February 15, 2024: Nvidia has a brand new AI chatbot called “Chat with RTX”, designed to run directly on Windows PCs Nvidia GeForce RTX Graphics cards.
The special thing about this chatbot is that it really works locally and subsequently doesn’t require a web connection to operate.
Nvidia goals to offer a personalised AI experience by allowing users to feed their very own documents, text files, PDFs and even YouTube videos into the chatbot.
This information is then incorporated into the chatbot's responses, making it a useful gizmo for quickly finding information or getting summaries of videos and documents.
Chat with RTX is powered by Nvidia's advanced technologies, including GPU acceleration and Retrieval-Augmented Generation (RAG) technology.
This setup allows the chatbot to quickly scan and index the provided files, providing quick and contextually relevant answers to users' questions.
Although it’s a robust tool, the chatbot has some limitations similar to: B. He is unable to transfer context between different questions and sometimes has problems with follow-up questions.
However, Nvidia is committed to improving Chat with RTX over time.
The chatbot is offered as a demo and may be downloaded without cost by anyone who has a GeForce RTX PC that meets the needed hardware requirements, including Windows 10/11, an RTX 30/40 GPU with no less than 8GB VRAM and the most recent Nvidia driver version.
Additionally, Nvidia is encouraging developers to explore the potential of RTX-accelerated AI applications by sponsoring a contest to create generative AI apps and plugins with RTX TensorRT-LLM Framework presented by Chat with RTX.
With Chat with RTX, Nvidia not only provides a tool for private use, but additionally demonstrates the capabilities of local AI processing that may provide quick responses and protect sensitive data on users' devices.
This initiative represents a step forward in making AI more accessible and customizable to individual needs while ensuring privacy and data security.
