Skip to main content

Create chatbot in 20 minutes using RASA


This blog will help you create a working chatbot with in 20 minutes.

For creating chatbot we need following libraries to be installed-
>> Python3
>> Pip3
>> Rasa

Lets start installing all libraries & dependencies which are need for creating chatbot.
Note: I have used MAC, therefore sharing commands related to it. You can install it on Windows, Linux or any other operating system using respective commands.

1. Install Python3
> brew install python3
> python --version #make sure you have python3 installed

2. Install Pip3
> curl -O https://bootstrap.pypa.io/get-pip.py
> sudo python3 get-pip.py

If you get issue related to Frameoworks while installing pip, follow below steps - 
> cd /usr/local/lib
> mkdir Frameworks
> sudo chown -R $(whoami) $(brew --prefix)/*

Once installed check pip3 version
> pip3 --version
After python3 and pip3 is succeffully installed, proceed to next steps.

3. Install Rasa
> pip3 install rasa
After completion, rasa should be installed on your machine.
> rasa --version #check rasa version to confirm rasa latest version is installed
Now you are all set to proceed and work on you chatbot.

4. Create a new project
> rasa -init --no-prompt
This will create all required files for chatbot with sample trained data.

Next step is to train your model with sample data.
> rasa train 

You are all set to go. Run the rasa chatbot(in shell mode) by following command,
> rasa shell
This may take few seconds, so have some patience. Output will look something like this -
You can stop the rasa shell by using below command,
> /stop

5. Expose it as Rest API
Goto directly where you have rasa project installed
> cd rasa_project
> ls #look for credentials.yml file
> vi credentials.yml 
look for "rest:" and uncomment the line. Run below command to expose it as Rest API-
> rasa run -m models --enable-api --cors "*" --log-file out.log
by default, endpoint will be exposed on port 5005 and API will be http://localhost:5005. Run it in browser and you will see 'Hello from rasa 1.9.6' as response.

6. Test the chatbot with Postman
a. Open Postman and create a new POST request using URL:
    http://localhost:5005/webhooks/rest/webhook
b. Enter raw body text in JSON format as input
    {"sender":"Sumit B", "message":"who are you?"}
c. you should receive response in return, as shown in below example -


7. Integrate it with your website
You have to create a nice User Interface to call your rasa API and start interacting with your end users. One example of such a file is given below.
a. Create an index.html file and past the following code into it -
<html>
<head>
<link rel="stylesheet" href="https://npm-scalableminds.s3.eu-central-1.amazonaws.com/@scalableminds/chatroom@master/dist/Chatroom.css" />
</head>
<body>
<div class="chat-container"></div>
<script src="https://npm-scalableminds.s3.eu-central-1.amazonaws.com/@scalableminds/chatroom@master/dist/Chatroom.js"/></script>
<script type="text/javascript">
        var chatroom = new window.Chatroom({
        host: "http://localhost:5005",
        title: "Chat with Sumit B",
        container: document.querySelector(".chat-container"),
        welcomeMessage: "Hi, I am Sumit B. How may I help you?",
        speechRecognition: "en-US",
        voiceLang: "en-US"
        });
       chatroom.openChat();
</script>
</body>
</html>

b. Now run this index.html file using below command -
> python3 -m http.server 8080
c. Open browser and check http://localhost:8080 and you should see your chatbot with example UI


You can install Rasa X for better UI and easy training of model which I have covered in next blog 'Know the rasa ecosystem and train your model effectively'.

Comments

  1. How To Play Spades | TrickToActionHowTo
    How 위디스크 쿠폰 To Play Spades. If you like this 토 블리 game, then 스포츠토토 샤오미 you might want to 토토 마틴 넷마블 learn how to play Spades. You can be the king of spades, but when your 메이저사이트 승부벳 goal is to win the contract

    ReplyDelete

Post a Comment

Popular posts from this blog

AJAX Progrraming

Ajax , shorthand for Asynchronous JavaScript and XML , is a web development technique for creating interactive web applications. The intent is to make web pages feel more responsive by exchanging small amounts of data with the server behind the scenes, so that the entire web page does not have to be reloaded each time the user requests a change. This is meant to increase the web page's interactivity, speed, and usability. The Ajax technique uses a combination of: XHTML (or HTML) and CSS, for marking up and styling information. The DOM accessed with a client-side scripting language, especially JavaScript and JScript, to dynamically display and interact with the information presented. The XMLHttpRequest object is used to exchange data asynchronously with the web server. In some Ajax frameworks and in certain situations, an IFrame object is used instead of the XMLHttpRequest object to exchange data with the web server, and in other implementations, dynamically added tags may be used.

Nutch crawler and integration with Solr

Before moving ahead with this article, I assume you have Solr installed and running. If you would like to install Solr on windows, mac or via docker, please read Setup a Solr instance . There are several ways to install nutch which you can read from Nutch tutorial , however I have written this article for those who would like to install nutch using docker. I tried finding help on google but could not find any help for nutch installation using docker and spent good amount of time fixing issues specific to it. Therefore I have written this article to help and save time of other developers. Install nutch using docker- 1. Pull docker image of nutch using below command,      > docker pull apache/nutch 2. Once image is pulled, run the container,      > docker run -t -i -d --name nutchcontainer apache/nutch /bin/bash 3. You should be able to enter in the container and see bash prompt,      > bash-5.1#  Let's setup few important settings now- 1. Goto bin folder,       > bash-5.