langflow-base-nightly 1.7.0.dev52__py3-none-any.whl → 1.7.0.dev55__py3-none-any.whl

langflow/initial_setup/starter_projects/Knowledge Ingestion.json

@@ -737,7 +737,7 @@
             "last_updated": "2025-09-29T18:32:20.563Z",
             "legacy": false,
             "metadata": {
-              "code_hash": "c753e92261ae",
+              "code_hash": "52a451e4f053",
               "dependencies": {
                 "dependencies": [
                   {
@@ -867,7 +867,7 @@
                 "show": true,
                 "title_case": false,
                 "type": "code",
-                "value": "from __future__ import annotations\n\nimport asyncio\nimport contextlib\nimport hashlib\nimport json\nimport re\nimport uuid\nfrom dataclasses import asdict, dataclass, field\nfrom datetime import datetime, timezone\nfrom pathlib import Path\nfrom typing import TYPE_CHECKING, Any\n\nimport pandas as pd\nfrom cryptography.fernet import InvalidToken\nfrom langchain_chroma import Chroma\nfrom langflow.services.auth.utils import decrypt_api_key, encrypt_api_key\nfrom langflow.services.database.models.user.crud import get_user_by_id\n\nfrom lfx.base.knowledge_bases.knowledge_base_utils import get_knowledge_bases\nfrom lfx.base.models.openai_constants import OPENAI_EMBEDDING_MODEL_NAMES\nfrom lfx.components.processing.converter import convert_to_dataframe\nfrom lfx.custom import Component\nfrom lfx.io import (\n    BoolInput,\n    DropdownInput,\n    HandleInput,\n    IntInput,\n    Output,\n    SecretStrInput,\n    StrInput,\n    TableInput,\n)\nfrom lfx.schema.data import Data\nfrom lfx.schema.table import EditMode\nfrom lfx.services.deps import (\n    get_settings_service,\n    get_variable_service,\n    session_scope,\n)\n\nif TYPE_CHECKING:\n    from lfx.schema.dataframe import DataFrame\n\nHUGGINGFACE_MODEL_NAMES = [\n    \"sentence-transformers/all-MiniLM-L6-v2\",\n    \"sentence-transformers/all-mpnet-base-v2\",\n]\nCOHERE_MODEL_NAMES = [\"embed-english-v3.0\", \"embed-multilingual-v3.0\"]\n\n_KNOWLEDGE_BASES_ROOT_PATH: Path | None = None\n\n\ndef _get_knowledge_bases_root_path() -> Path:\n    \"\"\"Lazy load the knowledge bases root path from settings.\"\"\"\n    global _KNOWLEDGE_BASES_ROOT_PATH  # noqa: PLW0603\n    if _KNOWLEDGE_BASES_ROOT_PATH is None:\n        settings = get_settings_service().settings\n        knowledge_directory = settings.knowledge_bases_dir\n        if not knowledge_directory:\n            msg = \"Knowledge bases directory is not set in the settings.\"\n            raise ValueError(msg)\n        _KNOWLEDGE_BASES_ROOT_PATH = Path(knowledge_directory).expanduser()\n    return _KNOWLEDGE_BASES_ROOT_PATH\n\n\nclass KnowledgeIngestionComponent(Component):\n    \"\"\"Create or append to Langflow Knowledge from a DataFrame.\"\"\"\n\n    # ------ UI metadata ---------------------------------------------------\n    display_name = \"Knowledge Ingestion\"\n    description = \"Create or update knowledge in Langflow.\"\n    icon = \"upload\"\n    name = \"KnowledgeIngestion\"\n\n    def __init__(self, *args, **kwargs) -> None:\n        super().__init__(*args, **kwargs)\n        self._cached_kb_path: Path | None = None\n\n    @dataclass\n    class NewKnowledgeBaseInput:\n        functionality: str = \"create\"\n        fields: dict[str, dict] = field(\n            default_factory=lambda: {\n                \"data\": {\n                    \"node\": {\n                        \"name\": \"create_knowledge_base\",\n                        \"description\": \"Create new knowledge in Langflow.\",\n                        \"display_name\": \"Create new knowledge\",\n                        \"field_order\": [\n                            \"01_new_kb_name\",\n                            \"02_embedding_model\",\n                            \"03_api_key\",\n                        ],\n                        \"template\": {\n                            \"01_new_kb_name\": StrInput(\n                                name=\"new_kb_name\",\n                                display_name=\"Knowledge Name\",\n                                info=\"Name of the new knowledge to create.\",\n                                required=True,\n                            ),\n                            \"02_embedding_model\": DropdownInput(\n                                name=\"embedding_model\",\n                                display_name=\"Choose Embedding\",\n                                info=\"Select the embedding model to use for this knowledge base.\",\n                                required=True,\n                                options=OPENAI_EMBEDDING_MODEL_NAMES + HUGGINGFACE_MODEL_NAMES + COHERE_MODEL_NAMES,\n                                options_metadata=[{\"icon\": \"OpenAI\"} for _ in OPENAI_EMBEDDING_MODEL_NAMES]\n                                + [{\"icon\": \"HuggingFace\"} for _ in HUGGINGFACE_MODEL_NAMES]\n                                + [{\"icon\": \"Cohere\"} for _ in COHERE_MODEL_NAMES],\n                            ),\n                            \"03_api_key\": SecretStrInput(\n                                name=\"api_key\",\n                                display_name=\"API Key\",\n                                info=\"Provider API key for embedding model\",\n                                required=True,\n                                load_from_db=False,\n                            ),\n                        },\n                    },\n                }\n            }\n        )\n\n    # ------ Inputs --------------------------------------------------------\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            dialog_inputs=asdict(NewKnowledgeBaseInput()),\n        ),\n        HandleInput(\n            name=\"input_df\",\n            display_name=\"Input\",\n            info=(\n                \"Table with all original columns (already chunked / processed). \"\n                \"Accepts Data or DataFrame. If Data is provided, it is converted to a DataFrame automatically.\"\n            ),\n            input_types=[\"Data\", \"DataFrame\"],\n            required=True,\n        ),\n        TableInput(\n            name=\"column_config\",\n            display_name=\"Column Configuration\",\n            info=\"Configure column behavior for the knowledge base.\",\n            required=True,\n            table_schema=[\n                {\n                    \"name\": \"column_name\",\n                    \"display_name\": \"Column Name\",\n                    \"type\": \"str\",\n                    \"description\": \"Name of the column in the source DataFrame\",\n                    \"edit_mode\": EditMode.INLINE,\n                },\n                {\n                    \"name\": \"vectorize\",\n                    \"display_name\": \"Vectorize\",\n                    \"type\": \"boolean\",\n                    \"description\": \"Create embeddings for this column\",\n                    \"default\": False,\n                    \"edit_mode\": EditMode.INLINE,\n                },\n                {\n                    \"name\": \"identifier\",\n                    \"display_name\": \"Identifier\",\n                    \"type\": \"boolean\",\n                    \"description\": \"Use this column as unique identifier\",\n                    \"default\": False,\n                    \"edit_mode\": EditMode.INLINE,\n                },\n            ],\n            value=[\n                {\n                    \"column_name\": \"text\",\n                    \"vectorize\": True,\n                    \"identifier\": True,\n                },\n            ],\n        ),\n        IntInput(\n            name=\"chunk_size\",\n            display_name=\"Chunk Size\",\n            info=\"Batch size for processing embeddings\",\n            advanced=True,\n            value=1000,\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        BoolInput(\n            name=\"allow_duplicates\",\n            display_name=\"Allow Duplicates\",\n            info=\"Allow duplicate rows in the knowledge base\",\n            advanced=True,\n            value=False,\n        ),\n    ]\n\n    # ------ Outputs -------------------------------------------------------\n    outputs = [Output(display_name=\"Results\", name=\"dataframe_output\", method=\"build_kb_info\")]\n\n    # ------ Internal helpers ---------------------------------------------\n    def _get_kb_root(self) -> Path:\n        \"\"\"Return the root directory for knowledge bases.\"\"\"\n        return _get_knowledge_bases_root_path()\n\n    def _validate_column_config(self, df_source: pd.DataFrame) -> list[dict[str, Any]]:\n        \"\"\"Validate column configuration using Structured Output patterns.\"\"\"\n        if not self.column_config:\n            msg = \"Column configuration cannot be empty\"\n            raise ValueError(msg)\n\n        # Convert table input to list of dicts (similar to Structured Output)\n        config_list = self.column_config if isinstance(self.column_config, list) else []\n\n        # Validate column names exist in DataFrame\n        df_columns = set(df_source.columns)\n        for config in config_list:\n            col_name = config.get(\"column_name\")\n            if col_name not in df_columns:\n                msg = f\"Column '{col_name}' not found in DataFrame. Available columns: {sorted(df_columns)}\"\n                raise ValueError(msg)\n\n        return config_list\n\n    def _get_embedding_provider(self, embedding_model: str) -> str:\n        \"\"\"Get embedding provider by matching model name to lists.\"\"\"\n        if embedding_model in OPENAI_EMBEDDING_MODEL_NAMES:\n            return \"OpenAI\"\n        if embedding_model in HUGGINGFACE_MODEL_NAMES:\n            return \"HuggingFace\"\n        if embedding_model in COHERE_MODEL_NAMES:\n            return \"Cohere\"\n        return \"Custom\"\n\n    def _build_embeddings(self, embedding_model: str, api_key: str):\n        \"\"\"Build embedding model using provider patterns.\"\"\"\n        # Get provider by matching model name to lists\n        provider = self._get_embedding_provider(embedding_model)\n\n        # Validate provider and model\n        if provider == \"OpenAI\":\n            from langchain_openai import OpenAIEmbeddings\n\n            if not api_key:\n                msg = \"OpenAI API key is required when using OpenAI provider\"\n                raise ValueError(msg)\n            return OpenAIEmbeddings(\n                model=embedding_model,\n                api_key=api_key,\n                chunk_size=self.chunk_size,\n            )\n        if provider == \"HuggingFace\":\n            from langchain_huggingface import HuggingFaceEmbeddings\n\n            return HuggingFaceEmbeddings(\n                model=embedding_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=embedding_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        msg = f\"Unknown provider: {provider}\"\n        raise ValueError(msg)\n\n    def _build_embedding_metadata(self, embedding_model, api_key) -> dict[str, Any]:\n        \"\"\"Build embedding model metadata.\"\"\"\n        # Get provider by matching model name to lists\n        embedding_provider = self._get_embedding_provider(embedding_model)\n\n        api_key_to_save = None\n        if api_key and hasattr(api_key, \"get_secret_value\"):\n            api_key_to_save = api_key.get_secret_value()\n        elif isinstance(api_key, str):\n            api_key_to_save = api_key\n\n        encrypted_api_key = None\n        if api_key_to_save:\n            settings_service = get_settings_service()\n            try:\n                encrypted_api_key = encrypt_api_key(api_key_to_save, settings_service=settings_service)\n            except (TypeError, ValueError) as e:\n                self.log(f\"Could not encrypt API key: {e}\")\n\n        return {\n            \"embedding_provider\": embedding_provider,\n            \"embedding_model\": embedding_model,\n            \"api_key\": encrypted_api_key,\n            \"api_key_used\": bool(api_key),\n            \"chunk_size\": self.chunk_size,\n            \"created_at\": datetime.now(timezone.utc).isoformat(),\n        }\n\n    def _save_embedding_metadata(self, kb_path: Path, embedding_model: str, api_key: str) -> None:\n        \"\"\"Save embedding model metadata.\"\"\"\n        embedding_metadata = self._build_embedding_metadata(embedding_model, api_key)\n        metadata_path = kb_path / \"embedding_metadata.json\"\n        metadata_path.write_text(json.dumps(embedding_metadata, indent=2))\n\n    def _save_kb_files(\n        self,\n        kb_path: Path,\n        config_list: list[dict[str, Any]],\n    ) -> None:\n        \"\"\"Save KB files using File Component storage patterns.\"\"\"\n        try:\n            # Create directory (following File Component patterns)\n            kb_path.mkdir(parents=True, exist_ok=True)\n\n            # Save column configuration\n            # Only do this if the file doesn't exist already\n            cfg_path = kb_path / \"schema.json\"\n            if not cfg_path.exists():\n                cfg_path.write_text(json.dumps(config_list, indent=2))\n\n        except (OSError, TypeError, ValueError) as e:\n            self.log(f\"Error saving KB files: {e}\")\n\n    def _build_column_metadata(self, config_list: list[dict[str, Any]], df_source: pd.DataFrame) -> dict[str, Any]:\n        \"\"\"Build detailed column metadata.\"\"\"\n        metadata: dict[str, Any] = {\n            \"total_columns\": len(df_source.columns),\n            \"mapped_columns\": len(config_list),\n            \"unmapped_columns\": len(df_source.columns) - len(config_list),\n            \"columns\": [],\n            \"summary\": {\"vectorized_columns\": [], \"identifier_columns\": []},\n        }\n\n        for config in config_list:\n            col_name = config.get(\"column_name\")\n            vectorize = config.get(\"vectorize\") == \"True\" or config.get(\"vectorize\") is True\n            identifier = config.get(\"identifier\") == \"True\" or config.get(\"identifier\") is True\n\n            # Add to columns list\n            metadata[\"columns\"].append(\n                {\n                    \"name\": col_name,\n                    \"vectorize\": vectorize,\n                    \"identifier\": identifier,\n                }\n            )\n\n            # Update summary\n            if vectorize:\n                metadata[\"summary\"][\"vectorized_columns\"].append(col_name)\n            if identifier:\n                metadata[\"summary\"][\"identifier_columns\"].append(col_name)\n\n        return metadata\n\n    async def _create_vector_store(\n        self,\n        df_source: pd.DataFrame,\n        config_list: list[dict[str, Any]],\n        embedding_model: str,\n        api_key: str,\n    ) -> None:\n        \"\"\"Create vector store following Local DB component pattern.\"\"\"\n        try:\n            # Set up vector store directory\n            vector_store_dir = await self._kb_path()\n            if not vector_store_dir:\n                msg = \"Knowledge base path is not set. Please create a new knowledge base first.\"\n                raise ValueError(msg)\n            vector_store_dir.mkdir(parents=True, exist_ok=True)\n\n            # Create embeddings model\n            embedding_function = self._build_embeddings(embedding_model, api_key)\n\n            # Convert DataFrame to Data objects (following Local DB pattern)\n            data_objects = await self._convert_df_to_data_objects(df_source, config_list)\n\n            # Create vector store\n            chroma = Chroma(\n                persist_directory=str(vector_store_dir),\n                embedding_function=embedding_function,\n                collection_name=self.knowledge_base,\n            )\n\n            # Convert Data objects to LangChain Documents\n            documents = []\n            for data_obj in data_objects:\n                doc = data_obj.to_lc_document()\n                documents.append(doc)\n\n            # Add documents to vector store\n            if documents:\n                chroma.add_documents(documents)\n                self.log(f\"Added {len(documents)} documents to vector store '{self.knowledge_base}'\")\n\n        except (OSError, ValueError, RuntimeError) as e:\n            self.log(f\"Error creating vector store: {e}\")\n\n    async def _convert_df_to_data_objects(\n        self, df_source: pd.DataFrame, config_list: list[dict[str, Any]]\n    ) -> list[Data]:\n        \"\"\"Convert DataFrame to Data objects for vector store.\"\"\"\n        data_objects: list[Data] = []\n\n        # Set up vector store directory\n        kb_path = await self._kb_path()\n\n        # If we don't allow duplicates, we need to get the existing hashes\n        chroma = Chroma(\n            persist_directory=str(kb_path),\n            collection_name=self.knowledge_base,\n        )\n\n        # Get all documents and their metadata\n        all_docs = chroma.get()\n\n        # Extract all _id values from metadata\n        id_list = [metadata.get(\"_id\") for metadata in all_docs[\"metadatas\"] if metadata.get(\"_id\")]\n\n        # Get column roles\n        content_cols = []\n        identifier_cols = []\n\n        for config in config_list:\n            col_name = config.get(\"column_name\")\n            vectorize = config.get(\"vectorize\") == \"True\" or config.get(\"vectorize\") is True\n            identifier = config.get(\"identifier\") == \"True\" or config.get(\"identifier\") is True\n\n            if vectorize:\n                content_cols.append(col_name)\n            elif identifier:\n                identifier_cols.append(col_name)\n\n        # Convert each row to a Data object\n        for _, row in df_source.iterrows():\n            # Build content text from identifier columns using list comprehension\n            identifier_parts = [str(row[col]) for col in content_cols if col in row and pd.notna(row[col])]\n\n            # Join all parts into a single string\n            page_content = \" \".join(identifier_parts)\n\n            # Build metadata from NON-vectorized columns only (simple key-value pairs)\n            data_dict = {\n                \"text\": page_content,  # Main content for vectorization\n            }\n\n            # Add identifier columns if they exist\n            if identifier_cols:\n                identifier_parts = [str(row[col]) for col in identifier_cols if col in row and pd.notna(row[col])]\n                page_content = \" \".join(identifier_parts)\n\n            # Add metadata columns as simple key-value pairs\n            for col in df_source.columns:\n                if col not in content_cols and col in row and pd.notna(row[col]):\n                    # Convert to simple types for Chroma metadata\n                    value = row[col]\n                    data_dict[col] = str(value)  # Convert complex types to string\n\n            # Hash the page_content for unique ID\n            page_content_hash = hashlib.sha256(page_content.encode()).hexdigest()\n            data_dict[\"_id\"] = page_content_hash\n\n            # If duplicates are disallowed, and hash exists, prevent adding this row\n            if not self.allow_duplicates and page_content_hash in id_list:\n                self.log(f\"Skipping duplicate row with hash {page_content_hash}\")\n                continue\n\n            # Create Data object - everything except \"text\" becomes metadata\n            data_obj = Data(data=data_dict)\n            data_objects.append(data_obj)\n\n        return data_objects\n\n    def is_valid_collection_name(self, name, min_length: int = 3, max_length: int = 63) -> bool:\n        \"\"\"Validates collection name against conditions 1-3.\n\n        1. Contains 3-63 characters\n        2. Starts and ends with alphanumeric character\n        3. Contains only alphanumeric characters, underscores, or hyphens.\n\n        Args:\n            name (str): Collection name to validate\n            min_length (int): Minimum length of the name\n            max_length (int): Maximum length of the name\n\n        Returns:\n            bool: True if valid, False otherwise\n        \"\"\"\n        # Check length (condition 1)\n        if not (min_length <= len(name) <= max_length):\n            return False\n\n        # Check start/end with alphanumeric (condition 2)\n        if not (name[0].isalnum() and name[-1].isalnum()):\n            return False\n\n        # Check allowed characters (condition 3)\n        return re.match(r\"^[a-zA-Z0-9_-]+$\", name) is not None\n\n    async def _kb_path(self) -> Path | None:\n        # Check if we already have the path cached\n        cached_path = getattr(self, \"_cached_kb_path\", None)\n        if cached_path is not None:\n            return cached_path\n\n        # If not cached, compute it\n        async with session_scope() as db:\n            if not self.user_id:\n                msg = \"User ID is required for fetching knowledge base path.\"\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\n        kb_root = self._get_kb_root()\n\n        # Cache the result\n        self._cached_kb_path = kb_root / kb_user / self.knowledge_base\n\n        return self._cached_kb_path\n\n    # ---------------------------------------------------------------------\n    #                         OUTPUT METHODS\n    # ---------------------------------------------------------------------\n    async def build_kb_info(self) -> Data:\n        \"\"\"Main ingestion routine → returns a dict with KB metadata.\"\"\"\n        try:\n            input_value = self.input_df[0] if isinstance(self.input_df, list) else self.input_df\n            df_source: DataFrame = convert_to_dataframe(input_value, auto_parse=False)\n\n            # Validate column configuration (using Structured Output patterns)\n            config_list = self._validate_column_config(df_source)\n            column_metadata = self._build_column_metadata(config_list, df_source)\n\n            # Read the embedding info from the knowledge base folder\n            kb_path = await self._kb_path()\n            if not kb_path:\n                msg = \"Knowledge base path is not set. Please create a new knowledge base first.\"\n                raise ValueError(msg)\n            metadata_path = kb_path / \"embedding_metadata.json\"\n\n            # If the API key is not provided, try to read it from the metadata file\n            if metadata_path.exists():\n                settings_service = get_settings_service()\n                metadata = json.loads(metadata_path.read_text())\n                embedding_model = metadata.get(\"embedding_model\")\n                try:\n                    api_key = decrypt_api_key(metadata[\"api_key\"], settings_service)\n                except (InvalidToken, TypeError, ValueError) as e:\n                    self.log(f\"Could not decrypt API key. Please provide it manually. Error: {e}\")\n\n            # Check if a custom API key was provided, update metadata if so\n            if self.api_key:\n                api_key = self.api_key\n                self._save_embedding_metadata(\n                    kb_path=kb_path,\n                    embedding_model=embedding_model,\n                    api_key=api_key,\n                )\n\n            # Create vector store following Local DB component pattern\n            await self._create_vector_store(df_source, config_list, embedding_model=embedding_model, api_key=api_key)\n\n            # Save KB files (using File Component storage patterns)\n            self._save_kb_files(kb_path, config_list)\n\n            # Build metadata response\n            meta: dict[str, Any] = {\n                \"kb_id\": str(uuid.uuid4()),\n                \"kb_name\": self.knowledge_base,\n                \"rows\": len(df_source),\n                \"column_metadata\": column_metadata,\n                \"path\": str(kb_path),\n                \"config_columns\": len(config_list),\n                \"timestamp\": datetime.now(tz=timezone.utc).isoformat(),\n            }\n\n            # Set status message\n            self.status = f\"✅ KB **{self.knowledge_base}** saved · {len(df_source)} chunks.\"\n\n            return Data(data=meta)\n\n        except (OSError, ValueError, RuntimeError, KeyError) as e:\n            msg = f\"Error during KB ingestion: {e}\"\n            raise RuntimeError(msg) from e\n\n    async def _get_api_key_variable(self, field_value: dict[str, Any]):\n        async with session_scope() as db:\n            if not self.user_id:\n                msg = \"User ID is required for fetching global variables.\"\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            variable_service = get_variable_service()\n\n            # Process the api_key field variable\n            return await variable_service.get_variable(\n                user_id=current_user.id,\n                name=field_value[\"03_api_key\"],\n                field=\"\",\n                session=db,\n            )\n\n    async def update_build_config(\n        self,\n        build_config,\n        field_value: Any,\n        field_name: str | None = None,\n    ):\n        \"\"\"Update build configuration based on provider selection.\"\"\"\n        # Create a new knowledge base\n        if field_name == \"knowledge_base\":\n            async with session_scope() as db:\n                if not self.user_id:\n                    msg = \"User ID is required for fetching knowledge base list.\"\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            if isinstance(field_value, dict) and \"01_new_kb_name\" in field_value:\n                # Validate the knowledge base name - Make sure it follows these rules:\n                if not self.is_valid_collection_name(field_value[\"01_new_kb_name\"]):\n                    msg = f\"Invalid knowledge base name: {field_value['01_new_kb_name']}\"\n                    raise ValueError(msg)\n\n                api_key = field_value.get(\"03_api_key\", None)\n                with contextlib.suppress(Exception):\n                    # If the API key is a variable, resolve it\n                    api_key = await self._get_api_key_variable(field_value)\n\n                # Make sure api_key is a string\n                if not isinstance(api_key, str):\n                    msg = \"API key must be a string.\"\n                    raise ValueError(msg)\n\n                # We need to test the API Key one time against the embedding model\n                embed_model = self._build_embeddings(embedding_model=field_value[\"02_embedding_model\"], api_key=api_key)\n\n                # Try to generate a dummy embedding to validate the API key without blocking the event loop\n                try:\n                    await asyncio.wait_for(\n                        asyncio.to_thread(embed_model.embed_query, \"test\"),\n                        timeout=10,\n                    )\n                except TimeoutError as e:\n                    msg = \"Embedding validation timed out. Please verify network connectivity and key.\"\n                    raise ValueError(msg) from e\n                except Exception as e:\n                    msg = f\"Embedding validation failed: {e!s}\"\n                    raise ValueError(msg) from e\n\n                # Create the new knowledge base directory\n                kb_path = _get_knowledge_bases_root_path() / kb_user / field_value[\"01_new_kb_name\"]\n                kb_path.mkdir(parents=True, exist_ok=True)\n\n                # Save the embedding metadata\n                build_config[\"knowledge_base\"][\"value\"] = field_value[\"01_new_kb_name\"]\n                self._save_embedding_metadata(\n                    kb_path=kb_path,\n                    embedding_model=field_value[\"02_embedding_model\"],\n                    api_key=api_key,\n                )\n\n            # Update the knowledge base options dynamically\n            build_config[\"knowledge_base\"][\"options\"] = await get_knowledge_bases(\n                _get_knowledge_bases_root_path(),\n                user_id=self.user_id,\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"
+                "value": "from __future__ import annotations\n\nimport asyncio\nimport contextlib\nimport hashlib\nimport json\nimport re\nimport uuid\nfrom dataclasses import asdict, dataclass, field\nfrom datetime import datetime, timezone\nfrom pathlib import Path\nfrom typing import TYPE_CHECKING, Any\n\nimport pandas as pd\nfrom cryptography.fernet import InvalidToken\nfrom langchain_chroma import Chroma\nfrom langflow.services.auth.utils import decrypt_api_key, encrypt_api_key\nfrom langflow.services.database.models.user.crud import get_user_by_id\n\nfrom lfx.base.knowledge_bases.knowledge_base_utils import get_knowledge_bases\nfrom lfx.base.models.openai_constants import OPENAI_EMBEDDING_MODEL_NAMES\nfrom lfx.components.processing.converter import convert_to_dataframe\nfrom lfx.custom import Component\nfrom lfx.io import (\n    BoolInput,\n    DropdownInput,\n    HandleInput,\n    IntInput,\n    Output,\n    SecretStrInput,\n    StrInput,\n    TableInput,\n)\nfrom lfx.schema.data import Data\nfrom lfx.schema.table import EditMode\nfrom lfx.services.deps import (\n    get_settings_service,\n    get_variable_service,\n    session_scope,\n)\nfrom lfx.utils.validate_cloud import raise_error_if_astra_cloud_disable_component\n\nif TYPE_CHECKING:\n    from lfx.schema.dataframe import DataFrame\n\nHUGGINGFACE_MODEL_NAMES = [\n    \"sentence-transformers/all-MiniLM-L6-v2\",\n    \"sentence-transformers/all-mpnet-base-v2\",\n]\nCOHERE_MODEL_NAMES = [\"embed-english-v3.0\", \"embed-multilingual-v3.0\"]\n\n_KNOWLEDGE_BASES_ROOT_PATH: Path | None = None\n\n# Error message to raise if we're in Astra cloud environment and the component is not supported.\nastra_error_msg = \"Knowledge ingestion is not supported in Astra cloud environment.\"\n\n\ndef _get_knowledge_bases_root_path() -> Path:\n    \"\"\"Lazy load the knowledge bases root path from settings.\"\"\"\n    global _KNOWLEDGE_BASES_ROOT_PATH  # noqa: PLW0603\n    if _KNOWLEDGE_BASES_ROOT_PATH is None:\n        settings = get_settings_service().settings\n        knowledge_directory = settings.knowledge_bases_dir\n        if not knowledge_directory:\n            msg = \"Knowledge bases directory is not set in the settings.\"\n            raise ValueError(msg)\n        _KNOWLEDGE_BASES_ROOT_PATH = Path(knowledge_directory).expanduser()\n    return _KNOWLEDGE_BASES_ROOT_PATH\n\n\nclass KnowledgeIngestionComponent(Component):\n    \"\"\"Create or append to Langflow Knowledge from a DataFrame.\"\"\"\n\n    # ------ UI metadata ---------------------------------------------------\n    display_name = \"Knowledge Ingestion\"\n    description = \"Create or update knowledge in Langflow.\"\n    icon = \"upload\"\n    name = \"KnowledgeIngestion\"\n\n    def __init__(self, *args, **kwargs) -> None:\n        super().__init__(*args, **kwargs)\n        self._cached_kb_path: Path | None = None\n\n    @dataclass\n    class NewKnowledgeBaseInput:\n        functionality: str = \"create\"\n        fields: dict[str, dict] = field(\n            default_factory=lambda: {\n                \"data\": {\n                    \"node\": {\n                        \"name\": \"create_knowledge_base\",\n                        \"description\": \"Create new knowledge in Langflow.\",\n                        \"display_name\": \"Create new knowledge\",\n                        \"field_order\": [\n                            \"01_new_kb_name\",\n                            \"02_embedding_model\",\n                            \"03_api_key\",\n                        ],\n                        \"template\": {\n                            \"01_new_kb_name\": StrInput(\n                                name=\"new_kb_name\",\n                                display_name=\"Knowledge Name\",\n                                info=\"Name of the new knowledge to create.\",\n                                required=True,\n                            ),\n                            \"02_embedding_model\": DropdownInput(\n                                name=\"embedding_model\",\n                                display_name=\"Choose Embedding\",\n                                info=\"Select the embedding model to use for this knowledge base.\",\n                                required=True,\n                                options=OPENAI_EMBEDDING_MODEL_NAMES + HUGGINGFACE_MODEL_NAMES + COHERE_MODEL_NAMES,\n                                options_metadata=[{\"icon\": \"OpenAI\"} for _ in OPENAI_EMBEDDING_MODEL_NAMES]\n                                + [{\"icon\": \"HuggingFace\"} for _ in HUGGINGFACE_MODEL_NAMES]\n                                + [{\"icon\": \"Cohere\"} for _ in COHERE_MODEL_NAMES],\n                            ),\n                            \"03_api_key\": SecretStrInput(\n                                name=\"api_key\",\n                                display_name=\"API Key\",\n                                info=\"Provider API key for embedding model\",\n                                required=True,\n                                load_from_db=False,\n                            ),\n                        },\n                    },\n                }\n            }\n        )\n\n    # ------ Inputs --------------------------------------------------------\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            dialog_inputs=asdict(NewKnowledgeBaseInput()),\n        ),\n        HandleInput(\n            name=\"input_df\",\n            display_name=\"Input\",\n            info=(\n                \"Table with all original columns (already chunked / processed). \"\n                \"Accepts Data or DataFrame. If Data is provided, it is converted to a DataFrame automatically.\"\n            ),\n            input_types=[\"Data\", \"DataFrame\"],\n            required=True,\n        ),\n        TableInput(\n            name=\"column_config\",\n            display_name=\"Column Configuration\",\n            info=\"Configure column behavior for the knowledge base.\",\n            required=True,\n            table_schema=[\n                {\n                    \"name\": \"column_name\",\n                    \"display_name\": \"Column Name\",\n                    \"type\": \"str\",\n                    \"description\": \"Name of the column in the source DataFrame\",\n                    \"edit_mode\": EditMode.INLINE,\n                },\n                {\n                    \"name\": \"vectorize\",\n                    \"display_name\": \"Vectorize\",\n                    \"type\": \"boolean\",\n                    \"description\": \"Create embeddings for this column\",\n                    \"default\": False,\n                    \"edit_mode\": EditMode.INLINE,\n                },\n                {\n                    \"name\": \"identifier\",\n                    \"display_name\": \"Identifier\",\n                    \"type\": \"boolean\",\n                    \"description\": \"Use this column as unique identifier\",\n                    \"default\": False,\n                    \"edit_mode\": EditMode.INLINE,\n                },\n            ],\n            value=[\n                {\n                    \"column_name\": \"text\",\n                    \"vectorize\": True,\n                    \"identifier\": True,\n                },\n            ],\n        ),\n        IntInput(\n            name=\"chunk_size\",\n            display_name=\"Chunk Size\",\n            info=\"Batch size for processing embeddings\",\n            advanced=True,\n            value=1000,\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        BoolInput(\n            name=\"allow_duplicates\",\n            display_name=\"Allow Duplicates\",\n            info=\"Allow duplicate rows in the knowledge base\",\n            advanced=True,\n            value=False,\n        ),\n    ]\n\n    # ------ Outputs -------------------------------------------------------\n    outputs = [Output(display_name=\"Results\", name=\"dataframe_output\", method=\"build_kb_info\")]\n\n    # ------ Internal helpers ---------------------------------------------\n    def _get_kb_root(self) -> Path:\n        \"\"\"Return the root directory for knowledge bases.\"\"\"\n        return _get_knowledge_bases_root_path()\n\n    def _validate_column_config(self, df_source: pd.DataFrame) -> list[dict[str, Any]]:\n        \"\"\"Validate column configuration using Structured Output patterns.\"\"\"\n        if not self.column_config:\n            msg = \"Column configuration cannot be empty\"\n            raise ValueError(msg)\n\n        # Convert table input to list of dicts (similar to Structured Output)\n        config_list = self.column_config if isinstance(self.column_config, list) else []\n\n        # Validate column names exist in DataFrame\n        df_columns = set(df_source.columns)\n        for config in config_list:\n            col_name = config.get(\"column_name\")\n            if col_name not in df_columns:\n                msg = f\"Column '{col_name}' not found in DataFrame. Available columns: {sorted(df_columns)}\"\n                raise ValueError(msg)\n\n        return config_list\n\n    def _get_embedding_provider(self, embedding_model: str) -> str:\n        \"\"\"Get embedding provider by matching model name to lists.\"\"\"\n        if embedding_model in OPENAI_EMBEDDING_MODEL_NAMES:\n            return \"OpenAI\"\n        if embedding_model in HUGGINGFACE_MODEL_NAMES:\n            return \"HuggingFace\"\n        if embedding_model in COHERE_MODEL_NAMES:\n            return \"Cohere\"\n        return \"Custom\"\n\n    def _build_embeddings(self, embedding_model: str, api_key: str):\n        \"\"\"Build embedding model using provider patterns.\"\"\"\n        # Get provider by matching model name to lists\n        provider = self._get_embedding_provider(embedding_model)\n\n        # Validate provider and model\n        if provider == \"OpenAI\":\n            from langchain_openai import OpenAIEmbeddings\n\n            if not api_key:\n                msg = \"OpenAI API key is required when using OpenAI provider\"\n                raise ValueError(msg)\n            return OpenAIEmbeddings(\n                model=embedding_model,\n                api_key=api_key,\n                chunk_size=self.chunk_size,\n            )\n        if provider == \"HuggingFace\":\n            from langchain_huggingface import HuggingFaceEmbeddings\n\n            return HuggingFaceEmbeddings(\n                model=embedding_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=embedding_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        msg = f\"Unknown provider: {provider}\"\n        raise ValueError(msg)\n\n    def _build_embedding_metadata(self, embedding_model, api_key) -> dict[str, Any]:\n        \"\"\"Build embedding model metadata.\"\"\"\n        # Get provider by matching model name to lists\n        embedding_provider = self._get_embedding_provider(embedding_model)\n\n        api_key_to_save = None\n        if api_key and hasattr(api_key, \"get_secret_value\"):\n            api_key_to_save = api_key.get_secret_value()\n        elif isinstance(api_key, str):\n            api_key_to_save = api_key\n\n        encrypted_api_key = None\n        if api_key_to_save:\n            settings_service = get_settings_service()\n            try:\n                encrypted_api_key = encrypt_api_key(api_key_to_save, settings_service=settings_service)\n            except (TypeError, ValueError) as e:\n                self.log(f\"Could not encrypt API key: {e}\")\n\n        return {\n            \"embedding_provider\": embedding_provider,\n            \"embedding_model\": embedding_model,\n            \"api_key\": encrypted_api_key,\n            \"api_key_used\": bool(api_key),\n            \"chunk_size\": self.chunk_size,\n            \"created_at\": datetime.now(timezone.utc).isoformat(),\n        }\n\n    def _save_embedding_metadata(self, kb_path: Path, embedding_model: str, api_key: str) -> None:\n        \"\"\"Save embedding model metadata.\"\"\"\n        embedding_metadata = self._build_embedding_metadata(embedding_model, api_key)\n        metadata_path = kb_path / \"embedding_metadata.json\"\n        metadata_path.write_text(json.dumps(embedding_metadata, indent=2))\n\n    def _save_kb_files(\n        self,\n        kb_path: Path,\n        config_list: list[dict[str, Any]],\n    ) -> None:\n        \"\"\"Save KB files using File Component storage patterns.\"\"\"\n        try:\n            # Create directory (following File Component patterns)\n            kb_path.mkdir(parents=True, exist_ok=True)\n\n            # Save column configuration\n            # Only do this if the file doesn't exist already\n            cfg_path = kb_path / \"schema.json\"\n            if not cfg_path.exists():\n                cfg_path.write_text(json.dumps(config_list, indent=2))\n\n        except (OSError, TypeError, ValueError) as e:\n            self.log(f\"Error saving KB files: {e}\")\n\n    def _build_column_metadata(self, config_list: list[dict[str, Any]], df_source: pd.DataFrame) -> dict[str, Any]:\n        \"\"\"Build detailed column metadata.\"\"\"\n        metadata: dict[str, Any] = {\n            \"total_columns\": len(df_source.columns),\n            \"mapped_columns\": len(config_list),\n            \"unmapped_columns\": len(df_source.columns) - len(config_list),\n            \"columns\": [],\n            \"summary\": {\"vectorized_columns\": [], \"identifier_columns\": []},\n        }\n\n        for config in config_list:\n            col_name = config.get(\"column_name\")\n            vectorize = config.get(\"vectorize\") == \"True\" or config.get(\"vectorize\") is True\n            identifier = config.get(\"identifier\") == \"True\" or config.get(\"identifier\") is True\n\n            # Add to columns list\n            metadata[\"columns\"].append(\n                {\n                    \"name\": col_name,\n                    \"vectorize\": vectorize,\n                    \"identifier\": identifier,\n                }\n            )\n\n            # Update summary\n            if vectorize:\n                metadata[\"summary\"][\"vectorized_columns\"].append(col_name)\n            if identifier:\n                metadata[\"summary\"][\"identifier_columns\"].append(col_name)\n\n        return metadata\n\n    async def _create_vector_store(\n        self,\n        df_source: pd.DataFrame,\n        config_list: list[dict[str, Any]],\n        embedding_model: str,\n        api_key: str,\n    ) -> None:\n        \"\"\"Create vector store following Local DB component pattern.\"\"\"\n        try:\n            # Set up vector store directory\n            vector_store_dir = await self._kb_path()\n            if not vector_store_dir:\n                msg = \"Knowledge base path is not set. Please create a new knowledge base first.\"\n                raise ValueError(msg)\n            vector_store_dir.mkdir(parents=True, exist_ok=True)\n\n            # Create embeddings model\n            embedding_function = self._build_embeddings(embedding_model, api_key)\n\n            # Convert DataFrame to Data objects (following Local DB pattern)\n            data_objects = await self._convert_df_to_data_objects(df_source, config_list)\n\n            # Create vector store\n            chroma = Chroma(\n                persist_directory=str(vector_store_dir),\n                embedding_function=embedding_function,\n                collection_name=self.knowledge_base,\n            )\n\n            # Convert Data objects to LangChain Documents\n            documents = []\n            for data_obj in data_objects:\n                doc = data_obj.to_lc_document()\n                documents.append(doc)\n\n            # Add documents to vector store\n            if documents:\n                chroma.add_documents(documents)\n                self.log(f\"Added {len(documents)} documents to vector store '{self.knowledge_base}'\")\n\n        except (OSError, ValueError, RuntimeError) as e:\n            self.log(f\"Error creating vector store: {e}\")\n\n    async def _convert_df_to_data_objects(\n        self, df_source: pd.DataFrame, config_list: list[dict[str, Any]]\n    ) -> list[Data]:\n        \"\"\"Convert DataFrame to Data objects for vector store.\"\"\"\n        data_objects: list[Data] = []\n\n        # Set up vector store directory\n        kb_path = await self._kb_path()\n\n        # If we don't allow duplicates, we need to get the existing hashes\n        chroma = Chroma(\n            persist_directory=str(kb_path),\n            collection_name=self.knowledge_base,\n        )\n\n        # Get all documents and their metadata\n        all_docs = chroma.get()\n\n        # Extract all _id values from metadata\n        id_list = [metadata.get(\"_id\") for metadata in all_docs[\"metadatas\"] if metadata.get(\"_id\")]\n\n        # Get column roles\n        content_cols = []\n        identifier_cols = []\n\n        for config in config_list:\n            col_name = config.get(\"column_name\")\n            vectorize = config.get(\"vectorize\") == \"True\" or config.get(\"vectorize\") is True\n            identifier = config.get(\"identifier\") == \"True\" or config.get(\"identifier\") is True\n\n            if vectorize:\n                content_cols.append(col_name)\n            elif identifier:\n                identifier_cols.append(col_name)\n\n        # Convert each row to a Data object\n        for _, row in df_source.iterrows():\n            # Build content text from identifier columns using list comprehension\n            identifier_parts = [str(row[col]) for col in content_cols if col in row and pd.notna(row[col])]\n\n            # Join all parts into a single string\n            page_content = \" \".join(identifier_parts)\n\n            # Build metadata from NON-vectorized columns only (simple key-value pairs)\n            data_dict = {\n                \"text\": page_content,  # Main content for vectorization\n            }\n\n            # Add identifier columns if they exist\n            if identifier_cols:\n                identifier_parts = [str(row[col]) for col in identifier_cols if col in row and pd.notna(row[col])]\n                page_content = \" \".join(identifier_parts)\n\n            # Add metadata columns as simple key-value pairs\n            for col in df_source.columns:\n                if col not in content_cols and col in row and pd.notna(row[col]):\n                    # Convert to simple types for Chroma metadata\n                    value = row[col]\n                    data_dict[col] = str(value)  # Convert complex types to string\n\n            # Hash the page_content for unique ID\n            page_content_hash = hashlib.sha256(page_content.encode()).hexdigest()\n            data_dict[\"_id\"] = page_content_hash\n\n            # If duplicates are disallowed, and hash exists, prevent adding this row\n            if not self.allow_duplicates and page_content_hash in id_list:\n                self.log(f\"Skipping duplicate row with hash {page_content_hash}\")\n                continue\n\n            # Create Data object - everything except \"text\" becomes metadata\n            data_obj = Data(data=data_dict)\n            data_objects.append(data_obj)\n\n        return data_objects\n\n    def is_valid_collection_name(self, name, min_length: int = 3, max_length: int = 63) -> bool:\n        \"\"\"Validates collection name against conditions 1-3.\n\n        1. Contains 3-63 characters\n        2. Starts and ends with alphanumeric character\n        3. Contains only alphanumeric characters, underscores, or hyphens.\n\n        Args:\n            name (str): Collection name to validate\n            min_length (int): Minimum length of the name\n            max_length (int): Maximum length of the name\n\n        Returns:\n            bool: True if valid, False otherwise\n        \"\"\"\n        # Check length (condition 1)\n        if not (min_length <= len(name) <= max_length):\n            return False\n\n        # Check start/end with alphanumeric (condition 2)\n        if not (name[0].isalnum() and name[-1].isalnum()):\n            return False\n\n        # Check allowed characters (condition 3)\n        return re.match(r\"^[a-zA-Z0-9_-]+$\", name) is not None\n\n    async def _kb_path(self) -> Path | None:\n        # Check if we already have the path cached\n        cached_path = getattr(self, \"_cached_kb_path\", None)\n        if cached_path is not None:\n            return cached_path\n\n        # If not cached, compute it\n        async with session_scope() as db:\n            if not self.user_id:\n                msg = \"User ID is required for fetching knowledge base path.\"\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\n        kb_root = self._get_kb_root()\n\n        # Cache the result\n        self._cached_kb_path = kb_root / kb_user / self.knowledge_base\n\n        return self._cached_kb_path\n\n    # ---------------------------------------------------------------------\n    #                         OUTPUT METHODS\n    # ---------------------------------------------------------------------\n    async def build_kb_info(self) -> Data:\n        \"\"\"Main ingestion routine → returns a dict with KB metadata.\"\"\"\n        # Check if we're in Astra cloud environment and raise an error if we are.\n        raise_error_if_astra_cloud_disable_component(astra_error_msg)\n        try:\n            input_value = self.input_df[0] if isinstance(self.input_df, list) else self.input_df\n            df_source: DataFrame = convert_to_dataframe(input_value, auto_parse=False)\n\n            # Validate column configuration (using Structured Output patterns)\n            config_list = self._validate_column_config(df_source)\n            column_metadata = self._build_column_metadata(config_list, df_source)\n\n            # Read the embedding info from the knowledge base folder\n            kb_path = await self._kb_path()\n            if not kb_path:\n                msg = \"Knowledge base path is not set. Please create a new knowledge base first.\"\n                raise ValueError(msg)\n            metadata_path = kb_path / \"embedding_metadata.json\"\n\n            # If the API key is not provided, try to read it from the metadata file\n            if metadata_path.exists():\n                settings_service = get_settings_service()\n                metadata = json.loads(metadata_path.read_text())\n                embedding_model = metadata.get(\"embedding_model\")\n                try:\n                    api_key = decrypt_api_key(metadata[\"api_key\"], settings_service)\n                except (InvalidToken, TypeError, ValueError) as e:\n                    self.log(f\"Could not decrypt API key. Please provide it manually. Error: {e}\")\n\n            # Check if a custom API key was provided, update metadata if so\n            if self.api_key:\n                api_key = self.api_key\n                self._save_embedding_metadata(\n                    kb_path=kb_path,\n                    embedding_model=embedding_model,\n                    api_key=api_key,\n                )\n\n            # Create vector store following Local DB component pattern\n            await self._create_vector_store(df_source, config_list, embedding_model=embedding_model, api_key=api_key)\n\n            # Save KB files (using File Component storage patterns)\n            self._save_kb_files(kb_path, config_list)\n\n            # Build metadata response\n            meta: dict[str, Any] = {\n                \"kb_id\": str(uuid.uuid4()),\n                \"kb_name\": self.knowledge_base,\n                \"rows\": len(df_source),\n                \"column_metadata\": column_metadata,\n                \"path\": str(kb_path),\n                \"config_columns\": len(config_list),\n                \"timestamp\": datetime.now(tz=timezone.utc).isoformat(),\n            }\n\n            # Set status message\n            self.status = f\"✅ KB **{self.knowledge_base}** saved · {len(df_source)} chunks.\"\n\n            return Data(data=meta)\n\n        except (OSError, ValueError, RuntimeError, KeyError) as e:\n            msg = f\"Error during KB ingestion: {e}\"\n            raise RuntimeError(msg) from e\n\n    async def _get_api_key_variable(self, field_value: dict[str, Any]):\n        async with session_scope() as db:\n            if not self.user_id:\n                msg = \"User ID is required for fetching global variables.\"\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            variable_service = get_variable_service()\n\n            # Process the api_key field variable\n            return await variable_service.get_variable(\n                user_id=current_user.id,\n                name=field_value[\"03_api_key\"],\n                field=\"\",\n                session=db,\n            )\n\n    async def update_build_config(\n        self,\n        build_config,\n        field_value: Any,\n        field_name: str | None = None,\n    ):\n        \"\"\"Update build configuration based on provider selection.\"\"\"\n        # Check if we're in Astra cloud environment and raise an error if we are.\n        raise_error_if_astra_cloud_disable_component(astra_error_msg)\n        # Create a new knowledge base\n        if field_name == \"knowledge_base\":\n            async with session_scope() as db:\n                if not self.user_id:\n                    msg = \"User ID is required for fetching knowledge base list.\"\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            if isinstance(field_value, dict) and \"01_new_kb_name\" in field_value:\n                # Validate the knowledge base name - Make sure it follows these rules:\n                if not self.is_valid_collection_name(field_value[\"01_new_kb_name\"]):\n                    msg = f\"Invalid knowledge base name: {field_value['01_new_kb_name']}\"\n                    raise ValueError(msg)\n\n                api_key = field_value.get(\"03_api_key\", None)\n                with contextlib.suppress(Exception):\n                    # If the API key is a variable, resolve it\n                    api_key = await self._get_api_key_variable(field_value)\n\n                # Make sure api_key is a string\n                if not isinstance(api_key, str):\n                    msg = \"API key must be a string.\"\n                    raise ValueError(msg)\n\n                # We need to test the API Key one time against the embedding model\n                embed_model = self._build_embeddings(embedding_model=field_value[\"02_embedding_model\"], api_key=api_key)\n\n                # Try to generate a dummy embedding to validate the API key without blocking the event loop\n                try:\n                    await asyncio.wait_for(\n                        asyncio.to_thread(embed_model.embed_query, \"test\"),\n                        timeout=10,\n                    )\n                except TimeoutError as e:\n                    msg = \"Embedding validation timed out. Please verify network connectivity and key.\"\n                    raise ValueError(msg) from e\n                except Exception as e:\n                    msg = f\"Embedding validation failed: {e!s}\"\n                    raise ValueError(msg) from e\n\n                # Create the new knowledge base directory\n                kb_path = _get_knowledge_bases_root_path() / kb_user / field_value[\"01_new_kb_name\"]\n                kb_path.mkdir(parents=True, exist_ok=True)\n\n                # Save the embedding metadata\n                build_config[\"knowledge_base\"][\"value\"] = field_value[\"01_new_kb_name\"]\n                self._save_embedding_metadata(\n                    kb_path=kb_path,\n                    embedding_model=field_value[\"02_embedding_model\"],\n                    api_key=api_key,\n                )\n\n            # Update the knowledge base options dynamically\n            build_config[\"knowledge_base\"][\"options\"] = await get_knowledge_bases(\n                _get_knowledge_bases_root_path(),\n                user_id=self.user_id,\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"
               },
               "column_config": {
                 "_input_type": "TableInput",

langflow/initial_setup/starter_projects/Knowledge Retrieval.json

@@ -511,7 +511,7 @@
             "last_updated": "2025-08-26T16:19:16.681Z",
             "legacy": false,
             "metadata": {
-              "code_hash": "653abe6876b8",
+              "code_hash": "af0a162c3f80",
               "dependencies": {
                 "dependencies": [
                   {
@@ -605,7 +605,7 @@
                 "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 langflow.services.auth.utils import decrypt_api_key\nfrom langflow.services.database.models.user.crud import get_user_by_id\nfrom pydantic import SecretStr\n\nfrom lfx.base.knowledge_bases.knowledge_base_utils import get_knowledge_bases\nfrom lfx.custom import Component\nfrom lfx.io import BoolInput, DropdownInput, IntInput, MessageTextInput, Output, SecretStrInput\nfrom lfx.log.logger import logger\nfrom lfx.schema.data import Data\nfrom lfx.schema.dataframe import DataFrame\nfrom lfx.services.deps import get_settings_service, session_scope\n\n_KNOWLEDGE_BASES_ROOT_PATH: Path | None = None\n\n\ndef _get_knowledge_bases_root_path() -> Path:\n    \"\"\"Lazy load the knowledge bases root path from settings.\"\"\"\n    global _KNOWLEDGE_BASES_ROOT_PATH  # noqa: PLW0603\n    if _KNOWLEDGE_BASES_ROOT_PATH is None:\n        settings = get_settings_service().settings\n        knowledge_directory = settings.knowledge_bases_dir\n        if not knowledge_directory:\n            msg = \"Knowledge bases directory is not set in the settings.\"\n            raise ValueError(msg)\n        _KNOWLEDGE_BASES_ROOT_PATH = Path(knowledge_directory).expanduser()\n    return _KNOWLEDGE_BASES_ROOT_PATH\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                _get_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 = _get_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 collection to get embeddings\n                collection = chroma._collection  # noqa: SLF001\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"
+                "value": "import json\nfrom pathlib import Path\nfrom typing import Any\n\nfrom cryptography.fernet import InvalidToken\nfrom langchain_chroma import Chroma\nfrom langflow.services.auth.utils import decrypt_api_key\nfrom langflow.services.database.models.user.crud import get_user_by_id\nfrom pydantic import SecretStr\n\nfrom lfx.base.knowledge_bases.knowledge_base_utils import get_knowledge_bases\nfrom lfx.custom import Component\nfrom lfx.io import BoolInput, DropdownInput, IntInput, MessageTextInput, Output, SecretStrInput\nfrom lfx.log.logger import logger\nfrom lfx.schema.data import Data\nfrom lfx.schema.dataframe import DataFrame\nfrom lfx.services.deps import get_settings_service, session_scope\nfrom lfx.utils.validate_cloud import raise_error_if_astra_cloud_disable_component\n\n_KNOWLEDGE_BASES_ROOT_PATH: Path | None = None\n\n# Error message to raise if we're in Astra cloud environment and the component is not supported.\nastra_error_msg = \"Knowledge retrieval is not supported in Astra cloud environment.\"\n\n\ndef _get_knowledge_bases_root_path() -> Path:\n    \"\"\"Lazy load the knowledge bases root path from settings.\"\"\"\n    global _KNOWLEDGE_BASES_ROOT_PATH  # noqa: PLW0603\n    if _KNOWLEDGE_BASES_ROOT_PATH is None:\n        settings = get_settings_service().settings\n        knowledge_directory = settings.knowledge_bases_dir\n        if not knowledge_directory:\n            msg = \"Knowledge bases directory is not set in the settings.\"\n            raise ValueError(msg)\n        _KNOWLEDGE_BASES_ROOT_PATH = Path(knowledge_directory).expanduser()\n    return _KNOWLEDGE_BASES_ROOT_PATH\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        # Check if we're in Astra cloud environment and raise an error if we are.\n        raise_error_if_astra_cloud_disable_component(astra_error_msg)\n        if field_name == \"knowledge_base\":\n            # Update the knowledge base options dynamically\n            build_config[\"knowledge_base\"][\"options\"] = await get_knowledge_bases(\n                _get_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        # Check if we're in Astra cloud environment and raise an error if we are.\n        raise_error_if_astra_cloud_disable_component(astra_error_msg)\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        # Check if we're in Astra cloud environment and raise an error if we are.\n        raise_error_if_astra_cloud_disable_component(astra_error_msg)\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 = _get_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 collection to get embeddings\n                collection = chroma._collection  # noqa: SLF001\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",