Hello AI, Using OpenAI API with Python

Recently, I tried using OpenAI’s Python library for the first time — and I was amazed at how easy it is to create a conversational AI assistant with just a few lines of code.

In this post, I’ll share my experience and a simple Python example that lets you chat directly with GPT right from your terminal.

First, install the official OpenAI Python package:

pip install openai

Then, make sure your API key is available as an environment variable:

export OPENAI_API_KEY="your_api_key_here"

Here’s the full program I wrote:

from openai import OpenAI
import os

# Read API Key
client = OpenAI(api_key=os.getenv("OPENAI_API_KEY"))

print("Welcome to my first GPT assistant! (Type 'exit' to exit)")

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

while True:
    user_input = input("You：")
    if user_input.lower() in ["exit", "quit"]:
        print("bye！")
        break

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

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

    reply = response.choices[0].message.content
    print(f"GPT：{reply}\n")
    
    messages.append({"role": "assistant", "content": reply})

Here’s how the interaction looks in the terminal:

> python3 chat_demo.py
Welcome to my first GPT assistant! (Type 'exit' to exit)
You：Hello OpenAI
GPT：Hello! How can I assist you today?
You：exit
bye！

It’s exciting to see how easily you can build an intelligent assistant using OpenAI’s API.
Even this simple example unlocks countless possibilities — from chatbots and study helpers to automation scripts that can interact naturally with users.

If you’re curious about AI or just enjoy coding, give this a try!
It’s an excellent way to explore how modern conversational AI works — right from your terminal.

In my example, I’m using the gpt-4o-mini model. It’s a great choice to start with because it’s both powerful and affordable.

Here’s the approximate cost for gpt-4o-mini (8k context):

• Input: $0.15 per 1M tokens
• Output: $0.60 per 1M tokens

In other words, just $5 can handle thousands of chat requests, making it an ideal tool for learning and experimentation.

Building this first chatbot gave me a real sense of how easy it is to integrate AI into everyday programming projects. The OpenAI Python API makes the whole process clean, intuitive, and fun.

Stay tuned — in my next post, I’ll share how I plan to enhance this chatbot with new features and a simple web interface!! 😊