feat: tool mode for all vector store components (#5348)

* feat: tool mode for all vector store components

* [autofix.ci] apply automated fixes

* [autofix.ci] apply automated fixes (attempt 2/3)

* Update elasticsearch.py

* Update test_vector_store_rag.py

* Update vector_store_rag.py

---------

Co-authored-by: autofix-ci[bot] <114827586+autofix-ci[bot]@users.noreply.github.com>

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

@@ -2,12 +2,10 @@ from abc import abstractmethod
 from functools import wraps
 from typing import TYPE_CHECKING
 
-from loguru import logger
-
 from langflow.custom import Component
 from langflow.field_typing import Text, VectorStore
 from langflow.helpers.data import docs_to_data
-from langflow.io import Output
+from langflow.io import DataInput, MultilineInput, Output
 from langflow.schema import Data
 
 if TYPE_CHECKING:
@@ -53,6 +51,19 @@ class LCVectorStoreComponent(Component):
                 raise TypeError(msg)
 
     trace_type = "retriever"
+
+    inputs = [
+        MultilineInput(
+            name="search_query",
+            display_name="Search Query",
+            tool_mode=True,
+        ),
+        DataInput(
+            name="ingest_data",
+            display_name="Ingest Data",
+        ),
+    ]
+
     outputs = [
         Output(
             display_name="Search Results",
@@ -122,9 +133,9 @@ class LCVectorStoreComponent(Component):
             vector_store = self.build_vector_store()
             self._cached_vector_store = vector_store
 
-        logger.debug(f"Search input: {search_query}")
+        self.log(f"Search input: {search_query}")
-        logger.debug(f"Search type: {self.search_type}")
+        self.log(f"Search type: {self.search_type}")
-        logger.debug(f"Number of results: {self.number_of_results}")
+        self.log(f"Number of results: {self.number_of_results}")
 
         search_results = self.search_with_vector_store(
             search_query, self.search_type, vector_store, k=self.number_of_results

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

@@ -1,7 +1,7 @@
 import os
 from collections import defaultdict
 
-from astrapy import DataAPIClient
+from astrapy import AstraDBAdmin, DataAPIClient
 from astrapy.admin import parse_api_endpoint
 from langchain_astradb import AstraDBVectorStore
 
@@ -14,7 +14,6 @@ from langflow.io import (
     DropdownInput,
     HandleInput,
     IntInput,
-    MultilineInput,
     SecretStrInput,
     StrInput,
 )
@@ -24,52 +23,29 @@ from langflow.utils.version import get_version_info
 
 class AstraDBVectorStoreComponent(LCVectorStoreComponent):
     display_name: str = "Astra DB"
-    description: str = "Implementation of Vector Store using Astra DB with search capabilities"
+    description: str = "Ingest and search documents in Astra DB"
-    documentation: str = "https://docs.langflow.org/starter-projects-vector-store-rag"
+    documentation: str = "https://docs.datastax.com/en/langflow/astra-components.html"
     name = "AstraDB"
     icon: str = "AstraDB"
 
     _cached_vector_store: AstraDBVectorStore | None = None
 
-    VECTORIZE_PROVIDERS_MAPPING = defaultdict(
+    base_inputs = LCVectorStoreComponent.inputs
-        list,
+    if "search_query" not in [input_.name for input_ in base_inputs]:
-        {
+        base_inputs.append(
-            "Azure OpenAI": [
+            MessageTextInput(
-                "azureOpenAI",
+                name="search_query",
-                ["text-embedding-3-small", "text-embedding-3-large", "text-embedding-ada-002"],
+                display_name="Search Query",
-            ],
+                tool_mode=True,
-            "Hugging Face - Dedicated": ["huggingfaceDedicated", ["endpoint-defined-model"]],
+            )
-            "Hugging Face - Serverless": [
+        )
-                "huggingface",
+    if "ingest_data" not in [input_.name for input_ in base_inputs]:
-                [
+        base_inputs.append(
-                    "sentence-transformers/all-MiniLM-L6-v2",
+            DataInput(
-                    "intfloat/multilingual-e5-large",
+                name="ingest_data",
-                    "intfloat/multilingual-e5-large-instruct",
+                display_name="Ingest Data",
-                    "BAAI/bge-small-en-v1.5",
+            )
-                    "BAAI/bge-base-en-v1.5",
+        )
-                    "BAAI/bge-large-en-v1.5",
-                ],
-            ],
-            "Jina AI": [
-                "jinaAI",
-                [
-                    "jina-embeddings-v2-base-en",
-                    "jina-embeddings-v2-base-de",
-                    "jina-embeddings-v2-base-es",
-                    "jina-embeddings-v2-base-code",
-                    "jina-embeddings-v2-base-zh",
-                ],
-            ],
-            "Mistral AI": ["mistral", ["mistral-embed"]],
-            "Nvidia": ["nvidia", ["NV-Embed-QA"]],
-            "OpenAI": ["openai", ["text-embedding-3-small", "text-embedding-3-large", "text-embedding-ada-002"]],
-            "Upstage": ["upstageAI", ["solar-embedding-1-large"]],
-            "Voyage AI": [
-                "voyageAI",
-                ["voyage-large-2-instruct", "voyage-law-2", "voyage-code-2", "voyage-large-2", "voyage-2"],
-            ],
-        },
-    )
 
     inputs = [
         SecretStrInput(
@@ -81,13 +57,15 @@ class AstraDBVectorStoreComponent(LCVectorStoreComponent):
             advanced=os.getenv("ASTRA_ENHANCED", "false").lower() == "true",
             real_time_refresh=True,
         ),
-        SecretStrInput(
+        DropdownInput(
             name="api_endpoint",
-            display_name="Database" if os.getenv("ASTRA_ENHANCED", "false").lower() == "true" else "API Endpoint",
+            display_name="Database",
-            info="API endpoint URL for the Astra DB service.",
+            info="The Astra DB Database to use.",
-            value="ASTRA_DB_API_ENDPOINT",
             required=True,
+            refresh_button=True,
             real_time_refresh=True,
+            options=["Default database"],
+            value="Default database",
         ),
         DropdownInput(
             name="collection_name",
@@ -126,15 +104,7 @@ class AstraDBVectorStoreComponent(LCVectorStoreComponent):
             input_types=["Embeddings"],
             info="Allows an embedding model configuration.",
         ),
-        DataInput(
+        *base_inputs,
-            name="ingest_data",
-            display_name="Ingest Data",
-        ),
-        MultilineInput(
-            name="search_input",
-            display_name="Search Query",
-            tool_mode=True,
-        ),
         IntInput(
             name="number_of_results",
             display_name="Number of Search Results",
@@ -212,26 +182,18 @@ class AstraDBVectorStoreComponent(LCVectorStoreComponent):
 
         return build_config
 
-    def update_providers_mapping(self):
+    def get_vectorize_providers(self):
-        # If we don't have token or api_endpoint, we can't fetch the list of providers
-        if not self.token or not self.api_endpoint:
-            self.log("Astra DB token and API endpoint are required to fetch the list of Vectorize providers.")
-
-            return self.VECTORIZE_PROVIDERS_MAPPING
-
         try:
             self.log("Dynamically updating list of Vectorize providers.")
 
             # Get the admin object
-            client = DataAPIClient(token=self.token)
+            admin = AstraDBAdmin(token=self.token)
-            admin = client.get_admin()
+            db_admin = admin.get_database_admin(self.get_api_endpoint())
 
-            # Get the embedding providers
+            # Get the list of embedding providers
-            db_admin = admin.get_database_admin(self.api_endpoint)
             embedding_providers = db_admin.find_embedding_providers().as_dict()
 
             vectorize_providers_mapping = {}
-
             # Map the provider display name to the provider key and models
             for provider_key, provider_data in embedding_providers["embeddingProviders"].items():
                 display_name = provider_data["displayName"]
@@ -244,14 +206,37 @@ class AstraDBVectorStoreComponent(LCVectorStoreComponent):
         except Exception as e:  # noqa: BLE001
             self.log(f"Error fetching Vectorize providers: {e}")
 
-            return self.VECTORIZE_PROVIDERS_MAPPING
+            return {}
+
+    def get_database_list(self):
+        # Get the admin object
+        db_admin = AstraDBAdmin(token=self.token)
+        db_list = list(db_admin.list_databases())
+
+        # Generate the api endpoint for each database
+        return {db.info.name: f"https://{db.info.id}-{db.info.region}.apps.astra.datastax.com" for db in db_list}
+
+    def get_api_endpoint(self):
+        # Get the database name (or endpoint)
+        database = self.api_endpoint
+
+        # If the database is not set, get the first database in the list
+        if not database or database == "Default database":
+            database, _ = next(iter(self.get_database_list().items()))
+
+        # If the database is a URL, return it
+        if database.startswith("https://"):
+            return database
+
+        # Otherwise, get the URL from the database list
+        return self.get_database_list().get(database)
 
     def get_database(self):
         try:
             client = DataAPIClient(token=self.token)
 
             return client.get_database(
-                self.api_endpoint,
+                api_endpoint=self.get_api_endpoint(),
                 token=self.token,
             )
         except Exception as e:  # noqa: BLE001
@@ -259,13 +244,25 @@ class AstraDBVectorStoreComponent(LCVectorStoreComponent):
 
             return None
 
+    def _initialize_database_options(self):
+        if not self.token:
+            return ["Default database"]
+        try:
+            databases = ["Default database", *list(self.get_database_list().keys())]
+        except Exception as e:  # noqa: BLE001
+            self.log(f"Error fetching databases: {e}")
+
+            return ["Default database"]
+
+        return databases
+
     def _initialize_collection_options(self):
         database = self.get_database()
         if database is None:
             return ["+ Create new collection"]
 
         try:
-            collections = [collection.name for collection in database.list_collections()]
+            collections = [collection.name for collection in database.list_collections(keyspace=self.keyspace or None)]
         except Exception as e:  # noqa: BLE001
             self.log(f"Error fetching collections: {e}")
 
@@ -289,7 +286,7 @@ class AstraDBVectorStoreComponent(LCVectorStoreComponent):
         collection_name = self.get_collection_choice()
 
         try:
-            collection = database.get_collection(collection_name)
+            collection = database.get_collection(collection_name, keyspace=self.keyspace or None)
             collection_options = collection.options()
         except Exception as _:  # noqa: BLE001
             return None
@@ -297,8 +294,17 @@ class AstraDBVectorStoreComponent(LCVectorStoreComponent):
         return collection_options.vector
 
     def update_build_config(self, build_config: dict, field_value: str, field_name: str | None = None):
-        # Refresh the collection name options
+        # Always attempt to update the database list
-        build_config["collection_name"]["options"] = self._initialize_collection_options()
+        if field_name in ["token", "api_endpoint", "collection_name"]:
+            # Update the database selector
+            build_config["api_endpoint"]["options"] = self._initialize_database_options()
+
+            # Set the default API endpoint if not set
+            if build_config["api_endpoint"]["value"] == "Default database":
+                build_config["api_endpoint"]["value"] = build_config["api_endpoint"]["options"][0]
+
+            # Update the collection selector
+            build_config["collection_name"]["options"] = self._initialize_collection_options()
 
         # Update the choice of embedding model based on collection name
         if field_name == "collection_name":
@@ -368,7 +374,7 @@ class AstraDBVectorStoreComponent(LCVectorStoreComponent):
                 build_config["embedding_model"]["advanced"] = True
 
                 # Update the providers mapping
-                vectorize_providers = self.update_providers_mapping()
+                vectorize_providers = self.get_vectorize_providers()
 
                 new_parameter = DropdownInput(
                     name="embedding_provider",
@@ -402,7 +408,7 @@ class AstraDBVectorStoreComponent(LCVectorStoreComponent):
             )
 
             # Update the providers mapping
-            vectorize_providers = self.update_providers_mapping()
+            vectorize_providers = self.get_vectorize_providers()
             model_options = vectorize_providers[field_value][1]
 
             new_parameter = DropdownInput(
@@ -481,7 +487,7 @@ class AstraDBVectorStoreComponent(LCVectorStoreComponent):
                 setattr(self, attribute, None)
 
         # Fetch values from kwargs if any self.* attributes are None
-        provider_mapping = self.update_providers_mapping()
+        provider_mapping = self.get_vectorize_providers()
         provider_value = provider_mapping.get(self.embedding_provider, [None])[0] or kwargs.get("embedding_provider")
         model_name = self.model or kwargs.get("model")
         authentication = {**(self.z_04_authentication or {}), **kwargs.get("z_04_authentication", {})}
@@ -525,7 +531,7 @@ class AstraDBVectorStoreComponent(LCVectorStoreComponent):
             raise ImportError(msg) from e
 
         # Initialize parameters based on the collection name
-        is_new_collection = self.collection_name == "+ Create new collection"
+        is_new_collection = self.get_collection_options() is None
 
         # Get the embedding model
         embedding_params = {"embedding": self.embedding_model} if self.embedding_choice == "Embedding Model" else {}
@@ -553,11 +559,7 @@ class AstraDBVectorStoreComponent(LCVectorStoreComponent):
             }
 
         # Get the running environment for Langflow
-        environment = (
+        environment = parse_api_endpoint(self.get_api_endpoint()).environment if self.get_api_endpoint() else None
-            parse_api_endpoint(getattr(self, "api_endpoint", None)).environment
-            if getattr(self, "api_endpoint", None)
-            else None
-        )
 
         # Get Langflow version and platform information
         __version__ = get_version_info()["version"]
@@ -577,16 +579,16 @@ class AstraDBVectorStoreComponent(LCVectorStoreComponent):
             vector_store = AstraDBVectorStore(
                 # Astra DB Authentication Parameters
                 token=self.token,
-                api_endpoint=self.api_endpoint,
+                api_endpoint=self.get_api_endpoint(),
                 namespace=self.keyspace or None,
                 collection_name=self.get_collection_choice(),
                 environment=environment,
                 # Astra DB Usage Tracking Parameters
                 ext_callers=[(f"{langflow_prefix}langflow", __version__)],
                 # Astra DB Vector Store Parameters
-                **autodetect_params,
+                **autodetect_params or {},
-                **embedding_params,
+                **embedding_params or {},
-                **self.astradb_vectorstore_kwargs,
+                **self.astradb_vectorstore_kwargs or {},
             )
         except Exception as e:
             msg = f"Error initializing AstraDBVectorStore: {e}"
@@ -623,7 +625,7 @@ class AstraDBVectorStoreComponent(LCVectorStoreComponent):
         return "similarity"
 
     def _build_search_args(self):
-        query = self.search_input if isinstance(self.search_input, str) and self.search_input.strip() else None
+        query = self.search_query if isinstance(self.search_query, str) and self.search_query.strip() else None
 
         if query:
             args = {
@@ -648,7 +650,7 @@ class AstraDBVectorStoreComponent(LCVectorStoreComponent):
     def search_documents(self, vector_store=None) -> list[Data]:
         vector_store = vector_store or self.build_vector_store()
 
-        self.log(f"Search input: {self.search_input}")
+        self.log(f"Search input: {self.search_query}")
         self.log(f"Search type: {self.search_type}")
         self.log(f"Number of results: {self.number_of_results}")
 

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

@@ -2,19 +2,16 @@ import os
 
 import orjson
 from astrapy.admin import parse_api_endpoint
-from loguru import logger
 
 from langflow.base.vectorstores.model import LCVectorStoreComponent, check_cached_vector_store
 from langflow.helpers import docs_to_data
 from langflow.inputs import (
     BoolInput,
-    DataInput,
     DictInput,
     DropdownInput,
     FloatInput,
     HandleInput,
     IntInput,
-    MultilineInput,
     SecretStrInput,
     StrInput,
 )
@@ -24,7 +21,6 @@ from langflow.schema import Data
 class AstraDBGraphVectorStoreComponent(LCVectorStoreComponent):
     display_name: str = "Astra DB Graph"
     description: str = "Implementation of Graph Vector Store using Astra DB"
-    documentation: str = "https://python.langchain.com/api_reference/astradb/graph_vectorstores/langchain_astradb.graph_vectorstores.AstraDBGraphVectorStore.html"
     name = "AstraDBGraph"
     icon: str = "AstraDB"
 
@@ -56,15 +52,7 @@ class AstraDBGraphVectorStoreComponent(LCVectorStoreComponent):
             info="Metadata key used for incoming links.",
             advanced=True,
         ),
-        MultilineInput(
+        *LCVectorStoreComponent.inputs,
-            name="search_input",
-            display_name="Search Input",
-        ),
-        DataInput(
-            name="ingest_data",
-            display_name="Ingest Data",
-            is_list=True,
-        ),
         StrInput(
             name="keyspace",
             display_name="Keyspace",
@@ -129,14 +117,14 @@ class AstraDBGraphVectorStoreComponent(LCVectorStoreComponent):
             display_name="Metadata Indexing Include",
             info="Optional list of metadata fields to include in the indexing.",
             advanced=True,
-            is_list=True,
+            list=True,
         ),
         StrInput(
             name="metadata_indexing_exclude",
             display_name="Metadata Indexing Exclude",
             info="Optional list of metadata fields to exclude from the indexing.",
             advanced=True,
-            is_list=True,
+            list=True,
         ),
         StrInput(
             name="collection_indexing_policy",
@@ -205,7 +193,7 @@ class AstraDBGraphVectorStoreComponent(LCVectorStoreComponent):
             raise ValueError(msg) from e
 
         try:
-            logger.debug(f"Initializing Graph Vector Store {self.collection_name}")
+            self.log(f"Initializing Graph Vector Store {self.collection_name}")
 
             vector_store = AstraDBGraphVectorStore(
                 embedding=self.embedding_model,
@@ -232,7 +220,7 @@ class AstraDBGraphVectorStoreComponent(LCVectorStoreComponent):
             msg = f"Error initializing AstraDBGraphVectorStore: {e}"
             raise ValueError(msg) from e
 
-        logger.debug(f"Vector Store initialized: {vector_store.astra_env.collection_name}")
+        self.log(f"Vector Store initialized: {vector_store.astra_env.collection_name}")
         self._add_documents_to_vector_store(vector_store)
 
         return vector_store
@@ -247,14 +235,14 @@ class AstraDBGraphVectorStoreComponent(LCVectorStoreComponent):
                 raise TypeError(msg)
 
         if documents:
-            logger.debug(f"Adding {len(documents)} documents to the Vector Store.")
+            self.log(f"Adding {len(documents)} documents to the Vector Store.")
             try:
                 vector_store.add_documents(documents)
             except Exception as e:
                 msg = f"Error adding documents to AstraDBGraphVectorStore: {e}"
                 raise ValueError(msg) from e
         else:
-            logger.debug("No documents to add to the Vector Store.")
+            self.log("No documents to add to the Vector Store.")
 
     def _map_search_type(self) -> str:
         match self.search_type:
@@ -287,21 +275,21 @@ class AstraDBGraphVectorStoreComponent(LCVectorStoreComponent):
         if not vector_store:
             vector_store = self.build_vector_store()
 
-        logger.debug("Searching for documents in AstraDBGraphVectorStore.")
+        self.log("Searching for documents in AstraDBGraphVectorStore.")
-        logger.debug(f"Search input: {self.search_input}")
+        self.log(f"Search query: {self.search_query}")
-        logger.debug(f"Search type: {self.search_type}")
+        self.log(f"Search type: {self.search_type}")
-        logger.debug(f"Number of results: {self.number_of_results}")
+        self.log(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_query and isinstance(self.search_query, str) and self.search_query.strip():
             try:
                 search_type = self._map_search_type()
                 search_args = self._build_search_args()
 
-                docs = vector_store.search(query=self.search_input, search_type=search_type, **search_args)
+                docs = vector_store.search(query=self.search_query, search_type=search_type, **search_args)
 
                 # Drop links from the metadata. At this point the links don't add any value for building the
                 # context and haven't been restored to json which causes the conversion to fail.
-                logger.debug("Removing links from metadata.")
+                self.log("Removing links from metadata.")
                 for doc in docs:
                     if "links" in doc.metadata:
                         doc.metadata.pop("links")
@@ -310,15 +298,15 @@ class AstraDBGraphVectorStoreComponent(LCVectorStoreComponent):
                 msg = f"Error performing search in AstraDBGraphVectorStore: {e}"
                 raise ValueError(msg) from e
 
-            logger.debug(f"Retrieved documents: {len(docs)}")
+            self.log(f"Retrieved documents: {len(docs)}")
 
             data = docs_to_data(docs)
 
-            logger.debug(f"Converted documents to data: {len(data)}")
+            self.log(f"Converted documents to data: {len(data)}")
 
             self.status = data
             return data
-        logger.debug("No search input provided. Skipping search.")
+        self.log("No search input provided. Skipping search.")
         return []
 
     def get_retriever_kwargs(self):

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

@@ -1,16 +1,13 @@
 from langchain_community.vectorstores import Cassandra
-from loguru import logger
 
 from langflow.base.vectorstores.model import LCVectorStoreComponent, check_cached_vector_store
 from langflow.helpers.data import docs_to_data
 from langflow.inputs import BoolInput, DictInput, FloatInput
 from langflow.io import (
-    DataInput,
     DropdownInput,
     HandleInput,
     IntInput,
     MessageTextInput,
-    MultilineInput,
     SecretStrInput,
 )
 from langflow.schema import Data
@@ -77,14 +74,9 @@ class CassandraVectorStoreComponent(LCVectorStoreComponent):
             display_name="Cluster arguments",
             info="Optional dictionary of additional keyword arguments for the Cassandra cluster.",
             advanced=True,
-            is_list=True,
+            list=True,
-        ),
-        MultilineInput(name="search_query", display_name="Search Query"),
-        DataInput(
-            name="ingest_data",
-            display_name="Ingest Data",
-            is_list=True,
         ),
+        *LCVectorStoreComponent.inputs,
         HandleInput(name="embedding", display_name="Embedding", input_types=["Embeddings"]),
         IntInput(
             name="number_of_results",
@@ -114,7 +106,7 @@ class CassandraVectorStoreComponent(LCVectorStoreComponent):
             display_name="Search Metadata Filter",
             info="Optional dictionary of filters to apply to the search query.",
             advanced=True,
-            is_list=True,
+            list=True,
         ),
         MessageTextInput(
             name="body_search",
@@ -184,7 +176,7 @@ class CassandraVectorStoreComponent(LCVectorStoreComponent):
             setup_mode = SetupMode.ASYNC
 
         if documents:
-            logger.debug(f"Adding {len(documents)} documents to the Vector Store.")
+            self.log(f"Adding {len(documents)} documents to the Vector Store.")
             table = Cassandra.from_documents(
                 documents=documents,
                 embedding=self.embedding,
@@ -195,7 +187,7 @@ class CassandraVectorStoreComponent(LCVectorStoreComponent):
                 body_index_options=body_index_options,
             )
         else:
-            logger.debug("No documents to add to the Vector Store.")
+            self.log("No documents to add to the Vector Store.")
             table = Cassandra(
                 embedding=self.embedding,
                 table_name=self.table_name,
@@ -216,16 +208,16 @@ class CassandraVectorStoreComponent(LCVectorStoreComponent):
     def search_documents(self) -> list[Data]:
         vector_store = self.build_vector_store()
 
-        logger.debug(f"Search input: {self.search_query}")
+        self.log(f"Search input: {self.search_query}")
-        logger.debug(f"Search type: {self.search_type}")
+        self.log(f"Search type: {self.search_type}")
-        logger.debug(f"Number of results: {self.number_of_results}")
+        self.log(f"Number of results: {self.number_of_results}")
 
         if self.search_query and isinstance(self.search_query, str) and self.search_query.strip():
             try:
                 search_type = self._map_search_type()
                 search_args = self._build_search_args()
 
-                logger.debug(f"Search args: {search_args}")
+                self.log(f"Search args: {search_args}")
 
                 docs = vector_store.search(query=self.search_query, search_type=search_type, **search_args)
             except KeyError as e:
@@ -237,7 +229,7 @@ class CassandraVectorStoreComponent(LCVectorStoreComponent):
                     raise ValueError(msg) from e
                 raise
 
-            logger.debug(f"Retrieved documents: {len(docs)}")
+            self.log(f"Retrieved documents: {len(docs)}")
 
             data = docs_to_data(docs)
             self.status = data

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

@@ -1,18 +1,15 @@
 from uuid import UUID
 
 from langchain_community.graph_vectorstores import CassandraGraphVectorStore
-from loguru import logger
 
 from langflow.base.vectorstores.model import LCVectorStoreComponent, check_cached_vector_store
 from langflow.helpers.data import docs_to_data
 from langflow.inputs import DictInput, FloatInput
 from langflow.io import (
-    DataInput,
     DropdownInput,
     HandleInput,
     IntInput,
     MessageTextInput,
-    MultilineInput,
     SecretStrInput,
 )
 from langflow.schema import Data
@@ -21,7 +18,6 @@ from langflow.schema import Data
 class CassandraGraphVectorStoreComponent(LCVectorStoreComponent):
     display_name = "Cassandra Graph"
     description = "Cassandra Graph Vector Store"
-    documentation = "https://python.langchain.com/v0.2/api_reference/community/graph_vectorstores.html"
     name = "CassandraGraph"
     icon = "Cassandra"
 
@@ -66,14 +62,9 @@ class CassandraGraphVectorStoreComponent(LCVectorStoreComponent):
             display_name="Cluster arguments",
             info="Optional dictionary of additional keyword arguments for the Cassandra cluster.",
             advanced=True,
-            is_list=True,
+            list=True,
-        ),
-        MultilineInput(name="search_query", display_name="Search Query"),
-        DataInput(
-            name="ingest_data",
-            display_name="Ingest Data",
-            is_list=True,
         ),
+        *LCVectorStoreComponent.inputs,
         HandleInput(name="embedding", display_name="Embedding", input_types=["Embeddings"]),
         IntInput(
             name="number_of_results",
@@ -116,7 +107,7 @@ class CassandraGraphVectorStoreComponent(LCVectorStoreComponent):
             display_name="Search Metadata Filter",
             info="Optional dictionary of filters to apply to the search query.",
             advanced=True,
-            is_list=True,
+            list=True,
         ),
     ]
 
@@ -164,7 +155,7 @@ class CassandraGraphVectorStoreComponent(LCVectorStoreComponent):
         setup_mode = SetupMode.OFF if self.setup_mode == "Off" else SetupMode.SYNC
 
         if documents:
-            logger.debug(f"Adding {len(documents)} documents to the Vector Store.")
+            self.log(f"Adding {len(documents)} documents to the Vector Store.")
             store = CassandraGraphVectorStore.from_documents(
                 documents=documents,
                 embedding=self.embedding,
@@ -172,7 +163,7 @@ class CassandraGraphVectorStoreComponent(LCVectorStoreComponent):
                 keyspace=self.keyspace,
             )
         else:
-            logger.debug("No documents to add to the Vector Store.")
+            self.log("No documents to add to the Vector Store.")
             store = CassandraGraphVectorStore(
                 embedding=self.embedding,
                 node_table=self.table_name,
@@ -195,16 +186,16 @@ class CassandraGraphVectorStoreComponent(LCVectorStoreComponent):
     def search_documents(self) -> list[Data]:
         vector_store = self.build_vector_store()
 
-        logger.debug(f"Search input: {self.search_query}")
+        self.log(f"Search input: {self.search_query}")
-        logger.debug(f"Search type: {self.search_type}")
+        self.log(f"Search type: {self.search_type}")
-        logger.debug(f"Number of results: {self.number_of_results}")
+        self.log(f"Number of results: {self.number_of_results}")
 
         if self.search_query and isinstance(self.search_query, str) and self.search_query.strip():
             try:
                 search_type = self._map_search_type()
                 search_args = self._build_search_args()
 
-                logger.debug(f"Search args: {search_args}")
+                self.log(f"Search args: {search_args}")
 
                 docs = vector_store.search(query=self.search_query, search_type=search_type, **search_args)
             except KeyError as e:
@@ -216,7 +207,7 @@ class CassandraGraphVectorStoreComponent(LCVectorStoreComponent):
                     raise ValueError(msg) from e
                 raise
 
-            logger.debug(f"Retrieved documents: {len(docs)}")
+            self.log(f"Retrieved documents: {len(docs)}")
 
             data = docs_to_data(docs)
             self.status = data

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

@@ -2,11 +2,10 @@ from copy import deepcopy
 
 from chromadb.config import Settings
 from langchain_chroma import Chroma
-from loguru import logger
 
 from langflow.base.vectorstores.model import LCVectorStoreComponent, check_cached_vector_store
 from langflow.base.vectorstores.utils import chroma_collection_to_data
-from langflow.io import BoolInput, DataInput, DropdownInput, HandleInput, IntInput, MultilineInput, StrInput
+from langflow.io import BoolInput, DropdownInput, HandleInput, IntInput, StrInput
 from langflow.schema import Data
 
 
@@ -15,7 +14,6 @@ class ChromaVectorStoreComponent(LCVectorStoreComponent):
 
     display_name: str = "Chroma DB"
     description: str = "Chroma Vector Store with search capabilities"
-    documentation = "https://python.langchain.com/docs/integrations/vectorstores/chroma"
     name = "Chroma"
     icon = "Chroma"
 
@@ -29,15 +27,7 @@ class ChromaVectorStoreComponent(LCVectorStoreComponent):
             name="persist_directory",
             display_name="Persist Directory",
         ),
-        MultilineInput(
+        *LCVectorStoreComponent.inputs,
-            name="search_query",
-            display_name="Search Query",
-        ),
-        DataInput(
-            name="ingest_data",
-            display_name="Ingest Data",
-            is_list=True,
-        ),
         HandleInput(name="embedding", display_name="Embedding", input_types=["Embeddings"]),
         StrInput(
             name="chroma_server_cors_allow_origins",
@@ -153,7 +143,7 @@ class ChromaVectorStoreComponent(LCVectorStoreComponent):
                 raise TypeError(msg)
 
         if documents and self.embedding is not None:
-            logger.debug(f"Adding {len(documents)} documents to the Vector Store.")
+            self.log(f"Adding {len(documents)} documents to the Vector Store.")
             vector_store.add_documents(documents)
         else:
-            logger.debug("No documents to add to the Vector Store.")
+            self.log("No documents to add to the Vector Store.")

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

@@ -4,12 +4,10 @@ from langflow.base.vectorstores.model import LCVectorStoreComponent, check_cache
 from langflow.helpers.data import docs_to_data
 from langflow.inputs import BoolInput, FloatInput
 from langflow.io import (
-    DataInput,
     DictInput,
     DropdownInput,
     HandleInput,
     IntInput,
-    MultilineInput,
     SecretStrInput,
     StrInput,
 )
@@ -19,7 +17,6 @@ from langflow.schema import Data
 class ClickhouseVectorStoreComponent(LCVectorStoreComponent):
     display_name = "Clickhouse"
     description = "Clickhouse Vector Store with search capabilities"
-    documentation = "https://python.langchain.com/v0.2/docs/integrations/vectorstores/clickhouse/"
     name = "Clickhouse"
     icon = "Clickhouse"
 
@@ -54,8 +51,7 @@ class ClickhouseVectorStoreComponent(LCVectorStoreComponent):
         ),
         StrInput(name="index_param", display_name="Param of the index", value="'L2Distance',100", advanced=True),
         DictInput(name="index_query_params", display_name="index query params", advanced=True),
-        MultilineInput(name="search_query", display_name="Search Query"),
+        *LCVectorStoreComponent.inputs,
-        DataInput(name="ingest_data", display_name="Ingest Data", is_list=True),
         HandleInput(name="embedding", display_name="Embedding", input_types=["Embeddings"]),
         IntInput(
             name="number_of_results",

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

@@ -4,14 +4,13 @@ from langchain_community.vectorstores import CouchbaseVectorStore
 
 from langflow.base.vectorstores.model import LCVectorStoreComponent, check_cached_vector_store
 from langflow.helpers.data import docs_to_data
-from langflow.io import DataInput, HandleInput, IntInput, MultilineInput, SecretStrInput, StrInput
+from langflow.io import HandleInput, IntInput, SecretStrInput, StrInput
 from langflow.schema import Data
 
 
 class CouchbaseVectorStoreComponent(LCVectorStoreComponent):
     display_name = "Couchbase"
     description = "Couchbase Vector Store with search capabilities"
-    documentation = "https://python.langchain.com/v0.1/docs/integrations/document_loaders/couchbase/"
     name = "Couchbase"
     icon = "Couchbase"
 
@@ -25,12 +24,7 @@ class CouchbaseVectorStoreComponent(LCVectorStoreComponent):
         StrInput(name="scope_name", display_name="Scope Name", required=True),
         StrInput(name="collection_name", display_name="Collection Name", required=True),
         StrInput(name="index_name", display_name="Index Name", required=True),
-        MultilineInput(name="search_query", display_name="Search Query"),
+        *LCVectorStoreComponent.inputs,
-        DataInput(
-            name="ingest_data",
-            display_name="Ingest Data",
-            is_list=True,
-        ),
         HandleInput(name="embedding", display_name="Embedding", input_types=["Embeddings"]),
         IntInput(
             name="number_of_results",

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

@@ -2,16 +2,13 @@ from typing import Any
 
 from langchain.schema import Document
 from langchain_elasticsearch import ElasticsearchStore
-from loguru import logger
 
 from langflow.base.vectorstores.model import LCVectorStoreComponent, check_cached_vector_store
 from langflow.io import (
-    DataInput,
     DropdownInput,
     FloatInput,
     HandleInput,
     IntInput,
-    MultilineInput,
     SecretStrInput,
     StrInput,
 )
@@ -23,7 +20,6 @@ class ElasticsearchVectorStoreComponent(LCVectorStoreComponent):
 
     display_name: str = "Elasticsearch"
     description: str = "Elasticsearch Vector Store with with advanced, customizable search capabilities."
-    documentation = "https://python.langchain.com/docs/integrations/vectorstores/elasticsearch"
     name = "Elasticsearch"
     icon = "ElasticsearchStore"
 
@@ -47,11 +43,7 @@ class ElasticsearchVectorStoreComponent(LCVectorStoreComponent):
             value="langflow",
             info="The index name where the vectors will be stored in Elasticsearch cluster.",
         ),
-        MultilineInput(
+        *LCVectorStoreComponent.inputs,
-            name="search_input",
-            display_name="Search Input",
-            info="Enter a search query. Leave empty to retrieve all documents.",
-        ),
         StrInput(
             name="username",
             display_name="Username",
@@ -72,11 +64,6 @@ class ElasticsearchVectorStoreComponent(LCVectorStoreComponent):
                 "Required for both local and Elastic Cloud setups unless API keys are used."
             ),
         ),
-        DataInput(
-            name="ingest_data",
-            display_name="Ingest Data",
-            is_list=True,
-        ),
         HandleInput(
             name="embedding",
             display_name="Embedding",
@@ -155,7 +142,7 @@ class ElasticsearchVectorStoreComponent(LCVectorStoreComponent):
                 documents.append(data.to_lc_document())
             else:
                 error_message = "Vector Store Inputs must be Data objects."
-                logger.error(error_message)
+                self.log(error_message)
                 raise TypeError(error_message)
         return documents
 
@@ -163,10 +150,10 @@ class ElasticsearchVectorStoreComponent(LCVectorStoreComponent):
         """Adds documents to the Vector Store."""
         documents = self._prepare_documents()
         if documents and self.embedding:
-            logger.debug(f"Adding {len(documents)} documents to the Vector Store.")
+            self.log(f"Adding {len(documents)} documents to the Vector Store.")
             vector_store.add_documents(documents)
         else:
-            logger.debug("No documents to add to the Vector Store.")
+            self.log("No documents to add to the Vector Store.")
 
     def search(self, query: str | None = None) -> list[dict[str, Any]]:
         """Search for similar documents in the vector store or retrieve all documents if no query is provided."""
@@ -180,7 +167,7 @@ class ElasticsearchVectorStoreComponent(LCVectorStoreComponent):
             search_type = self.search_type.lower()
             if search_type not in {"similarity", "mmr"}:
                 msg = f"Invalid search type: {self.search_type}"
-                logger.error(msg)
+                self.log(msg)
                 raise ValueError(msg)
             try:
                 if search_type == "similarity":
@@ -192,7 +179,7 @@ class ElasticsearchVectorStoreComponent(LCVectorStoreComponent):
                     "Error occurred while querying the Elasticsearch VectorStore,"
                     " there is no Data into the VectorStore."
                 )
-                logger.exception(msg)
+                self.log(msg)
                 raise ValueError(msg) from e
             return [
                 {"page_content": doc.page_content, "metadata": doc.metadata, "score": score} for doc, score in results
@@ -228,7 +215,7 @@ class ElasticsearchVectorStoreComponent(LCVectorStoreComponent):
 
         If no search input is provided, retrieve all documents.
         """
-        results = self.search(self.search_input)
+        results = self.search(self.search_query)
         retrieved_data = [
             Data(
                 text=result["page_content"],

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

@@ -1,9 +1,8 @@
 from langchain_community.vectorstores import FAISS
-from loguru import logger
 
 from langflow.base.vectorstores.model import LCVectorStoreComponent, check_cached_vector_store
 from langflow.helpers.data import docs_to_data
-from langflow.io import BoolInput, DataInput, HandleInput, IntInput, MultilineInput, StrInput
+from langflow.io import BoolInput, HandleInput, IntInput, StrInput
 from langflow.schema import Data
 
 
@@ -12,7 +11,6 @@ class FaissVectorStoreComponent(LCVectorStoreComponent):
 
     display_name: str = "FAISS"
     description: str = "FAISS Vector Store with search capabilities"
-    documentation = "https://python.langchain.com/docs/modules/data_connection/vectorstores/integrations/faiss"
     name = "FAISS"
     icon = "FAISS"
 
@@ -27,15 +25,7 @@ class FaissVectorStoreComponent(LCVectorStoreComponent):
             display_name="Persist Directory",
             info="Path to save the FAISS index. It will be relative to where Langflow is running.",
         ),
-        MultilineInput(
+        *LCVectorStoreComponent.inputs,
-            name="search_query",
-            display_name="Search Query",
-        ),
-        DataInput(
-            name="ingest_data",
-            display_name="Ingest Data",
-            is_list=True,
-        ),
         BoolInput(
             name="allow_dangerous_deserialization",
             display_name="Allow Dangerous Deserialization",
@@ -93,8 +83,8 @@ class FaissVectorStoreComponent(LCVectorStoreComponent):
             msg = "Failed to load the FAISS index."
             raise ValueError(msg)
 
-        logger.debug(f"Search input: {self.search_query}")
+        self.log(f"Search input: {self.search_query}")
-        logger.debug(f"Number of results: {self.number_of_results}")
+        self.log(f"Number of results: {self.number_of_results}")
 
         if self.search_query and isinstance(self.search_query, str) and self.search_query.strip():
             docs = vector_store.similarity_search(
@@ -102,11 +92,11 @@ class FaissVectorStoreComponent(LCVectorStoreComponent):
                 k=self.number_of_results,
             )
 
-            logger.debug(f"Retrieved documents: {len(docs)}")
+            self.log(f"Retrieved documents: {len(docs)}")
 
             data = docs_to_data(docs)
-            logger.debug(f"Converted documents to data: {len(data)}")
+            self.log(f"Converted documents to data: {len(data)}")
-            logger.debug(data)
+            self.log(data)
             return data  # Return the search results data
-        logger.debug("No search input provided. Skipping search.")
+        self.log("No search input provided. Skipping search.")
         return []

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

@@ -1,11 +1,8 @@
-from loguru import logger
-
 from langflow.base.vectorstores.model import LCVectorStoreComponent, check_cached_vector_store
 from langflow.helpers import docs_to_data
 from langflow.inputs import DictInput, FloatInput
 from langflow.io import (
     BoolInput,
-    DataInput,
     DropdownInput,
     HandleInput,
     IntInput,
@@ -19,7 +16,6 @@ from langflow.schema import Data
 class HCDVectorStoreComponent(LCVectorStoreComponent):
     display_name: str = "Hyper-Converged Database"
     description: str = "Implementation of Vector Store using Hyper-Converged Database (HCD) with search capabilities"
-    documentation: str = "https://python.langchain.com/docs/integrations/vectorstores/astradb"
     name = "HCD"
     icon: str = "HCD"
 
@@ -51,15 +47,7 @@ class HCDVectorStoreComponent(LCVectorStoreComponent):
             value="HCD_API_ENDPOINT",
             required=True,
         ),
-        MultilineInput(
+        *LCVectorStoreComponent.inputs,
-            name="search_input",
-            display_name="Search Input",
-        ),
-        DataInput(
-            name="ingest_data",
-            display_name="Ingest Data",
-            is_list=True,
-        ),
         StrInput(
             name="namespace",
             display_name="Namespace",
@@ -263,14 +251,14 @@ class HCDVectorStoreComponent(LCVectorStoreComponent):
                 raise TypeError(msg)
 
         if documents:
-            logger.debug(f"Adding {len(documents)} documents to the Vector Store.")
+            self.log(f"Adding {len(documents)} documents to the Vector Store.")
             try:
                 vector_store.add_documents(documents)
             except Exception as e:
                 msg = f"Error adding documents to AstraDBVectorStore: {e}"
                 raise ValueError(msg) from e
         else:
-            logger.debug("No documents to add to the Vector Store.")
+            self.log("No documents to add to the Vector Store.")
 
     def _map_search_type(self) -> str:
         if self.search_type == "Similarity with score threshold":
@@ -294,27 +282,27 @@ class HCDVectorStoreComponent(LCVectorStoreComponent):
     def search_documents(self) -> list[Data]:
         vector_store = self.build_vector_store()
 
-        logger.debug(f"Search input: {self.search_input}")
+        self.log(f"Search query: {self.search_query}")
-        logger.debug(f"Search type: {self.search_type}")
+        self.log(f"Search type: {self.search_type}")
-        logger.debug(f"Number of results: {self.number_of_results}")
+        self.log(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_query and isinstance(self.search_query, str) and self.search_query.strip():
             try:
                 search_type = self._map_search_type()
                 search_args = self._build_search_args()
 
-                docs = vector_store.search(query=self.search_input, search_type=search_type, **search_args)
+                docs = vector_store.search(query=self.search_query, search_type=search_type, **search_args)
             except Exception as e:
                 msg = f"Error performing search in AstraDBVectorStore: {e}"
                 raise ValueError(msg) from e
 
-            logger.debug(f"Retrieved documents: {len(docs)}")
+            self.log(f"Retrieved documents: {len(docs)}")
 
             data = docs_to_data(docs)
-            logger.debug(f"Converted documents to data: {len(data)}")
+            self.log(f"Converted documents to data: {len(data)}")
             self.status = data
             return data
-        logger.debug("No search input provided. Skipping search.")
+        self.log("No search input provided. Skipping search.")
         return []
 
     def get_retriever_kwargs(self):

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

@@ -2,13 +2,11 @@ from langflow.base.vectorstores.model import LCVectorStoreComponent, check_cache
 from langflow.helpers.data import docs_to_data
 from langflow.io import (
     BoolInput,
-    DataInput,
     DictInput,
     DropdownInput,
     FloatInput,
     HandleInput,
     IntInput,
-    MultilineInput,
     SecretStrInput,
     StrInput,
 )
@@ -20,7 +18,6 @@ class MilvusVectorStoreComponent(LCVectorStoreComponent):
 
     display_name: str = "Milvus"
     description: str = "Milvus vector store with search capabilities"
-    documentation = "https://python.langchain.com/docs/integrations/vectorstores/milvus"
     name = "Milvus"
     icon = "Milvus"
 
@@ -53,12 +50,7 @@ class MilvusVectorStoreComponent(LCVectorStoreComponent):
         DictInput(name="search_params", display_name="Search Parameters", advanced=True),
         BoolInput(name="drop_old", display_name="Drop Old Collection", value=False, advanced=True),
         FloatInput(name="timeout", display_name="Timeout", advanced=True),
-        MultilineInput(name="search_query", display_name="Search Query"),
+        *LCVectorStoreComponent.inputs,
-        DataInput(
-            name="ingest_data",
-            display_name="Ingest Data",
-            is_list=True,
-        ),
         HandleInput(name="embedding", display_name="Embedding", input_types=["Embeddings"]),
         IntInput(
             name="number_of_results",

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

@@ -5,14 +5,13 @@ from langchain_community.vectorstores import MongoDBAtlasVectorSearch
 
 from langflow.base.vectorstores.model import LCVectorStoreComponent, check_cached_vector_store
 from langflow.helpers.data import docs_to_data
-from langflow.io import BoolInput, DataInput, HandleInput, IntInput, MultilineInput, SecretStrInput, StrInput
+from langflow.io import BoolInput, HandleInput, IntInput, SecretStrInput, StrInput
 from langflow.schema import Data
 
 
 class MongoVectorStoreComponent(LCVectorStoreComponent):
     display_name = "MongoDB Atlas"
     description = "MongoDB Atlas Vector Store with search capabilities"
-    documentation = "https://python.langchain.com/docs/modules/data_connection/vectorstores/integrations/mongodb_atlas"
     name = "MongoDBAtlasVector"
     icon = "MongoDB"
 
@@ -30,12 +29,7 @@ class MongoVectorStoreComponent(LCVectorStoreComponent):
         StrInput(name="db_name", display_name="Database Name", required=True),
         StrInput(name="collection_name", display_name="Collection Name", required=True),
         StrInput(name="index_name", display_name="Index Name", required=True),
-        MultilineInput(name="search_query", display_name="Search Query"),
+        *LCVectorStoreComponent.inputs,
-        DataInput(
-            name="ingest_data",
-            display_name="Ingest Data",
-            is_list=True,
-        ),
         HandleInput(name="embedding", display_name="Embedding", input_types=["Embeddings"]),
         IntInput(
             name="number_of_results",

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

@@ -2,12 +2,10 @@ import json
 from typing import Any
 
 from langchain_community.vectorstores import OpenSearchVectorSearch
-from loguru import logger
 
 from langflow.base.vectorstores.model import LCVectorStoreComponent, check_cached_vector_store
 from langflow.io import (
     BoolInput,
-    DataInput,
     DropdownInput,
     FloatInput,
     HandleInput,
@@ -24,7 +22,6 @@ class OpenSearchVectorStoreComponent(LCVectorStoreComponent):
 
     display_name: str = "OpenSearch"
     description: str = "OpenSearch Vector Store with advanced, customizable search capabilities."
-    documentation = "https://python.langchain.com/docs/integrations/vectorstores/opensearch"
     name = "OpenSearch"
     icon = "OpenSearch"
 
@@ -41,20 +38,7 @@ class OpenSearchVectorStoreComponent(LCVectorStoreComponent):
             value="langflow",
             info="The index name where the vectors will be stored in OpenSearch cluster.",
         ),
-        MultilineInput(
+        *LCVectorStoreComponent.inputs,
-            name="search_input",
-            display_name="Search Input",
-            info=(
-                "Enter a search query. Leave empty to retrieve all documents. "
-                "If you need a more advanced search consider using Hybrid Search Query instead."
-            ),
-            value="",
-        ),
-        DataInput(
-            name="ingest_data",
-            display_name="Ingest Data",
-            is_list=True,
-        ),
         HandleInput(name="embedding", display_name="Embedding", input_types=["Embeddings"]),
         DropdownInput(
             name="search_type",
@@ -120,7 +104,7 @@ class OpenSearchVectorStoreComponent(LCVectorStoreComponent):
             from langchain_community.vectorstores import OpenSearchVectorSearch
         except ImportError as e:
             error_message = f"Failed to import required modules: {e}"
-            logger.exception(error_message)
+            self.log(error_message)
             raise ImportError(error_message) from e
 
         try:
@@ -136,7 +120,7 @@ class OpenSearchVectorStoreComponent(LCVectorStoreComponent):
             )
         except Exception as e:
             error_message = f"Failed to create OpenSearchVectorSearch instance: {e}"
-            logger.exception(error_message)
+            self.log(error_message)
             raise RuntimeError(error_message) from e
 
         if self.ingest_data:
@@ -152,19 +136,19 @@ class OpenSearchVectorStoreComponent(LCVectorStoreComponent):
                 documents.append(_input.to_lc_document())
             else:
                 error_message = f"Expected Data object, got {type(_input)}"
-                logger.error(error_message)
+                self.log(error_message)
                 raise TypeError(error_message)
 
         if documents and self.embedding is not None:
-            logger.debug(f"Adding {len(documents)} documents to the Vector Store.")
+            self.log(f"Adding {len(documents)} documents to the Vector Store.")
             try:
                 vector_store.add_documents(documents)
             except Exception as e:
                 error_message = f"Error adding documents to Vector Store: {e}"
-                logger.exception(error_message)
+                self.log(error_message)
                 raise RuntimeError(error_message) from e
         else:
-            logger.debug("No documents to add to the Vector Store.")
+            self.log("No documents to add to the Vector Store.")
 
     def search(self, query: str | None = None) -> list[dict[str, Any]]:
         """Search for similar documents in the vector store or retrieve all documents if no query is provided."""
@@ -178,7 +162,7 @@ class OpenSearchVectorStoreComponent(LCVectorStoreComponent):
                     hybrid_query = json.loads(self.hybrid_search_query)
                 except json.JSONDecodeError as e:
                     error_message = f"Invalid hybrid search query JSON: {e}"
-                    logger.exception(error_message)
+                    self.log(error_message)
                     raise ValueError(error_message) from e
 
                 results = vector_store.client.search(index=self.index_name, body=hybrid_query)
@@ -223,11 +207,11 @@ class OpenSearchVectorStoreComponent(LCVectorStoreComponent):
 
         except Exception as e:
             error_message = f"Error during search: {e}"
-            logger.exception(error_message)
+            self.log(error_message)
             raise RuntimeError(error_message) from e
 
         error_message = f"Error during search. Invalid search type: {self.search_type}"
-        logger.error(error_message)
+        self.log(error_message)
         raise ValueError(error_message)
 
     def search_documents(self) -> list[Data]:
@@ -236,7 +220,7 @@ class OpenSearchVectorStoreComponent(LCVectorStoreComponent):
         If no search input is provided, retrieve all documents.
         """
         try:
-            query = self.search_input.strip() if self.search_input else None
+            query = self.search_query.strip() if self.search_query else None
             results = self.search(query)
             retrieved_data = [
                 Data(
@@ -247,7 +231,7 @@ class OpenSearchVectorStoreComponent(LCVectorStoreComponent):
             ]
         except Exception as e:
             error_message = f"Error during document search: {e}"
-            logger.exception(error_message)
+            self.log(error_message)
             raise RuntimeError(error_message) from e
 
         self.status = retrieved_data

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

@@ -2,7 +2,7 @@ from langchain_community.vectorstores import PGVector
 
 from langflow.base.vectorstores.model import LCVectorStoreComponent, check_cached_vector_store
 from langflow.helpers.data import docs_to_data
-from langflow.io import DataInput, HandleInput, IntInput, MultilineInput, SecretStrInput, StrInput
+from langflow.io import HandleInput, IntInput, SecretStrInput, StrInput
 from langflow.schema import Data
 from langflow.utils.connection_string_parser import transform_connection_string
 
@@ -10,19 +10,13 @@ from langflow.utils.connection_string_parser import transform_connection_string
 class PGVectorStoreComponent(LCVectorStoreComponent):
     display_name = "PGVector"
     description = "PGVector Vector Store with search capabilities"
-    documentation = "https://python.langchain.com/v0.2/docs/integrations/vectorstores/pgvector/"
     name = "pgvector"
     icon = "cpu"
 
     inputs = [
         SecretStrInput(name="pg_server_url", display_name="PostgreSQL Server Connection String", required=True),
         StrInput(name="collection_name", display_name="Table", required=True),
-        MultilineInput(name="search_query", display_name="Search Query"),
+        *LCVectorStoreComponent.inputs,
-        DataInput(
-            name="ingest_data",
-            display_name="Ingestion Data",
-            is_list=True,
-        ),
         HandleInput(name="embedding", display_name="Embedding", input_types=["Embeddings"]),
         IntInput(
             name="number_of_results",

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

@@ -3,14 +3,13 @@ from langchain_pinecone import Pinecone
 
 from langflow.base.vectorstores.model import LCVectorStoreComponent, check_cached_vector_store
 from langflow.helpers.data import docs_to_data
-from langflow.io import DataInput, DropdownInput, HandleInput, IntInput, MultilineInput, SecretStrInput, StrInput
+from langflow.io import DropdownInput, HandleInput, IntInput, SecretStrInput, StrInput
 from langflow.schema import Data
 
 
 class PineconeVectorStoreComponent(LCVectorStoreComponent):
     display_name = "Pinecone"
     description = "Pinecone Vector Store with search capabilities"
-    documentation = "https://python.langchain.com/v0.2/docs/integrations/vectorstores/pinecone/"
     name = "Pinecone"
     icon = "Pinecone"
     inputs = [
@@ -31,12 +30,7 @@ class PineconeVectorStoreComponent(LCVectorStoreComponent):
             value="text",
             advanced=True,
         ),
-        MultilineInput(name="search_query", display_name="Search Query"),
+        *LCVectorStoreComponent.inputs,
-        DataInput(
-            name="ingest_data",
-            display_name="Ingest Data",
-            is_list=True,
-        ),
         HandleInput(name="embedding", display_name="Embedding", input_types=["Embeddings"]),
         IntInput(
             name="number_of_results",

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

@@ -4,11 +4,9 @@ from langchain_community.vectorstores import Qdrant
 from langflow.base.vectorstores.model import LCVectorStoreComponent, check_cached_vector_store
 from langflow.helpers.data import docs_to_data
 from langflow.io import (
-    DataInput,
     DropdownInput,
     HandleInput,
     IntInput,
-    MultilineInput,
     SecretStrInput,
     StrInput,
 )
@@ -18,7 +16,6 @@ from langflow.schema import Data
 class QdrantVectorStoreComponent(LCVectorStoreComponent):
     display_name = "Qdrant"
     description = "Qdrant Vector Store with search capabilities"
-    documentation = "https://python.langchain.com/docs/modules/data_connection/vectorstores/integrations/qdrant"
     icon = "Qdrant"
 
     inputs = [
@@ -40,12 +37,7 @@ class QdrantVectorStoreComponent(LCVectorStoreComponent):
         ),
         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),
-        MultilineInput(name="search_query", display_name="Search Query"),
+        *LCVectorStoreComponent.inputs,
-        DataInput(
-            name="ingest_data",
-            display_name="Ingest Data",
-            is_list=True,
-        ),
         HandleInput(name="embedding", display_name="Embedding", input_types=["Embeddings"]),
         IntInput(
             name="number_of_results",

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

@@ -5,7 +5,7 @@ from langchain_community.vectorstores.redis import Redis
 
 from langflow.base.vectorstores.model import LCVectorStoreComponent, check_cached_vector_store
 from langflow.helpers.data import docs_to_data
-from langflow.io import DataInput, HandleInput, IntInput, MultilineInput, SecretStrInput, StrInput
+from langflow.io import HandleInput, IntInput, SecretStrInput, StrInput
 from langflow.schema import Data
 
 
@@ -14,7 +14,6 @@ class RedisVectorStoreComponent(LCVectorStoreComponent):
 
     display_name: str = "Redis"
     description: str = "Implementation of Vector Store using Redis"
-    documentation = "https://python.langchain.com/docs/integrations/vectorstores/redis"
     name = "Redis"
     icon = "Redis"
 
@@ -29,12 +28,7 @@ class RedisVectorStoreComponent(LCVectorStoreComponent):
             name="schema",
             display_name="Schema",
         ),
-        MultilineInput(name="search_query", display_name="Search Query"),
+        *LCVectorStoreComponent.inputs,
-        DataInput(
-            name="ingest_data",
-            display_name="Ingest Data",
-            is_list=True,
-        ),
         IntInput(
             name="number_of_results",
             display_name="Number of Results",

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

@@ -3,14 +3,13 @@ from supabase.client import Client, create_client
 
 from langflow.base.vectorstores.model import LCVectorStoreComponent, check_cached_vector_store
 from langflow.helpers.data import docs_to_data
-from langflow.io import DataInput, HandleInput, IntInput, MultilineInput, SecretStrInput, StrInput
+from langflow.io import HandleInput, IntInput, SecretStrInput, StrInput
 from langflow.schema import Data
 
 
 class SupabaseVectorStoreComponent(LCVectorStoreComponent):
     display_name = "Supabase"
     description = "Supabase Vector Store with search capabilities"
-    documentation = "https://python.langchain.com/v0.2/docs/integrations/vectorstores/supabase/"
     name = "SupabaseVectorStore"
     icon = "Supabase"
 
@@ -19,12 +18,7 @@ class SupabaseVectorStoreComponent(LCVectorStoreComponent):
         SecretStrInput(name="supabase_service_key", display_name="Supabase Service Key", required=True),
         StrInput(name="table_name", display_name="Table Name", advanced=True),
         StrInput(name="query_name", display_name="Query Name"),
-        MultilineInput(name="search_query", display_name="Search Query"),
+        *LCVectorStoreComponent.inputs,
-        DataInput(
-            name="ingest_data",
-            display_name="Ingest Data",
-            is_list=True,
-        ),
         HandleInput(name="embedding", display_name="Embedding", input_types=["Embeddings"]),
         IntInput(
             name="number_of_results",

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

@@ -3,7 +3,6 @@ from langchain_community.vectorstores import UpstashVectorStore
 from langflow.base.vectorstores.model import LCVectorStoreComponent, check_cached_vector_store
 from langflow.helpers.data import docs_to_data
 from langflow.io import (
-    DataInput,
     HandleInput,
     IntInput,
     MultilineInput,
@@ -16,7 +15,6 @@ from langflow.schema import Data
 class UpstashVectorStoreComponent(LCVectorStoreComponent):
     display_name = "Upstash"
     description = "Upstash Vector Store with search capabilities"
-    documentation = "https://python.langchain.com/v0.2/docs/integrations/vectorstores/upstash/"
     name = "Upstash"
     icon = "Upstash"
 
@@ -45,17 +43,12 @@ class UpstashVectorStoreComponent(LCVectorStoreComponent):
             display_name="Namespace",
             info="Leave empty for default namespace.",
         ),
-        MultilineInput(name="search_query", display_name="Search Query"),
+        *LCVectorStoreComponent.inputs,
         MultilineInput(
             name="metadata_filter",
             display_name="Metadata Filter",
             info="Filters documents by metadata. Look at the documentation for more information.",
         ),
-        DataInput(
-            name="ingest_data",
-            display_name="Ingest Data",
-            is_list=True,
-        ),
         HandleInput(
             name="embedding",
             display_name="Embedding",

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

@@ -1,11 +1,10 @@
 from typing import TYPE_CHECKING
 
 from langchain_community.vectorstores import Vectara
-from loguru import logger
 
 from langflow.base.vectorstores.model import LCVectorStoreComponent, check_cached_vector_store
 from langflow.helpers.data import docs_to_data
-from langflow.io import HandleInput, IntInput, MessageTextInput, SecretStrInput, StrInput
+from langflow.io import HandleInput, IntInput, SecretStrInput, StrInput
 from langflow.schema import Data
 
 if TYPE_CHECKING:
@@ -17,7 +16,6 @@ class VectaraVectorStoreComponent(LCVectorStoreComponent):
 
     display_name: str = "Vectara"
     description: str = "Vectara Vector Store with search capabilities"
-    documentation = "https://python.langchain.com/docs/modules/data_connection/vectorstores/integrations/vectara"
     name = "Vectara"
     icon = "Vectara"
 
@@ -30,16 +28,7 @@ class VectaraVectorStoreComponent(LCVectorStoreComponent):
             display_name="Embedding",
             input_types=["Embeddings"],
         ),
-        HandleInput(
+        *LCVectorStoreComponent.inputs,
-            name="ingest_data",
-            display_name="Ingest Data",
-            input_types=["Document", "Data"],
-            is_list=True,
-        ),
-        MessageTextInput(
-            name="search_query",
-            display_name="Search Query",
-        ),
         IntInput(
             name="number_of_results",
             display_name="Number of Results",
@@ -81,11 +70,11 @@ class VectaraVectorStoreComponent(LCVectorStoreComponent):
                 documents.append(_input)
 
         if documents:
-            logger.debug(f"Adding {len(documents)} documents to Vectara.")
+            self.log(f"Adding {len(documents)} documents to Vectara.")
             vector_store.add_documents(documents)
             self.status = f"Added {len(documents)} documents to Vectara"
         else:
-            logger.debug("No documents to add to Vectara.")
+            self.log("No documents to add to Vectara.")
             self.status = "No valid documents to add to Vectara"
 
     def search_documents(self) -> list[Data]:

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

@@ -58,7 +58,12 @@ class VectaraRagComponent(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),
         SecretStrInput(name="vectara_api_key", display_name="Vectara API Key", required=True),
-        MessageTextInput(name="search_query", display_name="Search Query", info="The query to receive an answer on."),
+        MessageTextInput(
+            name="search_query",
+            display_name="Search Query",
+            info="The query to receive an answer on.",
+            tool_mode=True,
+        ),
         FloatInput(
             name="lexical_interpolation",
             display_name="Hybrid Search Factor",

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

@@ -15,7 +15,6 @@ class VectaraSelfQueryRetriverComponent(CustomComponent):
 
     display_name: str = "Vectara Self Query Retriever for Vectara Vector Store"
     description: str = "Implementation of Vectara Self Query Retriever"
-    documentation = "https://python.langchain.com/docs/integrations/retrievers/self_query/vectara_self_query"
     name = "VectaraSelfQueryRetriver"
     icon = "Vectara"
     legacy = True

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

@@ -3,14 +3,13 @@ from langchain_community.vectorstores import Weaviate
 
 from langflow.base.vectorstores.model import LCVectorStoreComponent, check_cached_vector_store
 from langflow.helpers.data import docs_to_data
-from langflow.io import BoolInput, DataInput, HandleInput, IntInput, MultilineInput, SecretStrInput, StrInput
+from langflow.io import BoolInput, HandleInput, IntInput, SecretStrInput, StrInput
 from langflow.schema import Data
 
 
 class WeaviateVectorStoreComponent(LCVectorStoreComponent):
     display_name = "Weaviate"
     description = "Weaviate Vector Store with search capabilities"
-    documentation = "https://python.langchain.com/docs/modules/data_connection/vectorstores/integrations/weaviate"
     name = "Weaviate"
     icon = "Weaviate"
 
@@ -24,12 +23,7 @@ class WeaviateVectorStoreComponent(LCVectorStoreComponent):
             info="Requires capitalized index name.",
         ),
         StrInput(name="text_key", display_name="Text Key", value="text", advanced=True),
-        MultilineInput(name="search_query", display_name="Search Query"),
+        *LCVectorStoreComponent.inputs,
-        DataInput(
-            name="ingest_data",
-            display_name="Ingest Data",
-            is_list=True,
-        ),
         HandleInput(name="embedding", display_name="Embedding", input_types=["Embeddings"]),
         IntInput(
             name="number_of_results",

src/backend/base/langflow/initial_setup/starter_projects/vector_store_rag.py

@@ -33,7 +33,7 @@ def rag_graph():
     chat_input = ChatInput()
     rag_vector_store = AstraDBVectorStoreComponent()
     rag_vector_store.set(
-        search_input=chat_input.message_response,
+        search_query=chat_input.message_response,
         embedding_model=openai_embeddings.build_embeddings,
     )
 

src/backend/tests/integration/components/astra/test_astra_component.py

@@ -56,7 +56,6 @@ async def test_base(astradb_client: AstraDB):
         },
     )
 
-    assert results["vector_store"] is not None
     assert results["search_results"] == []
     assert astradb_client.collection(BASIC_COLLECTION)
 
@@ -73,7 +72,7 @@ async def test_astra_embeds_and_search():
             "api_endpoint": api_endpoint,
             "collection_name": BASIC_COLLECTION,
             "number_of_results": 1,
-            "search_input": "test1",
+            "search_query": "test1",
             "ingest_data": ComponentInputHandle(
                 clazz=TextToData, inputs={"text_data": ["test1", "test2"]}, output_name="from_text"
             ),
@@ -117,7 +116,7 @@ def test_astra_vectorize():
             api_endpoint=api_endpoint,
             collection_name=VECTORIZE_COLLECTION,
             ingest_data=records,
-            search_input="test",
+            search_query="test",
             number_of_results=2,
             pre_delete_collection=True,
         )
@@ -173,7 +172,7 @@ def test_astra_vectorize_with_provider_api_key():
             api_endpoint=api_endpoint,
             collection_name=VECTORIZE_COLLECTION_OPENAI,
             ingest_data=records,
-            search_input="test",
+            search_query="test",
             number_of_results=2,
             pre_delete_collection=True,
         )
@@ -228,7 +227,7 @@ def test_astra_vectorize_passes_authentication():
             api_endpoint=api_endpoint,
             collection_name=VECTORIZE_COLLECTION_OPENAI_WITH_AUTH,
             ingest_data=records,
-            search_input="test",
+            search_query="test",
             number_of_results=2,
             pre_delete_collection=True,
         )

src/backend/tests/unit/initial_setup/starter_projects/test_vector_store_rag.py

@@ -49,7 +49,7 @@ def rag_graph():
     chat_input.get_output("message").value = "What is the meaning of life?"
     rag_vector_store = AstraDBVectorStoreComponent(_id="rag-vector-store-123")
     rag_vector_store.set(
-        search_input=chat_input.message_response,
+        search_query=chat_input.message_response,
         api_endpoint="https://astra.example.com",
         token="token",  # noqa: S106
         embedding_model=openai_embeddings.build_embeddings,