-
Notifications
You must be signed in to change notification settings - Fork 25.7k
DiskBBQ to dynamically adapt nProbe when centroids scores diff is large-ish (multi segment case) #131911
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
Closed
Conversation
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
Contributor
Author
|
the first implementation calculates the difference in percentage between the score of the closest centroid with the score of the nProbe-th centroid and it doubles |
Contributor
Author
|
For example with multiple segments on Wikipedia dataset with Cohere-1024 embeddings current candidate |
Contributor
Author
|
this is being superseeded by #132396 |
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Outdated suggestions cannot be applied.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.
This is a first attempt at dynamically adapt each segment's
nProbeparam to the distribution of the centroids wrt a specific query vector.This seeks to detect if a specific query vector lies close to most of
nProbecentroids, if so, it might be worth to explore more centroids.See #129290.
this patch also adds a
merge_policyparam toKnnIndexTesterso that we could better test differing numbers of merge policies (for this patch it was useful to set it to"merge_policy" : "no", "forge_merge" : false, to search with multiple segments).