benwtrent commented on PR #15903:
URL: https://github.com/apache/lucene/pull/15903#issuecomment-4165103849

   ```
   recall  latency(ms)  netCPU  avgCpuCount     nDoc  topK  fanout  maxConn  
beamWidth  quantized  index(s)  index_docs/s  force_merge(s)  num_segments  
index_size(MB)  vec_disk(MB)  vec_RAM(MB)  indexType
   0.954        1.222   1.217        0.996  1000000    10     100       32      
  250    -8 bits    333.87       2995.20          193.90             1         
3717.10      3677.368      747.681       HNSW
   ```
   
   Thats the last run @mccullocht did for Lucene's OSQ technique.
   
   I realize performance apples to apples will take way more work (panama 
vector APIs, etc.). I am more concerned about recall, and I am not sure TQ will 
provide any significant recall improvement itself. 
   
   The main thing I think that OSQ might be missing is some random rotation for 
non-guassian component vectors (which are an anomaly for the modern models). 
But, adding that to the existing OSQ for Lucene would be a snap (though careful 
thought would be needed as that could be a significant performance burden with 
very little benefit for many users).
   


-- 
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