Python

Docling

IBM-grade document understanding

by docling-project · MIT

63 374stars4 482forksPythonlanguage54 days agolast push

Document AI & OCRDocument parsing toolkitMITRuns locallyPythonIntermediate

From the README

Install

pip install docling

📑 Advanced PDF understanding incl. page layout, reading order, table structure, code, formulas, image classification, and more
🧬 A unified, expressive [DoclingDocument][doclingdocument] representation format
↪️ Various [export formats][supportedformats] and options, including Markdown, HTML, WebVTT, DocLang, DocTags and lossless JSON

Excerpts from the project README on GitHub. Copyright and licensing remain with the respective authors.

🛡 Published security advisories

A high count usually means the project is heavily examined. A low count usually means it is little examined — not that it is safe.

No public activity signals for this tool — it has no open repository we can measure.

Olud Pulse ⓘ ★★★★★★★★★★ /100 signals tracked

🐳 Docker pulls 📦 PyPI downloads / month 📦 npm downloads / month 🚀 Latest release ·

Visit website →View on GitHub

What is Docling?

Docling parses PDFs, DOCX, PPTX and images into structured representations with layout, tables and reading order, designed to plug straight into RAG frameworks.

Why people choose Docling

Rich structured output: layout, tables, reading order
First-class integrations with LangChain and LlamaIndex
Backed by IBM Research, MIT-licensed

Docling at a glance

Category	Document AI & OCR
Type	Document parsing toolkit
License	MIT
Runs locally	Yes
Built with	Python
Skill level	Intermediate
Best for	teams building document pipelines for RAG