跳转到主要内容

​
概述

Function Calling 允许模型调用你定义的函数，实现与外部系统的交互。模型不会直接执行函数，而是返回函数名和参数，由你的代码执行后将结果返回给模型。

​
完整示例

import json
from openai import OpenAI

client = OpenAI(api_key="sk-xxx", base_url="https://crazyrouter.com/v1")

# 1. 定义工具
tools = [
    {
        "type": "function",
        "function": {
            "name": "get_weather",
            "description": "获取指定城市的天气信息",
            "parameters": {
                "type": "object",
                "properties": {
                    "city": {
                        "type": "string",
                        "description": "城市名称，如：北京"
                    },
                    "unit": {
                        "type": "string",
                        "enum": ["celsius", "fahrenheit"],
                        "description": "温度单位"
                    }
                },
                "required": ["city"]
            }
        }
    },
    {
        "type": "function",
        "function": {
            "name": "search_products",
            "description": "搜索商品",
            "parameters": {
                "type": "object",
                "properties": {
                    "query": {"type": "string", "description": "搜索关键词"},
                    "max_price": {"type": "number", "description": "最高价格"}
                },
                "required": ["query"]
            }
        }
    }
]

# 2. 模拟函数实现
def get_weather(city, unit="celsius"):
    return {"city": city, "temperature": 22, "unit": unit, "condition": "晴"}

def search_products(query, max_price=None):
    return [{"name": f"{query} 商品A", "price": 99}, {"name": f"{query} 商品B", "price": 199}]

# 3. 对话循环
messages = [{"role": "user", "content": "北京今天天气怎么样？顺便帮我搜一下雨伞"}]

response = client.chat.completions.create(
    model="gpt-4o",
    messages=messages,
    tools=tools,
    tool_choice="auto"
)

message = response.choices[0].message

# 4. 处理工具调用
if message.tool_calls:
    messages.append(message)

    for tool_call in message.tool_calls:
        func_name = tool_call.function.name
        args = json.loads(tool_call.function.arguments)

        if func_name == "get_weather":
            result = get_weather(**args)
        elif func_name == "search_products":
            result = search_products(**args)

        messages.append({
            "role": "tool",
            "tool_call_id": tool_call.id,
            "content": json.dumps(result, ensure_ascii=False)
        })

    # 5. 获取最终回复
    final = client.chat.completions.create(
        model="gpt-4o",
        messages=messages,
        tools=tools
    )
    print(final.choices[0].message.content)

​
强制调用特定函数

response = client.chat.completions.create(
    model="gpt-4o",
    messages=messages,
    tools=tools,
    tool_choice={"type": "function", "function": {"name": "get_weather"}}
)

​
支持的模型

Function Calling 支持以下模型：
  • gpt-4o、gpt-4o-mini、gpt-4-turbo
  • claude-sonnet-4-20250514、claude-opus-4-20250514
  • gemini-2.5-pro、gemini-2.5-flash
不同模型对 Function Calling 的支持程度不同。GPT-4o 支持并行调用多个函数，部分模型可能仅支持单次调用。