AI engineering glossary · RAG vector search
What is retrieval evaluation?
Retrieval evaluation: Assessing only the retriever, by checking whether known relevant passages appear in its top results. It uses ranking metrics such as recall at k, hit rate and NDCG, and runs without any language model.
Retrieval evaluation: an example
For 100 questions, the correct chunk is in the top 5 for 91, giving hit rate 0.91.
Related terms
More RAG vector search terms
- Retrieval-augmented generation
- Retriever
- Scalar quantisation
- Score fusion
- Self-RAG
- Semantic cache
- Semantic chunking
- Sentence window retrieval
Where you learn it
Retrieval 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.