pdf2md

Convert PDF files to Markdown using Mistral's OCR API.

Setup

uv as package manager is highly recommended (https://docs.astral.sh/uv/getting-started/installation)

1. Clone/copy this project to your machine

2. Copy .env.example to .env and add your Mistral API key:

   cp .env.example .env
   # Edit .env and set MISTRAL_API_KEY

3. Install dependencies:

   uv sync

Usage

Run from the project directory:

uv run --env-file .env main.py input.pdf

With custom output folder:

uv run --env-file .env main.py input.pdf -o output_folder

Installing as a global command

Windows (not tested)

Add the project folder to PATH (windows add folder to path)

Then run from anywhere: pdf2md input.pdf

Linux/MacOS

Add an alias to your shell profile (.bashrc or .zshrc):

alias pdf2md='uv run --project <path_to_this_folder> --env-file <path_to_this_folder>/.env <path_to_this_folder>/main.py'

Output

Creates a folder (same name as the PDF) containing:

• filename.md - The converted markdown
• img-*.jpeg - Extracted images (if any)