All projects
Topics
Related projects
markitdown186.6kLightweight Python utility converting PDFs, Office documents, images, audio, HTML, and other files to Markdown for LLM text-analysis pipelines developers.
free-programming-books-zh_CN119.1k:books: 免费的计算机编程类中文书籍，欢迎投稿
Stirling-PDF92.9kSelf-hosted web application offering 50+ PDF tools for merging, splitting, compressing, signing, converting, and OCR, aimed at users seeking private local document processing.
PaddleOCR90.1kLightweight multilingual OCR toolkit converting PDFs and images into structured data for AI workflows, supporting 100+ languages for developers building document parsing pipelines.