{ "data": { "edges": [ { "className": "", "data": { "sourceHandle": { "dataType": "KnowledgeRetrieval", "id": "KnowledgeRetrieval-kgwih", "name": "retrieve_data", "output_types": [ "DataFrame" ] }, "targetHandle": { "fieldName": "input_value", "id": "ChatOutput-OG4M9", "inputTypes": [ "Data", "DataFrame", "Message" ], "type": "other" } }, "id": "xy-edge__KnowledgeRetrieval-kgwih{œdataTypeœ:œKnowledgeRetrievalœ,œidœ:œKnowledgeRetrieval-kgwihœ,œnameœ:œretrieve_dataœ,œoutput_typesœ:[œDataFrameœ]}-ChatOutput-OG4M9{œfieldNameœ:œinput_valueœ,œidœ:œChatOutput-OG4M9œ,œinputTypesœ:[œDataœ,œDataFrameœ,œMessageœ],œtypeœ:œotherœ}", "source": "KnowledgeRetrieval-kgwih", "sourceHandle": "{œdataTypeœ: œKnowledgeRetrievalœ, œidœ: œKnowledgeRetrieval-kgwihœ, œnameœ: œretrieve_dataœ, œoutput_typesœ: [œDataFrameœ]}", "target": "ChatOutput-OG4M9", "targetHandle": "{œfieldNameœ: œinput_valueœ, œidœ: œChatOutput-OG4M9œ, œinputTypesœ: [œDataœ, œDataFrameœ, œMessageœ], œtypeœ: œotherœ}" }, { "className": "", "data": { "sourceHandle": { "dataType": "TextInput", "id": "TextInput-k48NL", "name": "text", "output_types": [ "Message" ] }, "targetHandle": { "fieldName": "search_query", "id": "KnowledgeRetrieval-kgwih", "inputTypes": [ "Message" ], "type": "str" } }, "id": "xy-edge__TextInput-k48NL{œdataTypeœ:œTextInputœ,œidœ:œTextInput-k48NLœ,œnameœ:œtextœ,œoutput_typesœ:[œMessageœ]}-KnowledgeRetrieval-kgwih{œfieldNameœ:œsearch_queryœ,œidœ:œKnowledgeRetrieval-kgwihœ,œinputTypesœ:[œMessageœ],œtypeœ:œstrœ}", "source": "TextInput-k48NL", "sourceHandle": "{œdataTypeœ: œTextInputœ, œidœ: œTextInput-k48NLœ, œnameœ: œtextœ, œoutput_typesœ: [œMessageœ]}", "target": "KnowledgeRetrieval-kgwih", "targetHandle": "{œfieldNameœ: œsearch_queryœ, œidœ: œKnowledgeRetrieval-kgwihœ, œinputTypesœ: [œMessageœ], œtypeœ: œstrœ}" } ], "nodes": [ { "data": { "id": "note-6CE3d", "node": { "description": "## Knowledge Retrieval\n\nA stand-alone component handles the retrieval of ingested knowledge from existing knowledge bases. To retrieve knowledge:\n\n1. Select your knowledge base from the Knowledge Base dropdown. If you do not see it, choose \"Refresh List\".\n2. (Optional) Enter a Search Query to be performed against the knowledge base.\n\nNote that by default, 5 results are returned, which can be configured by clicking Controls at the top of the component.\n", "display_name": "", "documentation": "", "template": {} }, "type": "note" }, "dragging": false, "height": 384, "id": "note-6CE3d", "measured": { "height": 384, "width": 371 }, "position": { "x": -215.63964109627526, "y": -365.1224988685513 }, "resizing": false, "selected": false, "type": "noteNode", "width": 371 }, { "data": { "id": "TextInput-k48NL", "node": { "base_classes": [ "Message" ], "beta": false, "conditional_paths": [], "custom_fields": {}, "description": "Get user text inputs.", "display_name": "Text Input", "documentation": "https://docs.langflow.org/components-io#text-input", "edited": false, "field_order": [ "input_value" ], "frozen": false, "icon": "type", "legacy": false, "lf_version": "1.5.0.post1", "metadata": {}, "minimized": false, "output_types": [], "outputs": [ { "allows_loop": false, "cache": true, "display_name": "Output Text", "group_outputs": false, "method": "text_response", "name": "text", "selected": "Message", "tool_mode": true, "types": [ "Message" ], "value": "__UNDEFINED__" } ], "pinned": false, "template": { "_type": "Component", "code": { "advanced": true, "dynamic": true, "fileTypes": [], "file_path": "", "info": "", "list": false, "load_from_db": false, "multiline": true, "name": "code", "password": false, "placeholder": "", "required": true, "show": true, "title_case": false, "type": "code", "value": "from langflow.base.io.text import TextComponent\nfrom langflow.io import MultilineInput, Output\nfrom langflow.schema.message import Message\n\n\nclass TextInputComponent(TextComponent):\n display_name = \"Text Input\"\n description = \"Get user text inputs.\"\n documentation: str = \"https://docs.langflow.org/components-io#text-input\"\n icon = \"type\"\n name = \"TextInput\"\n\n inputs = [\n MultilineInput(\n name=\"input_value\",\n display_name=\"Text\",\n info=\"Text to be passed as input.\",\n ),\n ]\n outputs = [\n Output(display_name=\"Output Text\", name=\"text\", method=\"text_response\"),\n ]\n\n def text_response(self) -> Message:\n return Message(\n text=self.input_value,\n )\n" }, "input_value": { "_input_type": "MultilineInput", "advanced": false, "copy_field": false, "display_name": "Text", "dynamic": false, "info": "Text to be passed as input.", "input_types": [ "Message" ], "list": false, "list_add_label": "Add More", "load_from_db": false, "multiline": true, "name": "input_value", "placeholder": "", "required": false, "show": true, "title_case": false, "tool_mode": false, "trace_as_input": true, "trace_as_metadata": true, "type": "str", "value": "IBM Acquires DataStax" } }, "tool_mode": false }, "showNode": true, "type": "TextInput" }, "dragging": false, "id": "TextInput-k48NL", "measured": { "height": 204, "width": 320 }, "position": { "x": 234.35280633316273, "y": -280.9003423728733 }, "selected": false, "type": "genericNode" }, { "data": { "id": "ChatOutput-OG4M9", "node": { "base_classes": [ "Message" ], "beta": false, "conditional_paths": [], "custom_fields": {}, "description": "Display a chat message in the Playground.", "display_name": "Chat Output", "documentation": "https://docs.langflow.org/components-io#chat-output", "edited": false, "field_order": [ "input_value", "should_store_message", "sender", "sender_name", "session_id", "data_template", "background_color", "chat_icon", "text_color", "clean_data" ], "frozen": false, "icon": "MessagesSquare", "legacy": false, "lf_version": "1.5.0.post1", "metadata": {}, "minimized": true, "output_types": [], "outputs": [ { "allows_loop": false, "cache": true, "display_name": "Output Message", "group_outputs": false, "method": "message_response", "name": "message", "selected": "Message", "tool_mode": true, "types": [ "Message" ], "value": "__UNDEFINED__" } ], "pinned": false, "template": { "_type": "Component", "code": { "advanced": true, "dynamic": true, "fileTypes": [], "file_path": "", "info": "", "list": false, "load_from_db": false, "multiline": true, "name": "code", "password": false, "placeholder": "", "required": true, "show": true, "title_case": false, "type": "code", "value": "from collections.abc import Generator\nfrom typing import Any\n\nimport orjson\nfrom fastapi.encoders import jsonable_encoder\n\nfrom langflow.base.io.chat import ChatComponent\nfrom langflow.helpers.data import safe_convert\nfrom langflow.inputs.inputs import BoolInput, DropdownInput, HandleInput, MessageTextInput\nfrom langflow.schema.data import Data\nfrom langflow.schema.dataframe import DataFrame\nfrom langflow.schema.message import Message\nfrom langflow.schema.properties import Source\nfrom langflow.template.field.base import Output\nfrom langflow.utils.constants import (\n MESSAGE_SENDER_AI,\n MESSAGE_SENDER_NAME_AI,\n MESSAGE_SENDER_USER,\n)\n\n\nclass ChatOutput(ChatComponent):\n display_name = \"Chat Output\"\n description = \"Display a chat message in the Playground.\"\n documentation: str = \"https://docs.langflow.org/components-io#chat-output\"\n icon = \"MessagesSquare\"\n name = \"ChatOutput\"\n minimized = True\n\n inputs = [\n HandleInput(\n name=\"input_value\",\n display_name=\"Inputs\",\n info=\"Message to be passed as output.\",\n input_types=[\"Data\", \"DataFrame\", \"Message\"],\n required=True,\n ),\n BoolInput(\n name=\"should_store_message\",\n display_name=\"Store Messages\",\n info=\"Store the message in the history.\",\n value=True,\n advanced=True,\n ),\n DropdownInput(\n name=\"sender\",\n display_name=\"Sender Type\",\n options=[MESSAGE_SENDER_AI, MESSAGE_SENDER_USER],\n value=MESSAGE_SENDER_AI,\n advanced=True,\n info=\"Type of sender.\",\n ),\n MessageTextInput(\n name=\"sender_name\",\n display_name=\"Sender Name\",\n info=\"Name of the sender.\",\n value=MESSAGE_SENDER_NAME_AI,\n advanced=True,\n ),\n MessageTextInput(\n name=\"session_id\",\n display_name=\"Session ID\",\n info=\"The session ID of the chat. If empty, the current session ID parameter will be used.\",\n advanced=True,\n ),\n MessageTextInput(\n name=\"data_template\",\n display_name=\"Data Template\",\n value=\"{text}\",\n advanced=True,\n info=\"Template to convert Data to Text. If left empty, it will be dynamically set to the Data's text key.\",\n ),\n ]\n outputs = [\n Output(\n display_name=\"Output Message\",\n name=\"message\",\n method=\"message_response\",\n ),\n ]\n\n def _build_source(self, id_: str | None, display_name: str | None, source: str | None) -> Source:\n source_dict = {}\n if id_:\n source_dict[\"id\"] = id_\n if display_name:\n source_dict[\"display_name\"] = display_name\n if source:\n # Handle case where source is a ChatOpenAI object\n if hasattr(source, \"model_name\"):\n source_dict[\"source\"] = source.model_name\n elif hasattr(source, \"model\"):\n source_dict[\"source\"] = str(source.model)\n else:\n source_dict[\"source\"] = str(source)\n return Source(**source_dict)\n\n async def message_response(self) -> Message:\n # First convert the input to string if needed\n text = self.convert_to_string()\n\n # Get source properties\n source, icon, display_name, source_id = self.get_properties_from_source_component()\n\n # Create or use existing Message object\n if isinstance(self.input_value, Message):\n message = self.input_value\n # Update message properties\n message.text = text\n else:\n message = Message(text=text)\n\n # Set message properties\n message.sender = self.sender\n message.sender_name = self.sender_name\n message.session_id = self.session_id\n message.flow_id = self.graph.flow_id if hasattr(self, \"graph\") else None\n message.properties.source = self._build_source(source_id, display_name, source)\n\n # Store message if needed\n if self.session_id and self.should_store_message:\n stored_message = await self.send_message(message)\n self.message.value = stored_message\n message = stored_message\n\n self.status = message\n return message\n\n def _serialize_data(self, data: Data) -> str:\n \"\"\"Serialize Data object to JSON string.\"\"\"\n # Convert data.data to JSON-serializable format\n serializable_data = jsonable_encoder(data.data)\n # Serialize with orjson, enabling pretty printing with indentation\n json_bytes = orjson.dumps(serializable_data, option=orjson.OPT_INDENT_2)\n # Convert bytes to string and wrap in Markdown code blocks\n return \"```json\\n\" + json_bytes.decode(\"utf-8\") + \"\\n```\"\n\n def _validate_input(self) -> None:\n \"\"\"Validate the input data and raise ValueError if invalid.\"\"\"\n if self.input_value is None:\n msg = \"Input data cannot be None\"\n raise ValueError(msg)\n if isinstance(self.input_value, list) and not all(\n isinstance(item, Message | Data | DataFrame | str) for item in self.input_value\n ):\n invalid_types = [\n type(item).__name__\n for item in self.input_value\n if not isinstance(item, Message | Data | DataFrame | str)\n ]\n msg = f\"Expected Data or DataFrame or Message or str, got {invalid_types}\"\n raise TypeError(msg)\n if not isinstance(\n self.input_value,\n Message | Data | DataFrame | str | list | Generator | type(None),\n ):\n type_name = type(self.input_value).__name__\n msg = f\"Expected Data or DataFrame or Message or str, Generator or None, got {type_name}\"\n raise TypeError(msg)\n\n def convert_to_string(self) -> str | Generator[Any, None, None]:\n \"\"\"Convert input data to string with proper error handling.\"\"\"\n self._validate_input()\n if isinstance(self.input_value, list):\n clean_data: bool = getattr(self, \"clean_data\", False)\n return \"\\n\".join([safe_convert(item, clean_data=clean_data) for item in self.input_value])\n if isinstance(self.input_value, Generator):\n return self.input_value\n return safe_convert(self.input_value)\n" }, "data_template": { "_input_type": "MessageTextInput", "advanced": true, "display_name": "Data Template", "dynamic": false, "info": "Template to convert Data to Text. If left empty, it will be dynamically set to the Data's text key.", "input_types": [ "Message" ], "list": false, "list_add_label": "Add More", "load_from_db": false, "name": "data_template", "placeholder": "", "required": false, "show": true, "title_case": false, "tool_mode": false, "trace_as_input": true, "trace_as_metadata": true, "type": "str", "value": "{text}" }, "input_value": { "_input_type": "HandleInput", "advanced": false, "display_name": "Inputs", "dynamic": false, "info": "Message to be passed as output.", "input_types": [ "Data", "DataFrame", "Message" ], "list": false, "list_add_label": "Add More", "name": "input_value", "placeholder": "", "required": true, "show": true, "title_case": false, "trace_as_metadata": true, "type": "other", "value": "" }, "sender": { "_input_type": "DropdownInput", "advanced": true, "combobox": false, "dialog_inputs": {}, "display_name": "Sender Type", "dynamic": false, "info": "Type of sender.", "name": "sender", "options": [ "Machine", "User" ], "options_metadata": [], "placeholder": "", "required": false, "show": true, "title_case": false, "toggle": false, "tool_mode": false, "trace_as_metadata": true, "type": "str", "value": "Machine" }, "sender_name": { "_input_type": "MessageTextInput", "advanced": true, "display_name": "Sender Name", "dynamic": false, "info": "Name of the sender.", "input_types": [ "Message" ], "list": false, "list_add_label": "Add More", "load_from_db": false, "name": "sender_name", "placeholder": "", "required": false, "show": true, "title_case": false, "tool_mode": false, "trace_as_input": true, "trace_as_metadata": true, "type": "str", "value": "AI" }, "session_id": { "_input_type": "MessageTextInput", "advanced": true, "display_name": "Session ID", "dynamic": false, "info": "The session ID of the chat. If empty, the current session ID parameter will be used.", "input_types": [ "Message" ], "list": false, "list_add_label": "Add More", "load_from_db": false, "name": "session_id", "placeholder": "", "required": false, "show": true, "title_case": false, "tool_mode": false, "trace_as_input": true, "trace_as_metadata": true, "type": "str", "value": "" }, "should_store_message": { "_input_type": "BoolInput", "advanced": true, "display_name": "Store Messages", "dynamic": false, "info": "Store the message in the history.", "list": false, "list_add_label": "Add More", "name": "should_store_message", "placeholder": "", "required": false, "show": true, "title_case": false, "tool_mode": false, "trace_as_metadata": true, "type": "bool", "value": true } }, "tool_mode": false }, "showNode": false, "type": "ChatOutput" }, "dragging": false, "id": "ChatOutput-OG4M9", "measured": { "height": 48, "width": 192 }, "position": { "x": 1043.5413322661916, "y": -202.42300688367868 }, "selected": false, "type": "genericNode" }, { "data": { "id": "KnowledgeRetrieval-kgwih", "node": { "base_classes": [ "DataFrame" ], "beta": false, "conditional_paths": [], "custom_fields": {}, "description": "Search and retrieve data from knowledge.", "display_name": "Knowledge Retrieval", "documentation": "", "edited": false, "field_order": [ "knowledge_base", "api_key", "search_query", "top_k", "include_metadata", "include_embeddings" ], "frozen": false, "icon": "download", "last_updated": "2025-08-26T16:19:16.681Z", "legacy": false, "metadata": {}, "minimized": false, "output_types": [], "outputs": [ { "allows_loop": false, "cache": true, "display_name": "Results", "group_outputs": false, "method": "retrieve_data", "name": "retrieve_data", "selected": "DataFrame", "tool_mode": true, "types": [ "DataFrame" ], "value": "__UNDEFINED__" } ], "pinned": false, "template": { "_type": "Component", "api_key": { "_input_type": "SecretStrInput", "advanced": true, "display_name": "Embedding Provider API Key", "dynamic": false, "info": "API key for the embedding provider to generate embeddings.", "input_types": [], "load_from_db": false, "name": "api_key", "password": true, "placeholder": "", "required": false, "show": true, "title_case": false, "type": "str", "value": "" }, "code": { "advanced": true, "dynamic": true, "fileTypes": [], "file_path": "", "info": "", "list": false, "load_from_db": false, "multiline": true, "name": "code", "password": false, "placeholder": "", "required": true, "show": true, "title_case": false, "type": "code", "value": "import json\nfrom pathlib import Path\nfrom typing import Any\n\nfrom cryptography.fernet import InvalidToken\nfrom langchain_chroma import Chroma\nfrom loguru import logger\nfrom pydantic import SecretStr\n\nfrom langflow.base.knowledge_bases.knowledge_base_utils import get_knowledge_bases\nfrom langflow.custom import Component\nfrom langflow.io import BoolInput, DropdownInput, IntInput, MessageTextInput, Output, SecretStrInput\nfrom langflow.schema.data import Data\nfrom langflow.schema.dataframe import DataFrame\nfrom langflow.services.auth.utils import decrypt_api_key\nfrom langflow.services.database.models.user.crud import get_user_by_id\nfrom langflow.services.deps import get_settings_service, session_scope\n\nsettings = get_settings_service().settings\nknowledge_directory = settings.knowledge_bases_dir\nif not knowledge_directory:\n msg = \"Knowledge bases directory is not set in the settings.\"\n raise ValueError(msg)\nKNOWLEDGE_BASES_ROOT_PATH = Path(knowledge_directory).expanduser()\n\n\nclass KnowledgeRetrievalComponent(Component):\n display_name = \"Knowledge Retrieval\"\n description = \"Search and retrieve data from knowledge.\"\n icon = \"download\"\n name = \"KnowledgeRetrieval\"\n\n inputs = [\n DropdownInput(\n name=\"knowledge_base\",\n display_name=\"Knowledge\",\n info=\"Select the knowledge to load data from.\",\n required=True,\n options=[],\n refresh_button=True,\n real_time_refresh=True,\n ),\n SecretStrInput(\n name=\"api_key\",\n display_name=\"Embedding Provider API Key\",\n info=\"API key for the embedding provider to generate embeddings.\",\n advanced=True,\n required=False,\n ),\n MessageTextInput(\n name=\"search_query\",\n display_name=\"Search Query\",\n info=\"Optional search query to filter knowledge base data.\",\n tool_mode=True,\n ),\n IntInput(\n name=\"top_k\",\n display_name=\"Top K Results\",\n info=\"Number of top results to return from the knowledge base.\",\n value=5,\n advanced=True,\n required=False,\n ),\n BoolInput(\n name=\"include_metadata\",\n display_name=\"Include Metadata\",\n info=\"Whether to include all metadata in the output. If false, only content is returned.\",\n value=True,\n advanced=False,\n ),\n BoolInput(\n name=\"include_embeddings\",\n display_name=\"Include Embeddings\",\n info=\"Whether to include embeddings in the output. Only applicable if 'Include Metadata' is enabled.\",\n value=False,\n advanced=True,\n ),\n ]\n\n outputs = [\n Output(\n name=\"retrieve_data\",\n display_name=\"Results\",\n method=\"retrieve_data\",\n info=\"Returns the data from the selected knowledge base.\",\n ),\n ]\n\n async def update_build_config(self, build_config, field_value, field_name=None): # noqa: ARG002\n if field_name == \"knowledge_base\":\n # Update the knowledge base options dynamically\n build_config[\"knowledge_base\"][\"options\"] = await get_knowledge_bases(\n KNOWLEDGE_BASES_ROOT_PATH,\n user_id=self.user_id, # Use the user_id from the component context\n )\n\n # If the selected knowledge base is not available, reset it\n if build_config[\"knowledge_base\"][\"value\"] not in build_config[\"knowledge_base\"][\"options\"]:\n build_config[\"knowledge_base\"][\"value\"] = None\n\n return build_config\n\n def _get_kb_metadata(self, kb_path: Path) -> dict:\n \"\"\"Load and process knowledge base metadata.\"\"\"\n metadata: dict[str, Any] = {}\n metadata_file = kb_path / \"embedding_metadata.json\"\n if not metadata_file.exists():\n logger.warning(f\"Embedding metadata file not found at {metadata_file}\")\n return metadata\n\n try:\n with metadata_file.open(\"r\", encoding=\"utf-8\") as f:\n metadata = json.load(f)\n except json.JSONDecodeError:\n logger.error(f\"Error decoding JSON from {metadata_file}\")\n return {}\n\n # Decrypt API key if it exists\n if \"api_key\" in metadata and metadata.get(\"api_key\"):\n settings_service = get_settings_service()\n try:\n decrypted_key = decrypt_api_key(metadata[\"api_key\"], settings_service)\n metadata[\"api_key\"] = decrypted_key\n except (InvalidToken, TypeError, ValueError) as e:\n logger.error(f\"Could not decrypt API key. Please provide it manually. Error: {e}\")\n metadata[\"api_key\"] = None\n return metadata\n\n def _build_embeddings(self, metadata: dict):\n \"\"\"Build embedding model from metadata.\"\"\"\n runtime_api_key = self.api_key.get_secret_value() if isinstance(self.api_key, SecretStr) else self.api_key\n provider = metadata.get(\"embedding_provider\")\n model = metadata.get(\"embedding_model\")\n api_key = runtime_api_key or metadata.get(\"api_key\")\n chunk_size = metadata.get(\"chunk_size\")\n\n # Handle various providers\n if provider == \"OpenAI\":\n from langchain_openai import OpenAIEmbeddings\n\n if not api_key:\n msg = \"OpenAI API key is required. Provide it in the component's advanced settings.\"\n raise ValueError(msg)\n return OpenAIEmbeddings(\n model=model,\n api_key=api_key,\n chunk_size=chunk_size,\n )\n if provider == \"HuggingFace\":\n from langchain_huggingface import HuggingFaceEmbeddings\n\n return HuggingFaceEmbeddings(\n model=model,\n )\n if provider == \"Cohere\":\n from langchain_cohere import CohereEmbeddings\n\n if not api_key:\n msg = \"Cohere API key is required when using Cohere provider\"\n raise ValueError(msg)\n return CohereEmbeddings(\n model=model,\n cohere_api_key=api_key,\n )\n if provider == \"Custom\":\n # For custom embedding models, we would need additional configuration\n msg = \"Custom embedding models not yet supported\"\n raise NotImplementedError(msg)\n # Add other providers here if they become supported in ingest\n msg = f\"Embedding provider '{provider}' is not supported for retrieval.\"\n raise NotImplementedError(msg)\n\n async def retrieve_data(self) -> DataFrame:\n \"\"\"Retrieve data from the selected knowledge base by reading the Chroma collection.\n\n Returns:\n A DataFrame containing the data rows from the knowledge base.\n \"\"\"\n # Get the current user\n async with session_scope() as db:\n if not self.user_id:\n msg = \"User ID is required for fetching Knowledge Base data.\"\n raise ValueError(msg)\n current_user = await get_user_by_id(db, self.user_id)\n if not current_user:\n msg = f\"User with ID {self.user_id} not found.\"\n raise ValueError(msg)\n kb_user = current_user.username\n kb_path = KNOWLEDGE_BASES_ROOT_PATH / kb_user / self.knowledge_base\n\n metadata = self._get_kb_metadata(kb_path)\n if not metadata:\n msg = f\"Metadata not found for knowledge base: {self.knowledge_base}. Ensure it has been indexed.\"\n raise ValueError(msg)\n\n # Build the embedder for the knowledge base\n embedding_function = self._build_embeddings(metadata)\n\n # Load vector store\n chroma = Chroma(\n persist_directory=str(kb_path),\n embedding_function=embedding_function,\n collection_name=self.knowledge_base,\n )\n\n # If a search query is provided, perform a similarity search\n if self.search_query:\n # Use the search query to perform a similarity search\n logger.info(f\"Performing similarity search with query: {self.search_query}\")\n results = chroma.similarity_search_with_score(\n query=self.search_query or \"\",\n k=self.top_k,\n )\n else:\n results = chroma.similarity_search(\n query=self.search_query or \"\",\n k=self.top_k,\n )\n\n # For each result, make it a tuple to match the expected output format\n results = [(doc, 0) for doc in results] # Assign a dummy score of 0\n\n # If include_embeddings is enabled, get embeddings for the results\n id_to_embedding = {}\n if self.include_embeddings and results:\n doc_ids = [doc[0].metadata.get(\"_id\") for doc in results if doc[0].metadata.get(\"_id\")]\n\n # Only proceed if we have valid document IDs\n if doc_ids:\n # Access underlying client to get embeddings\n collection = chroma._client.get_collection(name=self.knowledge_base)\n embeddings_result = collection.get(where={\"_id\": {\"$in\": doc_ids}}, include=[\"metadatas\", \"embeddings\"])\n\n # Create a mapping from document ID to embedding\n for i, metadata in enumerate(embeddings_result.get(\"metadatas\", [])):\n if metadata and \"_id\" in metadata:\n id_to_embedding[metadata[\"_id\"]] = embeddings_result[\"embeddings\"][i]\n\n # Build output data based on include_metadata setting\n data_list = []\n for doc in results:\n kwargs = {\n \"content\": doc[0].page_content,\n }\n if self.search_query:\n kwargs[\"_score\"] = -1 * doc[1]\n if self.include_metadata:\n # Include all metadata, embeddings, and content\n kwargs.update(doc[0].metadata)\n if self.include_embeddings:\n kwargs[\"_embeddings\"] = id_to_embedding.get(doc[0].metadata.get(\"_id\"))\n\n data_list.append(Data(**kwargs))\n\n # Return the DataFrame containing the data\n return DataFrame(data=data_list)\n" }, "include_embeddings": { "_input_type": "BoolInput", "advanced": true, "display_name": "Include Embeddings", "dynamic": false, "info": "Whether to include embeddings in the output. Only applicable if 'Include Metadata' is enabled.", "list": false, "list_add_label": "Add More", "name": "include_embeddings", "placeholder": "", "required": false, "show": true, "title_case": false, "tool_mode": false, "trace_as_metadata": true, "type": "bool", "value": false }, "include_metadata": { "_input_type": "BoolInput", "advanced": false, "display_name": "Include Metadata", "dynamic": false, "info": "Whether to include all metadata in the output. If false, only content is returned.", "list": false, "list_add_label": "Add More", "name": "include_metadata", "placeholder": "", "required": false, "show": true, "title_case": false, "tool_mode": false, "trace_as_metadata": true, "type": "bool", "value": true }, "knowledge_base": { "_input_type": "DropdownInput", "advanced": false, "combobox": false, "dialog_inputs": {}, "display_name": "Knowledge", "dynamic": false, "info": "Select the knowledge to load data from.", "name": "knowledge_base", "options": [], "options_metadata": [], "placeholder": "", "real_time_refresh": true, "refresh_button": true, "required": true, "show": true, "title_case": false, "toggle": false, "tool_mode": false, "trace_as_metadata": true, "type": "str", "value": null }, "search_query": { "_input_type": "MessageTextInput", "advanced": false, "display_name": "Search Query", "dynamic": false, "info": "Optional search query to filter knowledge base data.", "input_types": [ "Message" ], "list": false, "list_add_label": "Add More", "load_from_db": false, "name": "search_query", "placeholder": "", "required": false, "show": true, "title_case": false, "tool_mode": true, "trace_as_input": true, "trace_as_metadata": true, "type": "str", "value": "" }, "top_k": { "_input_type": "IntInput", "advanced": true, "display_name": "Top K Results", "dynamic": false, "info": "Number of top results to return from the knowledge base.", "list": false, "list_add_label": "Add More", "name": "top_k", "placeholder": "", "required": false, "show": true, "title_case": false, "tool_mode": false, "trace_as_metadata": true, "type": "int", "value": 5 } }, "tool_mode": false }, "showNode": true, "type": "KnowledgeRetrieval" }, "dragging": false, "id": "KnowledgeRetrieval-kgwih", "measured": { "height": 329, "width": 320 }, "position": { "x": 635.7729107873928, "y": -337.735556504938 }, "selected": false, "type": "genericNode" } ], "viewport": { "x": 90.80151692622985, "y": 591.5552904741861, "zoom": 1.0053880437940252 } }, "description": "An example of performing a vector search against data in a Knowledge Base to retrieve relevant documents.", "endpoint_name": null, "id": "e262d49f-c800-4962-948b-c94f79eb5fb8", "is_component": false, "last_tested_version": "1.5.0.post2", "name": "Knowledge Retrieval", "tags": [] }