Chunking
Splitting long source documents into smaller units for embedding and retrieval. Strategy dramatically affects RAG quality — semantic chunking (splitting at meaning boundaries) with 20-30% overlap outperforms naive fixed-size chunking on most enterprise document types.
Related terms
- Embedding
A numeric vector representation of text (or images, audio, etc.) produced by a model such that semantically similar inputs map to nearby vectors. Used to power search, clustering, and retrieval in modern GenAI stacks.
- Retrieval-Augmented Generation (RAG)
A pattern where an LLM answers a query by first retrieving relevant documents from an external corpus (typically via a vector database or hybrid search) and injecting them into the prompt as grounding context. RAG addresses freshness and factual grounding without model retraining.
Related on this site
Where this fits
Chunking is part of the AI Fundamentals vocabulary used in the Generative AI Maturity Framework. See the full glossary for the complete set of 149 defined terms, or take the free maturity assessment to see where your organisation stands.