AI engineering glossary · RAG vector search
What is RAG evaluation?
RAG evaluation: Measuring a RAG system's quality by testing retrieval and generation separately and together, using a set of questions with known answers or relevant documents. Splitting the analysis shows whether failures come from missing passages or poor answering.
RAG evaluation: an example
On 200 test questions, the retriever finds the right chunk in 88% of cases, and the generator answers correctly in 79%.
Related terms
More RAG vector search terms
- Ragas
- RAPTOR
- Re-embedding
- Recall-latency trade-off
- Reciprocal rank fusion
- Recursive character splitting
- Reranker
- Reranking
Where you learn it
RAG evaluation is part of the AI Engineering Program, which teaches it with notes, a hands-on lab and an exam. The first lesson is free.