工具调用

Ollama 支持工具调用（也称为函数调用），这允许模型调用工具并将其结果纳入回复中。

调用单个工具

调用单个工具并在后续请求中包含其响应。

也称为“单次”工具调用。

cURL

curl -s http://localhost:11434/api/chat -H "Content-Type: application/json" -d '{
  "model": "qwen3",
  "messages": [{"role": "user", "content": "What is the temperature in New York?"}],
  "stream": false,
  "tools": [
    {
      "type": "function",
      "function": {
        "name": "get_temperature",
        "description": "Get the current temperature for a city",
        "parameters": {
          "type": "object",
          "required": ["city"],
          "properties": {
            "city": {"type": "string", "description": "The name of the city"}
          }
        }
      }
    }
  ]
}'

生成包含单个工具结果的响应

curl -s http://localhost:11434/api/chat -H "Content-Type: application/json" -d '{
  "model": "qwen3",
  "messages": [
    {"role": "user", "content": "What is the temperature in New York?"},
    {
      "role": "assistant",
      "tool_calls": [
        {
          "type": "function",
          "function": {
            "index": 0,
            "name": "get_temperature",
            "arguments": {"city": "New York"}
          }
        }
      ]
    },
    {"role": "tool", "tool_name": "get_temperature", "content": "22°C"}
  ],
  "stream": false
}'

Python

安装 Ollama Python SDK：

# 使用 pip
pip install ollama -U

# 使用 uv
uv add ollama    

from ollama import chat

def get_temperature(city: str) -> str:
  """获取城市的当前温度
  
  Args:
    city: 城市名称

  Returns:
    该城市的当前温度
  """
  temperatures = {
    "New York": "22°C",
    "London": "15°C",
    "Tokyo": "18°C",
  }
  return temperatures.get(city, "Unknown")

messages = [{"role": "user", "content": "What is the temperature in New York?"}]

# 在 tools 列表中直接传递函数，或将其作为 JSON schema 传递
response = chat(model="qwen3", messages=messages, tools=[get_temperature], think=True)

messages.append(response.message)
if response.message.tool_calls:
  # 仅推荐用于只返回单个工具调用的模型
  call = response.message.tool_calls[0]
  result = get_temperature(**call.function.arguments)
  # 将工具结果添加到消息中
  messages.append({"role": "tool", "tool_name": call.function.name, "content": str(result)})

  final_response = chat(model="qwen3", messages=messages, tools=[get_temperature], think=True)
  print(final_response.message.content)

JavaScript

安装 Ollama JavaScript 库：

# 使用 npm
npm i ollama

# 使用 bun
bun i ollama

import ollama from 'ollama'

function getTemperature(city: string): string {
  const temperatures: Record<string, string> = {
    'New York': '22°C',
    'London': '15°C',
    'Tokyo': '18°C',
  }
  return temperatures[city] ?? 'Unknown'
}

const tools = [
  {
    type: 'function',
    function: {
      name: 'get_temperature',
      description: 'Get the current temperature for a city',
      parameters: {
        type: 'object',
        required: ['city'],
        properties: {
          city: { type: 'string', description: 'The name of the city' },
        },
      },
    },
  },
]

const messages = [{ role: 'user', content: "What is the temperature in New York?" }]

const response = await ollama.chat({
  model: 'qwen3',
  messages,
  tools,
  think: true,
})

messages.push(response.message)
if (response.message.tool_calls?.length) {
  // 仅推荐用于只返回单个工具调用的模型
  const call = response.message.tool_calls[0]
  const args = call.function.arguments as { city: string }
  const result = getTemperature(args.city)
  // 将工具结果添加到消息中
  messages.push({ role: 'tool', tool_name: call.function.name, content: result })

  // 生成最终响应
  const finalResponse = await ollama.chat({ model: 'qwen3', messages, tools, think: true })
  console.log(finalResponse.message.content)
}

并行工具调用

cURL

并行请求多个工具调用，然后将所有工具响应发送回模型。

curl -s http://localhost:11434/api/chat -H "Content-Type: application/json" -d '{
  "model": "qwen3",
  "messages": [{"role": "user", "content": "What are the current weather conditions and temperature in New York and London?"}],
  "stream": false,
  "tools": [
    {
      "type": "function",
      "function": {
        "name": "get_temperature",
        "description": "Get the current temperature for a city",
        "parameters": {
          "type": "object",
          "required": ["city"],
          "properties": {
            "city": {"type": "string", "description": "The name of the city"}
          }
        }
      }
    },
    {
      "type": "function",
      "function": {
        "name": "get_conditions",
        "description": "Get the current weather conditions for a city",
        "parameters": {
          "type": "object",
          "required": ["city"],
          "properties": {
            "city": {"type": "string", "description": "The name of the city"}
          }
        }
      }
    }
  ]
}'

生成包含多个工具结果的响应

curl -s http://localhost:11434/api/chat -H "Content-Type: application/json" -d '{
  "model": "qwen3",
  "messages": [
    {"role": "user", "content": "What are the current weather conditions and temperature in New York and London?"},
    {
      "role": "assistant",
      "tool_calls": [
        {
          "type": "function",
          "function": {
            "index": 0,
            "name": "get_temperature",
            "arguments": {"city": "New York"}
          }
        },
        {
          "type": "function",
          "function": {
            "index": 1,
            "name": "get_conditions",
            "arguments": {"city": "New York"}
          }
        },
        {
          "type": "function",
          "function": {
            "index": 2,
            "name": "get_temperature",
            "arguments": {"city": "London"}
          }
        },
        {
          "type": "function",
          "function": {
            "index": 3,
            "name": "get_conditions",
            "arguments": {"city": "London"}
          }
        }
      ]
    },
    {"role": "tool", "tool_name": "get_temperature", "content": "22°C"},
    {"role": "tool", "tool_name": "get_conditions", "content": "Partly cloudy"},
    {"role": "tool", "tool_name": "get_temperature", "content": "15°C"},
    {"role": "tool", "tool_name": "get_conditions", "content": "Rainy"}
  ],
  "stream": false
}'

Python

from ollama import chat

def get_temperature(city: str) -> str:
  """Get the current temperature for a city
  
  Args:
    city: The name of the city

  Returns:
    The current temperature for the city
  """
  temperatures = {
    "New York": "22°C",
    "London": "15°C",
    "Tokyo": "18°C"
  }
  return temperatures.get(city, "Unknown")

def get_conditions(city: str) -> str:
  """Get the current weather conditions for a city
  
  Args:
    city: The name of the city

  Returns:
    The current weather conditions for the city
  """
  conditions = {
    "New York": "Partly cloudy",
    "London": "Rainy",
    "Tokyo": "Sunny"
  }
  return conditions.get(city, "Unknown")

messages = [{'role': 'user', 'content': 'What are the current weather conditions and temperature in New York and London?'}]

# python 客户端会自动将函数解析为工具架构，因此我们可以直接传递它们
# 也可以直接将架构传递给 tools 列表 
response = chat(model='qwen3', messages=messages, tools=[get_temperature, get_conditions], think=True)

# 将助手消息添加到消息列表中
messages.append(response.message)
if response.message.tool_calls:
  # 处理每个工具调用 
  for call in response.message.tool_calls:
    # 执行相应的工具
    if call.function.name == 'get_temperature':
      result = get_temperature(**call.function.arguments)
    elif call.function.name == 'get_conditions':
      result = get_conditions(**call.function.arguments)
    else:
      result = 'Unknown tool'
    # 将工具结果添加到消息列表中
    messages.append({'role': 'tool',  'tool_name': call.function.name, 'content': str(result)})

  # 生成最终响应
  final_response = chat(model='qwen3', messages=messages, tools=[get_temperature, get_conditions], think=True)
  print(final_response.message.content)

JavaScript

import ollama from 'ollama'

function getTemperature(city: string): string {
  const temperatures: { [key: string]: string } = {
    "New York": "22°C",
    "London": "15°C",
    "Tokyo": "18°C"
  }
  return temperatures[city] || "Unknown"
}

function getConditions(city: string): string {
  const conditions: { [key: string]: string } = {
    "New York": "Partly cloudy",
    "London": "Rainy",
    "Tokyo": "Sunny"
  }
  return conditions[city] || "Unknown"
}

const tools = [
  {
    type: 'function',
    function: {
      name: 'get_temperature',
      description: 'Get the current temperature for a city',
      parameters: {
        type: 'object',
        required: ['city'],
        properties: {
          city: { type: 'string', description: 'The name of the city' },
        },
      },
    },
  },
  {
    type: 'function',
    function: {
      name: 'get_conditions',
      description: 'Get the current weather conditions for a city',
      parameters: {
        type: 'object',
        required: ['city'],
        properties: {
          city: { type: 'string', description: 'The name of the city' },
        },
      },
    },
  }
]

const messages = [{ role: 'user', content: 'What are the current weather conditions and temperature in New York and London?' }]

const response = await ollama.chat({
  model: 'qwen3',
  messages,
  tools,
  think: true
})

// 将助手消息添加到消息列表中
messages.push(response.message)
if (response.message.tool_calls) {
  // 处理每个工具调用 
  for (const call of response.message.tool_calls) {
    // 执行相应的工具
    let result: string
    if (call.function.name === 'get_temperature') {
      const args = call.function.arguments as { city: string }
      result = getTemperature(args.city)
    } else if (call.function.name === 'get_conditions') {
      const args = call.function.arguments as { city: string }
      result = getConditions(args.city)
    } else {
      result = 'Unknown tool'
    }
    // 将工具结果添加到消息列表中
    messages.push({ role: 'tool', tool_name: call.function.name, content: result })
  }

  // 生成最终响应
  const finalResponse = await ollama.chat({ model: 'qwen3', messages, tools, think: true })
  console.log(finalResponse.message.content)
}

多轮工具调用（Agent 循环）

Agent 循环允许模型决定何时调用工具，并将工具结果纳入其回复中。

告知模型它处于一个循环中并且可以进行多次工具调用可能会有所帮助。

Python

from ollama import chat, ChatResponse

def add(a: int, b: int) -> int:
  """Add two numbers"""
  """
  Args:
    a: The first number
    b: The second number

  Returns:
    The sum of the two numbers
  """
  return a + b

def multiply(a: int, b: int) -> int:
  """Multiply two numbers"""
  """
  Args:
    a: The first number
    b: The second number

  Returns:
    The product of the two numbers
  """
  return a * b

available_functions = {
  'add': add,
  'multiply': multiply,
}

messages = [{'role': 'user', 'content': 'What is (11434+12341)*412?'}]
while True:
    response: ChatResponse = chat(
        model='qwen3',
        messages=messages,
        tools=[add, multiply],
        think=True,
    )
    messages.append(response.message)
    print("Thinking: ", response.message.thinking)
    print("Content: ", response.message.content)
    if response.message.tool_calls:
        for tc in response.message.tool_calls:
            if tc.function.name in available_functions:
                print(f"Calling {tc.function.name} with arguments {tc.function.arguments}")
                result = available_functions[tc.function.name](**tc.function.arguments)
                print(f"Result: {result}")
                # 将工具结果添加到消息列表中
                messages.append({'role': 'tool', 'tool_name': tc.function.name, 'content': str(result)})
    else:
        # 当没有更多工具调用时结束循环
        break
  # 使用更新后的消息继续循环

JavaScript

import ollama from 'ollama'

type ToolName = 'add' | 'multiply'

function add(a: number, b: number): number {
  return a + b
}

function multiply(a: number, b: number): number {
  return a * b
}

const availableFunctions: Record<ToolName, (a: number, b: number) => number> = {
  add,
  multiply,
}

const tools = [
  {
    type: 'function',
    function: {
      name: 'add',
      description: 'Add two numbers',
      parameters: {
        type: 'object',
        required: ['a', 'b'],
        properties: {
          a: { type: 'integer', description: 'The first number' },
          b: { type: 'integer', description: 'The second number' },
        },
      },
    },
  },
  {
    type: 'function',
    function: {
      name: 'multiply',
      description: 'Multiply two numbers',
      parameters: {
        type: 'object',
        required: ['a', 'b'],
        properties: {
          a: { type: 'integer', description: 'The first number' },
          b: { type: 'integer', description: 'The second number' },
        },
      },
    },
  },
]

async function agentLoop() {
  const messages = [{ role: 'user', content: 'What is (11434+12341)*412?' }]

  while (true) {
    const response = await ollama.chat({
      model: 'qwen3',
      messages,
      tools,
      think: true,
    })

    messages.push(response.message)
    console.log('Thinking:', response.message.thinking)
    console.log('Content:', response.message.content)

    const toolCalls = response.message.tool_calls ?? []
    if (toolCalls.length) {
      for (const call of toolCalls) {
        const fn = availableFunctions[call.function.name as ToolName]
        if (!fn) {
          continue
        }

        const args = call.function.arguments as { a: number; b: number }
        console.log(`Calling ${call.function.name} with arguments`, args)
        const result = fn(args.a, args.b)
        console.log(`Result: ${result}`)
        messages.push({ role: 'tool', tool_name: call.function.name, content: String(result) })
      }
    } else {
      break
    }
  }
}

agentLoop().catch(console.error)

流式传输中的工具调用

在流式传输时，收集 thinking、content 和 tool_calls 的每个数据块，然后在后续请求中将这些字段与任何工具结果一起返回。

Python

from ollama import chat 

def get_temperature(city: str) -> str:
  """Get the current temperature for a city
  
  Args:
    city: The name of the city

  Returns:
    The current temperature for the city
  """
  temperatures = {
    'New York': '22°C',
    'London': '15°C',
  }
  return temperatures.get(city, 'Unknown')

messages = [{'role': 'user', 'content': "What is the temperature in New York?"}]

while True:
  stream = chat(
    model='qwen3',
    messages=messages,
    tools=[get_temperature],
    stream=True,
    think=True,
  )

  thinking = ''
  content = ''
  tool_calls = []

  done_thinking = False
  # 累积部分字段
  for chunk in stream:
    if chunk.message.thinking:
      thinking += chunk.message.thinking
      print(chunk.message.thinking, end='', flush=True)
    if chunk.message.content:
      if not done_thinking:
        done_thinking = True
        print('\n')
      content += chunk.message.content
      print(chunk.message.content, end='', flush=True)
    if chunk.message.tool_calls:
      tool_calls.extend(chunk.message.tool_calls)
      print(chunk.message.tool_calls)

  # 将累积的字段添加到消息列表中
  if thinking or content or tool_calls:
    messages.append({'role': 'assistant', 'thinking': thinking, 'content': content, 'tool_calls': tool_calls})

  if not tool_calls:
    break

  for call in tool_calls:
    if call.function.name == 'get_temperature':
      result = get_temperature(**call.function.arguments)
    else:
      result = 'Unknown tool'
    messages.append({'role': 'tool', 'tool_name': call.function.name, 'content': result})

JavaScript

import ollama from 'ollama'

function getTemperature(city: string): string {
  const temperatures: Record<string, string> = {
    'New York': '22°C',
    'London': '15°C',
  }
  return temperatures[city] ?? 'Unknown'
}

const getTemperatureTool = {
  type: 'function',
  function: {
    name: 'get_temperature',
    description: 'Get the current temperature for a city',
    parameters: {
      type: 'object',
      required: ['city'],
      properties: {
        city: { type: 'string', description: 'The name of the city' },
      },
    },
  },
}

async function agentLoop() {
  const messages = [{ role: 'user', content: "What is the temperature in New York?" }]

  while (true) {
    const stream = await ollama.chat({
      model: 'qwen3',
      messages,
      tools: [getTemperatureTool],
      stream: true,
      think: true,
    })

    let thinking = ''
    let content = ''
    const toolCalls: any[] = []
    let doneThinking = false

    for await (const chunk of stream) {
      if (chunk.message.thinking) {
        thinking += chunk.message.thinking
        process.stdout.write(chunk.message.thinking)
      }
      if (chunk.message.content) {
        if (!doneThinking) {
          doneThinking = true
          process.stdout.write('\n')
        }
        content += chunk.message.content
        process.stdout.write(chunk.message.content)
      }
      if (chunk.message.tool_calls?.length) {
        toolCalls.push(...chunk.message.tool_calls)
        console.log(chunk.message.tool_calls)
      }
    }

    if (thinking || content || toolCalls.length) {
      messages.push({ role: 'assistant', thinking, content, tool_calls: toolCalls } as any)
    }

    if (!toolCalls.length) {
      break
    }

    for (const call of toolCalls) {
      if (call.function.name === 'get_temperature') {
        const args = call.function.arguments as { city: string }
        const result = getTemperature(args.city)
        messages.push({ role: 'tool', tool_name: call.function.name, content: result } )
      } else {
        messages.push({ role: 'tool', tool_name: call.function.name, content: 'Unknown tool' } )
      }
    }
  }
}

agentLoop().catch(console.error)

此循环流式传输助手响应，累积部分字段，将它们一起传回，并附加工具结果，以便模型完成其回答。

在 Ollama Python SDK 中使用函数作为工具

Python SDK 会自动将函数解析为工具 schema，因此我们可以直接传递它们。如有需要，仍可传递 schemas。

from ollama import chat

def get_temperature(city: str) -> str:
  """获取某个城市的当前温度
  
  Args:
    city: 城市名称

  Returns:
    该城市的当前温度
  """
  temperatures = {
    'New York': '22°C',
    'London': '15°C',
  }
  return temperatures.get(city, 'Unknown')

available_functions = {
  'get_temperature': get_temperature,
}
# 直接将函数作为工具列表的一部分传递
response = chat(model='qwen3', messages=messages, tools=available_functions.values(), think=True)