Closed
Description
Is this a new bug in the Pinecone Python client?
- I believe this is a new bug in the Pinecone Python Client
- I have searched the existing issues, and I could not find an existing issue for this bug
Current Behavior
If you query pinecone index with a vector ID with topk=1, the returned vectors sometimes have different id. If you keep top_k > 1, sometimes the correct vector is found in positions k>1.
Expected Behavior
If I search using vector id, the whole point is to get the vector whose id matches the query. Then find other vectors with high similarity scores.
Steps To Reproduce
It's hard to provide a reproducible steps, because it happens sometimes. We see it happening a lot in our production environment. So I rather attach some relevant screenshots from the UI.
checkour more examples https://community.pinecone.io/t/bug-pinecone-search-by-id-is-returning-incorrect-result/5554
Relevant log output
check https://community.pinecone.io/t/bug-pinecone-search-by-id-is-returning-incorrect-result/5554
Environment
- OS:
- Python:
- pinecone:
Additional Context
No response