RAG Chunk

Noun · AI & Machine Learning

Definitions

  1. A chunk of source content prepared for indexing and retrieval in a retrieval-augmented generation system. Chunk size and boundaries affect both what gets retrieved and how useful the retrieved evidence is to the model.

    In plain English: A piece of source content stored for retrieval in a RAG system.

    Example: "They changed the chunking strategy because each RAG chunk was too large and mixed unrelated sections from the policy manual."

Related Terms