---
id: "b924"
language: "en"
library: "tools"
official_url: "https://github.com/docling-project/docling"
profile_updated_on: "2026-10-23"
---

# Docling

Parse document layouts, tables and reading order into structured content for RAG and agents.

- Company / organization: Docling project
- Category: Model development
- Official website: [https://github.com/docling-project/docling](https://github.com/docling-project/docling)
- Profile updated: 2026-10-23


## Overview

Docling prepares source documents for AI applications. Layout analysis, OCR and optional vision-language models convert PDFs, Office files and images into DoclingDocument, with Markdown, HTML and JSON exports. It is a preprocessing component for retrieval pipelines, rather than a ready-made document chatbot. Local execution is supported; external models or services depend on configuration.

## Usage guide & costs

### Before you start

Code is MIT; OCR, vision-language and speech models have their own licenses. Prepare model files and runtime resources separately; the code license does not cover every model weight.

[Official details](https://github.com/docling-project/docling/blob/main/LICENSE)
[Official details](https://github.com/docling-project/docling/blob/main/README.md)


## Official sources and references

- [Official website](https://github.com/docling-project/docling)
- [Documentation](https://docling-project.github.io/docling/)
- [Documentation](https://github.com/docling-project/docling/blob/main/README.md)

## Reading & subscriptions

- [Interactive profile](../../../products/docling--b924.html)
- [Read](../../../read/en/products/docling--b924.html)
- [JSON](../../../read/en/products/docling--b924.json)

Descriptions summarize public information; consult official websites for features, pricing and regional availability.