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.