Remove explicit K from exact search context #2212
Closed
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
VijayanB
requested review from
heemin32,
navneet1v,
vamshin,
jmazanec15,
naveentatikonda,
junqiu-lei,
martin-gaievski,
ryanbogan,
luyuncheng and
shatejas
as code owners
VijayanB
changed the title
VijayanB
added
backport 2.x
Refactoring
K can be extracted from knn query instead of explicitly passing as input to ExactSearch Context. Previously this was added mainly with assumption that 'k' can be different from Query if rescore context is not null. However, the main reason we have different K from Query is due to quantization. Having larger K is apt for Approx search, for exact search we don't need to collect more than expected top k from query. Signed-off-by: Vijayan Balasubramanian <[email protected]>
If we are approximating distance with exact search, why not maintain oversample? |
|
Closing this PR since this is required for oversampling. |
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Outdated suggestions cannot be applied.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.
Description
K can be extracted from knn query instead of explicitly passing as input to ExactSearch Context. Previously this was
added mainly with assumption that 'k' can be different from Query if rescore context is not null. However, the main reason we have different K from Query is due to quantization. Having larger K is apt for Approx search, for exact search we don't need to collect more than expected top k from query.
Related Issues
Check List
--signoff.By submitting this pull request, I confirm that my contribution is made under the terms of the Apache 2.0 license.
For more information on following Developer Certificate of Origin and signing off your commits, please check here.