Platform | Download Link |
---|---|
iOS | Download on the App Store |
Android | Download APK |
macOS | Download DMG |
Web | Access the Web App |
Windows | Download Exe |
RAGDrive is an innovative, open-source application designed to bring the power of large language models (LLMs) directly to your local system. With RAGDrive, you can easily configure and run LLMs on your local machine while enjoying a suite of advanced features, such as web search, document uploads, and web scraping. RAGDrive also offers a straightforward way to connect and configure popular LLM platforms like OpenAI, Groq, Sambanova, Hugging Face, and Anthropic—all wrapped up in a simple and easy-to-use UI.
Note: RAGDrive is currently under development, and contributions are welcome!
Watch the introduction video on YouTube for a quick overview of RAGDrive.
- Run Local LLMs: Access and run LLMs on your local machine.
- Web Search Integration: Search the web and integrate results seamlessly.
- Document Uploads: Easily upload and process documents.
- Web Scraping: Collect data directly from websites.
- Connect with Leading LLM Services: Seamlessly integrate with popular LLM platforms like OpenAI, Groq, Sambanova, Hugging Face, and Anthropic.
RAGDrive supports building for WINDOWS, LINUX, and MACOS, making it versatile for various operating systems. For detailed build instructions, please refer to the documentation in this repository.
- Electron + Vite: The project is built using Electron and Vite for efficient cross-platform desktop application development.
- Node.js: Supports backend operations and interaction with external APIs.
- React: Provides a dynamic and responsive UI.
Make sure you have Node.js installed on your local machine. Optionally, you can choose to use yarn or pnpm for package management.
-
Clone the repository:
git clone https://github.com/NidumAI-Inc/ragdrive.git cd ragdrive
-
Install the dependencies:
npm install # or yarn install # or pnpm install
-
Start the development server:
npm start # or yarn start # or pnpm start
We welcome contributions! If you’re interested in improving RAGDrive, please reach out at [email protected] or submit a pull request. Contributors will be credited in the project documentation.
Special thanks to lama.cpp, node-llama-cpp, and DuckDuckGo Search for their invaluable support and resources.
Happy coding! 🚀