NVIDIA has made a significant move by releasing Chat with RTX, a free download that allows users of Windows PCs with NVIDIA RTX graphics cards to create and use personalized chatbots. These chatbots leverage the power of local GPUs to deliver a fast, bespoke AI experience. With a requirement of an NVIDIA GeForce RTX 30 Series GPU or above, boasting at least 8GB of VRAM, users can now provide a custom dataset for chatbots to pull from, furnishing individualized responses based on personal content. Chat with RTX utilizes a sophisticated AI technique known as retrieval-augmented generation (RAG), combined with NVIDIA TensorRT-LLM software and RTX acceleration, to enable users to integrate local files into chatbot responses. This means users can ask their bespoke chatbot context-sensitive questions and receive answers in real time, without the need to manually search through their notes or files. The application supports a variety of file formats, allowing for a seamless and efficient augmentation of data. Furthermore, Chat with RTX offers another level of convenience and privacy, as it operates locally on users' PCs. This ensures not only quicker responses but also keeps sensitive data private, never needing to leave the local device. NVIDIA's approach here also underscores a growing trend towards edge computing, where processing takes place on local devices rather than being reliant on cloud-based solutions. Additionally, Chat with RTX underscores the potential for developers to create LLM-based applications empowered by NVIDIA's RTX GPUs, with resources and a contest inviting innovation in this space.