CodeBrowser / github / docling-project/docling
docling-project/docling
# Get your documents ready for gen AI
$ git clone https://github.com/docling-project/docling.git
stars
63,564
forks
4,492
language
Python
license
MIT License
What is docling-project/docling?
Docling is a library that converts documents (PDFs, Word files, PowerPoint presentations, HTML, and Excel spreadsheets) into structured formats like JSON and Markdown. Developers use it to parse and extract content from various document types so they can feed clean, machine-readable data into AI models and applications. It handles complex document elements like tables and maintains document structure during conversion.
Links
Homepage View on GitHub
Topics
#ai #convert #document-parser #document-parsing #documents #docx #html #markdown #pdf #pdf-converter #pdf-to-json #pdf-to-text #pptx #tables #xlsx
Activity
932 open issues · last updated Jul 21, 2026