Re:The LLM RAG Obituary: Killed by Agents, Buried by Context...
by CuriouslyC on Wednesday October 01, 2025 @08:43PM
(#45445285)
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.
[ Parent
| on HN ]
Re:The LLM RAG Obituary: Killed by Agents, Buried by Context...
by nbstme on Wednesday October 01, 2025 @08:53PM
(#45445329)
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.
Re:The LLM RAG Obituary: Killed by Agents, Buried by Context...
by tw1984 on Thursday October 02, 2025 @08:11AM
(#45448626)
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.
Re:The LLM RAG Obituary: Killed by Agents, Buried by Context...
by CuriouslyC on Thursday October 02, 2025 @11:47AM
(#45451289)
So you're saying grep isn't a form of information retrieval?
Re:The LLM RAG Obituary: Killed by Agents, Buried by Context...
by tw1984 on Thursday October 02, 2025 @07:34PM
(#45456850)
information retrieval is a much larger superset of RAG.
grep + agentic LLM is not RAG.
Re:The LLM RAG Obituary: Killed by Agents, Buried by Context...
by leobg on Friday October 03, 2025 @01:49PM
(#45465639)
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..