Merge remote-tracking branch 'origin/dev' into zustand/io/migration

src/backend/langflow/api/v1/chat.py

@@ -1,6 +1,6 @@
 import time
 
-from fastapi import APIRouter, Body, Depends, HTTPException, Query, WebSocket, WebSocketException, status
+from fastapi import APIRouter, Body, Depends, HTTPException, WebSocket, WebSocketException, status
 from fastapi.responses import StreamingResponse
 from langflow.api.utils import build_input_keys_response, format_elapsed_time
 from langflow.api.v1.schemas import (
@@ -15,7 +15,7 @@ from langflow.api.v1.schemas import (
 from langflow.graph.graph.base import Graph
 from langflow.graph.vertex.base import StatelessVertex
 from langflow.processing.process import process_tweaks_on_graph
-from langflow.services.auth.utils import get_current_active_user, get_current_user_by_jwt
+from langflow.services.auth.utils import get_current_active_user, get_current_user_for_websocket
 from langflow.services.cache.service import BaseCacheService
 from langflow.services.cache.utils import update_build_status
 from langflow.services.chat.service import ChatService
@@ -32,17 +32,16 @@ router = APIRouter(tags=["Chat"])
 async def chat(
     client_id: str,
     websocket: WebSocket,
-    token: str = Query(...),
     db: Session = Depends(get_session),
     chat_service: "ChatService" = Depends(get_chat_service),
 ):
     """Websocket endpoint for chat."""
     try:
-        user = await get_current_user_by_jwt(token, db)
+        user = await get_current_user_for_websocket(websocket, db)
         await websocket.accept()
         if not user:
             await websocket.close(code=status.WS_1008_POLICY_VIOLATION, reason="Unauthorized")
-        if not user.is_active:
+        elif not user.is_active:
             await websocket.close(code=status.WS_1008_POLICY_VIOLATION, reason="Unauthorized")
 
         if client_id in chat_service.cache_service:

src/backend/langflow/components/agents/AgentInitializer.py

@@ -41,12 +41,11 @@ class AgentInitializerComponent(CustomComponent):
                 handle_parsing_errors=True,
                 max_iterations=max_iterations,
             )
-        else:
-            return initialize_agent(
-                tools=tools,
-                llm=llm,
-                agent=agent,
-                return_intermediate_steps=True,
-                handle_parsing_errors=True,
-                max_iterations=max_iterations,
-            )
+        return initialize_agent(
+            tools=tools,
+            llm=llm,
+            agent=agent,
+            return_intermediate_steps=True,
+            handle_parsing_errors=True,
+            max_iterations=max_iterations,
+        )

src/backend/langflow/components/agents/OpenAIConversationalAgent.py

@@ -3,13 +3,12 @@ from typing import List, Optional
 from langchain.agents.agent import AgentExecutor
 from langchain.agents.agent_toolkits.conversational_retrieval.openai_functions import _get_default_system_message
 from langchain.agents.openai_functions_agent.base import OpenAIFunctionsAgent
-from langchain_community.chat_models import ChatOpenAI
 from langchain.memory.token_buffer import ConversationTokenBufferMemory
 from langchain.prompts import SystemMessagePromptTemplate
 from langchain.prompts.chat import MessagesPlaceholder
 from langchain.schema.memory import BaseMemory
 from langchain.tools import Tool
-
+from langchain_community.chat_models import ChatOpenAI
 from langflow import CustomComponent
 from langflow.field_typing.range_spec import RangeSpec
 
@@ -20,11 +19,12 @@ class ConversationalAgent(CustomComponent):
 
     def build_config(self):
         openai_function_models = [
+            "gpt-4-turbo-preview",
+            "gpt-4-0125-preview",
             "gpt-4-1106-preview",
-            "gpt-3.5-turbo",
-            "gpt-3.5-turbo-16k",
-            "gpt-4",
-            "gpt-4-32k",
+            "gpt-4-vision-preview",
+            "gpt-3.5-turbo-0125",
+            "gpt-3.5-turbo-1106",
         ]
         return {
             "tools": {"display_name": "Tools"},

src/backend/langflow/components/chains/PromptRunner.py

@@ -1,7 +1,6 @@
 from langchain.llms.base import BaseLLM
 from langchain.prompts import PromptTemplate
 from langchain_core.messages import BaseMessage
-
 from langflow import CustomComponent
 from langflow.field_typing import Text
 

src/backend/langflow/components/documentloaders/FileLoader.py

@@ -1,5 +1,4 @@
-from langchain.schema import Document
-
+from langchain_core.documents import Document
 from langflow import CustomComponent
 from langflow.utils.constants import LOADERS_INFO
 

src/backend/langflow/components/documentloaders/UrlLoader.py

@@ -1,7 +1,8 @@
 from typing import List
 
 from langchain import document_loaders
-from langchain.schema import Document
+from langchain_core.documents import Document
+
 from langflow import CustomComponent
 
 

src/backend/langflow/components/embeddings/OpenAIEmbeddings.py

@@ -42,7 +42,11 @@ class OpenAIEmbeddingsComponent(CustomComponent):
                 "advanced": True,
             },
             "max_retries": {"display_name": "Max Retries", "advanced": True},
-            "model": {"display_name": "Model", "advanced": True},
+            "model": {
+                "display_name": "Model",
+                "advanced": False,
+                "options": ["text-embedding-3-small", "text-embedding-3-large", "text-embedding-ada-002"],
+            },
             "model_kwargs": {"display_name": "Model Kwargs", "advanced": True},
             "openai_api_base": {"display_name": "OpenAI API Base", "password": True, "advanced": True},
             "openai_api_key": {"display_name": "OpenAI API Key", "password": True},
@@ -74,10 +78,10 @@ class OpenAIEmbeddingsComponent(CustomComponent):
         disallowed_special: List[str] = ["all"],
         chunk_size: int = 1000,
         client: Optional[Any] = None,
-        deployment: str = "text-embedding-ada-002",
+        deployment: str = "text-embedding-3-small",
         embedding_ctx_length: int = 8191,
         max_retries: int = 6,
-        model: str = "text-embedding-ada-002",
+        model: str = "text-embedding-3-small",
         model_kwargs: NestedDict = {},
         openai_api_base: Optional[str] = None,
         openai_api_key: Optional[str] = "",

src/backend/langflow/components/llms/ChatOpenAI.py

@@ -2,6 +2,7 @@ from typing import Optional, Union
 
 from langchain.llms import BaseLLM
 from langchain_community.chat_models.openai import ChatOpenAI
+
 from langflow import CustomComponent
 from langflow.field_typing import BaseLanguageModel, NestedDict
 
@@ -30,11 +31,12 @@ class ChatOpenAIComponent(CustomComponent):
                 "advanced": False,
                 "required": False,
                 "options": [
+                    "gpt-4-turbo-preview",
+                    "gpt-4-0125-preview",
                     "gpt-4-1106-preview",
-                    "gpt-4",
-                    "gpt-4-32k",
-                    "gpt-3.5-turbo",
-                    "gpt-3.5-turbo-16k",
+                    "gpt-4-vision-preview",
+                    "gpt-3.5-turbo-0125",
+                    "gpt-3.5-turbo-1106",
                 ],
             },
             "openai_api_base": {

src/backend/langflow/components/textsplitters/LanguageRecursiveTextSplitter.py

@@ -1,7 +1,7 @@
 from typing import Optional
 
-from langchain.schema import Document
 from langchain.text_splitter import Language
+from langchain_core.documents import Document
 
 from langflow import CustomComponent
 

src/backend/langflow/components/textsplitters/RecursiveCharacterTextSplitter.py

@@ -1,7 +1,10 @@
 from typing import Optional
+
+from langchain_core.documents import Document
+
 from langflow import CustomComponent
-from langchain.schema import Document
 from langflow.utils.util import build_loader_repr_from_documents
+from langchain.text_splitter import RecursiveCharacterTextSplitter
 
 
 class RecursiveCharacterTextSplitterComponent(CustomComponent):
@@ -54,7 +57,6 @@ class RecursiveCharacterTextSplitterComponent(CustomComponent):
         Returns:
             list[str]: The chunks of text.
         """
-        from langchain.text_splitter import RecursiveCharacterTextSplitter
 
         if separators == "":
             separators = None

src/backend/langflow/components/utilities/GetRequest.py

@@ -1,9 +1,10 @@
-from langflow import CustomComponent
-from langchain.schema import Document
-from langflow.services.database.models.base import orjson_dumps
-import requests
 from typing import Optional
 
+import requests
+from langchain_core.documents import Document
+from langflow import CustomComponent
+from langflow.services.database.models.base import orjson_dumps
+
 
 class GetRequest(CustomComponent):
     display_name: str = "GET Request"

src/backend/langflow/components/utilities/JSONDocumentBuilder.py

@@ -11,7 +11,7 @@
 
 # - **Document:** The Document containing the JSON object.
 
-from langchain.schema import Document
+from langchain_core.documents import Document
 from langflow import CustomComponent
 from langflow.services.database.models.base import orjson_dumps
 

src/backend/langflow/components/utilities/PostRequest.py

@@ -1,9 +1,10 @@
-from langflow import CustomComponent
-from langchain.schema import Document
-from langflow.services.database.models.base import orjson_dumps
-import requests
 from typing import Optional
 
+import requests
+from langchain_core.documents import Document
+from langflow import CustomComponent
+from langflow.services.database.models.base import orjson_dumps
+
 
 class PostRequest(CustomComponent):
     display_name: str = "POST Request"

src/backend/langflow/components/utilities/UpdateRequest.py

@@ -1,7 +1,8 @@
 from typing import List, Optional
+
 import requests
+from langchain_core.documents import Document
 from langflow import CustomComponent
-from langchain.schema import Document
 from langflow.services.database.models.base import orjson_dumps
 
 

src/backend/langflow/components/vectorstores/Redis.py

@@ -1,9 +1,11 @@
-from typing import Optional
+from typing import Optional, Union
 
 from langchain.embeddings.base import Embeddings
-from langchain.schema import Document
 from langchain_community.vectorstores import VectorStore
 from langchain_community.vectorstores.redis import Redis
+from langchain_core.documents import Document
+from langchain_core.retrievers import BaseRetriever
+
 from langflow import CustomComponent
 
 
@@ -42,7 +44,7 @@ class RedisComponent(CustomComponent):
         redis_server_url: str,
         redis_index_name: str,
         documents: Optional[Document] = None,
-    ) -> VectorStore:
+    ) -> Union[VectorStore, BaseRetriever]:
         """
         Builds the Vector Store or BaseRetriever object.
 
@@ -55,10 +57,19 @@ class RedisComponent(CustomComponent):
         Returns:
         - VectorStore: The Vector Store object.
         """
-
-        return Redis.from_documents(
-            documents=documents,  # type: ignore
-            embedding=embedding,
-            redis_url=redis_server_url,
-            index_name=redis_index_name,
-        )
+        if documents is None:
+            redis_vs = Redis.from_existing_index(
+                embedding=embedding,
+                index_name=redis_index_name,
+                schema=None,
+                key_prefix=None,
+                redis_url=redis_server_url,
+            )
+        else:
+            redis_vs = Redis.from_documents(
+                documents=documents,  # type: ignore
+                embedding=embedding,
+                redis_url=redis_server_url,
+                index_name=redis_index_name,
+            )
+        return redis_vs

src/backend/langflow/components/vectorstores/Vectara.py

@@ -3,11 +3,12 @@ import urllib
 import urllib.request
 from typing import List, Optional, Union
 
-from langchain.embeddings import FakeEmbeddings
-from langchain.schema import BaseRetriever, Document
-from langchain_community.vectorstores import Vectara, VectorStore
+from langchain_community.embeddings import FakeEmbeddings
+from langchain_community.vectorstores.vectara import Vectara
+from langchain_core.vectorstores import VectorStore
 
 from langflow import CustomComponent
+from langflow.field_typing import BaseRetriever, Document
 
 
 class VectaraComponent(CustomComponent):
@@ -18,25 +19,18 @@ class VectaraComponent(CustomComponent):
     field_config = {
         "vectara_customer_id": {
             "display_name": "Vectara Customer ID",
-            "required": True,
         },
         "vectara_corpus_id": {
             "display_name": "Vectara Corpus ID",
-            "required": True,
         },
         "vectara_api_key": {
             "display_name": "Vectara API Key",
             "password": True,
-            "required": True,
-        },
-        "code": {"show": False},
-        "documents": {
-            "display_name": "Documents",
-            "info": "Pass in either for Self Query Retriever or for making a Vectara Object",
         },
+        "documents": {"display_name": "Documents", "info": "If provided, will be upserted to corpus (optional)"},
         "files_url": {
             "display_name": "Files Url",
-            "info": "Make vectara object using url of files(documents not needed)",
+            "info": "Make vectara object using url of files (optional)",
         },
     }
 
@@ -48,6 +42,8 @@ class VectaraComponent(CustomComponent):
         files_url: Optional[List[str]] = None,
         documents: Optional[Document] = None,
     ) -> Union[VectorStore, BaseRetriever]:
+        source = "Langflow"
+
         if documents is not None:
             return Vectara.from_documents(
                 documents=documents,
@@ -55,6 +51,7 @@ class VectaraComponent(CustomComponent):
                 vectara_customer_id=vectara_customer_id,
                 vectara_corpus_id=vectara_corpus_id,
                 vectara_api_key=vectara_api_key,
+                source=source,
             )
 
         if files_url is not None:
@@ -70,10 +67,12 @@ class VectaraComponent(CustomComponent):
                 vectara_customer_id=vectara_customer_id,
                 vectara_corpus_id=vectara_corpus_id,
                 vectara_api_key=vectara_api_key,
+                source=source,
             )
 
         return Vectara(
             vectara_customer_id=vectara_customer_id,
             vectara_corpus_id=vectara_corpus_id,
             vectara_api_key=vectara_api_key,
+            source=source,
         )

src/backend/langflow/components/vectorstores/pgvector.py

@@ -1,13 +1,15 @@
-from typing import List, Optional
+from typing import Optional, Union
 
 from langchain.embeddings.base import Embeddings
-from langchain.schema import Document
 from langchain_community.vectorstores import VectorStore
 from langchain_community.vectorstores.pgvector import PGVector
+from langchain_core.documents import Document
+from langchain_core.retrievers import BaseRetriever
+
 from langflow import CustomComponent
 
 
-class PostgresqlVectorComponent(CustomComponent):
+class PGVectorComponent(CustomComponent):
     """
     A custom component for implementing a Vector Store using PostgreSQL.
     """
@@ -15,7 +17,6 @@ class PostgresqlVectorComponent(CustomComponent):
     display_name: str = "PGVector"
     description: str = "Implementation of Vector Store using PostgreSQL"
     documentation = "https://python.langchain.com/docs/integrations/vectorstores/pgvector"
-    beta = True
 
     def build_config(self):
         """
@@ -25,8 +26,7 @@ class PostgresqlVectorComponent(CustomComponent):
         - dict: A dictionary containing the configuration options for the component.
         """
         return {
-            "index_name": {"display_name": "Index Name", "value": "your_index"},
-            "code": {"show": True, "display_name": "Code"},
+            "code": {"show": False},
             "documents": {"display_name": "Documents", "is_list": True},
             "embedding": {"display_name": "Embedding"},
             "pg_server_url": {
@@ -41,8 +41,8 @@ class PostgresqlVectorComponent(CustomComponent):
         embedding: Embeddings,
         pg_server_url: str,
         collection_name: str,
-        documents: Optional[List[Document]] = None,
-    ) -> VectorStore:
+        documents: Optional[Document] = None,
+    ) -> Union[VectorStore, BaseRetriever]:
         """
         Builds the Vector Store or BaseRetriever object.
 
@@ -58,13 +58,13 @@ class PostgresqlVectorComponent(CustomComponent):
 
         try:
             if documents is None:
-                return PGVector.from_existing_index(
+                vector_store = PGVector.from_existing_index(
                     embedding=embedding,
                     collection_name=collection_name,
                     connection_string=pg_server_url,
                 )
 
-            return PGVector.from_documents(
+            vector_store = PGVector.from_documents(
                 embedding=embedding,
                 documents=documents,
                 collection_name=collection_name,
@@ -72,3 +72,4 @@ class PostgresqlVectorComponent(CustomComponent):
             )
         except Exception as e:
             raise RuntimeError(f"Failed to build PGVector: {e}")
+        return vector_store

src/backend/langflow/config.yaml

@@ -174,6 +174,8 @@ prompts:
 textsplitters:
   CharacterTextSplitter:
     documentation: "https://python.langchain.com/docs/modules/data_connection/document_transformers/text_splitters/character_text_splitter"
+  RecursiveCharacterTextSplitter:
+    documentation: "https://python.langchain.com/docs/modules/data_connection/document_transformers/recursive_text_splitter"
 toolkits:
   OpenAPIToolkit:
     documentation: ""

src/backend/langflow/interface/custom/directory_reader/directory_reader.py

@@ -2,6 +2,7 @@ import ast
 import os
 import zlib
 
+from langflow.interface.custom.custom_component import CustomComponent
 from loguru import logger
 
 
@@ -245,9 +246,18 @@ class DirectoryReader:
             else:
                 component_name_camelcase = component_name
 
+            if validation_result:
+                try:
+                    output_types = self.get_output_types_from_code(result_content)
+                except Exception as exc:
+                    logger.exception(f"Error while getting output types from code: {str(exc)}")
+                    output_types = [component_name_camelcase]
+            else:
+                output_types = [component_name_camelcase]
+
             component_info = {
                 "name": "CustomComponent",
-                "output_types": [component_name_camelcase],
+                "output_types": output_types,
                 "file": filename,
                 "code": result_content if validation_result else "",
                 "error": "" if validation_result else result_content,
@@ -259,3 +269,13 @@ class DirectoryReader:
                 response["menu"].append(menu_result)
         logger.debug("-------------------- Component menu list built --------------------")
         return response
+
+    @staticmethod
+    def get_output_types_from_code(code: str) -> list:
+        """
+        Get the output types from the code.
+        """
+        custom_component = CustomComponent(code=code)
+        types_list = custom_component.get_function_entrypoint_return_type
+        # Get the name of types classes
+        return [type_.__name__ for type_ in types_list if hasattr(type_, "__name__")]

src/backend/langflow/interface/custom/utils.py

@@ -7,8 +7,6 @@ from typing import Any, Dict, List, Optional, Union
 from uuid import UUID
 
 from fastapi import HTTPException
-from loguru import logger
-
 from langflow.field_typing.range_spec import RangeSpec
 from langflow.interface.custom.code_parser.utils import extract_inner_type
 from langflow.interface.custom.custom_component import CustomComponent
@@ -21,6 +19,7 @@ from langflow.interface.importing.utils import eval_custom_component_code
 from langflow.template.field.base import TemplateField
 from langflow.template.frontend_node.custom_components import CustomComponentFrontendNode
 from langflow.utils.util import get_base_classes
+from loguru import logger
 
 
 def add_output_types(frontend_node: CustomComponentFrontendNode, return_types: List[str]):

src/backend/langflow/interface/initialize/loading.py

@@ -9,8 +9,8 @@ from langchain.agents.agent_toolkits.base import BaseToolkit
 from langchain.agents.tools import BaseTool
 from langchain.chains.base import Chain
 from langchain.document_loaders.base import BaseLoader
-from langchain.schema import Document
 from langchain_community.vectorstores import VectorStore
+from langchain_core.documents import Document
 from loguru import logger
 from pydantic import ValidationError
 

src/backend/langflow/interface/initialize/vector_store.py

@@ -2,7 +2,6 @@ import os
 from typing import Any, Callable, Dict, Type
 
 import orjson
-from langchain.schema import Document
 from langchain_community.vectorstores import (
     FAISS,
     Chroma,
@@ -13,6 +12,7 @@ from langchain_community.vectorstores import (
     SupabaseVectorStore,
     Weaviate,
 )
+from langchain_core.documents import Document
 
 
 def docs_in_params(params: dict) -> bool:

src/backend/langflow/services/auth/utils.py

@@ -7,6 +7,7 @@ from fastapi import Depends, HTTPException, Security, status
 from fastapi.security import APIKeyHeader, APIKeyQuery, OAuth2PasswordBearer
 from jose import JWTError, jwt
 from sqlmodel import Session
+from starlette.websockets import WebSocket
 
 from langflow.services.database.models.api_key.model import ApiKey
 from langflow.services.database.models.api_key.crud import check_key
@@ -130,6 +131,21 @@ async def get_current_user_by_jwt(
     return user
 
 
+async def get_current_user_for_websocket(
+    websocket: WebSocket,
+    db: Session = Depends(get_session),
+    query_param: str = Security(api_key_query),
+) -> Optional[User]:
+    token = websocket.query_params.get("token")
+    api_key = websocket.query_params.get("x-api-key")
+    if token:
+        return await get_current_user_by_jwt(token, db)
+    elif api_key:
+        return await api_key_security(api_key, query_param, db)
+    else:
+        return None
+
+
 def get_current_active_user(current_user: Annotated[User, Depends(get_current_user)]):
     if not current_user.is_active:
         raise HTTPException(status_code=400, detail="Inactive user")

src/backend/langflow/utils/constants.py

@@ -8,12 +8,12 @@ OPENAI_MODELS = [
     "text-ada-001",
 ]
 CHAT_OPENAI_MODELS = [
+    "gpt-4-turbo-preview",
+    "gpt-4-0125-preview",
     "gpt-4-1106-preview",
     "gpt-4-vision-preview",
-    "gpt-4",
-    "gpt-4-32k",
-    "gpt-3.5-turbo",
-    "gpt-3.5-turbo-16k",
+    "gpt-3.5-turbo-0125",
+    "gpt-3.5-turbo-1106",
 ]
 
 

src/backend/langflow/utils/util.py

@@ -1,14 +1,14 @@
-import re
-import inspect
 import importlib
+import inspect
+import re
 from functools import wraps
-from typing import List, Optional, Dict, Any, Union
+from typing import Any, Dict, List, Optional, Union
 
 from docstring_parser import parse
+from langchain_core.documents import Document
 
 from langflow.template.frontend_node.constants import FORCE_SHOW_FIELDS
 from langflow.utils import constants
-from langchain.schema import Document
 
 
 def remove_ansi_escape_codes(text):