multi_turn.py

"""This sample demonstrates a multi-turn conversation with the chat completion API.
When using the model for a chat application, you'll need to manage the history of that
conversation and send the latest messages to the model.
"""

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"

# Create a client
client = OpenAI(
    base_url=endpoint,
    api_key=token,
)

# Call the chat completion API
response = client.chat.completions.create(
    messages=[
        {
            "role": "system",
            "content": "You are a helpful assistant.",
        },
        {
            "role": "user",
            "content": "What is the capital of France?",
        },
        {
            "role": "assistant",
            "content": "The capital of France is Paris.",
        },
        {
            "role": "user",
            "content": "What about Spain?",
        },
    ],
    model=model_name,
)

# Print the response
print(response.choices[0].message.content)