Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

fix(reranking): uses semantic search score #198

Merged
merged 1 commit into from
Nov 7, 2023

Conversation

massi-ang
Copy link
Collaborator

Fills up the documents returned by the retriever with the top scored semantic search documents

Issue #, if available:

Fix #197

Description of changes:
The fill-up logic is changed so:

  • only selects records that have a semantic search score and ignore other records
  • for aurora takes into consideration that "inner" metric produces negative values
  • correctly implements the filtering of the top-k items

By submitting this pull request, I confirm that you can use, modify, copy, and redistribute this contribution, under the terms of your choice.

Fills up the documents returned by the retriever with
the top scored semantic search documents
@bigadsoleiman bigadsoleiman merged commit 5776d33 into aws-samples:main Nov 7, 2023
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
Status: Done
Development

Successfully merging this pull request may close these issues.

Error when using opensearch or aurora workspaces and hybrid search
2 participants