An open API service indexing awesome lists of open source software.

https://github.com/docling-project/website

The Docling website
https://github.com/docling-project/website

Last synced: 8 months ago
JSON representation

The Docling website

Awesome Lists containing this project

README

          

# Docling Website

This is the official website for [Docling](https://github.com/docling-project/docling), a powerful document processing tool that prepares your files for GenAI, RAG, and beyond.

## About Docling

Docling transforms messy PDFs, DOCX, and slides into clean, structured dataβ€”ready for RAG, GenAI apps, or anything downstream. It handles complex layouts, tables, and formulas so you don't have to.

### Key Features

- **πŸ—‚οΈ Multi-format Support**: Parse PDF, DOCX, PPTX, XLSX, HTML, audio, and images
- **πŸ“‘ Deep PDF Understanding**: Layout, tables, reading order, code, and formulas
- **🧬 Unified Format**: Consistent DoclingDocument structure for all outputs
- **β†ͺ Multiple Export Formats**: Markdown, HTML, DocTags, or lossless JSON
- **πŸ”’ Local Processing**: Run locally for sensitive or air-gapped environments
- **πŸ€– AI Framework Integration**: Works with LangChain, LlamaIndex, Haystack, and more
- **πŸ” OCR Support**: Handle scanned PDFs and images
- **πŸ‘“ Visual Language Models**: Compatible with SmolDocling
- **πŸŽ™οΈ Audio Support**: Automatic speech recognition (ASR)
- **πŸ’» Developer Friendly**: Fast CLI and easy integration

## Tech Stack

This website is built with:

- [Next.js 14](https://nextjs.org/) - React framework
- [TypeScript](https://www.typescriptlang.org/) - Type safety
- [Sass](https://sass-lang.com/) - CSS preprocessing
- [Bootstrap 5](https://getbootstrap.com/) - UI components

## Getting Started

First, install dependencies:

```bash
npm install
# or
yarn install
# or
pnpm install
```

Then, run the development server:

```bash
npm run dev
# or
yarn dev
# or
pnpm dev
```

Open [http://localhost:3000](http://localhost:3000) with your browser to see the result.

## Project Structure

```
src/
β”œβ”€β”€ app/ # Next.js app router
β”œβ”€β”€ components/ # React components
β”‚ β”œβ”€β”€ pages/ # Page-specific components
β”‚ β”œβ”€β”€ ui/ # Reusable UI components
β”‚ β”œβ”€β”€ icons/ # SVG icons
β”‚ β”œβ”€β”€ header/ # Header components
β”‚ └── footer/ # Footer components
β”œβ”€β”€ styles/ # Global styles and fonts
β”œβ”€β”€ lib/ # Utilities and types
└── utils/ # Constants and helpers
```

## Learn More

- **Concepts**: [Learn Docling fundamentals](https://docling-project.github.io/docling/concepts/)
- **Examples**: [Try out recipes for various use cases](https://docling-project.github.io/docling/examples/)
- **Integrations**: [Popular frameworks and tools](https://docling-project.github.io/docling/integrations/)
- **Reference**: [See more API details](https://docling-project.github.io/docling/reference/document_converter/)

## Contributing

This website is part of the [Docling project](https://github.com/docling-project/docling). Your feedback and contributions are welcome!

## License

This project is part of the Docling ecosystem. See the main [Docling repository](https://github.com/docling-project/docling) for license information.