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
> sudo python3

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:
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 -
<link rel="stylesheet" href="" />
<div class="chat-container"></div>
<script src=""/></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"

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'.


Popular posts from this blog

Cannot alter the login 'sa', because it does not exist or you do not have permission.

Working on projects, it can happen that 'sa' account gets locked. If it is on local machine OR development boxes, onus would be on you to fix it. If scripts and SQL steps are not working, this might help you fixing the issue. Steps to unlock 'sa' account and resetting the password. 1. Open SQL Server Configuration Manager 2. Select SQL Server Services -> 'SQL Server' service. 3. Right click on 'SQL Server' service and click on "Startup Parameters". For 2008, server "Startup Parameters" are inside Advanced tab.   4. Add '-m' in startup parameters as shown above and click on 'Add'. This will put SQL server into 'Single User Mode' and local admin will have 'Super User' rights. For 2008, server you have to add ':-m' in the last of the existing query. 5. Save the settings and Restart the service. 6. Now open the SQL Server Management Studio and connect to database using 'Windows A

Could not load file or assembly 'Microsoft.Web.Infrastructure'

Could not load file or assembly 'Microsoft.Web.Infrastructure, Version=, Culture=neutral, PublicKeyToken=31bf3856ad364e35' or one of its dependencies. The system cannot find the file specified. What 'Micorosoft.Web.Infrastructure' does? This dll lets HTTP modules register at run time. Solution to above problem: Copy 'Micorosoft.Web.Infrastructure' dll in bin folder of your project and this problem should be resolved. If you have .Net framework installed on machine, this dll should be present on it. You can search for this dll and copy it in your active project folder.   Alternatively,  you can install this dll using nuget package manager PM> Install-Package Microsoft.Web.Infrastructure -Version 1.0.0 Happy coding!!

Dockerize a dotnet core application with SQL connectivity

Before reading this article, I am assuming that you know Docker, Dotnet core and have a dotnet core application which is trying to connect to SQL server. Read how to build aspnet core app, docker and run the docker container. If docker container is running and you are not able to connect to database, this blog should help you fix it.  Prerequisite -  Make sure code is working via running aspnet core locally via visual studio or command line. Port 1433 is opened for connecting to SQL server. Solution If you have Docker file ready, it should somewhat look like below file -  FROM AS build-env WORKDIR /app # Copy csproj and restore as distinct layers COPY /SampleAPI/*.csproj ./ RUN dotnet restore # Copy everything else and build COPY . . WORKDIR /app/SampleAPI RUN dotnet publish -c Production -o publish # Build runtime image FROM WORKDIR /app/SampleAPI COPY --from=build-env /app/SampleAPI . WORK