool(client.indices.exists(index=self.index_name))\n            except OpenSearchException as exists_error:\n                self._log_index_admin_skip(\"indices.exists\", exists_error)\n\n            try:\n                if not index_exists:\n                    self.log(f\"Creating index '{self.index_name}' with base mapping\")\n                    client.indices.create(index=self.index_name, body=mapping)\n            except RequestError as creation_error:\n                if creation_error.error == \"resource_already_exists_exception\":\n                    pass  # Index was created concurrently\n                else:\n                    error_msg = str(creation_error).lower()\n                    if \"invalid engine\" in error_msg or \"illegal_argument\" in error_msg:\n                        if \"jvector\" in error_msg:\n                            msg = (\n                                \"The 'jvector' engine is not available in your OpenSearch installation. \"\n                                \"Use 'nmslib' or 'faiss' for standard OpenSearch, or upgrade to 2.9+.\"\n                            )\n                            raise ValueError(msg) from creation_error\n                        if \"index.knn\" in error_msg:\n                            msg = (\n                                \"The index has index.knn: false. Delete the existing index and let the \"\n                                \"component recreate it, or create a new index with a different name.\"\n                            )\n                            raise ValueError(msg) from creation_error\n                    logger.warning(f\"Failed to create index '{self.index_name}': {creation_error}\")\n                    raise\n\n            # Ensure the dynamic field exists in the index\n            self._ensure_embedding_field_mapping(\n                client=client,\n                index_name=self.index_name,\n                field_name=dynamic_field_name,\n                dim=dim,\n                engine=engine,\n                space_type=space_type,\n                ef_construction=ef_construction,\n                m=m,\n            )\n\n        self.log(\n            f\"Indexing {len(texts)} documents into '{self.index_name}' with model '{embedding_model}'...\"\n        )\n        logger.info(f\"Will store embeddings in field: {dynamic_field_name}\")\n        logger.info(f\"Will tag documents with embedding_model: {embedding_model}\")\n\n        # Build stable document IDs from the chunk positions.\n        import uuid as _uuid\n\n        chunk_ids: list[str] = []\n        for i, m in enumerate(metadatas or [{}] * len(texts)):\n            doc_id = str(m.get(\"document_id\") or \"\").strip()\n            if doc_id and doc_id.lower() != \"none\":\n                chunk_ids.append(f\"{doc_id}_{i}\")\n            else:\n                chunk_ids.append(str(_uuid.uuid4()))\n\n        return_ids = self._bulk_ingest_embeddings(\n            client=client,\n            index_name=self.index_name,\n            embeddings=vectors,\n            texts=texts,\n            metadatas=metadatas,\n            ids=chunk_ids if chunk_ids else None,\n            vector_field=dynamic_field_name,  # Use dynamic field name\n            text_field=\"text\",\n            embedding_model=embedding_model,  # Track the model\n            embedding_provider=embedding_provider or None,\n            embedding_space_id=embedding_space_id,\n            mapping=mapping,\n            is_aoss=is_aoss,\n        )\n        self.log(metadatas)\n\n        logger.info(\n            f\"Ingestion complete: Successfully indexed {len(return_ids)} documents with model '{embedding_model}'\"\n        )\n        self.log(f\"Successfully indexed {len(return_ids)} documents with model {embedding_model}.\")\n\n    # ---------- helpers for filters ----------\n    def _is_placeholder_term(self, term_obj: dict) -> bool:\n        # term_obj like {\"filename\": \"__IMPOSSIBLE_VALUE__\"}\n        return any(v == \"__IMPOSSIBLE_VALUE__\" for v in term_obj.values())\n\n    @staticmethod\n    def _is_valid_range_clause(clause: Any) -> bool:\n        \"\"\"Return True for a single-field range clause with at least one bound.\"\"\"\n        if not isinstance(clause, dict) or not isinstance(clause.get(\"range\"), dict):\n            return False\n        range_obj = clause[\"range\"]\n        if len(range_obj) != 1:\n            return False\n        bounds = next(iter(range_obj.values()))\n        if not isinstance(bounds, dict):\n            return False\n        return any(\n            key in bounds and bounds[key] not in (None, \"\") for key in (\"gte\", \"gt\", \"lte\", \"lt\")\n        )\n\n    def _coerce_filter_clauses(self, filter_obj: dict | None) -> list[dict]:\n        \"\"\"Convert filter expressions into OpenSearch-compatible filter clauses.\n\n        This method accepts two filter formats and converts them to standardized\n        OpenSearch query clauses:\n\n        Format A - Explicit filters:\n        {\"filter\": [{\"term\": {\"field\": \"value\"}}, {\"terms\": {\"field\": [\"val1\", \"val2\"]}}],\n         \"limit\": 10, \"score_threshold\": 1.5}\n\n        Format B - Context-style mapping:\n        {\"data_sources\": [\"file1.pdf\"], \"document_types\": [\"pdf\"], \"owners\": [\"user1\"]}\n\n        Args:\n            filter_obj: Filter configuration dictionary or None\n\n        Returns:\n            List of OpenSearch filter clauses (term/terms/range objects)\n            Placeholder values with \"__IMPOSSIBLE_VALUE__\" are ignored\n        \"\"\"\n        if not filter_obj:\n            return []\n\n        # If it is a string, try to parse it once\n        if isinstance(filter_obj, str):\n            try:\n                filter_obj = json.loads(filter_obj)\n            except json.JSONDecodeError:\n                # Not valid JSON - treat as no filters\n                return []\n\n        # Case A: already an explicit list/dict under \"filter\"\n        if \"filter\" in filter_obj:\n            raw = filter_obj[\"filter\"]\n            if isinstance(raw, dict):\n                raw = [raw]\n            explicit_clauses: list[dict] = []\n            for f in raw or []:\n                if (\n                    \"term\" in f\n                    and isinstance(f[\"term\"], dict)\n                    and not self._is_placeholder_term(f[\"term\"])\n                ):\n                    explicit_clauses.append(f)\n                elif \"terms\" in f and isinstance(f[\"terms\"], dict):\n                    field, vals = next(iter(f[\"terms\"].items()))\n                    if isinstance(vals, list) and len(vals) > 0:\n                        explicit_clauses.append(f)\n                elif self._is_valid_range_clause(f):\n                    explicit_clauses.append(f)\n            return explicit_clauses\n\n        # Case B: convert context-style maps into clauses\n        field_mapping = {\n            \"data_sources\": \"filename\",\n            \"document_types\": \"mimetype\",\n            \"owners\": \"owner\",\n        }\n        context_clauses: list[dict] = []\n        for k, values in filter_obj.items():\n            if not isinstance(values, list):\n                continue\n            field = field_mapping.get(k, k)\n            if len(values) == 0:\n                # Match-nothing placeholder (kept to mirror your tool semantics)\n                context_clauses.append({\"term\": {field: \"__IMPOSSIBLE_VALUE__\"}})\n            elif len(values) == 1:\n                if values[0] != \"__IMPOSSIBLE_VALUE__\":\n                    context_clauses.append({\"term\": {field: values[0]}})\n            else:\n                context_clauses.append({\"terms\": {field: values}})\n        return context_clauses\n\n    def _parse_filter_expression(self) -> dict | None:\n        \"\"\"Parse and validate optional filter_expression JSON.\n\n        Returns:\n            Parsed JSON object as a dict, or None when unset/blank.\n\n        Raises:\n            ValueError: If JSON is invalid or does not decode to an object.\n        \"\"\"\n        filter_expression = getattr(self, \"filter_expression\", \"\")\n        if not isinstance(filter_expression, str) or not filter_expression.strip():\n            return None\n        try:\n            filter_obj = json.loads(filter_expression)\n        except json.JSONDecodeError as e:\n            msg = f\"Invalid filter_expression JSON: {e}\"\n            raise ValueError(msg) from e\n\n        if not isinstance(filter_obj, dict):\n            msg = \"Invalid filter_expression JSON type: expected a JSON object.\"\n            raise TypeError(msg)\n        return filter_obj\n\n    def _resolve_limit(self, filter_obj: dict | None, default_limit: int | None) -> int | None:\n        \"\"\"Resolve an integer result limit from filter settings.\"\"\"\n        if not filter_obj:\n            return default_limit\n        raw_limit = filter_obj.get(\"limit\", default_limit)\n        if raw_limit is None:\n            return None\n        if isinstance(raw_limit, bool):\n            msg = \"Invalid filter_expression.limit: expected a positive integer.\"\n            raise TypeError(msg)\n        try:\n            limit = int(raw_limit)\n        except (TypeError, ValueError) as e:\n            msg = \"Invalid filter_expression.limit: expected a positive integer.\"\n            raise ValueError(msg) from e\n        if limit <= 0:\n            msg = \"Invalid filter_expression.limit: expected a positive integer.\"\n            raise ValueError(msg)\n        return limit\n\n    def _resolve_score_threshold(self, filter_obj: dict | None) -> float | None:\n        \"\"\"Resolve optional positive min score from filter settings.\"\"\"\n        if not filter_obj:\n            return None\n        score_threshold = filter_obj.get(\"score_threshold\")\n        if score_threshold is None:\n            score_threshold = filter_obj.get(\"scoreThreshold\")\n        if not isinstance(score_threshold, (int, float)) or score_threshold <= 0:\n            return None\n        return float(score_threshold)\n\n    def _detect_available_models(\n        self, client: OpenSearch, filter_clauses: list[dict] | None = None\n    ) -> list[EmbeddingSpace]:\n        \"\"\"Detect which embedding models have documents in the index.\n\n        Uses aggregation to find all unique embedding_model values, optionally\n        filtered to only documents matching the user's filter criteria.\n\n        Args:\n            client: OpenSearch client instance\n            filter_clauses: Optional filter clauses to scope model detection\n\n        Returns:\n            List of embedding model names found in the index\n        \"\"\"\n        try:\n            spaces: list[EmbeddingSpace] = []\n            seen: set[str] = set()\n            result: dict[str, Any] = {}\n\n            # Composite aggregations must be top-level. Exact and legacy\n            # spaces use different document filters, so paginate them in two\n            # independent passes rather than nesting composite under filter.\n            for legacy in (False, True):\n                after = None\n                while True:\n                    agg_query = {\n                        \"size\": 0,\n                        \"aggs\": build_embedding_space_aggregation(\n                            size=EMBEDDING_SPACE_PAGE_SIZE,\n                            qualified_after=None if legacy else after,\n                            legacy_after=after if legacy else None,\n                            include_qualified=not legacy,\n                            include_legacy=legacy,\n                        ),\n                    }\n                    bool_query: dict[str, Any] = {}\n                    if filter_clauses:\n                        bool_query[\"filter\"] = filter_clauses\n                    if legacy:\n                        bool_query[\"must_not\"] = [{\"exists\": {\"field\": \"embedding_space_id\"}}]\n                    if bool_query:\n                        agg_query[\"query\"] = {\"bool\": bool_query}\n\n                    logger.debug(f\"Model detection query: {agg_query}\")\n                    result = client.search(\n                        index=self.index_name,\n                        body=agg_query,\n                        params={\"terminate_after\": 0},\n                    )\n                    for space in embedding_spaces_from_aggregation(result):\n                        if space.space_id not in seen:\n                            seen.add(space.space_id)\n                            spaces.append(space)\n\n                    qualified_after, legacy_after = embedding_space_after_keys(result)\n                    next_after = legacy_after if legacy else qualified_after\n                    if not next_after or next_after == after:\n                        break\n                    after = next_after\n\n            # Log detailed bucket info for debugging\n            logger.info(\n                f\"Detected embedding spaces in corpus: {[space.space_id for space in spaces]}\"\n                + (f\" (with {len(filter_clauses)} filters)\" if filter_clauses else \"\")\n            )\n            if not spaces:\n                total_hits = result.get(\"hits\", {}).get(\"total\", {})\n                total_count = (\n                    total_hits.get(\"value\", 0) if isinstance(total_hits, dict) else total_hits\n                )\n                logger.warning(\n                    f\"No embedding_model values found in index '{self.index_name}'. \"\n                    f\"Total docs in index: {total_count}. \"\n                    f\"This may indicate documents were indexed without the embedding_model field.\"\n                )\n        except (OpenSearchException, KeyError, ValueError) as e:\n            logger.warning(f\"Failed to detect embedding models: {e}\")\n            # Provider provenance cannot be inferred safely after discovery\n            # fails. Keyword search remains available without guessing.\n            return []\n        else:\n            return spaces\n\n    def _get_index_properties(self, client: OpenSearch) -> dict[str, Any] | None:\n        \"\"\"Retrieve flattened mapping properties for the current index.\"\"\"\n        try:\n            mapping = client.indices.get_mapping(index=self.index_name)\n        except OpenSearchException as e:\n            logger.warning(\n                f\"Failed to fetch mapping for index '{self.index_name}': {e}. Proceeding without mapping metadata.\"\n            )\n            return None\n\n        properties: dict[str, Any] = {}\n        for index_data in mapping.values():\n            props = index_data.get(\"mappings\", {}).get(\"properties\", {})\n            if isinstance(props, dict):\n                properties.update(props)\n        return properties\n\n    def _is_knn_vector_field(self, properties: dict[str, Any] | None, field_name: str) -> bool:\n        \"\"\"Check whether the field is mapped as a knn_vector.\"\"\"\n        if not field_name:\n            return False\n        if properties is None:\n            logger.warning(\n                f\"Mapping metadata unavailable; assuming field '{field_name}' is usable.\"\n            )\n            return True\n        field_def = properties.get(field_name)\n        if not isinstance(field_def, dict):\n            return False\n        if field_def.get(\"type\") == \"knn_vector\":\n            return True\n\n        nested_props = field_def.get(\"properties\")\n        return bool(isinstance(nested_props, dict) and nested_props.get(\"type\") == \"knn_vector\")\n\n    _INNER_KNN_FILTER_ENGINES = frozenset({\"lucene\", \"faiss\", \"jvector\"})\n\n    def _supports_inner_knn_filter(\n        self, properties: dict[str, Any] | None, field_name: str\n    ) -> bool:\n        \"\"\"True when the field's k-NN engine supports a filter inside the k-NN clause.\"\"\"\n        field_def = (properties or {}).get(field_name)\n        if not isinstance(field_def, dict):\n            return False\n        method = field_def.get(\"method\")\n        engine = method.get(\"engine\") if isinstance(method, dict) else None\n        return isinstance(engine, str) and engine.lower() in self._INNER_KNN_FILTER_ENGINES\n\n    def _exact_filtered_knn_query(\n        self,\n        properties: dict[str, Any] | None,\n        field_name: str,\n        vector: list[float],\n        filter_clauses: list[dict],\n    ) -> dict[str, Any]:\n        \"\"\"Exact k-NN scoring over only the documents matching *filter_clauses*.\"\"\"\n        field_def = (properties or {}).get(field_name)\n        method = field_def.get(\"method\") if isinstance(field_def, dict) else None\n        space_type = (method or {}).get(\"space_type\") if isinstance(method, dict) else None\n        return {\n            \"script_score\": {\n                \"query\": {\"bool\": {\"filter\": [{\"exists\": {\"field\": field_name}}, *filter_clauses]}},\n                \"script\": {\n                    \"source\": \"knn_score\",\n                    \"lang\": \"knn\",\n                    \"params\": {\n                        \"field\": field_name,\n                        \"query_value\": vector,\n                        \"space_type\": space_type or \"l2\",\n                    },\n                },\n            }\n        }\n\n    def _get_field_dimension(\n        self, properties: dict[str, Any] | None, field_name: str\n    ) -> int | None:\n        \"\"\"Get the dimension of a knn_vector field from the index mapping.\n\n        Args:\n            properties: Index properties from mapping\n            field_name: Name of the vector field\n\n        Returns:\n            Dimension of the field, or None if not found\n        \"\"\"\n        if not field_name or properties is None:\n            return None\n\n        field_def = properties.get(field_name)\n        if not isinstance(field_def, dict):\n            return None\n\n        # Check direct knn_vector field\n        if field_def.get(\"type\") == \"knn_vector\":\n            return field_def.get(\"dimension\")\n\n        # Check nested properties\n        nested_props = field_def.get(\"properties\")\n        if isinstance(nested_props, dict) and nested_props.get(\"type\") == \"knn_vector\":\n            return nested_props.get(\"dimension\")\n\n        return None\n\n    def _get_filename_agg_field(self, index_properties: dict[str, Any] | None) -> str:\n        \"\"\"Choose the appropriate field for filename aggregations.\"\"\"\n        if not index_properties:\n            return \"filename.keyword\"\n\n        filename_def = index_properties.get(\"filename\")\n        if not isinstance(filename_def, dict):\n            return \"filename.keyword\"\n\n        field_type = filename_def.get(\"type\")\n        fields_def = filename_def.get(\"fields\", {})\n\n        # Top-level keyword with no subfields\n        if field_type == \"keyword\" and not isinstance(fields_def, dict):\n            return \"filename\"\n\n        # Text field with keyword subfield\n        if isinstance(fields_def, dict) and \"keyword\" in fields_def:\n            return \"filename.keyword\"\n\n        # Fallback: aggregate on filename directly\n        return \"filename\"\n\n    # ---------- search (multi-model hybrid) ----------\n    def search(self, query: str | None = None) -> list[dict[str, Any]]:\n        \"\"\"Perform multi-model hybrid search combining multiple vector similarities and keyword matching.\n\n        This method executes a sophisticated search that:\n        1. Auto-detects all embedding models present in the index\n        2. Generates query embeddings for ALL detected models in parallel\n        3. Combines multiple KNN queries using dis_max (picks best match)\n        4. Adds keyword search with fuzzy matching (30% weight)\n        5. Applies optional filtering and score thresholds\n        6. Returns aggregations for faceted search\n\n        Search weights:\n        - Semantic search (dis_max across all models): 70%\n        - Keyword search: 30%\n\n        Args:\n            query: Search query string (used for both vector embedding and keyword search)\n\n        Returns:\n            List of search results with page_content, metadata, and relevance scores\n\n        Raises:\n            ValueError: If filter JSON is invalid\n        \"\"\"\n        logger.info(self.ingest_data)\n        client = self.build_client()\n        q = (query or \"\").strip()\n\n        # Parse optional filter expression\n        filter_obj = self._parse_filter_expression()\n\n        # Build filter clauses first so we can use them in model detection\n        filter_clauses = self._coerce_filter_clauses(filter_obj)\n\n        # Detect available embedding models in the index (scoped by filters)\n        available_spaces = self._detect_available_models(client, filter_clauses)\n\n        if not available_spaces:\n            logger.warning(\"No embedding spaces found in index; using keyword-only search\")\n\n        # Generate embeddings for ALL detected models\n        query_embeddings = {}\n\n        # Normalize embedding to list\n        embeddings_list = self.embedding if isinstance(self.embedding, list) else [self.embedding]\n        # Filter out None values (fail-safe mode)\n        embeddings_list = [e for e in embeddings_list if e is not None]\n\n        if not embeddings_list:\n            logger.warning(\n                \"No valid embedding adapter is available; continuing with keyword-only search.\"\n            )\n\n        # Create a comprehensive map of model names to embedding objects\n        # Check all possible identifiers (deployment, model, model_id, model_name)\n        # Also leverage available_models list from EmbeddingsWithModels\n        # Handle duplicate identifiers by creating combined keys\n        embedding_by_model = {}\n        identifier_conflicts = {}  # Track which identifiers have conflicts\n\n        for idx, emb_obj in enumerate(embeddings_list):\n            # Get all possible identifiers for this embedding\n            identifiers = []\n            deployment = getattr(emb_obj, \"deployment\", None)\n            model = getattr(emb_obj, \"model\", None)\n            model_id = getattr(emb_obj, \"model_id\", None)\n            model_name = getattr(emb_obj, \"model_name\", None)\n            dimensions = getattr(emb_obj, \"dimensions\", None)\n            available_models_attr = getattr(emb_obj, \"available_models\", None)\n\n            logger.info(\n                f\"Embedding object {idx}: deployment={deployment}, model={model}, \"\n                f\"model_id={model_id}, model_name={model_name}, dimensions={dimensions}, \"\n                f\"available_models={available_models_attr}\"\n            )\n\n            # If this embedding has available_models dict, map all models to their dedicated instances\n            if available_models_attr and isinstance(available_models_attr, dict):\n                logger.info(\n                    f\"Embedding object {idx} provides {len(available_models_attr)} models via available_models dict\"\n                )\n                for model_name_key, dedicated_embedding in available_models_attr.items():\n                    if model_name_key and str(model_name_key).strip():\n                        model_str = str(model_name_key).strip()\n                        if model_str not in embedding_by_model:\n                            # Use the dedicated embedding instance from the dict\n                            embedding_by_model[model_str] = dedicated_embedding\n                            logger.info(\n                                f\"Mapped available model '{model_str}' to dedicated embedding instance\"\n                            )\n                        else:\n                            # Conflict detected - track it\n                            if model_str not in identifier_conflicts:\n                                identifier_conflicts[model_str] = [embedding_by_model[model_str]]\n                            identifier_conflicts[model_str].append(dedicated_embedding)\n                            logger.warning(\n                                f\"Available model '{model_str}' has conflict - used by multiple embeddings\"\n                            )\n\n            # Also map traditional identifiers (for backward compatibility)\n            if deployment:\n                identifiers.append(str(deployment))\n            if model:\n                identifiers.append(str(model))\n            if model_id:\n                identifiers.append(str(model_id))\n            if model_name:\n                identifiers.append(str(model_name))\n\n            # Map all identifiers to this embedding object\n            for identifier in identifiers:\n                if identifier not in embedding_by_model:\n                    embedding_by_model[identifier] = emb_obj\n                    logger.info(f\"Mapped identifier '{identifier}' to embedding object {idx}\")\n                else:\n                    # Conflict detected - track it\n                    if identifier not in identifier_conflicts:\n                        identifier_conflicts[identifier] = [embedding_by_model[identifier]]\n                    identifier_conflicts[identifier].append(emb_obj)\n                    logger.warning(\n                        f\"Identifier '{identifier}' has conflict - used by multiple embeddings\"\n                    )\n\n            # For embeddings with model+deployment, create combined identifier\n            # This helps when deployment is the same but model differs\n            if deployment and model and deployment != model:\n                combined_id = f\"{deployment}:{model}\"\n                if combined_id not in embedding_by_model:\n                    embedding_by_model[combined_id] = emb_obj\n                    logger.info(\n                        f\"Created combined identifier '{combined_id}' for embedding object {idx}\"\n                    )\n\n        # Log conflicts\n        if identifier_conflicts:\n            logger.warning(\n                f\"Found {len(identifier_conflicts)} conflicting identifiers. \"\n                f\"Consider using combined format 'deployment:model' or specifying unique model names.\"\n            )\n            for conflict_id, emb_list in identifier_conflicts.items():\n                logger.warning(\n                    f\"  Conflict on '{conflict_id}': {len(emb_list)} embeddings use this identifier\"\n                )\n\n        logger.info(f\"Generating embeddings for {len(available_spaces)} spaces in index\")\n        logger.info(f\"Available embedding identifiers: {list(embedding_by_model.keys())}\")\n        self.log(\n            f\"[SEARCH] Embedding spaces detected in index: \"\n            f\"{[space.space_id for space in available_spaces]}\"\n        )\n        self.log(f\"[SEARCH] Available embedding identifiers: {list(embedding_by_model.keys())}\")\n\n        # Track matching status for debugging\n        matched_models = []\n        unmatched_models = []\n\n        for space in available_spaces:\n            model_name = space.space_id\n            try:\n                emb_obj = None\n\n                # The OpenRAG proxy adapter can create an immutable child for\n                # any provider-qualified or legacy route. Resolve through it\n                # first so a legacy OpenAI vector is never queried through the\n                # currently selected Azure/Watsonx provider by accident.\n                for candidate in embeddings_list:\n                    resolver = getattr(candidate, \"for_model\", None)\n                    if callable(resolver):\n                        emb_obj = resolver(space.route_model)\n                        break\n\n                # Backward compatibility for custom flows that still wire one\n                # concrete embedding adapter per model.\n                if emb_obj is None:\n                    for identifier in (space.space_id, space.field_identity):\n                        if identifier in embedding_by_model:\n                            emb_obj = embedding_by_model[identifier]\n                            break\n\n                if emb_obj is not None:\n                    emb_deployment = getattr(emb_obj, \"deployment\", None)\n                    emb_model = getattr(emb_obj, \"model\", None)\n                    emb_model_id = getattr(emb_obj, \"model_id\", None)\n                    emb_dimensions = getattr(emb_obj, \"dimensions\", None)\n                    emb_available_models = getattr(emb_obj, \"available_models\", None)\n\n                    logger.info(\n                        f\"Using embedding object for model '{model_name}': \"\n                        f\"deployment={emb_deployment}, model={emb_model}, model_id={emb_model_id}, \"\n                        f\"dimensions={emb_dimensions}\"\n                    )\n\n                    # Check if this is a dedicated instance from available_models dict\n                    if emb_available_models and isinstance(emb_available_models, dict):\n                        logger.info(\n                            f\"Model '{model_name}' using dedicated instance from available_models dict \"\n                            f\"(pre-configured with correct model and dimensions)\"\n                        )\n\n                    # Use the embedding instance directly - no model switching needed!\n                    vec = emb_obj.embed_query(q)\n                    query_embeddings[space.field_identity] = vec\n                    matched_models.append(model_name)\n                    logger.info(\n                        f\"Generated embedding for model: {model_name} (actual dimensions: {len(vec)})\"\n                    )\n                    self.log(f\"[MATCH] Model '{model_name}' - generated {len(vec)}-dim embedding\")\n                else:\n                    # No matching embedding found for this model\n                    unmatched_models.append(model_name)\n                    logger.warning(\n                        f\"No matching embedding found for model '{model_name}'. \"\n                        f\"This model will be skipped. Available identifiers: {list(embedding_by_model.keys())}\"\n                    )\n                    self.log(\n                        f\"[NO MATCH] Model '{model_name}' - available: {list(embedding_by_model.keys())}\"\n                    )\n            except Exception as e:  # provider clients expose different exception families\n                logger.warning(f\"Failed to generate embedding for {model_name}: {e}\")\n                self.log(f\"[ERROR] Embedding generation failed for '{model_name}': {e}\")\n\n        # Log summary of model matching\n        logger.info(\n            f\"Model matching summary: {len(matched_models)} matched, {len(unmatched_models)} unmatched\"\n        )\n        self.log(\n            f\"[SUMMARY] Model matching: {len(matched_models)} matched, {len(unmatched_models)} unmatched\"\n        )\n        if unmatched_models:\n            self.log(f\"[WARN] Unmatched models in index: {unmatched_models}\")\n\n        if not query_embeddings:\n            self.log(\n                \"[WARN] No indexed embedding space could be resolved; \"\n                \"continuing with keyword-only search\"\n            )\n\n        index_properties = self._get_index_properties(client)\n        # Build KNN queries for each model\n        embedding_fields: list[str] = []\n        knn_queries_with_candidates = []\n        knn_queries_without_candidates = []\n\n        raw_num_candidates = getattr(self, \"num_candidates\", 1000)\n        try:\n            num_candidates = int(raw_num_candidates) if raw_num_candidates is not None else 0\n        except (TypeError, ValueError):\n            num_candidates = 0\n        use_num_candidates = num_candidates > 0\n\n        for model_name, embedding_vector in query_embeddings.items():\n            field_name = get_embedding_field_name(model_name)\n            selected_field = field_name\n            vector_dim = len(embedding_vector)\n\n            # Only use the expected dynamic field - no legacy fallback\n            # This prevents dimension mismatches between models\n            if not self._is_knn_vector_field(index_properties, selected_field):\n                logger.warning(\n                    f\"Skipping model {model_name}: field '{field_name}' is not mapped as knn_vector. \"\n                    f\"Documents must be indexed with this embedding model before querying.\"\n                )\n                self.log(\n                    f\"[SKIP] Field '{selected_field}' not a knn_vector - skipping model '{model_name}'\"\n                )\n                continue\n\n            # Validate vector dimensions match the field dimensions\n            field_dim = self._get_field_dimension(index_properties, selected_field)\n            if field_dim is not None and field_dim != vector_dim:\n                logger.error(\n                    f\"Dimension mismatch for model '{model_name}': \"\n                    f\"Query vector has {vector_dim} dimensions but field '{selected_field}' expects {field_dim}. \"\n                    f\"Skipping this model to prevent search errors.\"\n                )\n                self.log(\n                    f\"[DIM MISMATCH] Model '{model_name}': query={vector_dim} vs field={field_dim} - skipping\"\n                )\n                continue\n\n            logger.info(\n                f\"Adding KNN query for model '{model_name}': field='{selected_field}', \"\n                f\"query_dims={vector_dim}, field_dims={field_dim or 'unknown'}\"\n            )\n            embedding_fields.append(selected_field)\n            base_query = {\n                \"knn\": {\n                    selected_field: {\n                        \"vector\": embedding_vector,\n                        \"k\": 50,\n                    }\n                }\n            }\n            # A filter must apply before neighbours are chosen, or a narrow range\n            # sees only whatever survives the global top-k. Engines with native\n            # filtering take it inside the kNN clause; nmslib cannot, so a\n            # filtered search scores the filtered documents exactly instead.\n            if filter_clauses:\n                if index_properties is None or self._supports_inner_knn_filter(\n                    index_properties, selected_field\n                ):\n                    # Without readable mapping metadata the engine and metric are\n                    # unknown, so keep the native clause rather than guess a metric.\n                    base_query[\"knn\"][selected_field][\"filter\"] = {\n                        \"bool\": {\"filter\": filter_clauses}\n                    }\n                else:\n                    base_query = self._exact_filtered_knn_query(\n                        index_properties, selected_field, embedding_vector, filter_clauses\n                    )\n\n            if use_num_candidates and \"knn\" in base_query:\n                query_with_candidates = copy.deepcopy(base_query)\n                query_with_candidates[\"knn\"][selected_field][\"num_candidates\"] = num_candidates\n            else:\n                query_with_candidates = base_query\n\n            knn_queries_with_candidates.append(query_with_candidates)\n            knn_queries_without_candidates.append(base_query)\n\n        if not knn_queries_with_candidates:\n            logger.warning(\n                \"No valid knn_vector fields found for embedding models. \"\n                \"This may indicate an empty index or missing field mappings. \"\n                \"Continuing with keyword-only search.\"\n            )\n            self.log(\n                f\"[WARN] No valid KNN queries could be built. \"\n                f\"Query embeddings generated: {list(query_embeddings.keys())}, \"\n                f\"but no matching knn_vector fields found in index; using keyword search.\"\n            )\n\n        # Get limit and score threshold\n        limit = self._resolve_limit(filter_obj, default_limit=self.number_of_results)\n        score_threshold = self._resolve_score_threshold(filter_obj)\n\n        # Determine the best aggregation field for filename based on index mapping\n        filename_agg_field = self._get_filename_agg_field(index_properties)\n\n        keyword_query = {\n            \"multi_match\": {\n                \"query\": q,\n                \"fields\": [\"text^2\", \"filename^1.5\"],\n                \"type\": \"best_fields\",\n                \"fuzziness\": \"AUTO\",\n                \"boost\": 0.3 if knn_queries_with_candidates else 1.0,\n            }\n        }\n        should_queries: list[dict[str, Any]] = [keyword_query]\n        if knn_queries_with_candidates:\n            should_queries.insert(\n                0,\n                {\n                    \"dis_max\": {\n                        \"tie_breaker\": 0.0,\n                        \"boost\": 0.7,\n                        \"queries\": knn_queries_with_candidates,\n                    }\n                },\n            )\n\n        # Keyword search intentionally has no embedding-field existence filter:\n        # documents in an unresolved legacy space must remain discoverable.\n        body = {\n            \"query\": {\n                \"bool\": {\n                    \"should\": should_queries,\n                    \"minimum_should_match\": 1,\n                    \"filter\": filter_clauses,\n                }\n            },\n            \"aggs\": {\n                \"data_sources\": {\"terms\": {\"field\": filename_agg_field, \"size\": 20}},\n                \"document_types\": {\"terms\": {\"field\": \"mimetype\", \"size\": 10}},\n                \"owners\": {\"terms\": {\"field\": \"owner\", \"size\": 10}},\n                \"embedding_models\": {\"terms\": {\"field\": \"embedding_model\", \"size\": 10}},\n            },\n            \"_source\": [\n                \"filename\",\n                \"mimetype\",\n                \"page\",\n                \"text\",\n                \"source_url\",\n                \"owner\",\n                \"embedding_model\",\n                \"embedding_provider\",\n                \"embedding_space_id\",\n                \"parser\",\n                \"chunk_size\",\n                \"chunk_overlap\",\n                \"allowed_users\",\n                \"allowed_groups\",\n                \"allowed_principals\",\n            ],\n            \"size\": limit,\n        }\n\n        if score_threshold is not None:\n            body[\"min_score\"] = score_threshold\n\n        logger.info(\n            f\"Executing hybrid search with {len(knn_queries_with_candidates)} resolved embedding spaces: \"\n            f\"{list(query_embeddings.keys())}\"\n        )\n        self.log(\n            f\"[EXEC] Executing search with {len(knn_queries_with_candidates)} KNN queries, limit={limit}\"\n        )\n        self.log(f\"[EXEC] Embedding models used: {list(query_embeddings.keys())}\")\n        self.log(f\"[EXEC] KNN fields being queried: {embedding_fields}\")\n\n        try:\n            resp = client.search(index=self.index_name, body=body, params={\"terminate_after\": 0})\n        except RequestError as e:\n            error_message = str(e)\n            lowered = error_message.lower()\n            if knn_queries_with_candidates and use_num_candidates and \"num_candidates\" in lowered:\n                logger.warning(\n                    \"Retrying search without num_candidates parameter due to cluster capabilities\",\n                    error=error_message,\n                )\n                fallback_body = copy.deepcopy(body)\n                try:\n                    fallback_body[\"query\"][\"bool\"][\"should\"][0][\"dis_max\"][\"queries\"] = (\n                        knn_queries_without_candidates\n                    )\n                except (KeyError, IndexError, TypeError) as inner_err:\n                    raise e from inner_err\n                resp = client.search(\n                    index=self.index_name,\n                    body=fallback_body,\n                    params={\"terminate_after\": 0},\n                )\n            elif knn_queries_with_candidates and (\n                \"knn_vector\" in lowered or (\"field\" in lowered and \"knn\" in lowered)\n            ):\n                logger.warning(\n                    \"KNN search failed for an indexed embedding field; retrying keyword-only\",\n                    error=error_message,\n                )\n                fallback_body = copy.deepcopy(body)\n                fallback_body[\"query\"][\"bool\"][\"should\"] = [keyword_query]\n                resp = client.search(\n                    index=self.index_name,\n                    body=fallback_body,\n                    params={\"terminate_after\": 0},\n                )\n            else:\n                raise\n        hits = resp.get(\"hits\", {}).get(\"hits\", [])\n\n        logger.info(f\"Found {len(hits)} results\")\n        self.log(f\"[RESULT] Search complete: {len(hits)} results found\")\n\n        if len(hits) == 0:\n            self.log(\n                f\"[EMPTY] Debug info: \"\n                f\"spaces_in_index={[space.space_id for space in available_spaces]}, \"\n                f\"matched_models={matched_models}, \"\n                f\"knn_fields={embedding_fields}, \"\n                f\"filters={len(filter_clauses)} clauses\"\n            )\n\n        return [\n            {\n                \"page_content\": fence_untrusted_text(hit[\"_source\"].get(\"text\", \"\")),\n                \"metadata\": {\n                    **{k: v for k, v in hit[\"_source\"].items() if k != \"text\"},\n                    \"chunk_id\": hit.get(\"_id\"),\n                    \"id\": hit.get(\"_id\"),\n                    \"score\": hit.get(\"_score\"),\n                },\n                \"score\": hit.get(\"_score\"),\n            }\n            for hit in hits\n        ]\n\n    def search_documents(self) -> list[Data]:\n        \"\"\"Search documents and return results as a list of Data objects.\n\n        This is the main interface method that performs the multi-model search using the\n        configured search_query and returns results in a format that downstream Parser\n        components and tool wrappers can consume directly without DataFrame string truncation.\n\n        Always builds the vector store (triggering ingestion if needed), then performs\n        search only if a query is provided.\n\n        Returns:\n            List containing search results with text and metadata\n\n        Raises:\n            Exception: If search operation fails\n        \"\"\"\n\n        try:\n            # Always build/cache the vector store to ensure ingestion happens\n            logger.info(f\"Search query: {self.search_query}\")\n            if self._cached_vector_store is None:\n                self.build_vector_store()\n\n            # Only perform search if query is provided\n            search_query = (self.search_query or \"\").strip()\n            if not search_query:\n                self.log(\"No search query provided - ingestion completed, returning empty results\")\n\n                return []\n\n            # Perform search with the provided query\n            raw = self.search(search_query)\n            raw_list = [Data(text=hit[\"page_content\"], **hit[\"metadata\"]) for hit in raw]\n            return raw_list\n\n        except Exception as e:\n            self.log(f\"search_documents error: {e}\")\n            raise\n\n    # -------- dynamic UI handling (auth switch) --------\n    async def update_build_config(\n        self, build_config: dict, field_value: str, field_name: str | None = None\n    ) -> dict:\n        \"\"\"Dynamically update component configuration based on field changes.\n\n        This method handles real-time UI updates, particularly for authentication\n        mode changes that show/hide relevant input fields.\n\n        Args:\n            build_config: Current component configuration\n            field_value: New value for the changed field\n            field_name: Name of the field that changed\n\n        Returns:\n            Updated build configuration with appropriate field visibility\n        \"\"\"\n        try:\n            if field_name == \"auth_mode\":\n                mode = (field_value or \"basic\").strip().lower()\n                is_basic = mode == \"basic\"\n                is_jwt = mode == \"jwt\"\n                is_openrag = mode == \"openrag\"\n\n                build_config[\"username\"][\"show\"] = is_basic\n                build_config[\"password\"][\"show\"] = is_basic\n\n                build_config[\"jwt_token\"][\"show\"] = is_jwt\n                build_config[\"jwt_header\"][\"show\"] = is_jwt\n                build_config[\"bearer_prefix\"][\"show\"] = is_jwt\n\n                build_config[\"username\"][\"required\"] = is_basic\n                build_config[\"password\"][\"required\"] = is_basic\n\n                # build_config[\"jwt_token\"][\"required\"] = is_jwt\n                build_config[\"jwt_header\"][\"required\"] = is_jwt\n                build_config[\"bearer_prefix\"][\"required\"] = False\n\n                # In 'openrag' mode, expose the OPENRAG_* fields up front\n                # since they are the only credentials required.\n                for openrag_field in (\n                    \"openrag_ingest_url\",\n                    \"openrag_ingest_token\",\n                    \"openrag_ingest_run_id\",\n                    \"openrag_ingest_batch_size\",\n                ):\n                    if openrag_field in build_config:\n                        build_config[openrag_field][\"advanced\"] = not is_openrag\n                        build_config[openrag_field][\"required\"] = (\n                            is_openrag and openrag_field != \"openrag_ingest_batch_size\"\n                        )\n\n                if is_basic or is_openrag:\n                    build_config[\"jwt_token\"][\"value\"] = \"\"\n\n                return build_config\n\n        except (KeyError, ValueError) as e:\n            self.log(f\"update_build_config error: {e}\")\n\n        return build_config\n"
              },
              "docs_metadata": {
                "_input_type": "TableInput",
                "advanced": false,
                "api_editable": false,
                "display_name": "Document Metadata",
                "dynamic": false,
                "info": "Additional metadata key-value pairs to be added to all ingested documents. Useful for tagging documents with source information, categories, or other custom attributes.",
                "input_types": [
                  "Data",
                  "JSON"
                ],
                "is_list": true,
                "list_add_label": "Add More",
                "name": "docs_metadata",
                "override_skip": false,
                "placeholder": "",
                "required": false,
                "show": true,
                "table_icon": "Table",
                "table_schema": [
                  {
                    "description": "Key name",
                    "display_name": "Key",
                    "formatter": "text",
                    "name": "key",
                    "type": "str"
                  },
                  {
                    "description": "Value of the metadata",
                    "display_name": "Value",
                    "formatter": "text",
                    "name": "value",
                    "type": "str"
                  }
                ],
                "title_case": false,
                "tool_mode": false,
                "trace_as_metadata": true,
                "track_in_telemetry": false,
                "trigger_icon": "Table",
                "trigger_text": "Open table",
                "type": "table",
                "value": []
              },
              "ef_construction": {
                "_input_type": "IntInput",
                "advanced": true,
                "api_editable": false,
                "display_name": "EF Construction",
                "dynamic": false,
                "info": "Size of the dynamic candidate list during index construction. Higher values improve recall but increase indexing time and memory usage.",
                "list": false,
                "list_add_label": "Add More",
                "name": "ef_construction",
                "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": 512
              },
              "embedding": {
                "_input_type": "HandleInput",
                "advanced": false,
                "api_editable": false,
                "display_name": "Embedding",
                "dynamic": false,
                "info": "",
                "input_types": [
                  "Embeddings"
                ],
                "list": true,
                "list_add_label": "Add More",
                "name": "embedding",
                "override_skip": false,
                "placeholder": "",
                "required": false,
                "show": true,
                "title_case": false,
                "trace_as_metadata": true,
                "track_in_telemetry": false,
                "type": "other",
                "value": ""
              },
              "embedding_model_name": {
                "_input_type": "StrInput",
                "advanced": false,
                "api_editable": false,
                "display_name": "Embedding Model Name",
                "dynamic": false,
                "info": "Name of the embedding model to use for ingestion. This selects which embedding from the list will be used to embed documents. Matches on deployment, model, model_id, or model_name. For duplicate deployments, use combined format: 'deployment:model' (e.g., 'text-embedding-ada-002:text-embedding-3-large'). Leave empty to use the first embedding. Error message will show all available identifiers.",
                "list": false,
                "list_add_label": "Add More",
                "load_from_db": true,
                "name": "embedding_model_name",
                "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": "SELECTED_EMBEDDING_MODEL"
              },
              "embedding_provider_name": {
                "_input_type": "StrInput",
                "advanced": true,
                "api_editable": false,
                "display_name": "Embedding Provider",
                "dynamic": false,
                "info": "Exact OpenRAG provider key used for new ingestion metadata and vector fields. Bound to SELECTED_EMBEDDING_PROVIDER in managed OpenRAG flows.",
                "list": false,
                "list_add_label": "Add More",
                "load_from_db": true,
                "name": "embedding_provider_name",
                "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": "SELECTED_EMBEDDING_PROVIDER"
              },
              "engine": {
                "_input_type": "DropdownInput",
                "advanced": true,
                "api_editable": false,
                "combobox": false,
                "dialog_inputs": {},
                "display_name": "Vector Engine",
                "dynamic": false,
                "external_options": {},
                "info": "Vector search engine for similarity calculations. 'nmslib' works with standard OpenSearch. 'jvector' requires OpenSearch 2.9+. 'lucene' requires index.knn: true. Amazon OpenSearch Serverless only supports 'nmslib' or 'faiss'.",
                "name": "engine",
                "options": [
                  "nmslib",
                  "faiss",
                  "lucene",
                  "jvector"
                ],
                "options_metadata": [],
                "override_skip": false,
                "placeholder": "",
                "required": false,
                "show": true,
                "title_case": false,
                "toggle": false,
                "tool_mode": false,
                "trace_as_metadata": true,
                "track_in_telemetry": true,
                "type": "str",
                "value": "jvector"
              },
              "filter_expression": {
                "_input_type": "MultilineInput",
                "advanced": false,
                "ai_enabled": false,
                "api_editable": false,
                "copy_field": false,
                "display_name": "Search Filters (JSON)",
                "dynamic": false,
                "info": "Optional JSON configuration for search filtering, result limits, and score thresholds.\n\nFormat 1 - Explicit filters:\n{\"filter\": [{\"term\": {\"filename\":\"doc.pdf\"}}, {\"terms\":{\"owner\":[\"user1\",\"user2\"]}}], \"limit\": 10, \"score_threshold\": 1.6}\n\nFormat 2 - Context-style mapping:\n{\"data_sources\":[\"file.pdf\"], \"document_types\":[\"application/pdf\"], \"owners\":[\"user123\"]}\n\nUse __IMPOSSIBLE_VALUE__ as placeholder to ignore specific filters.",
                "input_types": [
                  "Message"
                ],
                "list": false,
                "list_add_label": "Add More",
                "load_from_db": false,
                "multiline": true,
                "name": "filter_expression",
                "override_skip": false,
                "password": 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": ""
              },
              "index_name": {
                "_input_type": "StrInput",
                "advanced": false,
                "api_editable": false,
                "display_name": "Index Name",
                "dynamic": false,
                "info": "The OpenSearch index name where documents will be stored and searched. Will be created automatically if it doesn't exist.",
                "list": false,
                "list_add_label": "Add More",
                "load_from_db": true,
                "name": "index_name",
                "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_INDEX_NAME"
              },
              "ingest_data": {
                "_input_type": "HandleInput",
                "advanced": false,
                "api_editable": false,
                "display_name": "Ingest Data",
                "dynamic": false,
                "info": "",
                "input_types": [
                  "Data",
                  "DataFrame",
                  "Table"
                ],
                "list": true,
                "list_add_label": "Add More",
                "name": "ingest_data",
                "override_skip": false,
                "placeholder": "",
                "required": false,
                "show": true,
                "title_case": false,
                "trace_as_metadata": true,
                "track_in_telemetry": false,
                "type": "other",
                "value": ""
              },
              "is_refresh": false,
              "jwt_header": {
                "_input_type": "StrInput",
                "advanced": true,
                "api_editable": false,
                "display_name": "JWT Header Name",
                "dynamic": false,
                "info": "",
                "list": false,
                "list_add_label": "Add More",
                "load_from_db": false,
                "name": "jwt_header",
                "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": "Authorization"
              },
              "jwt_token": {
                "_input_type": "SecretStrInput",
                "advanced": false,
                "api_editable": false,
                "display_name": "JWT Token",
                "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": false,
                "name": "jwt_token",
                "override_skip": false,
                "password": true,
                "placeholder": "",
                "required": false,
                "show": false,
                "title_case": false,
                "track_in_telemetry": false,
                "type": "str",
                "value": ""
              },
              "m": {
                "_input_type": "IntInput",
                "advanced": true,
                "api_editable": false,
                "display_name": "M Parameter",
                "dynamic": false,
                "info": "Number of bidirectional connections for each vector in the HNSW graph. Higher values improve search quality but increase memory usage and indexing time.",
                "list": false,
                "list_add_label": "Add More",
                "name": "m",
                "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": 16
              },
              "max_retries": {
                "_input_type": "StrInput",
                "advanced": true,
                "api_editable": false,
                "display_name": "Max Retries",
                "dynamic": false,
                "info": "Number of retries for failed connections before raising an error.",
                "list": false,
                "list_add_label": "Add More",
                "load_from_db": false,
                "name": "max_retries",
                "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": "3"
              },
              "num_candidates": {
                "_input_type": "IntInput",
                "advanced": true,
                "api_editable": false,
                "display_name": "Candidate Pool Size",
                "dynamic": false,
                "info": "Number of approximate neighbors to consider for each KNN query. Some OpenSearch deployments do not support this parameter; set to 0 to disable.",
                "list": false,
                "list_add_label": "Add More",
                "name": "num_candidates",
                "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": 1000
              },
              "number_of_results": {
                "_input_type": "IntInput",
                "advanced": true,
                "api_editable": false,
                "display_name": "Default Result Limit",
                "dynamic": false,
                "info": "Default maximum number of search results to return when no limit is specified in the filter expression.",
                "list": false,
                "list_add_label": "Add More",
                "name": "number_of_results",
                "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": 10
              },
              "openrag_ingest_batch_size": {
                "_input_type": "IntInput",
                "advanced": false,
                "api_editable": false,
                "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": false,
                "api_editable": false,
                "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": true,
                "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": "SecretStrInput",
                "advanced": false,
                "api_editable": false,
                "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": true,
                "show": true,
                "title_case": false,
                "track_in_telemetry": false,
                "type": "str",
                "value": "OPENRAG_INGEST_TOKEN"
              },
              "openrag_ingest_url": {
                "_input_type": "StrInput",
                "advanced": false,
                "api_editable": false,
                "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": 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,
                "api_editable": 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,
                "api_editable": false,
                "display_name": "OpenSearch Password",
                "dynamic": false,
                "info": "",
                "input_types": [],
                "load_from_db": true,
                "name": "password",
                "override_skip": false,
                "password": true,
                "placeholder": "",
                "required": false,
                "show": false,
                "title_case": false,
                "track_in_telemetry": false,
                "type": "str",
                "value": "OPENSEARCH_PASSWORD"
              },
              "request_timeout": {
                "_input_type": "StrInput",
                "advanced": true,
                "api_editable": false,
                "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,
                "api_editable": 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,
                "trace_as_metadata": true,
                "track_in_telemetry": false,
                "type": "query",
                "value": ""
              },
              "should_cache_vector_store": {
                "_input_type": "BoolInput",
                "advanced": true,
                "api_editable": false,
                "display_name": "Cache Vector Store",
                "dynamic": false,
                "info": "If True, the vector store will be cached for the current build of the component. This is useful for components that have multiple output methods and want to share the same vector store.",
                "list": false,
                "list_add_label": "Add More",
                "name": "should_cache_vector_store",
                "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": true
              },
              "space_type": {
                "_input_type": "DropdownInput",
                "advanced": true,
                "api_editable": false,
                "combobox": false,
                "dialog_inputs": {},
                "display_name": "Distance Metric",
                "dynamic": false,
                "external_options": {},
                "info": "Distance metric for calculating vector similarity. 'l2' (Euclidean) is most common, 'cosinesimil' for cosine similarity, 'innerproduct' for dot product.",
                "name": "space_type",
                "options": [
                  "l2",
                  "l1",
                  "cosinesimil",
                  "linf",
                  "innerproduct"
                ],
                "options_metadata": [],
                "override_skip": false,
                "placeholder": "",
                "required": false,
                "show": true,
                "title_case": false,
                "toggle": false,
                "tool_mode": false,
                "trace_as_metadata": true,
                "track_in_telemetry": true,
                "type": "str",
                "value": "l2"
              },
              "use_ssl": {
                "_input_type": "BoolInput",
                "advanced": true,
                "api_editable": false,
                "display_name": "Use SSL/TLS",
                "dynamic": false,
                "info": "Enable SSL/TLS encryption for secure connections to OpenSearch.",
                "list": false,
                "list_add_label": "Add More",
                "name": "use_ssl",
                "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": true
              },
              "username": {
                "_input_type": "StrInput",
                "advanced": false,
                "api_editable": false,
                "display_name": "Username",
                "dynamic": false,
                "info": "",
                "list": false,
                "list_add_label": "Add More",
                "load_from_db": false,
                "name": "username",
                "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": "admin"
              },
              "vector_field": {
                "_input_type": "StrInput",
                "advanced": true,
                "api_editable": false,
                "display_name": "Legacy Vector Field Name",
                "dynamic": false,
                "info": "Legacy field name for backward compatibility. New documents use dynamic fields (chunk_embedding_{model_name}) based on the embedding_model_name.",
                "list": false,
                "list_add_label": "Add More",
                "load_from_db": false,
                "name": "vector_field",
                "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": "chunk_embedding"
              },
              "verify_certs": {
                "_input_type": "BoolInput",
                "advanced": true,
                "api_editable": false,
                "display_name": "Verify SSL Certificates",
                "dynamic": false,
                "info": "Verify SSL certificates when connecting. Disable for self-signed certificates in development environments.",
                "list": false,
                "list_add_label": "Add More",
                "name": "verify_certs",
                "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
              }
            },
            "tool_mode": false
          },
          "selected_output": "search_results",
          "showNode": false,
          "type": "ext:openrag:OpenSearchVectorStoreComponentMultimodalMultiEmbedding@extra"
        },
        "dragging": false,
        "id": "OpenSearchVectorStoreComponentMultimodalMultiEmbedding-WaE28",
        "position": {
          "x": 1782.4529230544917,
          "y": 1889.4261474579816
        },
        "selected": false,
        "type": "genericNode"
      },
      {
        "data": {
          "id": "ext:openrag:OpenRAGSplitTextComponent@extra-0ttMH",
          "node": {
            "base_classes": [
              "Table"
            ],
            "beta": false,
            "bundle": "openrag",
            "conditional_paths": [],
            "custom_fields": {},
            "description": "Split text into chunks no longer than the chunk size.",
            "display_name": "Split Text",
            "documentation": "https://docs.langflow.org/split-text",
            "edited": false,
            "extension": "openrag",
            "extension_version": "0.0.0",
            "field_order": [
              "data_inputs",
              "chunk_overlap",
              "chunk_size",
              "separator",
              "text_key",
              "keep_separator",
              "clean_output"
            ],
            "frozen": false,
            "icon": "scissors-line-dashed",
            "legacy": false,
            "legacy_module": "split_text",
            "metadata": {
              "code_hash": "a94056a09995",
              "dependencies": {
                "dependencies": [
                  {
                    "name": "langchain_text_splitters",
                    "version": "1.1.2"
                  },
                  {
                    "name": "lfx",
                    "version": "1.12.3"
                  }
                ],
                "total_dependencies": 2
              },
              "module": "_lfx_ext.extra.openrag.split_text"
            },
            "minimized": false,
            "name": "OpenRAGSplitText",
            "namespaced_id": "ext:openrag:OpenRAGSplitTextComponent@extra",
            "output_types": [],
            "outputs": [
              {
                "allows_loop": false,
                "cache": true,
                "display_name": "Chunks",
                "group_outputs": false,
                "method": "split_text",
                "name": "dataframe",
                "selected": "Table",
                "tool_mode": true,
                "types": [
                  "Table"
                ],
                "value": "__UNDEFINED__"
              }
            ],
            "pinned": false,
            "template": {
              "_type": "Component",
              "chunk_overlap": {
                "_input_type": "IntInput",
                "advanced": false,
                "api_editable": false,
                "display_name": "Chunk Overlap",
                "dynamic": false,
                "info": "Number of characters to overlap between chunks.",
                "list": false,
                "list_add_label": "Add More",
                "name": "chunk_overlap",
                "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": 200
              },
              "chunk_size": {
                "_input_type": "IntInput",
                "advanced": false,
                "api_editable": false,
                "display_name": "Chunk Size",
                "dynamic": false,
                "info": "The maximum length of each chunk. Text is split on the separator first; any piece still longer than this is split on finer boundaries (lines, sentences, spaces, then characters).",
                "list": false,
                "list_add_label": "Add More",
                "name": "chunk_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": 1000
              },
              "clean_output": {
                "_input_type": "BoolInput",
                "advanced": true,
                "api_editable": false,
                "display_name": "Clean Output",
                "dynamic": false,
                "info": "When enabled, only the text column is included in the output. Metadata columns are removed.",
                "list": false,
                "list_add_label": "Add More",
                "name": "clean_output",
                "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
              },
              "code": {
                "advanced": true,
                "api_editable": false,
                "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 langchain_text_splitters import RecursiveCharacterTextSplitter\nfrom lfx.custom.custom_component.component import Component\nfrom lfx.io import BoolInput, DropdownInput, HandleInput, IntInput, MessageTextInput, Output\nfrom lfx.schema.data import Data\nfrom lfx.schema.dataframe import DataFrame\nfrom lfx.schema.message import Message\nfrom lfx.utils.util import unescape_string\n\n# Tried in order after the configured separator. Docling joins consecutive\n# lines that have no blank line between them into one Markdown paragraph, so a\n# long document can arrive with almost no newlines; without these fallbacks a\n# single paragraph becomes one chunk of any size.\nFALLBACK_SEPARATORS = (\"\\n\\n\", \"\\n\", \"。\", \". \", \" \", \"\")\n\n\ndef build_separators(separator: str) -> list[str]:\n    separators = [separator] if separator else []\n    separators += [s for s in FALLBACK_SEPARATORS if s not in separators]\n    return separators\n\n\nclass OpenRAGSplitTextComponent(Component):\n    display_name: str = \"Split Text\"\n    description: str = \"Split text into chunks no longer than the chunk size.\"\n    documentation: str = \"https://docs.langflow.org/split-text\"\n    icon = \"scissors-line-dashed\"\n    # Distinct from Langflow's built-in \"SplitText\": in restricted mode Langflow\n    # replaces drifted code of a known built-in type with its own copy.\n    name = \"OpenRAGSplitText\"\n\n    inputs = [\n        HandleInput(\n            name=\"data_inputs\",\n            display_name=\"Input\",\n            info=\"The data with texts to split in chunks.\",\n            input_types=[\"Data\", \"JSON\", \"DataFrame\", \"Table\", \"Message\"],\n            required=True,\n        ),\n        IntInput(\n            name=\"chunk_overlap\",\n            display_name=\"Chunk Overlap\",\n            info=\"Number of characters to overlap between chunks.\",\n            value=200,\n        ),\n        IntInput(\n            name=\"chunk_size\",\n            display_name=\"Chunk Size\",\n            info=(\n                \"The maximum length of each chunk. Text is split on the separator first; \"\n                \"any piece still longer than this is split on finer boundaries \"\n                \"(lines, sentences, spaces, then characters).\"\n            ),\n            value=1000,\n        ),\n        MessageTextInput(\n            name=\"separator\",\n            display_name=\"Separator\",\n            info=(\n                \"The preferred character to split on. Use \\\\n for newline. \"\n                \"Examples: \\\\n\\\\n for paragraphs, \\\\n for lines, . for sentences\"\n            ),\n            value=\"\\n\",\n        ),\n        MessageTextInput(\n            name=\"text_key\",\n            display_name=\"Text Key\",\n            info=\"The key to use for the text column.\",\n            value=\"text\",\n            advanced=True,\n        ),\n        DropdownInput(\n            name=\"keep_separator\",\n            display_name=\"Keep Separator\",\n            info=\"Whether to keep the separator in the output chunks and where to place it.\",\n            options=[\"False\", \"True\", \"Start\", \"End\"],\n            value=\"False\",\n            advanced=True,\n        ),\n        BoolInput(\n            name=\"clean_output\",\n            display_name=\"Clean Output\",\n            info=\"When enabled, only the text column is included in the output. Metadata columns are removed.\",\n            value=False,\n            advanced=True,\n        ),\n    ]\n\n    outputs = [\n        Output(display_name=\"Chunks\", name=\"dataframe\", method=\"split_text\"),\n    ]\n\n    def _docs_to_data(self, docs, *, clean: bool = False) -> list[Data]:\n        return [\n            Data(text=doc.page_content) if clean else Data(text=doc.page_content, data=doc.metadata)\n            for doc in docs\n        ]\n\n    def _fix_separator(self, separator: str) -> str:\n        \"\"\"Fix common separator issues and convert to proper format.\"\"\"\n        if separator == \"/n\":\n            return \"\\n\"\n        if separator == \"/t\":\n            return \"\\t\"\n        return separator\n\n    def split_text_base(self):\n        separator = self._fix_separator(self.separator)\n        separator = unescape_string(separator)\n\n        if isinstance(self.data_inputs, DataFrame):\n            if not len(self.data_inputs):\n                msg = \"DataFrame is empty\"\n                raise TypeError(msg)\n\n            self.data_inputs.text_key = self.text_key\n            try:\n                documents = self.data_inputs.to_lc_documents()\n            except Exception as e:\n                msg = f\"Error converting DataFrame to documents: {e}\"\n                raise TypeError(msg) from e\n        elif isinstance(self.data_inputs, Message):\n            self.data_inputs = [self.data_inputs.to_data()]\n            return self.split_text_base()\n        else:\n            if not self.data_inputs:\n                msg = \"No data inputs provided\"\n                raise TypeError(msg)\n\n            documents = []\n            if isinstance(self.data_inputs, Data):\n                self.data_inputs.text_key = self.text_key\n                documents = [self.data_inputs.to_lc_document()]\n            else:\n                try:\n                    documents = [\n                        input_.to_lc_document()\n                        for input_ in self.data_inputs\n                        if isinstance(input_, Data)\n                    ]\n                    if not documents:\n                        msg = f\"No valid Data inputs found in {type(self.data_inputs)}\"\n                        raise TypeError(msg)\n                except AttributeError as e:\n                    msg = f\"Invalid input type in collection: {e}\"\n                    raise TypeError(msg) from e\n        try:\n            # Convert string 'False'/'True' to boolean\n            keep_sep = self.keep_separator\n            if isinstance(keep_sep, str):\n                keep_sep = keep_sep.lower()\n                if keep_sep == \"false\":\n                    keep_sep = False\n                elif keep_sep == \"true\":\n                    keep_sep = True\n                # LangChain only recognises lowercase 'start' and 'end'\n\n            splitter = RecursiveCharacterTextSplitter(\n                chunk_overlap=self.chunk_overlap,\n                chunk_size=self.chunk_size,\n                separators=build_separators(separator),\n                keep_separator=keep_sep,\n            )\n            return splitter.split_documents(documents)\n        except Exception as e:\n            msg = f\"Error splitting text: {e}\"\n            raise TypeError(msg) from e\n\n    def split_text(self) -> DataFrame:\n        docs = self.split_text_base()\n        df = DataFrame(self._docs_to_data(docs, clean=self.clean_output))\n        return df if self.clean_output else df.smart_column_order()\n"
              },
              "data_inputs": {
                "_input_type": "HandleInput",
                "advanced": false,
                "api_editable": false,
                "display_name": "Input",
                "dynamic": false,
                "info": "The data with texts to split in chunks.",
                "input_types": [
                  "Data",
                  "JSON",
                  "DataFrame",
                  "Table",
                  "Message"
                ],
                "list": false,
                "list_add_label": "Add More",
                "name": "data_inputs",
                "override_skip": false,
                "placeholder": "",
                "required": true,
                "show": true,
                "title_case": false,
                "trace_as_metadata": true,
                "track_in_telemetry": false,
                "type": "other",
                "value": ""
              },
              "keep_separator": {
                "_input_type": "DropdownInput",
                "advanced": true,
                "api_editable": false,
                "combobox": false,
                "dialog_inputs": {},
                "display_name": "Keep Separator",
                "dynamic": false,
                "external_options": {},
                "info": "Whether to keep the separator in the output chunks and where to place it.",
                "name": "keep_separator",
                "options": [
                  "False",
                  "True",
                  "Start",
                  "End"
                ],
                "options_metadata": [],
                "override_skip": false,
                "placeholder": "",
                "required": false,
                "show": true,
                "title_case": false,
                "toggle": false,
                "tool_mode": false,
                "trace_as_metadata": true,
                "track_in_telemetry": true,
                "type": "str",
                "value": "False"
              },
              "separator": {
                "_input_type": "MessageTextInput",
                "advanced": false,
                "api_editable": false,
                "display_name": "Separator",
                "dynamic": false,
                "info": "The preferred character to split on. Use \\n for newline. Examples: \\n\\n for paragraphs, \\n for lines, . for sentences",
                "input_types": [
                  "Message"
                ],
                "list": false,
                "list_add_label": "Add More",
                "load_from_db": false,
                "name": "separator",
                "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"
              },
              "text_key": {
                "_input_type": "MessageTextInput",
                "advanced": true,
                "api_editable": false,
                "display_name": "Text Key",
                "dynamic": false,
                "info": "The key to use for the text column.",
                "input_types": [
                  "Message"
                ],
                "list": false,
                "list_add_label": "Add More",
                "load_from_db": false,
                "name": "text_key",
                "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": "text"
              }
            },
            "tool_mode": false
          },
          "showNode": false,
          "type": "ext:openrag:OpenRAGSplitTextComponent@extra"
        },
        "dragging": false,
        "id": "ext:openrag:OpenRAGSplitTextComponent@extra-0ttMH",
        "position": {
          "x": 1480.0015861525885,
          "y": 1826.6203215715343
        },
        "selected": false,
        "type": "genericNode"
      }
    ],
    "viewport": {
      "x": -384.55512601779697,
      "y": -1192.2699535694164,
      "zoom": 0.805631081977362
    }
  },
  "description": "Load your data for chat context with Retrieval Augmented Generation.",
  "endpoint_name": null,
  "id": "5488df7c-b93f-4f87-a446-b67028bc0813",
  "is_component": false,
  "last_tested_version": "1.12.10",
  "locked": true,
  "name": "OpenSearch Ingestion Flow",
  "tags": [
    "openai",
    "astradb",
    "rag",
    "q-a"
  ]
}