I do wonder if the term will make a comeback, Retrieval Augmented Generation as a concept is a fairly fundamental idea, or maybe it's considered too generic which is why tool calling is used in favour if it?

The problem with tool calling is it's too generic in my mind, maybe RAG will make a return when we get around to having different flavours of it, digging into the rich vein that is Information Retrieval

Also is it just me that doesn't like this sort of wording?

> agent has to hold

I find it very generic, I'd much prefer process or recall or any term that indicates what the agent is doing with tokens in that context

I think it’ll just become “agentic search” and “information retrieval” again because RAG is too intertwined with a particular kind of implementation/use case of basic document scoring + first gen vector dbs that is IMO undesirable for more sophisticated approaches to associate themselves with.

You need a lot more unstructured data than most typical “RAG” users doing document search are dealing with for it it to not be a solved problem, IMO (just give a tool calling agent your sql schema/directory structure). Even that is still an interesting problem for more typical use cases, but only at large scales where you start needing to do multiple passes or fan-out or convert data that could be structured like that into data that already is. I’m interested in large scale code search, coding agent context/conversation search, and network/trace analysis which has a lot of domain-specific considerations that make it interesting but definitely not structured like a typical “document chunking with cosine similarity” RAG implementation.