Search icon CANCEL
Arrow left icon
Explore Products
Best Sellers
New Releases
Books
Videos
Audiobooks
Learning Hub
Conferences
Free Learning
Arrow right icon
Arrow up icon
GO TO TOP
Building AI Applications with Microsoft Semantic Kernel

You're reading from   Building AI Applications with Microsoft Semantic Kernel Easily integrate generative AI capabilities and copilot experiences into your applications

Arrow left icon
Product type Paperback
Published in Jun 2024
Publisher Packt
ISBN-13 9781835463703
Length 252 pages
Edition 1st Edition
Languages
Tools
Concepts
Arrow right icon
Author (1):
Arrow left icon
Lucas A. Meyer Lucas A. Meyer
Author Profile Icon Lucas A. Meyer
Lucas A. Meyer
Arrow right icon
View More author details
Toc

Table of Contents (14) Chapters Close

Preface 1. Part 1:Introduction to Generative AI and Microsoft Semantic Kernel FREE CHAPTER
2. Chapter 1: Introducing Microsoft Semantic Kernel 3. Chapter 2: Creating Better Prompts 4. Part 2: Creating AI Applications with Semantic Kernel
5. Chapter 3: Extending Semantic Kernel 6. Chapter 4: Performing Complex Actions by Chaining Functions 7. Chapter 5: Programming with Planners 8. Chapter 6: Adding Memories to Your AI Application 9. Part 3: Real-World Use Cases
10. Chapter 7: Real-World Use Case – Retrieval-Augmented Generation 11. Chapter 8: Real-World Use Case – Making Your Application Available on ChatGPT 12. Index 13. Other Books You May Enjoy

What is a planner?

So far, we have been performing complex requests by performing the function calls ourselves. This, however, requires you to restrict the kind of requests that your users can make to what you can predict and write ahead of time. It also restricts your users to only generating one output at a time. Sometimes, you may want to give them the ability to do more.

For example, if you have a semantic function that allows users to request jokes (as we built in Chapter 1) and a user requests “tell me a knock-knock joke,” you can simply call the semantic function that tells knock-knock jokes. But if the user requests three knock-knock jokes, the function wouldn’t know how to handle it.

A planner is a built-in function from Semantic Kernel that receives a user request and then goes through the descriptions of all the functions, parameters, and outputs of the functions you loaded in your kernel and decides the best way to combine them, generating a plan...

lock icon The rest of the chapter is locked
Register for a free Packt account to unlock a world of extra content!
A free Packt account unlocks extra newsletters, articles, discounted offers, and much more. Start advancing your knowledge today.
Unlock this book and the full library FREE for 7 days
Get unlimited access to 7000+ expert-authored eBooks and videos courses covering every tech area you can think of
Renews at €18.99/month. Cancel anytime