[leobg]

https://github.com/nmslib/hnswlib

Used it to index 40M text snippets in the legal domain. Allows incremental adding.

I love how it just works. You know, doesn’t ANNOY me or makes a FAISS. ;-)

[kacperlukawski]

What is a memory usage with 40M vectors?

[leobg]

Good point! I believe it was on the order of 20 GB. Used a Hetzner 512 GB bare metal server. $50/m.

P.S. Many people seem to think that for vector search you need a GPU. You don't.