skills.rest
leonanpereirapinto
leonanpereirapintoCOMMUNITY
Explore all skills by this author →
𝕏@leonanpereirapGitHub

docling

Convert PDFs, Word, HTML, and images into structured Markdown, JSON, or HTML output.

1|Updated Mar 27, 2026
Search Tags:#ocr#rag#conversion#chunking#export#document-processing#docling
One-click install
npx skills add https://github.com/leonanpereirapinto/ai-utils --skill docling-leonanpereirapinto
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: docling
Source: https://github.com/leonanpereirapinto/ai-utils/tree/main/libs/docling/skills/beagle-docling
Command: npx skills add https://github.com/leonanpereirapinto/ai-utils --skill docling-leonanpereirapinto

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Docling provides a local reference snapshot to convert diverse document formats into structured, searchable content, enabling efficient retrieval and analysis.

Core Features & Use Cases

  • Conversion: Convert PDFs, Word, HTML, and images into structured outputs.
  • OCR & Chunking: Apply OCR and chunk content for RAG pipelines.
  • Export: Output to Markdown, JSON, or HTML for downstream systems.

Quick Start

Run a sample document through Docling to produce Markdown output for immediate inspection.

Frequently Asked Questions about docling

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I convert PDFs and Word documents into structured content for RAG?▼

Convert PDFs and Word documents into structured content by applying Docling with OCR and chunking strategies to produce searchable Markdown, JSON, or HTML outputs.

Can I use OCR to extract text from images for retrieval-augmented workflows?▼

Yes, you can extract text from images for retrieval-augmented workflows by applying OCR options during document conversion to generate structured, searchable content.

What is the best way to chunk documents for a retrieval pipeline?▼

Chunk documents for a retrieval pipeline by applying chunking strategies during document conversion, which segments structured content for efficient retrieval and analysis.

Does document processing support exporting to Markdown and JSON?▼

Document processing supports exporting to Markdown, JSON, and HTML formats, allowing you to output structured content for downstream systems and immediate inspection.

How does converting HTML to structured content improve searchability?▼

Converting HTML to structured content improves searchability by transforming diverse formats into normalized outputs, enabling efficient retrieval and analysis within downstream systems.

Related Skills

Explore More Data & Analytics Skills→
hmzainjamilhmzainjamil
1

PDF Converter

Convert PDF files to editable office formats and back to PDF.

Community
Intermediate
patrykkopycinskipatrykkopycinski
6

vector-search-setup

Configure Elasticsearch indices with dense_vector mappings for kNN and hybrid retrieval.

Community
Intermediate
camoneartcamoneart
5

rag-implementation

Implement RAG systems with vector databases and retrieval strategies.

Community
Advanced
anilcan-karaanilcan-kara

ocr-and-documents

Extract text from PDFs and scanned documents using pymupdf or marker-pdf.

Community
Intermediate