AI engineering glossary · RAG vector search
What is Self-RAG?
Self-RAG: An approach in which a language model is trained to decide when to retrieve and to critique its own retrieved passages and outputs using special reflection tokens. It aims for retrieval only when useful and answers better supported by evidence.
Self-RAG: an example
The model skips retrieval for a greeting but retrieves for a factual question and marks a passage as supportive.
Related terms
More RAG vector search terms
- Semantic cache
- Semantic chunking
- Sentence window retrieval
- Similarity threshold
- Small-to-big retrieval
- Sparse retrieval
- Structure-aware chunking
- Synthetic test set
Where you learn it
Self-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.