ModelRefs / Chunk Overlap — AI Glossary
Chunk Overlap — AI Glossary
Including a portion of the previous chunk's text at the start of the next chunk to preserve context across chunk boundaries.
Overview
Text splitting into chunks risks losing context at boundaries: a sentence may start in one chunk and complete in the next. Chunk overlap (typically 10–20% of chunk size) duplicates the tail of each chunk into the head of the next, preserving sentence/paragraph boundaries. Increases total stored vectors proportionally.
Reference details
| Topic | rag |
|---|---|
| Also known as | chunk stride, window overlap |
| Last reviewed | 2026-06-24 |
Related terms
Commonly confused with
The parameter that stops a sentence spanning a boundary from being lost to both chunks. It is not a substitute for a splitter that respects structure — overlap patches boundaries blindly, while a structure-aware split avoids creating bad ones. Overlap also multiplies storage and can return two chunks containing the same passage, which crowds the top-k with duplicates.
Continue your research
Use these connected ModelRefs sections to compare alternatives, inspect implementation paths, and review the evidence and governance boundaries relevant to Chunk Overlap — AI Glossary.
Frequently asked questions
What is Chunk Overlap?
Including a portion of the previous chunk's text at the start of the next chunk to preserve context across chunk boundaries.
Is Chunk Overlap the same as chunk stride?
Yes — chunk stride, window overlap are common aliases for Chunk Overlap.
What concepts are related to Chunk Overlap?
Closely related concepts include text splitter, parent document retrieval, naive rag.