[lossolo]

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.

[hannasanarion]

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.