benwtrent opened a new pull request, #13181:
URL: https://github.com/apache/lucene/pull/13181
With quantized vectors, and with current vectors, we separate out the
"scoring" vs. "iteration", requiring the user to always iterate the raw vectors
and provide their own similarity function.
While this is flexible, it creates frustration in:
- Just iterating and scoring, especially since the field already has a
similarity function stored...Why can't we just know which one to use and use it!
- Iterating and scoring quantized vectors. By default it would be good to
be able to iterate and score quantized vectors (e.g. without going through the
HNSW graph).
I see two options on providing this:
- A new top level thing on the LeafReader (getVectorScorer or something).
- Extend the vector value iterators to be able to return a scorer given
some vector value (what this PR demonstrates).
This is a POC, not all interfaces are supplied. I am opening what I have for
discussion.
Folks who might be interested: @jpountz @msokolov @mccullocht
--
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
