Most vectordb is a hammer looking for a nail
I think it can be more efficient for two-step RAG so you can reuse the natural language query directly, but for agentic RAG it might indeed be overkill.
Exactly this, agree completely
I think it can be more efficient for two-step RAG so you can reuse the natural language query directly, but for agentic RAG it might indeed be overkill.
Exactly this, agree completely