ChatterBot 1.2.5__py3-none-any.whl → 1.2.7__py3-none-any.whl

chatterbot/__init__.py

@@ -4,7 +4,7 @@ ChatterBot is a machine learning, conversational dialog engine.
 from .chatterbot import ChatBot
 
 
-__version__ = '1.2.5'
+__version__ = '1.2.7'
 
 __all__ = (
     'ChatBot',

chatterbot/chatterbot.py

@@ -1,4 +1,5 @@
 import logging
+from typing import Union
 from chatterbot.storage import StorageAdapter
 from chatterbot.logic import LogicAdapter
 from chatterbot.search import TextSearch, IndexedTextSearch
@@ -40,11 +41,21 @@ class ChatBot(object):
 
     :param logger: A ``Logger`` object.
     :type logger: logging.Logger
+
+    :param model: A definition used to load a large language model.
+                  Defaults to ``None``.
+                  (Added in version 1.2.7)
+    :type model: dict
+
+    :param stream: Return output as a streaming responses when a ``model`` is defined.
+                   (Added in version 1.2.7)
     """
 
-    def __init__(self, name, **kwargs):
+    def __init__(self, name, stream=False, **kwargs):
         self.name = name
 
+        self.stream = stream
+
         self.logger = kwargs.get('logger', logging.getLogger(__name__))
 
         storage_adapter = kwargs.get('storage_adapter', 'chatterbot.storage.SQLStorageAdapter')
@@ -112,10 +123,15 @@ class ChatBot(object):
         # NOTE: 'xx' is the language code for a multi-language model
         self.nlp = spacy.blank(self.tagger.language.ISO_639_1)
 
+        self.model = None
+        if model := kwargs.get('model'):
+            import_path = model.pop('client')
+            self.model = utils.initialize_class(import_path, self, **model)
+
         # Allow the bot to save input it receives so that it can learn
         self.read_only = kwargs.get('read_only', False)
 
-    def get_response(self, statement=None, **kwargs) -> Statement:
+    def get_response(self, statement: Union[Statement, str, dict] = None, **kwargs) -> Statement:
         """
         Return the bot's response based on the input.
 
@@ -185,6 +201,10 @@ class ChatBot(object):
             additional_response_selection_parameters
         )
 
+        # If streaming is enabled return the response immediately
+        if self.stream:
+            return response
+
         # Update any response data that needs to be changed
         if persist_values_to_response:
             for response_key in persist_values_to_response:
@@ -219,6 +239,12 @@ class ChatBot(object):
         result = None
         max_confidence = -1
 
+        # If a model is provided, use it to process the input statement
+        # instead of the logic adapters
+        if self.model:
+            model_response = self.model.process(input_statement)
+            return model_response
+
         for adapter in self.logic_adapters:
             if adapter.can_process(input_statement):
 

chatterbot/conversation.py

@@ -22,13 +22,13 @@ class StatementMixin(object):
 
     extra_statement_field_names = []
 
-    def get_statement_field_names(self):
+    def get_statement_field_names(self) -> list[str]:
         """
         Return the list of field names for the statement.
         """
         return self.statement_field_names + self.extra_statement_field_names
 
-    def get_tags(self):
+    def get_tags(self) -> list[str]:
         """
         Return the list of tags for this statement.
         """
@@ -79,7 +79,7 @@ class Statement(StatementMixin):
         'storage',
     )
 
-    def __init__(self, text, in_response_to=None, **kwargs):
+    def __init__(self, text: str, in_response_to=None, **kwargs):
 
         self.id = kwargs.get('id')
         self.text = str(text)

chatterbot/corpus.py

@@ -18,7 +18,7 @@ except (ImportError, ModuleNotFoundError):
 CORPUS_EXTENSION = 'yml'
 
 
-def get_file_path(dotted_path, extension='json'):
+def get_file_path(dotted_path, extension='json') -> str:
     """
     Reads a dotted file path and returns the file path.
     """
@@ -41,7 +41,7 @@ def get_file_path(dotted_path, extension='json'):
     return corpus_path
 
 
-def read_corpus(file_name):
+def read_corpus(file_name) -> dict:
     """
     Read and return the data from a corpus json file.
     """
@@ -59,7 +59,7 @@ def read_corpus(file_name):
         return yaml.safe_load(data_file)
 
 
-def list_corpus_files(dotted_path):
+def list_corpus_files(dotted_path) -> list[str]:
     """
     Return a list of file paths to each data file in the specified corpus.
     """

chatterbot/ext/django_chatterbot/abstract_models.py

@@ -117,7 +117,7 @@ class AbstractBaseStatement(models.Model, StatementMixin):
             return self.text
         return '<empty>'
 
-    def get_tags(self):
+    def get_tags(self) -> list[str]:
         """
         Return the list of tags for this statement.
         (Overrides the method from StatementMixin)

chatterbot/ext/sqlalchemy_app/models.py

@@ -13,7 +13,7 @@ class ModelBase(object):
     """
 
     @declared_attr
-    def __tablename__(cls):
+    def __tablename__(cls) -> str:
         """
         Return the lowercase class name as the name of the table.
         """
@@ -99,7 +99,7 @@ class Statement(Base, StatementMixin):
         server_default=''
     )
 
-    def get_tags(self):
+    def get_tags(self) -> list[str]:
         """
         Return a list of tags for this statement.
         """

chatterbot/filters.py

@@ -1,4 +1,4 @@
-def get_recent_repeated_responses(chatbot, conversation, sample=10, threshold=3, quantity=3):
+def get_recent_repeated_responses(chatbot, conversation, sample=10, threshold=3, quantity=3) -> list:
     """
     A filter that eliminates possibly repetitive responses to prevent
     a chat bot from repeating statements that it has recently said.

chatterbot/llm.py

@@ -0,0 +1,145 @@
+"""
+Large Language Model (LLM) clients.
+
+    .. note::
+        As a part of the development process when choosing models it is
+        important to research and understand the models you are using.
+
+        A good example of why this is important can be found in the
+        description of the Phi-3 model from Microsoft which discusses
+        responsible AI considerations such as the limitations of the
+        model, and appropriate use cases.
+        https://huggingface.co/microsoft/Phi-3-mini-4k-instruct-gguf#responsible-ai-considerations
+"""
+
+
+class ModelClient:
+    """
+    A base class to define the interface for language model clients.
+    """
+
+    def __init__(self, chatbot, model: str, **kwargs):
+        self.chatbot = chatbot
+        self.model = model
+
+
+class Ollama(ModelClient):
+    """
+    This client class allows the use of Ollama models for chatbot responses.
+
+    .. warning::
+        This is a new and experimental class. It may not work as expected
+        and its functionality may change in future releases.
+
+    .. note::
+        Added in version 1.2.7
+    """
+
+    def __init__(self, chatbot, model: str, **kwargs):
+        """
+        keyword arguments:
+            host: The host URL for the Ollama server.
+                Default is 'http://localhost:11434'.
+        """
+        super().__init__(chatbot, model)
+        from ollama import Client, AsyncClient
+
+        self.host = kwargs.get('host', 'http://localhost:11434')
+
+        # TODO: Look into supporting the async client
+        self.async_mode = False
+
+        # https://github.com/ollama/ollama-python
+        if self.async_mode:
+            self.client = AsyncClient(
+                host=self.host,
+            )
+        else:
+            self.client = Client(
+                host=self.host,
+            )
+
+    def process(self, statement):
+
+        system_message = {
+            'role': 'system',
+            'content': 'Please keep responses short and concise.'
+        }
+        message = {
+            'role': 'user',
+            'content': statement.text
+        }
+
+        if self.chatbot.stream:
+            for part in self.client.chat(
+                model=self.model,
+                messages=[system_message, message],
+                stream=True
+            ):
+                yield part['message']['content']
+        else:
+            response = self.client.chat(
+                model=self.model,
+                messages=[system_message, message]
+            )
+
+            return response.message.content
+
+
+class OpenAI(ModelClient):
+    """
+    This client class allows the use of the OpenAI API to generate chatbot responses.
+
+    .. warning::
+        This is a new and experimental class. It may not work as expected
+        and its functionality may change in future releases.
+
+    .. note::
+        Added in version 1.2.7
+    """
+
+    def __init__(self, chatbot, model, **kwargs):
+        super().__init__(chatbot, model, **kwargs)
+        from openai import OpenAI as OpenAIClient
+        from openai import AsyncOpenAI as AsyncOpenAIClient
+
+        self.host = kwargs.get('host', None)
+
+        # TODO: Look into supporting the async client
+        self.async_mode = False
+
+        # https://github.com/openai/openai-python
+        if self.async_mode:
+            self.client = AsyncOpenAIClient(
+                base_url=self.host,
+            )
+        else:
+            self.client = OpenAIClient(
+                base_url=self.host,
+            )
+
+    def process(self, statement):
+
+        system_message = {
+            'role': 'developer',
+            'content': 'Please keep responses short and concise.'
+        }
+        message = {
+            'role': 'user',
+            'content': statement.text
+        }
+
+        if self.chatbot.stream:
+            for part in self.client.chat.completions.create(
+                model=self.model,
+                messages=[system_message, message],
+                stream=True
+            ):
+                yield part
+        else:
+            response = self.client.chat.completions.create(
+                model=self.model,
+                messages=[system_message, message]
+            )
+
+            return response.output_text

chatterbot/logic/__init__.py

@@ -5,6 +5,7 @@ from chatterbot.logic.specific_response import SpecificResponseAdapter
 from chatterbot.logic.time_adapter import TimeLogicAdapter
 from chatterbot.logic.unit_conversion import UnitConversion
 
+
 __all__ = (
     'LogicAdapter',
     'BestMatch',

chatterbot/logic/best_match.py

@@ -1,4 +1,5 @@
 from chatterbot.logic import LogicAdapter
+from chatterbot.conversation import Statement
 from chatterbot import filters
 
 
@@ -22,7 +23,7 @@ class BestMatch(LogicAdapter):
 
         self.excluded_words = kwargs.get('excluded_words')
 
-    def process(self, input_statement, additional_response_selection_parameters=None):
+    def process(self, input_statement: Statement, additional_response_selection_parameters=None) -> Statement:
 
         # Get all statements that have a response text similar to the input statement
         search_results = self.search_algorithm.search(input_statement)

chatterbot/logic/logic_adapter.py

@@ -86,7 +86,7 @@ class LogicAdapter(Adapter):
         """
         return True
 
-    def process(self, statement, additional_response_selection_parameters=None) -> Statement:
+    def process(self, statement: Statement, additional_response_selection_parameters: dict = None) -> Statement:
         """
         Override this method and implement your logic for selecting a response to an input statement.
 
@@ -99,11 +99,9 @@ class LogicAdapter(Adapter):
         lowest confidence level and 1 is the highest.
 
         :param statement: An input statement to be processed by the logic adapter.
-        :type statement: Statement
 
         :param additional_response_selection_parameters: Parameters to be used when
             filtering results to choose a response from.
-        :type additional_response_selection_parameters: dict
         """
         raise self.AdapterMethodNotImplementedError()
 

chatterbot/logic/mathematical_evaluation.py

@@ -25,7 +25,7 @@ class MathematicalEvaluation(LogicAdapter):
         self.language = kwargs.get('language', languages.ENG)
         self.cache = {}
 
-    def can_process(self, statement):
+    def can_process(self, statement) -> bool:
         """
         Determines whether it is appropriate for this
         adapter to respond to the user input.
@@ -34,7 +34,7 @@ class MathematicalEvaluation(LogicAdapter):
         self.cache[statement.text] = response
         return response.confidence == 1
 
-    def process(self, statement, additional_response_selection_parameters=None):
+    def process(self, statement: Statement, additional_response_selection_parameters: dict = None) -> Statement:
         """
         Takes a statement string.
         Returns the equation from the statement with the mathematical terms solved.

chatterbot/logic/specific_response.py

@@ -40,7 +40,7 @@ class SpecificResponseAdapter(LogicAdapter):
 
         return spacy.load(model)
 
-    def can_process(self, statement):
+    def can_process(self, statement) -> bool:
         if self.matcher:
             doc = self.nlp(statement.text)
             matches = self.matcher(doc)
@@ -52,7 +52,7 @@ class SpecificResponseAdapter(LogicAdapter):
 
         return False
 
-    def process(self, statement, additional_response_selection_parameters=None):
+    def process(self, statement: Statement, additional_response_selection_parameters: dict = None) -> Statement:
 
         if callable(self._output_text):
             response_statement = Statement(text=self._output_text())

chatterbot/logic/time_adapter.py

@@ -51,7 +51,7 @@ class TimeLogicAdapter(LogicAdapter):
         # Add the patterns to the matcher
         self.matcher.add('TimeQuestionList', patterns)
 
-    def process(self, statement, additional_response_selection_parameters=None):
+    def process(self, statement: Statement, additional_response_selection_parameters: dict = None) -> Statement:
         now = datetime.now()
 
         # Check if the input statement contains a time-related question

chatterbot/logic/unit_conversion.py

@@ -137,12 +137,12 @@ class UnitConversion(LogicAdapter):
 
         return response
 
-    def can_process(self, statement):
+    def can_process(self, statement) -> bool:
         response = self.process(statement)
         self.cache[statement.text] = response
         return response.confidence == 1.0
 
-    def process(self, statement, additional_response_selection_parameters=None):
+    def process(self, statement: Statement, additional_response_selection_parameters: dict = None) -> Statement:
         response = Statement(text='')
         input_text = statement.text
         try:

chatterbot/response_selection.py

@@ -6,13 +6,11 @@ from chatterbot.conversation import Statement
 import logging
 
 
-def get_most_frequent_response(input_statement, response_list, storage=None) -> Statement:
+def get_most_frequent_response(input_statement: Statement, response_list: list[Statement], storage=None) -> Statement:
     """
     :param input_statement: A statement, that closely matches an input to the chat bot.
-    :type input_statement: Statement
 
     :param response_list: A list of statement options to choose a response from.
-    :type response_list: list
 
     :param storage: An instance of a storage adapter to allow the response selection
                     method to access other statements if needed.
@@ -41,13 +39,11 @@ def get_most_frequent_response(input_statement, response_list, storage=None) ->
     return matching_response
 
 
-def get_first_response(input_statement, response_list, storage=None) -> Statement:
+def get_first_response(input_statement: Statement, response_list: list[Statement], storage=None) -> Statement:
     """
     :param input_statement: A statement, that closely matches an input to the chat bot.
-    :type input_statement: Statement
 
     :param response_list: A list of statement options to choose a response from.
-    :type response_list: list
 
     :param storage: An instance of a storage adapter to allow the response selection
                     method to access other statements if needed.
@@ -62,7 +58,7 @@ def get_first_response(input_statement, response_list, storage=None) -> Statemen
     return response_list[0]
 
 
-def get_random_response(input_statement, response_list, storage=None) -> Statement:
+def get_random_response(input_statement: Statement, response_list: list[Statement], storage=None) -> Statement:
     """
     :param input_statement: A statement, that closely matches an input to the chat bot.
     :type input_statement: Statement

chatterbot/storage/django_storage.py

@@ -24,7 +24,7 @@ class DjangoStorageAdapter(StorageAdapter):
         from django.apps import apps
         return apps.get_model(self.django_app_name, 'Tag')
 
-    def count(self):
+    def count(self) -> int:
         Statement = self.get_model('statement')
         return Statement.objects.count()
 

chatterbot/storage/mongodb.py

@@ -54,7 +54,7 @@ class MongoDatabaseAdapter(StorageAdapter):
 
         return statement
 
-    def count(self):
+    def count(self) -> int:
         return self.statements.count_documents({})
 
     def mongo_to_object(self, statement_data):

chatterbot/storage/redis.py

@@ -132,7 +132,7 @@ class RedisVectorStorageAdapter(StorageAdapter):
 
         return StatementObject(**values)
 
-    def count(self):
+    def count(self) -> int:
         """
         Return the number of entries in the database.
         """

chatterbot/storage/sql_storage.py

@@ -44,7 +44,7 @@ class SQLStorageAdapter(StorageAdapter):
                 dbapi_connection.execute('PRAGMA journal_mode=WAL')
                 dbapi_connection.execute('PRAGMA synchronous=NORMAL')
 
-        if not inspect(self.engine).has_table(self.engine, 'statement'):
+        if not inspect(self.engine).has_table('statement'):
             self.create_database()
 
         # Check if the expected index exists on the text field of the statement table
@@ -90,7 +90,7 @@ class SQLStorageAdapter(StorageAdapter):
 
         return StatementObject(**statement.serialize())
 
-    def count(self):
+    def count(self) -> int:
         """
         Return the number of entries in the database.
         """

chatterbot/storage/storage_adapter.py

@@ -54,7 +54,7 @@ class StorageAdapter(object):
 
         return Statement
 
-    def count(self):
+    def count(self) -> int:
         """
         Return the number of entries in the database.
         """

chatterbot/tagging.py

@@ -1,3 +1,4 @@
+from typing import List, Union, Tuple
 from chatterbot import languages
 from chatterbot.utils import get_model_for_language
 import spacy
@@ -20,7 +21,7 @@ class LowercaseTagger(object):
             'chatterbot_lowercase_indexer', name='chatterbot_lowercase_indexer', last=True
         )
 
-    def get_text_index_string(self, text):
+    def get_text_index_string(self, text: Union[str, List[str]]):
         if isinstance(text, list):
             documents = self.nlp.pipe(text)
             return [document._.search_index for document in documents]
@@ -28,7 +29,7 @@ class LowercaseTagger(object):
             document = self.nlp(text)
             return document._.search_index
 
-    def as_nlp_pipeline(self, texts):
+    def as_nlp_pipeline(self, texts: Union[List[str], Tuple[str, dict]]):
 
         process_as_tuples = texts and isinstance(texts[0], tuple)
 
@@ -52,7 +53,7 @@ class PosLemmaTagger(object):
             'chatterbot_bigram_indexer', name='chatterbot_bigram_indexer', last=True
         )
 
-    def get_text_index_string(self, text):
+    def get_text_index_string(self, text: Union[str, List[str]]) -> str:
         """
         Return a string of text containing part-of-speech, lemma pairs.
         """
@@ -63,7 +64,7 @@ class PosLemmaTagger(object):
             document = self.nlp(text)
             return document._.search_index
 
-    def as_nlp_pipeline(self, texts):
+    def as_nlp_pipeline(self, texts: Union[List[str], Tuple[str, dict]]):
         """
         Accepts a single string or a list of strings, or a list of tuples
         where the first element is the text and the second element is a

chatterbot/trainers.py

@@ -1,12 +1,13 @@
 import os
-import sys
 import csv
 import time
 import glob
 import json
 import tarfile
+from typing import List, Union
 from tqdm import tqdm
 from dateutil import parser as date_parser
+from chatterbot.chatterbot import ChatBot
 from chatterbot.conversation import Statement
 
 
@@ -20,7 +21,7 @@ class Trainer(object):
            the environment variable if it is set.
     """
 
-    def __init__(self, chatbot, **kwargs):
+    def __init__(self, chatbot: ChatBot, **kwargs):
         self.chatbot = chatbot
 
         environment_default = bool(int(os.environ.get('CHATTERBOT_SHOW_TRAINING_PROGRESS', True)))
@@ -30,7 +31,7 @@ class Trainer(object):
             environment_default
         )
 
-    def get_preprocessed_statement(self, input_statement):
+    def get_preprocessed_statement(self, input_statement: Statement) -> Statement:
         """
         Preprocess the input statement.
         """
@@ -58,7 +59,7 @@ class Trainer(object):
             )
             super().__init__(message or default)
 
-    def _generate_export_data(self):
+    def _generate_export_data(self) -> list:
         result = []
         for statement in self.chatbot.storage.filter():
             if statement.in_response_to:
@@ -82,7 +83,7 @@ class ListTrainer(Trainer):
     where the list represents a conversation.
     """
 
-    def train(self, conversation: list):
+    def train(self, conversation: List[str]):
         """
         Train the chat bot based on the provided list of
         statements that represents a single conversation.
@@ -95,7 +96,6 @@ class ListTrainer(Trainer):
         # Run the pipeline in bulk to improve performance
         documents = self.chatbot.tagger.as_nlp_pipeline(conversation)
 
-        # for text in enumerate(conversation):
         for document in tqdm(documents, desc='List Trainer', disable=self.disable_progress):
             statement_search_text = document._.search_index
 
@@ -123,7 +123,7 @@ class ChatterBotCorpusTrainer(Trainer):
     ChatterBot dialog corpus.
     """
 
-    def train(self, *corpus_paths):
+    def train(self, *corpus_paths: Union[str, List[str]]):
         from chatterbot.corpus import load_corpus, list_corpus_files
 
         data_file_paths = []
@@ -178,7 +178,17 @@ class GenericFileTrainer(Trainer):
     or directory of those file types.
     """
 
-    def __init__(self, chatbot, **kwargs):
+    # NOTE: If the value is an integer, this be the
+    # column index instead of the key or header
+    DEFAULT_STATEMENT_TO_HEADER_MAPPING = {
+        'text': 'text',
+        'conversation': 'conversation',
+        'created_at': 'created_at',
+        'persona': 'persona',
+        'tags': 'tags'
+    }
+
+    def __init__(self, chatbot: ChatBot, **kwargs):
         """
         data_path: str The path to the data file or directory.
         field_map: dict A dictionary containing the column name to header mapping.
@@ -187,22 +197,12 @@ class GenericFileTrainer(Trainer):
 
         self.file_extension = None
 
-        # NOTE: If the key is an integer, this be the
-        # column index instead of the key or header
-        DEFAULT_STATEMENT_TO_HEADER_MAPPING = {
-            'text': 'text',
-            'conversation': 'conversation',
-            'created_at': 'created_at',
-            'persona': 'persona',
-            'tags': 'tags'
-        }
-
         self.field_map = kwargs.get(
             'field_map',
-            DEFAULT_STATEMENT_TO_HEADER_MAPPING
+            self.DEFAULT_STATEMENT_TO_HEADER_MAPPING
         )
 
-    def _get_file_list(self, data_path, limit):
+    def _get_file_list(self, data_path: str, limit: Union[int, None]):
         """
         Get a list of files to read from the data set.
         """
@@ -302,6 +302,20 @@ class GenericFileTrainer(Trainer):
                         f'Current mapping: {self.field_map}'
                     )
 
+            response_to_search_index_mapping = {}
+
+            if 'in_response_to' in self.field_map.keys():
+                # Generate the search_in_response_to value for the in_response_to fields
+                response_documents = self.chatbot.tagger.as_nlp_pipeline([
+                    (
+                        row[self.field_map['in_response_to']]
+                    ) for row in data if len(row) > 0 and row[self.field_map['in_response_to']] is not None
+                ])
+
+                # (Process the response values the same way as the text values)
+                for document in response_documents:
+                    response_to_search_index_mapping[document.text] = document._.search_index
+
             for document, context in documents:
                 statement = Statement(
                     text=document.text,
@@ -314,14 +328,19 @@ class GenericFileTrainer(Trainer):
                     statement.created_at = date_parser.parse(context['created_at'])
 
                 statement.search_text = document._.search_index
-                statement.search_in_response_to = previous_statement_search_text
 
                 # Use the in_response_to attribute for the previous statement if
                 # one is defined, otherwise use the last statement which was created
                 if 'in_response_to' in self.field_map.keys():
                     statement.in_response_to = context.get(self.field_map['in_response_to'], None)
+                    statement.search_in_response_to = response_to_search_index_mapping.get(
+                        context.get(self.field_map['in_response_to'], None), ''
+                    )
                 else:
+                    # List-type data such as CSVs with no response specified can use
+                    # the previous statement as the in_response_to value
                     statement.in_response_to = previous_statement_text
+                    statement.search_in_response_to = previous_statement_search_text
 
                 for preprocessor in self.chatbot.preprocessors:
                     statement = preprocessor(statement)
@@ -345,7 +364,6 @@ class GenericFileTrainer(Trainer):
                 )
             )
 
-
 class CsvFileTrainer(GenericFileTrainer):
     """
     .. note::
@@ -358,11 +376,11 @@ class CsvFileTrainer(GenericFileTrainer):
     parameter is set to 'tsv'.
 
     :param str file_extension: The file extension to look for when searching for files (defaults to 'csv').
-    :param str field_map: A dictionary containing the database column name to header mapping.
+    :param dict field_map: A dictionary containing the database column name to header mapping.
                           Values can be either the header name (str) or the column index (int).
     """
 
-    def __init__(self, chatbot, **kwargs):
+    def __init__(self, chatbot: ChatBot, **kwargs):
         super().__init__(chatbot, **kwargs)
 
         self.file_extension = kwargs.get('file_extension', 'csv')
@@ -376,26 +394,26 @@ class JsonFileTrainer(GenericFileTrainer):
     Allow chatbots to be trained with data from a JSON file or
     directory of JSON files.
 
-    :param str field_map: A dictionary containing the database column name to header mapping.
+    :param dict field_map: A dictionary containing the database column name to header mapping.
     """
 
-    def __init__(self, chatbot, **kwargs):
+    DEFAULT_STATEMENT_TO_KEY_MAPPING = {
+        'text': 'text',
+        'conversation': 'conversation',
+        'created_at': 'created_at',
+        'in_response_to': 'in_response_to',
+        'persona': 'persona',
+        'tags': 'tags'
+    }
+
+    def __init__(self, chatbot: ChatBot, **kwargs):
         super().__init__(chatbot, **kwargs)
 
         self.file_extension = 'json'
 
-        DEFAULT_STATEMENT_TO_KEY_MAPPING = {
-            'text': 'text',
-            'conversation': 'conversation',
-            'created_at': 'created_at',
-            'in_response_to': 'in_response_to',
-            'persona': 'persona',
-            'tags': 'tags'
-        }
-
         self.field_map = kwargs.get(
             'field_map',
-            DEFAULT_STATEMENT_TO_KEY_MAPPING
+            self.DEFAULT_STATEMENT_TO_KEY_MAPPING
         )
 
 
@@ -412,7 +430,7 @@ class UbuntuCorpusTrainer(CsvFileTrainer):
     :param str ubuntu_corpus_data_directory: The directory where the Ubuntu corpus data is already located, or where it should be downloaded and extracted.
     """
 
-    def __init__(self, chatbot, **kwargs):
+    def __init__(self, chatbot: ChatBot, **kwargs):
         super().__init__(chatbot, **kwargs)
         home_directory = os.path.expanduser('~')
 
@@ -434,7 +452,7 @@ class UbuntuCorpusTrainer(CsvFileTrainer):
             'persona': 1,
         }
 
-    def is_downloaded(self, file_path):
+    def is_downloaded(self, file_path: str):
         """
         Check if the data file is already downloaded.
         """
@@ -444,7 +462,7 @@ class UbuntuCorpusTrainer(CsvFileTrainer):
 
         return False
 
-    def is_extracted(self, file_path):
+    def is_extracted(self, file_path: str):
         """
         Check if the data file is already extracted.
         """
@@ -454,7 +472,7 @@ class UbuntuCorpusTrainer(CsvFileTrainer):
             return True
         return False
 
-    def download(self, url, show_status=True):
+    def download(self, url: str, show_status=True):
         """
         Download a file from the given url.
         Show a progress indicator for the download status.
@@ -493,7 +511,7 @@ class UbuntuCorpusTrainer(CsvFileTrainer):
             print('Download location: %s' % file_path)
         return file_path
 
-    def extract(self, file_path):
+    def extract(self, file_path: str):
         """
         Extract a tar file at the specified file path.
         """
@@ -533,7 +551,7 @@ class UbuntuCorpusTrainer(CsvFileTrainer):
 
         return True
     
-    def _get_file_list(self, data_path, limit):
+    def _get_file_list(self, data_path: str, limit: Union[int, None]):
         """
         Get a list of files to read from the data set.
         """
@@ -564,7 +582,7 @@ class UbuntuCorpusTrainer(CsvFileTrainer):
 
             yield file_path
 
-    def train(self, data_download_url, limit=None):
+    def train(self, data_download_url: str, limit: Union[int, None] = None):
         """
         :param str data_download_url: The URL to download the Ubuntu dialog corpus from.
         :param int limit: The maximum number of files to train from.

chatterbot/utils.py

@@ -1,11 +1,12 @@
 """
 ChatterBot utility functions
 """
+from typing import Union
 import importlib
 import time
 
 
-def import_module(dotted_path):
+def import_module(dotted_path: str):
     """
     Imports the specified module based on the
     dot notated import path for the module.
@@ -17,7 +18,7 @@ def import_module(dotted_path):
     return getattr(module, module_parts[-1])
 
 
-def initialize_class(data, *args, **kwargs):
+def initialize_class(data: Union[dict, str], *args, **kwargs):
     """
     :param data: A string or dictionary containing a import_path attribute.
     """

{chatterbot-1.2.5.dist-info → chatterbot-1.2.7.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: ChatterBot
-Version: 1.2.5
+Version: 1.2.7
 Summary: ChatterBot is a machine learning, conversational dialog engine
 Author: Gunther Cox
 License-Expression: BSD-3-Clause
@@ -39,19 +39,21 @@ Requires-Dist: tqdm
 Provides-Extra: test
 Requires-Dist: flake8; extra == "test"
 Requires-Dist: coverage; extra == "test"
-Requires-Dist: nose; extra == "test"
 Requires-Dist: sphinx<8.2,>=5.3; extra == "test"
 Requires-Dist: sphinx-sitemap>=2.6.0; extra == "test"
 Requires-Dist: huggingface_hub; extra == "test"
 Provides-Extra: dev
 Requires-Dist: pint>=0.8.1; extra == "dev"
 Requires-Dist: pyyaml<7.0,>=6.0; extra == "dev"
-Requires-Dist: chatterbot-corpus>=1.2.2; extra == "dev"
+Requires-Dist: chatterbot-corpus<1.3.0,>=1.2.2; extra == "dev"
+Requires-Dist: ollama<1.0,>=0.4.7; extra == "dev"
+Requires-Dist: openai; extra == "dev"
 Provides-Extra: redis
-Requires-Dist: redis[hiredis]; extra == "redis"
-Requires-Dist: langchain-redis; extra == "redis"
-Requires-Dist: langchain-huggingface; extra == "redis"
-Requires-Dist: sentence-transformers; extra == "redis"
+Requires-Dist: redis[hiredis]<5.3; extra == "redis"
+Requires-Dist: langchain-redis<=0.2.0; extra == "redis"
+Requires-Dist: langchain-huggingface<=0.1.2; extra == "redis"
+Requires-Dist: accelerate<=1.6.0; extra == "redis"
+Requires-Dist: sentence-transformers<=4.0.2; extra == "redis"
 Provides-Extra: mongodb
 Requires-Dist: pymongo<4.12,>=4.11; extra == "mongodb"
 Dynamic: license-file
@@ -66,10 +68,11 @@ known conversations. The language independent design of ChatterBot allows it
 to be trained to speak any language.
 
 [![Package Version](https://img.shields.io/pypi/v/chatterbot.svg)](https://pypi.python.org/pypi/chatterbot/)
-[![Python 3.9](https://img.shields.io/badge/python-3.9-blue.svg)](https://www.python.org/downloads/release/python-360/)
+[![Python 3.12](https://img.shields.io/badge/python-3.12-blue.svg)](https://www.python.org/downloads/release/python-360/)
 [![Coverage Status](https://img.shields.io/coveralls/gunthercox/ChatterBot.svg)](https://coveralls.io/r/gunthercox/ChatterBot)
-[![Code Climate](https://codeclimate.com/github/gunthercox/ChatterBot/badges/gpa.svg)](https://codeclimate.com/github/gunthercox/ChatterBot)
+[![Follow on Bluesky](https://img.shields.io/badge/🦋%20Bluesky-1185fe)](https://bsky.app/profile/chatterbot.us)
 [![Join the chat at https://gitter.im/chatterbot/Lobby](https://badges.gitter.im/chatterbot/Lobby.svg)](https://gitter.im/chatterbot/Lobby?utm_source=badge&utm_medium=badge&utm_content=badge)
+<!-- [![Code Climate](https://codeclimate.com/github/gunthercox/ChatterBot/badges/gpa.svg)](https://codeclimate.com/github/gunthercox/ChatterBot) -->
 
 An example of typical input would be something like this:
 
@@ -80,7 +83,7 @@ An example of typical input would be something like this:
 
 ## How it works
 
-An untrained instance of ChatterBot starts off with no knowledge of how to communicate. Each time a user enters a statement, the library saves the text that they entered and the text that the statement was in response to. As ChatterBot receives more input the number of responses that it can reply and the accuracy of each response in relation to the input statement increase. The program selects the closest matching response by searching for the closest matching known statement that matches the input, it then returns the most likely response to that statement based on how frequently each response is issued by the people the bot communicates with.
+An untrained instance of ChatterBot starts off with no knowledge of how to communicate. Each time a user enters a statement, the library saves the text that they entered and the text that the statement was in response to. As ChatterBot receives more input the number of responses that it can reply to, and the accuracy of each response in relation to the input statement increases. The program selects the closest matching response by searching for the closest matching known statement that matches the input, it then returns the most likely response to that statement based on how frequently each response is issued by the people the bot communicates with.
 
 # [Documentation](https://docs.chatterbot.us)
 

{chatterbot-1.2.5.dist-info → chatterbot-1.2.7.dist-info}/RECORD

@@ -1,26 +1,27 @@
-chatterbot/__init__.py,sha256=QJV-6PyWrpW0rpSjVn0lKcH3dqb77TlYoU74kv8uVjc,158
+chatterbot/__init__.py,sha256=fIvZMoUZCqkxB9WkmF1UB7t9qwksyGYoO_TMZwUuF0E,158
 chatterbot/__main__.py,sha256=zvH4uxtGlGrP-ht_LkhX29duzjm3hRH800SDCq4YOwg,637
 chatterbot/adapters.py,sha256=LJ_KqLpHKPdYAFpMGK63RVH4weV5X0Zh5uGyan6qdVU,878
-chatterbot/chatterbot.py,sha256=nqxdeTBWdA_LDIEWTMf2gphvpNfd0c9htNwrxa_7pzo,12543
+chatterbot/chatterbot.py,sha256=bzBw0qAiDwA8r2BzgcL4WaWdJWcRkWqHePSGsntPq9U,13493
 chatterbot/comparisons.py,sha256=kYYR5DUipdzr7ok08m8s6r9LBez4GBQICaSmLZcmoiM,6184
 chatterbot/components.py,sha256=ld3Xam8olBClvE5QqcFYggE7Q7tODCFek7BO7lhfyeU,1782
 chatterbot/constants.py,sha256=c_KPQKc82CHX6H3maeyTYqWatx6j-N-8HJhmejoVi60,1875
-chatterbot/conversation.py,sha256=-JshXr4Uvsl8NVeEgm1am2e4UStBN1BXfMQHYkQFvco,3162
-chatterbot/corpus.py,sha256=n1sFU0KF-oRdj7g3nXft7uHOVilwbj_mVZnaeIHgC54,2409
+chatterbot/conversation.py,sha256=uLLm5qa6fzHKNBGelykBEw-RD1BLdu_BoYfZUm4wbzI,3193
+chatterbot/corpus.py,sha256=7TYGLU1JvoewFqIRkmyMPfl9q6TCbIyRZ-7OQFMbTZ4,2437
 chatterbot/exceptions.py,sha256=gqAlckDna6SB53kyqutmCtCqWxia40WBdUOnGVQ2Kbk,163
-chatterbot/filters.py,sha256=vDSDJz2FM10xT6ybs7qJiqy4X5I4gTEfwEnjBGUxZ9g,847
+chatterbot/filters.py,sha256=VeXyVTa6SKmff1Ha6IHuBKEq2Y-UoAP_L9LRmykArzk,855
 chatterbot/languages.py,sha256=XSenfc5FxHk_JWG5gGHsZvjvrPBbCaVCm_OU-BeER_M,32784
+chatterbot/llm.py,sha256=ojIAxuenXvX6ivXXnDfbmDbsp1ZLzWPmwFE-Szd0Yeg,4207
 chatterbot/parsing.py,sha256=vS-w70cMkjq4YEpDOv_pXWhAI6Zj06WYDAcMDhYDj0M,23174
 chatterbot/preprocessors.py,sha256=kqsgnejSj6Z1rr9U2TGHKOp-MMaFWBdNT41EwyhQFls,1389
-chatterbot/response_selection.py,sha256=JpUVuBYrgxhHkDMRHXyWvhluSLxQED5mAhE1-VvJSmg,2970
+chatterbot/response_selection.py,sha256=T0sA3FiCc0qN5fM6co4hzd7tRmbPwq8uJHkYixLMmPw,2920
 chatterbot/search.py,sha256=FTwwON2eKPWqoc5uoKh4AUmuXDCqyfMcMcXB4wijpxg,4910
-chatterbot/tagging.py,sha256=czcI2g18vILujphkjvobRyEewJU8-QjS7QRzY-hCZ4o,2429
-chatterbot/trainers.py,sha256=S_y-Q67hgU7p1A_ixJsR91nW_FniJUsSzbdtAQ8KJQM,19749
-chatterbot/utils.py,sha256=ubPiBapvUvdFVhrDjxqq5IGekUh9qMUJs_dQ605xLAI,2924
+chatterbot/tagging.py,sha256=HwiNrOA1c173H_lze93fgdm_Xu70f7xgTKgnWUAET2s,2592
+chatterbot/trainers.py,sha256=CZezNX68Byg9gg2z-PUZbTc5pqzTzbhgSmqHx7P6Ivg,20973
+chatterbot/utils.py,sha256=cPYwU5fU00HeSD_ErIIKFs8FwKwGYx08Krizhz1Hfas,2972
 chatterbot/vectorstores.py,sha256=-S1NB8PrZzoFIu95n2W7N4UaXuCUpyDUXIGYFebjv08,2056
 chatterbot/ext/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 chatterbot/ext/django_chatterbot/__init__.py,sha256=iWzmBzpAsYwkwi1faxAPFY9L1bbL97RgVXK2uqULIMc,92
-chatterbot/ext/django_chatterbot/abstract_models.py,sha256=skMqOqxIL_xOyfU8ZabtDqzUKTz0YtqGkaylB3TC1JA,3883
+chatterbot/ext/django_chatterbot/abstract_models.py,sha256=U3KzKo1D6ahgmweFYuLoaMF6Vibk_urQuU3F-I8rg8o,3896
 chatterbot/ext/django_chatterbot/admin.py,sha256=jyCJGLRcRoeaoYWZFv-TCivcDUNTE4Li7pmYE8_hYCM,266
 chatterbot/ext/django_chatterbot/apps.py,sha256=YSqF77pD9Pl2-BP6KeQZRr22XhL8gInpHVkVTLtZsUU,464
 chatterbot/ext/django_chatterbot/model_admin.py,sha256=aJVE6u1fquMrvFTm_0aclK6FSAcUtfZcj-RPnXmm6iM,353
@@ -48,22 +49,22 @@ chatterbot/ext/django_chatterbot/migrations/0019_alter_statement_id_alter_tag_id
 chatterbot/ext/django_chatterbot/migrations/0020_alter_statement_conversation_and_more.py,sha256=PpcIvl6sO9jNBxW4UgvFMv_j0eNmUBHire5qo7u-XAg,2133
 chatterbot/ext/django_chatterbot/migrations/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 chatterbot/ext/sqlalchemy_app/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-chatterbot/ext/sqlalchemy_app/models.py,sha256=ZQ-R_5rA-f1agaqYGUQhuuO7zx__BvTDUvJo5R7ZrDY,2492
-chatterbot/logic/__init__.py,sha256=28-5swBCPfSVMl8xB5C8frOKZ2oj28rQfenbd9E4r-4,531
-chatterbot/logic/best_match.py,sha256=8TNW0uZ_Uq-XPfaZUMUZDVH6KzDT65j59xblxQBv-dQ,4820
-chatterbot/logic/logic_adapter.py,sha256=zcYrzyywZ0kT3GsjcMRr69abvswurlNYOPLsUpIwaB8,5144
-chatterbot/logic/mathematical_evaluation.py,sha256=GPDKUwNFajERof2R-MkPGi2jJRP-rKAGm_f0V9JHDHE,2282
-chatterbot/logic/specific_response.py,sha256=akWHkfe0AjzlCUvjs_PbKFNkX4SZhu_tzY45xCRXoo0,2236
-chatterbot/logic/time_adapter.py,sha256=1PT6tWtGauZLRH02-Xlh2LublDpu_3hnCqHBqNGM9yg,2256
-chatterbot/logic/unit_conversion.py,sha256=-ENMLqZqtZx0riUi0guda2oJECST0M7pZG4cSIv3ieM,5898
+chatterbot/ext/sqlalchemy_app/models.py,sha256=UUJ6cXsZRvOqXcMgxSb7n36Bw_wsapP02-HCpdZMozA,2512
+chatterbot/logic/__init__.py,sha256=bqYcX4iPwTKwsL7ey9XN9zK7Z_YrLNKtOojZEpVSdA4,532
+chatterbot/logic/best_match.py,sha256=QttbNGxtUt3FnoHgDo2BOpnerITlDD1hA4LoW2CWO1s,4890
+chatterbot/logic/logic_adapter.py,sha256=vhu2-TtEpoQxfJE9ERu9Zm-eC-KB9KIPJUtagN7hi0U,5067
+chatterbot/logic/mathematical_evaluation.py,sha256=FXBRt_OOWj72bKUip5RIdFIro79kMzy1E9sWARr5Mn8,2322
+chatterbot/logic/specific_response.py,sha256=eNIpcphquPOFqxa77HriO9b0PIkZrmc2JqZ6Em34qe8,2276
+chatterbot/logic/time_adapter.py,sha256=q07kob5EPZElAbIk8kzNrficBYNCnvS5MaZGz5nxBBc,2288
+chatterbot/logic/unit_conversion.py,sha256=CWtAnaSHPBjsKN63rtv6xUXU2JQj2qXCAwzX1xyYnhA,5938
 chatterbot/storage/__init__.py,sha256=ADw0WQe0YKr1UIDQLaxwf0mHDnuKW_CSzgz11K4TM-4,465
-chatterbot/storage/django_storage.py,sha256=BpuVEO4rPOiPu7f7KW1Zyar2LqEXy6I4HgPYhyGP0kE,6305
-chatterbot/storage/mongodb.py,sha256=Ozvdvcjb3LGZxcvbSQGzwP9VloYQbmsa2FaKunFpMyU,7934
-chatterbot/storage/redis.py,sha256=FKROrzZ-7WXZ8ZoK0dKmTDdS45TxL04XOSeu0p3Jrak,12675
-chatterbot/storage/sql_storage.py,sha256=dAMLByFKQgbiTFoBUtKDeqadYRdwVO5fz1OONTcVCH4,13076
-chatterbot/storage/storage_adapter.py,sha256=fvyb-qNiB0HMJ0siVMCWUIY--6d-C47N1_kKZVFZAv4,6110
-chatterbot-1.2.5.dist-info/licenses/LICENSE,sha256=5b04U8mi0wp5gJMYlKi49EalnD9Q2nwY_6UEI_Avgu4,1476
-chatterbot-1.2.5.dist-info/METADATA,sha256=UgfV52vY3Rq4A_8rVZurYhKcU0DeNwply-UBh42aTd0,7049
-chatterbot-1.2.5.dist-info/WHEEL,sha256=CmyFI0kx5cdEMTLiONQRbGQwjIoR1aIYB7eCAQ4KPJ0,91
-chatterbot-1.2.5.dist-info/top_level.txt,sha256=W2TzAbAJ-eBXTIKZZhVlkrh87msJNmBQpyhkrHqjSrE,11
-chatterbot-1.2.5.dist-info/RECORD,,
+chatterbot/storage/django_storage.py,sha256=Mo1shGkABulZA3LS-4ucJSK7X1I49UKgzUGuQHnG52s,6312
+chatterbot/storage/mongodb.py,sha256=XVp7p3tOwjEZ0vCIFjjSuJY--Js090O5HymjU92qp8c,7941
+chatterbot/storage/redis.py,sha256=45rH7lLUK8uTrQt01UGXScayQgEP-aWMV8i8934c_5w,12682
+chatterbot/storage/sql_storage.py,sha256=EMOWr0Pm9_TA44WEhJ4f3gyGblFwbBII16Jeuc5xpVM,13070
+chatterbot/storage/storage_adapter.py,sha256=yOZXxazJeVTRK74ao5PUC0pZPxw84ExuxjsTLT5LBj8,6117
+chatterbot-1.2.7.dist-info/licenses/LICENSE,sha256=5b04U8mi0wp5gJMYlKi49EalnD9Q2nwY_6UEI_Avgu4,1476
+chatterbot-1.2.7.dist-info/METADATA,sha256=i88UIutDqJz1xy4o5KiZKqKu2c9Nfl7bHlZfNKimH8c,7314
+chatterbot-1.2.7.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
+chatterbot-1.2.7.dist-info/top_level.txt,sha256=W2TzAbAJ-eBXTIKZZhVlkrh87msJNmBQpyhkrHqjSrE,11
+chatterbot-1.2.7.dist-info/RECORD,,

{chatterbot-1.2.5.dist-info → chatterbot-1.2.7.dist-info}/WHEEL

@@ -1,5 +1,5 @@
 Wheel-Version: 1.0
-Generator: setuptools (78.1.0)
+Generator: setuptools (80.9.0)
 Root-Is-Purelib: true
 Tag: py3-none-any