Merge branch 'two_edges' of https://github.com/langflow-ai/langflow into two_edges

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

@@ -111,7 +111,7 @@ async def retrieve_vertices_order(
         run_id = uuid.uuid4()
         graph.set_run_id(run_id)
         vertices_to_run = list(graph.vertices_to_run) + get_top_level_vertices(graph, graph.vertices_to_run)
-        await chat_service.set_cache(flow_id, graph)
+        await chat_service.set_cache(str(flow_id), graph)
         return VerticesOrderResponse(ids=first_layer, run_id=run_id, vertices_to_run=vertices_to_run)
 
     except Exception as exc:

src/backend/base/langflow/base/models/model.py

@@ -3,7 +3,7 @@ import warnings
 from typing import Optional, Union
 
 from langchain_core.language_models.llms import LLM
-from langchain_core.messages import AIMessage, HumanMessage, SystemMessage
+from langchain_core.messages import AIMessage, BaseMessage, HumanMessage, SystemMessage
 
 from langflow.custom import Component
 from langflow.field_typing import LanguageModel
@@ -120,7 +120,7 @@ class LCModelComponent(Component):
     def get_chat_result(
         self, runnable: LanguageModel, stream: bool, input_value: str | Message, system_message: Optional[str] = None
     ):
-        messages: list[Union[HumanMessage, SystemMessage]] = []
+        messages: list[Union[BaseMessage]] = []
         if not input_value and not system_message:
             raise ValueError("The message you want to send to the model is empty.")
         if system_message:
@@ -136,7 +136,7 @@ class LCModelComponent(Component):
                         messages.append(input_value.to_lc_message())
             else:
                 messages.append(HumanMessage(content=input_value))
-        inputs = messages or {}
+        inputs: Union[list, dict] = messages or {}
         try:
             if stream:
                 return runnable.stream(inputs)

src/backend/base/langflow/components/embeddings/AmazonBedrockEmbeddings.py

@@ -1,9 +1,7 @@
-from typing import Optional
-
 from langchain_community.embeddings import BedrockEmbeddings
 from langflow.base.models.model import LCModelComponent
 from langflow.field_typing import Embeddings
-from langflow.io import DropdownInput, Output, SecretStrInput, TextInput
+from langflow.io import DropdownInput, Output, TextInput
 
 
 class AmazonBedrockEmbeddingsComponent(LCModelComponent):

src/backend/base/langflow/components/embeddings/AzureOpenAIEmbeddings.py

@@ -1,4 +1,3 @@
-from typing import Optional
 from langchain_openai import AzureOpenAIEmbeddings
 from pydantic.v1 import SecretStr
 

src/backend/base/langflow/components/embeddings/CohereEmbeddings.py

@@ -2,7 +2,7 @@ from langchain_community.embeddings.cohere import CohereEmbeddings
 
 from langflow.base.models.model import LCModelComponent
 from langflow.field_typing import Embeddings
-from langflow.io import BoolInput, DictInput, DropdownInput, FloatInput, IntInput, Output, SecretStrInput, TextInput
+from langflow.io import DropdownInput, FloatInput, IntInput, Output, SecretStrInput, TextInput
 
 
 class CohereEmbeddingsComponent(LCModelComponent):
@@ -34,7 +34,7 @@ class CohereEmbeddingsComponent(LCModelComponent):
     ]
 
     def build_embeddings(self) -> Embeddings:
-        return CohereEmbeddings(
+        return CohereEmbeddings(  # type: ignore
             cohere_api_key=self.cohere_api_key,
             model=self.model,
             truncate=self.truncate,

src/backend/base/langflow/components/embeddings/HuggingFaceEmbeddings.py

@@ -1,5 +1,3 @@
-from typing import Dict, Optional
-
 from langchain_community.embeddings.huggingface import HuggingFaceEmbeddings
 
 from langflow.base.models.model import LCModelComponent

src/backend/base/langflow/components/embeddings/HuggingFaceInferenceAPIEmbeddings.py

@@ -1,11 +1,9 @@
-from typing import Dict, Optional
-
 from langchain_community.embeddings.huggingface import HuggingFaceInferenceAPIEmbeddings
 from pydantic.v1.types import SecretStr
 
 from langflow.base.models.model import LCModelComponent
 from langflow.field_typing import Embeddings
-from langflow.io import BoolInput, DictInput, FloatInput, Output, SecretStrInput, TextInput
+from langflow.io import BoolInput, DictInput, Output, SecretStrInput, TextInput
 
 
 class HuggingFaceInferenceAPIEmbeddingsComponent(LCModelComponent):

src/backend/base/langflow/components/embeddings/OllamaEmbeddings.py

@@ -1,5 +1,3 @@
-from typing import Optional
-
 from langchain_community.embeddings import OllamaEmbeddings
 from langflow.base.models.model import LCModelComponent
 from langflow.field_typing import Embeddings

src/backend/base/langflow/components/embeddings/VertexAIEmbeddings.py

@@ -1,5 +1,3 @@
-from typing import List, Optional
-
 from langflow.base.models.model import LCModelComponent
 from langflow.field_typing import Embeddings
 from langflow.io import BoolInput, DictInput, FileInput, FloatInput, IntInput, Output, TextInput

src/backend/base/langflow/components/experimental/Embed.py

@@ -9,7 +9,7 @@ class EmbedComponent(CustomComponent):
     def build_config(self):
         return {"texts": {"display_name": "Texts"}, "embbedings": {"display_name": "Embeddings"}}
 
-    def build(self, texts: list[str], embbedings: Embeddings) -> Embeddings:
+    def build(self, texts: list[str], embbedings: Embeddings) -> Data:
         vectors = Data(vector=embbedings.embed_documents(texts))
         self.status = vectors
         return vectors

src/backend/base/langflow/components/model_specs/ChatAnthropicSpecs.py

@@ -1,86 +0,0 @@
-from typing import Optional
-
-from langchain_anthropic import ChatAnthropic
-from pydantic.v1.types import SecretStr
-
-from langflow.field_typing import LanguageModel
-
-
-class AnthropicLLM(CustomComponent):
-    display_name: str = "Anthropic"
-    description: str = "Generate text using Anthropic Chat&Completion LLMs."
-    icon = "Anthropic"
-
-    field_order = [
-        "model",
-        "anthropic_api_key",
-        "max_tokens",
-        "temperature",
-        "anthropic_api_url",
-    ]
-
-    def build_config(self):
-        return {
-            "model": {
-                "display_name": "Model Name",
-                "options": [
-                    "claude-3-opus-20240229",
-                    "claude-3-sonnet-20240229",
-                    "claude-3-haiku-20240307",
-                    "claude-2.1",
-                    "claude-2.0",
-                    "claude-instant-1.2",
-                    "claude-instant-1",
-                ],
-                "info": "Name of the model to use.",
-                "required": True,
-                "value": "claude-3-opus-20240229",
-            },
-            "anthropic_api_key": {
-                "display_name": "Anthropic API Key",
-                "required": True,
-                "password": True,
-                "info": "Your Anthropic API key.",
-            },
-            "max_tokens": {
-                "display_name": "Max Tokens",
-                "advanced": True,
-                "info": "The maximum number of tokens to generate. Set to 0 for unlimited tokens.",
-            },
-            "temperature": {
-                "display_name": "Temperature",
-                "field_type": "float",
-                "value": 0.1,
-            },
-            "anthropic_api_url": {
-                "display_name": "Anthropic API URL",
-                "advanced": True,
-                "info": "Endpoint of the Anthropic API. Defaults to 'https://api.anthropic.com' if not specified.",
-            },
-            "code": {"show": False},
-        }
-
-    def build(
-        self,
-        model: str,
-        anthropic_api_key: Optional[str] = None,
-        max_tokens: Optional[int] = 1000,
-        temperature: Optional[float] = None,
-        anthropic_api_url: Optional[str] = None,
-    ) -> LanguageModel:
-        # Set default API endpoint if not provided
-        if not anthropic_api_url:
-            anthropic_api_url = "https://api.anthropic.com"
-
-        try:
-            output = ChatAnthropic(
-                model_name=model,
-                anthropic_api_key=(SecretStr(anthropic_api_key) if anthropic_api_key else None),
-                max_tokens_to_sample=max_tokens,  # type: ignore
-                temperature=temperature,
-                anthropic_api_url=anthropic_api_url,
-            )
-        except Exception as e:
-            raise ValueError("Could not connect to Anthropic API.") from e
-
-        return output

src/backend/base/langflow/components/models/AmazonBedrockModel.py

@@ -2,7 +2,7 @@ from langchain_aws import ChatBedrock
 
 from langflow.base.constants import STREAM_INFO_TEXT
 from langflow.base.models.model import LCModelComponent
-from langflow.field_typing import LanguageModel, Text
+from langflow.field_typing import LanguageModel
 from langflow.io import BoolInput, DictInput, DropdownInput, MessageInput, Output, StrInput
 
 
@@ -78,7 +78,7 @@ class AmazonBedrockComponent(LCModelComponent):
         cache = self.cache
         stream = self.stream
         try:
-            output = ChatBedrock(
+            output = ChatBedrock(  # type: ignore
                 credentials_profile_name=credentials_profile_name,
                 model_id=model_id,
                 region_name=region_name,

src/backend/base/langflow/components/models/AnthropicModel.py

@@ -98,9 +98,9 @@ class AnthropicModelComponent(LCModelComponent):
         try:
             from anthropic import BadRequestError
         except ImportError:
-            return
+            return None
         if isinstance(exception, BadRequestError):
             message = exception.body.get("error", {}).get("message")  # type: ignore
             if message:
                 return message
-        return
+        return None

src/backend/base/langflow/components/models/AzureOpenAIModel.py

@@ -3,7 +3,7 @@ from pydantic.v1 import SecretStr
 
 from langflow.base.constants import STREAM_INFO_TEXT
 from langflow.base.models.model import LCModelComponent
-from langflow.field_typing import LanguageModel, Text
+from langflow.field_typing import LanguageModel
 from langflow.io import BoolInput, DropdownInput, FloatInput, IntInput, MessageInput, Output, SecretStrInput, StrInput
 
 

src/backend/base/langflow/components/models/GoogleGenerativeAIModel.py

@@ -2,7 +2,7 @@ from pydantic.v1 import SecretStr
 
 from langflow.base.constants import STREAM_INFO_TEXT
 from langflow.base.models.model import LCModelComponent
-from langflow.field_typing import LanguageModel, Text
+from langflow.field_typing import LanguageModel
 from langflow.io import BoolInput, DropdownInput, FloatInput, IntInput, MessageInput, Output, SecretStrInput, StrInput
 
 

src/backend/base/langflow/components/models/HuggingFaceModel.py

@@ -43,7 +43,7 @@ class HuggingFaceEndpointsComponent(LCModelComponent):
         model_kwargs = self.model_kwargs or {}
 
         try:
-            llm = HuggingFaceEndpoint(
+            llm = HuggingFaceEndpoint(  # type: ignore
                 endpoint_url=endpoint_url,
                 task=task,
                 huggingfacehub_api_token=huggingfacehub_api_token,

src/backend/base/langflow/components/models/OpenAIModel.py

@@ -82,25 +82,26 @@ class OpenAIModelComponent(LCModelComponent):
         temperature = self.temperature
         model_name: str = self.model_name
         max_tokens = self.max_tokens
-        model_kwargs = self.model_kwargs
+        model_kwargs = self.model_kwargs or {}
         openai_api_base = self.openai_api_base or "https://api.openai.com/v1"
         json_mode = bool(output_schema_dict)
         seed = self.seed
+        model_kwargs["seed"] = seed
+
         if openai_api_key:
             api_key = SecretStr(openai_api_key)
         else:
             api_key = None
         output = ChatOpenAI(
             max_tokens=max_tokens or None,
-            model_kwargs=model_kwargs or {},
+            model_kwargs=model_kwargs,
             model=model_name,
             base_url=openai_api_base,
             api_key=api_key,
             temperature=temperature or 0.1,
-            seed=seed,
         )
         if json_mode:
-            output = output.with_structured_output(schema=output_schema_dict, method="json_mode")
+            output = output.with_structured_output(schema=output_schema_dict, method="json_mode")  # type: ignore
 
         return output
 

src/backend/base/langflow/components/models/VertexAiModel.py

@@ -1,5 +1,6 @@
 from langchain_google_vertexai import ChatVertexAI
 
+from langflow.base.constants import STREAM_INFO_TEXT
 from langflow.base.models.model import LCModelComponent
 from langflow.field_typing import LanguageModel
 from langflow.io import BoolInput, FileInput, FloatInput, IntInput, MessageInput, MultilineInput, Output, StrInput

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

@@ -47,7 +47,7 @@ class RecursiveCharacterTextSplitterComponent(Component):
         Split text into chunks of a specified length.
 
         Args:
-            separators (list[str]): The characters to split on.
+            separators (list[str] | None): The characters to split on.
             chunk_size (int): The maximum length of each chunk.
             chunk_overlap (int): The amount of overlap between chunks.
 
@@ -63,9 +63,9 @@ class RecursiveCharacterTextSplitterComponent(Component):
             self.separators = [unescape_string(x) for x in self.separators]
 
         # Make sure chunk_size and chunk_overlap are ints
-        if isinstance(self.chunk_size, str):
+        if self.chunk_size:
             self.chunk_size = int(self.chunk_size)
-        if isinstance(self.chunk_overlap, str):
+        if self.chunk_overlap:
             self.chunk_overlap = int(self.chunk_overlap)
         splitter = RecursiveCharacterTextSplitter(
             separators=self.separators,

src/backend/base/langflow/components/vectorstores/AstraDB.py

@@ -181,10 +181,6 @@ class AstraVectorStoreComponent(LCVectorStoreComponent):
         if self.add_to_vector_store:
             self._add_documents_to_vector_store(vector_store)
 
-        return vector_store
-
-    def build_base_retriever(self):
-        vector_store = self.build_vector_store()
         self.status = self._astradb_collection_to_data(vector_store.collection)
         return vector_store
 

src/backend/base/langflow/components/vectorstores/Cassandra.py

@@ -7,7 +7,6 @@ from langflow.custom import Component
 from langflow.helpers.data import docs_to_data
 from langflow.io import BoolInput, DropdownInput, HandleInput, IntInput, Output, SecretStrInput, StrInput
 from langflow.schema import Data
-from langflow.field_typing import Retriever
 
 
 class CassandraVectorStoreComponent(Component):
@@ -99,9 +98,6 @@ class CassandraVectorStoreComponent(Component):
     def build_vector_store(self) -> Cassandra:
         return self._build_cassandra()
 
-    def build_base_retriever(self) -> Retriever:
-        return self._build_cassandra()
-
     def _build_cassandra(self) -> Cassandra:
         try:
             import cassio

src/backend/base/langflow/components/vectorstores/Chroma.py

@@ -1,5 +1,5 @@
 from copy import deepcopy
-from typing import TYPE_CHECKING, List
+from typing import TYPE_CHECKING
 
 from chromadb.config import Settings
 from langchain_chroma.vectorstores import Chroma

src/backend/base/langflow/components/vectorstores/Couchbase.py

@@ -8,7 +8,6 @@ from langflow.custom import Component
 from langflow.helpers.data import docs_to_data
 from langflow.io import BoolInput, HandleInput, IntInput, Output, SecretStrInput, StrInput
 from langflow.schema import Data
-from langflow.field_typing import Retriever
 
 
 class CouchbaseVectorStoreComponent(Component):
@@ -66,9 +65,6 @@ class CouchbaseVectorStoreComponent(Component):
     def build_vector_store(self) -> CouchbaseVectorStore:
         return self._build_couchbase()
 
-    def build_base_retriever(self) -> Retriever:
-        return self._build_couchbase()
-
     def _build_couchbase(self) -> CouchbaseVectorStore:
         try:
             from couchbase.auth import PasswordAuthenticator  # type: ignore

src/backend/base/langflow/components/vectorstores/MongoDBAtlasVector.py

@@ -8,8 +8,6 @@ from langflow.helpers.data import docs_to_data
 from langflow.io import BoolInput, HandleInput, IntInput, Output, StrInput
 from langflow.schema import Data
 
-from langflow.field_typing import Retriever
-
 
 class MongoVectorStoreComponent(Component):
     display_name = "MongoDB Atlas"
@@ -63,9 +61,6 @@ class MongoVectorStoreComponent(Component):
     def build_vector_store(self) -> MongoDBAtlasVectorSearch:
         return self._build_mongodb_atlas()
 
-    def build_base_retriever(self) -> Retriever:
-        return self._build_mongodb_atlas()
-
     def _build_mongodb_atlas(self) -> MongoDBAtlasVectorSearch:
         try:
             from pymongo import MongoClient

src/backend/base/langflow/components/vectorstores/Pinecone.py

@@ -70,9 +70,6 @@ class PineconeVectorStoreComponent(Component):
     def build_vector_store(self) -> Pinecone:
         return self._build_pinecone()
 
-    def build_base_retriever(self) -> Retriever:
-        return self._build_pinecone()
-
     def _build_pinecone(self) -> Pinecone:
         from langchain_pinecone._utilities import DistanceStrategy
         from langchain_pinecone.vectorstores import Pinecone

src/backend/base/langflow/components/vectorstores/Qdrant.py

@@ -4,7 +4,6 @@ from langchain_community.vectorstores import Qdrant
 from langchain_core.retrievers import BaseRetriever
 
 from langflow.custom import Component
-from langflow.field_typing import Retriever
 from langflow.helpers.data import docs_to_data
 from langflow.io import BoolInput, DropdownInput, HandleInput, IntInput, Output, SecretStrInput, StrInput
 from langflow.schema import Data
@@ -71,9 +70,6 @@ class QdrantVectorStoreComponent(Component):
     def build_vector_store(self) -> Qdrant:
         return self._build_qdrant()
 
-    def build_base_retriever(self) -> Retriever:
-        return self._build_qdrant()
-
     def _build_qdrant(self) -> Qdrant:
         qdrant_kwargs = {
             "collection_name": self.collection_name,

src/backend/base/langflow/components/vectorstores/SupabaseVectorStore.py

@@ -5,7 +5,6 @@ from langchain_core.retrievers import BaseRetriever
 from supabase.client import Client, create_client
 
 from langflow.custom import Component
-from langflow.field_typing import Retriever
 from langflow.helpers.data import docs_to_data
 from langflow.io import HandleInput, IntInput, Output, StrInput
 from langflow.schema import Data
@@ -58,9 +57,6 @@ class SupabaseVectorStoreComponent(Component):
     def build_vector_store(self) -> SupabaseVectorStore:
         return self._build_supabase()
 
-    def build_base_retriever(self) -> Retriever:
-        return self._build_supabase()
-
     def _build_supabase(self) -> SupabaseVectorStore:
         supabase: Client = create_client(self.supabase_url, supabase_key=self.supabase_service_key)
 

src/backend/base/langflow/components/vectorstores/Upstash.py

@@ -4,7 +4,6 @@ from langchain_community.vectorstores import UpstashVectorStore
 from langchain_core.retrievers import BaseRetriever
 
 from langflow.custom import Component
-from langflow.field_typing import Retriever
 from langflow.helpers.data import docs_to_data
 from langflow.io import BoolInput, HandleInput, IntInput, Output, StrInput
 from langflow.schema import Data
@@ -74,9 +73,6 @@ class UpstashVectorStoreComponent(Component):
     def build_vector_store(self) -> UpstashVectorStore:
         return self._build_upstash()
 
-    def build_base_retriever(self) -> Retriever:
-        return self._build_upstash()
-
     def _build_upstash(self) -> UpstashVectorStore:
         use_upstash_embedding = self.embedding is None
 

src/backend/base/langflow/components/vectorstores/Weaviate.py

@@ -5,7 +5,6 @@ from langchain_community.vectorstores import Weaviate
 from langchain_core.retrievers import BaseRetriever
 
 from langflow.custom import Component
-from langflow.field_typing import Retriever
 from langflow.helpers.data import docs_to_data
 from langflow.io import BoolInput, HandleInput, IntInput, Output, SecretStrInput, StrInput
 from langflow.schema import Data
@@ -59,9 +58,6 @@ class WeaviateVectorStoreComponent(Component):
     def build_vector_store(self) -> Weaviate:
         return self._build_weaviate()
 
-    def build_base_retriever(self) -> Retriever:
-        return self._build_weaviate()
-
     def _build_weaviate(self) -> Weaviate:
         if self.api_key:
             auth_config = weaviate.AuthApiKey(api_key=self.api_key)

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

@@ -8,8 +8,6 @@ from langflow.helpers.data import docs_to_data
 from langflow.io import BoolInput, HandleInput, IntInput, Output, StrInput
 from langflow.schema import Data
 
-from langflow.field_typing import Retriever
-
 
 class PGVectorStoreComponent(Component):
     display_name = "PGVector"
@@ -56,9 +54,6 @@ class PGVectorStoreComponent(Component):
     def build_vector_store(self) -> PGVector:
         return self._build_pgvector()
 
-    def build_base_retriever(self) -> Retriever:
-        return self._build_pgvector()
-
     def _build_pgvector(self) -> PGVector:
         if self.add_to_vector_store:
             documents = []

src/backend/base/langflow/graph/graph/base.py

@@ -6,7 +6,6 @@ from itertools import chain
 from typing import TYPE_CHECKING, Dict, Generator, List, Optional, Tuple, Type, Union
 from loguru import logger
 
-from langflow.exceptions.component import ComponentBuildException
 from langflow.exceptions.component import ComponentBuildException
 from langflow.graph.edge.base import ContractEdge
 from langflow.graph.graph.constants import lazy_load_vertex_dict

src/backend/base/langflow/graph/vertex/base.py

@@ -198,8 +198,8 @@ class Vertex:
         self.description: str = self.data["node"].get("description", "")
         self.frozen: bool = self.data["node"].get("frozen", False)
 
-        self.is_input: bool = self.data["node"].get("is_input") or self.is_input
-        self.is_output: bool = self.data["node"].get("is_output") or self.is_output
+        self.is_input = self.data["node"].get("is_input") or self.is_input
+        self.is_output = self.data["node"].get("is_output") or self.is_output
         template_dicts = {key: value for key, value in self.data["node"]["template"].items() if isinstance(value, dict)}
 
         self.has_session_id = "session_id" in template_dicts

src/backend/base/langflow/schema/data.py

@@ -106,8 +106,9 @@ class Data(BaseModel):
         Returns:
             Document: The converted Document.
         """
-        text = self.data.pop(self.text_key, self.default_value)
-        return Document(page_content=text, metadata=self.data)
+        data_copy = self.data.copy()
+        text = data_copy.pop(self.text_key, self.default_value)
+        return Document(page_content=text, metadata=data_copy)
 
     def to_lc_message(
         self,

src/backend/base/langflow/schema/message.py

@@ -1,5 +1,5 @@
 from datetime import datetime, timezone
-from typing import Annotated, Any, AsyncIterator, Iterator, Optional
+from typing import Annotated, Any, AsyncIterator, Iterator, Optional, List
 
 from fastapi.encoders import jsonable_encoder
 from langchain_core.load import load
@@ -42,7 +42,7 @@ class Message(Data):
         return value
 
     def model_post_init(self, __context: Any) -> None:
-        new_files = []
+        new_files: List[Any] = []
         for file in self.files or []:
             if is_image_file(file):
                 new_files.append(Image(path=file))

src/backend/base/langflow/template/template/base.py

@@ -1,4 +1,4 @@
-from typing import Callable, Union
+from typing import Callable, Union, cast
 
 from pydantic import BaseModel, Field, model_serializer
 
@@ -9,7 +9,7 @@ from langflow.utils.constants import DIRECT_TYPES
 
 class Template(BaseModel):
     type_name: str = Field(serialization_alias="_type")
-    fields: list[Input | InputTypes]
+    fields: list[Union[Input, InputTypes]]
 
     def process_fields(
         self,
@@ -49,7 +49,7 @@ class Template(BaseModel):
         field = next((field for field in self.fields if field.name == field_name), None)
         if field is None:
             raise ValueError(f"Field {field_name} not found in template {self.type_name}")
-        return field
+        return cast(Input, field)
 
     def update_field(self, field_name: str, field: Input) -> None:
         """Updates the field with the given name."""