This repository has been archived by the owner on Oct 30, 2024. It is now read-only.
fix: do not min/max-normalize already normalized similarity scores to not distort them #107
Conversation
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
… not distort them
Sign up for free
to subscribe to this conversation on GitHub.
Already have an account?
Sign in.
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
In our default flows, we're using a merging retriever with similarity search and bm25 search.
The similarityScores from the similarity search are already normalized (0-1 range), while the bm25 Scores are not.
Before this change we still did a min/max-normalization even over the observed similarityScores, which distorted them so much that it significantly impacted the merged document score.
For the future we may consider using zScore normalization - #106