langflow-base-nightly 0.5.0.dev31__py3-none-any.whl → 0.5.0.dev33__py3-none-any.whl

langflow/__main__.py

@@ -15,7 +15,9 @@ import click
 import httpx
 import typer
 from dotenv import load_dotenv
+from fastapi import HTTPException
 from httpx import HTTPError
+from jose import JWTError
 from multiprocess import cpu_count
 from multiprocess.context import Process
 from packaging import version as pkg_version
@@ -29,9 +31,9 @@ from langflow.cli.progress import create_langflow_progress
 from langflow.initial_setup.setup import get_or_create_default_folder
 from langflow.logging.logger import configure, logger
 from langflow.main import setup_app
-from langflow.services.database.utils import session_getter
+from langflow.services.auth.utils import check_key, get_current_user_by_jwt
 from langflow.services.deps import get_db_service, get_settings_service, session_scope
-from langflow.services.settings.constants import DEFAULT_SUPERUSER
+from langflow.services.settings.constants import DEFAULT_SUPERUSER, DEFAULT_SUPERUSER_PASSWORD
 from langflow.services.utils import initialize_services
 from langflow.utils.version import fetch_latest_version, get_version_info
 from langflow.utils.version import is_pre_release as langflow_is_pre_release
@@ -632,41 +634,138 @@ def print_banner(host: str, port: int, protocol: str) -> None:
 
 @app.command()
 def superuser(
-    username: str = typer.Option(..., prompt=True, help="Username for the superuser."),
-    password: str = typer.Option(..., prompt=True, hide_input=True, help="Password for the superuser."),
+    username: str = typer.Option(
+        None, help="Username for the superuser. Defaults to 'langflow' when AUTO_LOGIN is enabled."
+    ),
+    password: str = typer.Option(
+        None, help="Password for the superuser. Defaults to 'langflow' when AUTO_LOGIN is enabled."
+    ),
     log_level: str = typer.Option("error", help="Logging level.", envvar="LANGFLOW_LOG_LEVEL"),
+    auth_token: str = typer.Option(
+        None, help="Authentication token of existing superuser.", envvar="LANGFLOW_SUPERUSER_TOKEN"
+    ),
 ) -> None:
-    """Create a superuser."""
+    """Create a superuser.
+
+    When AUTO_LOGIN is enabled, uses default credentials.
+    In production mode, requires authentication.
+    """
     configure(log_level=log_level)
-    db_service = get_db_service()
 
-    async def _create_superuser():
-        await initialize_services()
-        async with session_getter(db_service) as session:
-            from langflow.services.auth.utils import create_super_user
-
-            if await create_super_user(db=session, username=username, password=password):
-                # Verify that the superuser was created
-                from langflow.services.database.models.user.model import User
-
-                stmt = select(User).where(User.username == username)
-                user: User = (await session.exec(stmt)).first()
-                if user is None or not user.is_superuser:
-                    typer.echo("Superuser creation failed.")
-                    return
-                # Now create the first folder for the user
-                result = await get_or_create_default_folder(session, user.id)
-                if result:
-                    typer.echo("Default folder created successfully.")
-                else:
-                    msg = "Could not create default folder."
-                    raise RuntimeError(msg)
-                typer.echo("Superuser created successfully.")
+    asyncio.run(_create_superuser(username, password, auth_token))
 
-            else:
+
+async def _create_superuser(username: str, password: str, auth_token: str | None):
+    """Create a superuser."""
+    await initialize_services()
+
+    settings_service = get_settings_service()
+    # Check if superuser creation via CLI is enabled
+    if not settings_service.auth_settings.ENABLE_SUPERUSER_CLI:
+        typer.echo("Error: Superuser creation via CLI is disabled.")
+        typer.echo("Set LANGFLOW_ENABLE_SUPERUSER_CLI=true to enable this feature.")
+        raise typer.Exit(1)
+
+    if settings_service.auth_settings.AUTO_LOGIN:
+        # Force default credentials for AUTO_LOGIN mode
+        username = DEFAULT_SUPERUSER
+        password = DEFAULT_SUPERUSER_PASSWORD
+    else:
+        # Production mode - prompt for credentials if not provided
+        if not username:
+            username = typer.prompt("Username")
+        if not password:
+            password = typer.prompt("Password", hide_input=True)
+
+    from langflow.services.database.models.user.crud import get_all_superusers
+
+    existing_superusers = []
+    async with session_scope() as session:
+        # Note that the default superuser is created by the initialize_services() function,
+        # but leaving this check here in case we change that behavior
+        existing_superusers = await get_all_superusers(session)
+    is_first_setup = len(existing_superusers) == 0
+
+    # If AUTO_LOGIN is true, only allow default superuser creation
+    if settings_service.auth_settings.AUTO_LOGIN:
+        if not is_first_setup:
+            typer.echo("Error: Cannot create additional superusers when AUTO_LOGIN is enabled.")
+            typer.echo("AUTO_LOGIN mode is for development with only the default superuser.")
+            typer.echo("To create additional superusers:")
+            typer.echo("1. Set LANGFLOW_AUTO_LOGIN=false")
+            typer.echo("2. Run this command again with --auth-token")
+            raise typer.Exit(1)
+
+        typer.echo(f"AUTO_LOGIN enabled. Creating default superuser '{username}'...")
+        typer.echo(f"Note: Default credentials are {DEFAULT_SUPERUSER}/{DEFAULT_SUPERUSER_PASSWORD}")
+    # AUTO_LOGIN is false - production mode
+    elif is_first_setup:
+        typer.echo("No superusers found. Creating first superuser...")
+    else:
+        # Authentication is required in production mode
+        if not auth_token:
+            typer.echo("Error: Creating a superuser requires authentication.")
+            typer.echo("Please provide --auth-token with a valid superuser API key or JWT token.")
+            typer.echo("To get a token, use: `uv run langflow api_key`")
+            raise typer.Exit(1)
+
+        # Validate the auth token
+        try:
+            auth_user = None
+            async with session_scope() as session:
+                # Try JWT first
+                user = None
+                try:
+                    user = await get_current_user_by_jwt(auth_token, session)
+                except (JWTError, HTTPException):
+                    # Try API key
+                    api_key_result = await check_key(session, auth_token)
+                    if api_key_result and hasattr(api_key_result, "is_superuser"):
+                        user = api_key_result
+                auth_user = user
+
+            if not auth_user or not auth_user.is_superuser:
+                typer.echo(
+                    "Error: Invalid token or insufficient privileges. Only superusers can create other superusers."
+                )
+                raise typer.Exit(1)
+        except typer.Exit:
+            raise  # Re-raise typer.Exit without wrapping
+        except Exception as e:  # noqa: BLE001
+            typer.echo(f"Error: Authentication failed - {e!s}")
+            raise typer.Exit(1) from None
+
+    # Auth complete, create the superuser
+    async with session_scope() as session:
+        from langflow.services.auth.utils import create_super_user
+
+        if await create_super_user(db=session, username=username, password=password):
+            # Verify that the superuser was created
+            from langflow.services.database.models.user.model import User
+
+            stmt = select(User).where(User.username == username)
+            created_user: User = (await session.exec(stmt)).first()
+            if created_user is None or not created_user.is_superuser:
                 typer.echo("Superuser creation failed.")
+                return
+            # Now create the first folder for the user
+            result = await get_or_create_default_folder(session, created_user.id)
+            if result:
+                typer.echo("Default folder created successfully.")
+            else:
+                msg = "Could not create default folder."
+                raise RuntimeError(msg)
 
-    asyncio.run(_create_superuser())
+            # Log the superuser creation for audit purposes
+            logger.warning(
+                f"SECURITY AUDIT: New superuser '{username}' created via CLI command"
+                + (" by authenticated user" if auth_token else " (first-time setup)")
+            )
+            typer.echo("Superuser created successfully.")
+
+        else:
+            logger.error(f"SECURITY AUDIT: Failed attempt to create superuser '{username}' via CLI")
+            typer.echo("Superuser creation failed.")
 
 
 # command to copy the langflow database from the cache to the current directory
@@ -749,6 +848,7 @@ def api_key(
         settings_service = get_settings_service()
         auth_settings = settings_service.auth_settings
         if not auth_settings.AUTO_LOGIN:
+            # TODO: Allow non-auto-login users to create API keys via CLI
             typer.echo("Auto login is disabled. API keys cannot be created through the CLI.")
             return None
 

langflow/components/data/kb_retrieval.py

@@ -66,7 +66,7 @@ class KBRetrievalComponent(Component):
             display_name="Include Metadata",
             info="Whether to include all metadata and embeddings in the output. If false, only content is returned.",
             value=True,
-            advanced=True,
+            advanced=False,
         ),
     ]
 

langflow/components/processing/save_file.py

@@ -53,7 +53,7 @@ class SaveToFileComponent(Component):
         ),
     ]
 
-    outputs = [Output(display_name="File Path", name="result", method="save_to_file")]
+    outputs = [Output(display_name="File Path", name="message", method="save_to_file")]
 
     async def save_to_file(self) -> Message:
         """Save the input to a file and upload it, returning a confirmation message."""

langflow/initial_setup/starter_projects/Knowledge Retrieval.json

@@ -2,11 +2,11 @@
   "data": {
     "edges": [
       {
-        "className": "",
+        "animated": false,
         "data": {
           "sourceHandle": {
             "dataType": "TextInput",
-            "id": "TextInput-Z3rM3",
+            "id": "TextInput-WyJxO",
             "name": "text",
             "output_types": [
               "Message"
@@ -14,25 +14,26 @@
           },
           "targetHandle": {
             "fieldName": "search_query",
-            "id": "KBRetrieval-tGoBR",
+            "id": "KBRetrieval-zz3I0",
             "inputTypes": [
               "Message"
             ],
             "type": "str"
           }
         },
-        "id": "xy-edge__TextInput-Z3rM3{œdataTypeœ:œTextInputœ,œidœ:œTextInput-Z3rM3œ,œnameœ:œtextœ,œoutput_typesœ:[œMessageœ]}-KBRetrieval-tGoBR{œfieldNameœ:œsearch_queryœ,œidœ:œKBRetrieval-tGoBRœ,œinputTypesœ:[œMessageœ],œtypeœ:œstrœ}",
-        "source": "TextInput-Z3rM3",
-        "sourceHandle": "{œdataTypeœ: œTextInputœ, œidœ: œTextInput-Z3rM3œ, œnameœ: œtextœ, œoutput_typesœ: [œMessageœ]}",
-        "target": "KBRetrieval-tGoBR",
-        "targetHandle": "{œfieldNameœ: œsearch_queryœ, œidœ: œKBRetrieval-tGoBRœ, œinputTypesœ: [œMessageœ], œtypeœ: œstrœ}"
+        "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}"
       },
       {
-        "className": "",
+        "animated": false,
         "data": {
           "sourceHandle": {
             "dataType": "KBRetrieval",
-            "id": "KBRetrieval-tGoBR",
+            "id": "KBRetrieval-zz3I0",
             "name": "chroma_kb_data",
             "output_types": [
               "DataFrame"
@@ -40,7 +41,7 @@
           },
           "targetHandle": {
             "fieldName": "input_value",
-            "id": "ChatOutput-tixOe",
+            "id": "ChatOutput-N7nxz",
             "inputTypes": [
               "Data",
               "DataFrame",
@@ -49,17 +50,18 @@
             "type": "other"
           }
         },
-        "id": "xy-edge__KBRetrieval-tGoBR{œdataTypeœ:œKBRetrievalœ,œidœ:œKBRetrieval-tGoBRœ,œnameœ:œchroma_kb_dataœ,œoutput_typesœ:[œDataFrameœ]}-ChatOutput-tixOe{œfieldNameœ:œinput_valueœ,œidœ:œChatOutput-tixOeœ,œinputTypesœ:[œDataœ,œDataFrameœ,œMessageœ],œtypeœ:œotherœ}",
-        "source": "KBRetrieval-tGoBR",
-        "sourceHandle": "{œdataTypeœ: œKBRetrievalœ, œidœ: œKBRetrieval-tGoBRœ, œnameœ: œchroma_kb_dataœ, œoutput_typesœ: [œDataFrameœ]}",
-        "target": "ChatOutput-tixOe",
-        "targetHandle": "{œfieldNameœ: œinput_valueœ, œidœ: œChatOutput-tixOeœ, œinputTypesœ: [œDataœ, œDataFrameœ, œMessageœ], œtypeœ: œotherœ}"
+        "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}"
       }
     ],
     "nodes": [
       {
         "data": {
-          "id": "note-YyBfz",
+          "id": "note-f86G8",
           "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": "",
@@ -70,7 +72,7 @@
         },
         "dragging": false,
         "height": 384,
-        "id": "note-YyBfz",
+        "id": "note-f86G8",
         "measured": {
           "height": 384,
           "width": 371
@@ -86,7 +88,7 @@
       },
       {
         "data": {
-          "id": "TextInput-Z3rM3",
+          "id": "TextInput-WyJxO",
           "node": {
             "base_classes": [
               "Message"
@@ -180,7 +182,7 @@
           "type": "TextInput"
         },
         "dragging": false,
-        "id": "TextInput-Z3rM3",
+        "id": "TextInput-WyJxO",
         "measured": {
           "height": 204,
           "width": 320
@@ -194,7 +196,7 @@
       },
       {
         "data": {
-          "id": "ChatOutput-tixOe",
+          "id": "ChatOutput-N7nxz",
           "node": {
             "base_classes": [
               "Message"
@@ -492,7 +494,7 @@
           "type": "ChatOutput"
         },
         "dragging": false,
-        "id": "ChatOutput-tixOe",
+        "id": "ChatOutput-N7nxz",
         "measured": {
           "height": 48,
           "width": 192
@@ -506,7 +508,7 @@
       },
       {
         "data": {
-          "id": "KBRetrieval-tGoBR",
+          "id": "KBRetrieval-zz3I0",
           "node": {
             "base_classes": [
               "DataFrame"
@@ -527,10 +529,10 @@
             ],
             "frozen": false,
             "icon": "database",
-            "last_updated": "2025-08-13T19:46:57.894Z",
+            "last_updated": "2025-08-14T17:19:22.182Z",
             "legacy": false,
             "metadata": {
-              "code_hash": "f82365a0977f",
+              "code_hash": "ee2b66958f09",
               "module": "langflow.components.data.kb_retrieval.KBRetrievalComponent"
             },
             "minimized": false,
@@ -587,11 +589,11 @@
                 "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\n\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.deps import get_settings_service\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                str(d.name) for d in KNOWLEDGE_BASES_ROOT_PATH.iterdir() if not d.name.startswith(\".\") and d.is_dir()\n            ]\n            if KNOWLEDGE_BASES_ROOT_PATH.exists()\n            else [],\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=True,\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    def _get_knowledge_bases(self) -> list[str]:\n        \"\"\"Retrieve a list of available knowledge bases.\n\n        Returns:\n            A list of knowledge base names.\n        \"\"\"\n        if not KNOWLEDGE_BASES_ROOT_PATH.exists():\n            return []\n\n        return [str(d.name) for d in KNOWLEDGE_BASES_ROOT_PATH.iterdir() if not d.name.startswith(\".\") and d.is_dir()]\n\n    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\"] = self._get_knowledge_bases()\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        provider = metadata.get(\"embedding_provider\")\n        model = metadata.get(\"embedding_model\")\n        api_key = metadata.get(\"api_key\")\n        chunk_size = metadata.get(\"chunk_size\")\n\n        # If user provided a key in the input, it overrides the stored one.\n        if self.api_key and self.api_key.get_secret_value():\n            api_key = self.api_key.get_secret_value()\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    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        kb_path = KNOWLEDGE_BASES_ROOT_PATH / 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\n\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.deps import get_settings_service\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                str(d.name) for d in KNOWLEDGE_BASES_ROOT_PATH.iterdir() if not d.name.startswith(\".\") and d.is_dir()\n            ]\n            if KNOWLEDGE_BASES_ROOT_PATH.exists()\n            else [],\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    def _get_knowledge_bases(self) -> list[str]:\n        \"\"\"Retrieve a list of available knowledge bases.\n\n        Returns:\n            A list of knowledge base names.\n        \"\"\"\n        if not KNOWLEDGE_BASES_ROOT_PATH.exists():\n            return []\n\n        return [str(d.name) for d in KNOWLEDGE_BASES_ROOT_PATH.iterdir() if not d.name.startswith(\".\") and d.is_dir()]\n\n    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\"] = self._get_knowledge_bases()\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        provider = metadata.get(\"embedding_provider\")\n        model = metadata.get(\"embedding_model\")\n        api_key = metadata.get(\"api_key\")\n        chunk_size = metadata.get(\"chunk_size\")\n\n        # If user provided a key in the input, it overrides the stored one.\n        if self.api_key and self.api_key.get_secret_value():\n            api_key = self.api_key.get_secret_value()\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    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        kb_path = KNOWLEDGE_BASES_ROOT_PATH / 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"
               },
               "include_metadata": {
                 "_input_type": "BoolInput",
-                "advanced": true,
+                "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.",
@@ -678,28 +680,28 @@
           "type": "KBRetrieval"
         },
         "dragging": false,
-        "id": "KBRetrieval-tGoBR",
+        "id": "KBRetrieval-zz3I0",
         "measured": {
-          "height": 286,
+          "height": 329,
           "width": 320
         },
         "position": {
-          "x": 640.6283193600648,
-          "y": -313.9694258557284
+          "x": 616.6226476085393,
+          "y": -343.13068334363356
         },
         "selected": false,
         "type": "genericNode"
       }
     ],
     "viewport": {
-      "x": 285.0464459586908,
-      "y": 588.7377652547386,
-      "zoom": 0.9833370380356916
+      "x": 177.06633386268413,
+      "y": 482.8027480187026,
+      "zoom": 0.8999566725119924
     }
   },
   "description": "An example of performing a vector search against data in a Knowledge Base to retrieve relevant documents.",
   "endpoint_name": null,
-  "id": "670745f6-08b1-480e-bdaf-64ba74967cba",
+  "id": "5487ee05-73d5-4b12-9b41-bc4c3a2f9326",
   "is_component": false,
   "last_tested_version": "1.5.0.post1",
   "name": "Knowledge Retrieval",

langflow/initial_setup/starter_projects/News Aggregator.json

@@ -1208,7 +1208,7 @@
             "legacy": false,
             "lf_version": "1.4.3",
             "metadata": {
-              "code_hash": "6f244023207e",
+              "code_hash": "9134859cf24d",
               "module": "langflow.components.processing.save_file.SaveToFileComponent"
             },
             "minimized": false,
@@ -1220,8 +1220,8 @@
                 "display_name": "File Path",
                 "group_outputs": false,
                 "method": "save_to_file",
-                "name": "result",
-                "selected": "Text",
+                "name": "message",
+                "selected": "Message",
                 "tool_mode": true,
                 "types": [
                   "Message"
@@ -1248,7 +1248,7 @@
                 "show": true,
                 "title_case": false,
                 "type": "code",
-                "value": "import json\nfrom collections.abc import AsyncIterator, Iterator\nfrom pathlib import Path\n\nimport orjson\nimport pandas as pd\nfrom fastapi import UploadFile\nfrom fastapi.encoders import jsonable_encoder\n\nfrom langflow.api.v2.files import upload_user_file\nfrom langflow.custom import Component\nfrom langflow.io import DropdownInput, HandleInput, StrInput\nfrom langflow.schema import Data, DataFrame, Message\nfrom langflow.services.auth.utils import create_user_longterm_token\nfrom langflow.services.database.models.user.crud import get_user_by_id\nfrom langflow.services.deps import get_session, get_settings_service, get_storage_service\nfrom langflow.template.field.base import Output\n\n\nclass SaveToFileComponent(Component):\n    display_name = \"Save File\"\n    description = \"Save data to a local file in the selected format.\"\n    documentation: str = \"https://docs.langflow.org/components-processing#save-file\"\n    icon = \"save\"\n    name = \"SaveToFile\"\n\n    # File format options for different types\n    DATA_FORMAT_CHOICES = [\"csv\", \"excel\", \"json\", \"markdown\"]\n    MESSAGE_FORMAT_CHOICES = [\"txt\", \"json\", \"markdown\"]\n\n    inputs = [\n        HandleInput(\n            name=\"input\",\n            display_name=\"Input\",\n            info=\"The input to save.\",\n            dynamic=True,\n            input_types=[\"Data\", \"DataFrame\", \"Message\"],\n            required=True,\n        ),\n        StrInput(\n            name=\"file_name\",\n            display_name=\"File Name\",\n            info=\"Name file will be saved as (without extension).\",\n            required=True,\n        ),\n        DropdownInput(\n            name=\"file_format\",\n            display_name=\"File Format\",\n            options=list(dict.fromkeys(DATA_FORMAT_CHOICES + MESSAGE_FORMAT_CHOICES)),\n            info=\"Select the file format to save the input. If not provided, the default format will be used.\",\n            value=\"\",\n            advanced=True,\n        ),\n    ]\n\n    outputs = [Output(display_name=\"File Path\", name=\"result\", method=\"save_to_file\")]\n\n    async def save_to_file(self) -> Message:\n        \"\"\"Save the input to a file and upload it, returning a confirmation message.\"\"\"\n        # Validate inputs\n        if not self.file_name:\n            msg = \"File name must be provided.\"\n            raise ValueError(msg)\n        if not self._get_input_type():\n            msg = \"Input type is not set.\"\n            raise ValueError(msg)\n\n        # Validate file format based on input type\n        file_format = self.file_format or self._get_default_format()\n        allowed_formats = (\n            self.MESSAGE_FORMAT_CHOICES if self._get_input_type() == \"Message\" else self.DATA_FORMAT_CHOICES\n        )\n        if file_format not in allowed_formats:\n            msg = f\"Invalid file format '{file_format}' for {self._get_input_type()}. Allowed: {allowed_formats}\"\n            raise ValueError(msg)\n\n        # Prepare file path\n        file_path = Path(self.file_name).expanduser()\n        if not file_path.parent.exists():\n            file_path.parent.mkdir(parents=True, exist_ok=True)\n        file_path = self._adjust_file_path_with_format(file_path, file_format)\n\n        # Save the input to file based on type\n        if self._get_input_type() == \"DataFrame\":\n            confirmation = self._save_dataframe(self.input, file_path, file_format)\n        elif self._get_input_type() == \"Data\":\n            confirmation = self._save_data(self.input, file_path, file_format)\n        elif self._get_input_type() == \"Message\":\n            confirmation = await self._save_message(self.input, file_path, file_format)\n        else:\n            msg = f\"Unsupported input type: {self._get_input_type()}\"\n            raise ValueError(msg)\n\n        # Upload the saved file\n        await self._upload_file(file_path)\n\n        # Return the final file path and confirmation message\n        final_path = Path.cwd() / file_path if not file_path.is_absolute() else file_path\n\n        return Message(text=f\"{confirmation} at {final_path}\")\n\n    def _get_input_type(self) -> str:\n        \"\"\"Determine the input type based on the provided input.\"\"\"\n        # Use exact type checking (type() is) instead of isinstance() to avoid inheritance issues.\n        # Since Message inherits from Data, isinstance(message, Data) would return True for Message objects,\n        # causing Message inputs to be incorrectly identified as Data type.\n        if type(self.input) is DataFrame:\n            return \"DataFrame\"\n        if type(self.input) is Message:\n            return \"Message\"\n        if type(self.input) is Data:\n            return \"Data\"\n        msg = f\"Unsupported input type: {type(self.input)}\"\n        raise ValueError(msg)\n\n    def _get_default_format(self) -> str:\n        \"\"\"Return the default file format based on input type.\"\"\"\n        if self._get_input_type() == \"DataFrame\":\n            return \"csv\"\n        if self._get_input_type() == \"Data\":\n            return \"json\"\n        if self._get_input_type() == \"Message\":\n            return \"json\"\n        return \"json\"  # Fallback\n\n    def _adjust_file_path_with_format(self, path: Path, fmt: str) -> Path:\n        \"\"\"Adjust the file path to include the correct extension.\"\"\"\n        file_extension = path.suffix.lower().lstrip(\".\")\n        if fmt == \"excel\":\n            return Path(f\"{path}.xlsx\").expanduser() if file_extension not in [\"xlsx\", \"xls\"] else path\n        return Path(f\"{path}.{fmt}\").expanduser() if file_extension != fmt else path\n\n    async def _upload_file(self, file_path: Path) -> None:\n        \"\"\"Upload the saved file using the upload_user_file service.\"\"\"\n        if not file_path.exists():\n            msg = f\"File not found: {file_path}\"\n            raise FileNotFoundError(msg)\n\n        with file_path.open(\"rb\") as f:\n            async for db in get_session():\n                user_id, _ = await create_user_longterm_token(db)\n                current_user = await get_user_by_id(db, user_id)\n\n                await upload_user_file(\n                    file=UploadFile(filename=file_path.name, file=f, size=file_path.stat().st_size),\n                    session=db,\n                    current_user=current_user,\n                    storage_service=get_storage_service(),\n                    settings_service=get_settings_service(),\n                )\n\n    def _save_dataframe(self, dataframe: DataFrame, path: Path, fmt: str) -> str:\n        \"\"\"Save a DataFrame to the specified file format.\"\"\"\n        if fmt == \"csv\":\n            dataframe.to_csv(path, index=False)\n        elif fmt == \"excel\":\n            dataframe.to_excel(path, index=False, engine=\"openpyxl\")\n        elif fmt == \"json\":\n            dataframe.to_json(path, orient=\"records\", indent=2)\n        elif fmt == \"markdown\":\n            path.write_text(dataframe.to_markdown(index=False), encoding=\"utf-8\")\n        else:\n            msg = f\"Unsupported DataFrame format: {fmt}\"\n            raise ValueError(msg)\n        return f\"DataFrame saved successfully as '{path}'\"\n\n    def _save_data(self, data: Data, path: Path, fmt: str) -> str:\n        \"\"\"Save a Data object to the specified file format.\"\"\"\n        if fmt == \"csv\":\n            pd.DataFrame(data.data).to_csv(path, index=False)\n        elif fmt == \"excel\":\n            pd.DataFrame(data.data).to_excel(path, index=False, engine=\"openpyxl\")\n        elif fmt == \"json\":\n            path.write_text(\n                orjson.dumps(jsonable_encoder(data.data), option=orjson.OPT_INDENT_2).decode(\"utf-8\"), encoding=\"utf-8\"\n            )\n        elif fmt == \"markdown\":\n            path.write_text(pd.DataFrame(data.data).to_markdown(index=False), encoding=\"utf-8\")\n        else:\n            msg = f\"Unsupported Data format: {fmt}\"\n            raise ValueError(msg)\n        return f\"Data saved successfully as '{path}'\"\n\n    async def _save_message(self, message: Message, path: Path, fmt: str) -> str:\n        \"\"\"Save a Message to the specified file format, handling async iterators.\"\"\"\n        content = \"\"\n        if message.text is None:\n            content = \"\"\n        elif isinstance(message.text, AsyncIterator):\n            async for item in message.text:\n                content += str(item) + \" \"\n            content = content.strip()\n        elif isinstance(message.text, Iterator):\n            content = \" \".join(str(item) for item in message.text)\n        else:\n            content = str(message.text)\n\n        if fmt == \"txt\":\n            path.write_text(content, encoding=\"utf-8\")\n        elif fmt == \"json\":\n            path.write_text(json.dumps({\"message\": content}, indent=2), encoding=\"utf-8\")\n        elif fmt == \"markdown\":\n            path.write_text(f\"**Message:**\\n\\n{content}\", encoding=\"utf-8\")\n        else:\n            msg = f\"Unsupported Message format: {fmt}\"\n            raise ValueError(msg)\n        return f\"Message saved successfully as '{path}'\"\n"
+                "value": "import json\nfrom collections.abc import AsyncIterator, Iterator\nfrom pathlib import Path\n\nimport orjson\nimport pandas as pd\nfrom fastapi import UploadFile\nfrom fastapi.encoders import jsonable_encoder\n\nfrom langflow.api.v2.files import upload_user_file\nfrom langflow.custom import Component\nfrom langflow.io import DropdownInput, HandleInput, StrInput\nfrom langflow.schema import Data, DataFrame, Message\nfrom langflow.services.auth.utils import create_user_longterm_token\nfrom langflow.services.database.models.user.crud import get_user_by_id\nfrom langflow.services.deps import get_session, get_settings_service, get_storage_service\nfrom langflow.template.field.base import Output\n\n\nclass SaveToFileComponent(Component):\n    display_name = \"Save File\"\n    description = \"Save data to a local file in the selected format.\"\n    documentation: str = \"https://docs.langflow.org/components-processing#save-file\"\n    icon = \"save\"\n    name = \"SaveToFile\"\n\n    # File format options for different types\n    DATA_FORMAT_CHOICES = [\"csv\", \"excel\", \"json\", \"markdown\"]\n    MESSAGE_FORMAT_CHOICES = [\"txt\", \"json\", \"markdown\"]\n\n    inputs = [\n        HandleInput(\n            name=\"input\",\n            display_name=\"Input\",\n            info=\"The input to save.\",\n            dynamic=True,\n            input_types=[\"Data\", \"DataFrame\", \"Message\"],\n            required=True,\n        ),\n        StrInput(\n            name=\"file_name\",\n            display_name=\"File Name\",\n            info=\"Name file will be saved as (without extension).\",\n            required=True,\n        ),\n        DropdownInput(\n            name=\"file_format\",\n            display_name=\"File Format\",\n            options=list(dict.fromkeys(DATA_FORMAT_CHOICES + MESSAGE_FORMAT_CHOICES)),\n            info=\"Select the file format to save the input. If not provided, the default format will be used.\",\n            value=\"\",\n            advanced=True,\n        ),\n    ]\n\n    outputs = [Output(display_name=\"File Path\", name=\"message\", method=\"save_to_file\")]\n\n    async def save_to_file(self) -> Message:\n        \"\"\"Save the input to a file and upload it, returning a confirmation message.\"\"\"\n        # Validate inputs\n        if not self.file_name:\n            msg = \"File name must be provided.\"\n            raise ValueError(msg)\n        if not self._get_input_type():\n            msg = \"Input type is not set.\"\n            raise ValueError(msg)\n\n        # Validate file format based on input type\n        file_format = self.file_format or self._get_default_format()\n        allowed_formats = (\n            self.MESSAGE_FORMAT_CHOICES if self._get_input_type() == \"Message\" else self.DATA_FORMAT_CHOICES\n        )\n        if file_format not in allowed_formats:\n            msg = f\"Invalid file format '{file_format}' for {self._get_input_type()}. Allowed: {allowed_formats}\"\n            raise ValueError(msg)\n\n        # Prepare file path\n        file_path = Path(self.file_name).expanduser()\n        if not file_path.parent.exists():\n            file_path.parent.mkdir(parents=True, exist_ok=True)\n        file_path = self._adjust_file_path_with_format(file_path, file_format)\n\n        # Save the input to file based on type\n        if self._get_input_type() == \"DataFrame\":\n            confirmation = self._save_dataframe(self.input, file_path, file_format)\n        elif self._get_input_type() == \"Data\":\n            confirmation = self._save_data(self.input, file_path, file_format)\n        elif self._get_input_type() == \"Message\":\n            confirmation = await self._save_message(self.input, file_path, file_format)\n        else:\n            msg = f\"Unsupported input type: {self._get_input_type()}\"\n            raise ValueError(msg)\n\n        # Upload the saved file\n        await self._upload_file(file_path)\n\n        # Return the final file path and confirmation message\n        final_path = Path.cwd() / file_path if not file_path.is_absolute() else file_path\n\n        return Message(text=f\"{confirmation} at {final_path}\")\n\n    def _get_input_type(self) -> str:\n        \"\"\"Determine the input type based on the provided input.\"\"\"\n        # Use exact type checking (type() is) instead of isinstance() to avoid inheritance issues.\n        # Since Message inherits from Data, isinstance(message, Data) would return True for Message objects,\n        # causing Message inputs to be incorrectly identified as Data type.\n        if type(self.input) is DataFrame:\n            return \"DataFrame\"\n        if type(self.input) is Message:\n            return \"Message\"\n        if type(self.input) is Data:\n            return \"Data\"\n        msg = f\"Unsupported input type: {type(self.input)}\"\n        raise ValueError(msg)\n\n    def _get_default_format(self) -> str:\n        \"\"\"Return the default file format based on input type.\"\"\"\n        if self._get_input_type() == \"DataFrame\":\n            return \"csv\"\n        if self._get_input_type() == \"Data\":\n            return \"json\"\n        if self._get_input_type() == \"Message\":\n            return \"json\"\n        return \"json\"  # Fallback\n\n    def _adjust_file_path_with_format(self, path: Path, fmt: str) -> Path:\n        \"\"\"Adjust the file path to include the correct extension.\"\"\"\n        file_extension = path.suffix.lower().lstrip(\".\")\n        if fmt == \"excel\":\n            return Path(f\"{path}.xlsx\").expanduser() if file_extension not in [\"xlsx\", \"xls\"] else path\n        return Path(f\"{path}.{fmt}\").expanduser() if file_extension != fmt else path\n\n    async def _upload_file(self, file_path: Path) -> None:\n        \"\"\"Upload the saved file using the upload_user_file service.\"\"\"\n        if not file_path.exists():\n            msg = f\"File not found: {file_path}\"\n            raise FileNotFoundError(msg)\n\n        with file_path.open(\"rb\") as f:\n            async for db in get_session():\n                user_id, _ = await create_user_longterm_token(db)\n                current_user = await get_user_by_id(db, user_id)\n\n                await upload_user_file(\n                    file=UploadFile(filename=file_path.name, file=f, size=file_path.stat().st_size),\n                    session=db,\n                    current_user=current_user,\n                    storage_service=get_storage_service(),\n                    settings_service=get_settings_service(),\n                )\n\n    def _save_dataframe(self, dataframe: DataFrame, path: Path, fmt: str) -> str:\n        \"\"\"Save a DataFrame to the specified file format.\"\"\"\n        if fmt == \"csv\":\n            dataframe.to_csv(path, index=False)\n        elif fmt == \"excel\":\n            dataframe.to_excel(path, index=False, engine=\"openpyxl\")\n        elif fmt == \"json\":\n            dataframe.to_json(path, orient=\"records\", indent=2)\n        elif fmt == \"markdown\":\n            path.write_text(dataframe.to_markdown(index=False), encoding=\"utf-8\")\n        else:\n            msg = f\"Unsupported DataFrame format: {fmt}\"\n            raise ValueError(msg)\n        return f\"DataFrame saved successfully as '{path}'\"\n\n    def _save_data(self, data: Data, path: Path, fmt: str) -> str:\n        \"\"\"Save a Data object to the specified file format.\"\"\"\n        if fmt == \"csv\":\n            pd.DataFrame(data.data).to_csv(path, index=False)\n        elif fmt == \"excel\":\n            pd.DataFrame(data.data).to_excel(path, index=False, engine=\"openpyxl\")\n        elif fmt == \"json\":\n            path.write_text(\n                orjson.dumps(jsonable_encoder(data.data), option=orjson.OPT_INDENT_2).decode(\"utf-8\"), encoding=\"utf-8\"\n            )\n        elif fmt == \"markdown\":\n            path.write_text(pd.DataFrame(data.data).to_markdown(index=False), encoding=\"utf-8\")\n        else:\n            msg = f\"Unsupported Data format: {fmt}\"\n            raise ValueError(msg)\n        return f\"Data saved successfully as '{path}'\"\n\n    async def _save_message(self, message: Message, path: Path, fmt: str) -> str:\n        \"\"\"Save a Message to the specified file format, handling async iterators.\"\"\"\n        content = \"\"\n        if message.text is None:\n            content = \"\"\n        elif isinstance(message.text, AsyncIterator):\n            async for item in message.text:\n                content += str(item) + \" \"\n            content = content.strip()\n        elif isinstance(message.text, Iterator):\n            content = \" \".join(str(item) for item in message.text)\n        else:\n            content = str(message.text)\n\n        if fmt == \"txt\":\n            path.write_text(content, encoding=\"utf-8\")\n        elif fmt == \"json\":\n            path.write_text(json.dumps({\"message\": content}, indent=2), encoding=\"utf-8\")\n        elif fmt == \"markdown\":\n            path.write_text(f\"**Message:**\\n\\n{content}\", encoding=\"utf-8\")\n        else:\n            msg = f\"Unsupported Message format: {fmt}\"\n            raise ValueError(msg)\n        return f\"Message saved successfully as '{path}'\"\n"
               },
               "file_format": {
                 "_input_type": "DropdownInput",

langflow/services/database/models/user/crud.py

@@ -60,3 +60,10 @@ async def update_user_last_login_at(user_id: UUID, db: AsyncSession):
         return await update_user(user, user_data, db)
     except Exception as e:  # noqa: BLE001
         logger.error(f"Error updating user last login at: {e!s}")
+
+
+async def get_all_superusers(db: AsyncSession) -> list[User]:
+    """Get all superuser accounts from the database."""
+    stmt = select(User).where(User.is_superuser == True)  # noqa: E712
+    result = await db.exec(stmt)
+    return list(result.all())

langflow/services/settings/auth.py

@@ -27,12 +27,25 @@ class AuthSettings(BaseSettings):
     API_KEY_ALGORITHM: str = "HS256"
     API_V1_STR: str = "/api/v1"
 
-    AUTO_LOGIN: bool = True
+    AUTO_LOGIN: bool = Field(
+        default=True,  # TODO: Set to False in v1.6
+        description=(
+            "Enable automatic login with default credentials. "
+            "SECURITY WARNING: This bypasses authentication and should only be used in development environments. "
+            "Set to False in production."
+        ),
+    )
     """If True, the application will attempt to log in automatically as a super user."""
     skip_auth_auto_login: bool = True
     """If True, the application will skip authentication when AUTO_LOGIN is enabled.
     This will be removed in v1.6"""
 
+    ENABLE_SUPERUSER_CLI: bool = Field(
+        default=True,
+        description="Allow creation of superusers via CLI. Set to False in production for security.",
+    )
+    """If True, allows creation of superusers via the CLI 'langflow superuser' command."""
+
     NEW_USER_IS_ACTIVE: bool = False
     SUPERUSER: str = DEFAULT_SUPERUSER
     SUPERUSER_PASSWORD: str = DEFAULT_SUPERUSER_PASSWORD

langflow/services/utils.py

@@ -68,15 +68,20 @@ async def get_or_create_super_user(session: AsyncSession, username, password, is
     return await create_super_user(username, password, db=session)
 
 
-async def setup_superuser(settings_service, session: AsyncSession) -> None:
+async def setup_superuser(settings_service: SettingsService, session: AsyncSession) -> None:
     if settings_service.auth_settings.AUTO_LOGIN:
         logger.debug("AUTO_LOGIN is set to True. Creating default superuser.")
+        username = DEFAULT_SUPERUSER
+        password = DEFAULT_SUPERUSER_PASSWORD
     else:
         # Remove the default superuser if it exists
         await teardown_superuser(settings_service, session)
+        username = settings_service.auth_settings.SUPERUSER
+        password = settings_service.auth_settings.SUPERUSER_PASSWORD
 
-    username = settings_service.auth_settings.SUPERUSER
-    password = settings_service.auth_settings.SUPERUSER_PASSWORD
+    if not username or not password:
+        msg = "Username and password must be set"
+        raise ValueError(msg)
 
     is_default = (username == DEFAULT_SUPERUSER) and (password == DEFAULT_SUPERUSER_PASSWORD)
 

{langflow_base_nightly-0.5.0.dev31.dist-info → langflow_base_nightly-0.5.0.dev33.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: langflow-base-nightly
-Version: 0.5.0.dev31
+Version: 0.5.0.dev33
 Summary: A Python package with a built-in web application
 Project-URL: Repository, https://github.com/langflow-ai/langflow
 Project-URL: Documentation, https://docs.langflow.org

{langflow_base_nightly-0.5.0.dev31.dist-info → langflow_base_nightly-0.5.0.dev33.dist-info}/RECORD

@@ -1,5 +1,5 @@
 langflow/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-langflow/__main__.py,sha256=80Jc0iW3DjkwRG_oDqHH9RkzJIakyCrPGvl_Zvhzaqc,32283
+langflow/__main__.py,sha256=x1urQ-v-LKMcuPfdxMXVxzY6vF7nZ1gMeQq6coMbl08,36812
 langflow/alembic.ini,sha256=fbUkg3Y988q24z9FRya85qBQBvKvEI8fQbR4CsWHHsk,3503
 langflow/langflow_launcher.py,sha256=ruVUD-ZXb-Bi9xtXYu17rXuwBr6OmPMF46mH-hPbfpQ,1984
 langflow/main.py,sha256=20UgLEpbG__xbT3zqQNvLsP2mYtjZcvNsGaAvUxWD3c,18195
@@ -257,7 +257,7 @@ langflow/components/data/directory.py,sha256=MqSUyq5cL6Xy2CqBREc0hJlcoega3r82ti2
 langflow/components/data/file.py,sha256=07zPsp7_qUyBpziW7UfQLHoWY70Ps6hRPyKyX3aLLzw,5861
 langflow/components/data/json_to_data.py,sha256=uN3yyVHo-DOvv0ZwYQx99V-rWddh3A6iDBKW7ga1J4c,3554
 langflow/components/data/kb_ingest.py,sha256=Ed8Z3lQdjsT-FScEYnJA0N68ReppmP7JZvczViZ12eU,24334
-langflow/components/data/kb_retrieval.py,sha256=-CNloJd_aEPZsZ_hhnwQdKoqZ7TKWO9_yTpqX6kJgLQ,9946
+langflow/components/data/kb_retrieval.py,sha256=7itmlY8JTS91P_oju0-sKDV2vZyWUuiQVRhg88I_3s8,9947
 langflow/components/data/news_search.py,sha256=PpuhSTH_gk1iWjX4X3N0PxIPAAdcrnH0GAtu_d5LSgA,6196
 langflow/components/data/rss.py,sha256=B_DZvPdnJhnh7qkzPHcp-ERsfqcft6kTNl58G94zJzg,2504
 langflow/components/data/sql_executor.py,sha256=rfIXj4-w8Jkq10DL9nCRVflbEDZGsw_C6Lrgrhk7UA8,3637
@@ -476,7 +476,7 @@ langflow/components/processing/parser.py,sha256=VWIJUgZQRN-eW8zgEUOECfpmy0nmfRI7
 langflow/components/processing/prompt.py,sha256=xHilcszTEdewqBufJusnkXWTrRqC8MX9fEEz1n-vgK0,2791
 langflow/components/processing/python_repl_core.py,sha256=FaNGm6f2ngniE2lueYaoxSn-hZ-yKePdV60y-jc9nfs,3477
 langflow/components/processing/regex.py,sha256=MQVd8nUwe3engl_JiI-wEn1BvXVm1e0vQOn99gdiOrw,2660
-langflow/components/processing/save_file.py,sha256=byRAIyB-KVM4FaL6_ZPhaP5NhT9Rl4Sett9n_xoBBmg,8841
+langflow/components/processing/save_file.py,sha256=kTSFnPJN7em85Dpa6EzqyALSc3A3eaP6MnQMPu_IojU,8842
 langflow/components/processing/select_data.py,sha256=t1InSoxLIageodImGpkNG1tWAirHKuFrU9QhNdom8PA,1765
 langflow/components/processing/split_text.py,sha256=2_Lp0jGdEAnuup4ucL-ZexpcarCL78wJAwQLCL2cleE,5323
 langflow/components/processing/structured_output.py,sha256=rSpvRVLAlxcnEWFJVvExZC-NTmIb6rUieBzYnSMV9po,7991
@@ -867,11 +867,11 @@ langflow/initial_setup/starter_projects/Image Sentiment Analysis.json,sha256=p3y
 langflow/initial_setup/starter_projects/Instagram Copywriter.json,sha256=iBqKLxara5PJsbztdq9k-M6q0mkd_OExISb71t9Ft6o,169884
 langflow/initial_setup/starter_projects/Invoice Summarizer.json,sha256=IdWYegxw5qTplYBdBt3Vl_b61bNgeTzPEtX6DVuimSM,95726
 langflow/initial_setup/starter_projects/Knowledge Ingestion.json,sha256=tqDxS1SO6L8ReXutxVgJSeoV-m_R6slPPsF1uswsMcc,81324
-langflow/initial_setup/starter_projects/Knowledge Retrieval.json,sha256=nfFOoBouPGbCxfXXH87A-fUox1gFIKm9utLjBAMAJqY,43432
+langflow/initial_setup/starter_projects/Knowledge Retrieval.json,sha256=abZ7akGNWy_ywoFWTcq0xyT--iRbEBnXh8Xx0Q1BizY,43494
 langflow/initial_setup/starter_projects/Market Research.json,sha256=i3IZbaXaXwNL_l222sikK4kCbtVjm_JU8xHrs-KTFI0,151362
 langflow/initial_setup/starter_projects/Meeting Summary.json,sha256=rm58p7Dkxb4vBzyin-Aa1i6XdMT0Au5D5_QuEuuxNDM,195851
 langflow/initial_setup/starter_projects/Memory Chatbot.json,sha256=d4imk-w2M69O8iCJT-Xbf9dleEf8uaLAsKzqLkMMZWw,85446
-langflow/initial_setup/starter_projects/News Aggregator.json,sha256=Lzs07rFOPH2btMNs0TRyPGsF_JRNwLFuFEHPhBIoSaI,113349
+langflow/initial_setup/starter_projects/News Aggregator.json,sha256=vx0oPSjujjvtvq1XexHHs5VqA_thHpP4toPp7bS4R1Y,113354
 langflow/initial_setup/starter_projects/Nvidia Remix.json,sha256=hv-3BxMnVVh4b8Jk_b80EDRRlxOKEmG0-qYsehX6TzE,315071
 langflow/initial_setup/starter_projects/Pokédex Agent.json,sha256=xBs9Ih8IRFDTAP64ra2DhO52iQHui7xj-2JMq6YL3kY,111969
 langflow/initial_setup/starter_projects/Portfolio Website Code Generator.json,sha256=GU8ESXR_Lf6_NdGihyuPyk4JUcO0KhzmL7dQQGr9XAo,123578
@@ -953,7 +953,7 @@ langflow/services/deps.py,sha256=hpY-jjKF2GrDC924BfnCaUpF99sgr_ERin2k8Q_cYaA,785
 langflow/services/factory.py,sha256=mbPR1IIG5Fot2MV8rrkpouwq72sbq--SFYM83IUMCB8,3023
 langflow/services/manager.py,sha256=SwTQwWzP9IrAgex0bfdp95IfnVbaMLm7HYS7DtVFO9U,5634
 langflow/services/schema.py,sha256=dZVRfY58rqCHs0VUdI5F773pgyYTPjVz3Hm2eUA_MxM,811
-langflow/services/utils.py,sha256=oFI46ywkr_lE_MdkegbRb6hDv6JYsHArVRLpaUxZ7L4,9593
+langflow/services/utils.py,sha256=w_s6zUIA4p0psKExGDvv4yHh3kSi5vHu84JNvpzXszI,9818
 langflow/services/auth/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 langflow/services/auth/factory.py,sha256=ML6QA2QfHpkbyzKAbJUHoW2cx6T6IvGp6SWGlnOZ_9s,389
 langflow/services/auth/service.py,sha256=mBlINyRcZZGR5jpWZQ6AOEm0CfXouz0D6UV3z73OM3w,364
@@ -999,7 +999,7 @@ langflow/services/database/models/transactions/__init__.py,sha256=rgYTZHOkYWztmi
 langflow/services/database/models/transactions/crud.py,sha256=Iv8_HDPLEPj6TZDzzspw6N-Qi6YinlfRWUFngdW5GWU,2807
 langflow/services/database/models/transactions/model.py,sha256=-NZyjAxFYQaNBApOFKat5Jy3TTTnrsIHMg8P0Yn9fjA,2289
 langflow/services/database/models/user/__init__.py,sha256=_em9DxemZQd6omKdWTlVYvDZ0NUix24UWOq5ymZs_-o,137
-langflow/services/database/models/user/crud.py,sha256=1lpjb7BS4p4c6A1X1OWiubmm3rDF0xQxq3ubu35DeDI,2196
+langflow/services/database/models/user/crud.py,sha256=M6CuXvP8hxiy5HgdKpmAWgWJCZTurR_cBxcnVQ8LiX8,2450
 langflow/services/database/models/user/model.py,sha256=uGFtG4n4fBS-p2aWMh_19BCLAH10MnMBhCX97TSrI9M,3036
 langflow/services/database/models/variable/__init__.py,sha256=9yX_efy4NkT5UvF4souRWZ-jjlidYwqp7cIuweSgOpc,150
 langflow/services/database/models/variable/model.py,sha256=aJROdKeNDDjWGsitmeTG0ZEhiuAVZMdJIrTG4y9dP7g,2820
@@ -1016,7 +1016,7 @@ langflow/services/session/factory.py,sha256=6IzDDO4a3Ui5P3-Crf2yXrJjFpvXET6kXWfq
 langflow/services/session/service.py,sha256=KR82A1sycF2gmb7zeqxn4EZ0_NxZcQN1ggRsergQNpI,2511
 langflow/services/session/utils.py,sha256=YkInqhL019XrgIyovOtkLqFF3jJmlQBSPbKiKOuWGiM,516
 langflow/services/settings/__init__.py,sha256=UISBvOQIqoA3a8opwJrTQp4PSTqpReY6GQ_7O6WuqJQ,65
-langflow/services/settings/auth.py,sha256=jpVRROmFtNp1rqoHYFINzsdnQ_QrglyLgB_uVHhpNVI,4562
+langflow/services/settings/auth.py,sha256=1WaQ74QemaN8J9A6rdMOiiu-7I380QkLDbfK0yeu9g4,5138
 langflow/services/settings/base.py,sha256=h5YtJ2ISz7bJjq3JOLDFccGxQKMEJ-UQfBRBLKQNFxo,24365
 langflow/services/settings/constants.py,sha256=Uf8HrGOpRE-55IZ7aopsZsEnzBb9rRPi--PFvJfUGqw,878
 langflow/services/settings/factory.py,sha256=Jf0leRvzUBlxZ6BsoCJEDKdH2kWR9Tiv-Dk8Y7cbqUE,595
@@ -1111,7 +1111,7 @@ langflow/utils/util_strings.py,sha256=Blz5lwvE7lml7nKCG9vVJ6me5VNmVtYzFXDVPHPK7v
 langflow/utils/validate.py,sha256=8RnY61LZFCBU1HIlPDCMI3vsXOmK_IFAYBGZIfZJcsU,16362
 langflow/utils/version.py,sha256=OjSj0smls9XnPd4-LpTH9AWyUO_NAn5mncqKkkXl_fw,2840
 langflow/utils/voice_utils.py,sha256=pzU6uuseI2_5mi-yXzFIjMavVRFyuVrpLmR6LqbF7mE,3346
-langflow_base_nightly-0.5.0.dev31.dist-info/METADATA,sha256=oNuRt9Jypx0ynOqLtC2pJk9IQ2yXWLqSkg6W5FI-eZU,4212
-langflow_base_nightly-0.5.0.dev31.dist-info/WHEEL,sha256=qtCwoSJWgHk21S1Kb4ihdzI2rlJ1ZKaIurTj_ngOhyQ,87
-langflow_base_nightly-0.5.0.dev31.dist-info/entry_points.txt,sha256=JvuLdXSrkeDmDdpb8M-VvFIzb84n4HmqUcIP10_EIF8,57
-langflow_base_nightly-0.5.0.dev31.dist-info/RECORD,,
+langflow_base_nightly-0.5.0.dev33.dist-info/METADATA,sha256=5XO02Mg1LMhMdnjlctfL1xGbNt7OWYtjo-FhT0OI__U,4212
+langflow_base_nightly-0.5.0.dev33.dist-info/WHEEL,sha256=qtCwoSJWgHk21S1Kb4ihdzI2rlJ1ZKaIurTj_ngOhyQ,87
+langflow_base_nightly-0.5.0.dev33.dist-info/entry_points.txt,sha256=JvuLdXSrkeDmDdpb8M-VvFIzb84n4HmqUcIP10_EIF8,57
+langflow_base_nightly-0.5.0.dev33.dist-info/RECORD,,