AI engineering glossary · RAG vector search
What is context relevance?
Context relevance: A RAG evaluation measure of how much of the retrieved context is actually useful for answering the question. Low values mean the retriever is fetching noise that wastes tokens and may distract the model.
Context relevance: an example
If 2 of 5 retrieved chunks bear on the question, context relevance is about 0.4.
Related terms
- Context precision
- Faithfulness
- Retrieval grading
More RAG vector search terms
- Contextual chunk enrichment
- Contextual retrieval
- Conversational RAG
- Corrective RAG
- Cosine distance
- Dense retrieval
- DiskANN
- Document loader
Where you learn it
Context relevance is part of the AI Engineering Program, which teaches it with notes, a hands-on lab and an exam. The first lesson is free.