https://github.com/harishdeivanayagam/rowfill
Open-source unstructured data (PDFs, Images, Audiofiles) processing platform built for knowledge workers
https://github.com/harishdeivanayagam/rowfill
document document-extraction document-parsing image-ocr langgraph llama llm nextjs ocr ocr-javascript ollama openai pdf pdfs unstructured unstructured-data vision vision-api
Last synced: 6 months ago
JSON representation
Open-source unstructured data (PDFs, Images, Audiofiles) processing platform built for knowledge workers
- Host: GitHub
- URL: https://github.com/harishdeivanayagam/rowfill
- Owner: harishdeivanayagam
- License: other
- Created: 2025-01-09T07:23:18.000Z (9 months ago)
- Default Branch: master
- Last Pushed: 2025-03-18T11:02:41.000Z (7 months ago)
- Last Synced: 2025-04-13T02:09:53.888Z (6 months ago)
- Topics: document, document-extraction, document-parsing, image-ocr, langgraph, llama, llm, nextjs, ocr, ocr-javascript, ollama, openai, pdf, pdfs, unstructured, unstructured-data, vision, vision-api
- Language: TypeScript
- Homepage: https://www.rowfill.com
- Size: 1.2 MB
- Stars: 275
- Watchers: 8
- Forks: 14
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
- License: LICENSE
Awesome Lists containing this project
README
Open-source document processing platform built for knowledge workers
## 👋 Welcome to Rowfill
Rowfill helps extract, analyze, and process data from complex documents, images, PDFs and more with advanced AI capabilities.
## ✨ Features
### 📄 Document Processing
- **Advanced OCR & Processing**: Extract text, tables, and handwriting from any document with high precision
- **Auto-schema Generation**: Automatically detect and adapt to document structures
- **Custom Actions**: Create tailored workflows with automated task processing
### 🔒 Privacy & Security
- **Local LLM Support**: Supports Local LLMs like Llama, Mistral also supports OpenAI vision models
- **Sync with your company data**: Clone sensitive data while maintaining privacy
- **Open Source**: Rowfill is a AGPLv3 licensed open source project
## 🚀 Getting Started
1. Run the docker compose file
2. Configure the environment variables (Refer to mockenv file)
3. Start extracting data from your documents!
## 📚 Documentation
Visit our [documentation](https://docs.rowfill.com) for:
- Detailed integration guides
- API reference
- Best practices
- Example implementations
- Privacy controls configuration
## 🤝 Contributing
We love contributions! If you'd like to contribute:
1. Fork the repository
2. Create your feature branch (`git checkout -b feature/AmazingFeature`)
3. Commit your changes (`git commit -m 'Add some AmazingFeature'`)
4. Push to the branch (`git push origin feature/AmazingFeature`)
5. Open a Pull Request
## 📝 License
This project is licensed under the AGPLV3 License - see the [LICENSE](LICENSE) file for details.
## 💬 Community & Support
- [Discord Community](https://discord.gg/y65HPrCe)
- [GitHub Issues](https://github.com/harishdeivanayagam/rowfill/issues)
- [Email Support](mailto:hello@rowfill.com)
## 🖥 Cloud Version
Cloud version (Alpha) is currently live at [Rowfill Cloud](https://cloud.rowfill.com)
To try it out, [contact us](mailto:support@rowfill.com)
---
**Note**: This project is a work in progress and is not yet ready for production use. We are actively working on it and will update this README as we make progress.
---
Built with ❤️ for the AI community