进击之路 - Alan的个人博客

title: “Understanding OpenAI Function Calling” tags:

AI slug: 324b9f7e date: 2024-08-11 17:24:33 summary: “What function calling is, how the schema-driven tool flow works, and a minimal weather example end-to-end.”

Many “agent” products have launched in China — Tencent’s 元宝/元器, ByteDance’s 豆包, Moonshot’s Kimi+, etc. A key technology behind them is function calling. So what is function calling?
这里我实际使用了下混元和OpenAI的，来梳理下function call怎么玩的。

Function Call

先说概念，顾名思义，即函数调用。

Note: from the API’s perspective, the model doesn’t directly run the function. It selects a function and arguments based on your predefined schema and the user’s input.

So function calling is a form of intent recognition.

Interaction flow

定义工具列表

      tools: [{
        type: "function", function: {
          name: "get_realtime_weather", summary: "获取当前的天气情况", parameters: {
            type: "object", properties: {
              city: {
                type: "string", summary: "城市名称"
              }
            }, required: ["city"], additionalProperties: true,
          }
        }
      }], // 工具选项，当为string类型时，可选参数为"none"/"auto", "none"表示不会使用工具，"auto"表示模型自行选择生成回复或调用工具；当为object类型时，强制模型调用指定的function
      tool_choice: "auto"

In this example, the function requires only a city parameter — and it’s marked as required.

The user asks “What should I wear tomorrow?”. The model infers it’s weather‑related and, since the city is required, prompts for it.
为了给您提供合适的穿衣建议，我需要知道您所在的城市。请问您能告诉我您所在的城市名称吗？（城市名称为必填项）
User replies “北京 (Beijing)”.

The model emits a tool call for get_realtime_weather with arguments.

{
  id: 'call_cqs8e7k2c3m5dtj9a9tg',
  type: 'function',
  function: { name: 'get_realtime_weather', arguments: '{"city":"北京"}' }
}

Your code executes the function and returns the result back to the model.

{
  "role": "tool",
  "content": "北京 天气晴朗，微风，最高气温27摄氏度，最低气温17摄氏度"
}

The model composes a final answer for the user based on the tool result.

{"created":1723369252,"id":"b097e75efe3d328fa0f6ecc1f884e908","model":"hunyuan","version":"202403121316","choices":[{"finish_reason":"stop","message":{"role":"assistant","content":"根据查询到的天气情况，北京明天天气晴朗，微风，最高气温27摄氏度，最低气温17摄氏度。建议您可以穿着长袖衬衫或薄型外套，搭配长裤。如果您对温度比较敏感，可以随身携带一件轻薄的外01,"completion_tokens":50,"total_tokens":151}}

That’s a complete function‑calling round‑trip.

这里贴下完整的message信息

 [
  { role: 'user', content: '我明天应该穿什么？' },
  {
    role: 'assistant',
    content: '为了给您提供合适的穿衣建议，我需要知道您所在的城市。请问您能告诉我您所在的城市名称吗？（城市名称为必填项）'
  },
  { role: 'user', content: '北京' },
  {
    role: 'assistant',
    content: '调用天气查询工具，输入参数为用户所在的城市北京。\n' +
      '\t\n' +
      '\t现在已经获得了用户所在的城市信息，可以使用天气查询工具来获取明天的天气情况。根据用户提供的城市信息和当前日期，可以计算出明天的日期，并查询那天的天气情况。',
    tool_calls: [ [Object] ]
  },
  { role: 'tool', content: '北京 天气晴朗，微风，最高气温27摄氏度，最低气温17摄氏度' },
  {
    role: 'assistant',
    content: '根据查询到的天气情况，明天北京天气晴朗，微风，最高气温27摄氏度，最低气温17摄氏度。建议您可以穿着长袖衬衫或薄型外套，搭配长裤。如果您对温度比较敏感，可以随身携带一件轻薄的外套以防温度变化。'
  }
]

https://static.1991421.cn/2024/2024-08-11-180536.jpeg

Agent

AI platforms support visual agent builders that compose multiple capabilities; function calling is the key for intent recognition and tool invocation.

With function calling, you can integrate and call any tool/function you expose.