kaivalnp commented on issue #12579: URL: https://github.com/apache/lucene/issues/12579#issuecomment-1762822602
Thanks @msokolov, this nicely summarizes what I'm trying to say! > https://typesense.org/docs/0.25.0/api/vector-search.html#distance-threshold I took a look here: and [seems like](https://github.com/typesense/typesense/blob/3bbfe20fcc126fa1a26099ff0022e235e81d1662/src/index.cpp#L2916-L2940) they first perform kNN searches, and then remove results below the threshold (like a post-filtering step that you mentioned) > since you can simulate this with a threshold + large K Yes, this would be the easiest way to find all (or a large number of) vectors within a radius using the existing `Knn[Byte|Float]VectorQuery` classes Interestingly, the threshold-based search proposed above may not need *any* invasive changes thanks to the amazing `KnnCollector` API added in #12434, so I wonder if we can start there directly? Opening a PR to discuss next steps.. -- 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
