The main class ChatBot is a connecting point between each of ChatterBot’s adapters. In this class, an input statement is processed and stored by the logic adapter and storage adapter. A response to the input is then generated and returned.

class chatterbot.ChatBot(name, **kwargs)[source]

A conversational dialog chat bot.

  • name (str) – A name is the only required parameter for the ChatBot class.
  • storage_adapter (str) – The dot-notated import path to a storage adapter class. Defaults to "".
  • logic_adapters (list) – A list of dot-notated import paths to each logic adapter the bot uses. Defaults to ["chatterbot.logic.BestMatch"].
  • logger (logging.Logger) – A Logger object.
exception ChatBotException[source]
generate_response(input_statement, additional_response_selection_parameters=None)[source]

Return a response based on a given input statement.

Parameters:input_statement – The input statement to be processed.

Returns the latest response in a conversation if it exists. Returns None if a matching conversation cannot be found.

get_response(statement=None, **kwargs)[source]

Return the bot’s response based on the input.

  • statement – An statement object or string.
  • additional_response_selection_parameters (dict) – Parameters to pass to the chat bot’s logic adapters to control response selection.
  • persist_values_to_response (dict) – Values that should be saved to the response that the chat bot generates.

A response to the input.

Return type:


learn_response(statement, previous_statement=None)[source]

Learn that the statement provided is a valid response.

Example chat bot parameters


Example expanded chat bot parameters

It is also possible to pass parameters directly to individual adapters. To do this, you must use a dictionary that contains a key called import_path which specifies the import path to the adapter class.

    'Leander Jenkins',
        'import_path': '',
        'database_uri': 'protocol://my-database'
            'import_path': 'my.logic.AdapterClass1',
            'statement_comparison_function': chatterbot.comparisons.LevenshteinDistance
            'response_selection_method': chatterbot.response_selection.get_first_response
            'import_path': 'my.logic.AdapterClass2',
            'statement_comparison_function': my_custom_comparison_function
            'response_selection_method': my_custom_selection_method

Enable logging

ChatterBot has built in logging. You can enable ChatterBot’s logging by setting the logging level in your code.

import logging


    # ...

The logging levels available are CRITICAL, ERROR, WARNING, INFO, DEBUG, and NOTSET. See the Python logging documentation for more information.

Using a custom logger

You can choose to use your own custom logging class with your chat bot. This can be useful when testing and debugging your code.

import logging

custom_logger = logging.getLogger(__name__)

    # ...


ChatterBot uses adapter modules to control the behavior of specific types of tasks. There are four distinct types of adapters that ChatterBot uses, these are storage adapters and logic adapters.

Adapters types

  1. Storage adapters - Provide an interface for ChatterBot to connect to various storage systems such as MongoDB or local file storage.
  2. Logic adapters - Define the logic that ChatterBot uses to respond to input it receives.

Accessing the ChatBot instance

When ChatterBot initializes each adapter, it sets an attribute named chatbot. The chatbot variable makes it possible for each adapter to have access to all of the other adapters being used. Suppose logic adapters need to share some information or perhaps you want to give your logic adapter direct access to the storage adapter. These are just a few cases where this functionality is useful.

Each adapter can be accessed on the chatbot object from within an adapter by referencing self.chatbot. Then, refers to the storage adapter, and self.chatbot.logic refers to the logic adapters.