NVIDIA Chat With RTX is a demo app that allows users to personalize a GPT large language model connected to their own content, enabling them to query a custom chatbot for contextually relevant answers. The app leverages retrieval-augmented generation (RAG), TensorRT-LLM, and RTX acceleration for fast and secure results on Windows RTX PCs. Users can chat with notes, documents, and videos in various formats, and developers can explore the TensorRT-LLM RAG developer reference project to create their own RAG-based applications for RTX.

Cover Image for NVIDIA Chat With RTX