refactor: Rename SplitContentComponent to SplitTextComponent and update related variables and descriptions

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

@@ -4,10 +4,12 @@ from .ExtractKeyFromData import ExtractKeyFromDataComponent
 from .FlowTool import FlowToolComponent
 from .Listen import ListenComponent
 from .ListFlows import ListFlowsComponent
+from .MergeData import MergeDataComponent
 from .Notify import NotifyComponent
 from .PythonFunction import PythonFunctionComponent
 from .RunFlow import RunFlowComponent
 from .RunnableExecutor import RunnableExecComponent
+from .SplitText import SplitTextComponent
 from .SQLExecutor import SQLExecutorComponent
 from .SubFlow import SubFlowComponent
 
@@ -21,10 +23,9 @@ __all__ = [
     "MergeDataComponent",
     "NotifyComponent",
     "PythonFunctionComponent",
-    "PythonFunctionComponent",
     "RunFlowComponent",
     "RunnableExecComponent",
+    "SplitTextComponent",
     "SQLExecutorComponent",
     "SubFlowComponent",
-    "SplitContentComponent",
 ]

src/backend/base/langflow/components/helpers/ParseData.py

@@ -11,9 +11,7 @@ class ParseDataComponent(Component):
     icon = "braces"
 
     inputs = [
-        HandleInput(
-            name="data", display_name="Data", info="The data to convert to text.", input_types=["Data"]
-        ),
+        HandleInput(name="data", display_name="Data", info="The data to convert to text.", input_types=["Data"]),
         MultilineInput(
             name="template",
             display_name="Template",

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

@@ -8,7 +8,6 @@ from langflow.inputs import MessageInput
 from langflow.template import Output
 
 
-
 class AmazonBedrockComponent(LCModelComponent):
     display_name: str = "Amazon Bedrock"
     description: str = "Generate text using Amazon Bedrock LLMs."

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

@@ -1,4 +1,3 @@
-
 from langchain_anthropic.chat_models import ChatAnthropic
 from pydantic.v1 import SecretStr
 
@@ -15,10 +14,7 @@ class AnthropicModelComponent(LCModelComponent):
     icon = "Anthropic"
 
     inputs = [
-        StrInput(
-            name="input_value",
-            display_name="Input",
-            input_types=["Text", "Data", "Prompt", "Message"]),
+        StrInput(name="input_value", display_name="Input", input_types=["Text", "Data", "Prompt", "Message"]),
         IntInput(
             name="max_tokens",
             display_name="Max Tokens",
@@ -30,7 +26,7 @@ class AnthropicModelComponent(LCModelComponent):
             display_name="Model Name",
             options=[
                 "claude-3-opus-20240229",
-                "claude-3-sonnet-20240229", 
+                "claude-3-sonnet-20240229",
                 "claude-3-haiku-20240307",
                 "claude-2.1",
                 "claude-2.0",
@@ -105,4 +101,3 @@ class AnthropicModelComponent(LCModelComponent):
             raise ValueError("Could not connect to Anthropic API.") from e
 
         return output
-    

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

@@ -6,6 +6,7 @@ from langflow.field_typing import BaseLanguageModel, Text
 from langflow.inputs import BoolInput, FloatInput, SecretStrInput, StrInput
 from langflow.template import Output
 
+
 class QianfanChatEndpointComponent(LCModelComponent):
     display_name: str = "Qianfan"
     description: str = "Generate text using Baidu Qianfan LLMs."
@@ -120,4 +121,4 @@ class QianfanChatEndpointComponent(LCModelComponent):
         except Exception as e:
             raise ValueError("Could not connect to Baidu Qianfan API.") from e
 
-        return output
+        return output

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

@@ -1,4 +1,3 @@
-
 from langchain_groq import ChatGroq
 from langflow.base.models.groq_constants import MODEL_NAMES
 from pydantic.v1 import SecretStr
@@ -8,6 +7,7 @@ from langflow.field_typing import BaseLanguageModel, Text
 from langflow.inputs import BoolInput, FloatInput, IntInput, SecretStrInput, StrInput, DropdownInput
 from langflow.template import Output
 
+
 class GroqModel(LCModelComponent):
     display_name: str = "Groq"
     description: str = "Generate text using Groq."

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

@@ -1,4 +1,3 @@
-
 from langchain_community.chat_models import ChatOllama
 from langflow.base.constants import STREAM_INFO_TEXT
 from langflow.base.models.model import LCModelComponent
@@ -6,6 +5,7 @@ from langflow.field_typing import BaseLanguageModel, Text
 from langflow.inputs import BoolInput, DictInput, DropdownInput, FloatInput, IntInput, StrInput
 from langflow.template import Output
 
+
 class ChatOllamaComponent(LCModelComponent):
     display_name = "Ollama"
     description = "Generate text using Ollama Local LLMs."

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

@@ -1,5 +1,4 @@
 from langflow.custom import Component
-from langflow.field_typing import Text
 from langflow.inputs import (
     StrInput,
     IntInput,
@@ -10,10 +9,10 @@ from langflow.inputs import (
 )
 from langflow.schema import Data
 from langflow.template import Output
-from langflow.field_typing import Embeddings
 
 from loguru import logger
 
+
 class AstraVectorStoreComponent(Component):
     display_name: str = "Astra DB Vector Store"
     description: str = "Implementation of Vector Store using Astra DB with search capabilities"

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

@@ -1,17 +1,15 @@
-from typing import Any, List, Optional, Tuple
+from typing import List
 
-from langchain_community.utilities.cassandra import SetupMode
 from langchain_community.vectorstores import Cassandra
-from langchain.embeddings.base import Embeddings
 from langchain.schema import BaseRetriever
 
 from langflow.custom import Component
-from langflow.field_typing import Embeddings, Text
 from langflow.schema import Data
 from langflow.inputs import BoolInput, IntInput, StrInput, HandleInput, DropdownInput
 from langflow.template import Output
 from langflow.helpers.data import docs_to_data
 
+
 class CassandraVectorStoreComponent(Component):
     display_name = "Cassandra"
     description = "Cassandra Vector Store with search capabilities"
@@ -19,24 +17,83 @@ class CassandraVectorStoreComponent(Component):
     icon = "Cassandra"
 
     inputs = [
-        StrInput(name="token", display_name="Token", info="Authentication token for accessing Cassandra on Astra DB.", password=True, required=True),
+        StrInput(
+            name="token",
+            display_name="Token",
+            info="Authentication token for accessing Cassandra on Astra DB.",
+            password=True,
+            required=True,
+        ),
         StrInput(name="database_id", display_name="Database ID", info="The Astra database ID.", required=True),
-        StrInput(name="table_name", display_name="Table Name", info="The name of the table where vectors will be stored.", required=True),
-        StrInput(name="keyspace", display_name="Keyspace", info="Optional key space within Astra DB. The keyspace should already be created.", advanced=True),
-        IntInput(name="ttl_seconds", display_name="TTL Seconds", info="Optional time-to-live for the added texts.", advanced=True),
-        IntInput(name="batch_size", display_name="Batch Size", info="Optional number of data to process in a single batch.", value=16, advanced=True),
-        StrInput(name="body_index_options", display_name="Body Index Options", info="Optional options used to create the body index.", advanced=True),
-        DropdownInput(name="setup_mode", display_name="Setup Mode", info="Configuration mode for setting up the Cassandra table, with options like 'Sync', 'Async', or 'Off'.", options=["Sync", "Async", "Off"], value="Sync", advanced=True),
+        StrInput(
+            name="table_name",
+            display_name="Table Name",
+            info="The name of the table where vectors will be stored.",
+            required=True,
+        ),
+        StrInput(
+            name="keyspace",
+            display_name="Keyspace",
+            info="Optional key space within Astra DB. The keyspace should already be created.",
+            advanced=True,
+        ),
+        IntInput(
+            name="ttl_seconds",
+            display_name="TTL Seconds",
+            info="Optional time-to-live for the added texts.",
+            advanced=True,
+        ),
+        IntInput(
+            name="batch_size",
+            display_name="Batch Size",
+            info="Optional number of data to process in a single batch.",
+            value=16,
+            advanced=True,
+        ),
+        StrInput(
+            name="body_index_options",
+            display_name="Body Index Options",
+            info="Optional options used to create the body index.",
+            advanced=True,
+        ),
+        DropdownInput(
+            name="setup_mode",
+            display_name="Setup Mode",
+            info="Configuration mode for setting up the Cassandra table, with options like 'Sync', 'Async', or 'Off'.",
+            options=["Sync", "Async", "Off"],
+            value="Sync",
+            advanced=True,
+        ),
         HandleInput(name="embedding", display_name="Embedding", input_types=["Embeddings"]),
-        HandleInput(name="vector_store_inputs", display_name="Vector Store Inputs", input_types=["Document", "Data"], is_list=True),
-        BoolInput(name="add_to_vector_store", display_name="Add to Vector Store", info="If true, the Vector Store Inputs will be added to the Vector Store."),
+        HandleInput(
+            name="vector_store_inputs",
+            display_name="Vector Store Inputs",
+            input_types=["Document", "Data"],
+            is_list=True,
+        ),
+        BoolInput(
+            name="add_to_vector_store",
+            display_name="Add to Vector Store",
+            info="If true, the Vector Store Inputs will be added to the Vector Store.",
+        ),
         StrInput(name="search_input", display_name="Search Input"),
-        IntInput(name="number_of_results", display_name="Number of Results", info="Number of results to return.", value=4, advanced=True),
+        IntInput(
+            name="number_of_results",
+            display_name="Number of Results",
+            info="Number of results to return.",
+            value=4,
+            advanced=True,
+        ),
     ]
 
     outputs = [
         Output(display_name="Vector Store", name="vector_store", method="build_vector_store", output_type=Cassandra),
-        Output(display_name="Base Retriever", name="base_retriever", method="build_base_retriever", output_type=BaseRetriever),
+        Output(
+            display_name="Base Retriever",
+            name="base_retriever",
+            method="build_base_retriever",
+            output_type=BaseRetriever,
+        ),
         Output(display_name="Search Results", name="search_results", method="search_documents"),
     ]
 

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

@@ -10,6 +10,7 @@ from langflow.inputs import BoolInput, IntInput, StrInput, HandleInput
 from langflow.template import Output
 from langflow.helpers.data import docs_to_data
 
+
 class CouchbaseVectorStoreComponent(Component):
     display_name = "Couchbase"
     description = "Couchbase Vector Store with search capabilities"
@@ -25,15 +26,40 @@ class CouchbaseVectorStoreComponent(Component):
         StrInput(name="collection_name", display_name="Collection Name", required=True),
         StrInput(name="index_name", display_name="Index Name", required=True),
         HandleInput(name="embedding", display_name="Embedding", input_types=["Embeddings"]),
-        HandleInput(name="vector_store_inputs", display_name="Vector Store Inputs", input_types=["Document", "Data"], is_list=True),
-        BoolInput(name="add_to_vector_store", display_name="Add to Vector Store", info="If true, the Vector Store Inputs will be added to the Vector Store."),
+        HandleInput(
+            name="vector_store_inputs",
+            display_name="Vector Store Inputs",
+            input_types=["Document", "Data"],
+            is_list=True,
+        ),
+        BoolInput(
+            name="add_to_vector_store",
+            display_name="Add to Vector Store",
+            info="If true, the Vector Store Inputs will be added to the Vector Store.",
+        ),
         StrInput(name="search_input", display_name="Search Input"),
-        IntInput(name="number_of_results", display_name="Number of Results", info="Number of results to return.", value=4, advanced=True),
+        IntInput(
+            name="number_of_results",
+            display_name="Number of Results",
+            info="Number of results to return.",
+            value=4,
+            advanced=True,
+        ),
     ]
 
     outputs = [
-        Output(display_name="Vector Store", name="vector_store", method="build_vector_store", output_type=CouchbaseVectorStore),
-        Output(display_name="Base Retriever", name="base_retriever", method="build_base_retriever", output_type=BaseRetriever),
+        Output(
+            display_name="Vector Store",
+            name="vector_store",
+            method="build_vector_store",
+            output_type=CouchbaseVectorStore,
+        ),
+        Output(
+            display_name="Base Retriever",
+            name="base_retriever",
+            method="build_base_retriever",
+            output_type=BaseRetriever,
+        ),
         Output(display_name="Search Results", name="search_results", method="search_documents"),
     ]
 

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

@@ -1,8 +1,6 @@
-from copy import deepcopy
-from typing import List, Optional, Union
+from typing import List
 
 from langchain.vectorstores import FAISS
-from langchain.embeddings.base import Embeddings
 from langchain.schema import BaseRetriever
 
 from langflow.custom import Component
@@ -36,9 +34,7 @@ class FaissVectorStoreComponent(Component):
             display_name="Index Name",
             value="langflow_index",
         ),
-        HandleInput(
-            name="embedding", display_name="Embedding", input_types=["Embeddings"]
-        ),
+        HandleInput(name="embedding", display_name="Embedding", input_types=["Embeddings"]),
         StrInput(
             name="vector_store_inputs",
             display_name="Vector Store Inputs",
@@ -163,11 +159,7 @@ class FaissVectorStoreComponent(Component):
         logger.debug(f"Search input: {self.search_input}")
         logger.debug(f"Number of results: {self.number_of_results}")
 
-        if (
-            self.search_input
-            and isinstance(self.search_input, str)
-            and self.search_input.strip()
-        ):
+        if self.search_input and isinstance(self.search_input, str) and self.search_input.strip():
             docs = vector_store.similarity_search(
                 query=self.search_input,
                 k=self.number_of_results,

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

@@ -9,6 +9,7 @@ from langflow.inputs import BoolInput, IntInput, StrInput, HandleInput
 from langflow.template import Output
 from langflow.helpers.data import docs_to_data
 
+
 class MongoVectorStoreComponent(Component):
     display_name = "MongoDB Atlas"
     description = "MongoDB Atlas Vector Store with search capabilities"
@@ -21,15 +22,40 @@ class MongoVectorStoreComponent(Component):
         StrInput(name="collection_name", display_name="Collection Name", required=True),
         StrInput(name="index_name", display_name="Index Name", required=True),
         HandleInput(name="embedding", display_name="Embedding", input_types=["Embeddings"]),
-        HandleInput(name="vector_store_inputs", display_name="Vector Store Inputs", input_types=["Document", "Data"], is_list=True),
-        BoolInput(name="add_to_vector_store", display_name="Add to Vector Store", info="If true, the Vector Store Inputs will be added to the Vector Store."),
+        HandleInput(
+            name="vector_store_inputs",
+            display_name="Vector Store Inputs",
+            input_types=["Document", "Data"],
+            is_list=True,
+        ),
+        BoolInput(
+            name="add_to_vector_store",
+            display_name="Add to Vector Store",
+            info="If true, the Vector Store Inputs will be added to the Vector Store.",
+        ),
         StrInput(name="search_input", display_name="Search Input"),
-        IntInput(name="number_of_results", display_name="Number of Results", info="Number of results to return.", value=4, advanced=True),
+        IntInput(
+            name="number_of_results",
+            display_name="Number of Results",
+            info="Number of results to return.",
+            value=4,
+            advanced=True,
+        ),
     ]
 
     outputs = [
-        Output(display_name="Vector Store", name="vector_store", method="build_vector_store", output_type=MongoDBAtlasVectorSearch),
-        Output(display_name="Base Retriever", name="base_retriever", method="build_base_retriever", output_type=BaseRetriever),
+        Output(
+            display_name="Vector Store",
+            name="vector_store",
+            method="build_vector_store",
+            output_type=MongoDBAtlasVectorSearch,
+        ),
+        Output(
+            display_name="Base Retriever",
+            name="base_retriever",
+            method="build_base_retriever",
+            output_type=BaseRetriever,
+        ),
         Output(display_name="Search Results", name="search_results", method="search_documents"),
     ]
 

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

@@ -9,6 +9,7 @@ from langflow.inputs import BoolInput, IntInput, StrInput, HandleInput, Dropdown
 from langflow.template import Output
 from langflow.helpers.data import docs_to_data
 
+
 class PineconeVectorStoreComponent(Component):
     display_name = "Pinecone"
     description = "Pinecone Vector Store with search capabilities"
@@ -18,19 +19,51 @@ class PineconeVectorStoreComponent(Component):
     inputs = [
         StrInput(name="index_name", display_name="Index Name", required=True),
         StrInput(name="namespace", display_name="Namespace", info="Namespace for the index."),
-        DropdownInput(name="distance_strategy", display_name="Distance Strategy", options=["Cosine", "Euclidean", "Dot Product"], value="Cosine", advanced=True),
+        DropdownInput(
+            name="distance_strategy",
+            display_name="Distance Strategy",
+            options=["Cosine", "Euclidean", "Dot Product"],
+            value="Cosine",
+            advanced=True,
+        ),
         StrInput(name="pinecone_api_key", display_name="Pinecone API Key", password=True, required=True),
         HandleInput(name="embedding", display_name="Embedding", input_types=["Embeddings"]),
-        StrInput(name="text_key", display_name="Text Key", info="Key in the record to use as text.", value="text", advanced=True),
-        HandleInput(name="vector_store_inputs", display_name="Vector Store Inputs", input_types=["Document", "Data"], is_list=True),
-        BoolInput(name="add_to_vector_store", display_name="Add to Vector Store", info="If true, the Vector Store Inputs will be added to the Vector Store."),
+        StrInput(
+            name="text_key",
+            display_name="Text Key",
+            info="Key in the record to use as text.",
+            value="text",
+            advanced=True,
+        ),
+        HandleInput(
+            name="vector_store_inputs",
+            display_name="Vector Store Inputs",
+            input_types=["Document", "Data"],
+            is_list=True,
+        ),
+        BoolInput(
+            name="add_to_vector_store",
+            display_name="Add to Vector Store",
+            info="If true, the Vector Store Inputs will be added to the Vector Store.",
+        ),
         StrInput(name="search_input", display_name="Search Input"),
-        IntInput(name="number_of_results", display_name="Number of Results", info="Number of results to return.", value=4, advanced=True),
+        IntInput(
+            name="number_of_results",
+            display_name="Number of Results",
+            info="Number of results to return.",
+            value=4,
+            advanced=True,
+        ),
     ]
 
     outputs = [
         Output(display_name="Vector Store", name="vector_store", method="build_vector_store", output_type=Pinecone),
-        Output(display_name="Base Retriever", name="base_retriever", method="build_base_retriever", output_type=BaseRetriever),
+        Output(
+            display_name="Base Retriever",
+            name="base_retriever",
+            method="build_base_retriever",
+            output_type=BaseRetriever,
+        ),
         Output(display_name="Search Results", name="search_results", method="search_documents"),
     ]
 

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

@@ -9,6 +9,7 @@ from langflow.inputs import BoolInput, IntInput, StrInput, HandleInput, Dropdown
 from langflow.template import Output
 from langflow.helpers.data import docs_to_data
 
+
 class QdrantVectorStoreComponent(Component):
     display_name = "Qdrant"
     description = "Qdrant Vector Store with search capabilities"
@@ -25,19 +26,45 @@ class QdrantVectorStoreComponent(Component):
         IntInput(name="timeout", display_name="Timeout", advanced=True),
         StrInput(name="path", display_name="Path", advanced=True),
         StrInput(name="url", display_name="URL", advanced=True),
-        DropdownInput(name="distance_func", display_name="Distance Function", options=["Cosine", "Euclidean", "Dot Product"], value="Cosine", advanced=True),
+        DropdownInput(
+            name="distance_func",
+            display_name="Distance Function",
+            options=["Cosine", "Euclidean", "Dot Product"],
+            value="Cosine",
+            advanced=True,
+        ),
         StrInput(name="content_payload_key", display_name="Content Payload Key", value="page_content", advanced=True),
         StrInput(name="metadata_payload_key", display_name="Metadata Payload Key", value="metadata", advanced=True),
         HandleInput(name="embedding", display_name="Embedding", input_types=["Embeddings"]),
-        HandleInput(name="vector_store_inputs", display_name="Vector Store Inputs", input_types=["Document", "Data"], is_list=True),
-        BoolInput(name="add_to_vector_store", display_name="Add to Vector Store", info="If true, the Vector Store Inputs will be added to the Vector Store."),
+        HandleInput(
+            name="vector_store_inputs",
+            display_name="Vector Store Inputs",
+            input_types=["Document", "Data"],
+            is_list=True,
+        ),
+        BoolInput(
+            name="add_to_vector_store",
+            display_name="Add to Vector Store",
+            info="If true, the Vector Store Inputs will be added to the Vector Store.",
+        ),
         StrInput(name="search_input", display_name="Search Input"),
-        IntInput(name="number_of_results", display_name="Number of Results", info="Number of results to return.", value=4, advanced=True),
+        IntInput(
+            name="number_of_results",
+            display_name="Number of Results",
+            info="Number of results to return.",
+            value=4,
+            advanced=True,
+        ),
     ]
 
     outputs = [
         Output(display_name="Vector Store", name="vector_store", method="build_vector_store", output_type=Qdrant),
-        Output(display_name="Base Retriever", name="base_retriever", method="build_base_retriever", output_type=BaseRetriever),
+        Output(
+            display_name="Base Retriever",
+            name="base_retriever",
+            method="build_base_retriever",
+            output_type=BaseRetriever,
+        ),
         Output(display_name="Search Results", name="search_results", method="search_documents"),
     ]
 
@@ -79,10 +106,7 @@ class QdrantVectorStoreComponent(Component):
 
             if documents:
                 qdrant = Qdrant.from_documents(
-                    documents,
-                    embedding=self.embedding,
-                    client_kwargs=server_kwargs,
-                    **qdrant_kwargs
+                    documents, embedding=self.embedding, client_kwargs=server_kwargs, **qdrant_kwargs
                 )
             else:
                 from qdrant_client import QdrantClient

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

@@ -10,6 +10,7 @@ from langflow.inputs import IntInput, StrInput, HandleInput
 from langflow.template import Output
 from langflow.helpers.data import docs_to_data
 
+
 class SupabaseVectorStoreComponent(Component):
     display_name = "Supabase"
     description = "Supabase Vector Store with search capabilities"
@@ -22,14 +23,35 @@ class SupabaseVectorStoreComponent(Component):
         StrInput(name="table_name", display_name="Table Name", advanced=True),
         StrInput(name="query_name", display_name="Query Name"),
         HandleInput(name="embedding", display_name="Embedding", input_types=["Embeddings"]),
-        HandleInput(name="vector_store_inputs", display_name="Vector Store Inputs", input_types=["Document", "Data"], is_list=True),
+        HandleInput(
+            name="vector_store_inputs",
+            display_name="Vector Store Inputs",
+            input_types=["Document", "Data"],
+            is_list=True,
+        ),
         StrInput(name="search_input", display_name="Search Input"),
-        IntInput(name="number_of_results", display_name="Number of Results", info="Number of results to return.", value=4, advanced=True),
+        IntInput(
+            name="number_of_results",
+            display_name="Number of Results",
+            info="Number of results to return.",
+            value=4,
+            advanced=True,
+        ),
     ]
 
     outputs = [
-        Output(display_name="Vector Store", name="vector_store", method="build_vector_store", output_type=SupabaseVectorStore),
-        Output(display_name="Base Retriever", name="base_retriever", method="build_base_retriever", output_type=BaseRetriever),
+        Output(
+            display_name="Vector Store",
+            name="vector_store",
+            method="build_vector_store",
+            output_type=SupabaseVectorStore,
+        ),
+        Output(
+            display_name="Base Retriever",
+            name="base_retriever",
+            method="build_base_retriever",
+            output_type=BaseRetriever,
+        ),
         Output(display_name="Search Results", name="search_results", method="search_documents"),
     ]
 

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

@@ -9,6 +9,7 @@ from langflow.inputs import BoolInput, IntInput, StrInput, HandleInput
 from langflow.template import Output
 from langflow.helpers.data import docs_to_data
 
+
 class UpstashVectorStoreComponent(Component):
     display_name = "Upstash"
     description = "Upstash Vector Store with search capabilities"
@@ -17,18 +18,56 @@ class UpstashVectorStoreComponent(Component):
 
     inputs = [
         StrInput(name="index_url", display_name="Index URL", info="The URL of the Upstash index.", required=True),
-        StrInput(name="index_token", display_name="Index Token", info="The token for the Upstash index.", required=True),
-        StrInput(name="text_key", display_name="Text Key", info="The key in the record to use as text.", value="text", advanced=True),
-        HandleInput(name="embedding", display_name="Embedding", input_types=["Embeddings"], info="To use Upstash's embeddings, don't provide an embedding."),
-        HandleInput(name="vector_store_inputs", display_name="Vector Store Inputs", input_types=["Document", "Data"], is_list=True),
-        BoolInput(name="add_to_vector_store", display_name="Add to Vector Store", info="If true, the Vector Store Inputs will be added to the Vector Store."),
+        StrInput(
+            name="index_token", display_name="Index Token", info="The token for the Upstash index.", required=True
+        ),
+        StrInput(
+            name="text_key",
+            display_name="Text Key",
+            info="The key in the record to use as text.",
+            value="text",
+            advanced=True,
+        ),
+        HandleInput(
+            name="embedding",
+            display_name="Embedding",
+            input_types=["Embeddings"],
+            info="To use Upstash's embeddings, don't provide an embedding.",
+        ),
+        HandleInput(
+            name="vector_store_inputs",
+            display_name="Vector Store Inputs",
+            input_types=["Document", "Data"],
+            is_list=True,
+        ),
+        BoolInput(
+            name="add_to_vector_store",
+            display_name="Add to Vector Store",
+            info="If true, the Vector Store Inputs will be added to the Vector Store.",
+        ),
         StrInput(name="search_input", display_name="Search Input"),
-        IntInput(name="number_of_results", display_name="Number of Results", info="Number of results to return.", value=4, advanced=True),
+        IntInput(
+            name="number_of_results",
+            display_name="Number of Results",
+            info="Number of results to return.",
+            value=4,
+            advanced=True,
+        ),
     ]
 
     outputs = [
-        Output(display_name="Vector Store", name="vector_store", method="build_vector_store", output_type=UpstashVectorStore),
-        Output(display_name="Base Retriever", name="base_retriever", method="build_base_retriever", output_type=BaseRetriever),
+        Output(
+            display_name="Vector Store",
+            name="vector_store",
+            method="build_vector_store",
+            output_type=UpstashVectorStore,
+        ),
+        Output(
+            display_name="Base Retriever",
+            name="base_retriever",
+            method="build_base_retriever",
+            output_type=BaseRetriever,
+        ),
         Output(display_name="Search Results", name="search_results", method="search_documents"),
     ]
 

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

@@ -10,6 +10,7 @@ from langflow.inputs import BoolInput, IntInput, StrInput, HandleInput
 from langflow.template import Output
 from langflow.helpers.data import docs_to_data
 
+
 class VectaraVectorStoreComponent(Component):
     display_name = "Vectara"
     description = "Vectara Vector Store with search capabilities"
@@ -20,15 +21,35 @@ class VectaraVectorStoreComponent(Component):
         StrInput(name="vectara_customer_id", display_name="Vectara Customer ID", required=True),
         StrInput(name="vectara_corpus_id", display_name="Vectara Corpus ID", required=True),
         StrInput(name="vectara_api_key", display_name="Vectara API Key", password=True, required=True),
-        HandleInput(name="vector_store_inputs", display_name="Vector Store Inputs", input_types=["Document", "Data"], is_list=True),
-        BoolInput(name="add_to_vector_store", display_name="Add to Vector Store", info="If true, the Vector Store Inputs will be added to the Vector Store."),
+        HandleInput(
+            name="vector_store_inputs",
+            display_name="Vector Store Inputs",
+            input_types=["Document", "Data"],
+            is_list=True,
+        ),
+        BoolInput(
+            name="add_to_vector_store",
+            display_name="Add to Vector Store",
+            info="If true, the Vector Store Inputs will be added to the Vector Store.",
+        ),
         StrInput(name="search_input", display_name="Search Input"),
-        IntInput(name="number_of_results", display_name="Number of Results", info="Number of results to return.", value=4, advanced=True),
+        IntInput(
+            name="number_of_results",
+            display_name="Number of Results",
+            info="Number of results to return.",
+            value=4,
+            advanced=True,
+        ),
     ]
 
     outputs = [
         Output(display_name="Vector Store", name="vector_store", method="build_vector_store", output_type=Vectara),
-        Output(display_name="Base Retriever", name="base_retriever", method="build_base_retriever", output_type=BaseRetriever),
+        Output(
+            display_name="Base Retriever",
+            name="base_retriever",
+            method="build_base_retriever",
+            output_type=BaseRetriever,
+        ),
         Output(display_name="Search Results", name="search_results", method="search_documents"),
     ]
 

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

@@ -10,6 +10,7 @@ from langflow.inputs import BoolInput, IntInput, StrInput, HandleInput
 from langflow.template import Output
 from langflow.helpers.data import docs_to_data
 
+
 class WeaviateVectorStoreComponent(Component):
     display_name = "Weaviate"
     description = "Weaviate Vector Store with search capabilities"
@@ -22,16 +23,36 @@ class WeaviateVectorStoreComponent(Component):
         StrInput(name="index_name", display_name="Index Name", required=True),
         StrInput(name="text_key", display_name="Text Key", value="text", advanced=True),
         HandleInput(name="embedding", display_name="Embedding", input_types=["Embeddings"]),
-        HandleInput(name="vector_store_inputs", display_name="Vector Store Inputs", input_types=["Document", "Data"], is_list=True),
-        BoolInput(name="add_to_vector_store", display_name="Add to Vector Store", info="If true, the Vector Store Inputs will be added to the Vector Store."),
+        HandleInput(
+            name="vector_store_inputs",
+            display_name="Vector Store Inputs",
+            input_types=["Document", "Data"],
+            is_list=True,
+        ),
+        BoolInput(
+            name="add_to_vector_store",
+            display_name="Add to Vector Store",
+            info="If true, the Vector Store Inputs will be added to the Vector Store.",
+        ),
         StrInput(name="search_input", display_name="Search Input"),
-        IntInput(name="number_of_results", display_name="Number of Results", info="Number of results to return.", value=4, advanced=True),
+        IntInput(
+            name="number_of_results",
+            display_name="Number of Results",
+            info="Number of results to return.",
+            value=4,
+            advanced=True,
+        ),
         BoolInput(name="search_by_text", display_name="Search By Text", advanced=True),
     ]
 
     outputs = [
         Output(display_name="Vector Store", name="vector_store", method="build_vector_store", output_type=Weaviate),
-        Output(display_name="Base Retriever", name="base_retriever", method="build_base_retriever", output_type=BaseRetriever),
+        Output(
+            display_name="Base Retriever",
+            name="base_retriever",
+            method="build_base_retriever",
+            output_type=BaseRetriever,
+        ),
         Output(display_name="Search Results", name="search_results", method="search_documents"),
     ]
 

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

@@ -9,6 +9,7 @@ from langflow.inputs import BoolInput, IntInput, StrInput, HandleInput
 from langflow.template import Output
 from langflow.helpers.data import docs_to_data
 
+
 class PGVectorStoreComponent(Component):
     display_name = "PGVector"
     description = "PGVector Vector Store with search capabilities"
@@ -19,15 +20,35 @@ class PGVectorStoreComponent(Component):
         StrInput(name="pg_server_url", display_name="PostgreSQL Server Connection String", required=True),
         StrInput(name="collection_name", display_name="Table", required=True),
         HandleInput(name="embedding", display_name="Embedding", input_types=["Embeddings"]),
-        HandleInput(name="vector_store_inputs", display_name="Vector Store Inputs", input_types=["Document", "Data"], is_list=True),
-        BoolInput(name="add_to_vector_store", display_name="Add to Vector Store", info="If true, the Vector Store Inputs will be added to the Vector Store."),
+        HandleInput(
+            name="vector_store_inputs",
+            display_name="Vector Store Inputs",
+            input_types=["Document", "Data"],
+            is_list=True,
+        ),
+        BoolInput(
+            name="add_to_vector_store",
+            display_name="Add to Vector Store",
+            info="If true, the Vector Store Inputs will be added to the Vector Store.",
+        ),
         StrInput(name="search_input", display_name="Search Input"),
-        IntInput(name="number_of_results", display_name="Number of Results", info="Number of results to return.", value=4, advanced=True),
+        IntInput(
+            name="number_of_results",
+            display_name="Number of Results",
+            info="Number of results to return.",
+            value=4,
+            advanced=True,
+        ),
     ]
 
     outputs = [
         Output(display_name="Vector Store", name="vector_store", method="build_vector_store", output_type=PGVector),
-        Output(display_name="Base Retriever", name="base_retriever", method="build_base_retriever", output_type=BaseRetriever),
+        Output(
+            display_name="Base Retriever",
+            name="base_retriever",
+            method="build_base_retriever",
+            output_type=BaseRetriever,
+        ),
         Output(display_name="Search Results", name="search_results", method="search_documents"),
     ]