How to Intermediate · 3 min read

Azure OpenAI with Microsoft 365 Copilot

Q: Azure OpenAI with Microsoft 365 Copilot

Use the AzureOpenAI client from the openai Python package configured with your Azure endpoint and API key to interact with Microsoft 365 Copilot. Microsoft 365 Copilot leverages Azure OpenAI models like gpt-4o for enterprise productivity, enabling AI-powered assistance within Office apps.

Quick answer

Use the AzureOpenAI client from the openai Python package configured with your Azure endpoint and API key to interact with Microsoft 365 Copilot. Microsoft 365 Copilot leverages Azure OpenAI models like gpt-4o for enterprise productivity, enabling AI-powered assistance within Office apps.

PREREQUISITES

Python 3.8+
Azure OpenAI API key
Azure OpenAI endpoint URL
pip install openai>=1.0

Setup

Install the openai Python package and set environment variables for your Azure OpenAI API key and endpoint. Use the AzureOpenAI client to authenticate.

bash

pip install openai>=1.0

output

Collecting openai
  Downloading openai-1.x.x-py3-none-any.whl (xx kB)
Installing collected packages: openai
Successfully installed openai-1.x.x

Step by step

This example shows how to call Azure OpenAI with the gpt-4o model, which powers Microsoft 365 Copilot features. Replace environment variables with your Azure OpenAI resource details.

python

import os
from openai import AzureOpenAI

client = AzureOpenAI(
    api_key=os.environ["AZURE_OPENAI_API_KEY"],
    azure_endpoint=os.environ["AZURE_OPENAI_ENDPOINT"],
    api_version="2024-02-01"
)

response = client.chat.completions.create(
    model=os.environ["AZURE_OPENAI_DEPLOYMENT"],  # e.g., "gpt-4o"
    messages=[{"role": "user", "content": "Summarize the latest Microsoft 365 Copilot features."}]
)

print("Response:", response.choices[0].message.content)

output

Response: Microsoft 365 Copilot integrates AI-powered assistance directly into Office apps, enabling users to generate content, automate tasks, and analyze data efficiently.

Common variations

Use async calls with asyncio for non-blocking integration.
Switch models by changing the deployment name in model parameter.
Enable streaming responses by adding stream=True to chat.completions.create.

python

import asyncio
from openai import AzureOpenAI

async def main():
    client = AzureOpenAI(
        api_key=os.environ["AZURE_OPENAI_API_KEY"],
        azure_endpoint=os.environ["AZURE_OPENAI_ENDPOINT"],
        api_version="2024-02-01"
    )

    stream = await client.chat.completions.create(
        model=os.environ["AZURE_OPENAI_DEPLOYMENT"],
        messages=[{"role": "user", "content": "Explain Microsoft 365 Copilot."}],
        stream=True
    )

    async for chunk in stream:
        print(chunk.choices[0].delta.content or "", end="", flush=True)

asyncio.run(main())

output

Microsoft 365 Copilot is an AI-powered assistant integrated into Office apps that helps users create, edit, and analyze content more efficiently.

Troubleshooting

If you get authentication errors, verify your AZURE_OPENAI_API_KEY and AZURE_OPENAI_ENDPOINT environment variables are correct.
Ensure your Azure OpenAI deployment name matches the model parameter exactly.
For network issues, check firewall rules and Azure resource permissions.

✅

Key Takeaways

Use the AzureOpenAI client with your Azure endpoint and API key to access Microsoft 365 Copilot models.
Set the deployment name in model to target specific Azure OpenAI models like gpt-4o.
Async and streaming calls improve responsiveness in interactive applications.
Verify environment variables and deployment names to avoid common authentication and configuration errors.

Verified 2026-04 · gpt-4o

Verify ↗