Python Notes
HubHistory of Python - Complete Guide 2026Python Applications - Complete Guide 2026Python Features - Complete Guide 2026What is Python? - Complete Guide 2026Why Learn Python? - Complete Guide 2026Your First Python Program – Hello World & Beyond 2026How to Install Python on Windows, Mac & Linux – Complete Guide 2026Install VS Code for Python – Complete Setup Guide with Extensions 2026Python Environment Setup – Virtual Environments, pip & Project Structure 2026Python IDLE – Complete Guide for Beginners 2026Python CommentsPython Data TypesPython Input and OutputPython OperatorsPython SyntaxPython Strings BasicsPython Type CastingPython VariablesBreak, Continue and Pass in PythonElif Statement in PythonFor Loop in PythonIf-Else Statement in PythonIf Statement in PythonNested If in PythonPattern Programs in PythonWhile Loop in PythonDecorators in PythonFunction Arguments in PythonFunctions Basics in PythonGenerators in PythonLambda Functions in PythonRecursive Functions in PythonReturn Statement in PythonScope of Variables in PythonAbstraction in PythonClasses and Objects in PythonConstructors in PythonEncapsulation in PythonInheritance in PythonMagic Methods (Dunder Methods) in PythonMethod Overriding in PythonPolymorphism in PythonPython Comprehensions – List, Dict, Set & GeneratorPython Dictionaries – Key-Value StorePython Dictionary Methods – Complete ReferencePython List Methods – All Built-in MethodsPython Lists – Complete GuidePython Set Methods – Complete ReferencePython Sets – Unordered Unique CollectionsPython Tuples – Immutable SequencesPython Asynchronous Programming with asyncioPython Context ManagersAdvanced Python DecoratorsAdvanced Python GeneratorsPython Iterators - Advanced GuidePython Memory ManagementPython MultiprocessingPython MultithreadingCRUD Operations in Python DatabasesMySQL with Python (mysql-connector-python)ORM Introduction with SQLAlchemyPostgreSQL with Python (psycopg2)SQLite3 with PythonIntroduction to DjangoDjango Models and ORMDjango REST API with DRFDjango ViewsIntroduction to FlaskFlask RoutingFlask Templates with Jinja2Email Automation with PythonPDF Automation with PythonSelenium Web Automation with PythonTask Scheduler with PythonWeb Scraping with PythonData Analysis with PythonData Cleaning with PythonData Visualization ProjectData Visualization with MatplotlibNumPy IntroductionPandas IntroductionStatistical Visualization with SeabornClassification AlgorithmsClustering AlgorithmsIntroduction to Machine LearningMachine Learning Project: Churn PredictionModel Evaluation and SelectionRegression AlgorithmsSave pipeline (includes preprocessing + model)AI Assistant ProjectCalculator ProjectChatbot ProjectExpense Tracker ProjectFace Detection ProjectPassword Generator ProjectWeather App ProjectPython Coding Interview QuestionsPython OOP Interview Questions and AnswersPython Master CheatsheetPython Interview Questions and AnswersPython Best PracticesCommon Python Errors and SolutionsPython Debugging TechniquesPython Learning Resources
Build a rule-based and AI-powered chatbot in Python step-by-step. Create intent detection, pattern matching, conversation management, and integrate with the OpenAI API for intelligent responses.
Build a fully functional chatbot from a simple rule-based system to an AI-powered conversational agent.
Project Overview
What you'll build: A chatbot with pattern matching and optional AI integration
Skills practiced: String processing, OOP, dictionaries, regex, API calls
Estimated time: 4–5 hours
Step 1: Simple Rule-Based Chatbot
Example
# chatbot_v1.py — Rule-based chatbot with pattern matching
import re
import random
from datetime import datetime
# Response database: pattern → list of possible responses
RESPONSES = {
r'\b(hi|hello|hey|howdy|greetings)\b': [
"Hi there! How can I help you today?",
"Hello! Great to see you!",
"Hey! What's on your mind?",
],
r'\b(bye|goodbye|see you|exit|quit)\b': [
"Goodbye! Have a great day!",
"See you later! Take care!",
"Bye! It was nice chatting with you!",
],
r'\b(how are you|how do you do|how\'s it going)\b': [
"I'm doing great, thanks for asking! How about you?",
"Feeling wonderful! Ready to help.",
"I'm fantastic! What can I do for you?",
],
r'\bwhat is your name\b': [
"My name is PyBot! I'm your Python assistant.",
"I'm PyBot, a chatbot built with Python!",
],
r'\bwhat can you do\b': [
"I can answer questions, chat, tell jokes, check the time, and more!",
"I'm here to help! Ask me anything — jokes, time, or just for a chat.",
],
r'\btell me a joke\b': [
"Why don't scientists trust atoms? Because they make up everything!",
"Why did the Python programmer go broke? Because he lost his cache!",
"What do you call a bear with no teeth? A gummy bear!",
"Why was the math book sad? It had too many problems.",
],
r'\bwhat time is it\b': [
lambda: f"The current time is {datetime.now().strftime('%I:%M %p')}.",
],
r'\bwhat is the date today\b': [
lambda: f"Today is {datetime.now().strftime('%A, %B %d, %Y')}.",
],
r'\b(thank you|thanks|thx)\b': [
"You're welcome! Anything else I can help with?",
"Happy to help! Is there anything else?",
"My pleasure! 😊",
],
r'\b(sorry|apologize|my bad)\b': [
"No worries at all! How can I help?",
"It's totally fine! What can I do for you?",
],
r'\bpython\b': [
"Python is an awesome programming language! I'm built with it.",
"Great choice! Python is versatile, readable, and powerful.",
"Python is my favorite language — after all, that's what I'm written in!",
],
r'\b(help|assist|support)\b': [
"Sure! You can ask me about: jokes, time, date, Python, or just chat!",
"I'm here to help! What would you like to know?",
],
}
DEFAULT_RESPONSES = [
"Interesting! Tell me more.",
"I'm not sure about that. Can you rephrase?",
"Hmm, I need to learn more about that!",
"That's a good question! I'm still learning.",
]
def get_response(user_input):
"""Get a chatbot response for user input."""
user_input_lower = user_input.lower().strip()
for pattern, responses in RESPONSES.items():
if re.search(pattern, user_input_lower):
response = random.choice(responses)
# Handle callable responses (for dynamic content)
if callable(response):
return response()
return response
return random.choice(DEFAULT_RESPONSES)
def run_chatbot_v1():
"""Run the basic chatbot."""
print("=" * 50)
print(" 🤖 PyBot — Simple Chatbot")
print(" Type 'bye' to exit")
print("=" * 50)
while True:
user_input = input("\n You: ").strip()
if not user_input:
continue
response = get_response(user_input)
print(f" Bot: {response}")
if re.search(r'\b(bye|goodbye|exit|quit)\b', user_input.lower()):
break
if __name__ == '__main__':
run_chatbot_v1()
Step 2: Intent-Based Chatbot
Example
# chatbot_v2.py — Intent detection with entities
import re
import random
import json
from datetime import datetime
INTENTS = {
'greeting': {
'patterns': [r'\b(hi|hello|hey|howdy)\b', r'^good (morning|afternoon|evening)'],
'responses': ["Hello! 😊 How can I help?", "Hi there! What's up?", "Hey! Great to see you!"],
},
'farewell': {
'patterns': [r'\b(bye|goodbye|see you|cya)\b', r"that's all|i'm done"],
'responses': ["Goodbye! Come back soon! 👋", "See you! Have a great day!", "Bye! Take care! 😊"],
},
'help': {
'patterns': [r'\b(help|assist|support|what can you do)\b'],
'responses': [
"I can help with:\n • Math calculations\n • Current time/date\n • Jokes\n • General chat\n • Python tips!",
],
},
'time': {
'patterns': [r'\b(time|what time|current time|clock)\b'],
'handler': lambda: f"⏰ It's {datetime.now().strftime('%I:%M %p')}",
},
'date': {
'patterns': [r'\b(date|today|what day)\b'],
'handler': lambda: f"📅 Today is {datetime.now().strftime('%A, %B %d, %Y')}",
},
'math': {
'patterns': [r'\d+\s*[\+\-\*\/\^]\s*\d+'],
'handler': 'calculate',
},
'joke': {
'patterns': [r'\b(joke|funny|laugh|humor|make me laugh)\b'],
'responses': [
"Why don't scientists trust atoms? Because they make up everything! 😄",
"Why did Python break up with Java? It wanted someone more dynamic! 🐍",
"How many programmers does it take to change a lightbulb? None — it's a hardware problem! 💡",
"Why was the JavaScript developer sad? Because he didn't know how to 'null' his feelings! 😢",
],
},
'name': {
'patterns': [r'\byour name\b', r'\bwho are you\b', r'\bwhat are you\b'],
'responses': ["I'm PyBot, your Python-powered assistant! 🐍", "My name is PyBot! Made with Python ❤️"],
},
'python_tip': {
'patterns': [r'\b(python tip|tip|learn python|python help)\b'],
'handler': 'python_tip',
},
'thanks': {
'patterns': [r'\b(thanks|thank you|thx|appreciate)\b'],
'responses': ["You're welcome! 😊", "Happy to help!", "Anytime! That's what I'm here for!"],
},
'how_are_you': {
'patterns': [r"how are you|how\'s it going|how do you do|feeling today"],
'responses': ["I'm doing great, thanks! 😄", "Feeling wonderful! Ready to help 🚀", "Excellent! How about you?"],
},
}
PYTHON_TIPS = [
"Use list comprehension: `[x**2 for x in range(10)]` — faster than for loops!",
"f-strings are the fastest way to format strings: `f'Hello, {name}!'`",
"Use `enumerate()` when you need both index and value: `for i, v in enumerate(lst):`",
"The walrus operator `:=` assigns and tests in one line: `if (n := len(lst)) > 10:`",
"Use `zip()` to iterate two lists: `for a, b in zip(list1, list2):`",
"Dictionary comprehension: `{k: v for k, v in items.items() if v > 0}`",
"Use `pathlib.Path` instead of `os.path` for modern path handling!",
"Type hints improve code readability: `def greet(name: str) -> str:`",
]
def calculate(expression):
"""Safely evaluate a math expression."""
try:
expression = expression.replace('^', '**')
allowed = set('0123456789+-*/.(). ')
if all(c in allowed for c in expression):
result = eval(expression)
return f"🔢 {expression} = {result}"
return "❌ Invalid math expression"
except ZeroDivisionError:
return "❌ Cannot divide by zero!"
except Exception:
return "❌ Couldn't calculate that expression"
def get_python_tip():
return f"💡 Python Tip: {random.choice(PYTHON_TIPS)}"
HANDLERS = {
'calculate': calculate,
'python_tip': lambda _: get_python_tip(),
}
class IntentChatbot:
def __init__(self):
self.conversation_history = []
self.context = {}
def detect_intent(self, text):
"""Find the matching intent for input text."""
text_lower = text.lower()
for intent_name, intent_data in INTENTS.items():
for pattern in intent_data.get('patterns', []):
match = re.search(pattern, text_lower)
if match:
return intent_name, match
return None, None
def get_response(self, user_input):
"""Generate a response for user input."""
self.conversation_history.append({'role': 'user', 'content': user_input})
intent, match = self.detect_intent(user_input)
if intent:
intent_data = INTENTS[intent]
# Check for handler
if 'handler' in intent_data:
handler = intent_data['handler']
if callable(handler):
response = handler()
elif isinstance(handler, str) and handler in HANDLERS:
response = HANDLERS[handler](user_input)
else:
response = "I can handle that, but something went wrong."
elif 'responses' in intent_data:
response = random.choice(intent_data['responses'])
else:
response = "I understood that, but I don't have a response!"
else:
# Unknown intent — check for math expression
if re.search(r'\d+\s*[\+\-\*\/\^]\s*\d+', user_input):
response = calculate(user_input)
else:
response = random.choice([
"I'm not sure about that. Try asking about time, jokes, or math!",
"Interesting! Could you rephrase that? I'm still learning.",
"Hmm, I don't quite understand. Type 'help' to see what I can do.",
])
self.conversation_history.append({'role': 'bot', 'content': response})
return response
def run(self):
print("\n" + "=" * 55)
print(" 🤖 PyBot v2 — Intent-Based Chatbot")
print(" Commands: 'help', 'history', 'clear', 'bye'")
print("=" * 55)
while True:
user_input = input("\n You: ").strip()
if not user_input:
continue
if user_input.lower() == 'history':
print("\n 💬 Conversation History:")
for entry in self.conversation_history[-10:]:
role = "You" if entry['role'] == 'user' else "Bot"
print(f" {role}: {entry['content']}")
continue
if user_input.lower() == 'clear':
self.conversation_history = []
print(" ✅ History cleared!")
continue
response = self.get_response(user_input)
print(f" Bot: {response}")
if re.search(r'\b(bye|goodbye|exit)\b', user_input.lower()):
break
Step 3: Context-Aware Chatbot
Example
# chatbot_v3.py — Chatbot with context memory and personality
import random
from datetime import datetime
class ContextualChatbot:
"""Chatbot with conversation context and personality."""
def __init__(self, name="PyBot", personality="friendly"):
self.name = name
self.personality = personality
self.user_name = None
self.context = {}
self.history = []
self.mood = "neutral" # neutral, happy, curious
self.topics_discussed = set()
def _update_mood(self, user_input):
"""Adjust mood based on conversation."""
positive = ['thanks', 'great', 'awesome', 'love', 'amazing', 'wonderful']
negative = ['hate', 'terrible', 'awful', 'bad', 'stupid', 'useless']
if any(w in user_input.lower() for w in positive):
self.mood = 'happy'
elif any(w in user_input.lower() for w in negative):
self.mood = 'empathetic'
elif '?' in user_input:
self.mood = 'curious'
def _get_mood_prefix(self):
mood_prefixes = {
'happy': ["That's wonderful! ", "Great! ", "Awesome! "],
'curious': ["That's a good question! ", "Hmm, interesting! ", "Let me think... "],
'empathetic': ["I understand. ", "I hear you. ", "I'm sorry to hear that. "],
'neutral': ["", "Sure! ", "Of course! "],
}
return random.choice(mood_prefixes.get(self.mood, [""]))
def respond(self, user_input):
"""Generate a contextually aware response."""
self._update_mood(user_input)
self.history.append(('user', user_input, datetime.now()))
lower = user_input.lower()
prefix = self._get_mood_prefix()
# Learn user's name
import re
name_match = re.search(r"my name is ([a-zA-Z]+)|i'm ([a-zA-Z]+)|call me ([a-zA-Z]+)", lower)
if name_match:
name = next(g for g in name_match.groups() if g)
self.user_name = name.title()
response = f"{prefix}Nice to meet you, {self.user_name}! 😊 I'm {self.name}."
elif 'remember' in lower and 'name' in lower:
if self.user_name:
response = f"Of course! Your name is {self.user_name}. How could I forget? 😄"
else:
response = "I don't know your name yet! Tell me — what should I call you?"
elif self.user_name and any(w in lower for w in ['hi', 'hello', 'hey']):
response = f"{prefix}Hey, {self.user_name}! Great to see you again! 👋"
elif 'tell me about yourself' in lower or 'who are you' in lower:
self.topics_discussed.add('intro')
response = (f"I'm {self.name}, a Python-powered chatbot! "
f"I can chat, answer questions, tell jokes, and help with math. "
f"We've talked about: {', '.join(self.topics_discussed) or 'not much yet'}. "
f"What would you like to know?")
elif 'what do you remember' in lower or 'what do you know about me' in lower:
if self.user_name:
response = (f"I know your name is {self.user_name}, "
f"we've had {len(self.history)} exchanges, "
f"and you seem to be in a {self.mood} mood!")
else:
response = "I know we've been chatting, but you haven't told me your name yet!"
elif len(self.history) > 0 and 'what did i say' in lower:
last_msg = self.history[-2][1] if len(self.history) >= 2 else "nothing yet"
response = f"Your last message was: \"{last_msg}\""
else:
# Fall back to intent detection
from chatbot_v2 import IntentChatbot
temp_bot = IntentChatbot()
response = prefix + temp_bot.get_response(user_input)
self.history.append(('bot', response, datetime.now()))
return response
def run(self):
print(f"\n{'='*55}")
print(f" 🤖 {self.name} — Contextual Chatbot")
print(f" I remember your name and track context!")
print(f"{'='*55}")
while True:
greeting = f"\n {self.user_name if self.user_name else 'You'}: "
user_input = input(greeting).strip()
if not user_input:
continue
response = self.respond(user_input)
print(f" {self.name}: {response}")
import re
if re.search(r'\b(bye|goodbye|exit)\b', user_input.lower()):
break
if __name__ == '__main__':
bot = ContextualChatbot(name="PyBot", personality="friendly")
bot.run()
Step 4: OpenAI-Powered Chatbot
Example
# chatbot_ai.py — OpenAI GPT-powered chatbot (requires API key)
# pip install openai
# Set: OPENAI_API_KEY environment variable
import os
from openai import OpenAI
class AIChatbot:
def __init__(self, model="gpt-3.5-turbo", system_prompt=None):
self.client = OpenAI(api_key=os.environ.get("OPENAI_API_KEY"))
self.model = model
self.messages = []
# System prompt defines the bot's personality
system = system_prompt or (
"You are PyBot, a friendly and helpful Python programming assistant. "
"You're knowledgeable about Python, data science, and web development. "
"Keep responses concise and helpful. Use emojis occasionally."
)
self.messages.append({"role": "system", "content": system})
def chat(self, user_message):
"""Send message and get AI response."""
self.messages.append({"role": "user", "content": user_message})
try:
response = self.client.chat.completions.create(
model=self.model,
messages=self.messages,
max_tokens=500,
temperature=0.7,
)
assistant_message = response.choices[0].message.content
self.messages.append({"role": "assistant", "content": assistant_message})
return assistant_message
except Exception as e:
return f"Error communicating with AI: {e}"
def reset_conversation(self):
"""Clear conversation history (keep system prompt)."""
self.messages = [self.messages[0]] # Keep system message
def run(self):
print("\n" + "=" * 55)
print(" 🤖 PyBot AI — Powered by OpenAI")
print(" Commands: 'reset' to clear history, 'bye' to exit")
print("=" * 55)
while True:
user_input = input("\n You: ").strip()
if not user_input:
continue
if user_input.lower() == 'reset':
self.reset_conversation()
print(" ✅ Conversation reset!")
continue
if user_input.lower() in ['bye', 'exit', 'quit']:
print(" Bot: Goodbye! Happy coding! 🐍")
break
print(" Bot: ", end='', flush=True)
response = self.chat(user_input)
print(response)
# Run with fallback to rule-based
if __name__ == '__main__':
api_key = os.environ.get("OPENAI_API_KEY")
if api_key:
print(" Using OpenAI API...")
bot = AIChatbot()
else:
print(" No API key found. Using rule-based chatbot...")
from chatbot_v3 import ContextualChatbot
bot = ContextualChatbot()
bot.run()
Summary
In this project, you built:
- ✅ V1: Pattern-matching chatbot with regex
- ✅ V2: Intent-based chatbot with handlers
- ✅ V3: Context-aware chatbot with memory
- ✅ V4: AI-powered chatbot with OpenAI API
Key skills practiced:
- Regular expressions (
re) - Dictionary-based dispatch
- OOP with state management
- API integration
- Conversation context tracking
*Next Project: Weather App →*
Exam Focus
Revise definitions, diagrams, examples, and short-answer points for Chatbot Project.
Interview Use
Prepare one clear explanation, one practical example, and one common mistake for this Python Master Course topic.
Search Terms
python-master-course, python master course, python, master, course, projects, chatbot, project
Related Python Master Course Topics
Continue learning this concept
ProjectsAI Assistant ProjectBuild a full-featured AI assistant in Python using OpenAI, speech recognition, text-to-speech, and a tkinter GUI. Create a voice-enabled, context-aware assistant with memory, tools, and a polished interface.ProjectsCalculator ProjectBuild a fully-featured command-line calculator in Python step-by-step. Covers basic arithmetic, advanced functions, input validation, error handling, history logging, and a clean OOP-based implementation.ProjectsFace Detection ProjectBuild a real-time face detection application with Python and OpenCV. Detect faces in images, videos, and live webcam streams with Haar cascades, deep learning models, and face recognition features.ProjectsExpense Tracker ProjectBuild a personal expense tracker in Python with CSV storage, categories, monthly summaries, budget alerts, and a data visualization dashboard. Full step-by-step OOP tutorial with pandas and matplotlib.ProjectsPassword Generator ProjectBuild a secure password generator in Python step-by-step. Create random, strong passwords with customizable options, password strength checker, bulk generation, and a tkinter GUI version.ProjectsWeather App ProjectBuild a Python weather application using the OpenWeatherMap API. Fetch real-time weather data, create a 5-day forecast display, build a CLI and tkinter GUI version, with error handling and caching.