RAG & Search
Chunking
Splitting large documents into smaller pieces that can be searched and supplied to a model.
Example
A 100-page manual is divided into smaller passages before being added to search.
Why it matters
It lets a system search and use focused passages instead of loading an entire document.
You'll hear it
“That exception was separated from the rule it changes.”
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
- Can a sentence be split in the wrong place?
- Yes. Poor boundaries can leave fragments that are difficult to interpret correctly.
- Should every kind of document be split the same way?
- No. Tables, headings and long explanations may need different treatment.
- Can splitting affect which evidence is found?
- Yes. How ideas are grouped influences what each searchable piece represents.