vecindex: redistribute vectors across level during split #135506
+450
−111
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
When a partition is split, move vectors to closer partitions: * For each vector in the splitting partition, move it to a "sibling" partition if its centroid is closer. * For each nearby vector at the same level as the splitting partition, move it to the splitting partition if its centroid is closer. These optimizations significantly increase the recall rate of searches. Prevent non-leaf-level partitions from becoming empty due to moving vectors between partitions, since that would cause the K-means tree to become unbalanced. Epic: CRDB-42943 Release note: None
|
This change is |
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Outdated suggestions cannot be applied.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.
When a partition is split, move vectors to closer partitions:
These optimizations significantly increase the recall rate of searches.
Prevent non-leaf-level partitions from becoming empty due to moving vectors between partitions, since that would cause the K-means tree to become unbalanced.
Epic: CRDB-42943
Release note: None