fix: Astra - fix embedding retrieval top-k limit - Githubissues

deepset-ai / haystack-core-integrations

Additional packages (components, document stores and the likes) to extend the capabilities of Haystack version 2.0 and onwards

https://haystack.deepset.ai

Apache License 2.0

122 stars 120 forks source link

fix: Astra - fix embedding retrieval top-k limit #1210

Closed basoko closed 12 hours ago

basoko commented 3 days ago

Related Issues

fixes #1204

Proposed Changes:

After upgrading the astrapy lib #1145 there is a bug that don't limit the number of results when using an embedding search. As a result of this, many more expected documents are retrieved.

How did you test it?

Integration test.

Notes for the reviewer

Add test_embedding_retrieval.py following the same pattern as in other store integrations.

Checklist

I have read the contributors guidelines and the code of conduct
I have updated the related issue with new insights and changes
I added unit tests and updated the docstrings
I've used one of the conventional commit types for my PR title: fix:, feat:, build:, chore:, ci:, docs:, style:, refactor:, perf:, test:.

davidsbatista commented 3 days ago

Hi @basoko, and thanks for your contribution! The changes look good to me, I will nevertheless have @Amnah199 haver another look, before approvalal.

davidsbatista commented 15 hours ago

@Amnah199 I've already had a look, LGTM, can you have a quick second look?