Nvidia recently released its new ‘Chat With RTX’ tech demo, which lets users download and run an AI chatbot locally on their Windows 11 PC.
The tech demo is free and available for download through Nvidia’s website. The demo requires a Nvidia GeForce RTX 30 Series GPU or higher, with 8GB of video random access memory (VRAM).
The demo lets you personalize your own GPT large language model (LLM) and connect it to your content. Using the software, you can query a custom chatbot to quickly get “contextually relevant answers” based on the video or document you’ve provided. Nvidia highlights that since Chat With RTX runs locally on your PC, “you’ll get fast and secure results.”
“Rather than relying on cloud-based LLM services, Chat with RTX lets users process sensitive data on a local PC without the need to share it with a third party or have an internet connection,” Nvidia said in its blog post.
The chatbot supports various file formats, including text, pdf, doc/docx and XML. All you have to do is browse your PC, select a document and then enter your query. In the video example, the program scans a user’s notes to find out what restaurant their friend recommended.
Another cool thing about Chat with RTX is you can provide it with a YouTube URL, and the program will load the transcription of the video and allow you to make queries based on the content the video covers. I can see this feature being extremely handy to get a quick answer about a specific point in a video or quick summaries of long videos.
Chat With RTX is just a tech demo, but what it offers is an interesting glimpse of how Nvidia plans to make its desktop RTX GPUs take full advantage of AI technology.
Image Credit: Nvidia
MobileSyrup may earn a commission from purchases made via our links, which helps fund the journalism we provide free on our website. These links do not influence our editorial content. Support us here.
