# Docling
[](https://arxiv.org/abs/2408.09869) [](https://pypi.org/project/docling/)  [](https://python-poetry.org/) [](https://github.com/psf/black) [](https://pycqa.github.io/isort/) [](https://pydantic.dev) [](https://github.com/pre-commit/pre-commit) [](https://opensource.org/licenses/MIT) Docling parses documents and exports them to the desired format with ease and speed. ## Features * ποΈ Reads popular document formats (PDF, DOCX, PPTX, Images, HTML, AsciiDoc, Markdown) and exports to Markdown and JSON * π Advanced PDF document understanding incl. page layout, reading order & table structures * π§© Unified, expressive [DoclingDocument](./concepts/docling_document.md) representation format * π€ Easy integration with LlamaIndex π¦ & LangChain π¦π for powerful RAG / QA applications * π OCR support for scanned PDFs * π» Simple and convenient CLI ### Coming soon * βΎοΈ Equation & code extraction * π Metadata extraction, including title, authors, references & language * π¦π Native LangChain extension ## IBM β€οΈ Open Source AI Docling has been brought to you by IBM.