ChatRTX can integrate knowledge from YouTube videos into queries.

What’s New

ChatRTX uses retrieval-augmented generation, NVIDIA TensorRT-LLM software and NVIDIA RTX acceleration to bring chatbot capabilities to RTX-powered Windows PCs and workstations. Backed by its powerful large language models (LLMs), users can query their notes and documents with ChatRTX, which can quickly generate relevant responses, while running locally on the user’s device.

The latest version adds support for additional LLMs, including Gemma, the latest open, local LLM trained by Google. Gemma was developed from the same research and technology used to create the company’s Gemini models and is built for responsible AI development. ChatRTX also now supports ChatGLM3, an open, bilingual (English and Chinese) LLM based on the general language model framework.

Users can also interact with image data thanks to support for Contrastive Language-Image Pre-training from OpenAI. CLIP is a neural network that, through training and refinement, learns visual concepts from natural language supervision – that is, the model recognizes what it’s “seeing” in image collections. With CLIP support in ChatRTX, users can interact with photos and images on their local devices through words, terms and phrases, without the need for complex metadata labeling.

The new ChatRTX release also lets people chat with their data using their voice. Thanks to support for Whisper, an automatic speech recognition system that uses AI to process spoken language, users can send voice queries to the application and ChatRTX will provide text responses.

System Requirements

• Windows 11
• 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
• Driver: 535.11 or later