Enable kwargs in SearchIndex and Embedding Retriever - 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

121 stars 119 forks source link

Enable kwargs in SearchIndex and Embedding Retriever #1185

Closed Amnah199 closed 1 week ago

Amnah199 commented 1 week ago

Related Issues

fixes issue discussed here: https://github.com/deepset-ai/haystack-core-integrations/pull/1122#discussion_r1805588806

Proposed Changes:

Allow users to pass kwargs to SearchIndex and client.search to enable configuration of semantic ranking if needed.
Removed passing DuplicatePolicy to the document store as its not needed.
Added a wait_for_index_deletion to ensure the index is deleted after each test to prevent failures caused by max no. of indexes allowed.

How did you test it?

Ran the tests
Locally tested an example for semantic ranking

Notes for the reviewer

NA

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:.

Amnah199 commented 1 week ago

@ttmenezes would be nice to have your review as well.