NVIDIA Chat with RTX

Chat With RTX is a demo app that lets you personalize a GPT large language model (LLM) connected to your own content—docs, notes, videos, or other data.

NVIDIA Chat with RTX is a personalized AI chatbot demo app designed to run locally on Windows RTX PCs or workstations. It allows users to connect a GPT-based large language model (LLM) to their own content, such as documents, notes, images, and videos, enabling quick, contextually relevant responses. Leveraging NVIDIA's TensorRT-LLM, NIM microservices, and RTX acceleration, the app ensures fast, private, and efficient performance. It supports multiple file formats and features automatic speech recognition for voice interactions. With access to NVIDIA NIM microservices, users can optimize AI models and build custom workflows. Ideal for developers and professionals, Chat with RTX combines privacy, speed, and advanced AI capabilities, making it a powerful tool for personalized, on-device AI solutions.