Tool use with Live API

使用工具可讓 Live API 在維持即時連線的同時，在真實世界中執行動作及擷取外部內容，而非僅限於對話。您可以使用 Live API 定義工具，例如函式呼叫、程式碼執行和Google 搜尋。

支援工具總覽

以下簡要說明各模型可用的工具：

工具 分層模型
gemini-live-2.5-flash-preview
gemini-2.0-flash-live-001		 gemini-2.5-flash-preview-native-audio-dialog gemini-2.5-flash-exp-native-audio-thinking-dialog
搜尋 是 是 是
函式呼叫 是 是 否
程式碼執行 是 否 否
網址內容 是 否 否

函式呼叫

如同一般內容產生要求，Live API 也支援函式呼叫。函式呼叫可讓 Live API 與外部資料和程式互動，大幅提升應用程式可達成的功能。

您可以將函式宣告定義為工作階段設定的一部分。收到工具呼叫後，用戶端應使用 session.send_tool_response 方法，以 FunctionResponse 物件清單做為回應。

詳情請參閱函式呼叫教學課程。

Python

import asyncio
from google import genai
from google.genai import types

client = genai.Client()
model = "gemini-live-2.5-flash-preview"

# Simple function definitions
turn_on_the_lights = {"name": "turn_on_the_lights"}
turn_off_the_lights = {"name": "turn_off_the_lights"}

tools = [{"function_declarations": [turn_on_the_lights, turn_off_the_lights]}]
config = {"response_modalities": ["TEXT"], "tools": tools}

async def main():
    async with client.aio.live.connect(model=model, config=config) as session:
        prompt = "Turn on the lights please"
        await session.send_client_content(turns={"parts": [{"text": prompt}]})

        async for chunk in session.receive():
            if chunk.server_content:
                if chunk.text is not None:
                    print(chunk.text)
            elif chunk.tool_call:
                function_responses = []
                for fc in chunk.tool_call.function_calls:
                    function_response = types.FunctionResponse(
                        id=fc.id,
                        name=fc.name,
                        response={ "result": "ok" } # simple, hard-coded function response
                    )
                    function_responses.append(function_response)

                await session.send_tool_response(function_responses=function_responses)

if __name__ == "__main__":
    asyncio.run(main())

JavaScript 

import { GoogleGenAI, Modality } from '@google/genai';

const ai = new GoogleGenAI({});
const model = 'gemini-live-2.5-flash-preview';

// Simple function definitions
const turn_on_the_lights = { name: "turn_on_the_lights" } // , description: '...', parameters: { ... }
const turn_off_the_lights = { name: "turn_off_the_lights" }

const tools = [{ functionDeclarations: [turn_on_the_lights, turn_off_the_lights] }]

const config = {
  responseModalities: [Modality.TEXT],
  tools: tools
}

async function live() {
  const responseQueue = [];

  async function waitMessage() {
    let done = false;
    let message = undefined;
    while (!done) {
      message = responseQueue.shift();
      if (message) {
        done = true;
      } else {
        await new Promise((resolve) => setTimeout(resolve, 100));
      }
    }
    return message;
  }

  async function handleTurn() {
    const turns = [];
    let done = false;
    while (!done) {
      const message = await waitMessage();
      turns.push(message);
      if (message.serverContent && message.serverContent.turnComplete) {
        done = true;
      } else if (message.toolCall) {
        done = true;
      }
    }
    return turns;
  }

  const session = await ai.live.connect({
    model: model,
    callbacks: {
      onopen: function () {
        console.debug('Opened');
      },
      onmessage: function (message) {
        responseQueue.push(message);
      },
      onerror: function (e) {
        console.debug('Error:', e.message);
      },
      onclose: function (e) {
        console.debug('Close:', e.reason);
      },
    },
    config: config,
  });

  const inputTurns = 'Turn on the lights please';
  session.sendClientContent({ turns: inputTurns });

  let turns = await handleTurn();

  for (const turn of turns) {
    if (turn.serverContent && turn.serverContent.modelTurn && turn.serverContent.modelTurn.parts) {
      for (const part of turn.serverContent.modelTurn.parts) {
        if (part.text) {
          console.debug('Received text: %s\n', part.text);
        }
      }
    }
    else if (turn.toolCall) {
      const functionResponses = [];
      for (const fc of turn.toolCall.functionCalls) {
        functionResponses.push({
          id: fc.id,
          name: fc.name,
          response: { result: "ok" } // simple, hard-coded function response
        });
      }

      console.debug('Sending tool response...\n');
      session.sendToolResponse({ functionResponses: functionResponses });
    }
  }

  // Check again for new messages
  turns = await handleTurn();

  for (const turn of turns) {
    if (turn.serverContent && turn.serverContent.modelTurn && turn.serverContent.modelTurn.parts) {
      for (const part of turn.serverContent.modelTurn.parts) {
        if (part.text) {
          console.debug('Received text: %s\n', part.text);
        }
      }
    }
  }

  session.close();
}

async function main() {
  await live().catch((e) => console.error('got error', e));
}

main();

模型可從單一提示產生多個函式呼叫，以及連結輸出的必要程式碼。這個程式碼會在沙箱環境中執行，產生後續的 BidiGenerateContentToolCall 訊息。

非同步函式呼叫

根據預設，函式呼叫會依序執行，也就是說，執行作業會暫停，直到每個函式呼叫的結果都已可用為止。這可確保依序處理，也就是說，您無法在函式執行期間繼續與模型互動。

如果不想封鎖對話，您可以指示模型以非同步方式執行函式。如要這樣做，您必須先在函式定義中加入 behavior：

Python

  # Non-blocking function definitions
  turn_on_the_lights = {"name": "turn_on_the_lights", "behavior": "NON_BLOCKING"} # turn_on_the_lights will run asynchronously
  turn_off_the_lights = {"name": "turn_off_the_lights"} # turn_off_the_lights will still pause all interactions with the model

JavaScript 

import { GoogleGenAI, Modality, Behavior } from '@google/genai';

// Non-blocking function definitions
const turn_on_the_lights = {name: "turn_on_the_lights", behavior: Behavior.NON_BLOCKING}

// Blocking function definitions
const turn_off_the_lights = {name: "turn_off_the_lights"}

const tools = [{ functionDeclarations: [turn_on_the_lights, turn_off_the_lights] }]

NON-BLOCKING 可確保函式以非同步方式執行，同時讓您繼續與模型互動。

接著，您需要使用 scheduling 參數，告訴模型在收到 FunctionResponse 時應如何運作。可以是：

  • 中斷其執行的工作，並立即告知您收到的回應 (scheduling="INTERRUPT")。
  • 等待目前執行的作業完成 (scheduling="WHEN_IDLE")，

  • 或者不採取任何行動，稍後在討論中使用該知識 (scheduling="SILENT")

Python

# for a non-blocking function definition, apply scheduling in the function response:
  function_response = types.FunctionResponse(
      id=fc.id,
      name=fc.name,
      response={
          "result": "ok",
          "scheduling": "INTERRUPT" # Can also be WHEN_IDLE or SILENT
      }
  )

JavaScript 

import { GoogleGenAI, Modality, Behavior, FunctionResponseScheduling } from '@google/genai';

// for a non-blocking function definition, apply scheduling in the function response:
const functionResponse = {
  id: fc.id,
  name: fc.name,
  response: {
    result: "ok",
    scheduling: FunctionResponseScheduling.INTERRUPT  // Can also be WHEN_IDLE or SILENT
  }
}

程式碼執行

您可以將程式碼執行作業定義為工作階段設定的一部分。這可讓 Live API 生成及執行 Python 程式碼，並以動態方式執行運算，以利產生結果。詳情請參閱程式碼執行教學課程。

Python

import asyncio
from google import genai
from google.genai import types

client = genai.Client()
model = "gemini-live-2.5-flash-preview"

tools = [{'code_execution': {}}]
config = {"response_modalities": ["TEXT"], "tools": tools}

async def main():
    async with client.aio.live.connect(model=model, config=config) as session:
        prompt = "Compute the largest prime palindrome under 100000."
        await session.send_client_content(turns={"parts": [{"text": prompt}]})

        async for chunk in session.receive():
            if chunk.server_content:
                if chunk.text is not None:
                    print(chunk.text)

                model_turn = chunk.server_content.model_turn
                if model_turn:
                    for part in model_turn.parts:
                      if part.executable_code is not None:
                        print(part.executable_code.code)

                      if part.code_execution_result is not None:
                        print(part.code_execution_result.output)

if __name__ == "__main__":
    asyncio.run(main())

JavaScript 

import { GoogleGenAI, Modality } from '@google/genai';

const ai = new GoogleGenAI({});
const model = 'gemini-live-2.5-flash-preview';

const tools = [{codeExecution: {}}]
const config = {
  responseModalities: [Modality.TEXT],
  tools: tools
}

async function live() {
  const responseQueue = [];

  async function waitMessage() {
    let done = false;
    let message = undefined;
    while (!done) {
      message = responseQueue.shift();
      if (message) {
        done = true;
      } else {
        await new Promise((resolve) => setTimeout(resolve, 100));
      }
    }
    return message;
  }

  async function handleTurn() {
    const turns = [];
    let done = false;
    while (!done) {
      const message = await waitMessage();
      turns.push(message);
      if (message.serverContent && message.serverContent.turnComplete) {
        done = true;
      } else if (message.toolCall) {
        done = true;
      }
    }
    return turns;
  }

  const session = await ai.live.connect({
    model: model,
    callbacks: {
      onopen: function () {
        console.debug('Opened');
      },
      onmessage: function (message) {
        responseQueue.push(message);
      },
      onerror: function (e) {
        console.debug('Error:', e.message);
      },
      onclose: function (e) {
        console.debug('Close:', e.reason);
      },
    },
    config: config,
  });

  const inputTurns = 'Compute the largest prime palindrome under 100000.';
  session.sendClientContent({ turns: inputTurns });

  const turns = await handleTurn();

  for (const turn of turns) {
    if (turn.serverContent && turn.serverContent.modelTurn && turn.serverContent.modelTurn.parts) {
      for (const part of turn.serverContent.modelTurn.parts) {
        if (part.text) {
          console.debug('Received text: %s\n', part.text);
        }
        else if (part.executableCode) {
          console.debug('executableCode: %s\n', part.executableCode.code);
        }
        else if (part.codeExecutionResult) {
          console.debug('codeExecutionResult: %s\n', part.codeExecutionResult.output);
        }
      }
    }
  }

  session.close();
}

async function main() {
  await live().catch((e) => console.error('got error', e));
}

main();

您可以將 Google 搜尋設為工作階段設定的一部分，啟用基準建立功能。這可提高 Live API 的準確度，並避免產生幻覺。詳情請參閱基礎教學課程。

Python

import asyncio
from google import genai
from google.genai import types

client = genai.Client()
model = "gemini-live-2.5-flash-preview"

tools = [{'google_search': {}}]
config = {"response_modalities": ["TEXT"], "tools": tools}

async def main():
    async with client.aio.live.connect(model=model, config=config) as session:
        prompt = "When did the last Brazil vs. Argentina soccer match happen?"
        await session.send_client_content(turns={"parts": [{"text": prompt}]})

        async for chunk in session.receive():
            if chunk.server_content:
                if chunk.text is not None:
                    print(chunk.text)

                # The model might generate and execute Python code to use Search
                model_turn = chunk.server_content.model_turn
                if model_turn:
                    for part in model_turn.parts:
                      if part.executable_code is not None:
                        print(part.executable_code.code)

                      if part.code_execution_result is not None:
                        print(part.code_execution_result.output)

if __name__ == "__main__":
    asyncio.run(main())

JavaScript 

import { GoogleGenAI, Modality } from '@google/genai';

const ai = new GoogleGenAI({});
const model = 'gemini-live-2.5-flash-preview';

const tools = [{googleSearch: {}}]
const config = {
  responseModalities: [Modality.TEXT],
  tools: tools
}

async function live() {
  const responseQueue = [];

  async function waitMessage() {
    let done = false;
    let message = undefined;
    while (!done) {
      message = responseQueue.shift();
      if (message) {
        done = true;
      } else {
        await new Promise((resolve) => setTimeout(resolve, 100));
      }
    }
    return message;
  }

  async function handleTurn() {
    const turns = [];
    let done = false;
    while (!done) {
      const message = await waitMessage();
      turns.push(message);
      if (message.serverContent && message.serverContent.turnComplete) {
        done = true;
      } else if (message.toolCall) {
        done = true;
      }
    }
    return turns;
  }

  const session = await ai.live.connect({
    model: model,
    callbacks: {
      onopen: function () {
        console.debug('Opened');
      },
      onmessage: function (message) {
        responseQueue.push(message);
      },
      onerror: function (e) {
        console.debug('Error:', e.message);
      },
      onclose: function (e) {
        console.debug('Close:', e.reason);
      },
    },
    config: config,
  });

  const inputTurns = 'When did the last Brazil vs. Argentina soccer match happen?';
  session.sendClientContent({ turns: inputTurns });

  const turns = await handleTurn();

  for (const turn of turns) {
    if (turn.serverContent && turn.serverContent.modelTurn && turn.serverContent.modelTurn.parts) {
      for (const part of turn.serverContent.modelTurn.parts) {
        if (part.text) {
          console.debug('Received text: %s\n', part.text);
        }
        else if (part.executableCode) {
          console.debug('executableCode: %s\n', part.executableCode.code);
        }
        else if (part.codeExecutionResult) {
          console.debug('codeExecutionResult: %s\n', part.codeExecutionResult.output);
        }
      }
    }
  }

  session.close();
}

async function main() {
  await live().catch((e) => console.error('got error', e));
}

main();

結合多種工具

您可以結合 Live API 中的多種工具，進一步提升應用程式的功能：

Python

prompt = """
Hey, I need you to do three things for me.

1. Compute the largest prime palindrome under 100000.
2. Then use Google Search to look up information about the largest earthquake in California the week of Dec 5 2024?
3. Turn on the lights

Thanks!
"""

tools = [
    {"google_search": {}},
    {"code_execution": {}},
    {"function_declarations": [turn_on_the_lights, turn_off_the_lights]},
]

config = {"response_modalities": ["TEXT"], "tools": tools}

# ... remaining model call

JavaScript 

const prompt = `Hey, I need you to do three things for me.

1. Compute the largest prime palindrome under 100000.
2. Then use Google Search to look up information about the largest earthquake in California the week of Dec 5 2024?
3. Turn on the lights

Thanks!
`

const tools = [
  { googleSearch: {} },
  { codeExecution: {} },
  { functionDeclarations: [turn_on_the_lights, turn_off_the_lights] }
]

const config = {
  responseModalities: [Modality.TEXT],
  tools: tools
}

// ... remaining model call

後續步驟