fix: refine_factor should be used in search_in_partition for IVF V2 Indices
#2933
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
chebbyChefNEQ
approved these changes
Sep 25, 2024
Codecov ReportAll modified and coverable lines are covered by tests ✅
Additional details and impacted files@@ Coverage Diff @@
## main #2933 +/- ##
==========================================
- Coverage 77.75% 77.74% -0.02%
==========================================
Files 231 231
Lines 70485 70487 +2
Branches 70485 70487 +2
==========================================
- Hits 54808 54799 -9
Misses 12773 12773
- Partials 2904 2915 +11
Flags with carried forward coverage won't be shown. Click here to find out more. ☔ View full report in Codecov by Sentry. |
ankitvij-db
pushed a commit
to ankitvij-db/lance
that referenced
this pull request
Sep 26, 2024
…V2 Indices (lancedb#2933) In testing we saw that `refine_factor` was not increasing recall even when set to a large enough value that it should be doing brute force search in V3 indices. After tracing through the code we found that `refine_factor` was not being utilized in the individual partitions `search_in_partition` function, so they could only return at most `k` values to be refined. This change makes it so that the `search_in_partition` function will return `refine_factor * k` values for further refinement.
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
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Outdated suggestions cannot be applied.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 testing we saw that
refine_factorwas not increasing recall even when set to a large enough value that it should be doing brute force search in V3 indices. After tracing through the code we found thatrefine_factorwas not being utilized in the individual partitionssearch_in_partitionfunction, so they could only return at mostkvalues to be refined. This change makes it so that thesearch_in_partitionfunction will returnrefine_factor * kvalues for further refinement.