We have a RAG powered product in production right now used by thousands of users.
RAG is part of the solution, it provides the required style, formatting and subject matter idiosyncrasies of the domain.
But it isn't enough to do (prompt + RAG query on that prompt) alone, we have a handwritten series of prompts, so the user input is just one step in a branching decision tree of deciding which prompts to apply, in sequence (prompt 1 output = prompt 2 input) and also composition (deciding to combine prompt (3 + 5, but not prompt 4)) for example.
We have a RAG powered product in production right now used by thousands of users.
RAG is part of the solution, it provides the required style, formatting and subject matter idiosyncrasies of the domain.
But it isn't enough to do (prompt + RAG query on that prompt) alone, we have a handwritten series of prompts, so the user input is just one step in a branching decision tree of deciding which prompts to apply, in sequence (prompt 1 output = prompt 2 input) and also composition (deciding to combine prompt (3 + 5, but not prompt 4)) for example.
what planet are you on? RAG has been working everywhere for a while
You’re better off using OS/ES and using AI to help you craft the exact query to run on an index.