Glossary · Phase 1 · Building with LLMs
Overlap
In chunking, the words repeated at the end of one chunk and the start of the next, so an idea split across a boundary still appears whole somewhere.
Try it now
Each chunk starts 3 words after the one before (size minus overlap), so neighbors share one word. The loop stops once a chunk reaches the end.
Learn it properly
Chunking documents · Split long documents so the right piece can be retrieved. About 25 minutes.
Other terms from the same lesson
- chunking: Cutting long documents into smaller pieces so the most relevant pieces can be found and sent to a model.
- metadata: Facts stored alongside a piece of content, such as which document it came from, its date or its section, used to filter and cite.
Never trained an AI?
Teach a small one to write, right in your browser. It takes about 20 seconds and needs no account.