←back to thread

249 points colesantiago | 4 comments | | HN request time: 0.62s | source
1. softwaredoug ◴[] No.40750448[source]
Is this a death knell to many of the vector DBs pushing RAG solutions right now?

(Or maybe it’s validation in RAG and these companies should rejoice)

replies(3): >>40751016 #>>40751164 #>>40751653 #
2. nextworddev ◴[] No.40751016[source]
Your workload is my opportunity - OpenAI, probably
3. posix_monad ◴[] No.40751164[source]
Nah, that was Postgres vector extensions
4. PeterCorless ◴[] No.40751653[source]
"RAG" is more of a concept than a specification. So the Cambrian explosion of how to actually do it will continue unabated.

Likewise, I don't think it's going to stem the tide of adding vector indexes and similarity search techniques to traditional databases.

Instead, if anything, I think this is a validation that traditional databases aren't going anywhere — OLAP or OLTP. Behind all the LLM models you're still going to need true, authoritative data in databases to avoid (or at least minimize) the hallucination problem.

AI needs, if anything, even more programmatic ways to get at that data.