Probably good to add a disclaimer at the top that clarifies the definition, since RAG is ultimately just a pattern, and vector indexes are just one way to implement the pattern.
Indeed, industry at large sees RAG as equivalent to "vector indexes and cosine similarity w.r.t. input query", and the rest of the article explains thoroughly why that's not the right approach.
> industry at large sees RAG as equivalent to "vector indexes and cosine similarity w.r.t. input query"
Yep, and this is getting really old. Information retrieval is not a new problem domain. Somehow, when retrieved info is fed into an LLM, all nuance is lost and we end up with endless pronouncements about whether retrieval is/is not "dead".