docling

Convert PDFs, DOCX, and images into structured DoclingDocument objects.

20|4|Updated Nov 9, 2025

Search Tags:#ocr #markdown #pdf extraction #chunking #data preparation #document parsing #rag pipeline

One-click install

npx skills add https://github.com/anderskev/amelia --skill docling

Or copy as Structured Prompt for Agent▼

Please help me install this Agent Skill.
Skill: docling
Source: https://github.com/anderskev/amelia/tree/main/.claude/skills/amelia/docling
Command: npx skills add https://github.com/anderskev/amelia --skill docling

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

Extracting structured information from diverse document formats (PDFs, DOCX, images) for AI applications like RAG is challenging due to layout complexities, OCR needs, and varied content types. Docling simplifies this by providing a unified parsing solution.

Core Features & Use Cases

Multi-Format Parsing: Convert PDFs, Word, PowerPoint, HTML, and images into structured DoclingDocument objects.
Advanced Data Extraction: Extract text, tables, and images with layout understanding, including OCR for scanned documents.
RAG-Ready Chunking: Generate context-rich chunks with hierarchical metadata, optimized for vector databases and retrieval.
Use Case: Process a folder of mixed legal documents (scanned PDFs, DOCX contracts) to extract key clauses and tables, then chunk them for a RAG system to answer specific legal questions.

Quick Start

Convert the attached 'report.pdf' into Markdown format, ensuring OCR is enabled for any scanned text.