←back to thread

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

(blog.abdellatif.io)
548 points tifa2up | 1 comments | 20 Oct 25 15:55 UTC | HN request time: 0.207s | 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 #
1. sangwook ◴[22 Oct 25 05:04 UTC] No.45665062[source]▶
S3 Vectors is great in terms of cost. But it provides around 500ms median query latency for 1M vectors, unlike other vector stores. And it does not support keyword search and sparse vectors. So I think it is better to choose which vector store to use based on your requirements.