563
Dictionary

Chunking

Splitting documents into retrievable pieces before embedding them for RAG.

1 min readupdated 2026-06-22

/ quick answer

Chunking decides what unit of text your retriever returns. Too small → loses context. Too big → wastes tokens and dilutes relevance. Common strategies: fixed-size, sentence, semantic, and structural (by heading/section). Splitting documents into retrievable pieces before embedding them for RAG.

Splitting documents into retrievable pieces before embedding them for RAG. Chunking decides what unit of text your retriever returns. Too small → loses context. Too big → wastes tokens and dilutes relevance. Common strategies: fixed-size, sentence, semantic, and structural (by heading/section). In practice: A 40-page PDF split into ~800-token overlapping chunks by markdown heading typically outperforms naive 500-char splits on Q&A accuracy. This dictionary node is part of the Onexial knowledge graph and links to related concepts, workflows and tools below.
Definition
Chunking decides what unit of text your retriever returns. Too small → loses context. Too big → wastes tokens and dilutes relevance. Common strategies: fixed-size, sentence, semantic, and structural (by heading/section).
Example
A 40-page PDF split into ~800-token overlapping chunks by markdown heading typically outperforms naive 500-char splits on Q&A accuracy.
Related Workflows
Related Tool Stacks
/ frequently asked

What is Chunking?

Chunking decides what unit of text your retriever returns. Too small → loses context. Too big → wastes tokens and dilutes relevance. Common strategies: fixed-size, sentence, semantic, and structural (by heading/section).

What is an example of Chunking?

A 40-page PDF split into ~800-token overlapping chunks by markdown heading typically outperforms naive 500-char splits on Q&A accuracy.

Why does Chunking matter for AI and automation?

Splitting documents into retrievable pieces before embedding them for RAG. It connects to the workflows, prompts and tool stacks linked on this page, so you can move from definition to execution without leaving Onexial.

/ topics#ai#rag

/ continue exploring

Related concepts

The vocabulary this page depends on.

  • Contextual Compression

    Contextual compression is a technique used to reduce the size of the input context for a Large Language Model (LLM) while retaining its most relevant information, typically by summarizing or filtering.

  • Reranking

    A second-pass model that reorders retrieved chunks by true relevance to the query.

all dictionary

Related workflows

Turn this into a repeatable process.

all workflows

Related tool stacks

The tools that run it in production.

all tool stacks

Related prompts

Reusable prompts for this job.

all prompts

Comparisons & alternatives

Pick between the options.

all comparisons