What is overlap in document chunking?
PICTURE THIS: A SENTENCE BECOMES TOKENS
The model does not read letters like humans. It reads these pieces, then predicts the next one.
Simple meaning
Overlap copies a few tokens or sentences from the end of one chunk into the start of the next.
WHY — Tokens instead of words?
LLMs use tokens (not full words) because it helps them:
who only read docs from people who shipped.
and tied to GenAI / LLM work.
Each piece maps to a number the network can learn.
Fixed pieces are what transformers expect as input.
STEPS — What happens with tokens?
Before the model can read a sentence, it goes through these steps:
- 1Overlap copies a few
tokens or sentences from the end of one chunk into the start of the next.
- 2It reduces the chance
that a fact is split across a boundary.
- 3Too much overlap wastes
index space and duplicates hits.
- 4Context mix
Attention looks at nearby tokens together.
- 5Next token
The model scores what should come next.
- 6Decode
IDs turn back into readable text.
EXAMPLE — See it in action
Here's a short line you can speak, broken into clear beats:
Note: Adapt this scaffold to your own project — keep it under 60–90 seconds.
Key takeaway
Overlap copies a few tokens or sentences from the end of one chunk into the start of the next. It reduces the chance that a fact is split across a boundary.