2 Building Your First Project with Semantic Kernel

In this chapter, we dive into the practical application of Semantic Kernel, demonstrating how to build AI-powered applications that leverage the capabilities of large language models. We'll start by creating a simple console application that interacts with OpenAI's GPT models, then progress to developing a chatbot capable of controlling a robot car. Along the way, we'll cover essential topics such as obtaining and securing API keys, setting up your development environment, and integrating Semantic Kernel with GPT models, and integrating native and semantic plugins. By the end of this chapter, you'll have a solid foundation for building more complex AI-driven applications using Semantic Kernel.

2.1 A Robot Car Story

2.1.1 A Fire-Detecting Robot Car

2.1.2 Challenges in Programming Complex Movements

2.1.3 Revisiting the Problem with Generative AI

2.1.4 Semantic Kernel: The Spark That Ignites My Robot Car

2.2 Building a Simple Console Application

2.2.1 How to Get an OpenAI API Key

2.2.2 How to Get an Azure OpenAI API key

2.2.3 Securing API Keys

2.2.4 Diving into Semantic Kernel: Your First AI-Powered Application

2.3 Transitioning to Your First Chatbot Application

2.3.1 Structuring AI Prompts for Reusability and Scalability

2.3.2 Leveling Up: Building a Chatbot with Memory

2.3.3 Decoupling Assistant-Specific Behavior from Assistant Persona

2.3.4 Enhancing Chatbot Autonomy

2.3.5 What Follows Next

2.4 Summary