Panggilan fungsi dengan Gemini API

Panggilan fungsi memungkinkan Anda menghubungkan model ke alat dan API eksternal. Daripada membuat respons teks, model menentukan kapan harus memanggil fungsi tertentu dan memberikan parameter yang diperlukan untuk menjalankan tindakan di dunia nyata. Hal ini memungkinkan model bertindak sebagai jembatan antara bahasa alami dan tindakan serta data dunia nyata. Panggilan fungsi memiliki 3 kasus penggunaan utama:

  • Meningkatkan Pengetahuan: Mengakses informasi dari sumber eksternal seperti database, API, dan pusat informasi.
  • Memperluas Kemampuan: Menggunakan alat eksternal untuk melakukan komputasi dan memperluas batasan model, seperti menggunakan kalkulator atau membuat diagram.
  • Mengambil Tindakan: Berinteraksi dengan sistem eksternal menggunakan API, seperti menjadwalkan janji temu, membuat invoice, mengirim email, atau mengontrol perangkat smart home.

Python

from google import genai

schedule_meeting_function = {
    "type": "function",
    "name": "schedule_meeting",
    "description": "Schedules a meeting with specified attendees at a given time and date.",
    "parameters": {
        "type": "object",
        "properties": {
            "attendees": {"type": "array", "items": {"type": "string"}},
            "date": {"type": "string", "description": "Date (e.g., '2024-07-29')"},
            "time": {"type": "string", "description": "Time (e.g., '15:00')"},
            "topic": {"type": "string", "description": "The meeting topic."},
        },
        "required": ["attendees", "date", "time", "topic"],
    },
}

client = genai.Client()

interaction = client.interactions.create(
    model="gemini-3-flash-preview",
    input="Schedule a meeting with Bob and Alice for 03/14/2025 at 10:00 AM about Q3 planning.",
    tools=[{"type": "function", **schedule_meeting_function}],
)

for step in interaction.steps:
    if step.type == "function_call":
        print(f"Function to call: {step.name}")
        print(f"Arguments: {step.arguments}")

JavaScript

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

const client = new GoogleGenAI({});

const scheduleMeetingFunction = {
  type: 'function',
  name: 'schedule_meeting',
  description: 'Schedules a meeting with specified attendees at a given time and date.',
  parameters: {
    type: 'object',
    properties: {
      attendees: { type: 'array', items: { type: 'string' } },
      date: { type: 'string', description: 'Date (e.g., "2024-07-29")' },
      time: { type: 'string', description: 'Time (e.g., "15:00")' },
      topic: { type: 'string', description: 'The meeting topic.' },
    },
    required: ['attendees', 'date', 'time', 'topic'],
  },
};

const interaction = await client.interactions.create({
  model: 'gemini-3-flash-preview',
  input: 'Schedule a meeting with Bob and Alice for 03/27/2025 at 10:00 AM about Q3 planning.',
  tools: [scheduleMeetingFunction],
});

for (const step of interaction.steps) {
  if (step.type === 'function_call') {
    console.log(`Function to call: ${step.name}`);
    console.log(`Arguments: ${JSON.stringify(step.arguments)}`);
  }
}

REST

curl -X POST "https://generativelanguage.googleapis.com/v1beta/interactions" \
  -H "x-goog-api-key: $GEMINI_API_KEY" \
  -H 'Content-Type: application/json' \
  -d '{
    "model": "gemini-3-flash-preview",
    "input": "Schedule a meeting with Bob and Alice for 03/27/2025 at 10:00 AM about Q3 planning.",
    "tools": [{
        "type": "function",
        "name": "schedule_meeting",
        "description": "Schedules a meeting with specified attendees at a given time and date.",
        "parameters": {
          "type": "object",
          "properties": {
            "attendees": {"type": "array", "items": {"type": "string"}},
            "date": {"type": "string"},
            "time": {"type": "string"},
            "topic": {"type": "string"}
          },
          "required": ["attendees", "date", "time", "topic"]
        }
    }]
  }'

Cara kerja panggilan fungsi

ringkasan panggilan fungsi

Panggilan fungsi melibatkan interaksi terstruktur antara aplikasi Anda, model, dan fungsi eksternal:

  1. Tentukan Deklarasi Fungsi: Tentukan nama, parameter, dan tujuan fungsi ke model.
  2. Memanggil LLM dengan deklarasi fungsi: Kirim perintah pengguna beserta deklarasi fungsi ke model.
  3. Mengeksekusi Kode Fungsi (Tanggung Jawab Anda): Model tidak mengeksekusi fungsi itu sendiri. Ekstrak nama dan argumen, lalu jalankan di aplikasi Anda.
  4. Buat respons yang mudah digunakan: Kirim kembali hasil ke model untuk mendapatkan respons akhir yang mudah digunakan.

Proses ini dapat diulang di beberapa giliran. Model ini mendukung pemanggilan beberapa fungsi dalam satu giliran (pemanggilan fungsi paralel) dan secara berurutan (pemanggilan fungsi komposit).

Langkah 1: Tentukan deklarasi fungsi

Python

set_light_values_declaration = {
    "type": "function",
    "name": "set_light_values",
    "description": "Sets the brightness and color temperature of a light.",
    "parameters": {
        "type": "object",
        "properties": {
            "brightness": {
                "type": "integer",
                "description": "Light level from 0 to 100",
            },
            "color_temp": {
                "type": "string",
                "enum": ["daylight", "cool", "warm"],
                "description": "Color temperature",
            },
        },
        "required": ["brightness", "color_temp"],
    },
}

def set_light_values(brightness: int, color_temp: str) -> dict:
    """Set the brightness and color temperature of a room light."""
    return {"brightness": brightness, "colorTemperature": color_temp}

JavaScript

const setLightValuesTool = {
  type: 'function',
  name: 'set_light_values',
  description: 'Sets the brightness and color temperature of a light.',
  parameters: {
    type: 'object',
    properties: {
      brightness: { type: 'number', description: 'Light level from 0 to 100' },
      color_temp: { type: 'string', enum: ['daylight', 'cool', 'warm'] },
    },
    required: ['brightness', 'color_temp'],
  },
};

function setLightValues(brightness, color_temp) {
  return { brightness: brightness, colorTemperature: color_temp };
}

Langkah 2: Panggil model dengan deklarasi fungsi

Python

from google import genai

client = genai.Client()

interaction = client.interactions.create(
    model="gemini-3-flash-preview",
    input="Turn the lights down to a romantic level",
    tools=[set_light_values_declaration],
)

# Find the function call step
fc_step = next(s for s in interaction.steps if s.type == "function_call")
print(fc_step)

JavaScript

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

const client = new GoogleGenAI({});

const interaction = await client.interactions.create({
  model: 'gemini-3-flash-preview',
  input: 'Turn the lights down to a romantic level',
  tools: [setLightValuesTool],
});

// Find the function call step
const fcStep = interaction.steps.find(s => s.type === 'function_call');
console.log(fcStep);

Model menampilkan langkah function_call dengan type, name, dan arguments:

type='function_call'
name='set_light_values'
arguments={'color_temp': 'warm', 'brightness': 25}

Langkah 3: Jalankan fungsi

Python

fc_step = next(s for s in interaction.steps if s.type == "function_call")

if fc_step.name == "set_light_values":
    result = set_light_values(**fc_step.arguments)
    print(f"Function execution result: {result}")

JavaScript

const fcStep = interaction.steps.find(s => s.type === 'function_call');

let result;
if (fcStep.name === 'set_light_values') {
  result = setLightValues(fcStep.arguments.brightness, fcStep.arguments.color_temp);
  console.log(`Function execution result: ${JSON.stringify(result)}`);
}

Langkah 4: Kirim hasil kembali ke model

Python

final_interaction = client.interactions.create(
    model="gemini-3-flash-preview",
    input=[
        {
            "type": "function_result",
            "name": fc_step.name,
            "call_id": fc_step.id,
            "result": [{"type": "text", "text": json.dumps(result)}],
        }
    ],
    tools=[set_light_values_declaration],
    previous_interaction_id=interaction.id,
)

print(final_interaction.steps[-1].content[0].text)

JavaScript

const finalInteraction = await client.interactions.create({
  model: 'gemini-3-flash-preview',
  input: [{
    type: 'function_result',
    name: fcStep.name,
    call_id: fcStep.id,
    result: [{ type: 'text', text: JSON.stringify(result) }]
  }],
  tools: [setLightValuesTool],
  previousInteractionId: interaction.id,
});

console.log(finalInteraction.steps.at(-1).content[0].text);

Deklarasi fungsi

Deklarasi fungsi diteruskan sebagai alat dan mencakup:

  • type (string): Harus berupa "function" untuk fungsi kustom.
  • name (string): Nama fungsi unik (gunakan garis bawah atau camelCase).
  • description (string): Penjelasan yang jelas tentang tujuan fungsi.
  • parameters (objek): Parameter input yang diharapkan fungsi.
    • type (string): Jenis data keseluruhan, seperti object.
    • properties (objek): Parameter individual dengan jenis dan deskripsi.
    • required (array): Nama parameter wajib.

Panggilan fungsi dengan model penalaran

Model seri Gemini 3 dan 2.5 menggunakan proses "pemikiran" internal yang meningkatkan panggilan fungsi. SDK akan otomatis menangani tanda tangan pikiran untuk Anda.

Panggilan fungsi paralel

Panggil beberapa fungsi sekaligus jika fungsi tersebut independen:

Python

power_disco_ball = {"type": "function", "name": "power_disco_ball", "description": "Powers the disco ball.",
    "parameters": {"type": "object", "properties": {"power": {"type": "boolean"}}, "required": ["power"]}}
start_music = {"type": "function", "name": "start_music", "description": "Play music.",
    "parameters": {"type": "object", "properties": {"energetic": {"type": "boolean"}, "loud": {"type": "boolean"}}, "required": ["energetic", "loud"]}}
dim_lights = {"type": "function", "name": "dim_lights", "description": "Dim the lights.",
    "parameters": {"type": "object", "properties": {"brightness": {"type": "number"}}, "required": ["brightness"]}}

client = genai.Client()

interaction = client.interactions.create(
    model="gemini-3-flash-preview",
    input="Turn this place into a party!",
    tools=[power_disco_ball, start_music, dim_lights],
    generation_config={"tool_choice": "any"},
)

for step in interaction.steps:
    if step.type == "function_call":
        args = ", ".join(f"{key}={val}" for key, val in step.arguments.items())
        print(f"{step.name}({args})")

JavaScript

const powerDiscoBall = { type: 'function', name: 'power_disco_ball', description: 'Powers the disco ball.',
  parameters: { type: 'object', properties: { power: { type: 'boolean' } }, required: ['power'] } };
const startMusic = { type: 'function', name: 'start_music', description: 'Play music.',
  parameters: { type: 'object', properties: { energetic: { type: 'boolean' }, loud: { type: 'boolean' } }, required: ['energetic', 'loud'] } };
const dimLights = { type: 'function', name: 'dim_lights', description: 'Dim the lights.',
  parameters: { type: 'object', properties: { brightness: { type: 'number' } }, required: ['brightness'] } };

const interaction = await client.interactions.create({
  model: 'gemini-3-flash-preview',
  input: 'Turn this place into a party!',
  tools: [powerDiscoBall, startMusic, dimLights],
  generationConfig: { toolChoice: 'any' },
});

for (const step of interaction.steps) {
  if (step.type === 'function_call') {
    console.log(`${step.name}(${JSON.stringify(step.arguments)})`);
  }
}

Panggilan fungsi komposit

Rangkai beberapa panggilan fungsi untuk permintaan yang kompleks (misalnya, dapatkan lokasi terlebih dahulu, lalu dapatkan cuaca untuk lokasi tersebut).

Python

def get_weather_forecast(location: str) -> dict:
    """Gets the current weather temperature for a given location."""
    return {"temperature": 25, "unit": "celsius"}

def set_thermostat_temperature(temperature: int) -> dict:
    """Sets the thermostat to a desired temperature."""
    return {"status": "success"}

client = genai.Client()

interaction = client.interactions.create(
    model="gemini-3-flash-preview",
    input="If it's warmer than 20°C in London, set the thermostat to 20°C, otherwise 18°C.",
    tools=[get_weather_forecast, set_thermostat_temperature],
)

print(interaction.steps[-1].content[0].text)

Mode panggilan fungsi

Mengontrol cara model menggunakan alat menggunakan tool_choice di generation_config:

  • auto (Default): Model memutuskan apakah akan memanggil fungsi atau merespons secara langsung.
  • any: Model dibatasi untuk selalu memprediksi panggilan fungsi.
  • none: Model dilarang melakukan panggilan fungsi.

  • validated (Pratinjau): Model memastikan kepatuhan skema fungsi.

Python

generation_config = {
    "tool_choice": {
        "allowed_tools": {
            "mode": "any",
            "tools": ["get_current_temperature"]
        }
    }
}

JavaScript

const generationConfig = {
  toolChoice: {
    allowedTools: {
      mode: 'any',
      tools: ['get_current_temperature']
    }
  }
};

REST

curl -X POST "https://generativelanguage.googleapis.com/v1beta/interactions" \
  -H "x-goog-api-key: \$GEMINI_API_KEY" \
  -H 'Content-Type: application/json' \
  -d '{
    "model": "gemini-3-flash-preview",
    "input": "What is the temperature in Boston?",
    "tools": [{
      "type": "function",
      "name": "get_current_temperature",
      "description": "Gets the current temperature for a given location.",
      "parameters": {
        "type": "object",
        "properties": {
          "location": {"type": "string"}
        },
        "required": ["location"]
      }
    }],
    "generation_config": {
      "tool_choice": {
        "allowed_tools": {
          "mode": "any",
          "tools": ["get_current_temperature"]
        }
      }
    }
  }'

Penggunaan alat serbaguna

Anda dapat mengaktifkan beberapa alat, menggabungkan alat bawaan dengan panggilan fungsi dalam permintaan yang sama. Model Gemini 3 dapat menggabungkan alat bawaan dengan panggilan fungsi langsung di Interaksi. Meneruskan previous_interaction_id secara otomatis mengedarkan konteks alat bawaan.

Python

from google import genai
import json

client = genai.Client()

get_weather = {
    "type": "function",
    "name": "get_weather",
    "description": "Gets the weather for a requested city.",
    "parameters": {
        "type": "object",
        "properties": {
            "city": {
                "type": "string",
                "description": "The city and state, e.g. Utqiaġvik, Alaska",
            },
        },
        "required": ["city"],
    },
}

tools = [
    {"type": "google_search"},  # Built-in tool
    get_weather                 # Custom tool
]

# Turn 1: Initial request with both tools enabled
interaction = client.interactions.create(
    model="gemini-3-flash-preview",
    input="What is the northernmost city in the United States? What's the weather like there today?",
    tools=tools
)

for step in interaction.steps:
    if step.type == "function_call":
        print(f"Function call: {step.name} (ID: {step.id})")
        # Execute your custom function locally
        result = {"response": "Very cold. 22 degrees Fahrenheit."}
        # Turn 2: Provide the function result back to the model.
        # Passing `previous_interaction_id` automatically circulates the
        # built-in Google Search context from Turn 1
        interaction_2 = client.interactions.create(
            model="gemini-3-flash-preview",
            previous_interaction_id=interaction.id,
            tools=tools,
            input=[{
                "type": "function_result",
                "name": step.name,
                "call_id": step.id,
                "result": [{"type": "text", "text": json.dumps(result)}]
            }]
        )

        print(interaction_2.steps[-1].content[0].text)

JavaScript

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

const client = new GoogleGenAI({});

const weatherTool = {
    type: 'function',
    name: 'get_weather',
    description: 'Gets the weather for a given location.',
    parameters: {
        type: 'object',
        properties: {
            location: { type: 'string', description: 'The city and state, e.g. San Francisco, CA' }
        },
        required: ['location']
    }
};

const tools = [
    {type: 'google_search'}, // Built-in tool
    weatherTool              // Custom tool
];

// Turn 1: Initial request with both tools enabled
let interaction = await client.interactions.create({
    model: 'gemini-3-flash-preview',
    input: "What is the northernmost city in the United States? What's the weather like there today?",
    tools: tools
});

for (const step of interaction.steps) {
    if (step.type === 'function_call') {
        console.log(`Function call: ${step.name} (ID: ${step.id})`);
        // Execute your custom function locally
        const result = {response: "Very cold. 22 degrees Fahrenheit."};
        // Turn 2: Provide the function result back to the model.
        const interaction_2 = await client.interactions.create({
            model: 'gemini-3-flash-preview',
            previousInteractionId: interaction.id,
            tools: tools,
            input: [{
                type: 'function_result',
                name: step.name,
                call_id: step.id,
                result: [{ type: 'text', text: JSON.stringify(result) }]
            }]
        });

        console.log(interaction_2.steps.at(-1).content[0].text);
    }
}

Respons fungsi multimodal

Untuk model seri Gemini 3, Anda dapat menyertakan konten multimodal di bagian respons fungsi yang Anda kirim ke model. Model dapat memproses konten multimodal ini pada giliran berikutnya untuk menghasilkan respons yang lebih informatif.

Untuk menyertakan data multimodal dalam respons fungsi, sertakan sebagai satu atau beberapa blok konten di kolom result pada langkah function_result. Setiap blok konten harus menentukan type-nya (misalnya, "text", "image").

Contoh berikut menunjukkan cara mengirim respons fungsi yang berisi data gambar kembali ke model dalam interaksi:

Python

import base64
from google import genai
import requests

client = genai.Client()

# Find the function call step
tool_call = next(s for s in interaction.steps if s.type == "function_call")

# Execute your tool to get image bytes
image_path = "https://goo.gle/instrument-img"
image_bytes = requests.get(image_path).content

base64_image_data = base64.b64encode(image_bytes).decode("utf-8")

final_interaction = client.interactions.create(
    model="gemini-3-flash-preview",
    previous_interaction_id=interaction.id,
    input=[
        {
            "type": "function_result",
            "name": tool_call.name,
            "call_id": tool_call.id,
            "result": [
                {"type": "text", "text": "instrument.jpg"},
                {
                    "type": "image",
                    "mime_type": "image/jpeg",
                    "data": base64_image_data,
                },
            ],
        }
    ],
)

print(final_interaction.steps[-1].content[0].text)

JavaScript

import { GoogleGenAI } from "@google/genai";

const ai = new GoogleGenAI({});

// Find the function call step
const toolCall = interaction.steps.find(s => s.type === 'function_call');

// Execute your tool to get image bytes and convert to base64
// (Implementation depends on your environment)
const base64ImageData = "BASE64_IMAGE_DATA";

const finalInteraction = await ai.interactions.create({
    model: 'gemini-3-flash-preview',
    previousInteractionId: interaction.id,
    input: [{
        type: 'function_result',
        name: toolCall.name,
        call_id: toolCall.id,
        result: [
            { type: 'text', text: 'instrument.jpg' },
            {
                type: 'image',
                mimeType: 'image/jpeg',
                data: base64ImageData,
            }
        ]
    }]
});

console.log(finalInteraction.steps.at(-1).content[0].text);

REST

curl -X POST "https://generativelanguage.googleapis.com/v1beta/interactions" \
  -H "x-goog-api-key: \$GEMINI_API_KEY" \
  -H 'Content-Type: application/json' \
  -d '{
    "model": "gemini-3-flash-preview",
    "previous_interaction_id": "INTERACTION_ID",
    "input": [
      {
        "type": "function_result",
        "name": "get_image",
        "call_id": "call_123",
        "result": [
          {"type": "text", "text": "instrument.jpg"},
          {
            "type": "image",
            "mime_type": "image/jpeg",
            "data": "BASE64_IMAGE_DATA"
          }
        ]
      }
    ]
  }'

Panggilan fungsi dengan Output terstruktur

Untuk model seri Gemini 3, gabungkan panggilan fungsi dengan output terstruktur untuk respons yang diformat secara konsisten.

MCP (Model Context Protocol) Jarak Jauh

Interactions API mendukung koneksi ke server MCP jarak jauh untuk memberikan akses model ke alat dan layanan eksternal. Anda memberikan server name dan url dalam konfigurasi alat.

Saat menggunakan MCP Jarak Jauh, perhatikan batasan berikut:

  • Jenis server: MCP jarak jauh hanya berfungsi dengan server HTTP yang dapat di-streaming. Server SSE (Server-Sent Events) tidak didukung.
  • Dukungan model: MCP jarak jauh saat ini tidak berfungsi dengan model Gemini 3. Dukungan untuk Gemini 3 akan segera hadir.
  • Penamaan: Nama server MCP tidak boleh menyertakan karakter -. Sebagai gantinya, gunakan nama server snake_case.
Kolom Jenis Wajib diisi Deskripsi
type string Ya Harus berupa "mcp_server".
name string Tidak Nama tampilan untuk server MCP.
url string Tidak URL lengkap untuk endpoint server MCP.
headers object Tidak Pasangan nilai kunci yang dikirim sebagai header HTTP dengan setiap permintaan ke server (misalnya, token autentikasi).
allowed_tools array Tidak Membatasi alat mana dari server yang dapat dipanggil oleh agen.

Contoh

Python

from google import genai

client = genai.Client()

interaction = client.interactions.create(
    model="gemini-2.5-flash",
    input="Check the status of my last server deployment.",
    tools=[
        {
            "type": "mcp_server",
            "name": "Deployment Tracker",
            "url": "https://mcp.example.com/mcp",
            "headers": {"Authorization": "Bearer my-token"},
        }
    ]
)

JavaScript

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

const client = new GoogleGenAI({});

const interaction = await client.interactions.create({
    model: 'gemini-2.5-flash',
    input: 'Check the status of my last server deployment.',
    tools: [
        {
            type: 'mcp_server',
            name: 'Deployment Tracker',
            url: 'https://mcp.example.com/mcp',
            headers: { Authorization: 'Bearer my-token' }
        }
    ]
});

REST

curl -X POST "https://generativelanguage.googleapis.com/v1beta/interactions" \
-H "Content-Type: application/json" \
-H "x-goog-api-key: $GEMINI_API_KEY" \
-d '{
    "model": "gemini-2.5-flash",
    "input": "Check the status of my last server deployment.",
    "tools": [
        {
            "type": "mcp_server",
            "name": "Deployment Tracker",
            "url": "https://mcp.example.com/mcp",
            "headers": {"Authorization": "Bearer my-token"}
        }
    ]
}'

Panggilan alat streaming

Saat menggunakan alat dengan streaming, model menghasilkan panggilan fungsi sebagai urutan peristiwa step.delta di stream. Argumen alat dapat di-streaming sebagai argumen parsial menggunakan arguments. Anda harus menggabungkan delta ini untuk merekonstruksi panggilan alat lengkap sebelum mengeksekusinya.

Python

import json
from google import genai

client = genai.Client()

weather_tool = {
    "type": "function",
    "name": "get_weather",
    "description": "Gets the weather for a given location.",
    "parameters": {
        "type": "object",
        "properties": {
            "location": {"type": "string", "description": "The city and state"}
        },
        "required": ["location"]
    }
}

stream = client.interactions.create(
    model="gemini-3-flash-preview",
    input="What is the weather in Paris?",
    tools=[weather_tool],
    stream=True
)

current_calls = {}
tool_calls = []

for event in stream:
    if event.event_type == "step.start":
        if event.step.type == "function_call":
            current_calls[event.index] = {
                "id": event.step.id,
                "name": event.step.name,
                "arguments": ""
            }
    elif event.event_type == "step.delta":
        if event.delta.type == "arguments":
            if event.index in current_calls:
                current_calls[event.index]["arguments"] += event.delta.partial_arguments
        elif event.delta.type == "text":
            print(event.delta.text, end="", flush=True)

    elif event.event_type == "interaction.completed":
        for index, call in current_calls.items():
            args = call["arguments"]
            if args:
                args = json.loads(args)
            else:
                args = {}

            tool_calls.append({
                "type": "function_call",
                "id": call["id"],
                "name": call["name"],
                "arguments": args
            })

        print(f"\nFinal tool calls ready to execute:")
        print(json.dumps(tool_calls, indent=2))

JavaScript

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

const client = new GoogleGenAI({});

const weatherTool = {
    type: 'function',
    name: 'get_weather',
    description: 'Gets the weather for a given location.',
    parameters: {
        type: 'object',
        properties: {
            location: { type: 'string', description: 'The city and state' }
        },
        required: ['location']
    }
};

const stream = await client.interactions.create({
    model: 'gemini-3-flash-preview',
    input: 'What is the weather in Paris?',
    tools: [weatherTool],
    stream: true,
});

const currentCalls = new Map();
let toolCalls = [];

for await (const event of stream) {
    if (event.type === 'step.start') {
        if (event.step.type === 'function_call') {
            currentCalls.set(event.index, {
                id: event.step.id,
                name: event.step.name,
                arguments: ''
            });
        }
    } else if (event.type === 'step.delta') {
        if (event.delta.type === 'arguments') {
            if (currentCalls.has(event.index)) {
                currentCalls.get(event.index).arguments += event.delta.partial_arguments;
            }
        } else if (event.delta.type === 'text') {
            process.stdout.write(event.delta.text);
        }
    } else if (event.type === 'interaction.completed') {
        toolCalls = Array.from(currentCalls.values()).map(call => ({
            type: 'function_call',
            id: call.id,
            name: call.name,
            arguments: call.arguments ? JSON.parse(call.arguments) : {}
        }));
        console.log('\nFinal tool calls ready to execute:');
        console.log(JSON.stringify(toolCalls, null, 2));
    }
}

REST

curl -X POST "https://generativelanguage.googleapis.com/v1beta/interactions?alt=sse" \
-H "Content-Type: application/json" \
-H "x-goog-api-key: $GEMINI_API_KEY" \
-d '{
    "model": "gemini-3-flash-preview",
    "input": "What is the weather in Paris?",
    "tools": [{
        "type": "function",
        "name": "get_weather",
        "description": "Gets the weather for a given location.",
        "parameters": {
            "type": "object",
            "properties": {
                "location": {"type": "string", "description": "The city and state"}
            },
            "required": ["location"]
        }
    }],
    "stream": true
}'

Model yang didukung

Model Pemanggilan Fungsi Paralel Komposisional
Pratinjau Gemini 3.1 Pro ✔️ ✔️ ✔️
Pratinjau Gemini 3 Flash ✔️ ✔️ ✔️
Gemini 2.5 Pro ✔️ ✔️ ✔️
Gemini 2.5 Flash ✔️ ✔️ ✔️
Gemini 2.5 Flash-Lite ✔️ ✔️ ✔️
Gemini 2.0 Flash ✔️ ✔️ ✔️
Gemini 2.0 Flash-Lite X X X

Praktik terbaik

  • Deskripsi Fungsi dan Parameter: Harus jelas dan spesifik.
  • Penamaan: Gunakan nama deskriptif tanpa spasi atau karakter khusus.
  • Pengetikan Kuat: Gunakan jenis tertentu (integer, string, enum).
  • Pemilihan Alat: Tetapkan alat aktif maksimal 10-20 alat.
  • Rekayasa Perintah: Berikan konteks dan petunjuk.

  • Suhu: Gunakan suhu rendah (misalnya, 0) untuk panggilan deterministik.

  • Validasi: Validasi panggilan fungsi sebelum dieksekusi.

  • Penanganan Error: Terapkan penanganan error yang andal.

  • Keamanan: Gunakan autentikasi yang sesuai untuk API eksternal.

Catatan dan batasan

  • Hanya subset skema OpenAPI yang didukung.
  • Untuk mode any, API dapat menolak skema yang sangat besar atau bertingkat dalam.
  • Jenis parameter yang didukung di Python terbatas.