Hacker News new | past | comments | ask | show | jobs | submit login

Even in production my guess is most teams would be better off just rolling their own embedding model (huggingface) + caching (redis/rocksdb) + FAISS (nearest neighbor) and be good to go. I suppose there is some expertise needed, but working with a vector database vendor has major drawbacks too.



Or you just shove it into Postgres + pg_vector and just use the DBMS you already use anyway.


Using Postgres with pgvector is trivial and cheap. Its also available on AWS RDS.


Also on supabase!




Consider applying for YC's Spring batch! Applications are open till Feb 11.

Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact

Search: