- Nvidia updates ChatRTX chatbot with new AI models for RTX GPU users.
- New models include Google’s Gemma, ChatGLM3, and OpenAI’s CLIP for improved document and media search.
- Requires RTX 30- or 40-series GPU with minimum 8GB VRAM.
- ChatRTX simplifies local execution of AI models, providing an intuitive interface for users.
- Addition of voice query functionality via Whisper AI speech recognition system.
- Available for download from Nvidia’s website.
Main AI News:
Nvidia continues to enrich its experimental ChatRTX chatbot, catering to RTX GPU owners with a suite of new AI models. This local Windows PC application, initially unveiled as “Chat with RTX” in February, now integrates Google’s Gemma, ChatGLM3, and OpenAI’s CLIP model, broadening its utility for users seeking enhanced document and media search capabilities.
To access this evolving toolkit, users require an RTX 30- or 40-series GPU boasting a minimum of 8GB of VRAM. ChatRTX establishes a local chatbot server accessible via a browser, enabling users to analyze personal documents and YouTube videos, generating summaries and responses tailored to individual data sets.
Google’s Gemma model, optimized for high-performance laptops and desktop PCs, seamlessly integrates into ChatRTX. Nvidia’s application simplifies the local execution of these models, offering users an intuitive interface to navigate between different AI models, ensuring optimal compatibility with their data analysis and search requirements.
ChatRTX, available for download via Nvidia’s website, now introduces support for ChatGLM3, an expansive bilingual (English and Chinese) language model, alongside OpenAI’s CLIP. This inclusion empowers users to interact with and search local photo data, facilitating image recognition training within the model.
In a significant update, Nvidia introduces voice query functionality to ChatRTX, integrating Whisper, an AI-driven speech recognition system. This addition enables users to leverage voice commands for seamless data exploration and search experiences.
Conclusion:
Nvidia’s integration of Google’s Gemma model and voice commands into ChatRTX marks a significant advancement in AI-driven document and media search capabilities for RTX GPU users. This expansion enhances Nvidia’s competitive edge in the market, catering to the evolving needs of users seeking efficient and intuitive AI-powered solutions for data analysis and exploration. The inclusion of voice query functionality further amplifies the accessibility and usability of the ChatRTX platform, positioning Nvidia as a key player in the burgeoning AI software market.
