Comment by antirez
5 months ago
One of the silver bullets of Claude, in the context of coding, is that it does NOT use RAG when you use it via the web interface. Sure, you burn your tokens but the model sees everything and this let it reply in a much better way. Is Claude Code doing the same and just doing document-level RAG, so that if a document is relevant and if it fits, all the document will be put inside the context window? I really hope so! Also, this means that splitting large code bases into manageable file sizes will make more and more sense. Another Q: is the context size of Sonnet 3.7 the same of 3.5? Btw Thanks you so much for Claude Sonnet, in the latest months it changed the way I work and I'm able to do a lot more, now.
Right -- Claude Code doesn't use RAG currently. In our testing we found that agentic search out-performed RAG for the kinds of things people use Code for.
Interesting - can you elaborate a little on what you mean by agentic search here?
Since the Claude Code docs suggest installing Ripgrep, my guess is that they mean that Claude Code often runs searches to find snippets to improve in the context.
I would argue that this is still RAG. There's a common misconception (or at least I think it's a misconception) that RAG only counts if you used vector search - I like to expand the definition of RAG to include non-vector search (like Ripgrep in this case), or any other technique where you use Retrieval techniques to Augment the Generation phase.
IR (Information Retrieval) has been around for many decades before vector search become fashionable: https://en.wikipedia.org/wiki/Information_retrieval
7 replies →
I guess it's what sometimes it's called "self RAG", that is, the agent looks inside the files how a human would be to find that's relevant.
7 replies →