alessandrobenedetti commented on PR #12679: URL: https://github.com/apache/lucene/pull/12679#issuecomment-2126740768
Hi @kaivalnp, thanks for this contribution! My question is why do we have two thresholds, one for grap traversal (used to decide if it's worth exploring a candidate neighbour) and the resulting threshold (used to accept or not a result)? The lower the traversal threshold, the longer the search but the more likely the possibility of finding more vectors within the accepted threshold. The higher the traversal threshold, the shorter the search but you are less likely to find all vectors within the accepted threshold. Is it a matter of tuning? Did I get it right? -- 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
