๐ RAG on Windows using NVIDIA NIM, TensorRT-LLM and LlamaIndex ๐ฆ
April 2, 2025 ยท View on GitHub
Installer
If you are using ChatRTX installer, setup of the models selected during installation is done by the installer.
ChatRTX Backend APIs
ChatRTX APIs serve as the foundation for the ChatRTX application, providing backend inference and RAG capabilities. These APIs allow developers to seamlessly integrate their applications with the inference engine and utilize the various AI models supported by ChatRTX. This integration enables developers to incorporate advanced AI inference and RAG features into their applications
ChatRTX UI Client
Prerequisite
- Node and NPM installed
Run ChatRTX - Development
- Set the python enviromnent path in file config.js at src\bridge_commands
- In one terminal run
npm run watch - In another run
npm run start-electron
Build ChatRTX
- Set the python enviromnent path in file config-packed.js at src\bridge_commands if needed.
- Run
npm run build-electron. This creates dist and contains NVIDIA ChatRTX.exe at location dist\win-unpacked which launches ChatRTX app
This project will download and install additional third-party open source software projects. Review the license terms of these open source projects before use.