benwtrent commented on issue #12313: URL: https://github.com/apache/lucene/issues/12313#issuecomment-2108168850
> Not sure I understand option 3. Are you thinking that graph has different types of edges b/w documents based on diff. similarity functions? So if you were using max similarity you would follow one path, but if you wanted avg. similarity, you might use a different set of edges? Option 3 is the same as option 2, except on graph building we ensure the connectivity between the vertices (still docs with multi-vectors) reflects the connections that would have been built if each vector was vertex. This would significantly increase document connections and could slow down search/index times but would (conceivably) improve recall. Maybe option 2 is enough, and recall & speed tradeoff is still good enough given our current parameters (maxConn & beamwidth). -- 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
