fix: consistent score calculation in FAISSRetriever#2434
Open
0xbyt4 wants to merge 1 commit intoOpenMind:mainfrom
Open
fix: consistent score calculation in FAISSRetriever#24340xbyt4 wants to merge 1 commit intoOpenMind:mainfrom
0xbyt4 wants to merge 1 commit intoOpenMind:mainfrom
Conversation
search() used raw FAISS distance as score while batch_search() used 1/(1+dist) normalization. Same distance value produced different scores depending on which method was called (e.g., 0.1 vs 0.909 for dist=0.1). Align search() to use the same normalization formula as batch_search().
github-actions
bot
added
robotics
Codecov Report✅ All modified and coverable lines are covered by tests. 📢 Thoughts on this report? Let us know! |
This file contains hidden or 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
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Summary
search()returned raw FAISS distance as score whilebatch_search()used1/(1+dist)normalizationquery()but 0.909 viaquery_batch()search()to use the same1/(1+dist)formula asbatch_search()