Re:Pg_vectorsearch: An index that is faster than pgvector's ...
by 3abiton on Wednesday October 14, 2026 @09:23AM
(#50087379)
Checks notes, one dayabase per client, per user, per project ... etc
Re:Pg_vectorsearch: An index that is faster than pgvector's ...
by qeternity on Wednesday October 14, 2026 @09:33AM
(#50087548)
Partitioning is the easy bit I think, and falls out naturally from Postgres.
But how are people doing recency biasing with vector databases?
All of our approaches are either expensive or super hacky.
Edit: post filtering only
I don't understand how people are efficiently implementing tenant/user/permission scopes with these indexes.