Running First OpenAI Api Call

📁 First Things First — Set Up Your File Structure

Before we dive in, let's get organized:

1. In your project root, create a new folder called level1

2. Inside that folder, create a new notebook file called part1.ipynb

Your structure should look like this:

llm_engineering/
└── level1/
    └── part1.ipynb

✅ Make sure your Kernel is pointed to the correct virtual environment before running anything! 🐍

🧩 Step 1 — Import the Necessary Packages

▶️ Create a new code cell and run it:

import os
from dotenv import load_dotenv
from IPython.display import Markdown, display
from openai import OpenAI

⚠️ Common Issue: Kernel Problems

If the cell hangs forever, throws import errors, or simply won't execute, the culprit is usually the Python kernel. Double check the top-right corner of your notebook — it should be pointing to your local .venv virtual environment, not the system Python.

🔑 Step 2 — Load Your Environment Variables

▶️ Create another code cell and run it:

# Load environment variables from .env file
load_dotenv(override=True)
api_key = os.getenv('OPENAI_API_KEY')

# Validate the key
if not api_key:
    print("No API key was found - please head over to the troubleshooting notebook in this folder to identify & fix!")
elif not api_key.startswith("sk-proj-"):
    print("An API key was found, but it doesn't start sk-proj-; please check you're using the right key - see troubleshooting notebook")
elif api_key.strip() != api_key:
    print("An API key was found, but it looks like it might have space or tab characters at the start or end - please remove them - see troubleshooting notebook")
else:
    print("API key found and looks good so far!")

🔍 What's happening under the hood?

1. 📂 Reads your .env file

2. 📥 Loads the environment variables into memory

3. 🔎 Fetches the OPENAI_API_KEY value

4. ✅ Validates the key format and structure

Expected output:

API key found and looks good so far!

🌩️ Step 3 — Your First Cloud LLM Call

Now comes the exciting part — your very first real request to OpenAI! 🎉

Unlike local models like Ollama that run on your machine, this sends a request to OpenAI's cloud-hosted models and gets a response back in real time.

▶️ Create a new code cell and run it:

# Preview: this is all it takes to send a message to OpenAI!
message = "Hello, GPT! This is my first ever message to you! Hi!"
messages = [{"role": "user", "content": message}]
messages

This simply prepares your message in the format OpenAI expects. ✉️

▶️ Now create another code cell and run it:

openai = OpenAI()

response = openai.chat.completions.create(model="gpt-4o-mini", messages=messages)
response.choices[0].message.content

This actually sends the request to OpenAI and prints back the model's reply.

openai = OpenAI()

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

response.choices[0].message.content

Expected Output

You should see a friendly response from GPT printed below the cell — if you do, congratulations! You've just made your first ever LLM API call! 🎊

✅ Special Note

📌 Important Reminders — Keep These in Mind!

These two points are crucial — remember them for all upcoming lessons:

1. 🖥️ Always select your virtual environment as the kernel before running any notebook. You can check this in the top-right corner of your notebook.

2. ▶️ Always create a separate code cell for each step and run it immediately. Don't skip running a cell before moving to the next one — skipping this is one of the most common causes of errors!

💡 Get into the habit of these two practices from the start and you'll save yourself a lot of headaches down the road! 🙌