Nvidia, known for its cutting-edge technology in the graphics card industry, is constantly pushing boundaries in the realm of artificial intelligence. One such example of this is their experimental ChatRTX chatbot, which is receiving updates to include more AI models for RTX GPU owners.
The latest update to the ChatRTX chatbot introduces new AI models such as Google’s Gemma, ChatGLM3, and OpenAI’s CLIP. These additions aim to make it easier for users to search through personal documents and photos with the help of their RTX GPUs.
Nvidia initially introduced ChatRTX as a demo app called “Chat with RTX” earlier this year. The app acts as a local chatbot server that can be accessed from a browser, allowing for seamless interaction with personal data. Users can feed local documents and YouTube videos into the chatbot to receive summaries and answers to their queries.
One of the key features of ChatRTX is the ability to choose between different AI models to best suit the user’s needs. By including models like Google’s Gemma and ChatGLM3, Nvidia is simplifying the process of running complex AI models locally.
ChatGLM3, an open bilingual language model, adds English and Chinese language support to the chatbot. This expansion in language capabilities ensures that a wider range of users can benefit from ChatRTX’s powerful search capabilities.
In addition to text-based queries, Nvidia is also updating ChatRTX to support voice commands. By integrating Whisper, an AI speech recognition system, users can now search through their data using voice commands, further enhancing the user experience.
Overall, Nvidia’s continuous updates to the ChatRTX chatbot demonstrate their commitment to innovation in the AI space. By providing users with a versatile and user-friendly tool for exploring and analyzing data, Nvidia is empowering RTX GPU owners to make the most of their hardware capabilities.
Leave a Reply