Nvidia has recently announced updates to its experimental ChatRTX chatbot, providing RTX GPU owners with access to more AI models for enhanced functionality. These updates aim to improve the user experience and expand the capabilities of the chatbot.
The latest update includes the addition of Google’s Gemma, ChatGLM3, and OpenAI’s CLIP models to the existing repertoire of AI models. These new models allow users to search through personal documents and photos more efficiently, providing a powerful search tool for analyzing data.
To access these new features, users will need an RTX 30- or 40-series GPU with 8GB of VRAM or more. The chatbot runs locally on a Windows PC, creating a chatbot server that can be accessed from a browser. This enables users to feed their local documents and media, such as YouTube videos, into the chatbot for analysis.
The inclusion of Google’s Gemma model, designed for powerful laptops and desktop PCs, brings added convenience to users. Nvidia’s ChatRTX simplifies the process of running complex AI models locally, offering a user-friendly interface for selecting and utilizing different models based on the user’s specific data needs.
ChatRTX now supports ChatGLM3, an open bilingual language model that supports English and Chinese. This expansion of language support enhances the chatbot’s usability for a broader range of users, enabling seamless communication and data analysis across multiple languages.
In addition to text-based queries, Nvidia has integrated Whisper, an AI speech recognition system, to support voice queries within ChatRTX. This feature allows users to search their data using their voice, further enhancing the user experience and accessibility of the chatbot.
Overall, Nvidia’s updates to the ChatRTX chatbot demonstrate a commitment to providing RTX GPU owners with advanced AI capabilities for data analysis and search. With the integration of new AI models, expanded language support, and voice query functionality, users can experience a more robust and user-friendly chatbot experience.
Leave a Reply