github/langchain
1
0
Fork 0
mirror of https://github.com/hwchase17/langchain.git synced 2025-08-19 17:45:25 +00:00
Code Issues Packages Projects Releases Wiki Activity

Add search_kwargs option for VectorDBQAWithSourcesChain (#657)

Browse Source 
Allows for passing additional vectorstore params like namespace, etc. to
VectorDBQAWithSourcesChain

Example:
`chain = VectorDBQAWithSourcesChain.from_llm(OpenAI(temperature=0),
vectorstore=store, search_kwargs={"namespace": namespace})`
This commit is contained in:
iocuydi 2023-01-19 16:48:13 -06:00 committed by GitHub
parent bfb23f4608
commit 207e319a70
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
1 changed files with 6 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

7
langchain/chains/qa_with_sources/vector_db.py
View File

@ -14,7 +14,12 @@ class VectorDBQAWithSourcesChain(BaseQAWithSourcesChain, BaseModel):
vectorstore: VectorStore vectorstore: VectorStore
"""Vector Database to connect to.""" """Vector Database to connect to."""
k: int = 4 k: int = 4
"""Number of results to return from store"""
search_kwargs: Dict[str, Any] = {}
"""Extra search args"""
def _get_docs(self, inputs: Dict[str, Any]) -> List[Document]: def _get_docs(self, inputs: Dict[str, Any]) -> List[Document]:
question = inputs[self.question_key] question = inputs[self.question_key]
return self.vectorstore.similarity_search(question, k=self.k) return self.vectorstore.similarity_search(
question, k=self.k, **self.search_kwargs
)