ldc-doc

Adds MS Word .doc support to the llm-dataset-converter library.

Requirements

• antiword available on PATH

  • Debian/Ubuntu: sudo apt install antiword
  • Windows: Softpedia

Installation

pip install git+https://github.com/waikato-llm/llm-dataset-converter.git
pip install git+https://github.com/waikato-llm/ldc-doc.git

Plugins

See here for an overview of all plugins.