Azure OpenAI Provider¶

Import: from selectools import AzureOpenAIProvider Stability: beta Added in: v0.21.0

AzureOpenAIProvider lets selectools talk to OpenAI models deployed on Azure OpenAI Service. It extends OpenAIProvider and uses the OpenAI SDK's built-in AzureOpenAI client, so you get every feature of the regular OpenAI provider (streaming, tool calling, structured output, multimodal) without having to maintain a separate code path.

from selectools import Agent, AzureOpenAIProvider, tool

@tool()
def get_time() -> str:
    """Return the current time."""
    from datetime import datetime
    return datetime.utcnow().isoformat()

provider = AzureOpenAIProvider(
    azure_endpoint="https://my-resource.openai.azure.com",
    api_key="<your-azure-key>",
    azure_deployment="gpt-4o",  # your Azure deployment name
)

agent = Agent(tools=[get_time], provider=provider)
print(agent.run("What time is it?").content)

Install¶

No new dependencies. Azure support uses the same openai>=1.30.0 package that ships as a core selectools dependency.

pip install selectools  # Azure already supported

Constructor¶

AzureOpenAIProvider(
    azure_endpoint: str | None = None,
    api_key: str | None = None,
    api_version: str = "2024-10-21",
    azure_deployment: str | None = None,
    azure_ad_token: str | None = None,
)

Environment Variables¶

AzureOpenAIProvider() with no arguments works if you set the standard Azure env vars:

export AZURE_OPENAI_ENDPOINT="https://my-resource.openai.azure.com"
export AZURE_OPENAI_API_KEY="..."
export AZURE_OPENAI_DEPLOYMENT="gpt-4o"

provider = AzureOpenAIProvider()  # Reads everything from env

Azure Deployments vs Model IDs¶

In the public OpenAI API you pass model IDs like "gpt-4o". In Azure OpenAI you pass deployment names that you create in the Azure Portal. selectools maps the azure_deployment parameter to the model argument internally, so the rest of your agent code is unchanged:

# Same Agent code, swappable providers
agent = Agent(provider=OpenAIProvider(model="gpt-4o"))           # Public OpenAI
agent = Agent(provider=AzureOpenAIProvider(azure_deployment="gpt-4o"))  # Azure

AAD Token Auth¶

For enterprise deployments using Azure Active Directory:

from azure.identity import DefaultAzureCredential

credential = DefaultAzureCredential()
token = credential.get_token("https://cognitiveservices.azure.com/.default").token

provider = AzureOpenAIProvider(
    azure_endpoint="https://my-resource.openai.azure.com",
    azure_deployment="gpt-4o",
    azure_ad_token=token,
)

Inheritance¶

AzureOpenAIProvider extends OpenAIProvider, so it inherits everything:

• complete() / acomplete()
• stream() / astream()
• Tool calling, structured output, multimodal messages
• Token usage and cost tracking via selectools.pricing

Only __init__ is overridden — to use the AzureOpenAI client class instead of the regular OpenAI one.

Related Examples¶