ChatterBot Tutorial

This tutorial will guide you through the process of creating a simple command-line chat bot using ChatterBot.

Getting help

If you’re having trouble with this tutorial, you can post a message on Gitter to chat with other ChatterBot users who might be able to help.

You can also ask questions on Stack Overflow under the chatterbot tag.

If you believe that you have encountered an error in ChatterBot, please open a ticket on GitHub: https://github.com/gunthercox/ChatterBot/issues/new

Installing ChatterBot

You can install ChatterBot on your system using Python’s pip command.

pip install chatterbot

See Installation for alternative installation options.

Creating your first chat bot

Create a new file named chatbot.py. Then open chatbot.py in your editor of choice.

Before we do anything else, ChatterBot needs to be imported. The import for ChatterBot should look like the following line.

from chatterbot import ChatBot

Create a new instance of the ChatBot class.

bot = ChatBot('Norman')

This line of code has created a new chat bot named Norman. There is a few more parameters that we will want to specify before we run our program for the first time.

Setting the storage adapter

ChatterBot comes with built in adapter classes that allow it to connect to different types of databases. In this tutorial, we will be using the SQLStorageAdapter which allows the chat bot to connect to SQL databases. By default, this adapter will create a SQLite database.

The database parameter is used to specify the path to the database that the chat bot will use. For this example we will call the database sqlite:///database.sqlite3. this file will be created automatically if it doesn’t already exist.

bot = ChatBot(
    'Norman',
    storage_adapter='chatterbot.storage.SQLStorageAdapter',
    database_uri='sqlite:///database.sqlite3'
)

Note

The SQLStorageAdapter is ChatterBot’s default adapter. If you do not specify an adapter in your constructor, the SQLStorageAdapter adapter will be used automatically.

Specifying logic adapters

The logic_adapters parameter is a list of logic adapters. In ChatterBot, a logic adapter is a class that takes an input statement and returns a response to that statement.

You can choose to use as many logic adapters as you would like. In this example we will use two logic adapters. The TimeLogicAdapter returns the current time when the input statement asks for it. The MathematicalEvaluation adapter solves math problems that use basic operations.

bot = ChatBot(
    'Norman',
    storage_adapter='chatterbot.storage.SQLStorageAdapter',
    logic_adapters=[
        'chatterbot.logic.MathematicalEvaluation',
        'chatterbot.logic.TimeLogicAdapter'
    ],
    database_uri='sqlite:///database.sqlite3'
)

Getting a response from your chat bot

Next, you will want to create a while loop for your chat bot to run in. By breaking out of the loop when specific exceptions are triggered, we can exit the loop and stop the program when a user enters ctrl+c.

while True:
    try:
        bot_input = bot.get_response(input())
        print(bot_input)

    except(KeyboardInterrupt, EOFError, SystemExit):
        break

Training your chat bot

At this point your chat bot, Norman will learn to communicate as you talk to him. You can speed up this process by training him with examples of existing conversations.

from chatterbot.trainers import ListTrainer

trainer = ListTrainer(bot)

trainer.train([
    'How are you?',
    'I am good.',
    'That is good to hear.',
    'Thank you',
    'You are welcome.',
])

You can run the training process multiple times to reinforce preferred responses to particular input statements. You can also run the train command on a number of different example dialogs to increase the breadth of inputs that your chat bot can respond to.


This concludes this ChatterBot tutorial. Please see other sections of the documentation for more details and examples.

Up next: Examples