CAMeL Tools Lite (camel-lite)

camel-lite is a modernized, lightweight fork of the original CAMeL Tools suite for Arabic natural language processing.

It is designed to provide core Arabic NLP functionalities (like MLE disambiguation, morphological analysis, and text normalization) in a fast, dependency-lean package. This fork strips out heavy dependencies like PyTorch, adopts modern Python tooling (uv, Typer, Ruff), and utilizes strict type-checking.

Documentation

For a deep dive into our vision, architectural decisions, and future plans, please see our project documentation:

• Motivation & Vision: Why we built camel-lite and our overarching goals.
• Project Roadmap: Our immediate priorities and future plans for re-introducing optional heavy dependencies.

For API documentation, camel-lite maintains parity with the core features of the canonical upstream package.

Installation

uv pip install camel-lite

Citation

If you use camel-lite, please cite the original CAMeL Tools paper:

@inproceedings{obeid-etal-2020-camel,
   title = "{CAM}e{L} Tools: An Open Source Python Toolkit for {A}rabic Natural Language Processing",
   author = "Obeid, Ossama and Zalmout, Nasser and Khalifa, Salam and Taji, Dima and Oudah, Mai and Alhafni, Bashar and Inoue, Go and Eryani, Fadhl and Erdmann, Alexander and Habash, Nizar",
   booktitle = "Proceedings of the 12th Language Resources and Evaluation Conference",
   month = may,
   year = "2020",
   publisher = "European Language Resources Association",
   url = "https://www.aclweb.org/anthology/2020.lrec-1.868",
   pages = "7022--7032",
}

License

Available under the MIT license.