Reciprocal Rank Fusion (RRF) normalization technique in hybrid query #874
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
added 4 commits
August 16, 2024 12:33
Signed-off-by: Isaac Johnson <[email protected]>
Signed-off-by: Isaac Johnson <[email protected]>
Signed-off-by: Isaac Johnson <[email protected]>
Signed-off-by: Isaac Johnson <[email protected]>
Johnsonisaacn
changed the title
Johnsonisaacn
requested review from
heemin32,
navneet1v,
VijayanB,
vamshin,
jmazanec15,
naveentatikonda,
junqiu-lei,
martin-gaievski,
sean-zheng-amazon,
model-collapse,
zane-neo,
ylwu-amzn,
jngz-es,
vibrantvarun and
zhichao-aws
as code owners
vibrantvarun
changed the title
vibrantvarun
changed the title
Signed-off-by: Isaac Johnson <[email protected]>
|
we should be merging to feature branch https://github.com/opensearch-project/neural-search/tree/feature/rrf-score-normalization, not main. |
| List<TopDocs> topDocsPerSubQuery = compoundQueryTopDocs.getTopDocs(); | ||
| int numSubQueriesBound = topDocsPerSubQuery.size(); | ||
| for (int index = 0; index < numSubQueriesBound; index++) { | ||
| int numDocsPerSubQueryBound = topDocsPerSubQuery.get(index).scoreDocs.length; |
There was a problem hiding this comment.
we can have score docs array as a variable, should save few cpu cycles.
ScoreDoc[] scoreDocs = topDocsPerSubQuery.get(index).scoreDocs;
| @NonNull | ||
| private ScoreCombinationTechnique combinationTechnique; | ||
| @Nullable | ||
| private int rankConstant; |
There was a problem hiding this comment.
the rank constant should be a parameter for RRF normalization technique class, not the high level field in this DTO. You can pass it as param to RRF normalization technique constructor while creating its instance in a factory class
Johnsonisaacn
changed the base branch from
main
to
feature/rrf-score-normalization
Johnsonisaacn
changed the base branch from
feature/rrf-score-normalization
to
feature/rrf-score-normalization-v2
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
Adding ability to process and combine scores from multiple subqueries in neural search using the reciprocal rank fusion (RRF) technique. Built with a new processor and processor factory class apart from NormalizationProcessor. Changes to API included in RFC. Does not currently support weights when combining processed subquery scores, based on lack of examples in existing literature.
Related Issues
Resolves #[Issue number to be closed when this PR is merged]
#865
#659
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.