Nvidia Introduces RTX Chat: A New AI Chatbot for Your PC
Nvidia has unveiled a novel approach to running a Large Language Model (LLM) chatbot on your computer with RTX Chat. This announcement closely follows the release of Nvidia’s latest data center GPU, the RTX 2000 Ada.
The new Chat with RTX app from Nvidia enables users to create a customized chatbot tailored to their requirements, which can operate directly on their machine if equipped with an RTX GPU. This specialized GPT LLM is integrated with the content on your device, including documents, notes, videos, and other data. By operating locally, it ensures swift and secure outcomes compared to cloud-based solutions.
Similar to conventional chatbots, users can input queries into RTX Chat to receive contextually relevant responses. Moreover, it offers the flexibility to select from various open-source AI models like Mistral and Meta’s Llama. When searching for data within documents, it not only provides the required information but also cites reference files in its responses. Additionally, akin to Google’s Gemini chatbot, users can also search for information within YouTube videos.
Jensen Huang, the founder and CEO of Nvidia, remarked, “Generative AI is the single most significant platform transition in computing history and will transform every industry, including gaming. With over 100 million RTX AI PCs and workstations, NVIDIA is a massive installed base for developers and gamers to enjoy the magic of generative AI.”
However, RTX Chat has its limitations. It cannot recall previous conversations, necessitating a fresh start for each chat. Additionally, there are some issues to address, and it may consume a significant amount of system resources. Nevertheless, as RTX Chat is still under development, improvements are anticipated in the near future.
See Demo Version HERE