Build a Simple ChatGPT Bot with Python and OpenAI API in Minutes

The article introduces a beginner-friendly tutorial for building a simple chatbot using Python and the OpenAI API, emphasizing the importance of learning to collaborate with large language models.

First, register at platform.openai.com , create an API key, and add billing information (a $10 credit is usually enough for GPT‑3.5 trial). Save the key securely.

Install the required libraries in a Jupyter Notebook cell: !pip install openai python-dotenv --quiet Import the modules and load environment variables:

import openai
import os
from dotenv import load_dotenv

Create a .env file to store the API key safely:

api_key = "sk-proj-api-key-here"
# Save the key to a .env file
with open(".env", "w") as f:
    f.write(f"OPENAI_API_KEY={api_key}")
print(".env file created.")

Load the key and configure the OpenAI client:

load_dotenv()
openai.api_key = os.getenv("OPENAI_API_KEY")

Define a function that sends a list of messages to the GPT‑3.5‑turbo model and returns the assistant’s reply:

def chat_with_gpt(messages):
    response = openai.chat.completions.create(
        model="gpt-3.5-turbo",
        messages=messages,
        temperature=0.7,
    )
    return response.choices[0].message.content

messages = [
    {"role": "system", "content": "You are a helpful assistant."},
    {"role": "user", "content": "Hello, who are you?"}
]

The temperature parameter (0‑1) controls response randomness; 0.7 offers a good balance.

Run an interactive chat loop that continuously prompts the user, sends input to the model, and prints the assistant’s response until the user types "exit" or "quit":

while True:
    user_input = input("You: ")
    if user_input.lower() in ["exit", "quit"]:
        print("Goodbye!")
        break
    messages.append({"role": "user", "content": user_input})
    reply = chat_with_gpt(messages)
    messages.append({"role": "assistant", "content": reply})
    print(f"Assistant: {reply}")

This loop maintains conversation history, allowing GPT‑3.5 to reference earlier messages for more coherent replies.

By following these steps, you now have a working chatbot and a foundation for more advanced AI development.