openai.error.InvalidRequestError：“type”是 openai 函数调用中的必需属性 -“tools.0”

Question

我正在尝试使用openai的函数调用。但是，它会引发错误。代码如下：

import openai

def fetch_weather_with_openai(location, unit='celsius'):
    """
    Fetch weather using OpenAI's ChatCompletion.create with a simulated function call.

    Args:
    location (str): The location for which weather information is requested.
    unit (str): The unit of temperature (celsius or fahrenheit).

    Returns:
    str: The generated response simulating weather information.
    """

    function_payload = {
        "name": "get_current_weather",
        "description": "Get the current weather in a given location",
        "parameters": {
            "type": "object",
            "properties": {
            "location": {
                "type": "string",
                "description": "The city and state, e.g. San Francisco, CA"
            },
            "unit": {
                "type": "string",
                "enum": ["celsius", "fahrenheit"]
            }
         }
    }
}

    # Define the input message
    messages = [
        {"role": "user", "content": f"What's the weather like in {location}?"}
    ]

    response = openai.ChatCompletion.create(
        model=llm_config['model_name'],
        deployment_id=llm_config['deployment_name'],
        messages=messages,
        tools=[function_payload]
    )

    # Extract and return the response
    return response.choices[0].message['content']

# Example usage
response = fetch_weather_with_openai("Paris, France")
print(response)

错误如下：

File "c:\metatool-tool-desc-gen_reasoning_func_call.py", line 74, in <module>       
    response = fetch_weather_with_openai("Paris, France")
  File "c\:metatool-tool-desc-gen_reasoning_func_call.py", line 63, in fetch_weather_with_openai
    response = openai.ChatCompletion.create(
  File "C:\project\lib\site-packages\openai\api_resources\chat_completion.py", line 25, in create
    return super().create(*args, **kwargs)
  File "C:\project\lib\site-packages\openai\api_resources\abstract\engine_api_resource.py", line 153, in create
    response, _, api_key = requestor.request(
  File "C:\project\lib\site-packages\openai\api_requestor.py", line 298, in request
    resp, got_stream = self._interpret_response(result, stream)
  File "C:\project\lib\site-packages\openai\api_requestor.py", line 700, in _interpret_response
    self._interpret_response_line(
  File "C:\project\lib\site-packages\openai\api_requestor.py", line 763, in _interpret_response_line
    raise self.handle_error_response(
openai.error.InvalidRequestError: 'type' is a required property - 'tools.0'

我也很困惑，有些函数调用使用“工具”作为参数，而在某些源中参数是“函数”。

你能帮我解决这个代码吗？谢谢！

Answer 1

你的做法不正确。下面是修改后的代码。同样使用openai v0版本(openai==0.28.0)

import os

import openai
from dotenv import load_dotenv

load_dotenv()
openai.api_key = os.environ.get('OPENAI_API_KEY')
def fetch_weather_with_openai(location, unit='celsius'):
    """
    Fetch weather using OpenAI's ChatCompletion.create with a simulated function call.

    Args:
    location (str): The location for which weather information is requested.
    unit (str): The unit of temperature (celsius or fahrenheit).

    Returns:
    str: The generated response simulating weather information.
    """

    function_payload = [{"type":"function",
                         "function":{
        "name": "get_current_weather",
        "description": "Get the current weather in a given location",
        "parameters": {
            "type": "object",
            "properties": {
            "location": {
                "type": "string",
                "description": "The city and state, e.g. San Francisco, CA"
            },
            "unit": {
                "type": "string",
                "enum": ["celsius", "fahrenheit"]
            }
         }
    }
}}]

    # Define the input message
    messages = [
        {"role": "user", "content": f"What's the weather like in {location}?"}
    ]

    response = openai.ChatCompletion.create(
        model='gpt-4',
        # deployment_id=llm_config['deployment_name'],
        messages=messages,
        tools=function_payload
    )

    # Extract and return the response
    # print(response)
    return response.choices[0].message['tool_calls'][0]["function"]

# Example usage
response = fetch_weather_with_openai("Paris, France")
print(response)