If you haven\u2019t read part 1 of this blog, you can read it here in the blog: chatbot using RASA<\/a>. In the first part, we discussed in detail the RASA framework. Using the RASA NLU component of the framework we started coding \u201cTrippy: The Travel Agency Chatbot\u201d<\/a>. For Trippy, we created the training data and trained the model to identify the intent in the user query. So far, Trippy is able to identify when to:<\/p>\n\n\n\n So basically the Chatbot can do natural language processing(NLP) on the incoming query and identify the intent.<\/p>\n\n\n\n In this part, we will use RASA Core components which form the dialogue engine to make an AI chatbot converse with the customer. So far, we have created three files in the \u201ctrippy<\/strong>\u201d base directory:<\/p>\n\n\n\n In this blog, we will learn how to use the concept of Stories, Domain and Custom Actions to code the desired capability. So, let\u2019s begin.<\/p>\n\n\n Pizon Shetu<\/p> Data Scientist at Whiterock AI<\/p><\/div> Read Story<\/a><\/p><\/div><\/div> Corey Wade<\/p> Founder And Director at Berkeley Coding Academy<\/p><\/div> Read Story<\/a><\/p><\/div><\/div> Nick Lenczewski<\/p> Data Scientist at Ovative Group<\/p><\/div> Read Story<\/a><\/p><\/div><\/div><\/div><\/div>\n\n\n\n The dialogue management aspect is handled by the \u201cCore<\/strong>\u201d model of the RASA framework. A core model learns from data in the form of \u201cstories<\/strong>\u201d. You can learn more about Stories here<\/a>. In short, a story is a formatted representation of a conversation between a user and the chatbot. An example of a story from the official documentation<\/a> is as shown below:<\/p>\n\n\n\n Let\u2019s understand the format of a story.<\/p>\n\n\n\n Before we go ahead and create stories for Trippy, let’s also understand the concept of Domains<\/a> and Actions<\/a>.<\/p>\n\n\n\n A DOMAIN <\/strong>is a universe in which the AI chatbot functions. It includes all the intents, entities, slots, actions and optionally responses that the bot should be aware of. We covered intents and entities in detail in part 1. Let\u2019s understand the other three.<\/p>\n\n\n\n You can read more about other types of slots here<\/a>.<\/p>\n\n\n\n Utterance actions: <\/strong>start with utter_ and send a specific message to the user.<\/p>\n\n\n\n Retrieval actions: <\/strong>start with respond_ and send a message selected by a retrieval model.<\/p>\n\n\n\n Custom actions: <\/strong>run arbitrary code and send any number of messages (or none).<\/p>\n\n\n\n Default actions: <\/strong>e.g. action_listen, action_restart, action_default_fallback.<\/p>\n\n\n\n Now that we have an understanding of Stories and Domain, let’s create the stories and domain files for Trippy. If you recollect from Part 1, Trippy is coded to handle the following intents:<\/p>\n\n\n\n First, we will create the stories.md file. Here is a snippet of the stories.md file. You can request access to the complete file by sending us a request <form_link>. Now, let\u2019s create the domain.yml file. This file should contain all the intents, entities, actions and responses. The domain.yml file is as shown below: If you look at the responses section of the domain.yml file, you can see that it defines the responses for utter_ actions. There are other actions which are named action_ which are not defined here. Since these actions are not expected to return static text and in real-world, these should execute some query\/search etc. these are examples of Custom Actions. You can read more about how to configure custom actions here. We will use the python code to define our custom actions. For this, we will create a file \u201cactions.py\u201d. In this file, we define and map a class for each of the custom actions mentioned in the domain.yml file.<\/p>\n\n\n\n In a real-world scenario, the AI chatbot needs to compute, retrieve, process information gained from intent and entity extraction. This file actions.py is where you can do all of that.<\/p>\n\n\n\n There are some additional steps required to be performed to make these custom actions available for the AI chatbot. We need to define the endpoint url in the file endpoints.yml. Don\u2019t create this file right now, it will get created automatically (as we perform some steps later).<\/p>\n\n\n\n You may have noticed that we also defined an action utter_unclear<\/strong> in stories.md and domain.yml file. This action will be taken when the chatbot is not quite confident about the intent\/entity predictions. To leverage this, we need to set and define some policies in the config.yml file. The file snippet is as follows:<\/p>\n\n\n\n Now that we are using more framework components, it will be better to use less python code and more framework function to tie all these configurations and data together. So we will do things a little differently from part 1. It is recommended that you create a new directory for this.<\/p>\n\n\n\n Pre-requisites:<\/p>\n\n\n\n Steps:<\/p>\n\n\n\n 10. Start the training: Inspired by this analysis and want to learn how to do it \/ wish to replicate this for your project? We can help you there. Just leave your email address in this google form<\/a> and we will share the analysis with you within 48 hours.<\/strong><\/em><\/p>\n\n\n\n An image of interaction with Trippy is as shown below:<\/p>\n\n\n\n Additionally, you can also see that the custom actions are also able to receive the entities and intents extracted from the code.<\/p>\n\n\n\n You can see that Trippy is much more evolved now and is able to handle a sequence of flows in an expected manner. These capabilities are achieved using framework components without having to write a lot of code with complex IF-ELSE like statements that are good from maintainability and scalability aspects. In a real-world scenario, one rarely exposes chatbots through command-line. Trippy as of now interacts with the user through the Rasa shell. In the next Blog of this series, we will learn how to deploy Trippy on a Messaging Platform. We will be deploying Trippy on Slack. We will soon publish part 3 of the series. <\/p>\n\n\n\n For further reading, learn more about data science here<\/a> or see the breakdown of the job description of a data scientist here<\/a>.<\/em><\/p>\n\n\n\n Since you\u2019re here\u2026 In this series 2 of the blog post on how to build a secure AI Chatbot using RASA and Python, we will learn how to level up from Basic NLU to Dialogue Management & Custom Actions. How to Build a Secure AI Chatbot: What Did we Do in Part 1? If you haven\u2019t read part […]<\/p>\n","protected":false},"author":100,"featured_media":24084,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"_acf_changed":false,"_eb_attr":"","_eb_data_table":"","footnotes":""},"categories":[67],"tags":[],"marketing_tags":[],"class_list":{"0":"post-24080","1":"post","2":"type-post","3":"status-publish","4":"format-standard","5":"has-post-thumbnail","7":"category-data-science"},"acf":[],"_links":{"self":[{"href":"https:\/\/www.springboard.com\/blog\/wp-json\/wp\/v2\/posts\/24080"}],"collection":[{"href":"https:\/\/www.springboard.com\/blog\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/www.springboard.com\/blog\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/www.springboard.com\/blog\/wp-json\/wp\/v2\/users\/100"}],"replies":[{"embeddable":true,"href":"https:\/\/www.springboard.com\/blog\/wp-json\/wp\/v2\/comments?post=24080"}],"version-history":[{"count":4,"href":"https:\/\/www.springboard.com\/blog\/wp-json\/wp\/v2\/posts\/24080\/revisions"}],"predecessor-version":[{"id":46206,"href":"https:\/\/www.springboard.com\/blog\/wp-json\/wp\/v2\/posts\/24080\/revisions\/46206"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/www.springboard.com\/blog\/wp-json\/wp\/v2\/media\/24084"}],"wp:attachment":[{"href":"https:\/\/www.springboard.com\/blog\/wp-json\/wp\/v2\/media?parent=24080"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/www.springboard.com\/blog\/wp-json\/wp\/v2\/categories?post=24080"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/www.springboard.com\/blog\/wp-json\/wp\/v2\/tags?post=24080"},{"taxonomy":"marketing_tags","embeddable":true,"href":"https:\/\/www.springboard.com\/blog\/wp-json\/wp\/v2\/marketing_tags?post=24080"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}\n
Objective of Part 2?<\/h2>\n\n\n\n
\n
Get To Know Other\tData Science Students<\/h4>
![\"Pizon](\"https:\/\/res.cloudinary.com\/springboard-images\/image\/upload\/v1651030560\/Student%20Success\/Pizon_Shetu.jpg\")
<\/a>![\"Corey](\"https:\/\/res.cloudinary.com\/springboard-images\/image\/upload\/v1680712086\/Corey_Wade_LinkedIn.jpg\")
<\/a>![\"Nick](\"https:\/\/res.cloudinary.com\/springboard-images\/image\/upload\/v1667235351\/Student%20Success\/Nick_Lenczewski.jpg\")
<\/a>Dialogue Management: Teaching the AI Chatbot How to Respond<\/h2>\n\n\n\n
![\"rasa](\"https:\/\/www.springboard.com\/blog\/wp-content\/uploads\/2021\/06\/rasa-chatbot-1200x353.png\")
\n
\n
![\"rasa](\"https:\/\/www.springboard.com\/blog\/wp-content\/uploads\/2021\/06\/rasa-chatbot-ai-chatbot-using-rasa-3-1200x268.png\")
\n
\n
\n
<\/p>\n\n\n\n![\"rasa](\"https:\/\/www.springboard.com\/blog\/wp-content\/uploads\/2021\/06\/rasa-chatbot-ai-chatbot-using-rasa-4-1200x1296.png\")
<\/p>\n\n\n\n![\"rasa](\"https:\/\/www.springboard.com\/blog\/wp-content\/uploads\/2021\/06\/rasa-chatbot-ai-chatbot-using-rasa-5.png\")
![\"rasa](\"https:\/\/www.springboard.com\/blog\/wp-content\/uploads\/2021\/06\/rasa-chatbot-ai-chatbot-using-rasa-6-1200x722.png\")
![\"rasa](\"https:\/\/www.springboard.com\/blog\/wp-content\/uploads\/2021\/06\/rasa-chatbot-ai-chatbot-using-rasa-7.png\")
\n
\n
>> mkdir trippy_2
>> cd trippy_2<\/li>\n\n\n\n
>> rasa init –no-prompt
This will automatically create all the files that the project needs (with some data for the default demo project).<\/li>\n\n\n\n
action_endpoint:
url: “http:\/\/localhost:5055\/webhook” In a different shell, start the action sever:<\/li>\n\n\n\n
>> cd tripp_2
>> rasa run actions<\/li>\n<\/ol>\n\n\n\n![\"rasa](\"https:\/\/www.springboard.com\/blog\/wp-content\/uploads\/2021\/06\/rasa-chatbot-rasa-run-actions-1200x167.png\")
<\/figure>\n\n\n\n
>> rasa train
11.Start the shell to engage with the model:
>> rasa shell –endpoints endpoints.yml<\/p>\n\n\n\n![\"rasa](\"https:\/\/www.springboard.com\/blog\/wp-content\/uploads\/2021\/06\/rasa-chatbot-rasa-python-1-1200x1034.png\")
![\"rasa](\"https:\/\/www.springboard.com\/blog\/wp-content\/uploads\/2021\/06\/rasa-chatbot-rasa-python-1200x213.png\")
<\/strong>Curious about a career in data science? Experiment with our free data science learning path<\/a>, or join our Data Science Bootcamp<\/a>, where you\u2019ll get your tuition back if you don’t land a job after graduating. We\u2019re confident because our courses work \u2013 check out our student success stories<\/a> to get inspired.<\/p>\n","protected":false},"excerpt":{"rendered":"