microsoft/semantic-kernel · error · AgentInitializationException

Please provide an Azure OpenAI endpoint

Error message

Please provide an Azure OpenAI endpoint

What it means

After auth is resolved, the factory checks that azure_openai_settings.endpoint is set. An empty/None endpoint makes it impossible to build the AsyncAzureOpenAI client, so AgentInitializationException("Please provide an Azure OpenAI endpoint") is raised.

Source

Thrown at python/semantic_kernel/agents/open_ai/azure_assistant_agent.py:124

            and credential
        ):
            ad_token = get_entra_auth_token(credential, azure_openai_settings.token_endpoint)

        # If we still have no credentials, we can't proceed
        if not azure_openai_settings.api_key and not ad_token and not ad_token_provider and not credential:
            raise AgentInitializationException(
                "Please provide either an api_key, ad_token, ad_token_provider or credential for authentication."
            )

        merged_headers = dict(copy(default_headers)) if default_headers else {}
        if default_headers:
            merged_headers.update(default_headers)
        if APP_INFO:
            merged_headers.update(APP_INFO)
            merged_headers = prepend_semantic_kernel_to_user_agent(merged_headers)

        if not azure_openai_settings.endpoint:
            raise AgentInitializationException("Please provide an Azure OpenAI endpoint")

        if not azure_openai_settings.chat_deployment_name:
            raise AgentInitializationException("Please provide an Azure OpenAI deployment name")

        client = AsyncAzureOpenAI(
            azure_endpoint=str(azure_openai_settings.endpoint),
            api_version=azure_openai_settings.api_version,
            api_key=azure_openai_settings.api_key.get_secret_value() if azure_openai_settings.api_key else None,
            azure_ad_token=ad_token,
            azure_ad_token_provider=ad_token_provider,
            default_headers=merged_headers,
            **kwargs,
        )

        return client, azure_openai_settings.chat_deployment_name

    @staticmethod
    def create_client(

View on GitHub (pinned to c028a0c7dc)

Solutions

1. Set AZURE_OPENAI_ENDPOINT (e.g. https://<resource>.openai.azure.com/) in env or .env, or pass endpoint= explicitly.
2. Confirm env_file_path loads the file containing AZURE_OPENAI_ENDPOINT.
3. Use the Azure endpoint form (not a base_url) when targeting Azure OpenAI.

Example fix

// before
AzureOpenAIAssistantAgent(..., deployment_name=dep, api_key=k)  # no endpoint
# -> Please provide an Azure OpenAI endpoint

// after
AzureOpenAIAssistantAgent(
    ..., deployment_name=dep, api_key=k,
    endpoint="https://myresource.openai.azure.com/",
)

def has_endpoint(settings) -> bool:
    return bool(settings.endpoint)

def has_azure_endpoint(settings) -> bool:
    return getattr(settings, 'endpoint', None) not in (None, "")

When it happens

Trigger: Instantiating the Azure assistant without AZURE_OPENAI_ENDPOINT in the environment/args and without an endpoint= argument, or with base_url configured instead of endpoint (Azure requires the deployment endpoint).

Common situations: Missing AZURE_OPENAI_ENDPOINT env var; using base_url-style config (non-Azure) by mistake; endpoint var typo or in a different .env than env_file_path points to.

Related errors

• Failed to create Azure OpenAI settings: {exc}
• Please provide an Azure OpenAI deployment name
• Please provide either an api_key, ad_token, ad_token_provide
• Please provide an Azure OpenAI endpoint
• Failed to create Anthropic settings.

AI-assisted analysis of microsoft/semantic-kernel@c028a0c7dc (2026-08-13). Data as JSON: /api/errors/9bcff421431a7e67. Report an issue: GitHub.