Add _similarity_search_with_relevance_scores in Pinecone (#6446)

Just so it is consistent with other `VectorStore` classes.

This is a follow-up of #6056 which also discussed the potential of
adding `similarity_search_by_vector_returning_embeddings` that we will
continue the discussion here.

potentially related: #6286 


#### Who can review?

Tag maintainers/contributors who might be interested: @rlancemartin 

<!-- For a quicker response, figure out the right person to tag with @

  @hwchase17 - project lead

  Tracing / Callbacks
  - @agola11

  Async
  - @agola11

  DataLoaders
  - @eyurtsev

  Models
  - @hwchase17
  - @agola11

  Agents / Tools / Toolkits
  - @hwchase17

  VectorStores / Retrievers / Memory
  - @dev2049

 -->
This commit is contained in:
Wenchen Li 2023-06-20 12:36:40 +08:00 committed by GitHub
parent d4e8e0f5ab
commit 76ae9da9db
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23

View File

@ -160,6 +160,14 @@ class Pinecone(VectorStore):
)
return [doc for doc, _ in docs_and_scores]
def _similarity_search_with_relevance_scores(
self,
query: str,
k: int = 4,
**kwargs: Any,
) -> List[Tuple[Document, float]]:
return self.similarity_search_with_score(query, k)
def max_marginal_relevance_search_by_vector(
self,
embedding: List[float],