PeterCorless commented on PR #11262:
URL: https://github.com/apache/pinot/pull/11262#issuecomment-1939243726
> do we have a design doc or goals for supporting vector data types?
>
> e.g.
>
> * do we plan to support vector embeddings mostly as similarity search or
do we plan to also do sub-space analysis (e.g. do we want to store as opaque
binary or list of numbers)
> * how do we plan to add indexes? many of the search index algorithm in
vector databases out there, which one do we plan to support (and many of them
such as product quantizer would require sub-dimensions analysis)
>
> with that, i think it is much easier to review the change for adding
vector type
See:
https://docs.google.com/document/d/1aiXPbwK4rU_YdfMPt3K752SuCMy8KQehqM4ltPg9juE/edit
Also: https://github.com/apache/pinot/issues/10919
--
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: commits-unsubscr...@pinot.apache.org
For queries about this service, please contact Infrastructure at:
us...@infra.apache.org
-
To unsubscribe, e-mail: commits-unsubscr...@pinot.apache.org
For additional commands, e-mail: commits-h...@pinot.apache.org