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

chore: Updating Vectara Vector Store parameters format

Browse source
This commit is contained in:
joaoguilhermeS 2024-06-22 17:41:04 -03:00 • committed by Gabriel Luiz Freitas Almeida
commit 43a781b001
1 changed files with 20 additions and 26 deletions
Download patch file Download diff file Expand all files Collapse all files

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

@ -12,24 +12,19 @@ from langflow.schema import Data
class VectaraVectorStoreComponent(LCVectorStoreComponent):
display_name = "Vectara"
description = "Vectara Vector Store with search capabilities"
documentation = "https://python.langchain.com/docs/modules/data_connection/vectorstores/integrations/vectara"
documentation = "https://python.langchain.com/v0.2/docs/integrations/vectorstores/vectara/"
icon = "Vectara"
inputs = [
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),
MultilineInput(name="search_query", display_name="Search Query"),
DataInput(
name="vector_store_inputs",
name="ingest_data",
display_name="Vector Store Inputs",
is_list=True,
),
BoolInput(
name="add_to_vector_store",
display_name="Add to Vector Store",
info="If true, the Vector Store Inputs will be added to the Vector Store.",
),
MultilineInput(name="search_input", display_name="Search Input"),
IntInput(
name="number_of_results",
display_name="Number of Results",
@ -45,23 +40,22 @@ class VectaraVectorStoreComponent(LCVectorStoreComponent):
def _build_vectara(self) -> Vectara:
source = "Langflow"
if self.add_to_vector_store:
documents = []
for _input in self.vector_store_inputs or []:
if isinstance(_input, Data):
documents.append(_input.to_lc_document())
else:
documents.append(_input)
documents = []
for _input in self.ingest_data or []:
if isinstance(_input, Data):
documents.append(_input.to_lc_document())
else:
documents.append(_input)
if documents:
return Vectara.from_documents(
documents=documents,
embedding=FakeEmbeddings(size=768),
vectara_customer_id=self.vectara_customer_id,
vectara_corpus_id=self.vectara_corpus_id,
vectara_api_key=self.vectara_api_key,
source=source,
)
if documents:
return Vectara.from_documents(
documents=documents,
embedding=FakeEmbeddings(size=768),
vectara_customer_id=self.vectara_customer_id,
vectara_corpus_id=self.vectara_corpus_id,
vectara_api_key=self.vectara_api_key,
source=source,
)
return Vectara(
vectara_customer_id=self.vectara_customer_id,
@ -73,9 +67,9 @@ class VectaraVectorStoreComponent(LCVectorStoreComponent):
def search_documents(self) -> List[Data]:
vector_store = self._build_vectara()
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():
docs = vector_store.similarity_search(
query=self.search_input,
query=self.search_query,
k=self.number_of_results,
)