What is document chunking?

02 · See it in action

Follow the steps

1. Split a course handbook at section headings.
2. Keep titles and document IDs attached to each chunk.
3. Check whether answers remain understandable without the previous section.
4. Compare retrieval results across two chunk sizes using the same query set.

Worked example

Weak chunk: "This expires after 30 days."
Stronger chunk: "Trial access: trial access expires after 30 days."
Metadata: document=trial-policy, section=duration

Read the example once, then explain each part aloud in your own words. If it includes Python, you can understand the idea first and run the code later in a local Python environment. Code is shown as text; this page does not execute it.

Sign in to save your reading progress.