News for hackers. Stuff that matters.

A comment on Solving the out-of-context chunk problem for RAG. Parent comment

Re:Solving the out-of-context chunk problem for RAG by zmccormick7 on Wednesday July 24, 2024 @12:13PM (#41058553)
Agreed. Retrieval performance is very dependent on the quality of the search queries. Letting the LLM generate the search queries is much more reliable than just embedding the user input. Also, no retrieval system is going to return everything needed on the first try, so using a multi-step agent approach to retrieving information is the only way I've found to get extremely high accuracy.
[ Parent | on HN ]
Re:Solving the out-of-context chunk problem for RAG by nostrebored on Wednesday July 24, 2024 @11:22PM (#41064436)
The queries you see and the resulting user interaction should be trained into the embedding model.

This is a foundational problem that requires your data. The way you search Etsy is different than the way you search Amazon. The queries these systems see are different and so are the desired results.

Trying to solve the problem with pretrained models is not currently realistic.

[ Parent | on HN ]