Installation

Quick Install

The easiest way to install Docling is using pip:

pip install docling

System Requirements

Docling works on multiple platforms and architectures:

Supported Operating Systems

• macOS - Full support for both Intel and Apple Silicon (M1/M2/M3)
• Linux - Support for major distributions
• Windows - Full Windows support

Architecture Support

• x86_64 - Intel and AMD 64-bit processors
• arm64 - Apple Silicon and ARM processors

Python Version

Docling requires Python 3.8 or higher. We recommend Python 3.10 or later for the best experience.

Installation Methods

Using pip

The standard installation method using Python's package manager:

pip install docling

For a specific version:

pip install docling==2.68.0

Using pip with Virtual Environment

We recommend using a virtual environment to avoid conflicts with other packages:

# Create a virtual environment
python -m venv docling-env

# Activate the virtual environment
# On macOS/Linux:
source docling-env/bin/activate
# On Windows:
docling-env\Scripts\activate

# Install Docling
pip install docling

Using uv

Docling can also be installed using uv, a fast Python package installer:

uv pip install docling

Using conda

If you're using conda, you can install Docling via pip in your conda environment:

conda create -n docling python=3.10
conda activate docling
pip install docling

From Source

To install from source, clone the repository and install in development mode:

git clone https://github.com/docling-project/docling.git
cd docling
pip install -e .

For development with all dependencies:

pip install -e ".[dev]"

Verifying Installation

After installation, verify that Docling is correctly installed:

python -c "import docling; print(docling.__version__)"

Or test the CLI:

docling --version

Optional Dependencies

Some features require additional dependencies:

Visual Language Models

For VLM support (e.g., GraniteDocling), additional dependencies may be required. On Apple Silicon, MLX acceleration is automatically used when available.

Audio Processing

For audio file processing with ASR models, ensure you have the necessary audio processing libraries installed.

Docker Installation

Docling can also be run in Docker containers. Check the GitHub repository for Dockerfile examples and container images.

Troubleshooting

Common Issues

Import Errors

If you encounter import errors, ensure you're using the correct Python environment:

which python
python --version

Permission Errors

If you get permission errors, use --user flag or a virtual environment:

pip install --user docling

Model Download Issues

On first use, Docling downloads required models. Ensure you have internet connectivity and sufficient disk space. Models are cached locally for subsequent use.

Apple Silicon Optimization

On Apple Silicon Macs, Docling automatically uses MLX acceleration for supported models. Ensure you have the latest version for optimal performance.

Upgrading Docling

To upgrade to the latest version:

pip install --upgrade docling

To upgrade to a specific version:

pip install --upgrade docling==2.68.0

Next Steps

Once installed, you're ready to start using Docling:

• Check out the Getting Started guide
• Explore examples of common use cases
• Read the documentation for detailed information
• Try the CLI for quick conversions