Re:Show HN: Playground for comparing embedding models on Wik...
by davidtsong on Monday October 30, 2023 @10:49PM
(#38079615)
Definitely, top-k is a very naive way to do RAG. I think people have experimented with using a cross encoder like approach or even letting the LLM choose the sources. We will experiment with more approaches like this :)
Seems weird that every RAG app uses top-k especially since you might pull in information irrelevant to the context (e.g. if you were asking for the names of the authors of paper, you probably only want the top-1 embedding).