The Azure OpenAI and Semantic Kernel Fundamentals What The Hack is an introduction to understanding the conceptual foundations of infusing your application with AI using the Semantic Kernel development kit. Materials from this hack can serve as a foundation for building your own AI infused solutions with Semantic Kernel.
This hack consists of eight challenges and is designed to encourage learning and research. If you want a deeper understanding of how to implement an AI solution but have little or no experience with OpenAI or Semantic Kernel then this hack is for you.
Hack-a-thons are hosted as a team based activity where students work in groups of 3-5 people to solve the challenges. Each challenge is designed to be completed in 30-90 minutes.
This hack is designed for individuals who want to gain practical experience in working with Azure OpenAI and Semantic Kernel. By applying this knowledge, you will be able to integrate AI into your own applications.
Participants will learn how to:
- Build a simple chat using Semantic Kernel and C#
- Add plugins and enable auto calling to create Planners
- Create a workflow plugin using Logic Apps
- Implement Retrieval Augmented Generation (RAG)
- Document Chunking
- Grounding AI
- Working with Image generation
- Multi-Agent workflows
- Challenge 00: Prerequisites
- Prepare your workstation to work with Azure.
- Challenge 01: Azure OpenAI Fundamentals
- Deploy an Azure OpenAI Model
- Prompt Engineering
- What's possible through prompt engineering
- Best practices when using OpenAI text and chat models
- Challenge 02: Semantic Kernel Fundamentals
- Semantic Kernel Fundamentals
- Connect your OpenAI model using Semantic Kernel
- Test Your Application
- Challenge 03: Plugins
- Functions and Plugins Fundamentals
- Creating Semantic Kernel Plugins
- Enable auto function calling
- What is a Planner
- Challenge 04: Create a workflow plugin using Logic Apps
- Setup Azure DevOps
- Create a Logic App
- Import Logic App into Semantic Kernel
- Challenge 05: Retrieval-Augmented Generation (RAG)
- Document Chunking & Embedding
- Enhance AI responses by searching external sources
- Challenge 06: Responsible AI: Exploring Content Filters in Azure OpenAI
- Configuring content filters in Azure OpenAI Studio.
- Testing content filters.
- Creating custom filters to block specific words or phrases.
- Challenge 07: Image Generation using DALL-E
- Working with Text to Image Models
- Creating an Image Generating Plugin
- Challenge 08: Multi-Agent Systems
- Create a multi-agent conversation using Semantic Kernel
- Implement a multi-agent conversation using Azure OpenAI