The LLM RAG Obituary: Killed by Agents, Buried by Context Windows

Re:The LLM RAG Obituary: Killed by Agents, Buried by Context... by lossolo on Thursday October 02, 2025 @12:30PM (#45451873)

Most hybrid stacks (BM25 + dense via HNSW/IVF) still rely on embeddings as a first class signal. So in practice the vector side carries recall on paraphrase/synonymy/OOO vocab, while BM25 stabilizes precision on exact term and short doc cases. So my point still stands.

> The architecture doesn't care

The architecture does care because latency, recall shape, and failure modes differ.

I don't know of any serious RAG deployments that don't use vectors. I'm referring to large scale systems, not hobby projects or small sites.

[ Parent | on HN ]

Re:The LLM RAG Obituary: Killed by Agents, Buried by Context... by hannasanarion on Monday October 06, 2025 @09:42AM (#45491339)

But this thread and the OP article assume that RAG is always done *exclusively* with vectors, and that's just not true, it's almost never been true.

[ Parent | on HN ]