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.
Table of Contents (16 chapters)
1
Section 1: The Rasa Framework
5
Section 2: Rasa in Action
11
Section 3: Best Practices

Understanding how Rasa policies work

It is important to understand how Rasa policies work. By being familiar with their working principles, developers can debug the dialogue management function.

Using historical context is very important for a policy to predict the next action. Suppose our bot can book train tickets and plane tickets. There is a conversation that has been going on for multiple turns. In the last turn, when the bot asked the user where the departure point was, the user replied: "New York." If there is no historical information, our bot will not know whether it is currently booking a train ticket or a plane ticket. Therefore, the next action cannot be determined. Policies in Rasa normally use multiple history states (five by default).

It is crucial for Rasa's dialogue management module to turn those history states into some data structures that a policy can use. This conversion is the topic we will discuss in the next section.

Converting trackers...