Sematic Kernel Workshop

Learn how to build LLM Apps with Semantic Kernel through self-contained and independent lessons, in a flexible way so that you can choose the sequence that is most convenient for you.

Typically, each lesson is structured to last approximately one hour, and it is assumed that you already have some Python or coding skills for the hands-on labs.

Objectives

After completing this workshop, you will be able to:

• Author your own copilot using Semantic Kernel.

• Create AI plugins using semantic and native functions.

• Automate complex tasks execution with planners.

• Create prompt templates to define AI functions.

• Embed Generative AI in your applications.

Contents

1 Background - Introduction to LLMs

no-code. 1.5h duration

• Introduction to LLMs GPTs and other models.
• Azure AI Services Overview.
• Azure OpenAI Service Overview.

2 CoPilot Stack and Semantic Kernel

full-code. 1.5h duration

• Introduction to Copilots.
• Microsoft Copilots.
• Build your own Copilots.
• Copilot ecosystem (Copilots + Plugins).
• What is Semantic Kernel?
• Why Semantic Kernel?
• The role of the kernel.

3 Semantic Kernel Basic Concepts

full-code. 1.5h duration

• Native and Semantic Functions.
• Create AI Plugins from functions.
• Chain plugins together.

4 Semantic Kernel Advanced Topics

full-code. 3h duration

• Add Memory to your AI Apps.
• Use Planners to automate Plugins orchestration.
• Calling external connectors.

5 Best Practices and Lessons Learned

no-code. 0.5h duration

• Learn some best practices on service limits.
• Final discussions and wrap-up.

Requirements

• Workstation

  • Azure CLI
  • Anaconda
  • VS Code

• Cloud

  • Azure Subscription

Contributing

This project welcomes contributions and suggestions. Most contributions require you to agree to a Contributor License Agreement (CLA) declaring that you have the right to, and actually do, grant us the rights to use your contribution. For details, visit https://cla.opensource.microsoft.com.

When you submit a pull request, a CLA bot will automatically determine whether you need to provide a CLA and decorate the PR appropriately (e.g., status check, comment). Simply follow the instructions provided by the bot. You will only need to do this once across all repos using our CLA.

This project has adopted the Microsoft Open Source Code of Conduct. For more information see the Code of Conduct FAQ or contact opencode@microsoft.com with any additional questions or comments.

Trademarks

This project may contain trademarks or logos for projects, products, or services. Authorized use of Microsoft trademarks or logos is subject to and must follow Microsoft's Trademark & Brand Guidelines. Use of Microsoft trademarks or logos in modified versions of this project must not cause confusion or imply Microsoft sponsorship. Any use of third-party trademarks or logos are subject to those third-party's policies.

Code of Conduct

This project has adopted the Microsoft Open Source Code of Conduct. For more information see the Code of Conduct FAQ or contact opencode@microsoft.com with any additional questions or comments.

License

Copyright (c) Microsoft Corporation. All rights reserved.

Licensed under the MIT license.

Reporting Security Issues

Reporting Security Issues