Quickstarts and Walkthroughs
Use this section to get started with NVIDIA AI Workbench. These quickstarts and walkthroughs cover both basic and advanced tasks, including creating projects, writing code in JupyterLab, managing environments, and publishing to a Git server.
Quickstarts are designed to help you quickly become familiar with the AI Workbench desktop application, command line interface (CLI), and NVIDIA-created example projects. You can complete them in any order.
Quickstart Guides
- Basic Quickstart - Learn the core workflow: create a project, write code in JupyterLab, and push changes to Git.
- Basic Quickstart (CLI) - Use the AI Workbench command line interface (CLI) to manage projects, environments, and containers.
- Walkthrough: Project Dashboard for Onboarding, Monitoring and Managing Your Project - Use the Project Dashboard to monitor GPU usage, track project changes, and manage running applications.
- Walkthrough: Customize Your Environment - Modify project environments, install dependencies, and configure resource settings.
- Walkthrough: Customize Your Environment (CLI) - Manage project environments using the CLI, including package installation and container customization.
- Walkthrough: Add a Custom Application - Add and configure custom applications inside your AI Workbench project.
- Advanced Walkthrough: Hybrid RAG - Set up and run the Hybrid RAG example project, showcasing retrieval-augmented generation workflows.
- Advanced Walkthrough: Use Your Own Container - Bring your own container (BYOC) and integrate it into an AI Workbench project.
- Install Claude Code in a Project Container - Install Claude Code in a project container.
- Configure Claude Code Sandboxing in a Project Container - Create a sandbox configuration repository for Claude Code.
Next Steps
- Start with Basic Quickstart to familiarize yourself with the workflow.
- If you prefer the command line, go to Basic Quickstart (CLI).
- Learn how to customize environments in Walkthrough: Customize Your Environment or Walkthrough: Customize Your Environment (CLI).
- Explore NVIDIA-created example projects like Advanced Walkthrough: Hybrid RAG.
- For additional support, visit the NVIDIA Developer Forum.