enh: enable reranking through Cross Encoding#73
Open
VarinThakur01 wants to merge 29 commits intomainfrom
Open
Conversation
yonarw
reviewed
Mar 26, 2026
yonarw
reviewed
Mar 27, 2026
Contributor
yonarw
left a comment
There was a problem hiding this comment.
Three smaller remarks left, otherwise good for merge.
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
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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 PR adds the feature of reranking results using Cross Encoding.
The following things have been added
rerank_configinside the existing similarity search methods to support reranking.HanaRerankeras a standalone reranker to rerank documents.PR Extensions (For future)
VECTOR_EMBEDDING()andCROSS_ENCODE())similarity_search_with_relevance_scores()function doesn't support reranking as it uses the implementation from the parent class. (As the relevance functions are not properly set, we will add the support of reranking in a future PR after fixing therelevance_scorefunctions)