Welcome to module on ‘Building Chatbots with Rasa’
Chatbots have become popular in a large number of business domains. Companies are building chatbots for a host of services, which include hotel, fight and movie booking,customer support, bus and train schedule enquiry, tax -saving advice, accessing stock market information; etc.
But why are they getting so much attention?The reason is simple:They help reduce the time, effort and cost required to get a task done (and if designed well, they also improve the user experience).
In recent times, virtual assistants like Google Assistant ,Siri ,Alexa, Cortana etc.,have been providing a range of solutions to user , which include not only textual solutions, but more interactive ones through its ‘speech-based search engine’. These generic chatbots have significantly improved their conversational experience and have become more sophisticated, responsive and ‘natural.’
Apart from these generic jobs, chatbots can be seen in many domain-specific jobs such as coustmor care service flight room booking,tax-saving advice,etc. So,instead of a person assisting a user , we can now just place a chatbot that can interpret and identify what a user said or wanted, and determine a series of appropriate responses based on that information.
A chatbot can also handle queries pertaining to a particular domain or type of task. For example, a ‘weather bot’ can only predict weather. It cannot book a table at a restaurant or set up an alarm. Similarly, a restaurant discovery bot can only help you find restaurants in several cities; it might not be able to answer general questions such as “Who is the prime minister of India?”.
In this Module
In this module, you will learn how to build a domain-specific chatbot, specifically, a restaurant search chatbot. The bot will be able to ‘talk’ to users in English, and will help them search for restaurants offering multiple cuisines, suiting different budgets, etc., in several cities. You will be using an open-source machine learning (ML) framework called Rasa for building these conversational bots.
This module contains two sessions. In the first session, you will learn how to build a chatbot and deploy it on a public channel such as Slack, Facebook, etc. The second session defines the problem statement, deliverables, etc., of the group project.