Building AI Applications with Microsoft Semantic Kernel: Easily integrate generative AI capabilities and copilot experiences into your applications By: Lucas A Meyer

Author: Lucas A. Meyer

Unlock the power of Generative AI by effortlessly linking your C#, Java, and Python apps to cutting-edge models, orchestrating diverse AI services with finesse, and crafting bespoke applications through immersive, real-world examples

Key FeaturesSeamlessly link your C#, Java ,and Python applications to the latest AI models from OpenAI and HuggingFaceCombine and orchestrate several different AI services such as text and image generatorsCreate your own AI apps from real-world examplesBook DescriptionMicrosoft Semantic Kernel makes it easy to integrate the latest AI models from Microsoft and OpenAI into your applications by using connectors, prompt templates, plugins, and the powerful orchestration planner.

Written by Lucas A. Meyer, a Principal Research Scientist in the Microsoft’s AI for Good Lab, working with the Microsoft Semantic Kernel since the beginning. Lucas begins by introducing you to several different generative AI services such as GPT-3.5 and GPT-4 and shows you how you can use them with the Semantic Kernel. You will then learn to write prompt templates and reuse them with different AI services and variables. You will also learn to add functionality to the Semantic Kernel by creating your own plugins. The second part of the book shows you how to combine multiple plugins to execute complex actions, and how to let the Semantic Kernel itself use its own AI to solve complex problems by calling plugins, including the ones made by you. The book concludes by teaching you how to use vector databases to expand the memory of your AI services and help AI remember the context of earlier requests. Finally, the book walks you through several real-world examples of applications, such as RAG and custom GPT agents.

By the end of the book, you’ll be an expert in using Semantic Kernel to add AI capabilities to your applications.

What you will learnWrite reusable AI prompts and connect to different AI providersExplorer plugins that extend the capabilities of AI servicesOrchestrate multiple AI services to a taskUse vector databases as additional memory for your AI tasksLeverage the powerful planner to automatically call AI services for youWho this book is forThis book is for beginner to experienced .NET, Java, or Python software developers who want to quickly incorporate the latest AI technologies in their applications, without having to learn the details of every new AI service. Product managers with minor development experience will be able to create proof-of-concept applications. This book requires a working knowledge of the basics of programming.

Table of ContentsIntroducing the Microsoft Semantic KernelUnderstanding Prompt TemplatesChaining AI Prompts and PipelinesFrom Outputs to Outcomes with the PlannerExtending and Customizing the Semantic Kernel SDKAdvanced workflows with the Planner and Vector DatabasesCase Studies and Real World Examples