jbellis commented on issue #12615:
URL: https://github.com/apache/lucene/issues/12615#issuecomment-1772722737

   > It is possible that the candidate postings (gathered via HNSW) don't 
contain ANY filtered docs. This would require gathering more candidate postings.
   
   This was a big problem for our initial deployment, we'd filter down to a few 
valid items and then spend forever searching the graph for them.  Had to add a 
fairly accurate estimate of how many comparisons the index would need, and use 
that to decide whether to brute-force the comparison instead.  (This is in 
Cassandra, not JVector, specifically VectorMemtableIndex.expectedNodesVisited.) 
 I don't remember seeing code for this in Lucene but I mostly only looked at 
the HNSW code so I could have missed it.


-- 
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: [email protected]

For queries about this service, please contact Infrastructure at:
[email protected]


---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]

Reply via email to