​
1. Use Cases

The Function Calling feature enables the model to call external tools to enhance its capabilities. This capability can leverage external tools through the large model, such as searching for external knowledge, checking itineraries, or using specific domain tools, effectively addressing issues like hallucination and Knowledge Timeliness.

​
2. Usage

​
2.1 Adding tools Request Parameters via REST API

Add in the request body:

"tools": [
    {
        'type': 'function',
        'function': {
            'name': '对应到实际执行的函数名称',
            'description': '此处是函数相关描述',
            'parameters': {
                '_comments': '此处是函数参数相关描述'
            },
        }
    },
    {
        '_comments': '其他函数相关说明'
    }
]

For example, complete payload information:

payload = {
    "model": "deepseek-ai/DeepSeek-V2.5",
    "messages": [
        {
            "role": "user",
            "content": "中国大模型行业2025年将会迎来哪些机遇和挑战"
        }
    ],
    "tools": [
    {
        'type': 'function',
        'function': {
            'name': '对应到实际执行的函数名称',
            'description': '此处是函数相关描述',
            'parameters': {
                '_comments': '此处是函数参数相关描述'
            },
        }
    },
    {
        '_comments': '其他函数相关说明'
    }
    ]
    '_comments': '其他函数列表'
}

​
2.2 Request via OpenAI Library

This feature is compatible with OpenAI. When using the OpenAI library, add tools=[corresponding tools] to the corresponding request parameters. For example：

response = client.chat.completions.create(
    model="deepseek-ai/DeepSeek-V2.5",
    messages = messages,
    tools=[
        {
            'type': 'function',
            'function': {
                'name': '对应到实际执行的函数名称',
                'description': '此处是函数相关描述',
                'parameters': {
                    // 此处是函数参数相关描述
                },
            }
        },
        {
            // 其他函数相关说明
        }
    ]
    // chat.completions 其他参数
)

​
3. List of Supported Models

The current list of supported models includes:

  • Deepseek Series：

    • deepseek-ai/DeepSeek-V2.5
    • deepseek-ai/DeepSeek-V3

  • internlm Series：

    • internlm/internlm2_5-20b-chat
    • internlm/internlm2_5-7b-chat
    • Pro/internlm/internlm2_5-7b-chat

  • Qwen Series：

    • Qwen/Qwen2.5-72B-Instruct
    • Qwen/Qwen2.5-32B-Instruct
    • Qwen/Qwen2.5-14B-Instruct
    • Qwen/Qwen2.5-7B-Instruct
    • Pro/Qwen/Qwen2.5-7B-Instruct

  • GLM Series：

    • THUDM/glm-4-9b-chat
    • Pro/THUDM/glm-4-9b-chat
Note: The list of supported models is constantly being adjusted. Please refer to this document for the latest list of supported models.

​
4. Usage Examples

​
4.1. Example 1: Extending Large Language Model’s Numerical Computation Capability via Function Calling

his code inputs 4 functions: addition, subtraction, comparison, and counting duplicate letters in a string. It demonstrates how to use function calling to address execution issues in domains where token prediction is not strong for large language models.


from openai import OpenAI

client = OpenAI(
    api_key="您的 APIKEY", # 从https://cloud.siliconflow.cn/account/ak获取
    base_url="https://api.siliconflow.cn/v1"
)

def add(a: float, b: float):
    return a + b

def mul(a: float, b: float):
    return a * b

def compare(a: float, b: float):
    if a > b:
        return f'{a} is greater than {b}'
    elif a < b:
        return f'{b} is greater than {a}'
    else:
        return f'{a} is equal to {b}'

def count_letter_in_string(a: str, b: str):
    string = a.lower()
    letter = b.lower()
    
    count = string.count(letter)
    return(f"The letter '{letter}' appears {count} times in the string.")


tools = [
{
    'type': 'function',
    'function': {
        'name': 'add',
        'description': 'Compute the sum of two numbers',
        'parameters': {
            'type': 'object',
            'properties': {
                'a': {
                    'type': 'int',
                    'description': 'A number',
                },
                'b': {
                    'type': 'int',
                    'description': 'A number',
                },
            },
            'required': ['a', 'b'],
        },
    }
}, 
{
    'type': 'function',
    'function': {
        'name': 'mul',
        'description': 'Calculate the product of two numbers',
        'parameters': {
            'type': 'object',
            'properties': {
                'a': {
                    'type': 'int',
                    'description': 'A number',
                },
                'b': {
                    'type': 'int',
                    'description': 'A number',
                },
            },
            'required': ['a', 'b'],
        },
    }
},
{
    'type': 'function',
    'function': {
        'name': 'count_letter_in_string',
        'description': 'Count letter number in a string',
        'parameters': {
            'type': 'object',
            'properties': {
                'a': {
                    'type': 'str',
                    'description': 'source string',
                },
                'b': {
                    'type': 'str',
                    'description': 'letter',
                },
            },
            'required': ['a', 'b'],
        },
    }
},
{
    'type': 'function',
    'function': {
        'name': 'compare',
        'description': 'Compare two number, which one is bigger',
        'parameters': {
            'type': 'object',
            'properties': {
                'a': {
                    'type': 'float',
                    'description': 'A number',
                },
                'b': {
                    'type': 'float',
                    'description': 'A number',
                },
            },
            'required': ['a', 'b'],
        },
    }
}
]

def function_call_playground(prompt):
    messages = [{'role': 'user', 'content': prompt}]
    response = client.chat.completions.create(
        model="deepseek-ai/DeepSeek-V2.5",
        messages = messages,
        temperature=0.01,
        top_p=0.95,
        stream=False,
        tools=tools)

    # print(response)
    func1_name = response.choices[0].message.tool_calls[0].function.name
    func1_args = response.choices[0].message.tool_calls[0].function.arguments
    func1_out = eval(f'{func1_name}(**{func1_args})')
    # print(func1_out)

    messages.append(response.choices[0].message)
    messages.append({
        'role': 'tool',
        'content': f'{func1_out}',
        'tool_call_id': response.choices[0].message.tool_calls[0].id
    })
    # print(messages)
    response = client.chat.completions.create(
        model="deepseek-ai/DeepSeek-V2.5",
        messages=messages,
        temperature=0.01,
        top_p=0.95,
        stream=False,
        tools=tools)
    return response.choices[0].message.content
  
prompts = [
    "用中文回答：strawberry中有多少个r?", 
    "用中文回答：9.11和9.9，哪个小?"
]

for prompt in prompts:
    print(function_call_playground(prompt))

The model will output:

strawberry中有3个r。
9.11 比 9.9 小。

​
4.2. Example 2: Extending Large Language Model’s Understanding of External Environments via Function Calling This code inputs 1 function to query external information via an external API.

import requests
from openai import OpenAI

client = OpenAI(
    api_key="您的 APIKEY", # 从https://cloud.siliconflow.cn/account/ak获取
    base_url="https://api.siliconflow.cn/v1"
)

# 使用 WeatherAPI 的天气查询函数
def get_weather(city: str):
    # 使用 WeatherAPI 的 API 来获取天气信息
    api_key = "您的WeatherAPI APIKEY"  # 替换为你自己的 WeatherAPI APIKEY
    base_url = "http://api.weatherapi.com/v1/current.json"
    params = {
        'key': api_key,
        'q': city,
        'aqi': 'no'  # 不需要空气质量数据
    }
    
    # 调用天气 API
    response = requests.get(base_url, params=params)
    
    if response.status_code == 200:
        data = response.json()
        weather = data['current']['condition']['text']
        temperature = data['current']['temp_c']
        return f"The weather in {city} is {weather} with a temperature of {temperature}°C."
    else:
        return f"Could not retrieve weather information for {city}."

# 定义 OpenAI 的 function calling tools
tools = [
    {
        'type': 'function',
        'function': {
            'name': 'get_weather',
            'description': 'Get the current weather for a given city.',
            'parameters': {
                'type': 'object',
                'properties': {
                    'city': {
                        'type': 'string',
                        'description': 'The name of the city to query weather for.',
                    },
                },
                'required': ['city'],
            },
        }
    }
]

# 发送请求并处理 function calling
def function_call_playground(prompt):
    messages = [{'role': 'user', 'content': prompt}]
    
    # 发送请求到 OpenAI API
    response = client.chat.completions.create(
        model="deepseek-ai/DeepSeek-V2.5",
        messages=messages,
        temperature=0.01,
        top_p=0.95,
        stream=False,
        tools=tools
    )

    # 处理 API 返回的工具调用请求
    func1_name = response.choices[0].message.tool_calls[0].function.name
    func1_args = response.choices[0].message.tool_calls[0].function.arguments
    func1_out = eval(f'{func1_name}(**{func1_args})')

    # 将结果添加到对话中并返回
    messages.append(response.choices[0].message)
    messages.append({
        'role': 'tool',
        'content': f'{func1_out}',
        'tool_call_id': response.choices[0].message.tool_calls[0].id
    })
    
    # 返回模型响应
    response = client.chat.completions.create(
        model="deepseek-ai/DeepSeek-V2.5",
        messages=messages,
        temperature=0.01,
        top_p=0.95,
        stream=False,
        tools=tools
    )
    
    return response.choices[0].message.content

# 示例使用
prompt = "how is the weather today in beijing?"
print(function_call_playground(prompt))

The model will output:

The weather in Beijing today is sunny with a temperature of 21.4°C.
FIM completionFine-tuning