JChunk Documentation

A Java Library for Text Chunking.

JChunk is a lightweight and flexible library designed to provide multiple strategies for text chunking within Java applications.

Quick Start

Add the dependency for the chunker you need to your pom.xml (example shows the fixed chunker):

<dependency>
  <groupId>io.jchunk</groupId>
  <artifactId>jchunk-fixed</artifactId>
  <version>${jchunk.version}</version>
</dependency>

// Basic usage
FixedChunker chunker = new FixedChunker();
List<Chunk> chunks = chunker.split("Your text here");

Available Chunkers

• Fixed Character Chunker
• Recursive Character Chunker
• Semantic Chunker

Contributing

We welcome contributions! See the Contributing Guide for details.