basic.py

"""This sample demonstrates a basic call to the chat completion API.
It is leveraging your endpoint and key. The call is synchronous."""

import os
from openai import OpenAI

token = os.environ["GITHUB_TOKEN"]
endpoint = "https://models.inference.ai.azure.com"

# Pick one of the Azure OpenAI models from the GitHub Models service
model_name = "gpt-4o-mini"

client = OpenAI(
    base_url=endpoint,
    api_key=token,
)

response = client.chat.completions.create(
    messages=[
        {
            "role": "system",
            "content": "You are a helpful assistant.",
        },
        {
            "role": "user",
            "content": "What is the capital of France?",
        },
    ],
    model=model_name,
    # Optional parameters
    temperature=1.,
    max_tokens=1000,
    top_p=1.    
)

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