Comment by bcherny
5 months ago
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.
5 months ago
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
I agree that retrieval can take many forms besides vector search, but do we really want to call it RAG if the model is directing the search using a tool call? That like an important distinction to me and the name "agentic search" makes a lot more sense IMHO.
5 replies →
rag is an acronym with a pinned meaning now. just like the word drone. drone didnt really mean drone, but drone means drone now. no amount of complaining will fix it. :[
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.
As opposed to vector search, or…?
6 replies →