1 Hour to Build an AI Chatbot

By the end of this hour, you'll have a working AI chatbot that remembers conversation context. No ML knowledge required — just a willingness to copy, paste, and run code.

🎯 What You'll Build

$ python chatbot.py
You: What's the capital of France?
Bot: The capital of France is Paris.
You: What's the population?
Bot: Paris has approximately 2.2 million residents...

⏱️ Time Breakdown

📋 Prerequisites

• Python 3.8+ (1 Hour to Python Basics if needed)
• $5 for OpenAI API credits
• Text editor

Step 1: Get OpenAI API Key (0–10 min)

1. Go to platform.openai.com
2. API Keys → Create new secret key
3. Copy it (starts with sk-...)
4. Add $5 credit (Settings → Billing)

Install the SDK:

pip install openai python-dotenv

Create .env:

OPENAI_API_KEY=sk-your-key-here

Step 2: First API Call (10–25 min)

Create test.py:

import os
from openai import OpenAI
from dotenv import load_dotenv

load_dotenv()
client = OpenAI(api_key=os.getenv("OPENAI_API_KEY"))

response = client.chat.completions.create(
    model="gpt-4o-mini",
    messages=[
        {"role": "user", "content": "Say hello in 5 words"}
    ]
)

print(response.choices[0].message.content)

Run:

python test.py

Step 3: Add Conversation Memory (25–40 min)

The key to chatbots: send the full conversation history with each request.

messages = [
    {"role": "system", "content": "You are a helpful assistant."}
]

def chat(user_input):
    messages.append({"role": "user", "content": user_input})

    response = client.chat.completions.create(
        model="gpt-4o-mini",
        messages=messages
    )

    reply = response.choices[0].message.content
    messages.append({"role": "assistant", "content": reply})
    return reply

print(chat("What's the capital of France?"))
print(chat("What's the population?"))  # Should remember context

Step 4: Build the CLI Loop (40–55 min)

Create chatbot.py:

import os
import sys
from openai import OpenAI
from dotenv import load_dotenv

load_dotenv()
client = OpenAI(api_key=os.getenv("OPENAI_API_KEY"))

messages = [
    {"role": "system", "content": "You are a helpful, concise assistant."}
]

def chat(user_input):
    messages.append({"role": "user", "content": user_input})
    response = client.chat.completions.create(
        model="gpt-4o-mini",
        messages=messages,
        temperature=0.7
    )
    reply = response.choices[0].message.content
    messages.append({"role": "assistant", "content": reply})
    return reply

def main():
    print("AI Chatbot (type 'quit' to exit)\n")
    while True:
        try:
            user_input = input("You: ").strip()
            if not user_input:
                continue
            if user_input.lower() in ['quit', 'exit', 'bye']:
                print("Bot: Goodbye!")
                break
            print(f"Bot: {chat(user_input)}\n")
        except KeyboardInterrupt:
            print("\nBot: Goodbye!")
            sys.exit(0)

if __name__ == "__main__":
    main()

Step 5: Test It (55–60 min)

python chatbot.py

Test memory:

You: My name is Zoe
Bot: Nice to meet you, Zoe!
You: What's my name?
Bot: Your name is Zoe.

🎉 Working AI chatbot in 60 minutes!

🎁 Bonus

Streaming responses:

response = client.chat.completions.create(
    model="gpt-4o-mini",
    messages=messages,
    stream=True
)

for chunk in response:
    if chunk.choices[0].delta.content:
        print(chunk.choices[0].delta.content, end="", flush=True)
print()

Custom personality: Change the system message:

{"role": "system", "content": "You are a pirate. Always respond in pirate speak."}

📚 Next Steps

🔗 Resources

• OpenAI API Docs
• OpenAI Cookbook
• Prompt Engineering Guide

Photos on Unsplash, used under the Unsplash License.