NVIDIA just released a chatbot This is pretty neat because it gives the chatbot access to your files and documents. You can choose to provide Chat with RTX with personal information and have it generate summaries based on that information. You can also ask it questions like any other chatbot and it will access your data for answers.
The company allows users to “quickly, easily connect local files on a computer as a database to a large open-source language model like Mistral or Llama 2.” NVIDIA gives the example of a user asking the chatbot about a restaurant recommended by a partner while in Las Vegas. The program scans local files for answers. It supports all file formats including .txt, .pdf, .doc/.docx and .xml. The company says it will upload the relevant files to its database “within seconds”.
Chat with RTX also integrates YouTube videos and playlists. You can add a video URL to the database and it will combine the knowledge contained in the clip for contextual queries. NVIDIA says this will be useful when asking for travel recommendations “based on content from favorite influencer videos” or when looking for tutorials and summaries from educational resources.
The Verge contacted the chatbot and were impressed, writing that they could see it as “a valuable part of data mining for journalists or anyone who needs to analyze a trove of documents.”
This sounds like a big step toward something resembling an actual digital assistant that works within the contextual framework of your personal data. With most chatbots, data is sent to the cloud, but with RTX, a conversation “allows users to share with a third party or process sensitive data on a local computer without the need for an internet connection.” So it’s safer and is more context-aware.
There are some limitations. This is a demo product, so you should expect a lot of bugs, although NVIDIA has encouraged users to submit bug reports, etc. as soon as it starts giving, it should start suppressing them. There are also some serious hardware limitations here. Chat with RTX only works on Windows computers with an NVIDIA GeForce RTX 30 Series GPU or higher and at least 8 GB of VRAM.
NVIDIA has really been showing off its AI prowess lately as the company has launched its next generation. . this primarily due to the company’s AI and data center segments.
This article contains affiliate links; we may earn a commission if you click on such a link and make a purchase.
