adrian-wang opened a new pull request, #115:
URL: https://github.com/apache/paimon-vector-index/pull/115

   Use the complete distance-table range instead of the first 200 vector 
scores, which can clip unseen entries and corrupt inner-product ranking. Cover 
table-range extremes and single/batch search through the in-memory, FastScan, 
and persisted reader paths. Initialize the regression test's PQ codebook 
through the public setter so its derived caches stay consistent.
   
   Validation: Rust 1.95 core tests (664 passed, 2 ignored) and rustfmt.


-- 
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]

Reply via email to