Nvidia, the technology company known for its graphics processing units (GPUs), has unveiled a new feature called Chat with RTX. This feature allows users to create and customize their own AI chatbot using their own content and run it on their computers for free. However, users will need to have a GeForce RTX 30 Series GPU installed.
The Chat with RTX technology incorporates retrieval-augmented generation (RAG) and Nvidia TensorRT-LLM software, along with Nvidia RTX acceleration, to bring generative AI capabilities to local Windows PCs powered by GeForce GPUs. By linking local PC files to open-source language models like Mistral or Llama 2, users can receive quick and contextually appropriate responses.
The chatbot supports various file formats, including .txt, .pdf, .doc/.docx, and .xml, and can also utilize information from YouTube videos and playlists. It operates locally on Windows RTX PCs and workstations, ensuring fast results and data privacy. To utilize Chat with RTX, users must have a GeForce RTX 30 Series GPU or higher with a minimum 8GB of VRAM, Windows 10 or 11, and the latest Nvidia GPU drivers.
Nvidia’s release of Chat with RTX aligns with its CEO Jensen Huang’s call for countries to develop their own Sovereign AI to maintain control over their data. Huang has emphasized the importance of nations owning the intelligence generated from their data and human efforts.
OpenAI, another prominent AI company, is also aiming to personalize its chatbot known as ChatGPT by implementing a new memory feature. This update will enable the bot to retain user-specific details and conversation history for more personalized interactions.
Nvidia’s Chat with RTX provides users with the ability to customize their own AI chatbot and maintain control over their data. This release aligns with the global trend towards developing sovereign AI. OpenAI is also working on enhancing its chatbot’s personalization capabilities.