Contextual retrieval

Contextual retrieval is a retrieval-augmented generation technique that prepends a short, model-written summary of the surrounding document to each chunk before embedding and keyword indexing, so isolated chunks keep enough context to be found.

Contextual retrieval sits in the Retrieval & memory part of the Agentik {OS} glossary, which defines the words used to build and run AI agent systems.

Also called contextual embeddings.