---
title: "Content Chunking"
description: "Splitting long content into discrete, retrievable units for RAG pipelines."
topic: "Retrieval & Behavior"
canonical: "https://geordy.ai/glossary/retrieval-behavior/content-chunking"
---
# Content Chunking

Splitting long content into discrete, retrievable units for RAG pipelines.

Page structure determines chunk quality. RAG pipelines typically chunk by heading or by N tokens. Pages with clear h2/h3 hierarchy get chunked into self-contained, citable units. Pages without get chunked arbitrarily.
---

Source: https://geordy.ai/glossary/retrieval-behavior/content-chunking
This is a machine-readable markdown version of that page, generated by Geordy.