NVIDIA has upgraded its ChatRTX AI chatbot which takes the AI PC experience to a new level with improvements across the board.
NVIDIA ChatRTX Now Comes With Several Enhanced Input Options, Including Voice & Video Prompts
The ChatRTX chatbot by NVIDIA has seen tremendous advancements since it initially launched under the "Chat With RTX" branding. The differentiating factor between options such as OpenAI's ChatGPT and NVIDIA's ChatRTX is that the latter focuses on a more personalized experience, as it is designed to run on a local system, which means that you will have a GPT chatbot available to you all the time on your PC without the need to go online.
- ChatRTX adds to its growing list of supported LLMs, including Gemma, Google’s latest LLM, and ChatGLM3, an open, bilingual (English and Chinese) LLM, providing users with additional flexibility.
- New photo support enables ChatRTX users to easily search and interact locally with their photo data without the need for complex metadata labeling, thanks to OpenAI’s Contrastive Language-Image Pre-training (CLIP).
- ChatRTX users can now speak with their data, with added support for Whisper, an AI automatic speech recognition system that now enables ChatRTX to understand verbal speech.
Privacy is a massive bonus with NVIDIA's ChatRTX since you can even allow it to access local files. As a result of the edge AI environment, it is supposed to be much faster than alternatives out there.
Diving into the specifics, ChatRTX allows you to connect with multiple large language models out there, like Mistral and Llama 2 in the list. The AI chatbot leverages your graphics capabilities through NVIDIA's TensorRT-LLM & Retrieval Augmented Generated (RAG) software to deliver accelerated performance through the onboard RTX hardware. When you compare it to cloud-based options, ChatRTX will dominate them in terms of processing speeds.
As ChatRTX is more of a personalized asset, you can train it with your datasets, including files, by pointing them to the respective directory. Another interesting addition in NVIDIA's revamped ChatRTX is the ability to deal with images, as the chatbot has seen the integration of OpenAI's CLIP (Contrastive Language-Image Pre-Training). Through it, ChatRTX can natively navigate across images, which is a massive bonus for a personalized environment. You can even sort out images depending on a particular prompt, factor out specific ones, and do all kinds of stuff with a simple prompt.
System Requirements
| Platform | Windows |
| GPU | NVIDIA GeForce RTX 30 or 40 Series GPU or NVIDIA RTX Ampere or Ada Generation GPU with at least 8GB of VRAM |
| RAM | 16GB or greater |
| OS | Windows 11 |
| Driver | 535.11 or later |
| File Size | 35GB |
Speaking of prompts, ChatRTX allows you to input through your voice and recognizes it through the power of AI, which is another bonus. Overall, it's certainly interesting to see chatbots surface to cater to a more private environment, and with NVIDIA's RTX support, you will undoubtedly witness fast performance with ChatRTX. You can download the application from NVIDIA's page here, and navigate your way around.
About the author: Muhammad Zuhair is a hardware and technology reporter for Wccftech, specializing in the semiconductor industry and the complex interplay between technology, manufacturing, and geopolitics. His coverage focuses on the corporate strategies and technological roadmaps of industry giants like TSMC, NVIDIA, Samsung, and Intel. Zuhair's expertise lies in deconstructing complex topics such as fabrication nodes (e.g., 2nm process), the economic impact of policies like the CHIPS Act, and the strategic development of AI infrastructure from NVIDIA, AMD and Intel.
Follow Wccftech on Google to get more of our news coverage in your feeds.
