Quarkus Docling

This is a Quarkus extension for the Docling project. Docling simplifies document processing, parsing diverse formats — including advanced PDF understanding — and providing seamless integrations with the gen AI ecosystem.

Docling Java

Currently, this extension is an implementation of the Docling Serve API provided by Docling Java using a Quarkus REST client.

The eventual goal is to unify the DoclingDocument format with LangChain4j’s Document abstraction so that Docling can be used in a LangChain4j RAG pipeline for ingesting data.

Compatibility

Each release of this extension targets a single Quarkus LTS stream. New features are developed against the current baseline only and are not backported to earlier streams.

The table below also records which Docling Java version each release was built against, so you can find the matching upstream documentation for the API you are coding against.

Quarkus Docling Docling Java Quarkus

1.5.0

0.7.0

3.40 LTS

1.4.4

0.7.0

3.33 LTS

1.4.3

0.6.5

3.33 LTS

1.4.2

0.6.1

3.33 LTS

1.4.1

0.6.1

3.33 LTS

1.4.0

0.6.0

3.33 LTS

1.3.2

0.5.3

3.33 LTS

1.3.1

0.5.2

3.33 LTS

1.3.0

0.5.0

3.27 LTS

1.2.3

0.4.7

3.27 LTS

1.2.2

0.4.3

3.27 LTS

1.2.1

0.4.2

3.27 LTS

1.2.0

0.4.1

3.27 LTS

1.1.0

0.3.0

3.27 LTS

1.0.1

0.1.3

3.27 LTS

0.0.1 to 0.0.4

n/a

3.20 LTS

The 0.0.x releases predate Docling Java; they used a client generated from the Docling Serve OpenAPI specification. Docling Java 0.1.3 is not linked because the upstream documentation only goes back to 0.1.5.

If you are still on Quarkus 3.33 LTS, stay on 1.4.4. The extension metadata declares requires-quarkus-core: "[3.40,)", so Quarkus tooling will reject an incompatible combination rather than failing at runtime.

The definitive Docling Java version for any release is the docling-java.version property in that release’s pom.xml on Maven Central.

Docling Features

  • 🗂️ Parsing of multiple document formats incl. PDF, DOCX, XLSX, HTML, images, and more

  • 📑 Advanced PDF understanding incl. page layout, reading order, table structure, code, formulas, image classification, and more

  • 🧬 Unified, expressive DoclingDocument representation format

  • ↪️ Various export formats and options, including Markdown, HTML, and lossless JSON

  • 🔒 Local execution capabilities for sensitive data and air-gapped environments

  • 🤖 Plug-and-play integrations incl. LangChain, LlamaIndex, Crew AI & Haystack for agentic AI

  • 🔍 Extensive OCR support for scanned PDFs and images

  • 🥚 Support of several Visual Language Models SmolDocling

  • 💻 Simple and convenient CLI

What’s new