https://github.com/jchunk-io/jchunk

JChunk is a lightweight and flexible library designed to provide multiple strategies for text chunking within Java applications
https://github.com/jchunk-io/jchunk

chunk chunking etl-pipeline java rag text-splitter text-splitting

Last synced: 3 months ago
JSON representation

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

• Host: GitHub
• URL: https://github.com/jchunk-io/jchunk
• Owner: jchunk-io
• License: apache-2.0
• Created: 2024-07-22T20:38:29.000Z (over 1 year ago)
• Default Branch: main
• Last Pushed: 2025-09-27T22:23:52.000Z (3 months ago)
• Last Synced: 2025-09-28T00:17:41.983Z (3 months ago)
• Topics: chunk, chunking, etl-pipeline, java, rag, text-splitter, text-splitting
• Language: Java
• Homepage: https://central.sonatype.com/artifact/io.jchunk/jchunk
• Size: 77.8 MB
• Stars: 7
• Watchers: 1
• Forks: 3
• Open Issues: 8
• Metadata Files:
  • Readme: README.md
  • Contributing: CONTRIBUTING.md
  • License: LICENSE
  • Code of conduct: CODE_OF_CONDUCT.md
  • Codeowners: .github/CODEOWNERS

Awesome Lists containing this project

• awesome-java - JChunk

README

          
# JChunk

[![GitHub Actions Status](https://img.shields.io/github/actions/workflow/status/jchunk-io/jchunk/build.yml?branch=main&logo=GitHub&style=for-the-badge)](.)

[![Apache 2.0 License](https://img.shields.io/github/license/arconia-io/arconia?style=for-the-badge&logo=apache&color=brightgreen)](.)

## A Java Library for Text Chunking

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

## Docs

### Chunkers

 - [Fixed Chunker](jchunk-fixed/README.md)

 - [Recursive Character Chunker](jchunk-recursive-character/README.md)

 - [Semantic Chunker](jchunk-semantic/README.md)

### More

 - [Jchunk Documentation](docs/modules/ROOT/pages/index.adoc)

## Installing

### Maven

```xml

    io.jchunk

    jchunk-... 

    ${jchunk.version}

```

### Gradle

```groovy

implementation group: 'io.jchunk', name: 'jchunk-...', version: "${JCHUNK_VERSION}" // replace dots with desired module name

```

## Building

To build with tests

```sh

./mvnw clean verify -Dgpg.skip=true

```

To reformat using the java-format plugin

```sh

./mvnw spotless:apply

```

To check javadocs using the javadoc:javadoc

```sh

./mvnw javadoc:javadoc -Pjavadoc

```

## Contributing

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