# Docling AI Document Intelligence Pipeline

> Docling is an IBM-backed open-source toolkit that converts PDF, DOCX, PPTX, XLSX, HTML, images, audio, and LaTeX files into structured formats for gen AI workflows. It features advanced PDF layout understanding, OCR, table extraction, and integrations with LangChain, LlamaIndex, and CrewAI.

- Skill: `agentskillexchange/docling-ai-document-intelligence-pipeline` (Agent Skill)
- Install (CLI): `npx skillmds@latest add agentskillexchange/docling-ai-document-intelligence-pipeline`
- Raw SKILL.md: https://api.skillmd.com/api/skills/agentskillexchange/docling-ai-document-intelligence-pipeline/raw
- Safety review: pending (external: skill-scanner PASS, skillspector PASS)
- Works with: Claude Code, Claude.ai, OpenAI Codex
- Category: Web & Frontend
- Author: agentskillexchange (https://skillmd.com/u/agentskillexchange)
- Updated: 2026-09-08
- Page: https://skillmd.com/skills/agentskillexchange/docling-ai-document-intelligence-pipeline

---


# Docling AI Document Intelligence Pipeline

Docling is an IBM-backed open-source toolkit that converts PDF, DOCX, PPTX, XLSX, HTML, images, audio, and LaTeX files into structured formats for gen AI workflows. It features advanced PDF layout understanding, OCR, table extraction, and integrations with LangChain, LlamaIndex, and CrewAI.

## Installation

Use the upstream install or setup path that matches your environment:
- pip install docling

Requirements and caveats from upstream:
- [![PyPI - Python Version](https://img.shields.io/pypi/pyversions/docling)](https://pypi.org/project/docling/)
- **Note:** Python 3.9 support was dropped in docling version 2.70.0. Please use Python 3.10 or higher.
- ## 3. Python usage (recommended)

Basic usage or getting-started notes:
- 🔌 Connect to any agent using the [MCP server](https://docling-project.github.io/docling/usage/mcp/)
- 🔌 [MCP server](https://docling-project.github.io/docling/usage/mcp/) for agentic applications
- ### 1. Install

- Source: https://github.com/docling-project/docling
- Extracted from upstream docs: https://raw.githubusercontent.com/docling-project/docling/HEAD/README.md

## Source

- [Agent Skill Exchange](https://agentskillexchange.com/skills/docling-ai-document-intelligence-pipeline/)