multimodal-parsers 0.1.1

PDF processing pipeline: remove headers/footers, convert to markdown, and generate image captions

multimodal-parsers

PDF processing pipeline: removes headers/footers, converts to markdown, and generates image captions using MLX VLM.

Installation

pip install multimodal-parsers

Dependencies

The package automatically installs:

• Pillow
• mlx-vlm
• pymupdf
• scikit-learn
• numpy
• marker-pdf

Additionally, you may need to install:

pip install "unstructured[pdf]"

Usage

After installation, use the multimodal-parsers command:

multimodal-parsers <input_dir> <output_dir>

Example

multimodal-parsers Database/Private/Files Database/Private/Files/output

What it does

1. Removes headers and footers from PDF files using clustering algorithms
2. Converts PDFs to markdown using marker-pdf
3. Generates image captions using MLX VLM (InternVL3-1B-4bit)
4. Outputs final markdown files with captioned images

Development

git clone https://github.com/thuuyen98/PIER-QA
cd PIER-QA
pip install -e ".[dev]"

License

MIT License