vecindex: add adaptive search to increase accuracy #136032
Open
+573
−154
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
|
This change is |
andy-kimball
force-pushed
the
adaptive
branch
2 times, most recently
from
aa06355
to
c742e70
Compare
Adaptive search modifies the search algorithm to increase the search breadth in denser sections of the vector space and to decrease it in sparser sections. At each level of the tree, the search algorithm compiles a list of candidate partitions to search the next level down. It computes a Z-score for the candidates’ distances from the query vector, which indicates the “spread” of those distances, relative to the average. A negative Z-score indicates that partitions are more densely packed, and more should be searched. A positive Z-score indicates the opposite, and that fewer partitions should be searched. Epic: CRDB-42943 Release note: None
andy-kimball
force-pushed
the
adaptive
branch
from
c742e70
to
812c276
Compare
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Outdated suggestions cannot be applied.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.
Adaptive search modifies the search algorithm to increase the search breadth in denser sections of the vector space and to decrease it in sparser sections. At each level of the tree, the search algorithm compiles a list of candidate partitions to search the next level down. It computes a Z-score for the candidates’ distances from the query vector, which indicates the “spread” of those distances, relative to the average. A negative Z-score indicates that partitions are more densely packed, and more should be searched. A positive Z-score indicates the opposite, and that fewer partitions should be searched.
Epic: CRDB-42943
Release note: None