AI engineering glossary · RAG vector search
What is contextual retrieval?
Contextual retrieval: An approach where each chunk is prepended with a short, model-written explanation of its place in the document before indexing, applied to both embeddings and keyword indexes. It reduces failures caused by chunks that lack context.
Contextual retrieval: an example
The chunk 'Revenue rose 3%' is prefixed with 'From ACME's Q2 2024 report, Asia segment'.
Related terms
More RAG vector search terms
- Conversational RAG
- Corrective RAG
- Cosine distance
- Dense retrieval
- DiskANN
- Document loader
- Domain adaptation of embeddings
- efConstruction
Where you learn it
Contextual 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.