Understanding and leveraging Semantic Kernel - Introduction
Starting today, we’re launching a series that dives into a timely and important topic: empowering AI within our applications. While there are plenty of tutorials available online, this series will specifically focus on using Semantic Kernel, Microsoft’s tool for building enterprise-grade AI agents.
What are we aiming to achieve ?
Artificial intelligence has become such a buzzword today that it’s almost impossible for any company to ignore the topic—or to resist announcing that their products are "AI-powered". As a result, every developer is now expected to know how to build an AI agent or develop software that helps streamline business processes. And that’s precisely the focus of this series: exploring how to accomplish this.
There are countless options available for building AI agents, and every vendor eagerly promotes its own products, often claiming —sometimes emphatically— that theirs are the best on the market. Here, however, we’ll take a more modest approach by using a tool provided by Microsoft: Semantic Kernel, designed to build enterprise-grade AI agents.
We will therefore explore what Semantic Kernel is, why it might be the right tool for the job, and what specific problems it aims to solve. Along the way, we’ll delve into key concepts such as generative AI and large language models (LLMs). We’ll then see how to extend Semantic Kernel with plugins (including RAG—retrieval-augmented generation) and how to connect it to other tools using the new MCP protocol.
- Understanding and leveraging Semantic Kernel - Generative AI, LLMs and others
- Understanding and leveraging Semantic Kernel - Building a very simple agent in a few lines of C# code
- Understanding and leveraging Semantic Kernel - Using Semantic Kernel with Ollama
- Understanding and leveraging Semantic Kernel - Unleashing the power of plugins
- Understanding and leveraging Semantic Kernel - Integrating Semantic Kernel with the MCP protocol
- Understanding and leveraging Semantic Kernel - Logging and monitoring
We referred to the following book to clarify certain concepts. (Note however that, although the book was published in June 2024, some of its content is already outdated.)
Building AI Applications with Microsoft Semantic Kernel (Meyer)
Without further ado and as usual, let's begin with a few prerequisites to correctly understand the underlying concepts. Stay tyuned.
Understanding and leveraging Semantic Kernel - Generative AI, LLMs and others