Function Calling Patterns in Azure OpenAI

Function calling enables LLMs to interact with external systems by generating structured function invocations. Azure OpenAI’s implementation provides reliable, typed interactions between natural language and code.

Defining Functions

Functions are defined as JSON schemas that describe parameters and their types.

from openai import AzureOpenAI
import json

client = AzureOpenAI(
    api_key=os.environ["AZURE_OPENAI_KEY"],
    api_version="2024-08-01-preview",
    azure_endpoint=os.environ["AZURE_OPENAI_ENDPOINT"]
)

tools = [
    {
        "type": "function",
        "function": {
            "name": "get_weather",
            "description": "Get current weather for a location",
            "parameters": {
                "type": "object",
                "properties": {
                    "location": {
                        "type": "string",
                        "description": "City name, e.g., 'Seattle, WA'"
                    },
                    "unit": {
                        "type": "string",
                        "enum": ["celsius", "fahrenheit"],
                        "description": "Temperature unit"
                    }
                },
                "required": ["location"]
            }
        }
    },
    {
        "type": "function",
        "function": {
            "name": "search_products",
            "description": "Search product catalog",
            "parameters": {
                "type": "object",
                "properties": {
                    "query": {"type": "string", "description": "Search terms"},
                    "category": {"type": "string", "description": "Product category"},
                    "max_price": {"type": "number", "description": "Maximum price filter"}
                },
                "required": ["query"]
            }
        }
    }
]

Handling Function Calls

def process_with_functions(user_message: str):
    messages = [{"role": "user", "content": user_message}]

    response = client.chat.completions.create(
        model="gpt-4o",
        messages=messages,
        tools=tools,
        tool_choice="auto"
    )

    message = response.choices[0].message

    if message.tool_calls:
        # Process each function call
        for tool_call in message.tool_calls:
            function_name = tool_call.function.name
            arguments = json.loads(tool_call.function.arguments)

            # Execute the function
            result = execute_function(function_name, arguments)

            # Add results to conversation
            messages.append(message)
            messages.append({
                "role": "tool",
                "tool_call_id": tool_call.id,
                "content": json.dumps(result)
            })

        # Get final response with function results
        final_response = client.chat.completions.create(
            model="gpt-4o",
            messages=messages
        )
        return final_response.choices[0].message.content

    return message.content

Well-designed function schemas and clear descriptions ensure the model calls the right functions with correct parameters.