2 min read
RAG is a retrieval problem, not a prompting problem
Two-thirds of the accuracy gain in our production RAG system came from changes upstream of the model. Here is the measured breakdown, and what to fix in what order.
Topic
Retrieval-augmented generation — chunking, ranking, grounding and citation.
Two-thirds of the accuracy gain in our production RAG system came from changes upstream of the model. Here is the measured breakdown, and what to fix in what order.
The question is not which is better. It is which failure you are trying to fix — missing knowledge, wrong behaviour, or unacceptable cost.