markpdfdown
A high-quality PDF to Markdown tool based on large language model visual recognition. 一款基于大模型视觉识别的高质量PDF转Markdown工具
What is markpdfdown?
A high-quality PDF to Markdown tool based on large language model visual recognition. 一款基于大模型视觉识别的高质量PDF转Markdown工具
Overview of markpdfdown
What it is
MarkPDFDown is a tool that uses multimodal large language models to convert PDF files into Markdown format. It is designed to extract text, preserve formatting, and handle complex document structures such as tables, formulas, and diagrams. The tool supports multiple LLM providers through LiteLLM, including OpenAI, OpenRouter, and Requesty.
Key features
- PDF to Markdown conversion
- Image to Markdown conversion
- Multi-provider support (OpenAI, OpenRouter, Requesty) via LiteLLM
- Flexible CLI with file-based and pipe-based usage modes
- Format preservation for headings, lists, tables, and other elements
- Page range selection for converting specific pages
- Modular architecture with separation of concerns
Use cases
- Converting PDF documents into editable Markdown text
- Extracting content from scanned PDFs or image-heavy documents using multimodal AI
- Processing batches of PDF files for documentation or data extraction
- Integrating PDF conversion into automated pipelines via pipe mode or Docker
Getting started
bash# Using uv (recommended)curl -LsSf https://astral.sh/uv/install.sh | shgit clone https://github.com/MarkPDFdown/markpdfdown.gitcd markpdfdownuv syncuv pip install -e .# Basic conversionmarkpdfdown --input document.pdf --output output.md
License and pricing
This project is licensed under the Apache License 2.0. It is open source with no stated pricing.
Based on the project's public README and repository metadata.