←back to thread

249 points colesantiago | 1 comments | | HN request time: 0.209s | source
Show context
ot ◴[] No.40751253[source]
Very unexpected acquisition. I don't think that Rockset is a suitable infrastructure for RAG, a purpose-built inverted index would be far more efficient (both in terms of compute and storage), so I'm not sure how much of the technology would actually be useful for them.

I can think of two options

- Pure acqui-hire: virtually all of Rockset engineering leadership is ex-Meta, and OpenAI has been hiring several senior infra engineers from Meta, so these are all people that have worked together previously.

- OpenAI is building some product where customers can ingest large amounts of data, which could be managed by the Rockset infrastructure as source of truth, and then indexed by their RAG systems.

replies(4): >>40751357 #>>40751358 #>>40751772 #>>40751908 #
simonw ◴[] No.40751908[source]
RAG doesn't have to involve vector search.

The (very thin) blog post said "Enhancing our retrieval infrastructure" - my guess is this is more about other forms of retrieval, like constructing and executing SQL queries and using the results to help answer questions.

replies(2): >>40752396 #>>40753431 #
tirumaraiselvan ◴[] No.40753431[source]
> RAG doesn't have to involve vector search.

This. Not sure why RAG triggers vector search for everyone. Retrieval Augmented Generation is as generic as it can get.

replies(2): >>40753635 #>>40753975 #
1. clpmsf ◴[] No.40753635[source]
Most likely for the same reason that so many people seem to think they need a vector-specific database and a framework like langchain to build any type of GenAI-enabled application... the content marketing is working.