docling-project.github.io
Docling is an open-source tool that parses multiple document formats, including PDF, DOCX, PPTX, XLSX, HTML, EPUB, email formats, images, audio and more. It provides advanced PDF understanding such as page layout, reading order and table structure, a unified DoclingDocument representation, and export to Markdown, HTML and JSON. Integrations include LangChain, LlamaIndex, Crew AI and Haystack.
