chatGPT的Function calling示例

python 复制代码

import json
import os
from openai import OpenAI

client = OpenAI(
    api_key = os.getenv("OPENAI_API_KEY"),
)

# 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"""
    if "tokyo" in location.lower():
        return json.dumps({"location": "Tokyo", "temperature": "10", "unit": unit})
    elif "san francisco" in location.lower():
        return json.dumps({"location": "San Francisco", "temperature": "72", "unit": unit})
    elif "paris" in location.lower():
        return json.dumps({"location": "Paris", "temperature": "22", "unit": unit})
    else:
        return json.dumps({"location": location, "temperature": "unknown"})

python 复制代码

# Step 1: send the conversation and available functions to the model
messages = [{"role": "user", 
             "content": "What's the weather like in San Francisco, Tokyo, and Paris?"}]
tools = [
    {
        "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"]},
                },
                "required": ["location"],
            },
        },
    }
]       

response = client.chat.completions.create(
    model="gpt-3.5-turbo-1106",
    messages=messages,
    tools=tools,
    tool_choice="auto",  # auto is default, but we'll be explicit
)
response_message = response.choices[0].message
tool_calls = response_message.tool_calls

python 复制代码

# Step 2: check if the model wanted to call a function
global second_response 
if tool_calls:
    
    # 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
    messages.append(response_message)  # extend conversation with assistant's reply
    
    # Step 4: send the info for each function call and function response to the model
    for tool_call in tool_calls:
        function_name = tool_call.function.name
        function_to_call = available_functions[function_name] # 确定要调用的函数名
        function_args = json.loads(tool_call.function.arguments) # 从llm的返回对象中，获取调用函数的参数
        function_response = function_to_call(
            location=function_args.get("location"),
            unit=function_args.get("unit"),
        )
        messages.append(
            {
                "tool_call_id": tool_call.id,
                "role": "tool",
                "name": function_name,
                "content": function_response,
            }
        )  # extend conversation with function response

    #再次调用模型，将message对象给大模型
    second_response = client.chat.completions.create(
        model="gpt-3.5-turbo-1106",
        messages=messages,
    )  # get a new response from the model where it can see the function response

查看执行结果：

second_response

复制代码

ChatCompletion(id='chatcmpl-8aJh1gWOluIGMlaGqYkCrcRqCpuM9', choices=[Choice(finish_reason='stop', index=0, message=ChatCompletionMessage(content="Currently, the weather in San Francisco is 72°C, in Tokyo it's 10°C, and in Paris it's 22°C.", role='assistant', function_call=None, tool_calls=None), logprobs=None)], created=1703666199, model='gpt-3.5-turbo-1106', object='chat.completion', system_fingerprint='fp_772e8125bb', usage=CompletionUsage(completion_tokens=29, prompt_tokens=169, total_tokens=198))

返回了一堆

second_response.choices[0].message

复制代码

ChatCompletionMessage(content="Currently, the weather in San Francisco is 72°C, in Tokyo it's 10°C, and in Paris it's 22°C.", role='assistant', function_call=None, tool_calls=None)

second_response.choices[0].message.role

复制代码

'assistant'

second_response.choices[0].message.content

复制代码

"Currently, the weather in San Francisco is 72°C, in Tokyo it's 10°C, and in Paris it's 22°C."

可看到大模型又重新组织了语言，输出给用户

chatGPT的Function calling功能允许用户通过消息和模型进行交互，并根据用户提供的函数调用来获取所需的数据或执行特定的操作。下面是一个完整的例子：

用户发送一条消息给模型，包含问题和请求的函数调用，例如："我需要计算两个数字的和。"
自己的程序接收到消息后，解析函数调用，找到对应的函数，并执行它。在这个例子中，程序会调用一个名为 calculate_sum 的函数，计算两个数字的和。
程序获取到计算结果后，将结果返回给模型。
模型接收到结果后，使用语言模型重新组织语言，生成回复消息，并将消息返回给用户。

整个过程至少需要两次交互：

第一次交互：用户向模型提问，并告知需要调用的函数，例如："我需要计算两个数字的和。"
第二次交互：模型返回给自己的代码调用的函数列表，自己的代码根据函数列表，执行对应的函数，并将结果返回给模型。

在第二次交互中，自己的代码可以根据模型返回的函数列表，选择合适的函数，并将函数所需的参数传递给它。然后再将函数执行的结果返回给模型进行处理。

总结而言，Function calling功能通过将用户的函数调用传递给模型来实现更复杂的交互和操作。自己的代码根据模型返回的函数调用列表，调用相应的函数，并将结果传递给模型，模型根据结果生成回复消息，实现了更灵活和动态的对话交互。