msokolov commented on PR #15090: URL: https://github.com/apache/lucene/pull/15090#issuecomment-3292278407
> Are we cool with writing that stuff to metadata and loading? If so, I can make a chnage this week so we can see it in action and then go through the process of adding a new HNSW format that satisfies this. I think it's fine, thanks for volunteering. This should make extensibility, configuration, and so on easier. As this gets more complex I think we need it. It's not easy to find a one-size-fits-all setting; we know for example that different quantization settings are appropriate with different use cases and vector data varies a lot in its compressibility. Unless we're willing to fully embed hyper-parameter optimization into Lucene (and we shouldn't, it's too much magic) I think we have to expose the complexity to users so they can choose. -- 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
