Docling

Docling is an open-source library by IBM Research that efficiently converts PDF and other document formats into Markdown or JSON.

FreePython LibraryCLIDockerOpen source

Visit websitedocling-project.github.io

Compare with book-to-skill Explore Docling alternatives

Overview

Docling is an open-source library by IBM Research that efficiently converts PDF and other document formats into Markdown or JSON. Utilizing lightweight AI models, it provides high-quality layout analysis and table extraction, making it ideal for local RAG pipelines and data preparation.

Key features

Multi-format support (PDF, DOCX, PPTX, HTML)
Advanced table structure recognition
Lightweight local AI models
Markdown and JSON output
Integrated OCR support
Metadata and hierarchy preservation

Pricing

FreeStarting price: Free

View pricing page

Verified on: 8/23/2026 · Recheck pricing on the official page

Use cases

Local RAG data pipeline construction
Structuring large document archives
Offline parsing of sensitive documents

Who it is for

Open Source DevelopersData EngineersPrivacy-conscious Enterprises

Integrations

LangChainLlamaIndexHugging FacePydantic

How we verified this

Company, pricing, and feature details come from the primary sources below and our latest verification pass. When sources disagree, the official source and the most recent check win.

Last verified 08/23/2026Verified sources: 2