News for hackers. Stuff that matters.
Re:Rag is more than just embedding search by majorbadass on Thursday September 21, 2023 @01:32PM (#37601025)
Agree with your sentiment, though the article explicitly mentions precision/recall, suggesting at least some level of tuning. Query understanding via structured attributes is SOTA and used at top companies. Rewriting the query as a method is weird, and yeah I'm not so convinced.

One reoccuring problem - the hacker ethos doesn't scale with AI products. "Mess around until it works" is ok to prototype. This is effectively using the dev's intuition on the 10 examples they look at as the offline eval function.

But many (most?) new-wave AI products don't have consistent offline metrics they optimize for. I think this quickly stops working when you've absorbed the obvious gains.

Re:Rag is more than just embedding search by natsucks on Thursday September 21, 2023 @01:52PM (#37601358)
Do you know of a good example demonstrating RAG with query understanding via structured attributes?
Re:Rag is more than just embedding search by ivalm on Thursday September 21, 2023 @03:56PM (#37603328)
A bit of a plug but

https://auxhealth.io/try

Does it’s generations with RAG with a mix of structured attributes + semantic retrieval.