AI engineering glossary · RAG vector search
What is CRAG (Corrective RAG)?
Corrective RAG (also called CRAG): A RAG variant that evaluates the quality of retrieved passages and, if they look irrelevant or weak, triggers a fallback such as a web search or query rewrite before generating. It aims to stop poor retrieval from producing poor answers.
Corrective RAG: an example
If a grader marks all 5 retrieved chunks as off-topic, the system reruns the search with a rewritten query.
Related terms
- Self-RAG
- Retrieval grading
- Agentic RAG
More RAG vector search terms
- Cosine distance
- Dense retrieval
- DiskANN
- Document loader
- Domain adaptation of embeddings
- efConstruction
- efSearch
- Embedding
Where you learn it
Corrective RAG is part of the AI Engineering Program, which teaches it with notes, a hands-on lab and an exam. The first lesson is free.