README.md

NLPurify

A text cleaning and extraction engine was developed using a combination of traditional techniques like Unicode translations, cleaning using regular expressions, and modern tools like "natural language processing" and "large language models" to detect and clean long texts and create word vectors.

Getting Started

The source code is hosted at GitHub: sharkutilities/NLPurify. The binary installers for the latest release are available at the Python Package Index (PyPI).

pip install -U NLPurify

The module is currently under development, and new ideas are welcomed. Raise a new PR/issue for the same. The changes between each release are available here.

---

Caution

This code depreciates the existing GitHub Gist which was previously designed. Check #1 for more details.

Note

Legacy codes are available as a submodule. Check #5 for more details.