Re:Qdrant, the Vector Search Database, raised $28M in a Seri...
by therealdrag0 on Tuesday January 23, 2024 @09:53PM
(#39113050)
What’s you use for 100B records?
Re:Qdrant, the Vector Search Database, raised $28M in a Seri...
by lettergram on Tuesday January 23, 2024 @10:58PM
(#39113464)
Idk if I can talk about my exact project. But I worked alongside these folks:
https://www.capitalone.com/tech/machine-learning/learning-em...
Running an R&D group in the department.
I’ve been working with vectors for over a decade; particularly with embeddings used in AI. We’re talking projects from 100k to 100B+ records, used for AI applications
Postgres, particularly with pgvector and derivatives, can handle to millions of records very rapidly no problem. It’s very cheap, scales great, and is accurate.
I’m sure some of these open source solutions are improvements. That said, weigh vendor lock in, cost, risk and in the end it usually makes very little sense.