2024-10-14 14:13:13 +02:00
|
|
|
# Docling
|
|
|
|
|
|
|
|
<p align="center">
|
2024-10-22 15:29:36 +02:00
|
|
|
<img loading="lazy" alt="Docling" src="assets/docling_processing.png" width="100%" />
|
2024-10-14 14:13:13 +02:00
|
|
|
</p>
|
|
|
|
|
|
|
|
|
|
|
|
[](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)
|
|
|
|
|
2024-10-16 21:02:03 +02:00
|
|
|
Docling parses documents and exports them to the desired format with ease and speed.
|
2024-10-14 14:13:13 +02:00
|
|
|
|
|
|
|
## Features
|
|
|
|
|
2024-10-30 15:02:28 +01:00
|
|
|
* 🗂️ Reads popular document formats (PDF, DOCX, PPTX, Images, HTML, AsciiDoc, Markdown) and exports to Markdown and JSON
|
2024-10-16 21:02:03 +02:00
|
|
|
* 📑 Advanced PDF document understanding incl. page layout, reading order & table structures
|
2024-10-30 15:02:28 +01:00
|
|
|
* 🧩 Unified, expressive [DoclingDocument](./concepts/docling_document.md) representation format
|
2024-10-16 21:02:03 +02:00
|
|
|
* 📝 Metadata extraction, including title, authors, references & language
|
|
|
|
* 🤖 Seamless LlamaIndex 🦙 & LangChain 🦜🔗 integration for powerful RAG / QA applications
|
|
|
|
* 🔍 OCR support for scanned PDFs
|
|
|
|
* 💻 Simple and convenient CLI
|