[twelfthnight]

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.

[danielbln]

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

[hackernoteng]

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

[jonplackett]

Also on supabase!