耗时3天整理，一篇文章学会OpenAI大杀器-Function call

耗时3天整理，一篇文章学会OpenAI大杀器-Function call 第1张


1、让ChatGPT帮我买张火车票


想象下，你创建一个人工智能助手，你可以这样对他说：“帮我买北京的火车票，提前一天提醒我”！如果是ChatGPT的话，它必然会无情地拒绝你。


耗时3天整理，一篇文章学会OpenAI大杀器-Function call 第2张


ChatGPT是世界上最强大的模型，不过，它虽然知道你想让它帮你买票，但它却不懂如何买票，它能力的上限就摆在那儿了。好在OpenAI在GPT模型引入了一个强大的功能--函数调用(function call)。


相信有些小伙伴应该已经用过ChatGPT的plugins功能，Plugins的功能有不少是基于function call进行的


今天，我们一起来创建一个获取最新新闻的GPT，给大家展示如何使用function call，用于深入理解函数调用的概念以及它给我们带来的可能性。


2、函数调用(function call)是啥？


函数调用(function call)是OpenAIGPT-4-0613和GPT-3.5 Turbo-0613模型支持的功能，这两个模型经过训练，可以根据用户的提示检测需不需要调用用户提供的函数，并且用一个很规范的结构返回，而不是直接返回常规的文本。


函数调用(function)允许ChatGPT和其他的系统进行信息的交互，让ChatGPT回答他们原本无法回答的问题。例如，我们需要查询实时的天气，这些数据是ChatGPT没有的，所以ChatGPT需要从别的平台获取最新的天气情况。换句话就是说，函数调用，就是提供了一种方式，教AI模型怎么样和外面的系统进行交互。


3、函数调用(function-call)目的是什么？


函数调用，可以用来增强GPT模型的功能，让GPT能做到更多事情。其实还有两种方式可以增强GPT模型的能力。


  • 微调: 提供标注数据进一步训练模型，不过微调需要很多时间和精力准备训练数据。嵌入：构建机器人知识库，通过构建上下文和知识库的内容进行关联，从而让GPT获得更丰富的回答。

函数调用是第三种扩展GPT功能的方式，这种方式和其他两种不一样，它可以让我们和外部的系统进行交互！


4、怎么样使用函数调用？


在有函数调用(funciton-call)时候，我们调用GPT构建AI应用的模式非常简单。主要有几个步骤


1、用户(client)发请求给我们的服务(chat server)


2、我们的服务(chat server)给GPT提示词


3、重复执行



耗时3天整理，一篇文章学会OpenAI大杀器-Function call 第3张


有了函数调用(function-call)，调用的方式就比之前的复杂一些了，具体的步骤为


1、发送用户的提示词以及可以调用的函数


2、GPT模型根据用户的提示词，判断是用普通文本还是函数调用的格式响应


3、如果是函数调用格式，那么Chat Server就会执行这个函数，并且将结果返回给GPT


4、然后模型使用提供的数据，用连贯的文本响应。


耗时3天整理，一篇文章学会OpenAI大杀器-Function call 第4张


5、用API完成函数调用


在调用GPT接口时，我们一般使用的是Completions接口，这个接口发送的是POST请求，发送的数据格式如下图所示


{
  "model": "gpt-3.5-turbo",
  "messages": [
    {
      "role": "user",
      "content": "What's weather like today?"
    }
  ]
}


GPT返回的可能是下面这些内容


{
  "id": "chatcmpl-FWVo3hYwjrpAptzepU46JamvvgBzb",
  "object": "chat.completion",
  "created": 1687983115,
  "model": "gpt-3.5-turbo-0613",
  "choices": [
    {
      "index": 0,
      "message": {
        "role": "assistant",
        "content": "I'm sorry, but I don't have access to real-time information, including current weather conditions or forecasts. To find out the weather for your location today, I recommend using a weather website, app, or a voice-activated assistant like Siri, Google Assistant, or Alexa. Simply ask one of these services for the weather in your area, and they should be able to provide you with up-to-date information."
      },
      "finish_reason": "stop"
    }
  ],
  "usage": {
    "prompt_tokens": 15,
    "completion_tokens": 44,
    "total_tokens": 59
  }
}


在这里，为了记录上下文，我们需要在每个请求上，将整个消息历史记录返回给 API。例如，如果我们想继续讨论之前的问题，那么相应的 JSON 应该将是：


{
  "model": "gpt-3.5-turbo",
  "messages": [
    {
      "role": "user",
      "content": "How many planets does the solar system have?"
    },
    {
      "role": "assistant",
      "content": "I'm sorry, but I don't have access to real-time information, including current weather conditions or forecasts. To find out the weather for your location today, I recommend using a weather website, app, or a voice-activated assistant like Siri, Google Assistant, or Alexa. Simply ask one of these services for the weather in your area, and they should be able to provide you with up-to-date information."
    {
      "role": "user",
      "content": "how do I access these apps?"
    }
  ]
}


在上面的例子中，我们明确知道了，ChatGPT查不了实时信息，接下来，我们会加上function call，让ChatGPT可以查询实时信息。


{
  "model": "gpt-3.5-turbo-0613",
  "messages": [
    {
      "role": "user",
      "content": "How is the weather in NYC?"
    }
  ],
  "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"
        ]
      }
    }
  ]
}


当GPT模型决定调用我们提供的函数，那么我们就会收到下面类似的返回


{
  "id": "chatcmpl-7WWG94C1DCFlAk5xmUwrZ9OOhFnOq",
  "object": "chat.completion",
  "created": 1687984857,
  "model": "gpt-3.5-turbo-0613",
  "choices": [
    {
      "index": 0,
      "message": {
        "role": "assistant",
        "content": null,
        "function_call": {
          "name": "get_current_weather",
          "arguments": "{\n  \"location\": \"New York, NY\"\n}"
        }
      },
      "finish_reason": "function_call"
    }
  ],
  "usage": {
    "prompt_tokens": 81,
    "completion_tokens": 19,
    "total_tokens": 100
  }
}


get_current_weather将会使用返回的参数调用。OpenAI不执行该函数，我们的服务会执行这个函数，并且获取结果后解析返回给OpenAI。


一旦我们检索到天气数据，我们就会使用一种名为 的新的角色将其发送回模型function。例如：


{
    "model":"gpt-3.5-turbo-0613",
    "messages":[
        {
            "role":"user",
            "content":"How is the weather in NYC?"
        },
        {
            "role":"assistant",
            "content":null,
            "function_call":{
                "name":"get_current_weather",
                "arguments":"{\n  \"location\": \"New York, NY\"\n}"
            }
        },
        {
            "role":"function",
            "name":"get_current_weather",
            "content":"Temperature: 57F, Condition: Raining"
        }
    ],
    "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"
                ]
            }
        }
    ]
}


这里注意下，我们将整个消息历史记录传递给了 API，包括原始提示词、模型的函数调用以及代码中执行天气函数的结果，这种方式可以让模型能够理解调用函数的上下文。


最后，模型可能会回复一个格式正确的答案，回答我们最初的问题：


{
  "id": "chatcmpl-7WWQUccvLUfjhbIcuvFrj2MDJVEiN",
  "object": "chat.completion",
  "created": 1687985498,
  "model": "gpt-3.5-turbo-0613",
  "choices": [
    {
      "index": 0,
      "message": {
        "role": "assistant",
        "content": "The weather in New York City is currently raining with a temperature of 57 degrees Fahrenheit."
      },
      "finish_reason": "stop"
    }
  ],
  "usage": {
    "prompt_tokens": 119,
    "completion_tokens": 19,
    "total_tokens": 138
  }
}


以上，就是Function Call在调用过程中交互数据的格式，接下来，我们使用实际的例子，使用python开发function call的简单应用。


5.1 新闻机器人


为了实现这个功能，我们需要OpenAI 的key，key的获取可以在https://platform.openai.com/account/api-k

eys，

获取key之后，我们需要安装一些python依赖包


pip install openai tiktoken


我们需要导入一些依赖库


import openai
import tiktoken
import json
import os
import requests


接下来，将定义几个常量：


  • 指定 GPT 模型。我们将使用gpt-3.5-turbo-16k我们预设的提示词。用于对字符串和消息中的标记进行计数的编码；需要确保我们不超过语言模型的限制。调用的函数的最大数量openai.api_key 从openai平台获取的keyzsxq_cookie 知识星球的cookie

llm_model = "gpt-3.5-turbo-16k"
llm_max_tokens = 15500
llm_system_prompt = "You are an assistant that provides news and headlines to user requests. Always try to get the lastest breaking stories using the available function calls."
encoding_model_messages = "gpt-3.5-turbo-0613"
encoding_model_strings = "cl100k_base"
function_call_limit = 3
openai.api_key = "sk-xxx" # 需要设置
zsxq_cookie="zsxq_access_token=xxx" # 需要设置
news_key = "" # 新闻key


所有 GPT模型都有token限制。如果超过此限制，API 将抛出错误而不是响应我们的请求。因此，我们需要一个函数来计算token的数量。


{
  "id": "chatcmpl-FWVo3hYwjrpAptzepU46JamvvgBzb",
  "object": "chat.completion",
  "created": 1687983115,
  "model": "gpt-3.5-turbo-0613",
  "choices": [
    {
      "index": 0,
      "message": {
        "role": "assistant",
        "content": "I'm sorry, but I don't have access to real-time information, including current weather conditions or forecasts. To find out the weather for your location today, I recommend using a weather website, app, or a voice-activated assistant like Siri, Google Assistant, or Alexa. Simply ask one of these services for the weather in your area, and they should be able to provide you with up-to-date information."
      },
      "finish_reason": "stop"
    }
  ],
  "usage": {
    "prompt_tokens": 15,
    "completion_tokens": 44,
    "total_tokens": 59
  }
}
0


现在我们需要有一个函数来获取新闻，我们可以在https://newsapi.org/获取查询新闻的KEY


{
  "id": "chatcmpl-FWVo3hYwjrpAptzepU46JamvvgBzb",
  "object": "chat.completion",
  "created": 1687983115,
  "model": "gpt-3.5-turbo-0613",
  "choices": [
    {
      "index": 0,
      "message": {
        "role": "assistant",
        "content": "I'm sorry, but I don't have access to real-time information, including current weather conditions or forecasts. To find out the weather for your location today, I recommend using a weather website, app, or a voice-activated assistant like Siri, Google Assistant, or Alexa. Simply ask one of these services for the weather in your area, and they should be able to provide you with up-to-date information."
      },
      "finish_reason": "stop"
    }
  ],
  "usage": {
    "prompt_tokens": 15,
    "completion_tokens": 44,
    "total_tokens": 59
  }
}
1


为了让GPT模型知道我们存在get_top_headlines函数可以调用，我们需要用JSON结构描述我们的函数


{
  "id": "chatcmpl-FWVo3hYwjrpAptzepU46JamvvgBzb",
  "object": "chat.completion",
  "created": 1687983115,
  "model": "gpt-3.5-turbo-0613",
  "choices": [
    {
      "index": 0,
      "message": {
        "role": "assistant",
        "content": "I'm sorry, but I don't have access to real-time information, including current weather conditions or forecasts. To find out the weather for your location today, I recommend using a weather website, app, or a voice-activated assistant like Siri, Google Assistant, or Alexa. Simply ask one of these services for the weather in your area, and they should be able to provide you with up-to-date information."
      },
      "finish_reason": "stop"
    }
  ],
  "usage": {
    "prompt_tokens": 15,
    "completion_tokens": 44,
    "total_tokens": 59
  }
}
2


接下来，我们将定义complete函数，执行和GPT大模型交互的任务，主要步骤为：


  1. 在消息末尾添加系统提示。这个用于添加消息的上下文如果token总数超过模型的限制，则删除旧消息。将请求发送到 GPT API。从列表末尾删除系统消息


{
  "id": "chatcmpl-FWVo3hYwjrpAptzepU46JamvvgBzb",
  "object": "chat.completion",
  "created": 1687983115,
  "model": "gpt-3.5-turbo-0613",
  "choices": [
    {
      "index": 0,
      "message": {
        "role": "assistant",
        "content": "I'm sorry, but I don't have access to real-time information, including current weather conditions or forecasts. To find out the weather for your location today, I recommend using a weather website, app, or a voice-activated assistant like Siri, Google Assistant, or Alexa. Simply ask one of these services for the weather in your area, and they should be able to provide you with up-to-date information."
      },
      "finish_reason": "stop"
    }
  ],
  "usage": {
    "prompt_tokens": 15,
    "completion_tokens": 44,
    "total_tokens": 59
  }
}
3


最后，我们添加一个Run函数，循环接受我们的请求发送给GPT API


{
  "id": "chatcmpl-FWVo3hYwjrpAptzepU46JamvvgBzb",
  "object": "chat.completion",
  "created": 1687983115,
  "model": "gpt-3.5-turbo-0613",
  "choices": [
    {
      "index": 0,
      "message": {
        "role": "assistant",
        "content": "I'm sorry, but I don't have access to real-time information, including current weather conditions or forecasts. To find out the weather for your location today, I recommend using a weather website, app, or a voice-activated assistant like Siri, Google Assistant, or Alexa. Simply ask one of these services for the weather in your area, and they should be able to provide you with up-to-date information."
      },
      "finish_reason": "stop"
    }
  ],
  "usage": {
    "prompt_tokens": 15,
    "completion_tokens": 44,
    "total_tokens": 59
  }
}
4


最后，我们可以运行我们的程序进行测试了，要注意，运行这个python程序的电脑一定要在国外，另外一定要设置相应的key。国内的电脑无法调用GPT模型的API


{
  "id": "chatcmpl-FWVo3hYwjrpAptzepU46JamvvgBzb",
  "object": "chat.completion",
  "created": 1687983115,
  "model": "gpt-3.5-turbo-0613",
  "choices": [
    {
      "index": 0,
      "message": {
        "role": "assistant",
        "content": "I'm sorry, but I don't have access to real-time information, including current weather conditions or forecasts. To find out the weather for your location today, I recommend using a weather website, app, or a voice-activated assistant like Siri, Google Assistant, or Alexa. Simply ask one of these services for the weather in your area, and they should be able to provide you with up-to-date information."
      },
      "finish_reason": "stop"
    }
  ],
  "usage": {
    "prompt_tokens": 15,
    "completion_tokens": 44,
    "total_tokens": 59
  }
}
5

耗时3天整理，一篇文章学会OpenAI大杀器-Function call 第5张


5.2 破局精华贴机器人


在前面，我们已经添加了查询新闻的功能了，在这里，我们再加个简单的功能。让GPT模型帮我们查找知识星球的精华贴。


在前面我们应该都已经知道了，增加函数，我们需要添加一个函数描述，在这里我们只需要在原来的代码基础上添加即可


{
  "id": "chatcmpl-FWVo3hYwjrpAptzepU46JamvvgBzb",
  "object": "chat.completion",
  "created": 1687983115,
  "model": "gpt-3.5-turbo-0613",
  "choices": [
    {
      "index": 0,
      "message": {
        "role": "assistant",
        "content": "I'm sorry, but I don't have access to real-time information, including current weather conditions or forecasts. To find out the weather for your location today, I recommend using a weather website, app, or a voice-activated assistant like Siri, Google Assistant, or Alexa. Simply ask one of these services for the weather in your area, and they should be able to provide you with up-to-date information."
      },
      "finish_reason": "stop"
    }
  ],
  "usage": {
    "prompt_tokens": 15,
    "completion_tokens": 44,
    "total_tokens": 59
  }
}
6


然后，我们再实现我们的get_zsxq_article接口，获取星球的精华文章


{
  "id": "chatcmpl-FWVo3hYwjrpAptzepU46JamvvgBzb",
  "object": "chat.completion",
  "created": 1687983115,
  "model": "gpt-3.5-turbo-0613",
  "choices": [
    {
      "index": 0,
      "message": {
        "role": "assistant",
        "content": "I'm sorry, but I don't have access to real-time information, including current weather conditions or forecasts. To find out the weather for your location today, I recommend using a weather website, app, or a voice-activated assistant like Siri, Google Assistant, or Alexa. Simply ask one of these services for the weather in your area, and they should be able to provide you with up-to-date information."
      },
      "finish_reason": "stop"
    }
  ],
  "usage": {
    "prompt_tokens": 15,
    "completion_tokens": 44,
    "total_tokens": 59
  }
}
7


在这里，我们还有个关键点，要设置get_zsxq_article的cookie,这个步骤也很简单，我们下载一个谷歌浏览器，然后打开知识星球的网页版本，按F12


耗时3天整理，一篇文章学会OpenAI大杀器-Function call 第6张


在弹出右侧的框后，我们在刷新下知识星球的网页，然后按照红框中的指示，找到cookie即可。


耗时3天整理，一篇文章学会OpenAI大杀器-Function call 第7张


在获取cookie,填充到我们的代码后，我们可以运行，看看效果


耗时3天整理，一篇文章学会OpenAI大杀器-Function call 第8张


到这里，我们的实战演示就结束了。


那么，学会了function call，我们还有哪些东西可以做呢？


比如说，做一个简历润色机器人？或者做一个文章归纳小助手？


发挥你们的想象力吧！


文章来自于知乎 “小潘”，作者 “小潘”


耗时3天整理，一篇文章学会OpenAI大杀器-Function call 第9张