Oh interesting… I have the entire SEC database to index (only indexing the text in a sliver of it at the moment) and use tsvector and I could use something faster.
Ah, I remember now that ParadeDB's pitch was doing hybrid search by using pgvector with keyword rankings from pg_search. Never got the chance to try it.
Oh interesting… I have the entire SEC database to index (only indexing the text in a sliver of it at the moment) and use tsvector and I could use something faster.
unrelated! full-text search vs vector search, and this has a more permissive license.
Sometimes you want both. I wonder if there is a postgresql reranker…
(Tiger data employee fwiw)
We have an alternative full-text search extension as well, pg_textsearch that's completely open source that supports hybrid re-ranking
Here's a blog on it (i linked to the section on hybrid search, there's a code snippet for you in there)
https://www.tigerdata.com/blog/introducing-pg_textsearch-tru...
We're big fans of extending Postgres for more and more usecases
2 replies →
Ah, I remember now that ParadeDB's pitch was doing hybrid search by using pgvector with keyword rankings from pg_search. Never got the chance to try it.
This is our old pitch, we have our own vector data-type in our main index in beta.
pg_search does both vector (this) and full-text (bm25) in a single index.