Site icon StudyGyaan

Building Python Django Chatbot with Chatterbot

Data Science and Machine Learning

In today’s tech-driven world, chatbots have become an integral part of various applications, enabling seamless interactions between users and systems. Django, a powerful web framework, when combined with Chatterbot, a Python library for creating conversational agents, opens up a world of possibilities for creating intelligent chatbots. In this blog post, we’ll delve into the process of building a Django chatbot using Chatterbot, complete with a step-by-step guide and a hands-on example.

For this tutorial, we will be building a specialized chatbot with a specific theme – answering user questions related to the Coronavirus Disease (Covid-19). Our chatbot will greet users, engage in interactive conversations, and provide accurate and helpful information about Covid-19. Through this project, we aim to create a web-based chatbot that serves as a reliable resource for users seeking information about the pandemic and its various aspects.

Prerequisites:

Before we begin, make sure you have the following prerequisites installed:

  1. Python Version (version <=3.8 or >=3.4)
  2. Django (install using ‘pip install Django’)
  3. HTML, CSS, and JavaScript (basic knowledge)

Note: Package ‘chatterbot’ requires Python Version: <=3.8 or >=3.4

Creating Chatbot using Django and Chatterbot

We recommend you to first create your project with our instructions, then you can do changes according to your requriements.

Step 1: Installing Python 3.7 with pip3.7 along with Python3.10

This step is optional if you already have Python Version <=3.8 or >=3.4. Please check your python using this command – python -V or python3 -V

# Install Python 3.7 Version
sudo apt update
sudo apt install build-essential zlib1g-dev libncurses5-dev libgdbm-dev libnss3-dev libssl-dev libsqlite3-dev libreadline-dev libffi-dev wget libbz2-dev
sudo add-apt-repository ppa:deadsnakes/ppa
sudo apt install python3.7
python3.7 --version

# Install Pip
python3.7 -m pip install pip

# if you are getting distutils error
sudo apt-get install python3.7-distutils

Step 2: Create and Install Virtualenv for Python Version <=3.8 or >=3.4

As we will be using virtual environment for this project. Please read our blog on Using Virtual Environments for Python Projects, if you are not familar with virtualenv in Python.

Let’s install virtualenv using Python3.7

pip install virtualenv

Create virtualenv named venv and activate it.

python3.7 -m virtualenv venv
source venv/bin/activate

Please Note: When you have virtualenv activated, you will see python version 3.7. Outside virtualenv it will be different.

Step 3: Installing Required Libraries

pip install Django
pip install ChatterBot==1.0.8
pip install chatterbot-corpus==1.2.0
pip install spacy==2.1.9
pip install nltk==3.8.1

Step 4: Configuring Django Settings.py For Chatterbot

Create a new app (chatbot) within your Django project:

python manage.py startapp chatbot

Configure Chatterbot in your Django project’s settings.py:

INSTALLED_APPS = [
    # ...
    'chatterbot.ext.django_chatterbot', # chatterbot
    'chatbot', # app which we created above
]

TEMPLATES = [
    {
        'BACKEND': 'django.template.backends.django.DjangoTemplates',
        'DIRS': [BASE_DIR, 'templates/',],
        'APP_DIRS': True,
        'OPTIONS': {
            'context_processors': [
                'django.template.context_processors.debug',
                'django.template.context_processors.request',
                'django.contrib.auth.context_processors.auth',
                'django.contrib.messages.context_processors.messages',
            ],
        },
    },
]

Step 5: Implementing Chatterbot Logic

Create a new Python file (chatbot.py) inside chatbot app and and add the following code:

# chatbot/chatbot.py

from chatterbot import ChatBot
import spacy

spacy.cli.download("en_core_web_sm")
spacy.cli.download("en")

nlp = spacy.load('en_core_web_sm')

chatbot = ChatBot(
    'CoronaBot',
    storage_adapter='chatterbot.storage.SQLStorageAdapter',
    logic_adapters=[
        'chatterbot.logic.MathematicalEvaluation',
        'chatterbot.logic.TimeLogicAdapter',
        'chatterbot.logic.BestMatch',
        {
            'import_path': 'chatterbot.logic.BestMatch',
            'default_response': 'I am sorry, but I do not understand. I am still learning.',
            'maximum_similarity_threshold': 0.90
        }
    ],
    database_uri='sqlite:///database.sqlite3'
)

# Training With Own Questions 
from chatterbot.trainers import ListTrainer

trainer = ListTrainer(chatbot)

import os

# Get the base directory of your Django project
BASE_DIR = os.path.dirname(os.path.dirname(os.path.abspath(__file__)))

# Construct the paths to the data files
training_data_quesans_path = os.path.join(BASE_DIR, 'training_data', 'ques_ans.txt')
training_data_personal_path = os.path.join(BASE_DIR, 'training_data', 'personal_ques.txt')

# Open and read the data files
training_data_quesans = open(training_data_quesans_path).read().splitlines()
training_data_personal = open(training_data_personal_path).read().splitlines()

training_data = training_data_quesans + training_data_personal

trainer.train(training_data)

# Training With Corpus
from chatterbot.trainers import ChatterBotCorpusTrainer

trainer_corpus = ChatterBotCorpusTrainer(chatbot)

trainer_corpus.train(
    'chatterbot.corpus.english'
)

In above example, we are loading data from training_data/ques_ans.txt and training_data/personal_ques.txt. You can download the files from here.

In chatbot/views.py, add the following code to interact with Chatterbot:

from django.shortcuts import render
from .chatbot import chatbot

def chatbot_home(request):
    return render(request, 'index.html')

from django.http import HttpResponse
from chatterbot import ChatBot

def get_response(request):
    user_input = request.GET.get('msg')
    response = chatbot.get_response(user_input)
    return HttpResponse(str(response))

Step 6: Creating Chatbot UI

HTML Template (index.html) – Create a new HTML file index.html inside the “templates” folder (create if not created). Please copy the html content from here.

Bellow is the folder structure your project should look like:

chatbot_project/
├── chatbot_project/
│   ├── settings.py
│   ├── urls.py
│   └── ...
├── chatbot/
│   ├── ...
│   └── views.py
├── training_data/
│   ├── ques_ans.txt
│   └──personal_ques.txt
├── manage.py
└── templates/
    └── index.html

Step 7: Run the Flask App

Open your terminal, navigate to the chatbot_project directory, and execute the following command:

python3.7 manage.py runserver

Step 8: Interact with the Chatbot

Open your web browser and go to http://localhost:8000 to access the chat interface. Now, you can type messages in the input field, press “Send,” and watch your chatbot respond!

Note – If you are not getting right answer for questions, delete the .sqlite3 database file from your folder and re-run the flask app.

Find this tutorial on Github.

Blogs You Might Like to Read!
Exit mobile version