Skip to content
@docling-project

Docling Project

Welcome to the Docling Project

This is the GitHub organization Docling open-source project. We like to get continuous feedback from the community: take the poll!

Docling

Image

Docling is our main open-source package. It is a powerful library which simplifies document processing, parsing diverse formats — including advanced PDF understanding — and providing seamless integrations with the gen AI ecosystem.

We support an amazing community which helps us driving forward the adoption of Docling. Give it a try and join the community!



The key repositories of Docling are:

  • docling - The home of the main docling package.
  • docling-core - The definition of types, transforms, serializers, etc. If it has to do with the DoclingDocument you will find it here.
  • docling-parse - The backend PDF parser used by Docling.
  • docling-serve - The FastAPI wrappers for running Docling as REST API and distribute large jobs.
  • docling-ibm-models - The AI models powering Docling.
  • docling-sdg - Synthetic data generation (SDG) on documents for dataset generation for RAG, finetuning, etc.
  • docling-mcp - The definition of tools with the Model Context Protocol for document conversion, manipulation and generation agents.
  • docling-java - A Java API for interacting with Docling, currently based on docling-serve.

LF AI & Data

Docling is hosted as a project in the LF AI & Data Foundation.

Image

IBM ❤️ Open Source AI

The project was started by the AI for knowledge team at IBM Research Zurich.

Pinned Loading

  1. docling docling Public

    Get your documents ready for gen AI

    Python 66.4k 4.8k

  2. docling-serve docling-serve Public

    Running Docling as an API service

    Python 1.8k 340

  3. docling-core docling-core Public

    Docling core data types and transformations

    HTML 282 215

  4. community community Public

    7 2

  5. docling-workshops docling-workshops Public

    Docling workshops

    Jupyter Notebook 44 11

Repositories

Showing 10 of 27 repositories
  • docling Public

    Get your documents ready for gen AI

    docling-project/docling's past year of commit activity
    Python 66,430 MIT 4,787 802 (4 issues need help) 113 Updated Sep 15, 2026
  • docling-core Public

    Docling core data types and transformations

    docling-project/docling-core's past year of commit activity
    HTML 282 MIT 215 58 (1 issue needs help) 62 Updated Sep 15, 2026
  • docling-project/docling-jobkit's past year of commit activity
    Python 36 MIT 47 18 19 Updated Sep 15, 2026
  • docling.rs Public

    Full Rust port of Python docling

    docling-project/docling.rs's past year of commit activity
    Rust 73 MIT 17 1 0 Updated Sep 15, 2026
  • docling-java Public

    A Java API for Docling

    docling-project/docling-java's past year of commit activity
    Java 134 MIT 26 8 (1 issue needs help) 2 Updated Sep 14, 2026
  • docling-graph Public

    Transform unstructured documents into validated, rich and queryable knowledge graphs.

    docling-project/docling-graph's past year of commit activity
    Python 891 MIT 94 1 0 Updated Sep 12, 2026
  • docling-nlp Public

    Create fast graph language models from converted PDF documents for knowledge extraction and Q&A.

    docling-project/docling-nlp's past year of commit activity
    C++ 66 MIT 7 1 2 Updated Sep 12, 2026
  • docling-serve Public

    Running Docling as an API service

    docling-project/docling-serve's past year of commit activity
    Python 1,803 MIT 340 136 19 Updated Sep 11, 2026
  • docling-parse Public

    Simple package to extract text with coordinates from programmatic PDFs

    docling-project/docling-parse's past year of commit activity
    C++ 333 MIT 80 45 13 Updated Sep 11, 2026
  • docling-mcp Public

    Making docling agentic through MCP

    docling-project/docling-mcp's past year of commit activity
    Python 742 MIT 138 11 5 Updated Sep 7, 2026