RAG & Search
Chunk size
The amount of text placed into each chunk during document processing.
Example
A team tests whether 300-word or 700-word passages return more useful answers.
Why it matters
It helps balance having enough surrounding information against bringing in unnecessary material.
You'll hear it
“This passage is too short to explain the exception.”
Can you control it?
Set by the team
The people building or running the AI choose this setup. An everyday user generally needs their help to change how this part works.
Common questions
- Does a larger chunk always improve the answer?
- No. Extra text can include distractions or use up the available space.
- Can small chunks make a search result hard to understand?
- Yes. A passage may lose the background needed to interpret it.
- Is word count the only sizing method?
- No. Systems may use characters, text pieces or document boundaries such as paragraphs.