LatexToolkit 📝 → 📄

LatexToolkit is lightweight Python package working on top of magic-pdf. It is designed to convert documents into LaTeX format. Whether you're working with PDFs, markdown files, or other structured text formats, this toolkit is thought to streamline the workflow of LaTeX conversion.

Features

✔️ End to end pipeline from PDF to LaTeX .
✔️ Simple CLI tool for documents to LaTeX conversions.

Future features: Support of .doc , .docx , .ppt and .pptx. formats.

Code available here

Installation

1. Ensure to install first magic-pdf

Using Conda env:

conda create -n MinerU python=3.10
conda activate MinerU
pip install -U magic-pdf[full] --extra-index-url https://wheels.myhloli.com

Download model weight files:

pip install huggingface_hub
wget https://github.com/opendatalab/MinerU/raw/master/scripts/download_models_hf.py -O download_models_hf.py
python download_models_hf.py

If using GPU follow magic-pdf Official installation

2. Install LatexToolkit via pip:

pip install LatexToolkit

Ussage

Run the tool from the terminal to convert a document:

latex_toolkit input_file.pdf

or use it in your Python scripts:

from LatexToolkit import to_latex

to_latex("input_file.pdf")