Combinare strumenti integrati e chiamata di funzione

Gemini consente la combinazione di strumenti integrati, come google_search, e chiamata di funzioni (nota anche come strumenti personalizzati) in una singola interazione conservando ed esponendo la cronologia del contesto delle chiamate agli strumenti. Le combinazioni di strumenti integrati e personalizzati consentono workflow complessi e basati su agenti in cui, ad esempio, il modello può basarsi su dati web in tempo reale prima di richiamare la logica di business specifica.

Ecco un esempio che consente combinazioni di strumenti integrati e personalizzati con google_search e una funzione personalizzata getWeather:

Python

# This will only work for SDK newer than 2.0.0
from google import genai

client = genai.Client()

getWeather = {
    "type": "function",
    "name": "getWeather",
    "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"],
    },
}

# The Interactions API manages context automatically across tool calls.
# The model will first use Google Search, then call getWeather.
interaction = client.interactions.create(
    model="gemini-3.6-flash",
    input="What is the northernmost city in the United States? What's the weather like there today?",
    tools=[
        {"type": "google_search"},
        getWeather,
    ],
)

# Process steps: the interaction contains search results and a function call
for step in interaction.steps:
    if step.type == "function_call":
        print(f"Function call: {step.name} with args: {step.arguments}")
        # In a real application, you would execute the function here
        # and provide the result back to the model.

JavaScript

// This will only work for SDK newer than 2.0.0
import { GoogleGenAI } from '@google/genai';

const client = new GoogleGenAI({});

const getWeather = {
    type: "function",
    name: "getWeather",
    description: "Get the weather in a given location",
    parameters: {
        type: "object",
        properties: {
            location: {
                type: "string",
                description: "The city and state, e.g. San Francisco, CA"
            }
        },
        required: ["location"]
    }
};

// The Interactions API manages context automatically across tool calls.
// The model will first use Google Search, then call getWeather.
const interaction = await client.interactions.create({
    model: "gemini-3.6-flash",
    input: "What is the northernmost city in the United States? What's the weather like there today?",
    tools: [
        { type: "google_search" },
        getWeather,
    ],
});

// Process steps: the interaction contains search results and a function call
for (const step of interaction.steps) {
    if (step.type === "function_call") {
        console.log(`Function call: ${step.name} with args: