←back to thread

Production RAG: what I learned from processing 5M+ documents

(blog.abdellatif.io)
548 points tifa2up | 2 comments | 20 Oct 25 15:55 UTC | HN request time: 0.607s | source
Show context
hatmanstack ◴[20 Oct 25 18:00 UTC] No.45647032[source]▶
Not here to schlep for AWS but S3 Vectors is hands down the SOTA here. That combined with a Bedrock Knowledge Base to handle Discovery/Rebalance tasks makes for the simplest implementation on the Market.

Once Bedrock KB backed by S3 Vectors is released from Beta it'll eat everybody's lunch.

replies(3): >>45647181 #>>45650963 #>>45665062 #
cipherself ◴[21 Oct 25 00:08 UTC] No.45650963[source]▶
S3 Vectors is hands down the SOTA here

SOTA for what? Isn't it just a vector store?

replies(1): >>45656437 #
1. DSingularity ◴[21 Oct 25 14:42 UTC] No.45656437[source]▶
I think he just means it should be assumed to be standard practice and considered baseline at this point.
replies(1): >>45661789 #
2. cipherself ◴[21 Oct 25 21:13 UTC] No.45661789[source]▶
Assuming that's what he meant, why would it be considered baseline versus anything else? I am genuinely curious because I'd like to know more about issues people face with this or that vector store in general.