Search icon CANCEL
Subscription
0
Cart icon
Your Cart (0 item)
Close icon
You have no products in your basket yet
Save more on your purchases! discount-offer-chevron-icon
Savings automatically calculated. No voucher code required.
Arrow left icon
Explore Products
Best Sellers
New Releases
Books
Videos
Audiobooks
Learning Hub
Free Learning
Arrow right icon
Arrow up icon
GO TO TOP
Conversational AI with Rasa

You're reading from   Conversational AI with Rasa Build, test, and deploy AI-powered, enterprise-grade virtual assistants and chatbots

Arrow left icon
Product type Paperback
Published in Oct 2021
Publisher Packt
ISBN-13 9781801077057
Length 264 pages
Edition 1st Edition
Tools
Concepts
Arrow right icon
Authors (2):
Arrow left icon
Xiaoquan Kong Xiaoquan Kong
Author Profile Icon Xiaoquan Kong
Xiaoquan Kong
Guan Wang Guan Wang
Author Profile Icon Guan Wang
Guan Wang
Arrow right icon
View More author details
Toc

Table of Contents (16) Chapters Close

Preface 1. Section 1: The Rasa Framework
2. Chapter 1: Introduction to Chatbots and the Rasa Framework FREE CHAPTER 3. Chapter 2: Natural Language Understanding in Rasa 4. Chapter 3: Rasa Core 5. Section 2: Rasa in Action
6. Chapter 4: Handling Business Logic 7. Chapter 5: Working with Response Selector to Handle Chitchat and FAQs 8. Chapter 6: Knowledge Base Actions to Handle Question Answering 9. Chapter 7: Entity Roles and Groups for Complex Named Entity Recognition 10. Chapter 8: Working Principles and Customization of Rasa 11. Section 3: Best Practices
12. Chapter 9: Testing and Production Deployment 13. Chapter 10: Conversation-Driven Development and Interactive Learning 14. Chapter 11: Debugging, Optimization, and Community Ecosystem 15. Other Books You May Enjoy

Debugging Rasa systems

A chatbot is a complex software system. Therefore, we need to design and configure Rasa projects carefully. It is pretty common for developers to get different kinds of bugs when building Rasa-based chatbots. In general, those bugs can be of two types: one is that the prediction results are not as expected; another is that there is a code error in the Rasa system, and the bot cannot run normally. We will cover both types of bugs in the following subsections.

Wrong prediction of results

Two problems may cause the wrong prediction of results. It can be that the Natural Language Understanding (NLU) module makes the wrong prediction on user intent and entities, or it can be that a policy makes the wrong prediction on the next action. It is crucial to first make sure which of these problems is causing the wrong predictions.

Fortunately, most of the commands in Rasa have the debug function. Developers can turn on the debugging option to obtain critical internal...

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 $19.99/month. Cancel anytime
Banner background image