jyapayne/langflow
1
0
Fork 0
Code Issues Pull requests Projects Releases 1 Packages Wiki Activity Actions

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

Browse source 
* 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>
This commit is contained in:
Eric Hare 2024-12-19 08:49:09 -08:00 • committed by GitHub
commit 22877ae920
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
28 changed files with 412 additions and 572 deletions
Download patch file Download diff file Expand all files Collapse all files

23
src/backend/base/langflow/base/vectorstores/model.py
View file

@ -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}")
logger.debug(f"Search type: {self.search_type}")
logger.debug(f"Number of results: {self.number_of_results}")
self.log(f"Search input: {search_query}")
self.log(f"Search type: {self.search_type}")
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

180
src/backend/base/langflow/components/vectorstores/astradb.py
View file

@ -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"
documentation: str = "https://docs.langflow.org/starter-projects-vector-store-rag"
description: str = "Ingest and search documents in Astra DB"
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(
list,
{
"Azure OpenAI": [
"azureOpenAI",
["text-embedding-3-small", "text-embedding-3-large", "text-embedding-ada-002"],
],
"Hugging Face - Dedicated": ["huggingfaceDedicated", ["endpoint-defined-model"]],
"Hugging Face - Serverless": [
"huggingface",
[
"sentence-transformers/all-MiniLM-L6-v2",
"intfloat/multilingual-e5-large",
"intfloat/multilingual-e5-large-instruct",
"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"],
],
},
)
base_inputs = LCVectorStoreComponent.inputs
if "search_query" not in [input_.name for input_ in base_inputs]:
base_inputs.append(
MessageTextInput(
name="search_query",
display_name="Search Query",
tool_mode=True,
)
)
if "ingest_data" not in [input_.name for input_ in base_inputs]:
base_inputs.append(
DataInput(
name="ingest_data",
display_name="Ingest Data",
)
)
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",
info="API endpoint URL for the Astra DB service.",
value="ASTRA_DB_API_ENDPOINT",
display_name="Database",
info="The Astra DB Database to use.",
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(
name="ingest_data",
display_name="Ingest Data",
),
MultilineInput(
name="search_input",
display_name="Search Query",
tool_mode=True,
),
*base_inputs,
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):
# 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
def get_vectorize_providers(self):
try:
self.log("Dynamically updating list of Vectorize providers.")
# Get the admin object
client = DataAPIClient(token=self.token)
admin = client.get_admin()
admin = AstraDBAdmin(token=self.token)
db_admin = admin.get_database_admin(self.get_api_endpoint())
# Get the embedding providers
db_admin = admin.get_database_admin(self.api_endpoint)
# Get the list of embedding providers
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
build_config["collection_name"]["options"] = self._initialize_collection_options()
# Always attempt to update the database list
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 = (
parse_api_endpoint(getattr(self, "api_endpoint", None)).environment
if getattr(self, "api_endpoint", None)
else None
)
environment = parse_api_endpoint(self.get_api_endpoint()).environment if self.get_api_endpoint() 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,
**embedding_params,
**self.astradb_vectorstore_kwargs,
**autodetect_params or {},
**embedding_params or {},
**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}")

46
src/backend/base/langflow/components/vectorstores/astradb_graph.py
View file

@ -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(
name="search_input",
display_name="Search Input",
),
DataInput(
name="ingest_data",
display_name="Ingest Data",
is_list=True,
),
*LCVectorStoreComponent.inputs,
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.")
logger.debug(f"Search input: {self.search_input}")
logger.debug(f"Search type: {self.search_type}")
logger.debug(f"Number of results: {self.number_of_results}")
self.log("Searching for documents in AstraDBGraphVectorStore.")
self.log(f"Search query: {self.search_query}")
self.log(f"Search type: {self.search_type}")
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):

28
src/backend/base/langflow/components/vectorstores/cassandra.py
View file

@ -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,
),
MultilineInput(name="search_query", display_name="Search Query"),
DataInput(
name="ingest_data",
display_name="Ingest Data",
is_list=True,
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}")
logger.debug(f"Search type: {self.search_type}")
logger.debug(f"Number of results: {self.number_of_results}")
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}")
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

29
src/backend/base/langflow/components/vectorstores/cassandra_graph.py
View file

@ -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,
),
MultilineInput(name="search_query", display_name="Search Query"),
DataInput(
name="ingest_data",
display_name="Ingest Data",
is_list=True,
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}")
logger.debug(f"Search type: {self.search_type}")
logger.debug(f"Number of results: {self.number_of_results}")
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}")
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

18
src/backend/base/langflow/components/vectorstores/chroma.py
View file

@ -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(
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"]),
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.")

6
src/backend/base/langflow/components/vectorstores/clickhouse.py
View file

@ -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"),
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",

10
src/backend/base/langflow/components/vectorstores/couchbase.py
View file

@ -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"),
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",

27
src/backend/base/langflow/components/vectorstores/elasticsearch.py
View file

@ -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(
name="search_input",
display_name="Search Input",
info="Enter a search query. Leave empty to retrieve all documents.",
),
*LCVectorStoreComponent.inputs,
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"],

26
src/backend/base/langflow/components/vectorstores/faiss.py
View file

@ -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(
name="search_query",
display_name="Search Query",
),
DataInput(
name="ingest_data",
display_name="Ingest Data",
is_list=True,
),
*LCVectorStoreComponent.inputs,
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}")
logger.debug(f"Number of results: {self.number_of_results}")
self.log(f"Search input: {self.search_query}")
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)}")
logger.debug(data)
self.log(f"Converted documents to data: {len(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 []

34
src/backend/base/langflow/components/vectorstores/hcd.py
View file

@ -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(
name="search_input",
display_name="Search Input",
),
DataInput(
name="ingest_data",
display_name="Ingest Data",
is_list=True,
),
*LCVectorStoreComponent.inputs,
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}")
logger.debug(f"Search type: {self.search_type}")
logger.debug(f"Number of results: {self.number_of_results}")
self.log(f"Search query: {self.search_query}")
self.log(f"Search type: {self.search_type}")
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):

10
src/backend/base/langflow/components/vectorstores/milvus.py
View file

@ -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"),
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",

10
src/backend/base/langflow/components/vectorstores/mongodb_atlas.py
View file

@ -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"),
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",

40
src/backend/base/langflow/components/vectorstores/opensearch.py
View file

@ -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(
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,
),
*LCVectorStoreComponent.inputs,
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

10
src/backend/base/langflow/components/vectorstores/pgvector.py
View file

@ -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"),
DataInput(
name="ingest_data",
display_name="Ingestion Data",
is_list=True,
),
*LCVectorStoreComponent.inputs,
HandleInput(name="embedding", display_name="Embedding", input_types=["Embeddings"]),
IntInput(
name="number_of_results",

10
src/backend/base/langflow/components/vectorstores/pinecone.py
View file

@ -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"),
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",

10
src/backend/base/langflow/components/vectorstores/qdrant.py
View file

@ -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"),
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",

10
src/backend/base/langflow/components/vectorstores/redis.py
View file

@ -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"),
DataInput(
name="ingest_data",
display_name="Ingest Data",
is_list=True,
),
*LCVectorStoreComponent.inputs,
IntInput(
name="number_of_results",
display_name="Number of Results",

10
src/backend/base/langflow/components/vectorstores/supabase.py
View file

@ -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"),
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",

9
src/backend/base/langflow/components/vectorstores/upstash.py
View file

@ -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",

19
src/backend/base/langflow/components/vectorstores/vectara.py
View file

@ -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(
name="ingest_data",
display_name="Ingest Data",
input_types=["Document", "Data"],
is_list=True,
),
MessageTextInput(
name="search_query",
display_name="Search Query",
),
*LCVectorStoreComponent.inputs,
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]:

7
src/backend/base/langflow/components/vectorstores/vectara_rag.py
View file

@ -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",

1
src/backend/base/langflow/components/vectorstores/vectara_self_query.py
View file

@ -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

10
src/backend/base/langflow/components/vectorstores/weaviate.py
View file

@ -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"),
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",

388
src/backend/base/langflow/initial_setup/starter_projects/Vector Store RAG.json
View file

File diff suppressed because one or more lines are too long

2
src/backend/base/langflow/initial_setup/starter_projects/vector_store_rag.py
View file

@ -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,
)

9
src/backend/tests/integration/components/astra/test_astra_component.py
View file

@ -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,
)

2
src/backend/tests/unit/initial_setup/starter_projects/test_vector_store_rag.py
View file

@ -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,