OpenAI的函数调用示例代码，function_call

OpenAI 支持函数调用（Function Calling）。 通过这个功能，开发者能进一步拓展GPT的能力，比如联网获取实时信息，与第三方应用互动等。

1. OpenAI的function call功能，相当于开放了自定义插件的接口
2. 通过接入外部工具极大的改善了模型幻觉(一本正经的胡说八道)问题
3. 一定程度上缓解了数据安全问题，私有数据可以尽量自行处理。

流程和原理

这个function call功能流程如下（这里以调用python为例，实际上可以是任何语言或者api）：

1. User->ChatGPT. 你需要提供给ChatGPT一些函数，每个函数要写清楚函数的名称(name), 函数的作用(description)和参数(parameters)。并且问ChatGPT一个问题。
2. ChatGPT->User. ChatGPT会判断需不需要调用你提供的函数。如果判断你提供的函数可以解决你的问题，会将你的问题转化为设置好参数的函数。在对话系统的小模型时代，相当于做了个NLU意图分类+text2code。
3. User->ChatGPT. 你根据ChatGPT的给出的函数，自己运行函数，然后把函数运行的结果返回给ChatGPT。
4. ChatGPT->User. ChatGPT根据之前的对话信息和你给的结果，最终将问题会打给你。

看到这里你就会发现整个流程其实非常像一个only-one-job的HuggingGPT，只不过HuggingGPT是调用模型，这里是调用函数。

如果你自己搞一个函数的pipeline，其实就是langchain了。只不过langchain的结构是在函数里与ChatGPT对话来完成任务，而function call是在对话里调用函数，从体感上来说，还是function call更加丝滑一些，langchain哭晕在厕所。

如果再稍微设计一下prompt，让ChatGPT来自己决策完成任务需要使用哪些函数，其实就跟AutoGPT差不多了。

代码示例

1、首先需要拿到openai的key和url，

项目github地址：https://github.com/xing61/xiaoyi-robot

API_SECRET_KEY = "xxxx";   #你在智增增获取的key
BASE_URL = "https://flag.smarttrot.com/v1"  #智增增的base_url

openai.api_key = API_SECRET_KEY
openai.api_base = BASE_URL

# Example dummy function hard coded to return the same weather
# In production, this could be your backend API or an external API
def get_current_weather(location, unit="fahrenheit"):
    """Get the current weather in a given location"""
    weather_info = {
        "location": location,
        "temperature": "72",
        "unit": unit,
        "forecast": ["sunny", "windy"],
    }
    return json.dumps(weather_info)

def run_conversation():
    # Step 1: send the conversation and available functions to GPT
    messages = [{"role": "user", "content": "What's the weather like in Boston?"}]
    functions = [
        {
            "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"]},
                },
                "required": ["location"],
            },
        }
    ]
    response = openai.ChatCompletion.create(
        model="gpt-3.5-turbo-0613",
        messages=messages,
        functions=functions,
        # function_call="auto",  # auto is default, but we'll be explicit
        function_call={"name": "get_current_weather"},  # auto is default, but we'll be explicit
    )
    response_message = response["choices"][0]["message"]

    # Step 2: check if GPT wanted to call a function
    if response_message.get("function_call"):
        # Step 3: call the function
        # Note: the JSON response may not always be valid; be sure to handle errors
        available_functions = {
            "get_current_weather": get_current_weather,
        }  # only one function in this example, but you can have multiple
        function_name = response_message["function_call"]["name"]
        function_to_call = available_functions[function_name]
        function_args = json.loads(response_message["function_call"]["arguments"])
        function_response = function_to_call(
            location=function_args.get("location"),
            unit=function_args.get("unit"),
        )

        # Step 4: send the info on the function call and function response to GPT
        response_message["content"]="Testing"
        messages.append(response_message)  # extend conversation with assistant's reply
        messages.append(
            {
                "role": "function",
                "name": function_name,
                "content": function_response,
            }
        )  # extend conversation with function response
        second_response = openai.ChatCompletion.create(
            model="gpt-3.5-turbo-0613",
            messages=messages,
        )  # get a new response from GPT where it can see the function response
        return second_response

#print(run_conversation())

if __name__ == '__main__':
    run_conversation();