Book Image

Conversational AI with Rasa

By : Xiaoquan Kong, Guan Wang
Book Image

Conversational AI with Rasa

By: Xiaoquan Kong, Guan Wang

Overview of this book

The Rasa framework enables developers to create industrial-strength chatbots using state-of-the-art natural language processing (NLP) and machine learning technologies quickly, all in open source. Conversational AI with Rasa starts by showing you how the two main components at the heart of Rasa work – Rasa NLU (natural language understanding) and Rasa Core. You'll then learn how to build, configure, train, and serve different types of chatbots from scratch by using the Rasa ecosystem. As you advance, you'll use form-based dialogue management, work with the response selector for chitchat and FAQ-like dialogs, make use of knowledge base actions to answer questions for dynamic queries, and much more. Furthermore, you'll understand how to customize the Rasa framework, use conversation-driven development patterns and tools to develop chatbots, explore what your bot can do, and easily fix any mistakes it makes by using interactive learning. Finally, you'll get to grips with deploying the Rasa system to a production environment with high performance and high scalability and cover best practices for building an efficient and robust chat system. By the end of this book, you'll be able to build and deploy your own chatbots using Rasa, addressing the common pain points encountered in the chatbot life cycle.

Related Content you might be interested in

Current Title:

Small book image
Conversational AI with Rasa
Xiaoquan Kong | Guan Wang
Oct, 2021 | 264 pages
Small book image
Mastering spaCy
Duygu Altınok
Jul, 2021 | 356 pages
Table of Contents (16 chapters)
Preface
Preface
Who this book is for
What this book covers
To get the most out of this book
Download the example code files
Download the color images
Conventions used
Get in touch
Share your thoughts
1
Section 1: The Rasa Framework
Section 1: The Rasa Framework
Free Chapter
2
Chapter 1: Introduction to Chatbots and the Rasa Framework
Chapter 1: Introduction to Chatbots and the Rasa Framework
Technical requirements
What is ML?
Introduction to Natural Language Processing (NLP)
Chatbot basics
Introduction to the Rasa framework
Summary
Further reading
3
Chapter 2: Natural Language Understanding in Rasa
Chapter 2: Natural Language Understanding in Rasa
Technical requirements
The format of NLU training data
Overview of Rasa NLU components
Configuring your Rasa NLU via a pipeline
The output of Rasa NLU
Training and running Rasa NLU
Practice – building the NLU part of a medical bot
Summary
4
Chapter 3: Rasa Core
Chapter 3: Rasa Core
Technical requirements
Understanding the universe of your bot (domain)
Training data for dialogue management (stories)
Reacting to user input (action)
Understanding the memory of your bot (slots)
Understanding the decision-maker of your bot (policies)
Connecting with other services via endpoints
Building custom actions using Rasa SDK
Using channels to communicate with instant messaging software
Building a tell-the-time bot
Summary
5
Section 2: Rasa in Action
Section 2: Rasa in Action
6
Chapter 4: Handling Business Logic
Chapter 4: Handling Business Logic
Technical requirements
The fallback mechanism in Rasa
Making intents trigger actions
Using forms to complete tasks
Practice – building a weather forecast chatbot
Summary
7
Chapter 5: Working with Response Selector to Handle Chitchat and FAQs
Chapter 5: Working with Response Selector to Handle Chitchat and FAQs
Technical requirements
Defining retrieval intents – the questions users want to ask
Defining responses – the answers to the questions
Updating the configuration to use ResponseSelector
Learning by doing – building an FAQ bot
Summary
8
Chapter 6: Knowledge Base Actions to Handle Question Answering
Chapter 6: Knowledge Base Actions to Handle Question Answering
Technical requirements
Why do we need knowledge base actions?
How do you use knowledge base actions?
How do you customize knowledge base actions?
Learning by doing – building a knowledge-based music query chatbot
Summary
9
Chapter 7: Entity Roles and Groups for Complex Named Entity Recognition
Chapter 7: Entity Roles and Groups for Complex Named Entity Recognition
Technical requirements
Why do we need entity roles and entity groups?
Using entity roles to distinguish semantics roles in entities of the same type
Using entity groups to divide entities into groups
Configuring Rasa to use entity roles and groups
Learning by doing – building a ticket and drink booking bot
Summary
10
Chapter 8: Working Principles and Customization of Rasa
Chapter 8: Working Principles and Customization of Rasa
Understanding Rasa's NLU module
Understanding how Rasa policies work
Writing Rasa extensions
Practice – Creating your own custom English tokenizer
Summary
11
Section 3: Best Practices
Section 3: Best Practices
12
Chapter 9: Testing and Production Deployment
Chapter 9: Testing and Production Deployment
Testing Rasa projects
Deploying your Rasa assistant to production
Summary
13
Chapter 10: Conversation-Driven Development and Interactive Learning
Chapter 10: Conversation-Driven Development and Interactive Learning
Introduction to CDD
Introduction to Rasa X
Summary
14
Chapter 11: Debugging, Optimization, and Community Ecosystem
Chapter 11: Debugging, Optimization, and Community Ecosystem
Debugging Rasa systems
Optimizing Rasa systems
Understanding the community ecosystem of Rasa
Summary
Why subscribe?
15
Other Books You May Enjoy
Other Books You May Enjoy
Packt is searching for authors like you
Share your thoughts

Updating the configuration to use ResponseSelector

In order to perform an intelligent categorization of the questions, we need to use the ResponseSelector NLU component to train a model with existing training data. We need to add the ResponseSelector component to the pipeline. The ResponseSelector component depends on the featurizer and intent classifier, so make sure you place it after these components in your pipeline, as follows:

pipeline:
  - name: XXXFeaturizer # replace this with a real Featurizer
  - name: XXXClassifier # replace this with a real Classifier
  - name: ResponseSelector

In order to get the right answer based on the result from ResponseSelector, we need to initiate RulePolicy and implement a rule to do the mapping. Here is an example:

rules:
  - rule: map to chitchat
    steps:
    - intent: chitchat
    - action: utter_chitchat

Here, we create a rule...

Previous Section
End of Section 5
Next Section