支持私有化部署
AI知识库

53AI知识库

学习大模型的前沿技术与行业应用场景


一文彻底搞懂智能体Agent基于Function Calling的工具调用

发布日期:2025-05-16 21:43:27 浏览次数: 1520 作者:AI大模型应用开发
推荐语

AI智能体通过Function Calling实现高效工具调用和API交互,提升任务执行能力。

核心内容:
1. AI智能体与Function Calling技术介绍
2. Function Calling的优势与应用场景
3. 实际案例:使用qwen-plus查询北京和广州天气的流程详解

杨芳贤
53A创始人/腾讯云(TVP)最具价值专家

前言

AI智能体是指具备一定自主性、能感知环境并通过智能决策执行特定任务的软件或硬件实体。它结合了人工智能技术(如机器学习、自然语言处理、计算机视觉等),能够独立或协作完成目标。基于大语言模型(LLM)的Function Calling可以令智能体实现有效的工具使用和与外部API的交互。

并非所有的LLM模型都支持Function Calling。支持Function Calling的模型(如gpt-4,qwen-plus等)能够检测何时需要调用函数,并输出调用函数的函数名和所需参数的JSON格式结构化数据。

Function Calling提高了输出稳定性,并简化了提示工程的复杂程度。对于不支持Function Calling的模型,可通过ReACT的相对较为复杂的提示词工程,要求模型返回特定格式的响应,以便区分不同的阶段(思考、行动、观察)。

Function Calling主要有两个用途:

  • 获取数据:例如根据关键字从知识库检索内容、通过特定API接口获取业务数据
  • 执行行动:例如通过API接口修改业务状态数据、执行预定业务操作


本文包含如下内容:

  • 详细介绍Function Calling工具调用流程和涉及的交互消息
  • 手搓Agent代码实现Function Calling工具调用

Function Calling工具调用流程和交互消息

我们以查询北京和广州天气为例,LLM采用通义千问qwen-plus。查询天气的流程如下图:


1. 发起查询请求

向LLM发起查询时,messages列表只有一条消息(role为user, content为用户查询内容)。另外,还需要带上tools定义。

tools定义包含如下内容:

  • name: 函数名
  • description: 函数描述
  • parameters: 参数定义


本例中,定义了函数get_weather(location)

我们用curl发起POST请求,body的JSON结构可参考https://platform.openai.com/docs/api-reference/chat/create

#!/bin/bash

export OPENAI_API_BASE="https://dashscope.aliyuncs.com/compatible-mode/v1"
export OPENAI_API_KEY="sk-xxx"# 替换为你的key

curl ${OPENAI_API_BASE}/chat/completions \
-H"Content-Type: application/json" \
-H"Authorization: Bearer $OPENAI_API_KEY" \
-d'{
  "model": "qwen-plus",
  "messages": [
    {
      "role": "user",
      "content": "北京和广州天气怎么样"
    }
  ],
  "tools": [
    {
      "type": "function",
      "function": {
        "name": "get_weather",
        "description": "Get weather",
        "parameters": {
          "type": "object",
          "properties": {
            "location": {
              "type": "string",
              "description": "location"
            }
          },
          "required": ["location"]
        }
      }
    }
  ],
  "tool_choice": "auto"
}'

2. LLM返回tool_calls获取北京天气

LLM经过推理,发现需要调用函数获取北京天气,回复的消息带上tool_calls信息。

本例中,需要调用函数get_weather,参数名为location, 参数值为北京

完整的JSON响应如下:

{
  "choices": [
    {
      "message": {
        "content": "",
        "role": "assistant",
        "tool_calls": [
          {
            "index": 0,
            "id": "call_3ee91e7e0e0b420d811165",
            "type": "function",
            "function": {
              "name": "get_weather",
              "arguments": "{\"location\": \"北京\"}"
            }
          }
        ]
      },
      "finish_reason": "tool_calls",
      "index": 0,
      "logprobs": null
    }
  ],
  "object": "chat.completion",
  "usage": {
    "prompt_tokens": 166,
    "completion_tokens": 17,
    "total_tokens": 183,
    "prompt_tokens_details": {
      "cached_tokens": 0
    }
  },
  "created": 1745131660,
  "system_fingerprint": null,
  "model": "qwen-plus",
  "id": "chatcmpl-7c4fc4c8-92fa-90cc-aaf6-f673d7ab4220"
}

3. 处理函数调用获取北京天气

解析处理LLM的tool_calls获得函数名和参数列表,调用相应的API接口获得结果。

例如:通过http://weather.cma.cn/api/now/54511可获得北京的天气情况。

完整的JSON响应如下:

{
  "msg": "success",
  "code": 0,
  "data": {
    "location": {
      "id": "54511",
      "name": "北京",
      "path": "中国, 北京, 北京"
    },
    "now": {
      "precipitation": 0.0,
      "temperature": 24.3,
      "pressure": 1007.0,
      "humidity": 35.0,
      "windDirection": "西南风",
      "windDirectionDegree": 207.0,
      "windSpeed": 2.7,
      "windScale": "微风"
    },
    "alarm": [],
    "lastUpdate": "2025/04/20 14:25"
  }
}

4. 把上下文信息以及函数调用结果发给LLM

发给LLM的messages列表有3条messages:

  • 第1条role为user,是用户的输入
  • 第2条role为assistant,是LLM的tool_calls响应get_weather('北京')
  • 第3条role为tool,是工具调用get_weather('北京')的结果
#!/bin/bash

export OPENAI_API_BASE="https://dashscope.aliyuncs.com/compatible-mode/v1"
export OPENAI_API_KEY="sk-xxx"# 替换为你的key

curl ${OPENAI_API_BASE}/chat/completions \
-H"Content-Type: application/json" \
-H"Authorization: Bearer $OPENAI_API_KEY" \
-d'{
  "model": "qwen-plus",
  "messages": [
    {
      "role": "user",
      "content": "北京和广州天气怎么样"
    },
    {
      "role": "assistant",
      "tool_calls": [
        {
          "id": "call_3ee91e7e0e0b420d811165",
          "type": "function",
          "function": {
            "name": "get_weather",
            "arguments": "{\"location\": \"北京\"}"
          }
        }
      ]
    },
    {
      "role": "tool",
      "content": "{\"msg\":\"success\",\"code\":0,\"data\":{\"location\":{\"id\":\"54511\",\"name\":\"北京\",\"path\":\"中国, 北京, 北京\"},\"now\":{\"precipitation\":0.0,\"temperature\":24.3,\"pressure\":1007.0,\"humidity\":35.0,\"windDirection\":\"西南风\",\"windDirectionDegree\":207.0,\"windSpeed\":2.7,\"windScale\":\"微风\"},\"alarm\":[],\"lastUpdate\":\"2025/04/20 14:25\"}}",
      "tool_call_id": "call_3ee91e7e0e0b420d811165"
    }
  ],
  "tools": [
    {
      "type": "function",
      "function": {
        "name": "get_weather",
        "description": "Get weather",
        "parameters": {
          "type": "object",
          "properties": {
            "location": {
              "type": "string",
              "description": "location"
            }
          },
          "required": [
            "location"
          ]
        }
      }
    }
  ],
  "tool_choice": "auto"
}'

5. LLM返回tool_calls获取广州天气

LLM经过推理,发现需要调用函数获取广州天气,回复的消息带上tool_calls信息。

本例中,需要调用函数get_weather,参数名为location, 参数值为广州

完整的JSON响应如下:

{
  "choices": [
    {
      "message": {
        "content": "",
        "role": "assistant",
        "tool_calls": [
          {
            "index": 0,
            "id": "call_4a920a1bb9d54f8894c1ac",
            "type": "function",
            "function": {
              "name": "get_weather",
              "arguments": "{\"location\": \"广州\"}"
            }
          }
        ]
      },
      "finish_reason": "tool_calls",
      "index": 0,
      "logprobs": null
    }
  ],
  "object": "chat.completion",
  "usage": {
    "prompt_tokens": 312,
    "completion_tokens": 19,
    "total_tokens": 331,
    "prompt_tokens_details": {
      "cached_tokens": 0
    }
  },
  "created": 1745132731,
  "system_fingerprint": null,
  "model": "qwen-plus",
  "id": "chatcmpl-5e002b5b-7220-927e-9637-554355f80658"
}

6. 处理函数调用获取广州天气

解析处理LLM的tool_calls获得函数名和参数列表,调用相应的API接口获得结果。

例如:通过http://weather.cma.cn/api/now/59287可获得广州的天气情况。

完整的JSON响应如下:

{
  "msg": "success",
  "code": 0,
  "data": {
    "location": {
      "id": "59287",
      "name": "广州",
      "path": "中国, 广东, 广州"
    },
    "now": {
      "precipitation": 0.0,
      "temperature": 30.1,
      "pressure": 1002.0,
      "humidity": 64.0,
      "windDirection": "东南风",
      "windDirectionDegree": 167.0,
      "windSpeed": 2.4,
      "windScale": "微风"
    },
    "alarm": [],
    "lastUpdate": "2025/04/20 14:25"
  }
}

7. 把上下文信息以及函数调用结果发给LLM

发给LLM的messages列表有5条messages:

  • 第1条role为user,是用户的输入
  • 第2条role为assistant,是LLM的tool_calls响应get_weather('北京')
  • 第3条role为tool,是工具调用get_weather('北京')的结果
  • 第4条role为assistant,是LLM的tool_calls响应get_weather('广州')
  • 第5条role为tool,是工具调用get_weather('广州')的结果
#!/bin/bash

export OPENAI_API_BASE="https://dashscope.aliyuncs.com/compatible-mode/v1"
export OPENAI_API_KEY="sk-xxx"# 替换为你的key

curl ${OPENAI_API_BASE}/chat/completions \
-H"Content-Type: application/json" \
-H"Authorization: Bearer $OPENAI_API_KEY" \
-d'{
  "model": "qwen-plus",
  "messages": [
    {
      "role": "user",
      "content": "北京和广州天气怎么样"
    },
    {
      "role": "assistant",
      "tool_calls": [
        {
          "id": "call_3ee91e7e0e0b420d811165",
          "type": "function",
          "function": {
            "name": "get_weather",
            "arguments": "{\"location\": \"北京\"}"
          }
        }
      ]
    },
    {
      "role": "tool",
      "content": "{\"msg\":\"success\",\"code\":0,\"data\":{\"location\":{\"id\":\"54511\",\"name\":\"北京\",\"path\":\"中国, 北京, 北京\"},\"now\":{\"precipitation\":0.0,\"temperature\":24.3,\"pressure\":1007.0,\"humidity\":35.0,\"windDirection\":\"西南风\",\"windDirectionDegree\":207.0,\"windSpeed\":2.7,\"windScale\":\"微风\"},\"alarm\":[],\"lastUpdate\":\"2025/04/20 14:25\"}}",
      "tool_call_id": "call_3ee91e7e0e0b420d811165"
    },
    {
      "role": "assistant",
      "tool_calls": [
        {
          "id": "call_4a920a1bb9d54f8894c1ac",
          "type": "function",
          "function": {
            "name": "get_weather",
            "arguments": "{\"location\": \"广州\"}"
          }
        }
      ]
    },
    {
      "role": "tool",
      "content": "{\"msg\":\"success\",\"code\":0,\"data\":{\"location\":{\"id\":\"59287\",\"name\":\"广州\",\"path\":\"中国, 广东, 广州\"},\"now\":{\"precipitation\":0.0,\"temperature\":30.1,\"pressure\":1002.0,\"humidity\":64.0,\"windDirection\":\"东南风\",\"windDirectionDegree\":167.0,\"windSpeed\":2.4,\"windScale\":\"微风\"},\"alarm\":[],\"lastUpdate\":\"2025/04/20 14:25\"}}",
      "tool_call_id": "call_4a920a1bb9d54f8894c1ac"
    }
  ],
  "tools": [
    {
      "type": "function",
      "function": {
        "name": "get_weather",
        "description": "Get weather",
        "parameters": {
          "type": "object",
          "properties": {
            "location": {
              "type": "string",
              "description": "location"
            }
          },
          "required": [
            "location"
          ]
        }
      }
    }
  ],
  "tool_choice": "auto"
}'

8. LLM生成最终回复

LLM生成最终的回复:

北京的当前天气状况如下:
- 温度:24.3℃
- 湿度:35%
- 风向:西南风
- 风速:微风

广州的当前天气状况如下:
- 温度:30.1℃
- 湿度:64%
- 风向:东南风
- 风速:微风 

以上信息均来自最近更新,希望对你有帮助!

完整的JSON响应如下:

{
  "choices": [
    {
      "message": {
        "content": "北京的当前天气状况如下:\n- 温度:24.3℃\n- 湿度:35%\n- 风向:西南风\n- 风速:微风\n\n广州的当前天气状况如下:\n- 温度:30.1℃\n- 湿度:64%\n- 风向:东南风\n- 风速:微风 \n\n以上信息均来自最近更新,希望对你有帮助!",
        "role": "assistant"
      },
      "finish_reason": "stop",
      "index": 0,
      "logprobs": null
    }
  ],
  "object": "chat.completion",
  "usage": {
    "prompt_tokens": 460,
    "completion_tokens": 105,
    "total_tokens": 565,
    "prompt_tokens_details": {
      "cached_tokens": 0
    }
  },
  "created": 1745133460,
  "system_fingerprint": null,
  "model": "qwen-plus",
  "id": "chatcmpl-fd1edc89-3ddb-9e27-9029-d2be2c81f3c1"
}

手搓Agent代码实现Function Calling工具调用

1. 创建python环境

uv init agent
cd agent
uv venv
.venv\Scripts\activate

uv add openai requests python-dotenv

2. 设置API Key

创建.env,.env内容如下(注意修改OPENAI_API_KEY为您的key)

OPENAI_API_KEY=your_api_key_here
OPENAI_BASE_URL=https://dashscope.aliyuncs.com/compatible-mode/v1

把.env添加到.gitignore

3. 实现Agent代码

基于openai sdk实现agent的主体代码逻辑是:在允许的迭代次数范围内,循环处理,发起chat completions直至没有tool_calls, 迭代结束,输出结果。

伪代码:

maxIter = 5 # 最大迭代次数
for iterSeq in range(1, maxIter+1):
    构造chat completion请求(带tools列表和tool_choice)
        迭代次数达到最大值,tool_choice设置为none(不再调用工具)
        否则tool_choice设置为auto(根据需要调用工具)
    获取chat completion结果
    如果chat completion结果带有tool_calls
        解析并调用相应函数
        添加消息到消息列表,继续迭代
    否则,表明无需调用工具,迭代结束,输出结果

完整的main.py代码如下:

import json
import os
import requests
import urllib.parse
from typing import Iterable
from openai import OpenAI
from openai.types.chat.chat_completion_message_param import ChatCompletionMessageParam
from openai.types.chat.chat_completion_message_tool_call import (
    ChatCompletionMessageToolCall,
)
from openai.types.chat.chat_completion_user_message_param import (
    ChatCompletionUserMessageParam,
)
from openai.types.chat.chat_completion_tool_message_param import (
    ChatCompletionToolMessageParam,
)
from openai.types.chat.chat_completion_assistant_message_param import (
    ChatCompletionAssistantMessageParam,
)

# 加载环境变量
from dotenv import load_dotenv
load_dotenv()

api_key = os.getenv("OPENAI_API_KEY")
base_url = os.getenv("OPENAI_API_BASE")
model = "qwen-plus"
client = OpenAI(api_key=api_key, base_url=base_url)

# 工具定义
tools = [
    {
        "type": "function",
        "function": {
            "name": "get_weather",
            "description": "Get weather",
            "parameters": {
                "type": "object",
                "properties": {
                    "location": {"type": "string", "description": "location"}
                },
                "required": ["location"],
            },
        },
    }
]

# 实现获取天气
def get_weather(location: str) -> str:
    url = "http://weather.cma.cn/api/autocomplete?q=" + urllib.parse.quote(location)
    response = requests.get(url)
    data = response.json()
    if data["code"] != 0:
        return "没找到该位置的信息"
    location_code = ""
    for item in data["data"]:
        str_array = item.split("|")
        if (
            str_array[1] == location
            or str_array[1] + "市" == location
            or str_array[2] == location
        ):
            location_code = str_array[0]
            break
    if location_code == "":
        return "没找到该位置的信息"
    url = f"http://weather.cma.cn/api/now/{location_code}"
    return requests.get(url).text

# 实现工具调用
def invoke_tool(
    tool_call: ChatCompletionMessageToolCall,
) -> ChatCompletionToolMessageParam:
    result = ChatCompletionToolMessageParam(role="tool", tool_call_id=tool_call.id)
    if tool_call.function.name == "get_weather":
        args = json.loads(tool_call.function.arguments)
        result["content"] = get_weather(args["location"])
    else:
        result["content"] = "函数未定义"
    return result

def main():
    query = "北京和广州天气怎么样"
    messages: Iterable[ChatCompletionMessageParam] = list()
    messages.append(ChatCompletionUserMessageParam(role="user", content=query))
    maxIter = 5 # 最大迭代次数
    for iterSeq in range(1, maxIter+1):
        print(f">> iterSeq:{iterSeq}")
        print(f">>> messages: {messages}")
        # 当迭代次数达到最大值,不再调用工具
        toolChoice = "auto" if iterSeq < maxIter else "none"
        # 向LLM发起请求
        chat_completion = client.chat.completions.create(
            messages=messages,
            model=model,
            tools=tools,
            tool_choice=toolChoice
        )
        tool_calls = chat_completion.choices[0].message.tool_calls
        content = chat_completion.choices[0].message.content
        if isinstance(tool_calls, list):
            # LLM的响应信息有tool_calls信息
            messages.append(
                ChatCompletionAssistantMessageParam(
                    role="assistant", tool_calls=tool_calls, content=""
                )
            )
            for tool_call in tool_calls:
                print(f">>> tool_call: {tool_call}")
                result = invoke_tool(tool_call)
                print(f">>> tool_call result: {result}")
                messages.append(result)
        else:
            # LLM的响应信息没有tool_calls信息,迭代结束,获取响应文本
            print(f">>> final result: \n{content}")
            return
main()

运行代码:uv run .\main.py

输出日志如下:

>> iterSeq:1
>>> messages: [{'role': 'user', 'content': '北京和广州天气怎么样'}]
>>> tool_call: ChatCompletionMessageToolCall(id='call_db29421754a8447590d99d', function=Function(arguments='{"location": "北京"}', name='get_weather'), type='function', index=0)
>>> tool_call result: {'role': 'tool', 'tool_call_id': 'call_db29421754a8447590d99d', 'content': '{"msg":"success","code":0,"data":{"location":{"id":"54511","name":"北京","path":"中国, 北京, 北京"},"now":{"precipitation":0.0,"temperature":24.5,"pressure":1006.0,"humidity":34.0,"windDirection":"西南风","windDirectionDegree":191.0,"windSpeed":2.8,"windScale":"微风"},"alarm":[],"lastUpdate":"2025/04/20 15:35"}}'}
>> iterSeq:2
>>> messages: [{'role': 'user', 'content': '北京和广州天气怎么样'}, {'role': 'assistant', 'tool_calls': [ChatCompletionMessageToolCall(id='call_db29421754a8447590d99d', function=Function(arguments='{"location": "北京"}', name='get_weather'), type='function', index=0)], 'content': ''}, {'role': 'tool', 'tool_call_id': 'call_db29421754a8447590d99d', 'content': '{"msg":"success","code":0,"data":{"location":{"id":"54511","name":"北京","path":"中国, 北京, 北京"},"now":{"precipitation":0.0,"temperature":24.5,"pressure":1006.0,"humidity":34.0,"windDirection":"西南风","windDirectionDegree":191.0,"windSpeed":2.8,"windScale":"微风"},"alarm":[],"lastUpdate":"2025/04/20 15:35"}}'}]
>>> tool_call: ChatCompletionMessageToolCall(id='call_ae1c03437392444c869cbf', function=Function(arguments='{"location": "广州"}', name='get_weather'), type='function', index=0)
>>> tool_call result: {'role': 'tool', 'tool_call_id': 'call_ae1c03437392444c869cbf', 'content': '{"msg":"success","code":0,"data":{"location":{"id":"59287","name":"广州","path":"中国, 广东, 广州"},"now":{"precipitation":0.0,"temperature":30.4,"pressure":1001.0,"humidity":64.0,"windDirection":"东南风","windDirectionDegree":165.0,"windSpeed":2.2,"windScale":"微风"},"alarm":[],"lastUpdate":"2025/04/20 15:35"}}'}
>> iterSeq:3
>>> messages: [{'role': 'user', 'content': '北京和广州天气怎么样'}, {'role': 'assistant', 'tool_calls': [ChatCompletionMessageToolCall(id='call_db29421754a8447590d99d', function=Function(arguments='{"location": "北京"}', name='get_weather'), type='function', index=0)], 'content': ''}, {'role': 'tool', 'tool_call_id': 'call_db29421754a8447590d99d', 'content': '{"msg":"success","code":0,"data":{"location":{"id":"54511","name":"北京","path":"中国, 北京, 北京"},"now":{"precipitation":0.0,"temperature":24.5,"pressure":1006.0,"humidity":34.0,"windDirection":"西南风","windDirectionDegree":191.0,"windSpeed":2.8,"windScale":"微风"},"alarm":[],"lastUpdate":"2025/04/20 15:35"}}'}, {'role': 'assistant', 'tool_calls': [ChatCompletionMessageToolCall(id='call_ae1c03437392444c869cbf', function=Function(arguments='{"location": "广州"}', name='get_weather'), type='function', index=0)], 'content': ''}, {'role': 'tool', 'tool_call_id': 'call_ae1c03437392444c869cbf', 'content': '{"msg":"success","code":0,"data":{"location":{"id":"59287","name":"广州","path":"中国, 广东, 广州"},"now":{"precipitation":0.0,"temperature":30.4,"pressure":1001.0,"humidity":64.0,"windDirection":"东南风","windDirectionDegree":165.0,"windSpeed":2.2,"windScale":"微风"},"alarm":[],"lastUpdate":"2025/04/20 15:35"}}'}]
>>> final result: 
北京的当前天气状况如下:
- 温度:24.5°C
- 湿度:34%
- 风向:西南风
- 风速:微风 (2.8 m/s)
- 最后更新时间:2025/04/20 15:35

广州的当前天气状况如下:
- 温度:30.4°C
- 湿度:64%
- 风向:东南风
- 风速:微风 (2.2 m/s)
- 最后更新时间:2025/04/20 15:35

END


如果您觉得本文对您有帮助,欢迎关注、点赞、转发。
谢谢您的鼓励和支持。

参考资料

  • https://platform.openai.com/docs/guides/function-calling
  • https://platform.openai.com/docs/api-reference/chat/create

往期精彩

53AI,企业落地大模型首选服务商

产品:场景落地咨询+大模型应用平台+行业解决方案

承诺:免费场景POC验证,效果验证后签署服务协议。零风险落地应用大模型,已交付160+中大型企业

联系我们

售前咨询
186 6662 7370
预约演示
185 8882 0121

微信扫码

添加专属顾问

回到顶部

加载中...

扫码咨询