ContextGem: Effortless LLM extraction from documents

Simple and straight forward Python utility that converts a Microsoft Word document (`.docx`) to a Markdown file (`.md`) and vice versa. It supports multiple Markdown elements, including headings, bold and italic text, both unordered and ordered lists, and many more.

Convert multi .docx files (Word) to multi .md files with media (image source) (github markdown) using pandoc

This project is a Python application that converts Word documents to Markdown files. It uses the python-docx library to read Word documents, parses the content into headings, paragraphs, lists, tables, and images, converts these elements to their Markdown equivalents, and writes the result to a Markdown file.