langflow-base-nightly 0.5.1.dev1__py3-none-any.whl → 0.5.1.dev2__py3-none-any.whl

langflow/initial_setup/starter_projects/Knowledge Retrieval.json

@@ -2,66 +2,64 @@
   "data": {
     "edges": [
       {
-        "animated": false,
+        "className": "",
         "data": {
           "sourceHandle": {
-            "dataType": "TextInput",
-            "id": "TextInput-WyJxO",
-            "name": "text",
+            "dataType": "KnowledgeRetrieval",
+            "id": "KnowledgeRetrieval-kgwih",
+            "name": "retrieve_data",
             "output_types": [
-              "Message"
+              "DataFrame"
             ]
           },
           "targetHandle": {
-            "fieldName": "search_query",
-            "id": "KBRetrieval-zz3I0",
+            "fieldName": "input_value",
+            "id": "ChatOutput-OG4M9",
             "inputTypes": [
+              "Data",
+              "DataFrame",
               "Message"
             ],
-            "type": "str"
+            "type": "other"
           }
         },
-        "id": "xy-edge__TextInput-WyJxO{œdataTypeœ:œTextInputœ,œidœ:œTextInput-WyJxOœ,œnameœ:œtextœ,œoutput_typesœ:[œMessageœ]}-KBRetrieval-zz3I0{œfieldNameœ:œsearch_queryœ,œidœ:œKBRetrieval-zz3I0œ,œinputTypesœ:[œMessageœ],œtypeœ:œstrœ}",
-        "selected": false,
-        "source": "TextInput-WyJxO",
-        "sourceHandle": "{œdataTypeœ: œTextInputœ, œidœ: œTextInput-WyJxOœ, œnameœ: œtextœ, œoutput_typesœ: [œMessageœ]}",
-        "target": "KBRetrieval-zz3I0",
-        "targetHandle": "{œfieldNameœ: œsearch_queryœ, œidœ: œKBRetrieval-zz3I0œ, œinputTypesœ: [œMessageœ], œtypeœ: œstrœ}"
+        "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}"
       },
       {
-        "animated": false,
+        "className": "",
         "data": {
           "sourceHandle": {
-            "dataType": "KBRetrieval",
-            "id": "KBRetrieval-zz3I0",
-            "name": "chroma_kb_data",
+            "dataType": "TextInput",
+            "id": "TextInput-k48NL",
+            "name": "text",
             "output_types": [
-              "DataFrame"
+              "Message"
             ]
           },
           "targetHandle": {
-            "fieldName": "input_value",
-            "id": "ChatOutput-N7nxz",
+            "fieldName": "search_query",
+            "id": "KnowledgeRetrieval-kgwih",
             "inputTypes": [
-              "Data",
-              "DataFrame",
               "Message"
             ],
-            "type": "other"
+            "type": "str"
           }
         },
-        "id": "xy-edge__KBRetrieval-zz3I0{œdataTypeœ:œKBRetrievalœ,œidœ:œKBRetrieval-zz3I0œ,œnameœ:œchroma_kb_dataœ,œoutput_typesœ:[œDataFrameœ]}-ChatOutput-N7nxz{œfieldNameœ:œinput_valueœ,œidœ:œChatOutput-N7nxzœ,œinputTypesœ:[œDataœ,œDataFrameœ,œMessageœ],œtypeœ:œotherœ}",
-        "selected": false,
-        "source": "KBRetrieval-zz3I0",
-        "sourceHandle": "{œdataTypeœ: œKBRetrievalœ, œidœ: œKBRetrieval-zz3I0œ, œnameœ: œchroma_kb_dataœ, œoutput_typesœ: [œDataFrameœ]}",
-        "target": "ChatOutput-N7nxz",
-        "targetHandle": "{œfieldNameœ: œinput_valueœ, œidœ: œChatOutput-N7nxzœ, œinputTypesœ: [œDataœ, œDataFrameœ, œMessageœ], œtypeœ: œotherœ}"
+        "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-f86G8",
+          "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": "",
@@ -72,7 +70,7 @@
         },
         "dragging": false,
         "height": 384,
-        "id": "note-f86G8",
+        "id": "note-6CE3d",
         "measured": {
           "height": 384,
           "width": 371
@@ -88,7 +86,7 @@
       },
       {
         "data": {
-          "id": "TextInput-WyJxO",
+          "id": "TextInput-k48NL",
           "node": {
             "base_classes": [
               "Message"
@@ -191,7 +189,7 @@
           "type": "TextInput"
         },
         "dragging": false,
-        "id": "TextInput-WyJxO",
+        "id": "TextInput-k48NL",
         "measured": {
           "height": 204,
           "width": 320
@@ -205,7 +203,7 @@
       },
       {
         "data": {
-          "id": "ChatOutput-N7nxz",
+          "id": "ChatOutput-OG4M9",
           "node": {
             "base_classes": [
               "Message"
@@ -520,7 +518,7 @@
           "type": "ChatOutput"
         },
         "dragging": false,
-        "id": "ChatOutput-N7nxz",
+        "id": "ChatOutput-OG4M9",
         "measured": {
           "height": 48,
           "width": 192
@@ -534,7 +532,7 @@
       },
       {
         "data": {
-          "id": "KBRetrieval-zz3I0",
+          "id": "KnowledgeRetrieval-kgwih",
           "node": {
             "base_classes": [
               "DataFrame"
@@ -551,14 +549,15 @@
               "api_key",
               "search_query",
               "top_k",
-              "include_metadata"
+              "include_metadata",
+              "include_embeddings"
             ],
             "frozen": false,
-            "icon": "database",
-            "last_updated": "2025-08-14T17:19:22.182Z",
+            "icon": "download",
+            "last_updated": "2025-08-26T16:19:16.681Z",
             "legacy": false,
             "metadata": {
-              "code_hash": "6fcf86be1aca",
+              "code_hash": "1eaf43b9b167",
               "dependencies": {
                 "dependencies": [
                   {
@@ -596,7 +595,7 @@
                 ],
                 "total_dependencies": 8
               },
-              "module": "langflow.components.data.kb_retrieval.KBRetrievalComponent"
+              "module": "langflow.components.knowledge_bases.retrieval.KnowledgeRetrievalComponent"
             },
             "minimized": false,
             "output_types": [],
@@ -606,8 +605,8 @@
                 "cache": true,
                 "display_name": "Results",
                 "group_outputs": false,
-                "method": "get_chroma_kb_data",
-                "name": "chroma_kb_data",
+                "method": "retrieve_data",
+                "name": "retrieve_data",
                 "selected": "DataFrame",
                 "tool_mode": true,
                 "types": [
@@ -652,14 +651,32 @@
                 "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.data.kb_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 KBRetrievalComponent(Component):\n    display_name = \"Knowledge Retrieval\"\n    description = \"Search and retrieve data from knowledge.\"\n    icon = \"database\"\n    name = \"KBRetrieval\"\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        ),\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 and embeddings in the output. If false, only content is returned.\",\n            value=True,\n            advanced=False,\n        ),\n    ]\n\n    outputs = [\n        Output(\n            name=\"chroma_kb_data\",\n            display_name=\"Results\",\n            method=\"get_chroma_kb_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 get_chroma_kb_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 metadata is enabled, get embeddings for the results\n        id_to_embedding = {}\n        if self.include_metadata 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=[\"embeddings\", \"metadatas\"])\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            if self.include_metadata:\n                # Include all metadata, embeddings, and content\n                kwargs = {\n                    \"content\": doc[0].page_content,\n                    **doc[0].metadata,\n                }\n                if self.search_query:\n                    kwargs[\"_score\"] = -1 * doc[1]\n                kwargs[\"_embeddings\"] = id_to_embedding.get(doc[0].metadata.get(\"_id\"))\n            else:\n                # Only include content\n                kwargs = {\n                    \"content\": doc[0].page_content,\n                }\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 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 and embeddings in the output. If false, only content is returned.",
+                "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",
@@ -712,7 +729,7 @@
                 "required": false,
                 "show": true,
                 "title_case": false,
-                "tool_mode": false,
+                "tool_mode": true,
                 "trace_as_input": true,
                 "trace_as_metadata": true,
                 "type": "str",
@@ -740,33 +757,33 @@
             "tool_mode": false
           },
           "showNode": true,
-          "type": "KBRetrieval"
+          "type": "KnowledgeRetrieval"
         },
         "dragging": false,
-        "id": "KBRetrieval-zz3I0",
+        "id": "KnowledgeRetrieval-kgwih",
         "measured": {
           "height": 329,
           "width": 320
         },
         "position": {
-          "x": 616.6226476085393,
-          "y": -343.13068334363356
+          "x": 635.7729107873928,
+          "y": -337.735556504938
         },
         "selected": false,
         "type": "genericNode"
       }
     ],
     "viewport": {
-      "x": 177.06633386268413,
-      "y": 482.8027480187026,
-      "zoom": 0.8999566725119924
+      "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": "5487ee05-73d5-4b12-9b41-bc4c3a2f9326",
+  "id": "e262d49f-c800-4962-948b-c94f79eb5fb8",
   "is_component": false,
-  "last_tested_version": "1.5.0.post1",
+  "last_tested_version": "1.5.0.post2",
   "name": "Knowledge Retrieval",
   "tags": []
 }

langflow/initial_setup/starter_projects/Market Research.json

@@ -2269,7 +2269,7 @@
                 "show": true,
                 "title_case": false,
                 "type": "code",
-                "value": "import json\nimport re\n\nfrom langchain_core.tools import StructuredTool\nfrom pydantic import ValidationError\n\nfrom langflow.base.agents.agent import LCToolsAgentComponent\nfrom langflow.base.agents.events import ExceptionWithMessageError\nfrom langflow.base.models.model_input_constants import (\n    ALL_PROVIDER_FIELDS,\n    MODEL_DYNAMIC_UPDATE_FIELDS,\n    MODEL_PROVIDERS,\n    MODEL_PROVIDERS_DICT,\n    MODELS_METADATA,\n)\nfrom langflow.base.models.model_utils import get_model_name\nfrom langflow.components.helpers.current_date import CurrentDateComponent\nfrom langflow.components.helpers.memory import MemoryComponent\nfrom langflow.components.langchain_utilities.tool_calling import ToolCallingAgentComponent\nfrom langflow.custom.custom_component.component import _get_component_toolkit\nfrom langflow.custom.utils import update_component_build_config\nfrom langflow.field_typing import Tool\nfrom langflow.helpers.base_model import build_model_from_schema\nfrom langflow.io import BoolInput, DropdownInput, IntInput, MultilineInput, Output, TableInput\nfrom langflow.logging import logger\nfrom langflow.schema.data import Data\nfrom langflow.schema.dotdict import dotdict\nfrom langflow.schema.message import Message\nfrom langflow.schema.table import EditMode\n\n\ndef set_advanced_true(component_input):\n    component_input.advanced = True\n    return component_input\n\n\nMODEL_PROVIDERS_LIST = [\"Anthropic\", \"Google Generative AI\", \"Groq\", \"OpenAI\"]\n\n\nclass AgentComponent(ToolCallingAgentComponent):\n    display_name: str = \"Agent\"\n    description: str = \"Define the agent's instructions, then enter a task to complete using tools.\"\n    documentation: str = \"https://docs.langflow.org/agents\"\n    icon = \"bot\"\n    beta = False\n    name = \"Agent\"\n\n    memory_inputs = [set_advanced_true(component_input) for component_input in MemoryComponent().inputs]\n\n    # Filter out json_mode from OpenAI inputs since we handle structured output differently\n    openai_inputs_filtered = [\n        input_field\n        for input_field in MODEL_PROVIDERS_DICT[\"OpenAI\"][\"inputs\"]\n        if not (hasattr(input_field, \"name\") and input_field.name == \"json_mode\")\n    ]\n\n    inputs = [\n        DropdownInput(\n            name=\"agent_llm\",\n            display_name=\"Model Provider\",\n            info=\"The provider of the language model that the agent will use to generate responses.\",\n            options=[*MODEL_PROVIDERS_LIST, \"Custom\"],\n            value=\"OpenAI\",\n            real_time_refresh=True,\n            input_types=[],\n            options_metadata=[MODELS_METADATA[key] for key in MODEL_PROVIDERS_LIST] + [{\"icon\": \"brain\"}],\n        ),\n        *openai_inputs_filtered,\n        MultilineInput(\n            name=\"system_prompt\",\n            display_name=\"Agent Instructions\",\n            info=\"System Prompt: Initial instructions and context provided to guide the agent's behavior.\",\n            value=\"You are a helpful assistant that can use tools to answer questions and perform tasks.\",\n            advanced=False,\n        ),\n        IntInput(\n            name=\"n_messages\",\n            display_name=\"Number of Chat History Messages\",\n            value=100,\n            info=\"Number of chat history messages to retrieve.\",\n            advanced=True,\n            show=True,\n        ),\n        MultilineInput(\n            name=\"format_instructions\",\n            display_name=\"Output Format Instructions\",\n            info=\"Generic Template for structured output formatting. Valid only with Structured response.\",\n            value=(\n                \"You are an AI that extracts structured JSON objects from unstructured text. \"\n                \"Use a predefined schema with expected types (str, int, float, bool, dict). \"\n                \"Extract ALL relevant instances that match the schema - if multiple patterns exist, capture them all. \"\n                \"Fill missing or ambiguous values with defaults: null for missing values. \"\n                \"Remove exact duplicates but keep variations that have different field values. \"\n                \"Always return valid JSON in the expected format, never throw errors. \"\n                \"If multiple objects can be extracted, return them all in the structured format.\"\n            ),\n            advanced=True,\n        ),\n        TableInput(\n            name=\"output_schema\",\n            display_name=\"Output Schema\",\n            info=(\n                \"Schema Validation: Define the structure and data types for structured output. \"\n                \"No validation if no output schema.\"\n            ),\n            advanced=True,\n            required=False,\n            value=[],\n            table_schema=[\n                {\n                    \"name\": \"name\",\n                    \"display_name\": \"Name\",\n                    \"type\": \"str\",\n                    \"description\": \"Specify the name of the output field.\",\n                    \"default\": \"field\",\n                    \"edit_mode\": EditMode.INLINE,\n                },\n                {\n                    \"name\": \"description\",\n                    \"display_name\": \"Description\",\n                    \"type\": \"str\",\n                    \"description\": \"Describe the purpose of the output field.\",\n                    \"default\": \"description of field\",\n                    \"edit_mode\": EditMode.POPOVER,\n                },\n                {\n                    \"name\": \"type\",\n                    \"display_name\": \"Type\",\n                    \"type\": \"str\",\n                    \"edit_mode\": EditMode.INLINE,\n                    \"description\": (\"Indicate the data type of the output field (e.g., str, int, float, bool, dict).\"),\n                    \"options\": [\"str\", \"int\", \"float\", \"bool\", \"dict\"],\n                    \"default\": \"str\",\n                },\n                {\n                    \"name\": \"multiple\",\n                    \"display_name\": \"As List\",\n                    \"type\": \"boolean\",\n                    \"description\": \"Set to True if this output field should be a list of the specified type.\",\n                    \"default\": \"False\",\n                    \"edit_mode\": EditMode.INLINE,\n                },\n            ],\n        ),\n        *LCToolsAgentComponent._base_inputs,\n        # removed memory inputs from agent component\n        # *memory_inputs,\n        BoolInput(\n            name=\"add_current_date_tool\",\n            display_name=\"Current Date\",\n            advanced=True,\n            info=\"If true, will add a tool to the agent that returns the current date.\",\n            value=True,\n        ),\n    ]\n    outputs = [\n        Output(name=\"response\", display_name=\"Response\", method=\"message_response\"),\n        Output(name=\"structured_response\", display_name=\"Structured Response\", method=\"json_response\", tool_mode=False),\n    ]\n\n    async def get_agent_requirements(self):\n        \"\"\"Get the agent requirements for the agent.\"\"\"\n        llm_model, display_name = await self.get_llm()\n        if llm_model is None:\n            msg = \"No language model selected. Please choose a model to proceed.\"\n            raise ValueError(msg)\n        self.model_name = get_model_name(llm_model, display_name=display_name)\n\n        # Get memory data\n        self.chat_history = await self.get_memory_data()\n        if isinstance(self.chat_history, Message):\n            self.chat_history = [self.chat_history]\n\n        # Add current date tool if enabled\n        if self.add_current_date_tool:\n            if not isinstance(self.tools, list):  # type: ignore[has-type]\n                self.tools = []\n            current_date_tool = (await CurrentDateComponent(**self.get_base_args()).to_toolkit()).pop(0)\n            if not isinstance(current_date_tool, StructuredTool):\n                msg = \"CurrentDateComponent must be converted to a StructuredTool\"\n                raise TypeError(msg)\n            self.tools.append(current_date_tool)\n        return llm_model, self.chat_history, self.tools\n\n    async def message_response(self) -> Message:\n        try:\n            llm_model, self.chat_history, self.tools = await self.get_agent_requirements()\n            # Set up and run agent\n            self.set(\n                llm=llm_model,\n                tools=self.tools or [],\n                chat_history=self.chat_history,\n                input_value=self.input_value,\n                system_prompt=self.system_prompt,\n            )\n            agent = self.create_agent_runnable()\n            result = await self.run_agent(agent)\n\n            # Store result for potential JSON output\n            self._agent_result = result\n\n        except (ValueError, TypeError, KeyError) as e:\n            await logger.aerror(f\"{type(e).__name__}: {e!s}\")\n            raise\n        except ExceptionWithMessageError as e:\n            await logger.aerror(f\"ExceptionWithMessageError occurred: {e}\")\n            raise\n        # Avoid catching blind Exception; let truly unexpected exceptions propagate\n        except Exception as e:\n            await logger.aerror(f\"Unexpected error: {e!s}\")\n            raise\n        else:\n            return result\n\n    def _preprocess_schema(self, schema):\n        \"\"\"Preprocess schema to ensure correct data types for build_model_from_schema.\"\"\"\n        processed_schema = []\n        for field in schema:\n            processed_field = {\n                \"name\": str(field.get(\"name\", \"field\")),\n                \"type\": str(field.get(\"type\", \"str\")),\n                \"description\": str(field.get(\"description\", \"\")),\n                \"multiple\": field.get(\"multiple\", False),\n            }\n            # Ensure multiple is handled correctly\n            if isinstance(processed_field[\"multiple\"], str):\n                processed_field[\"multiple\"] = processed_field[\"multiple\"].lower() in [\"true\", \"1\", \"t\", \"y\", \"yes\"]\n            processed_schema.append(processed_field)\n        return processed_schema\n\n    async def build_structured_output_base(self, content: str):\n        \"\"\"Build structured output with optional BaseModel validation.\"\"\"\n        json_pattern = r\"\\{.*\\}\"\n        schema_error_msg = \"Try setting an output schema\"\n\n        # Try to parse content as JSON first\n        json_data = None\n        try:\n            json_data = json.loads(content)\n        except json.JSONDecodeError:\n            json_match = re.search(json_pattern, content, re.DOTALL)\n            if json_match:\n                try:\n                    json_data = json.loads(json_match.group())\n                except json.JSONDecodeError:\n                    return {\"content\": content, \"error\": schema_error_msg}\n            else:\n                return {\"content\": content, \"error\": schema_error_msg}\n\n        # If no output schema provided, return parsed JSON without validation\n        if not hasattr(self, \"output_schema\") or not self.output_schema or len(self.output_schema) == 0:\n            return json_data\n\n        # Use BaseModel validation with schema\n        try:\n            processed_schema = self._preprocess_schema(self.output_schema)\n            output_model = build_model_from_schema(processed_schema)\n\n            # Validate against the schema\n            if isinstance(json_data, list):\n                # Multiple objects\n                validated_objects = []\n                for item in json_data:\n                    try:\n                        validated_obj = output_model.model_validate(item)\n                        validated_objects.append(validated_obj.model_dump())\n                    except ValidationError as e:\n                        await logger.aerror(f\"Validation error for item: {e}\")\n                        # Include invalid items with error info\n                        validated_objects.append({\"data\": item, \"validation_error\": str(e)})\n                return validated_objects\n\n            # Single object\n            try:\n                validated_obj = output_model.model_validate(json_data)\n                return [validated_obj.model_dump()]  # Return as list for consistency\n            except ValidationError as e:\n                await logger.aerror(f\"Validation error: {e}\")\n                return [{\"data\": json_data, \"validation_error\": str(e)}]\n\n        except (TypeError, ValueError) as e:\n            await logger.aerror(f\"Error building structured output: {e}\")\n            # Fallback to parsed JSON without validation\n            return json_data\n\n    async def json_response(self) -> Data:\n        \"\"\"Convert agent response to structured JSON Data output with schema validation.\"\"\"\n        # Always use structured chat agent for JSON response mode for better JSON formatting\n        try:\n            system_components = []\n\n            # 1. Agent Instructions (system_prompt)\n            agent_instructions = getattr(self, \"system_prompt\", \"\") or \"\"\n            if agent_instructions:\n                system_components.append(f\"{agent_instructions}\")\n\n            # 2. Format Instructions\n            format_instructions = getattr(self, \"format_instructions\", \"\") or \"\"\n            if format_instructions:\n                system_components.append(f\"Format instructions: {format_instructions}\")\n\n            # 3. Schema Information from BaseModel\n            if hasattr(self, \"output_schema\") and self.output_schema and len(self.output_schema) > 0:\n                try:\n                    processed_schema = self._preprocess_schema(self.output_schema)\n                    output_model = build_model_from_schema(processed_schema)\n                    schema_dict = output_model.model_json_schema()\n                    schema_info = (\n                        \"You are given some text that may include format instructions, \"\n                        \"explanations, or other content alongside a JSON schema.\\n\\n\"\n                        \"Your task:\\n\"\n                        \"- Extract only the JSON schema.\\n\"\n                        \"- Return it as valid JSON.\\n\"\n                        \"- Do not include format instructions, explanations, or extra text.\\n\\n\"\n                        \"Input:\\n\"\n                        f\"{json.dumps(schema_dict, indent=2)}\\n\\n\"\n                        \"Output (only JSON schema):\"\n                    )\n                    system_components.append(schema_info)\n                except (ValidationError, ValueError, TypeError, KeyError) as e:\n                    await logger.aerror(f\"Could not build schema for prompt: {e}\", exc_info=True)\n\n            # Combine all components\n            combined_instructions = \"\\n\\n\".join(system_components) if system_components else \"\"\n            llm_model, self.chat_history, self.tools = await self.get_agent_requirements()\n            self.set(\n                llm=llm_model,\n                tools=self.tools or [],\n                chat_history=self.chat_history,\n                input_value=self.input_value,\n                system_prompt=combined_instructions,\n            )\n\n            # Create and run structured chat agent\n            try:\n                structured_agent = self.create_agent_runnable()\n            except (NotImplementedError, ValueError, TypeError) as e:\n                await logger.aerror(f\"Error with structured chat agent: {e}\")\n                raise\n            try:\n                result = await self.run_agent(structured_agent)\n            except (ExceptionWithMessageError, ValueError, TypeError, RuntimeError) as e:\n                await logger.aerror(f\"Error with structured agent result: {e}\")\n                raise\n            # Extract content from structured agent result\n            if hasattr(result, \"content\"):\n                content = result.content\n            elif hasattr(result, \"text\"):\n                content = result.text\n            else:\n                content = str(result)\n\n        except (ExceptionWithMessageError, ValueError, TypeError, NotImplementedError, AttributeError) as e:\n            await logger.aerror(f\"Error with structured chat agent: {e}\")\n            # Fallback to regular agent\n            content_str = \"No content returned from agent\"\n            return Data(data={\"content\": content_str, \"error\": str(e)})\n\n        # Process with structured output validation\n        try:\n            structured_output = await self.build_structured_output_base(content)\n\n            # Handle different output formats\n            if isinstance(structured_output, list) and structured_output:\n                if len(structured_output) == 1:\n                    return Data(data=structured_output[0])\n                return Data(data={\"results\": structured_output})\n            if isinstance(structured_output, dict):\n                return Data(data=structured_output)\n            return Data(data={\"content\": content})\n\n        except (ValueError, TypeError) as e:\n            await logger.aerror(f\"Error in structured output processing: {e}\")\n            return Data(data={\"content\": content, \"error\": str(e)})\n\n    async def get_memory_data(self):\n        # TODO: This is a temporary fix to avoid message duplication. We should develop a function for this.\n        messages = (\n            await MemoryComponent(**self.get_base_args())\n            .set(session_id=self.graph.session_id, order=\"Ascending\", n_messages=self.n_messages)\n            .retrieve_messages()\n        )\n        return [\n            message for message in messages if getattr(message, \"id\", None) != getattr(self.input_value, \"id\", None)\n        ]\n\n    async def get_llm(self):\n        if not isinstance(self.agent_llm, str):\n            return self.agent_llm, None\n\n        try:\n            provider_info = MODEL_PROVIDERS_DICT.get(self.agent_llm)\n            if not provider_info:\n                msg = f\"Invalid model provider: {self.agent_llm}\"\n                raise ValueError(msg)\n\n            component_class = provider_info.get(\"component_class\")\n            display_name = component_class.display_name\n            inputs = provider_info.get(\"inputs\")\n            prefix = provider_info.get(\"prefix\", \"\")\n\n            return self._build_llm_model(component_class, inputs, prefix), display_name\n\n        except (AttributeError, ValueError, TypeError, RuntimeError) as e:\n            await logger.aerror(f\"Error building {self.agent_llm} language model: {e!s}\")\n            msg = f\"Failed to initialize language model: {e!s}\"\n            raise ValueError(msg) from e\n\n    def _build_llm_model(self, component, inputs, prefix=\"\"):\n        model_kwargs = {}\n        for input_ in inputs:\n            if hasattr(self, f\"{prefix}{input_.name}\"):\n                model_kwargs[input_.name] = getattr(self, f\"{prefix}{input_.name}\")\n        return component.set(**model_kwargs).build_model()\n\n    def set_component_params(self, component):\n        provider_info = MODEL_PROVIDERS_DICT.get(self.agent_llm)\n        if provider_info:\n            inputs = provider_info.get(\"inputs\")\n            prefix = provider_info.get(\"prefix\")\n            # Filter out json_mode and only use attributes that exist on this component\n            model_kwargs = {}\n            for input_ in inputs:\n                if hasattr(self, f\"{prefix}{input_.name}\"):\n                    model_kwargs[input_.name] = getattr(self, f\"{prefix}{input_.name}\")\n\n            return component.set(**model_kwargs)\n        return component\n\n    def delete_fields(self, build_config: dotdict, fields: dict | list[str]) -> None:\n        \"\"\"Delete specified fields from build_config.\"\"\"\n        for field in fields:\n            build_config.pop(field, None)\n\n    def update_input_types(self, build_config: dotdict) -> dotdict:\n        \"\"\"Update input types for all fields in build_config.\"\"\"\n        for key, value in build_config.items():\n            if isinstance(value, dict):\n                if value.get(\"input_types\") is None:\n                    build_config[key][\"input_types\"] = []\n            elif hasattr(value, \"input_types\") and value.input_types is None:\n                value.input_types = []\n        return build_config\n\n    async def update_build_config(\n        self, build_config: dotdict, field_value: str, field_name: str | None = None\n    ) -> dotdict:\n        # Iterate over all providers in the MODEL_PROVIDERS_DICT\n        # Existing logic for updating build_config\n        if field_name in (\"agent_llm\",):\n            build_config[\"agent_llm\"][\"value\"] = field_value\n            provider_info = MODEL_PROVIDERS_DICT.get(field_value)\n            if provider_info:\n                component_class = provider_info.get(\"component_class\")\n                if component_class and hasattr(component_class, \"update_build_config\"):\n                    # Call the component class's update_build_config method\n                    build_config = await update_component_build_config(\n                        component_class, build_config, field_value, \"model_name\"\n                    )\n\n            provider_configs: dict[str, tuple[dict, list[dict]]] = {\n                provider: (\n                    MODEL_PROVIDERS_DICT[provider][\"fields\"],\n                    [\n                        MODEL_PROVIDERS_DICT[other_provider][\"fields\"]\n                        for other_provider in MODEL_PROVIDERS_DICT\n                        if other_provider != provider\n                    ],\n                )\n                for provider in MODEL_PROVIDERS_DICT\n            }\n            if field_value in provider_configs:\n                fields_to_add, fields_to_delete = provider_configs[field_value]\n\n                # Delete fields from other providers\n                for fields in fields_to_delete:\n                    self.delete_fields(build_config, fields)\n\n                # Add provider-specific fields\n                if field_value == \"OpenAI\" and not any(field in build_config for field in fields_to_add):\n                    build_config.update(fields_to_add)\n                else:\n                    build_config.update(fields_to_add)\n                # Reset input types for agent_llm\n                build_config[\"agent_llm\"][\"input_types\"] = []\n            elif field_value == \"Custom\":\n                # Delete all provider fields\n                self.delete_fields(build_config, ALL_PROVIDER_FIELDS)\n                # Update with custom component\n                custom_component = DropdownInput(\n                    name=\"agent_llm\",\n                    display_name=\"Language Model\",\n                    options=[*sorted(MODEL_PROVIDERS), \"Custom\"],\n                    value=\"Custom\",\n                    real_time_refresh=True,\n                    input_types=[\"LanguageModel\"],\n                    options_metadata=[MODELS_METADATA[key] for key in sorted(MODELS_METADATA.keys())]\n                    + [{\"icon\": \"brain\"}],\n                )\n                build_config.update({\"agent_llm\": custom_component.to_dict()})\n            # Update input types for all fields\n            build_config = self.update_input_types(build_config)\n\n            # Validate required keys\n            default_keys = [\n                \"code\",\n                \"_type\",\n                \"agent_llm\",\n                \"tools\",\n                \"input_value\",\n                \"add_current_date_tool\",\n                \"system_prompt\",\n                \"agent_description\",\n                \"max_iterations\",\n                \"handle_parsing_errors\",\n                \"verbose\",\n            ]\n            missing_keys = [key for key in default_keys if key not in build_config]\n            if missing_keys:\n                msg = f\"Missing required keys in build_config: {missing_keys}\"\n                raise ValueError(msg)\n        if (\n            isinstance(self.agent_llm, str)\n            and self.agent_llm in MODEL_PROVIDERS_DICT\n            and field_name in MODEL_DYNAMIC_UPDATE_FIELDS\n        ):\n            provider_info = MODEL_PROVIDERS_DICT.get(self.agent_llm)\n            if provider_info:\n                component_class = provider_info.get(\"component_class\")\n                component_class = self.set_component_params(component_class)\n                prefix = provider_info.get(\"prefix\")\n                if component_class and hasattr(component_class, \"update_build_config\"):\n                    # Call each component class's update_build_config method\n                    # remove the prefix from the field_name\n                    if isinstance(field_name, str) and isinstance(prefix, str):\n                        field_name = field_name.replace(prefix, \"\")\n                    build_config = await update_component_build_config(\n                        component_class, build_config, field_value, \"model_name\"\n                    )\n        return dotdict({k: v.to_dict() if hasattr(v, \"to_dict\") else v for k, v in build_config.items()})\n\n    async def _get_tools(self) -> list[Tool]:\n        component_toolkit = _get_component_toolkit()\n        tools_names = self._build_tools_names()\n        agent_description = self.get_tool_description()\n        # TODO: Agent Description Depreciated Feature to be removed\n        description = f\"{agent_description}{tools_names}\"\n        tools = component_toolkit(component=self).get_tools(\n            tool_name=\"Call_Agent\", tool_description=description, callbacks=self.get_langchain_callbacks()\n        )\n        if hasattr(self, \"tools_metadata\"):\n            tools = component_toolkit(component=self, metadata=self.tools_metadata).update_tools_metadata(tools=tools)\n        return tools\n"
+                "value": "import json\nimport re\n\nfrom langchain_core.tools import StructuredTool\nfrom pydantic import ValidationError\n\nfrom langflow.base.agents.agent import LCToolsAgentComponent\nfrom langflow.base.agents.events import ExceptionWithMessageError\nfrom langflow.base.models.model_input_constants import (\n    ALL_PROVIDER_FIELDS,\n    MODEL_DYNAMIC_UPDATE_FIELDS,\n    MODEL_PROVIDERS,\n    MODEL_PROVIDERS_DICT,\n    MODELS_METADATA,\n)\nfrom langflow.base.models.model_utils import get_model_name\nfrom langflow.components.helpers.current_date import CurrentDateComponent\nfrom langflow.components.helpers.memory import MemoryComponent\nfrom langflow.components.langchain_utilities.tool_calling import ToolCallingAgentComponent\nfrom langflow.custom.custom_component.component import _get_component_toolkit\nfrom langflow.custom.utils import update_component_build_config\nfrom langflow.field_typing import Tool\nfrom langflow.helpers.base_model import build_model_from_schema\nfrom langflow.io import BoolInput, DropdownInput, IntInput, MultilineInput, Output, TableInput\nfrom langflow.logging import logger\nfrom langflow.schema.data import Data\nfrom langflow.schema.dotdict import dotdict\nfrom langflow.schema.message import Message\nfrom langflow.schema.table import EditMode\n\n\ndef set_advanced_true(component_input):\n    component_input.advanced = True\n    return component_input\n\n\nMODEL_PROVIDERS_LIST = [\"Anthropic\", \"Google Generative AI\", \"Groq\", \"OpenAI\"]\n\n\nclass AgentComponent(ToolCallingAgentComponent):\n    display_name: str = \"Agent\"\n    description: str = \"Define the agent's instructions, then enter a task to complete using tools.\"\n    documentation: str = \"https://docs.langflow.org/agents\"\n    icon = \"bot\"\n    beta = False\n    name = \"Agent\"\n\n    memory_inputs = [set_advanced_true(component_input) for component_input in MemoryComponent().inputs]\n\n    # Filter out json_mode from OpenAI inputs since we handle structured output differently\n    openai_inputs_filtered = [\n        input_field\n        for input_field in MODEL_PROVIDERS_DICT[\"OpenAI\"][\"inputs\"]\n        if not (hasattr(input_field, \"name\") and input_field.name == \"json_mode\")\n    ]\n\n    inputs = [\n        DropdownInput(\n            name=\"agent_llm\",\n            display_name=\"Model Provider\",\n            info=\"The provider of the language model that the agent will use to generate responses.\",\n            options=[*MODEL_PROVIDERS_LIST, \"Custom\"],\n            value=\"OpenAI\",\n            real_time_refresh=True,\n            input_types=[],\n            options_metadata=[MODELS_METADATA[key] for key in MODEL_PROVIDERS_LIST] + [{\"icon\": \"brain\"}],\n        ),\n        *openai_inputs_filtered,\n        MultilineInput(\n            name=\"system_prompt\",\n            display_name=\"Agent Instructions\",\n            info=\"System Prompt: Initial instructions and context provided to guide the agent's behavior.\",\n            value=\"You are a helpful assistant that can use tools to answer questions and perform tasks.\",\n            advanced=False,\n        ),\n        IntInput(\n            name=\"n_messages\",\n            display_name=\"Number of Chat History Messages\",\n            value=100,\n            info=\"Number of chat history messages to retrieve.\",\n            advanced=True,\n            show=True,\n        ),\n        MultilineInput(\n            name=\"format_instructions\",\n            display_name=\"Output Format Instructions\",\n            info=\"Generic Template for structured output formatting. Valid only with Structured response.\",\n            value=(\n                \"You are an AI that extracts structured JSON objects from unstructured text. \"\n                \"Use a predefined schema with expected types (str, int, float, bool, dict). \"\n                \"Extract ALL relevant instances that match the schema - if multiple patterns exist, capture them all. \"\n                \"Fill missing or ambiguous values with defaults: null for missing values. \"\n                \"Remove exact duplicates but keep variations that have different field values. \"\n                \"Always return valid JSON in the expected format, never throw errors. \"\n                \"If multiple objects can be extracted, return them all in the structured format.\"\n            ),\n            advanced=True,\n        ),\n        TableInput(\n            name=\"output_schema\",\n            display_name=\"Output Schema\",\n            info=(\n                \"Schema Validation: Define the structure and data types for structured output. \"\n                \"No validation if no output schema.\"\n            ),\n            advanced=True,\n            required=False,\n            value=[],\n            table_schema=[\n                {\n                    \"name\": \"name\",\n                    \"display_name\": \"Name\",\n                    \"type\": \"str\",\n                    \"description\": \"Specify the name of the output field.\",\n                    \"default\": \"field\",\n                    \"edit_mode\": EditMode.INLINE,\n                },\n                {\n                    \"name\": \"description\",\n                    \"display_name\": \"Description\",\n                    \"type\": \"str\",\n                    \"description\": \"Describe the purpose of the output field.\",\n                    \"default\": \"description of field\",\n                    \"edit_mode\": EditMode.POPOVER,\n                },\n                {\n                    \"name\": \"type\",\n                    \"display_name\": \"Type\",\n                    \"type\": \"str\",\n                    \"edit_mode\": EditMode.INLINE,\n                    \"description\": (\"Indicate the data type of the output field (e.g., str, int, float, bool, dict).\"),\n                    \"options\": [\"str\", \"int\", \"float\", \"bool\", \"dict\"],\n                    \"default\": \"str\",\n                },\n                {\n                    \"name\": \"multiple\",\n                    \"display_name\": \"As List\",\n                    \"type\": \"boolean\",\n                    \"description\": \"Set to True if this output field should be a list of the specified type.\",\n                    \"default\": \"False\",\n                    \"edit_mode\": EditMode.INLINE,\n                },\n            ],\n        ),\n        *LCToolsAgentComponent._base_inputs,\n        # removed memory inputs from agent component\n        # *memory_inputs,\n        BoolInput(\n            name=\"add_current_date_tool\",\n            display_name=\"Current Date\",\n            advanced=True,\n            info=\"If true, will add a tool to the agent that returns the current date.\",\n            value=True,\n        ),\n    ]\n    outputs = [\n        Output(name=\"response\", display_name=\"Response\", method=\"message_response\"),\n        Output(name=\"structured_response\", display_name=\"Structured Response\", method=\"json_response\", tool_mode=False),\n    ]\n\n    async def get_agent_requirements(self):\n        \"\"\"Get the agent requirements for the agent.\"\"\"\n        llm_model, display_name = await self.get_llm()\n        if llm_model is None:\n            msg = \"No language model selected. Please choose a model to proceed.\"\n            raise ValueError(msg)\n        self.model_name = get_model_name(llm_model, display_name=display_name)\n\n        # Get memory data\n        self.chat_history = await self.get_memory_data()\n        if isinstance(self.chat_history, Message):\n            self.chat_history = [self.chat_history]\n\n        # Add current date tool if enabled\n        if self.add_current_date_tool:\n            if not isinstance(self.tools, list):  # type: ignore[has-type]\n                self.tools = []\n            current_date_tool = (await CurrentDateComponent(**self.get_base_args()).to_toolkit()).pop(0)\n            if not isinstance(current_date_tool, StructuredTool):\n                msg = \"CurrentDateComponent must be converted to a StructuredTool\"\n                raise TypeError(msg)\n            self.tools.append(current_date_tool)\n        return llm_model, self.chat_history, self.tools\n\n    async def message_response(self) -> Message:\n        try:\n            llm_model, self.chat_history, self.tools = await self.get_agent_requirements()\n            # Set up and run agent\n            self.set(\n                llm=llm_model,\n                tools=self.tools or [],\n                chat_history=self.chat_history,\n                input_value=self.input_value,\n                system_prompt=self.system_prompt,\n            )\n            agent = self.create_agent_runnable()\n            result = await self.run_agent(agent)\n\n            # Store result for potential JSON output\n            self._agent_result = result\n\n        except (ValueError, TypeError, KeyError) as e:\n            await logger.aerror(f\"{type(e).__name__}: {e!s}\")\n            raise\n        except ExceptionWithMessageError as e:\n            await logger.aerror(f\"ExceptionWithMessageError occurred: {e}\")\n            raise\n        # Avoid catching blind Exception; let truly unexpected exceptions propagate\n        except Exception as e:\n            await logger.aerror(f\"Unexpected error: {e!s}\")\n            raise\n        else:\n            return result\n\n    def _preprocess_schema(self, schema):\n        \"\"\"Preprocess schema to ensure correct data types for build_model_from_schema.\"\"\"\n        processed_schema = []\n        for field in schema:\n            processed_field = {\n                \"name\": str(field.get(\"name\", \"field\")),\n                \"type\": str(field.get(\"type\", \"str\")),\n                \"description\": str(field.get(\"description\", \"\")),\n                \"multiple\": field.get(\"multiple\", False),\n            }\n            # Ensure multiple is handled correctly\n            if isinstance(processed_field[\"multiple\"], str):\n                processed_field[\"multiple\"] = processed_field[\"multiple\"].lower() in [\"true\", \"1\", \"t\", \"y\", \"yes\"]\n            processed_schema.append(processed_field)\n        return processed_schema\n\n    async def build_structured_output_base(self, content: str):\n        \"\"\"Build structured output with optional BaseModel validation.\"\"\"\n        json_pattern = r\"\\{.*\\}\"\n        schema_error_msg = \"Try setting an output schema\"\n\n        # Try to parse content as JSON first\n        json_data = None\n        try:\n            json_data = json.loads(content)\n        except json.JSONDecodeError:\n            json_match = re.search(json_pattern, content, re.DOTALL)\n            if json_match:\n                try:\n                    json_data = json.loads(json_match.group())\n                except json.JSONDecodeError:\n                    return {\"content\": content, \"error\": schema_error_msg}\n            else:\n                return {\"content\": content, \"error\": schema_error_msg}\n\n        # If no output schema provided, return parsed JSON without validation\n        if not hasattr(self, \"output_schema\") or not self.output_schema or len(self.output_schema) == 0:\n            return json_data\n\n        # Use BaseModel validation with schema\n        try:\n            processed_schema = self._preprocess_schema(self.output_schema)\n            output_model = build_model_from_schema(processed_schema)\n\n            # Validate against the schema\n            if isinstance(json_data, list):\n                # Multiple objects\n                validated_objects = []\n                for item in json_data:\n                    try:\n                        validated_obj = output_model.model_validate(item)\n                        validated_objects.append(validated_obj.model_dump())\n                    except ValidationError as e:\n                        await logger.aerror(f\"Validation error for item: {e}\")\n                        # Include invalid items with error info\n                        validated_objects.append({\"data\": item, \"validation_error\": str(e)})\n                return validated_objects\n\n            # Single object\n            try:\n                validated_obj = output_model.model_validate(json_data)\n                return [validated_obj.model_dump()]  # Return as list for consistency\n            except ValidationError as e:\n                await logger.aerror(f\"Validation error: {e}\")\n                return [{\"data\": json_data, \"validation_error\": str(e)}]\n\n        except (TypeError, ValueError) as e:\n            await logger.aerror(f\"Error building structured output: {e}\")\n            # Fallback to parsed JSON without validation\n            return json_data\n\n    async def json_response(self) -> Data:\n        \"\"\"Convert agent response to structured JSON Data output with schema validation.\"\"\"\n        # Always use structured chat agent for JSON response mode for better JSON formatting\n        try:\n            system_components = []\n\n            # 1. Agent Instructions (system_prompt)\n            agent_instructions = getattr(self, \"system_prompt\", \"\") or \"\"\n            if agent_instructions:\n                system_components.append(f\"{agent_instructions}\")\n\n            # 2. Format Instructions\n            format_instructions = getattr(self, \"format_instructions\", \"\") or \"\"\n            if format_instructions:\n                system_components.append(f\"Format instructions: {format_instructions}\")\n\n            # 3. Schema Information from BaseModel\n            if hasattr(self, \"output_schema\") and self.output_schema and len(self.output_schema) > 0:\n                try:\n                    processed_schema = self._preprocess_schema(self.output_schema)\n                    output_model = build_model_from_schema(processed_schema)\n                    schema_dict = output_model.model_json_schema()\n                    schema_info = (\n                        \"You are given some text that may include format instructions, \"\n                        \"explanations, or other content alongside a JSON schema.\\n\\n\"\n                        \"Your task:\\n\"\n                        \"- Extract only the JSON schema.\\n\"\n                        \"- Return it as valid JSON.\\n\"\n                        \"- Do not include format instructions, explanations, or extra text.\\n\\n\"\n                        \"Input:\\n\"\n                        f\"{json.dumps(schema_dict, indent=2)}\\n\\n\"\n                        \"Output (only JSON schema):\"\n                    )\n                    system_components.append(schema_info)\n                except (ValidationError, ValueError, TypeError, KeyError) as e:\n                    await logger.aerror(f\"Could not build schema for prompt: {e}\", exc_info=True)\n\n            # Combine all components\n            combined_instructions = \"\\n\\n\".join(system_components) if system_components else \"\"\n            llm_model, self.chat_history, self.tools = await self.get_agent_requirements()\n            self.set(\n                llm=llm_model,\n                tools=self.tools or [],\n                chat_history=self.chat_history,\n                input_value=self.input_value,\n                system_prompt=combined_instructions,\n            )\n\n            # Create and run structured chat agent\n            try:\n                structured_agent = self.create_agent_runnable()\n            except (NotImplementedError, ValueError, TypeError) as e:\n                await logger.aerror(f\"Error with structured chat agent: {e}\")\n                raise\n            try:\n                result = await self.run_agent(structured_agent)\n            except (ExceptionWithMessageError, ValueError, TypeError, RuntimeError) as e:\n                await logger.aerror(f\"Error with structured agent result: {e}\")\n                raise\n            # Extract content from structured agent result\n            if hasattr(result, \"content\"):\n                content = result.content\n            elif hasattr(result, \"text\"):\n                content = result.text\n            else:\n                content = str(result)\n\n        except (ExceptionWithMessageError, ValueError, TypeError, NotImplementedError, AttributeError) as e:\n            await logger.aerror(f\"Error with structured chat agent: {e}\")\n            # Fallback to regular agent\n            content_str = \"No content returned from agent\"\n            return Data(data={\"content\": content_str, \"error\": str(e)})\n\n        # Process with structured output validation\n        try:\n            structured_output = await self.build_structured_output_base(content)\n\n            # Handle different output formats\n            if isinstance(structured_output, list) and structured_output:\n                if len(structured_output) == 1:\n                    return Data(data=structured_output[0])\n                return Data(data={\"results\": structured_output})\n            if isinstance(structured_output, dict):\n                return Data(data=structured_output)\n            return Data(data={\"content\": content})\n\n        except (ValueError, TypeError) as e:\n            await logger.aerror(f\"Error in structured output processing: {e}\")\n            return Data(data={\"content\": content, \"error\": str(e)})\n\n    async def get_memory_data(self):\n        # TODO: This is a temporary fix to avoid message duplication. We should develop a function for this.\n        messages = (\n            await MemoryComponent(**self.get_base_args())\n            .set(session_id=self.graph.session_id, order=\"Ascending\", n_messages=self.n_messages)\n            .retrieve_messages()\n        )\n        return [\n            message for message in messages if getattr(message, \"id\", None) != getattr(self.input_value, \"id\", None)\n        ]\n\n    async def get_llm(self):\n        if not isinstance(self.agent_llm, str):\n            return self.agent_llm, None\n\n        try:\n            provider_info = MODEL_PROVIDERS_DICT.get(self.agent_llm)\n            if not provider_info:\n                msg = f\"Invalid model provider: {self.agent_llm}\"\n                raise ValueError(msg)\n\n            component_class = provider_info.get(\"component_class\")\n            display_name = component_class.display_name\n            inputs = provider_info.get(\"inputs\")\n            prefix = provider_info.get(\"prefix\", \"\")\n\n            return self._build_llm_model(component_class, inputs, prefix), display_name\n\n        except (AttributeError, ValueError, TypeError, RuntimeError) as e:\n            await logger.aerror(f\"Error building {self.agent_llm} language model: {e!s}\")\n            msg = f\"Failed to initialize language model: {e!s}\"\n            raise ValueError(msg) from e\n\n    def _build_llm_model(self, component, inputs, prefix=\"\"):\n        model_kwargs = {}\n        for input_ in inputs:\n            if hasattr(self, f\"{prefix}{input_.name}\"):\n                model_kwargs[input_.name] = getattr(self, f\"{prefix}{input_.name}\")\n        return component.set(**model_kwargs).build_model()\n\n    def set_component_params(self, component):\n        provider_info = MODEL_PROVIDERS_DICT.get(self.agent_llm)\n        if provider_info:\n            inputs = provider_info.get(\"inputs\")\n            prefix = provider_info.get(\"prefix\")\n            # Filter out json_mode and only use attributes that exist on this component\n            model_kwargs = {}\n            for input_ in inputs:\n                if hasattr(self, f\"{prefix}{input_.name}\"):\n                    model_kwargs[input_.name] = getattr(self, f\"{prefix}{input_.name}\")\n\n            return component.set(**model_kwargs)\n        return component\n\n    def delete_fields(self, build_config: dotdict, fields: dict | list[str]) -> None:\n        \"\"\"Delete specified fields from build_config.\"\"\"\n        for field in fields:\n            build_config.pop(field, None)\n\n    def update_input_types(self, build_config: dotdict) -> dotdict:\n        \"\"\"Update input types for all fields in build_config.\"\"\"\n        for key, value in build_config.items():\n            if isinstance(value, dict):\n                if value.get(\"input_types\") is None:\n                    build_config[key][\"input_types\"] = []\n            elif hasattr(value, \"input_types\") and value.input_types is None:\n                value.input_types = []\n        return build_config\n\n    async def update_build_config(\n        self, build_config: dotdict, field_value: str, field_name: str | None = None\n    ) -> dotdict:\n        # Iterate over all providers in the MODEL_PROVIDERS_DICT\n        # Existing logic for updating build_config\n        if field_name in (\"agent_llm\",):\n            build_config[\"agent_llm\"][\"value\"] = field_value\n            provider_info = MODEL_PROVIDERS_DICT.get(field_value)\n            if provider_info:\n                component_class = provider_info.get(\"component_class\")\n                if component_class and hasattr(component_class, \"update_build_config\"):\n                    # Call the component class's update_build_config method\n                    build_config = await update_component_build_config(\n                        component_class, build_config, field_value, \"model_name\"\n                    )\n\n            provider_configs: dict[str, tuple[dict, list[dict]]] = {\n                provider: (\n                    MODEL_PROVIDERS_DICT[provider][\"fields\"],\n                    [\n                        MODEL_PROVIDERS_DICT[other_provider][\"fields\"]\n                        for other_provider in MODEL_PROVIDERS_DICT\n                        if other_provider != provider\n                    ],\n                )\n                for provider in MODEL_PROVIDERS_DICT\n            }\n            if field_value in provider_configs:\n                fields_to_add, fields_to_delete = provider_configs[field_value]\n\n                # Delete fields from other providers\n                for fields in fields_to_delete:\n                    self.delete_fields(build_config, fields)\n\n                # Add provider-specific fields\n                if field_value == \"OpenAI\" and not any(field in build_config for field in fields_to_add):\n                    build_config.update(fields_to_add)\n                else:\n                    build_config.update(fields_to_add)\n                # Reset input types for agent_llm\n                build_config[\"agent_llm\"][\"input_types\"] = []\n                build_config[\"agent_llm\"][\"display_name\"] = \"Model Provider\"\n            elif field_value == \"Custom\":\n                # Delete all provider fields\n                self.delete_fields(build_config, ALL_PROVIDER_FIELDS)\n                # Update with custom component\n                custom_component = DropdownInput(\n                    name=\"agent_llm\",\n                    display_name=\"Language Model\",\n                    options=[*sorted(MODEL_PROVIDERS), \"Custom\"],\n                    value=\"Custom\",\n                    real_time_refresh=True,\n                    input_types=[\"LanguageModel\"],\n                    options_metadata=[MODELS_METADATA[key] for key in sorted(MODELS_METADATA.keys())]\n                    + [{\"icon\": \"brain\"}],\n                )\n                build_config.update({\"agent_llm\": custom_component.to_dict()})\n            # Update input types for all fields\n            build_config = self.update_input_types(build_config)\n\n            # Validate required keys\n            default_keys = [\n                \"code\",\n                \"_type\",\n                \"agent_llm\",\n                \"tools\",\n                \"input_value\",\n                \"add_current_date_tool\",\n                \"system_prompt\",\n                \"agent_description\",\n                \"max_iterations\",\n                \"handle_parsing_errors\",\n                \"verbose\",\n            ]\n            missing_keys = [key for key in default_keys if key not in build_config]\n            if missing_keys:\n                msg = f\"Missing required keys in build_config: {missing_keys}\"\n                raise ValueError(msg)\n        if (\n            isinstance(self.agent_llm, str)\n            and self.agent_llm in MODEL_PROVIDERS_DICT\n            and field_name in MODEL_DYNAMIC_UPDATE_FIELDS\n        ):\n            provider_info = MODEL_PROVIDERS_DICT.get(self.agent_llm)\n            if provider_info:\n                component_class = provider_info.get(\"component_class\")\n                component_class = self.set_component_params(component_class)\n                prefix = provider_info.get(\"prefix\")\n                if component_class and hasattr(component_class, \"update_build_config\"):\n                    # Call each component class's update_build_config method\n                    # remove the prefix from the field_name\n                    if isinstance(field_name, str) and isinstance(prefix, str):\n                        field_name = field_name.replace(prefix, \"\")\n                    build_config = await update_component_build_config(\n                        component_class, build_config, field_value, \"model_name\"\n                    )\n        return dotdict({k: v.to_dict() if hasattr(v, \"to_dict\") else v for k, v in build_config.items()})\n\n    async def _get_tools(self) -> list[Tool]:\n        component_toolkit = _get_component_toolkit()\n        tools_names = self._build_tools_names()\n        agent_description = self.get_tool_description()\n        # TODO: Agent Description Depreciated Feature to be removed\n        description = f\"{agent_description}{tools_names}\"\n        tools = component_toolkit(component=self).get_tools(\n            tool_name=\"Call_Agent\", tool_description=description, callbacks=self.get_langchain_callbacks()\n        )\n        if hasattr(self, \"tools_metadata\"):\n            tools = component_toolkit(component=self, metadata=self.tools_metadata).update_tools_metadata(tools=tools)\n        return tools\n"
               },
               "handle_parsing_errors": {
                 "_input_type": "BoolInput",

langflow/initial_setup/starter_projects/News Aggregator.json

@@ -1585,7 +1585,7 @@
                 "show": true,
                 "title_case": false,
                 "type": "code",
-                "value": "import json\nimport re\n\nfrom langchain_core.tools import StructuredTool\nfrom pydantic import ValidationError\n\nfrom langflow.base.agents.agent import LCToolsAgentComponent\nfrom langflow.base.agents.events import ExceptionWithMessageError\nfrom langflow.base.models.model_input_constants import (\n    ALL_PROVIDER_FIELDS,\n    MODEL_DYNAMIC_UPDATE_FIELDS,\n    MODEL_PROVIDERS,\n    MODEL_PROVIDERS_DICT,\n    MODELS_METADATA,\n)\nfrom langflow.base.models.model_utils import get_model_name\nfrom langflow.components.helpers.current_date import CurrentDateComponent\nfrom langflow.components.helpers.memory import MemoryComponent\nfrom langflow.components.langchain_utilities.tool_calling import ToolCallingAgentComponent\nfrom langflow.custom.custom_component.component import _get_component_toolkit\nfrom langflow.custom.utils import update_component_build_config\nfrom langflow.field_typing import Tool\nfrom langflow.helpers.base_model import build_model_from_schema\nfrom langflow.io import BoolInput, DropdownInput, IntInput, MultilineInput, Output, TableInput\nfrom langflow.logging import logger\nfrom langflow.schema.data import Data\nfrom langflow.schema.dotdict import dotdict\nfrom langflow.schema.message import Message\nfrom langflow.schema.table import EditMode\n\n\ndef set_advanced_true(component_input):\n    component_input.advanced = True\n    return component_input\n\n\nMODEL_PROVIDERS_LIST = [\"Anthropic\", \"Google Generative AI\", \"Groq\", \"OpenAI\"]\n\n\nclass AgentComponent(ToolCallingAgentComponent):\n    display_name: str = \"Agent\"\n    description: str = \"Define the agent's instructions, then enter a task to complete using tools.\"\n    documentation: str = \"https://docs.langflow.org/agents\"\n    icon = \"bot\"\n    beta = False\n    name = \"Agent\"\n\n    memory_inputs = [set_advanced_true(component_input) for component_input in MemoryComponent().inputs]\n\n    # Filter out json_mode from OpenAI inputs since we handle structured output differently\n    openai_inputs_filtered = [\n        input_field\n        for input_field in MODEL_PROVIDERS_DICT[\"OpenAI\"][\"inputs\"]\n        if not (hasattr(input_field, \"name\") and input_field.name == \"json_mode\")\n    ]\n\n    inputs = [\n        DropdownInput(\n            name=\"agent_llm\",\n            display_name=\"Model Provider\",\n            info=\"The provider of the language model that the agent will use to generate responses.\",\n            options=[*MODEL_PROVIDERS_LIST, \"Custom\"],\n            value=\"OpenAI\",\n            real_time_refresh=True,\n            input_types=[],\n            options_metadata=[MODELS_METADATA[key] for key in MODEL_PROVIDERS_LIST] + [{\"icon\": \"brain\"}],\n        ),\n        *openai_inputs_filtered,\n        MultilineInput(\n            name=\"system_prompt\",\n            display_name=\"Agent Instructions\",\n            info=\"System Prompt: Initial instructions and context provided to guide the agent's behavior.\",\n            value=\"You are a helpful assistant that can use tools to answer questions and perform tasks.\",\n            advanced=False,\n        ),\n        IntInput(\n            name=\"n_messages\",\n            display_name=\"Number of Chat History Messages\",\n            value=100,\n            info=\"Number of chat history messages to retrieve.\",\n            advanced=True,\n            show=True,\n        ),\n        MultilineInput(\n            name=\"format_instructions\",\n            display_name=\"Output Format Instructions\",\n            info=\"Generic Template for structured output formatting. Valid only with Structured response.\",\n            value=(\n                \"You are an AI that extracts structured JSON objects from unstructured text. \"\n                \"Use a predefined schema with expected types (str, int, float, bool, dict). \"\n                \"Extract ALL relevant instances that match the schema - if multiple patterns exist, capture them all. \"\n                \"Fill missing or ambiguous values with defaults: null for missing values. \"\n                \"Remove exact duplicates but keep variations that have different field values. \"\n                \"Always return valid JSON in the expected format, never throw errors. \"\n                \"If multiple objects can be extracted, return them all in the structured format.\"\n            ),\n            advanced=True,\n        ),\n        TableInput(\n            name=\"output_schema\",\n            display_name=\"Output Schema\",\n            info=(\n                \"Schema Validation: Define the structure and data types for structured output. \"\n                \"No validation if no output schema.\"\n            ),\n            advanced=True,\n            required=False,\n            value=[],\n            table_schema=[\n                {\n                    \"name\": \"name\",\n                    \"display_name\": \"Name\",\n                    \"type\": \"str\",\n                    \"description\": \"Specify the name of the output field.\",\n                    \"default\": \"field\",\n                    \"edit_mode\": EditMode.INLINE,\n                },\n                {\n                    \"name\": \"description\",\n                    \"display_name\": \"Description\",\n                    \"type\": \"str\",\n                    \"description\": \"Describe the purpose of the output field.\",\n                    \"default\": \"description of field\",\n                    \"edit_mode\": EditMode.POPOVER,\n                },\n                {\n                    \"name\": \"type\",\n                    \"display_name\": \"Type\",\n                    \"type\": \"str\",\n                    \"edit_mode\": EditMode.INLINE,\n                    \"description\": (\"Indicate the data type of the output field (e.g., str, int, float, bool, dict).\"),\n                    \"options\": [\"str\", \"int\", \"float\", \"bool\", \"dict\"],\n                    \"default\": \"str\",\n                },\n                {\n                    \"name\": \"multiple\",\n                    \"display_name\": \"As List\",\n                    \"type\": \"boolean\",\n                    \"description\": \"Set to True if this output field should be a list of the specified type.\",\n                    \"default\": \"False\",\n                    \"edit_mode\": EditMode.INLINE,\n                },\n            ],\n        ),\n        *LCToolsAgentComponent._base_inputs,\n        # removed memory inputs from agent component\n        # *memory_inputs,\n        BoolInput(\n            name=\"add_current_date_tool\",\n            display_name=\"Current Date\",\n            advanced=True,\n            info=\"If true, will add a tool to the agent that returns the current date.\",\n            value=True,\n        ),\n    ]\n    outputs = [\n        Output(name=\"response\", display_name=\"Response\", method=\"message_response\"),\n        Output(name=\"structured_response\", display_name=\"Structured Response\", method=\"json_response\", tool_mode=False),\n    ]\n\n    async def get_agent_requirements(self):\n        \"\"\"Get the agent requirements for the agent.\"\"\"\n        llm_model, display_name = await self.get_llm()\n        if llm_model is None:\n            msg = \"No language model selected. Please choose a model to proceed.\"\n            raise ValueError(msg)\n        self.model_name = get_model_name(llm_model, display_name=display_name)\n\n        # Get memory data\n        self.chat_history = await self.get_memory_data()\n        if isinstance(self.chat_history, Message):\n            self.chat_history = [self.chat_history]\n\n        # Add current date tool if enabled\n        if self.add_current_date_tool:\n            if not isinstance(self.tools, list):  # type: ignore[has-type]\n                self.tools = []\n            current_date_tool = (await CurrentDateComponent(**self.get_base_args()).to_toolkit()).pop(0)\n            if not isinstance(current_date_tool, StructuredTool):\n                msg = \"CurrentDateComponent must be converted to a StructuredTool\"\n                raise TypeError(msg)\n            self.tools.append(current_date_tool)\n        return llm_model, self.chat_history, self.tools\n\n    async def message_response(self) -> Message:\n        try:\n            llm_model, self.chat_history, self.tools = await self.get_agent_requirements()\n            # Set up and run agent\n            self.set(\n                llm=llm_model,\n                tools=self.tools or [],\n                chat_history=self.chat_history,\n                input_value=self.input_value,\n                system_prompt=self.system_prompt,\n            )\n            agent = self.create_agent_runnable()\n            result = await self.run_agent(agent)\n\n            # Store result for potential JSON output\n            self._agent_result = result\n\n        except (ValueError, TypeError, KeyError) as e:\n            await logger.aerror(f\"{type(e).__name__}: {e!s}\")\n            raise\n        except ExceptionWithMessageError as e:\n            await logger.aerror(f\"ExceptionWithMessageError occurred: {e}\")\n            raise\n        # Avoid catching blind Exception; let truly unexpected exceptions propagate\n        except Exception as e:\n            await logger.aerror(f\"Unexpected error: {e!s}\")\n            raise\n        else:\n            return result\n\n    def _preprocess_schema(self, schema):\n        \"\"\"Preprocess schema to ensure correct data types for build_model_from_schema.\"\"\"\n        processed_schema = []\n        for field in schema:\n            processed_field = {\n                \"name\": str(field.get(\"name\", \"field\")),\n                \"type\": str(field.get(\"type\", \"str\")),\n                \"description\": str(field.get(\"description\", \"\")),\n                \"multiple\": field.get(\"multiple\", False),\n            }\n            # Ensure multiple is handled correctly\n            if isinstance(processed_field[\"multiple\"], str):\n                processed_field[\"multiple\"] = processed_field[\"multiple\"].lower() in [\"true\", \"1\", \"t\", \"y\", \"yes\"]\n            processed_schema.append(processed_field)\n        return processed_schema\n\n    async def build_structured_output_base(self, content: str):\n        \"\"\"Build structured output with optional BaseModel validation.\"\"\"\n        json_pattern = r\"\\{.*\\}\"\n        schema_error_msg = \"Try setting an output schema\"\n\n        # Try to parse content as JSON first\n        json_data = None\n        try:\n            json_data = json.loads(content)\n        except json.JSONDecodeError:\n            json_match = re.search(json_pattern, content, re.DOTALL)\n            if json_match:\n                try:\n                    json_data = json.loads(json_match.group())\n                except json.JSONDecodeError:\n                    return {\"content\": content, \"error\": schema_error_msg}\n            else:\n                return {\"content\": content, \"error\": schema_error_msg}\n\n        # If no output schema provided, return parsed JSON without validation\n        if not hasattr(self, \"output_schema\") or not self.output_schema or len(self.output_schema) == 0:\n            return json_data\n\n        # Use BaseModel validation with schema\n        try:\n            processed_schema = self._preprocess_schema(self.output_schema)\n            output_model = build_model_from_schema(processed_schema)\n\n            # Validate against the schema\n            if isinstance(json_data, list):\n                # Multiple objects\n                validated_objects = []\n                for item in json_data:\n                    try:\n                        validated_obj = output_model.model_validate(item)\n                        validated_objects.append(validated_obj.model_dump())\n                    except ValidationError as e:\n                        await logger.aerror(f\"Validation error for item: {e}\")\n                        # Include invalid items with error info\n                        validated_objects.append({\"data\": item, \"validation_error\": str(e)})\n                return validated_objects\n\n            # Single object\n            try:\n                validated_obj = output_model.model_validate(json_data)\n                return [validated_obj.model_dump()]  # Return as list for consistency\n            except ValidationError as e:\n                await logger.aerror(f\"Validation error: {e}\")\n                return [{\"data\": json_data, \"validation_error\": str(e)}]\n\n        except (TypeError, ValueError) as e:\n            await logger.aerror(f\"Error building structured output: {e}\")\n            # Fallback to parsed JSON without validation\n            return json_data\n\n    async def json_response(self) -> Data:\n        \"\"\"Convert agent response to structured JSON Data output with schema validation.\"\"\"\n        # Always use structured chat agent for JSON response mode for better JSON formatting\n        try:\n            system_components = []\n\n            # 1. Agent Instructions (system_prompt)\n            agent_instructions = getattr(self, \"system_prompt\", \"\") or \"\"\n            if agent_instructions:\n                system_components.append(f\"{agent_instructions}\")\n\n            # 2. Format Instructions\n            format_instructions = getattr(self, \"format_instructions\", \"\") or \"\"\n            if format_instructions:\n                system_components.append(f\"Format instructions: {format_instructions}\")\n\n            # 3. Schema Information from BaseModel\n            if hasattr(self, \"output_schema\") and self.output_schema and len(self.output_schema) > 0:\n                try:\n                    processed_schema = self._preprocess_schema(self.output_schema)\n                    output_model = build_model_from_schema(processed_schema)\n                    schema_dict = output_model.model_json_schema()\n                    schema_info = (\n                        \"You are given some text that may include format instructions, \"\n                        \"explanations, or other content alongside a JSON schema.\\n\\n\"\n                        \"Your task:\\n\"\n                        \"- Extract only the JSON schema.\\n\"\n                        \"- Return it as valid JSON.\\n\"\n                        \"- Do not include format instructions, explanations, or extra text.\\n\\n\"\n                        \"Input:\\n\"\n                        f\"{json.dumps(schema_dict, indent=2)}\\n\\n\"\n                        \"Output (only JSON schema):\"\n                    )\n                    system_components.append(schema_info)\n                except (ValidationError, ValueError, TypeError, KeyError) as e:\n                    await logger.aerror(f\"Could not build schema for prompt: {e}\", exc_info=True)\n\n            # Combine all components\n            combined_instructions = \"\\n\\n\".join(system_components) if system_components else \"\"\n            llm_model, self.chat_history, self.tools = await self.get_agent_requirements()\n            self.set(\n                llm=llm_model,\n                tools=self.tools or [],\n                chat_history=self.chat_history,\n                input_value=self.input_value,\n                system_prompt=combined_instructions,\n            )\n\n            # Create and run structured chat agent\n            try:\n                structured_agent = self.create_agent_runnable()\n            except (NotImplementedError, ValueError, TypeError) as e:\n                await logger.aerror(f\"Error with structured chat agent: {e}\")\n                raise\n            try:\n                result = await self.run_agent(structured_agent)\n            except (ExceptionWithMessageError, ValueError, TypeError, RuntimeError) as e:\n                await logger.aerror(f\"Error with structured agent result: {e}\")\n                raise\n            # Extract content from structured agent result\n            if hasattr(result, \"content\"):\n                content = result.content\n            elif hasattr(result, \"text\"):\n                content = result.text\n            else:\n                content = str(result)\n\n        except (ExceptionWithMessageError, ValueError, TypeError, NotImplementedError, AttributeError) as e:\n            await logger.aerror(f\"Error with structured chat agent: {e}\")\n            # Fallback to regular agent\n            content_str = \"No content returned from agent\"\n            return Data(data={\"content\": content_str, \"error\": str(e)})\n\n        # Process with structured output validation\n        try:\n            structured_output = await self.build_structured_output_base(content)\n\n            # Handle different output formats\n            if isinstance(structured_output, list) and structured_output:\n                if len(structured_output) == 1:\n                    return Data(data=structured_output[0])\n                return Data(data={\"results\": structured_output})\n            if isinstance(structured_output, dict):\n                return Data(data=structured_output)\n            return Data(data={\"content\": content})\n\n        except (ValueError, TypeError) as e:\n            await logger.aerror(f\"Error in structured output processing: {e}\")\n            return Data(data={\"content\": content, \"error\": str(e)})\n\n    async def get_memory_data(self):\n        # TODO: This is a temporary fix to avoid message duplication. We should develop a function for this.\n        messages = (\n            await MemoryComponent(**self.get_base_args())\n            .set(session_id=self.graph.session_id, order=\"Ascending\", n_messages=self.n_messages)\n            .retrieve_messages()\n        )\n        return [\n            message for message in messages if getattr(message, \"id\", None) != getattr(self.input_value, \"id\", None)\n        ]\n\n    async def get_llm(self):\n        if not isinstance(self.agent_llm, str):\n            return self.agent_llm, None\n\n        try:\n            provider_info = MODEL_PROVIDERS_DICT.get(self.agent_llm)\n            if not provider_info:\n                msg = f\"Invalid model provider: {self.agent_llm}\"\n                raise ValueError(msg)\n\n            component_class = provider_info.get(\"component_class\")\n            display_name = component_class.display_name\n            inputs = provider_info.get(\"inputs\")\n            prefix = provider_info.get(\"prefix\", \"\")\n\n            return self._build_llm_model(component_class, inputs, prefix), display_name\n\n        except (AttributeError, ValueError, TypeError, RuntimeError) as e:\n            await logger.aerror(f\"Error building {self.agent_llm} language model: {e!s}\")\n            msg = f\"Failed to initialize language model: {e!s}\"\n            raise ValueError(msg) from e\n\n    def _build_llm_model(self, component, inputs, prefix=\"\"):\n        model_kwargs = {}\n        for input_ in inputs:\n            if hasattr(self, f\"{prefix}{input_.name}\"):\n                model_kwargs[input_.name] = getattr(self, f\"{prefix}{input_.name}\")\n        return component.set(**model_kwargs).build_model()\n\n    def set_component_params(self, component):\n        provider_info = MODEL_PROVIDERS_DICT.get(self.agent_llm)\n        if provider_info:\n            inputs = provider_info.get(\"inputs\")\n            prefix = provider_info.get(\"prefix\")\n            # Filter out json_mode and only use attributes that exist on this component\n            model_kwargs = {}\n            for input_ in inputs:\n                if hasattr(self, f\"{prefix}{input_.name}\"):\n                    model_kwargs[input_.name] = getattr(self, f\"{prefix}{input_.name}\")\n\n            return component.set(**model_kwargs)\n        return component\n\n    def delete_fields(self, build_config: dotdict, fields: dict | list[str]) -> None:\n        \"\"\"Delete specified fields from build_config.\"\"\"\n        for field in fields:\n            build_config.pop(field, None)\n\n    def update_input_types(self, build_config: dotdict) -> dotdict:\n        \"\"\"Update input types for all fields in build_config.\"\"\"\n        for key, value in build_config.items():\n            if isinstance(value, dict):\n                if value.get(\"input_types\") is None:\n                    build_config[key][\"input_types\"] = []\n            elif hasattr(value, \"input_types\") and value.input_types is None:\n                value.input_types = []\n        return build_config\n\n    async def update_build_config(\n        self, build_config: dotdict, field_value: str, field_name: str | None = None\n    ) -> dotdict:\n        # Iterate over all providers in the MODEL_PROVIDERS_DICT\n        # Existing logic for updating build_config\n        if field_name in (\"agent_llm\",):\n            build_config[\"agent_llm\"][\"value\"] = field_value\n            provider_info = MODEL_PROVIDERS_DICT.get(field_value)\n            if provider_info:\n                component_class = provider_info.get(\"component_class\")\n                if component_class and hasattr(component_class, \"update_build_config\"):\n                    # Call the component class's update_build_config method\n                    build_config = await update_component_build_config(\n                        component_class, build_config, field_value, \"model_name\"\n                    )\n\n            provider_configs: dict[str, tuple[dict, list[dict]]] = {\n                provider: (\n                    MODEL_PROVIDERS_DICT[provider][\"fields\"],\n                    [\n                        MODEL_PROVIDERS_DICT[other_provider][\"fields\"]\n                        for other_provider in MODEL_PROVIDERS_DICT\n                        if other_provider != provider\n                    ],\n                )\n                for provider in MODEL_PROVIDERS_DICT\n            }\n            if field_value in provider_configs:\n                fields_to_add, fields_to_delete = provider_configs[field_value]\n\n                # Delete fields from other providers\n                for fields in fields_to_delete:\n                    self.delete_fields(build_config, fields)\n\n                # Add provider-specific fields\n                if field_value == \"OpenAI\" and not any(field in build_config for field in fields_to_add):\n                    build_config.update(fields_to_add)\n                else:\n                    build_config.update(fields_to_add)\n                # Reset input types for agent_llm\n                build_config[\"agent_llm\"][\"input_types\"] = []\n            elif field_value == \"Custom\":\n                # Delete all provider fields\n                self.delete_fields(build_config, ALL_PROVIDER_FIELDS)\n                # Update with custom component\n                custom_component = DropdownInput(\n                    name=\"agent_llm\",\n                    display_name=\"Language Model\",\n                    options=[*sorted(MODEL_PROVIDERS), \"Custom\"],\n                    value=\"Custom\",\n                    real_time_refresh=True,\n                    input_types=[\"LanguageModel\"],\n                    options_metadata=[MODELS_METADATA[key] for key in sorted(MODELS_METADATA.keys())]\n                    + [{\"icon\": \"brain\"}],\n                )\n                build_config.update({\"agent_llm\": custom_component.to_dict()})\n            # Update input types for all fields\n            build_config = self.update_input_types(build_config)\n\n            # Validate required keys\n            default_keys = [\n                \"code\",\n                \"_type\",\n                \"agent_llm\",\n                \"tools\",\n                \"input_value\",\n                \"add_current_date_tool\",\n                \"system_prompt\",\n                \"agent_description\",\n                \"max_iterations\",\n                \"handle_parsing_errors\",\n                \"verbose\",\n            ]\n            missing_keys = [key for key in default_keys if key not in build_config]\n            if missing_keys:\n                msg = f\"Missing required keys in build_config: {missing_keys}\"\n                raise ValueError(msg)\n        if (\n            isinstance(self.agent_llm, str)\n            and self.agent_llm in MODEL_PROVIDERS_DICT\n            and field_name in MODEL_DYNAMIC_UPDATE_FIELDS\n        ):\n            provider_info = MODEL_PROVIDERS_DICT.get(self.agent_llm)\n            if provider_info:\n                component_class = provider_info.get(\"component_class\")\n                component_class = self.set_component_params(component_class)\n                prefix = provider_info.get(\"prefix\")\n                if component_class and hasattr(component_class, \"update_build_config\"):\n                    # Call each component class's update_build_config method\n                    # remove the prefix from the field_name\n                    if isinstance(field_name, str) and isinstance(prefix, str):\n                        field_name = field_name.replace(prefix, \"\")\n                    build_config = await update_component_build_config(\n                        component_class, build_config, field_value, \"model_name\"\n                    )\n        return dotdict({k: v.to_dict() if hasattr(v, \"to_dict\") else v for k, v in build_config.items()})\n\n    async def _get_tools(self) -> list[Tool]:\n        component_toolkit = _get_component_toolkit()\n        tools_names = self._build_tools_names()\n        agent_description = self.get_tool_description()\n        # TODO: Agent Description Depreciated Feature to be removed\n        description = f\"{agent_description}{tools_names}\"\n        tools = component_toolkit(component=self).get_tools(\n            tool_name=\"Call_Agent\", tool_description=description, callbacks=self.get_langchain_callbacks()\n        )\n        if hasattr(self, \"tools_metadata\"):\n            tools = component_toolkit(component=self, metadata=self.tools_metadata).update_tools_metadata(tools=tools)\n        return tools\n"
+                "value": "import json\nimport re\n\nfrom langchain_core.tools import StructuredTool\nfrom pydantic import ValidationError\n\nfrom langflow.base.agents.agent import LCToolsAgentComponent\nfrom langflow.base.agents.events import ExceptionWithMessageError\nfrom langflow.base.models.model_input_constants import (\n    ALL_PROVIDER_FIELDS,\n    MODEL_DYNAMIC_UPDATE_FIELDS,\n    MODEL_PROVIDERS,\n    MODEL_PROVIDERS_DICT,\n    MODELS_METADATA,\n)\nfrom langflow.base.models.model_utils import get_model_name\nfrom langflow.components.helpers.current_date import CurrentDateComponent\nfrom langflow.components.helpers.memory import MemoryComponent\nfrom langflow.components.langchain_utilities.tool_calling import ToolCallingAgentComponent\nfrom langflow.custom.custom_component.component import _get_component_toolkit\nfrom langflow.custom.utils import update_component_build_config\nfrom langflow.field_typing import Tool\nfrom langflow.helpers.base_model import build_model_from_schema\nfrom langflow.io import BoolInput, DropdownInput, IntInput, MultilineInput, Output, TableInput\nfrom langflow.logging import logger\nfrom langflow.schema.data import Data\nfrom langflow.schema.dotdict import dotdict\nfrom langflow.schema.message import Message\nfrom langflow.schema.table import EditMode\n\n\ndef set_advanced_true(component_input):\n    component_input.advanced = True\n    return component_input\n\n\nMODEL_PROVIDERS_LIST = [\"Anthropic\", \"Google Generative AI\", \"Groq\", \"OpenAI\"]\n\n\nclass AgentComponent(ToolCallingAgentComponent):\n    display_name: str = \"Agent\"\n    description: str = \"Define the agent's instructions, then enter a task to complete using tools.\"\n    documentation: str = \"https://docs.langflow.org/agents\"\n    icon = \"bot\"\n    beta = False\n    name = \"Agent\"\n\n    memory_inputs = [set_advanced_true(component_input) for component_input in MemoryComponent().inputs]\n\n    # Filter out json_mode from OpenAI inputs since we handle structured output differently\n    openai_inputs_filtered = [\n        input_field\n        for input_field in MODEL_PROVIDERS_DICT[\"OpenAI\"][\"inputs\"]\n        if not (hasattr(input_field, \"name\") and input_field.name == \"json_mode\")\n    ]\n\n    inputs = [\n        DropdownInput(\n            name=\"agent_llm\",\n            display_name=\"Model Provider\",\n            info=\"The provider of the language model that the agent will use to generate responses.\",\n            options=[*MODEL_PROVIDERS_LIST, \"Custom\"],\n            value=\"OpenAI\",\n            real_time_refresh=True,\n            input_types=[],\n            options_metadata=[MODELS_METADATA[key] for key in MODEL_PROVIDERS_LIST] + [{\"icon\": \"brain\"}],\n        ),\n        *openai_inputs_filtered,\n        MultilineInput(\n            name=\"system_prompt\",\n            display_name=\"Agent Instructions\",\n            info=\"System Prompt: Initial instructions and context provided to guide the agent's behavior.\",\n            value=\"You are a helpful assistant that can use tools to answer questions and perform tasks.\",\n            advanced=False,\n        ),\n        IntInput(\n            name=\"n_messages\",\n            display_name=\"Number of Chat History Messages\",\n            value=100,\n            info=\"Number of chat history messages to retrieve.\",\n            advanced=True,\n            show=True,\n        ),\n        MultilineInput(\n            name=\"format_instructions\",\n            display_name=\"Output Format Instructions\",\n            info=\"Generic Template for structured output formatting. Valid only with Structured response.\",\n            value=(\n                \"You are an AI that extracts structured JSON objects from unstructured text. \"\n                \"Use a predefined schema with expected types (str, int, float, bool, dict). \"\n                \"Extract ALL relevant instances that match the schema - if multiple patterns exist, capture them all. \"\n                \"Fill missing or ambiguous values with defaults: null for missing values. \"\n                \"Remove exact duplicates but keep variations that have different field values. \"\n                \"Always return valid JSON in the expected format, never throw errors. \"\n                \"If multiple objects can be extracted, return them all in the structured format.\"\n            ),\n            advanced=True,\n        ),\n        TableInput(\n            name=\"output_schema\",\n            display_name=\"Output Schema\",\n            info=(\n                \"Schema Validation: Define the structure and data types for structured output. \"\n                \"No validation if no output schema.\"\n            ),\n            advanced=True,\n            required=False,\n            value=[],\n            table_schema=[\n                {\n                    \"name\": \"name\",\n                    \"display_name\": \"Name\",\n                    \"type\": \"str\",\n                    \"description\": \"Specify the name of the output field.\",\n                    \"default\": \"field\",\n                    \"edit_mode\": EditMode.INLINE,\n                },\n                {\n                    \"name\": \"description\",\n                    \"display_name\": \"Description\",\n                    \"type\": \"str\",\n                    \"description\": \"Describe the purpose of the output field.\",\n                    \"default\": \"description of field\",\n                    \"edit_mode\": EditMode.POPOVER,\n                },\n                {\n                    \"name\": \"type\",\n                    \"display_name\": \"Type\",\n                    \"type\": \"str\",\n                    \"edit_mode\": EditMode.INLINE,\n                    \"description\": (\"Indicate the data type of the output field (e.g., str, int, float, bool, dict).\"),\n                    \"options\": [\"str\", \"int\", \"float\", \"bool\", \"dict\"],\n                    \"default\": \"str\",\n                },\n                {\n                    \"name\": \"multiple\",\n                    \"display_name\": \"As List\",\n                    \"type\": \"boolean\",\n                    \"description\": \"Set to True if this output field should be a list of the specified type.\",\n                    \"default\": \"False\",\n                    \"edit_mode\": EditMode.INLINE,\n                },\n            ],\n        ),\n        *LCToolsAgentComponent._base_inputs,\n        # removed memory inputs from agent component\n        # *memory_inputs,\n        BoolInput(\n            name=\"add_current_date_tool\",\n            display_name=\"Current Date\",\n            advanced=True,\n            info=\"If true, will add a tool to the agent that returns the current date.\",\n            value=True,\n        ),\n    ]\n    outputs = [\n        Output(name=\"response\", display_name=\"Response\", method=\"message_response\"),\n        Output(name=\"structured_response\", display_name=\"Structured Response\", method=\"json_response\", tool_mode=False),\n    ]\n\n    async def get_agent_requirements(self):\n        \"\"\"Get the agent requirements for the agent.\"\"\"\n        llm_model, display_name = await self.get_llm()\n        if llm_model is None:\n            msg = \"No language model selected. Please choose a model to proceed.\"\n            raise ValueError(msg)\n        self.model_name = get_model_name(llm_model, display_name=display_name)\n\n        # Get memory data\n        self.chat_history = await self.get_memory_data()\n        if isinstance(self.chat_history, Message):\n            self.chat_history = [self.chat_history]\n\n        # Add current date tool if enabled\n        if self.add_current_date_tool:\n            if not isinstance(self.tools, list):  # type: ignore[has-type]\n                self.tools = []\n            current_date_tool = (await CurrentDateComponent(**self.get_base_args()).to_toolkit()).pop(0)\n            if not isinstance(current_date_tool, StructuredTool):\n                msg = \"CurrentDateComponent must be converted to a StructuredTool\"\n                raise TypeError(msg)\n            self.tools.append(current_date_tool)\n        return llm_model, self.chat_history, self.tools\n\n    async def message_response(self) -> Message:\n        try:\n            llm_model, self.chat_history, self.tools = await self.get_agent_requirements()\n            # Set up and run agent\n            self.set(\n                llm=llm_model,\n                tools=self.tools or [],\n                chat_history=self.chat_history,\n                input_value=self.input_value,\n                system_prompt=self.system_prompt,\n            )\n            agent = self.create_agent_runnable()\n            result = await self.run_agent(agent)\n\n            # Store result for potential JSON output\n            self._agent_result = result\n\n        except (ValueError, TypeError, KeyError) as e:\n            await logger.aerror(f\"{type(e).__name__}: {e!s}\")\n            raise\n        except ExceptionWithMessageError as e:\n            await logger.aerror(f\"ExceptionWithMessageError occurred: {e}\")\n            raise\n        # Avoid catching blind Exception; let truly unexpected exceptions propagate\n        except Exception as e:\n            await logger.aerror(f\"Unexpected error: {e!s}\")\n            raise\n        else:\n            return result\n\n    def _preprocess_schema(self, schema):\n        \"\"\"Preprocess schema to ensure correct data types for build_model_from_schema.\"\"\"\n        processed_schema = []\n        for field in schema:\n            processed_field = {\n                \"name\": str(field.get(\"name\", \"field\")),\n                \"type\": str(field.get(\"type\", \"str\")),\n                \"description\": str(field.get(\"description\", \"\")),\n                \"multiple\": field.get(\"multiple\", False),\n            }\n            # Ensure multiple is handled correctly\n            if isinstance(processed_field[\"multiple\"], str):\n                processed_field[\"multiple\"] = processed_field[\"multiple\"].lower() in [\"true\", \"1\", \"t\", \"y\", \"yes\"]\n            processed_schema.append(processed_field)\n        return processed_schema\n\n    async def build_structured_output_base(self, content: str):\n        \"\"\"Build structured output with optional BaseModel validation.\"\"\"\n        json_pattern = r\"\\{.*\\}\"\n        schema_error_msg = \"Try setting an output schema\"\n\n        # Try to parse content as JSON first\n        json_data = None\n        try:\n            json_data = json.loads(content)\n        except json.JSONDecodeError:\n            json_match = re.search(json_pattern, content, re.DOTALL)\n            if json_match:\n                try:\n                    json_data = json.loads(json_match.group())\n                except json.JSONDecodeError:\n                    return {\"content\": content, \"error\": schema_error_msg}\n            else:\n                return {\"content\": content, \"error\": schema_error_msg}\n\n        # If no output schema provided, return parsed JSON without validation\n        if not hasattr(self, \"output_schema\") or not self.output_schema or len(self.output_schema) == 0:\n            return json_data\n\n        # Use BaseModel validation with schema\n        try:\n            processed_schema = self._preprocess_schema(self.output_schema)\n            output_model = build_model_from_schema(processed_schema)\n\n            # Validate against the schema\n            if isinstance(json_data, list):\n                # Multiple objects\n                validated_objects = []\n                for item in json_data:\n                    try:\n                        validated_obj = output_model.model_validate(item)\n                        validated_objects.append(validated_obj.model_dump())\n                    except ValidationError as e:\n                        await logger.aerror(f\"Validation error for item: {e}\")\n                        # Include invalid items with error info\n                        validated_objects.append({\"data\": item, \"validation_error\": str(e)})\n                return validated_objects\n\n            # Single object\n            try:\n                validated_obj = output_model.model_validate(json_data)\n                return [validated_obj.model_dump()]  # Return as list for consistency\n            except ValidationError as e:\n                await logger.aerror(f\"Validation error: {e}\")\n                return [{\"data\": json_data, \"validation_error\": str(e)}]\n\n        except (TypeError, ValueError) as e:\n            await logger.aerror(f\"Error building structured output: {e}\")\n            # Fallback to parsed JSON without validation\n            return json_data\n\n    async def json_response(self) -> Data:\n        \"\"\"Convert agent response to structured JSON Data output with schema validation.\"\"\"\n        # Always use structured chat agent for JSON response mode for better JSON formatting\n        try:\n            system_components = []\n\n            # 1. Agent Instructions (system_prompt)\n            agent_instructions = getattr(self, \"system_prompt\", \"\") or \"\"\n            if agent_instructions:\n                system_components.append(f\"{agent_instructions}\")\n\n            # 2. Format Instructions\n            format_instructions = getattr(self, \"format_instructions\", \"\") or \"\"\n            if format_instructions:\n                system_components.append(f\"Format instructions: {format_instructions}\")\n\n            # 3. Schema Information from BaseModel\n            if hasattr(self, \"output_schema\") and self.output_schema and len(self.output_schema) > 0:\n                try:\n                    processed_schema = self._preprocess_schema(self.output_schema)\n                    output_model = build_model_from_schema(processed_schema)\n                    schema_dict = output_model.model_json_schema()\n                    schema_info = (\n                        \"You are given some text that may include format instructions, \"\n                        \"explanations, or other content alongside a JSON schema.\\n\\n\"\n                        \"Your task:\\n\"\n                        \"- Extract only the JSON schema.\\n\"\n                        \"- Return it as valid JSON.\\n\"\n                        \"- Do not include format instructions, explanations, or extra text.\\n\\n\"\n                        \"Input:\\n\"\n                        f\"{json.dumps(schema_dict, indent=2)}\\n\\n\"\n                        \"Output (only JSON schema):\"\n                    )\n                    system_components.append(schema_info)\n                except (ValidationError, ValueError, TypeError, KeyError) as e:\n                    await logger.aerror(f\"Could not build schema for prompt: {e}\", exc_info=True)\n\n            # Combine all components\n            combined_instructions = \"\\n\\n\".join(system_components) if system_components else \"\"\n            llm_model, self.chat_history, self.tools = await self.get_agent_requirements()\n            self.set(\n                llm=llm_model,\n                tools=self.tools or [],\n                chat_history=self.chat_history,\n                input_value=self.input_value,\n                system_prompt=combined_instructions,\n            )\n\n            # Create and run structured chat agent\n            try:\n                structured_agent = self.create_agent_runnable()\n            except (NotImplementedError, ValueError, TypeError) as e:\n                await logger.aerror(f\"Error with structured chat agent: {e}\")\n                raise\n            try:\n                result = await self.run_agent(structured_agent)\n            except (ExceptionWithMessageError, ValueError, TypeError, RuntimeError) as e:\n                await logger.aerror(f\"Error with structured agent result: {e}\")\n                raise\n            # Extract content from structured agent result\n            if hasattr(result, \"content\"):\n                content = result.content\n            elif hasattr(result, \"text\"):\n                content = result.text\n            else:\n                content = str(result)\n\n        except (ExceptionWithMessageError, ValueError, TypeError, NotImplementedError, AttributeError) as e:\n            await logger.aerror(f\"Error with structured chat agent: {e}\")\n            # Fallback to regular agent\n            content_str = \"No content returned from agent\"\n            return Data(data={\"content\": content_str, \"error\": str(e)})\n\n        # Process with structured output validation\n        try:\n            structured_output = await self.build_structured_output_base(content)\n\n            # Handle different output formats\n            if isinstance(structured_output, list) and structured_output:\n                if len(structured_output) == 1:\n                    return Data(data=structured_output[0])\n                return Data(data={\"results\": structured_output})\n            if isinstance(structured_output, dict):\n                return Data(data=structured_output)\n            return Data(data={\"content\": content})\n\n        except (ValueError, TypeError) as e:\n            await logger.aerror(f\"Error in structured output processing: {e}\")\n            return Data(data={\"content\": content, \"error\": str(e)})\n\n    async def get_memory_data(self):\n        # TODO: This is a temporary fix to avoid message duplication. We should develop a function for this.\n        messages = (\n            await MemoryComponent(**self.get_base_args())\n            .set(session_id=self.graph.session_id, order=\"Ascending\", n_messages=self.n_messages)\n            .retrieve_messages()\n        )\n        return [\n            message for message in messages if getattr(message, \"id\", None) != getattr(self.input_value, \"id\", None)\n        ]\n\n    async def get_llm(self):\n        if not isinstance(self.agent_llm, str):\n            return self.agent_llm, None\n\n        try:\n            provider_info = MODEL_PROVIDERS_DICT.get(self.agent_llm)\n            if not provider_info:\n                msg = f\"Invalid model provider: {self.agent_llm}\"\n                raise ValueError(msg)\n\n            component_class = provider_info.get(\"component_class\")\n            display_name = component_class.display_name\n            inputs = provider_info.get(\"inputs\")\n            prefix = provider_info.get(\"prefix\", \"\")\n\n            return self._build_llm_model(component_class, inputs, prefix), display_name\n\n        except (AttributeError, ValueError, TypeError, RuntimeError) as e:\n            await logger.aerror(f\"Error building {self.agent_llm} language model: {e!s}\")\n            msg = f\"Failed to initialize language model: {e!s}\"\n            raise ValueError(msg) from e\n\n    def _build_llm_model(self, component, inputs, prefix=\"\"):\n        model_kwargs = {}\n        for input_ in inputs:\n            if hasattr(self, f\"{prefix}{input_.name}\"):\n                model_kwargs[input_.name] = getattr(self, f\"{prefix}{input_.name}\")\n        return component.set(**model_kwargs).build_model()\n\n    def set_component_params(self, component):\n        provider_info = MODEL_PROVIDERS_DICT.get(self.agent_llm)\n        if provider_info:\n            inputs = provider_info.get(\"inputs\")\n            prefix = provider_info.get(\"prefix\")\n            # Filter out json_mode and only use attributes that exist on this component\n            model_kwargs = {}\n            for input_ in inputs:\n                if hasattr(self, f\"{prefix}{input_.name}\"):\n                    model_kwargs[input_.name] = getattr(self, f\"{prefix}{input_.name}\")\n\n            return component.set(**model_kwargs)\n        return component\n\n    def delete_fields(self, build_config: dotdict, fields: dict | list[str]) -> None:\n        \"\"\"Delete specified fields from build_config.\"\"\"\n        for field in fields:\n            build_config.pop(field, None)\n\n    def update_input_types(self, build_config: dotdict) -> dotdict:\n        \"\"\"Update input types for all fields in build_config.\"\"\"\n        for key, value in build_config.items():\n            if isinstance(value, dict):\n                if value.get(\"input_types\") is None:\n                    build_config[key][\"input_types\"] = []\n            elif hasattr(value, \"input_types\") and value.input_types is None:\n                value.input_types = []\n        return build_config\n\n    async def update_build_config(\n        self, build_config: dotdict, field_value: str, field_name: str | None = None\n    ) -> dotdict:\n        # Iterate over all providers in the MODEL_PROVIDERS_DICT\n        # Existing logic for updating build_config\n        if field_name in (\"agent_llm\",):\n            build_config[\"agent_llm\"][\"value\"] = field_value\n            provider_info = MODEL_PROVIDERS_DICT.get(field_value)\n            if provider_info:\n                component_class = provider_info.get(\"component_class\")\n                if component_class and hasattr(component_class, \"update_build_config\"):\n                    # Call the component class's update_build_config method\n                    build_config = await update_component_build_config(\n                        component_class, build_config, field_value, \"model_name\"\n                    )\n\n            provider_configs: dict[str, tuple[dict, list[dict]]] = {\n                provider: (\n                    MODEL_PROVIDERS_DICT[provider][\"fields\"],\n                    [\n                        MODEL_PROVIDERS_DICT[other_provider][\"fields\"]\n                        for other_provider in MODEL_PROVIDERS_DICT\n                        if other_provider != provider\n                    ],\n                )\n                for provider in MODEL_PROVIDERS_DICT\n            }\n            if field_value in provider_configs:\n                fields_to_add, fields_to_delete = provider_configs[field_value]\n\n                # Delete fields from other providers\n                for fields in fields_to_delete:\n                    self.delete_fields(build_config, fields)\n\n                # Add provider-specific fields\n                if field_value == \"OpenAI\" and not any(field in build_config for field in fields_to_add):\n                    build_config.update(fields_to_add)\n                else:\n                    build_config.update(fields_to_add)\n                # Reset input types for agent_llm\n                build_config[\"agent_llm\"][\"input_types\"] = []\n                build_config[\"agent_llm\"][\"display_name\"] = \"Model Provider\"\n            elif field_value == \"Custom\":\n                # Delete all provider fields\n                self.delete_fields(build_config, ALL_PROVIDER_FIELDS)\n                # Update with custom component\n                custom_component = DropdownInput(\n                    name=\"agent_llm\",\n                    display_name=\"Language Model\",\n                    options=[*sorted(MODEL_PROVIDERS), \"Custom\"],\n                    value=\"Custom\",\n                    real_time_refresh=True,\n                    input_types=[\"LanguageModel\"],\n                    options_metadata=[MODELS_METADATA[key] for key in sorted(MODELS_METADATA.keys())]\n                    + [{\"icon\": \"brain\"}],\n                )\n                build_config.update({\"agent_llm\": custom_component.to_dict()})\n            # Update input types for all fields\n            build_config = self.update_input_types(build_config)\n\n            # Validate required keys\n            default_keys = [\n                \"code\",\n                \"_type\",\n                \"agent_llm\",\n                \"tools\",\n                \"input_value\",\n                \"add_current_date_tool\",\n                \"system_prompt\",\n                \"agent_description\",\n                \"max_iterations\",\n                \"handle_parsing_errors\",\n                \"verbose\",\n            ]\n            missing_keys = [key for key in default_keys if key not in build_config]\n            if missing_keys:\n                msg = f\"Missing required keys in build_config: {missing_keys}\"\n                raise ValueError(msg)\n        if (\n            isinstance(self.agent_llm, str)\n            and self.agent_llm in MODEL_PROVIDERS_DICT\n            and field_name in MODEL_DYNAMIC_UPDATE_FIELDS\n        ):\n            provider_info = MODEL_PROVIDERS_DICT.get(self.agent_llm)\n            if provider_info:\n                component_class = provider_info.get(\"component_class\")\n                component_class = self.set_component_params(component_class)\n                prefix = provider_info.get(\"prefix\")\n                if component_class and hasattr(component_class, \"update_build_config\"):\n                    # Call each component class's update_build_config method\n                    # remove the prefix from the field_name\n                    if isinstance(field_name, str) and isinstance(prefix, str):\n                        field_name = field_name.replace(prefix, \"\")\n                    build_config = await update_component_build_config(\n                        component_class, build_config, field_value, \"model_name\"\n                    )\n        return dotdict({k: v.to_dict() if hasattr(v, \"to_dict\") else v for k, v in build_config.items()})\n\n    async def _get_tools(self) -> list[Tool]:\n        component_toolkit = _get_component_toolkit()\n        tools_names = self._build_tools_names()\n        agent_description = self.get_tool_description()\n        # TODO: Agent Description Depreciated Feature to be removed\n        description = f\"{agent_description}{tools_names}\"\n        tools = component_toolkit(component=self).get_tools(\n            tool_name=\"Call_Agent\", tool_description=description, callbacks=self.get_langchain_callbacks()\n        )\n        if hasattr(self, \"tools_metadata\"):\n            tools = component_toolkit(component=self, metadata=self.tools_metadata).update_tools_metadata(tools=tools)\n        return tools\n"
               },
               "handle_parsing_errors": {
                 "_input_type": "BoolInput",