AI engineering glossary · RAG vector search
What is parent-document retrieval?
Parent-document retrieval (also called Parent document retriever): A retrieval design where small chunks are used for matching but the larger parent section or document they came from is returned to the model. It combines the precise matching of small chunks with the fuller context of big ones.
Parent-document retrieval: an example
A 150-token child chunk matches the query, and the system returns its whole 1,200-token parent section to the generator.
Related terms
More RAG vector search terms
- pgvector
- Post-filtering
- Pre-filtering
- Product quantisation
- Proposition indexing
- Query decomposition
- Query expansion
- Query rewriting
Where you learn it
Parent-document 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.