A basic document parsing and loading utility - Markdown/HTML Conversion

Overview

The docp-* project suite is designed as a comprehensive (doc)ument (p)arsing library. Built in CPython, it consolidates the capabilities of various lower-level libraries, offering a unified solution for parsing binary document structures.

The suite is extended by several sister projects, each providing unique functionality:

The Toolset (Converters)

As of this release, PDF conversion into the following types is supported:

• PDF --> Markdown
• PDF --> HTML

Quickstart

Installation

To install docp-docling, first activate your target virtual environment, then use pip:

pip install docp-docling

For older releases, visit PyPI or the GitHub Releases page.

Model Fetching

If your project must remain offline, you’ll need to download the docling language model locally. The pdfparser.PDFParser class requires this model to be accessible, so it must be pre-fetched and set up before use. This section outlines how to download and configure the model for offline functionality.

1. Download the model:

docling-tools models download \
    --output-dir /path/to/models/docling-project

2. Update config.toml in docp-core:

   • Update the docling key in the paths.models table to match the download path specified in the previous step.

Enabling GPU Support

GPU support (CUDA) should be automatically detected by library internals. However, guidance for enabling GPU-support is available.

Example Usage

For convenience, here are a couple examples for how to convert a PDF into the supported formats.

Parse a PDF into Markdown format:

>>> from docp_docling import PDFParser

# Convert
>>> pdf = PDFParser(path='/path/to/file.pdf')
>>> pdf.to_markdown()

# Access the converted content
>>> pdf.content

# Render extracted text as HTML and preview in a browser.
>>> pdf.preview()

Parse a single page from a PDF into Markdown format, including images, and store to a file:

>>> from docp_docling import PDFParser

# Convert
>>> pdf = PDFParser(path='/path/to/file.pdf')
>>> pdf.to_markdown(page_no=1,
                    image_mode='embedded',  # <-- Include images
                    to_file=True)

# Render extracted text as HTML and preview in a browser.
>>> pdf.preview()

Parse a single page from a PDF into HTML format, including images:

>>> from docp_docling import PDFParser

# Convert
>>> pdf = PDFParser(path='/path/to/file.pdf')
>>> pdf.to_html(page_no=1,
                image_mode='embedded')  # <-- Include images

# Render extracted text and preview in a browser.
>>> pdf.preview()

Using the Library

The documentation suite provides detailed explanations and usage examples for each importable module. For in-depth documentation, code examples, and source links, refer to the Library API page.

A search field is available in the left navigation bar to help you quickly locate specific modules or methods.

Troubleshooting

No troubleshooting guidance is available at this time.

For questions not covered here, or to report bugs, issues, or suggestions, please open an issue on GitHub.