JChunk

A Java Library for Text Chunking

JChunk project is simple library that enables different types of text splitting strategies, essential for RAG applications.

Docs

Jchunk Website

Installing

Fixed Chunker

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

implementation("io.jchunk:jchunk-fixed:${JCHUNK_VERSION}")

Recursive Chunker

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

implementation("io.jchunk:jchunk-recursive-character:${JCHUNK_VERSION}")

Semantic Chunker

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

implementation("io.jchunk:jchunk-semantic:${JCHUNK_VERSION}")

Building

To build with tests

./mvnw clean verify -Dgpg.skip=true

To reformat using the java-format plugin

./mvnw spotless:apply

To check javadocs using the javadoc:javadoc

./mvnw javadoc:javadoc -Pjavadoc

Contributing

Please read CONTRIBUTING.md for details on our code of conduct, and the process for submitting pull requests to us.