vigyasharma commented on PR #14009: URL: https://github.com/apache/lucene/pull/14009#issuecomment-2900200570
@dungba88 : I shared an [alternate implementation](https://github.com/apache/lucene/pull/14698) for RerankVectorQuery that I feel can generalize more broadly. **Main Differences:** 1. While the primary use case would be to rerank results from a quantized `KnnFloatVectorQuery` against full precision vectors, this approach has no tight coupling. Users could provide any inner query and rerank against vectors stored in any field. 2. This can, in future, be extended to support reranking using Late Interaction models stored in a different field. We just need to override add some checks to ensure multi-vectors in provided `field` are compatible with provided `target`. This idea has been floated [here](https://github.com/apache/lucene/pull/13525#issuecomment-2445295372) earlier 3. Maintains a regular query flow of keeping heavier computation in Weight and Scorer, instead of heavy matching and scoring logic in rewrite. 4. This should implicitly use any slicing or per leaf parallel execution provided at searchers. We don't need to rewrite logic for per leaf threads. Please know that I don't mean to override your work, just needed to write it down to clarify my ideas. I'm happy to collaborate on whatever direction makes most sense. -- This is an automated message from the Apache Git Service. To respond to the message, please log on to GitHub and use the URL above to go to the specific comment. To unsubscribe, e-mail: issues-unsubscr...@lucene.apache.org For queries about this service, please contact Infrastructure at: us...@infra.apache.org --------------------------------------------------------------------- To unsubscribe, e-mail: issues-unsubscr...@lucene.apache.org For additional commands, e-mail: issues-h...@lucene.apache.org
