This repository has been archived by the owner on Nov 21, 2024. It is now read-only.
Support unlimited KNN search #43
Merged
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
save-buffer
reviewed
Aug 28, 2023
There was a problem hiding this comment.
I think looks good besides a few typos. Just to understand correctly: you are making it so that if we call gettuple many times, and we've run out of results, we'll re-search the index, returning more and more results each time? Is there a guarantee that searching with a larger ef_search will return all the same records, plus more?
Co-authored-by: Sasha Krassovsky <[email protected]>
Co-authored-by: Sasha Krassovsky <[email protected]>
knizhnik
force-pushed
the
unlimited_knn
branch
from
2b3e013 to
c1f81b2
Compare
save-buffer
approved these changes
Aug 30, 2023
Sign up for free
to subscribe to this conversation on GitHub.
Already have an account?
Sign in.
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Outdated suggestions cannot be applied.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.
Number of results returned HNSW search is limited by K=efSearch parameter.
But if query need to perform extra filtering of the results, then efSearch results may be not enough.
This PR repeats search with doubled efSearch parameter.