NVIDIA Developer
NVIDIA Developer
  • 862
  • 20 823 878
Setting Up a RAG Demo on NVIDIA AI Workbench
Walk through a complete start-to-finish installation of a generative AI retrieval-augmented generation (RAG) system with Lee Bushen, solutions architect at NVIDIA.
You can use this system to create a RAG project on your own computer (no local GPU required) in about 1 hour.
This approach uses NVIDIA AI Workbench to install the system. NVIDIA AI Workbench is an easy-to-use developer toolkit for data science, machine learning, and AI project development. AI Workbench is free, and you can install it in minutes.
For more details, see the resources listed below.
######################
CHAPTERS IN THIS VIDEO
######################
0:00 - Intro and Prerequisites
02:01 - Create GitHub and NGC Accounts
05:39 - AI Workbench Install
09:46 - Clone/Launch the RAG Project
16:49 - How to Re-Enter the API Key
18:35 - Example Prompts
23:11 - Stopping/Restarting the Demo
Project storage and sharing: github.com
Used for API calls to optimized LLM: ngc.nvidia.com
Download NVIDIA AI Workbench: www.nvidia.com/en-us/deep-learning-ai/solutions/data-science/workbench/
Hybrid RAG example project: github.com/NVIDIA/workbench-example-hybrid-rag
Sample user data files:
NVIDIA H100 data sheet: resources.nvidia.com/en-us-tensor-core/nvidia-tensor-core-gpu-datasheet
NVIDIA AI Enterprise Solution Overview:
resources.nvidia.com/en-us-data-center-overview-mc/en-us-data-center-overview/nvaie-solution-overview-4-0-update
zhlédnutí: 568

Video

JETSON AI LAB | Research Group Meeting (6/11/2024)
zhlédnutí 502Před 8 hodinami
www.jetson-ai-lab.com/research.html Topics Covered: * Agent Studio * Home Assistant 2024.6 * AWS IoT Greengrass (Romil Shah) * Open Q&A
Getting Started: NVIDIA cuOpt on Microsoft Azure Marketplace
zhlédnutí 807Před 18 hodinami
Learn how to launch NVIDIA cuOpt from Microsoft Azure Marketplace in three easy steps. The NVIDIA cuOpt offer on Microsoft Azure includes a VMI, which provides a standard, optimized runtime for easy cuOpt access. This ensures development compatibility between clouds and on-premises infrastructure. Optimize and solve complex problems with routing, supply chain, and more. 00:00 - Part 1: Introduc...
NVIDIA RTX Video SDK
zhlédnutí 1,9KPřed 18 hodinami
Add AI-enhanced super resolution and HDR tone mapping to watch or create sharper, more vibrant 4K HDR video. Enhance edges, restore details, remove artifacts, and much more with NVIDIA RTX Video SDK. To learn more, visit our RTX Video SDK page: nvda.ws/3RbPkib, and read the Technical Blog: developer.nvidia.com/blog/enhancing-low-resolution-sdr-video-with-the-nvidia-rtx-video-sdk/ Join the NVIDI...
Overview of NVIDIA RTX AI Toolkit
zhlédnutí 2,7KPřed dnem
Watch here for an end-to-end developer walkthrough of the NVIDIA RTX AI Toolkit, from model development to application deployment. This workflow showcases the model development workflow with AI Workbench and LlamaFactory-from customizing a Llama 3-7B model with the QLoRA technique to quantizing the model checkpoint with TensorRT Model Optimizer. The application deployment phase utilizes the NVI...
Generate Images Faster with Stable Diffusion and RTX
zhlédnutí 3,3KPřed dnem
ComfyUI offers a streamlined interface for Stable Diffusion, accelerated on NVIDIA RTX GPUs with NVIDIA TensorRT. Fast image generation combined with one-step RTX-enhanced ControlNets unlocks unprecedented workflow control. ✨ #TensorRT and GeForce #RTX unlock ComfyUI SD superhero powers 🦸⚡ 📗 DIY notebook: nvda.ws/3Kv1G1d ✨ RTX GPUs not only speed up image generation but offer access to the newe...
JETSON AI LAB | Research Group Meeting (5/29/2024)
zhlédnutí 3,6KPřed 14 dny
Topics Covered: * OpenAI-style Tools with NousResearch/Hermes-2-Pro-Llama-3-8B * Jetson Copilot with jetrag (Chitoku Yato) * whisper_trt for Orin Nano * Open Q&A
Understanding AI Workflows: From Concept to Production
zhlédnutí 1,8KPřed 14 dny
In this segment from the NVIDIA AI Infrastructure and Operations Fundamentals course you will learn the phases of a typical AI workflow, used by AI practitioners to develop, train, and deploy an AI model, with the key tasks and typical tools used in each phase. Artifical Intelligence(AI), is a broad area of knowledge with important foundational concepts such as Machine Learning(ML), Deep Learni...
Getting Started with ChatRTX in Three Steps
zhlédnutí 493Před 21 dnem
Get started with Chat RTX today. This step-by-step tutorial walks you through downloading, installing, launching, and using ChatRTX. Create a personalized chatbot with the Chat with RTX tech demo. Accelerated by TensorRT-LLM and Tensor Cores, you can quickly get tailored info from your files and content. Try it now. Appendix A - Short Story: drive.google.com/file/d/1NZQ3D37nM1FN794Die6xjaKeJp5h...
Deploying Generative AI in Production with NVIDIA NIM
zhlédnutí 9KPřed 21 dnem
Unlock the potential of generative AI with NVIDIA NIM. This video dives into how NVIDIA NIM microservices can transform your AI deployment into a production-ready powerhouse. Learn how NIM delivers flexible, scalable, and secure AI applications across any platform-cloud, data centers, or on-prem. Discover how its cloud-native architecture, backed by powerful tools like NVIDIA Triton Inference S...
JETSON AI LAB | Research Group Meeting (5/15/2024)
zhlédnutí 666Před 28 dny
www.jetson-ai-lab.com/research.html Topics Covered: * JetPack 6.0 GA / L4T R36.3 * VILA-1.5 on Video Sequences * Voicecraft (Martin Cerven) * JetBot / Nanosaur Updates (Chitoku Yato / Raffaello Bonghi) * Controller LLM & Advanced Function Calling * RAG Samples with LlamaIndex (Chitoku Yato)
Python Profiling: NVIDIA Nsight Tools Feature Spotlight
zhlédnutí 1,8KPřed 28 dny
Profile Python for AI and deep learning applications with NVIDIA's suite of Nsight Developer Tools. This video explores Python profiling features that will help you optimize GPU-accelerated Python code and ensure your applications are fully saturating available resources. 00:00 - Introduction 0:31 - Nsight Tools JupyterLab Extension 1:22 - Nsight Systems Python Profiling 2:03 - Nsight Compute P...
JETSON AI LAB | Realtime Video Vision/Language Model with VILA1.5-3b and Jetson Orin
zhlédnutí 3,1KPřed 28 dny
Samples from running multimodal Efficient-Large-Model/VILA1.5-3b on video sequences using Jetson AGX Orin, captured at the live rate. Tutorial & Benchmarks: www.jetson-ai-lab.com/tutorial_nano-vlm.html JetPack Containers: github.com/dusty-nv/jetson-containers
Geometric Fabrics: Generalizing Classical Mechanics to Capture the Physics of Behavior
zhlédnutí 1,4KPřed měsícem
Classical mechanical systems are central to controller design in energy shaping methods of geometric control. However, their expressivity is limited by position-only metrics and the intimate link between metric and geometry. Recent work on Riemannian Motion Policies (RMPs) has shown that shedding these restrictions results in powerful design tools, but at the expense of theoretical stability gu...
JETSON AI LAB | Research Group Meeting (5/1/2024)
zhlédnutí 847Před měsícem
Topics covered: * Function Calling with Llama-3 * Home Assistant / Wyoming (Mieszko Syty) * Smart Sorting / Recycling (Alvaro Costa)
JETSON AI LAB | Research Group Meeting (4/17/2024)
zhlédnutí 466Před měsícem
JETSON AI LAB | Research Group Meeting (4/17/2024)
JETSON AI LAB | Research Group Meeting (4/3/24)
zhlédnutí 1,1KPřed měsícem
JETSON AI LAB | Research Group Meeting (4/3/24)
ChatRTX Update: New Models & Features (Voice & Image Data Support)
zhlédnutí 2,8KPřed měsícem
ChatRTX Update: New Models & Features (Voice & Image Data Support)
JETSON AI LAB | Self-Learning Llama-3 Voice Agent with Function Calling and Automatic RAG
zhlédnutí 4,1KPřed měsícem
JETSON AI LAB | Self-Learning Llama-3 Voice Agent with Function Calling and Automatic RAG
Advancing HPC and AI Energy Efficiency with AWS and NVIDIA
zhlédnutí 1KPřed měsícem
Advancing HPC and AI Energy Efficiency with AWS and NVIDIA
Design and Test 5G and 6G Networks Using NVIDIA Aerial Omniverse Digital Twin
zhlédnutí 2,6KPřed měsícem
Design and Test 5G and 6G Networks Using NVIDIA Aerial Omniverse Digital Twin
Deploying AI in Real-World Robots | Aaron Saunders, Boston Dynamics CTO | NVIDIA GTC 2024
zhlédnutí 14KPřed měsícem
Deploying AI in Real-World Robots | Aaron Saunders, Boston Dynamics CTO | NVIDIA GTC 2024
The Future of AI and the Path to AGI - David Luan & Bryan Catanzaro | NVIDIA GTC 2024
zhlédnutí 10KPřed měsícem
The Future of AI and the Path to AGI - David Luan & Bryan Catanzaro | NVIDIA GTC 2024
Accelerating Simulations of Multiscale Chemical Reactors Using NVIDIA Modulus | NVIDIA GTC 2024
zhlédnutí 1,1KPřed měsícem
Accelerating Simulations of Multiscale Chemical Reactors Using NVIDIA Modulus | NVIDIA GTC 2024
Enabling Digital Twins for Science: A Perspective from CERN openlab | NVIDIA GTC 2024
zhlédnutí 1,9KPřed měsícem
Enabling Digital Twins for Science: A Perspective from CERN openlab | NVIDIA GTC 2024
Beyond the Output: Navigating the Ethical Challenges of Generative AI | NVIDIA GTC 2024
zhlédnutí 896Před 2 měsíci
Beyond the Output: Navigating the Ethical Challenges of Generative AI | NVIDIA GTC 2024
Generally Capable Agents in Open-Ended Worlds, Jim Fan, NVIDIA Lead of Embodied AI | NVIDIA GTC 2024
zhlédnutí 9KPřed 2 měsíci
Generally Capable Agents in Open-Ended Worlds, Jim Fan, NVIDIA Lead of Embodied AI | NVIDIA GTC 2024
Mesh Optimization Using FlexiCubes with NVIDIA Kaolin Library v0.15.0
zhlédnutí 1,3KPřed 2 měsíci
Mesh Optimization Using FlexiCubes with NVIDIA Kaolin Library v0.15.0
Accelerating Drug Discovery by Combining Quantum-Based Models w/ Machine Learning | NVIDIA GTC 2024
zhlédnutí 1,8KPřed 2 měsíci
Accelerating Drug Discovery by Combining Quantum-Based Models w/ Machine Learning | NVIDIA GTC 2024
Robotics in the Age of Generative AI with Vincent Vanhoucke, Google DeepMind | NVIDIA GTC 2024
zhlédnutí 10KPřed 2 měsíci
Robotics in the Age of Generative AI with Vincent Vanhoucke, Google DeepMind | NVIDIA GTC 2024

Komentáře

  • @sekinVR
    @sekinVR Před 11 hodinami

    ❤❤❤

  • @carlosrm8091
    @carlosrm8091 Před 14 hodinami

    Excuse me Sir. I have get the Application Error you describe. Im unsure If I have correct listened... You said I shall update BIOS? Isnt it? I dont see any relationship between BIOS and WSL2, as I have run Ubuntu over W11 in this PC before... Is it needed to install WSL nvidia graphic drivers to been able to use CUDA in workbench?

  • @montrio3d829
    @montrio3d829 Před 16 hodinami

    Metahuman?

  • @fotuoliu7940
    @fotuoliu7940 Před 19 hodinami

    辅导费

  • @sergeistadnik8305
    @sergeistadnik8305 Před dnem

    I wonder if there is a good guide for nim deployment in production?

  • @MrNewAmerican
    @MrNewAmerican Před dnem

    Enunciate . Clearly. Dont mumble. You are presenting to an audience. This is a "formal" interaction. You are not snubbing your mother's attempts to feed you vegetables at a high chair as a toddler. Speak slowly, clearly.

  • @vladimirgetselevich4704

    Very cool Agent studio framework!

  • @wasasquatch4027
    @wasasquatch4027 Před 2 dny

    Is this a pre-compile solution?

  • @chiranjib-konwar
    @chiranjib-konwar Před 2 dny

    awesome :) can we connect ?

  • @timreha
    @timreha Před 3 dny

    Very cool!

  • @lgscteam
    @lgscteam Před 4 dny

    I have 27tb total

  • @NVIDIADeveloper
    @NVIDIADeveloper Před 4 dny

    Lots of great questions in comments. Here are responses from our NIM team: Q: Does NVIDIA NIM deployment language model have training and fine-tuning capabilities? Does it have knowledge base functionality? A: NVIDIA NIM supports LoRA PEFT adapters trained by the Nemo Framework and Hugging Face Transformers libraries for use with NIM supported models. Stay tuned for blogs we'll be publishing, and see the documentation: docs.nvidia.com/nim/large-language-models/latest/peft.html Q: How to get access to NIM microservice? I've already raised a ticket. A: Get started at ai.nvidia.com and check out A Simple Guide to Deploying Generative AI with NVIDIA NIM: developer.nvidia.com/blog/a-simple-guide-to-deploying-generative-ai-with-nvidia-nim/. Q: What models is this good for? A: NVIDIA NIM supports a broad spectrum of AI models-from open-source community models to NVIDIA AI Foundation models and NVIDIA's partner ecosystem. Explore NVIDIA-managed serverless APIs and prototype applications with free credits in the NVIDIA API catalog (build.nvidia.com/explore/discover), and when ready to deploy to production, you can self-host models on NVIDIA accelerated infrastructure anywhere. Check out A Simple Guide to Deploying Generative AI with NVIDIA NIM (developer.nvidia.com/blog/a-simple-guide-to-deploying-generative-ai-with-nvidia-nim/)

    • @avataros111
      @avataros111 Před 4 dny

      Last 3 links are broken - page not found. You have to delete the last ) and other junk characters.

  • @zhaonanmeng7625
    @zhaonanmeng7625 Před 5 dny

    Nice guide!

  • @mistycloud4455
    @mistycloud4455 Před 6 dny

    That's so scary

  • @JoshuaMouch
    @JoshuaMouch Před 6 dny

    Take a look at Microsofts Semantic Kernel, please! It looks like it already does everything you're trying to do here... it would just need a plugin.

  • @arc8dia
    @arc8dia Před 7 dny

    Nvidia profiling tools. Good to know.

  • @TomanswerAi
    @TomanswerAi Před 7 dny

    Very cool! Does the notebook only contain workflow for basic generation? Anywhere to locate the other workflows used in this example?

  • @lareskorea_ziny
    @lareskorea_ziny Před 7 dny

    한국어로 자막을 번역해서 볼 수 있게 해주시면 더욱더 감사하겠습니다!!

  • @user-lm4nk1zk9y
    @user-lm4nk1zk9y Před 7 dny

    Not sure if you can see HDR without HDR monitor

  • @user-lb6fu3qk6r
    @user-lb6fu3qk6r Před 7 dny

    고맙습니다

  • @SantK1208
    @SantK1208 Před 8 dny

    How it’s different from low cost - Groq Cloud LPU inference

  • @carriewall5431
    @carriewall5431 Před 9 dny

    Loved your video! Could you please let us know where you got the button fly white jeans?

  • @AlgoNudger
    @AlgoNudger Před 9 dny

    it will be replaced by V-JEPA. 😂

  • @megaigrovoy
    @megaigrovoy Před 9 dny

    Where is tensor rt loader???

    • @NVIDIADeveloper
      @NVIDIADeveloper Před 9 dny

      Here's the related notebook console.brev.dev/launchable/deploy?userID=2x2sil999&orgID=ktj33l4xj&name=ComfyUI_TensorRT&instance=L4@g2-standard-4:nvidia-l4:1&diskStorage=500&cloudID=GCP&baseImage=docker.io/pytorch/pytorch:2.2.0-cuda12.1-cudnn8-runtime&ports=ComfUI:8188&file=github.com/brevdev/notebooks/blob/main/tensorrt-comfyui.ipynb&launchableID=env-2hQX3n7ae5mq3NjNZ32DfAG0tJf&=&linkId=100000264904516

    • @amoujhang1384
      @amoujhang1384 Před 8 dny

      I think this video is not using the TensorRT node. The link provided from notebook shows a different workflow.

    • @megaigrovoy
      @megaigrovoy Před 3 dny

      @@NVIDIADeveloper Ok, but where is instantid in your notebook?

  • @WallyMahar
    @WallyMahar Před 9 dny

    there is no try. BUY. correct?

  • @MohammadRauf1
    @MohammadRauf1 Před 10 dny

    that's a proper nerd fest

  • @mandingo9999998
    @mandingo9999998 Před 10 dny

    Great videos, extremely helpful. One question, I'm trying to install an updated license file on my DLS that has more license allocations. On my new DLS server, under Dashboard, License Server Details, at the bottom I do not have 'License Pools' listed. Even after disabling the server. Only have Overview, Server Features, and Leases.(?) Thank you-

  • @willian_z
    @willian_z Před 10 dny

    Hi, Is there a way to set default mode to WDDM mode for Data Center GPU? Every time I change slots for the GPU it resets itself to TTC. With combination of a CPU doesn't have an integrated Graphics, it is troublesome to get to the cli to change that. BIOS setup: SRIOV off, reBar on/off,

    • @willian_z
      @willian_z Před 10 dny

      btw the DataCenter GPU isn't displaying anything during boot time, e.g. BIOS, GRUB etc, only after it, is that relate to what the driver mode its on?

    • @willian_z
      @willian_z Před 10 dny

      sorry for spamming this thread but is it normal that after switching to WDDM, the HD Audio device isn't showing up for any DP devices physically plugged in?

  • @realthing2158
    @realthing2158 Před 11 dny

    Would this also benefit RTX 2080 Super and what do I need to do to enable it? Is downloading the latest drivers enough?

  • @bigwalrosswalross3356

    Cant wait to try it out :)

  • @MilesBellas
    @MilesBellas Před 11 dny

    Nvidia could buy Stable Diffusion, The Foundry and Autodesk to create a next generation development platform.....

    • @a.tevetoglu3366
      @a.tevetoglu3366 Před 9 dny

      No need to buy if omniverse connects all within one frame.

    • @asafun
      @asafun Před 9 dny

      We want to keep Stable Diffusion free.

    • @a.tevetoglu3366
      @a.tevetoglu3366 Před 7 dny

      @@asafun even blender, which also is free, is an option within NVIDIA's onmiverse.

  • @DawidRysStudio
    @DawidRysStudio Před 11 dny

    I discourage everyone the use of instatID and anything to do with insightface because you can start getting prosecuted for using it without a license 😂

  • @mihirchitnis905
    @mihirchitnis905 Před 11 dny

    Be honest who all thinks that the AI has ripped off green lantern for this super hero design.

  • @DonaldTrum2806
    @DonaldTrum2806 Před 11 dny

    Does NVIDIA nim deployment language model have training and fine-tuning capabilities, and does it have knowledge base functionality?

  • @Ms.Robot.
    @Ms.Robot. Před 12 dny

    Sweet. ❗❤🎉 I can't wait to see community contributions into this.

  • @lilacsky824
    @lilacsky824 Před 12 dny

    6:25 There seems to be an issue with the voice here.

  • @Le-fn5tl
    @Le-fn5tl Před 13 dny

    Very cool, thank you!

  • @phiai1618
    @phiai1618 Před 14 dny

    Here are ste-by-step walkthouroughs how to: 1. Generate deployable models for PyTorch ResNet50 using Nvidia PyTorch Container czcams.com/video/Js3QQv0fbcI/video.html 2. Deploy PyTorch ResNet50 model on AWS SageMaker using Nvidia Triton Inference Server czcams.com/video/N8i9SUrCrdM/video.html

  • @phiai1618
    @phiai1618 Před 14 dny

    Here are ste-by-step walkthouroughs how to: 1. Generate deployable models for PyTorch ResNet50 using Nvidia PyTorch Container czcams.com/video/Js3QQv0fbcI/video.html 2. Deploy PyTorch ResNet50 model on AWS SageMaker using Nvidia Triton Inference Server czcams.com/video/N8i9SUrCrdM/video.html

  • @phiai1618
    @phiai1618 Před 14 dny

    Here are ste-by-step walkthouroughs how to: 1. Generate deployable models for PyTorch ResNet50 using Nvidia PyTorch Container czcams.com/video/Js3QQv0fbcI/video.html 2. Deploy PyTorch ResNet50 model on AWS SageMaker using Nvidia Triton Inference Server czcams.com/video/N8i9SUrCrdM/video.html

  • @Poul7777777
    @Poul7777777 Před 14 dny

    Хуйня -не КАНё

  • @stevephillips5392
    @stevephillips5392 Před 15 dny

    Fascinating project. I am going to be trying and testing everything that comes out of this effort. (Can't wait to build an AI assistant that learns things about my family and my home and is able to offer a helpful suggestion every now and then. :) The Orin NX 16GB seems like an appropriate platform for prototyping. Thanks for your guiding hand to get this off the ground... seems like it is really happening.

  • @FennaVa
    @FennaVa Před 16 dny

    Been beating myself up a bit that I sold my 53 shares of NVDA at $374 each back in May 2023 and now it is at over $1,100. Now thinking of liquidating a few other investments to rebuy but afraid to do so. I also currently have 500k in savings making me next to nothing.

    • @NowakJosef
      @NowakJosef Před 16 dny

      Everyone needs a Margin of Safety in their portfolios and just remember, It's time in the market versus timing the market.

    • @ralfbrown-kl1gp
      @ralfbrown-kl1gp Před 16 dny

      Try slowly diversifying your investments over time tends to yield better returns than doing it in a single instance, buy and hold. buy 10% then when in profit add more, or just buy on a dip and hold. NVDA is not going down soon

    • @marcellasilva4015
      @marcellasilva4015 Před 16 dny

      De-risk your portfolios, shore up your core holdings, and take some profits while balancing your portfolio allocations. I’d also suggest you go with a managed portfolio, so it’s best you reach out to a proper fiduciary to guide you, that’s what works for me. We've made over 50% capital growth minus dividends.

    • @michaelanthonygutierrez
      @michaelanthonygutierrez Před 14 dny

      Stock market is rigged sorry. They have computers that buy and sell faster than people. But good luck.

    • @oliverdavis-tw2xl
      @oliverdavis-tw2xl Před 3 dny

      Market behavior can be complex and unpredictable. Mind if I ask you to recommend this particular coach to whom you have used their services?

  • @Heisenberg2097
    @Heisenberg2097 Před 16 dny

    Hehe. Though certain advances of AI are indeed striking. The crucial flaw of AI is still the same as all years before. Even the experts themselve cannot explain why their systems do what they do. AI winter #3 is already waiting.

  • @KatyYoder-cq1kc
    @KatyYoder-cq1kc Před 16 dny

    Let's talk about Globally Intellectual Property Theft: NOW ON LIFE SUPPORT: There is intensive mind control taking place using AI maliciously through satellite and biochemical warfare by supremacists, terrorists and communists. Please report to the highest level of governing bodies and intelligence agencies. I have been poisoned, harassed physically and mentally, raped by lesbians and ignored by the police, agencies and churches nationally as have my children. I and am under constant attack from my government and international WOKE military

  • @Era-rp9od
    @Era-rp9od Před 17 dny

    Thank you. We've been searching for graphical acceleration in a bare metal environment with Datacenter Cards like A40 and A10 for quite some time now. Does updating the driver of the card switch the A40 back to TCC?

  • @loedward1308
    @loedward1308 Před 17 dny

    AI aside. Trump needs to see this and humble himself. None of these genius AI tycoons on the stage were born and raised in this country, and most of them are leading this country to lead the world for AI development. This is something that he and his supporters who are against immigrants need to reflect.

  • @yunpengliu2929
    @yunpengliu2929 Před 18 dny

    nvolveqa_40k not found