AI engineering glossary · RAG vector search
What is small-to-big retrieval?
Small-to-big retrieval: A strategy that indexes small units, such as single sentences, for accurate matching and then expands to a larger surrounding unit before generation. It counters the trade-off where small chunks match well but give too little context.
Small-to-big retrieval: an example
A single sentence about 'interest on late payment' is matched, then the surrounding three paragraphs are sent to the model.
Related terms
More RAG vector search terms
- Sparse retrieval
- Structure-aware chunking
- Synthetic test set
- Table extraction
- Text extraction
- Top-k retrieval
- Two-stage retrieval
- Vector database
Where you learn it
Small-to-big retrieval is part of the AI Engineering Program, which teaches it with notes, a hands-on lab and an exam. The first lesson is free.