←back to thread

Retrieval Augmented Generation Based on SQLite

(github.com)
86 points emzo | 1 comments | 24 Jun 25 09:11 UTC | HN request time: 0.343s | source
Show context
wredcoll ◴[24 Jun 25 15:01 UTC] No.44367010[source]▶
This looks cool, and I'm interested in these keywords, but I read the entire readme and I'm still unsure what problem it's actually solving.

Anyone want to help out?

replies(3): >>44367069 #>>44367076 #>>44372222 #
1. webstrand ◴[24 Jun 25 15:07 UTC] No.44367069[source]▶
This is for LLMs. In general RAG takes a user prompt and uses it to find potentially relevant documents in the database. It then enriches the original prompt with those documents so that the LLM has context that wasn't in its training dataset.