Rassyan commented on issue #14007: URL: https://github.com/apache/lucene/issues/14007#issuecomment-2491209549
Excuse my ignorance, but I was wondering... > quantization methodologies can easily "re-hydrate" vectors so that iterating floats is still possible Could you elaborate on the computational costs associated with this? If the need to retrieve floats from users is not present, is it feasible to skip this rehydration step and directly use the quantized vectors for distance calculations? > higher fidelity quantization methods So, would int7 be considered a higher fidelity quantization method? Based on your experience and insights, how would you rate the fidelity of int7, int4, and binary quantization methods? Where do they stand in terms of maintaining accuracy while optimizing storage efficiency? Has the Lucene community already planned or discussed the implementation of a dedicated KnnVectorsFormat for handling only quantized vectors? Are there quick support mechanisms for users who are willing to compromise on accuracy for significant savings in disk space and do not require the original vectors? -- 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
