Download Nvidia Chat with RTX Download

Leveraging recovery augmented generation (RAG), TensorRT-LLM and RTX acceleration, you can query a custom chatbot to quickly get contextually relevant answers. And because everything runs locally on your Windows RTX PC or workstation, you get fast and secure results.

Characteristics

Chat with notes, documents and video

Chat with RTX supports various file formats, including text, pdf, doc/docx and xml. Just point the program at the folder containing your files and it will load them into the library in seconds. Additionally, you can enter the URL of a YouTube playlist and the app will load the transcripts of the videos in the playlist so you can query the content they cover.

Chat for developers

The Chat with RTX technology demo is built from the TensorRT-LLM RAG developer reference project available from GitHub. Developers can use this reference to develop and deploy their own RAG-based applications for RTX, accelerated by TensorRT-LLM.

Ask me anything

Chat with RTX uses recovery augmented generation (RAG), Nvidia TensorRT-LLM software, and Nvidia RTX acceleration to bring generative AI capabilities to local, GeForce-powered Windows PCs. Users can quickly and easily link local files on a PC as a dataset to an open source large language model such as Mistral or Llama 2, enabling queries for fast, contextually relevant answers.

Instead of searching through notes or saved content, users can simply type in their search. For example, one might ask, “What was the restaurant my partner recommended while in Las Vegas?” and Chat with RTX will scan local files the user points it to and provide the response with context.

The tool supports various file formats including .txt, .pdf, .doc/.docx and .xml. Point the program at the folder containing these files and the tool will load them into the library in seconds.

Users can also include information from YouTube videos and playlists. By adding a video URL to Chat with RTX, users can integrate this knowledge into the chatbot for contextual questions. For example, request travel recommendations based on content from your favorite influencer videos, or get quick guides and how-tos based on the best educational resources.

Since Chat with RTX runs locally on Windows RTX PCs and workstations, results are fast – and the user’s data stays on the device. Instead of relying on cloud-based LLM services, Chat with RTX allows users to process sensitive data on a local PC without having to share it with a third party or have an Internet connection.

In addition to a GeForce RTX 30 Series GPU or higher with a minimum of 8 GB of VRAM, Chat with RTX requires Windows 10 or 11, and the latest NVIDIA GPU drivers.

Chat with RTX can integrate knowledge from YouTube videos into queries.

System requirements

• Windows 11
• GPU: Nvidia GeForce RTX 30 or 40 Series GPU or Nvidia RTX Ampere or Ada Generation GPU with at least 8 GB VRAM
• RAM: 16 GB or more
• Driver: 535.11 or later