Python: Bug: While using AzureChatCompletion FunctionChoiceBehavior.Auto() returns error

[masterzdran]

Describe the bug
While calling chat_completion.get_chat_message_content(...) returns the following error:

 File "C:\root\playground\semantic-kernel\python\.venv\Lib\site-packages\semantic_kernel\connectors\ai\open_ai\services\open_ai_handler.py", line 99, in _send_completion_request    
    raise ServiceResponseException(
semantic_kernel.exceptions.service_exceptions.ServiceResponseException: ("<class 'semantic_kernel.connectors.ai.open_ai.services.azure_chat_completion.AzureChatCompletion'> service failed to complete the prompt", BadRequestError("Error code: 400 - {'error': {'message': 'Unrecognized request argument supplied: parallel_tool_calls', 'type': 'invalid_request_error', 'param': None, 'code': None}}"))

To Reproduce
from MS Learn example: https://learn.microsoft.com/en-us/semantic-kernel/get-started/quick-start-guide?pivots=programming-language-python

I have this code

async def main():
    # Initialize the kernel
    kernel = Kernel()

    # Add Azure OpenAI chat completion
    service_id = "default"
    kernel.add_service(
        AzureChatCompletion(
            service_id=service_id,
        ),
    )

    # Set the logging level for  semantic_kernel.kernel to DEBUG.
    setup_logging()
    logging.getLogger("kernel").setLevel(logging.DEBUG)

    # Add a plugin (the LightsPlugin class is defined below)
    plugin = kernel.add_plugin(parent_directory="./plugins/", plugin_name="LightsPlugin")

    execution_settings = AzureChatPromptExecutionSettings(
            function_choice_behavior=FunctionChoiceBehavior.Auto()
        )

    # Create a history of the conversation
    history = ChatHistory()

    # Initiate a back-and-forth chat
    userInput = None
    while True:
        # Collect user input
        userInput = input("User > ")

        # Terminate the loop if the user says "exit"
        if userInput == "exit":
            break

        # Add user input to the history
        history.add_user_message(userInput)
        chat_completion : AzureChatCompletion = kernel.get_service(type=ChatCompletionClientBase)

        # Get the response from the AI
        result = await chat_completion.get_chat_message_content(
            chat_history=history,
            settings=execution_settings,
            kernel=kernel,
            kernel_arguments=KernelArguments()
        )

        # Print the results
        print("Assistant > " + str(result))

        # Add the message from the agent to the chat history
        history.add_message(result)

# Run the main function
if __name__ == "__main__":
    asyncio.run(main())

Expected behavior
My expectation was to get a response from the "assistant" similar to the c# version.

Screenshots
If applicable, add screenshots to help explain your problem.

Platform

• OS: Windows
• IDE: VS Code
• Language: Python
• Source: Semantic Kernel 1.17.1, Python 3.11.9

Additional context

[moonbox3]

Hi @masterzdran, you'll need to use an api version greater than 2024-09-01-preview (for context see: https://learn.microsoft.com/en-us/azure/ai-services/openai/api-version-deprecation#changes-between-2024-09-01-preview-and-2024-08-01-preview). Since Azure OpenAI's latest GA api version is 2024-10-21 is the latest (newer than our default). I created an issue to handle it on our side, so the default api version will work properly with parallel_tool_calls. #10117

[moonbox3]

Here's a PR to upgrade the API VERSION. Please do try passing in (or configuring your .env file) to use this API version. #10118

Our tests are passing still with this update.

[masterzdran]

@moonbox3

I appreaciate your feedback. I added the 2024-09-01-preview and it has the expected behaviour.

thanks!

[moonbox3]

Closing issue.