RAG isn't dead, RAG is just fiddly, you need to tune retrieval to the task. Also, grep is a form of RAG, it just doesn't use embeddings.
RAG isn't dead, RAG is just fiddly, you need to tune retrieval to the task. Also, grep is a form of RAG, it just doesn't use embeddings.
Yes my point is that the entire RAG pipeline like ingest, chunk, embed, search with Elastic, rerank is in decline. Grep is far simpler. It’s trivial.
No, grep is not RAG. RAG is all about embeddings + vector search + LLM working under a fixed workflow.
Saying grep is also RAG is like saying ext4 + grep is a database.
You don't decide what "RAG" means, a term that's been around for much, much less time than "database".
So you're saying grep isn't a form of information retrieval?
information retrieval is a much larger superset of RAG.
grep + agentic LLM is not RAG.
Retrieval Augmented Generation. How you do the retrieving is irrelevant. You can do it manually and it’ll still be RAG. Also, most RAG pipelines combine multiple approaches - BM25, embeddings, etc..