Skip to content

Conversation

@DosticJelena
Copy link

Changes included in this PR:

  • created new type VectorStoreSparseEncoder and added new field of that type to PineconeVectorStore
  • added SPLADE and BM25 (beside SparseDict) from pinecone_text library as sparse/hybrid query mode options
  • included query_embedding to all query modes
  • added vector store and query mode compatibility check

Note: Please do not merge this PR

@DosticJelena DosticJelena force-pushed the hybrid_search_optimizations branch from 1b69715 to 69f5a13 Compare October 24, 2023 11:53
Copy link

@jamescalam jamescalam left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

lgtm! Thanks!

@DosticJelena DosticJelena force-pushed the hybrid_search_optimizations branch from 69f5a13 to b821625 Compare November 22, 2023 09:45
@DosticJelena DosticJelena force-pushed the hybrid_search_optimizations branch from 8ba159f to 93d9eee Compare December 29, 2023 15:09
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

2 participants