← Glossary
Chunking
Splitting a long document into smaller pieces before storing it for retrieval.
A RAG system can't hand an entire document library to a model at once, so source documents are split into smaller chunks (by paragraph, section, or a fixed size) before being embedded and stored. How a document is chunked directly affects retrieval quality — chunks that are too small lose context, chunks that are too large dilute relevance.
Where this shows up in practice
Have a project in mind?
Tell us what you're trying to automate or build — we'll reply with next steps, not a sales pitch.