Tools / repository

docling

Docling is an open-source document processing library that parses formats including PDF, DOCX, PPTX, XLSX, HTML, EPUB, audio, and video into a unified DoclingDocument representation, with exports to Markdown, HTML, JSON, and more. It offers OCR, PDF layout and table understanding, a CLI, an API server, and an MCP server.

URL: https://github.com/docling-project/docling
Collection: Developer Tools
License: MIT
Open source: Yes

ai convert document-parser document-parsing documents docx html markdown pdf pdf-converter pdf-to-json pdf-to-text pptx tables xlsx ocr gen-ai python developer-tools github open-source