Pgvector 0.5.0 Feature Highlights and how tos

Re:Pgvector 0.5.0 Feature Highlights and how tos by thawab on Tuesday August 29, 2023 @09:46PM (#37316653)

Congratulations, can anyone give an insight on how this compares to pg_embedding [0] (Postgres and use HNSW). Or the use-cases compared to other victor databases. It’s getting hard to keep up what’s happening in the LLM scene.

[0] https://github.com/neondatabase/pg_embedding

[ Parent | on HN ]

Re:Pgvector 0.5.0 Feature Highlights and how tos by kordlessagain on Tuesday August 29, 2023 @10:12PM (#37316830)

I suspect a lot of the paying use cases for vector search right now have a lot to do with enterprise search functionality. As for the LLM stuff, I do wonder if it's paying bills yet.

If anyone is into embeddings, check out Instructor Large/XL. It's quite good and super fast using L4s. Haven't quite figured out the instructions bits yet, but got it clustering things today and that was cool.

[ Parent | on HN ]

Re:Pgvector 0.5.0 Feature Highlights and how tos by roseway4 on Tuesday August 29, 2023 @11:26PM (#37317318)

Jonathan did just that in his prior blog post: https://jkatz05.com/post/postgres/pgvector-hnsw-performance/

pgvector_hnsw outperforms pg_embedding using a query per sec / recall measure across various common embedding widths and a range of dataset sizes.

[ Parent | on HN ]