Guida rapida di Vertex AI

Questa guida rapida mostra come installare l'SDK Google Gen AI per la lingua che preferisci e poi effettuare la prima richiesta API.

Requisiti

I requisiti per iniziare a utilizzare Vertex AI dipendono dal tuo Google Cloud flusso di lavoro. Devi:

• Utenti Google Cloud nuovi e utenti della modalità Express:
  • Avere un Account Google valido @gmail.com
  • Registrati per la modalità Express
  • Disporre di una chiave API in modalità express
  • Abilita l'API Vertex AI nella console
• Utenti esistenti:
  • Avere un Account Google e un progetto Google Cloud [e-mail]
  • Abilita fatturazione
  • Abilita l'API Vertex AI nella console
  • Aver configurato un metodo di autenticazione, ad esempio:
    • Credenziali predefinite dell'applicazione (ADC) o
    • Una chiave API associata a un account di servizio

Nota: le chiavi API di AI Studio non sono supportate in Vertex AI.

Scegli il metodo di autenticazione:

ADC Chiave API

Prima di iniziare

Se hai già configurato ADC, vai al passaggio successivo.

Per configurare ADC:

Configura il tuo progetto

Seleziona un progetto, abilita la fatturazione, abilita l'API Vertex AI e installa gcloud CLI:

Accedi al tuo Account Google.

Se non ne hai già uno, registrati per creare un nuovo account.

In the Google Cloud console, on the project selector page, select or create a Google Cloud project.

Roles required to select or create a project

• Select a project: Selecting a project doesn't require a specific IAM role—you can select any project that you've been granted a role on.
• Create a project: To create a project, you need the Project Creator role (roles/resourcemanager.projectCreator), which contains the resourcemanager.projects.create permission. Learn how to grant roles.

Note: If you don't plan to keep the resources that you create in this procedure, create a project instead of selecting an existing project. After you finish these steps, you can delete the project, removing all resources associated with the project.

Go to project selector

Verify that billing is enabled for your Google Cloud project.

Enable the Vertex AI API.

Roles required to enable APIs

To enable APIs, you need the Service Usage Admin IAM role (roles/serviceusage.serviceUsageAdmin), which contains the serviceusage.services.enable permission. Learn how to grant roles.

Enable the API

Installa Google Cloud CLI.

Se utilizzi un provider di identità (IdP) esterno, devi prima accedere a gcloud CLI con la tua identità federata.

Per inizializzare gcloud CLI, esegui questo comando:

gcloud init

In the Google Cloud console, on the project selector page, select or create a Google Cloud project.

Roles required to select or create a project

• Select a project: Selecting a project doesn't require a specific IAM role—you can select any project that you've been granted a role on.
• Create a project: To create a project, you need the Project Creator role (roles/resourcemanager.projectCreator), which contains the resourcemanager.projects.create permission. Learn how to grant roles.

Note: If you don't plan to keep the resources that you create in this procedure, create a project instead of selecting an existing project. After you finish these steps, you can delete the project, removing all resources associated with the project.

Go to project selector

Verify that billing is enabled for your Google Cloud project.

Enable the Vertex AI API.

Roles required to enable APIs

To enable APIs, you need the Service Usage Admin IAM role (roles/serviceusage.serviceUsageAdmin), which contains the serviceusage.services.enable permission. Learn how to grant roles.

Enable the API

Installa Google Cloud CLI.

Se utilizzi un provider di identità (IdP) esterno, devi prima accedere a gcloud CLI con la tua identità federata.

Per inizializzare gcloud CLI, esegui questo comando:

gcloud init

Crea credenziali di autenticazione locale

Se utilizzi una shell locale, crea le credenziali di autenticazione locali per il tuo account utente:

gcloud auth application-default login

Non è necessario eseguire questa operazione se utilizzi Cloud Shell.

Se viene restituito un errore di autenticazione e utilizzi un provider di identità (IdP) esterno, verifica di aver acceduto a gcloud CLI con la tua identità federata.

Configurare i ruoli richiesti

Se utilizzi una chiave API standard o ADC, al tuo progetto devono essere concesse anche le autorizzazioni Identity and Access Management appropriate per Vertex AI. Se utilizzi una chiave API in modalità express, puoi passare al passaggio successivo.

Per ottenere le autorizzazioni necessarie per utilizzare Vertex AI, chiedi all'amministratore di concederti il ruolo IAM Vertex AI User (roles/aiplatform.user) nel progetto. Per saperne di più sulla concessione dei ruoli, consulta Gestisci l'accesso a progetti, cartelle e organizzazioni.

Potresti anche riuscire a ottenere le autorizzazioni richieste tramite i ruoli personalizzati o altri ruoli predefiniti.

Installa l'SDK e configura l'ambiente

Sulla tua macchina locale, fai clic su una delle seguenti schede per installare l'SDK per il tuo linguaggio di programmazione.

Python

Installa e aggiorna l'SDK Gen AI per Python eseguendo questo comando.

pip install --upgrade google-genai

Imposta le variabili di ambiente:

# Replace the `GOOGLE_CLOUD_PROJECT_ID` and `GOOGLE_CLOUD_LOCATION` values
# with appropriate values for your project.
export GOOGLE_CLOUD_PROJECT=GOOGLE_CLOUD_PROJECT_ID
export GOOGLE_CLOUD_LOCATION=global
export GOOGLE_GENAI_USE_VERTEXAI=True
    

Go

Installa e aggiorna l'SDK Gen AI per Go eseguendo questo comando.

go get google.golang.org/genai

Imposta le variabili di ambiente:

# Replace the `GOOGLE_CLOUD_PROJECT_ID` and `GOOGLE_CLOUD_LOCATION` values
# with appropriate values for your project.
export GOOGLE_CLOUD_PROJECT=GOOGLE_CLOUD_PROJECT_ID
export GOOGLE_CLOUD_LOCATION=global
export GOOGLE_GENAI_USE_VERTEXAI=True
    

Node.js

Installa e aggiorna l'SDK Gen AI per Node.js eseguendo questo comando.

npm install @google/genai

Imposta le variabili di ambiente:

# Replace the `GOOGLE_CLOUD_PROJECT_ID` and `GOOGLE_CLOUD_LOCATION` values
# with appropriate values for your project.
export GOOGLE_CLOUD_PROJECT=GOOGLE_CLOUD_PROJECT_ID
export GOOGLE_CLOUD_LOCATION=global
export GOOGLE_GENAI_USE_VERTEXAI=True
    

Java

Installa e aggiorna l'SDK Gen AI per Java eseguendo questo comando.

Maven

Aggiungi quanto segue a pom.xml:

<dependencies>
  <dependency>
    <groupId>com.google.genai</groupId>
    <artifactId>google-genai</artifactId>
    <version>0.7.0</version>
  </dependency>
</dependencies>
    

Imposta le variabili di ambiente:

# Replace the `GOOGLE_CLOUD_PROJECT_ID` and `GOOGLE_CLOUD_LOCATION` values
# with appropriate values for your project.
export GOOGLE_CLOUD_PROJECT=GOOGLE_CLOUD_PROJECT_ID
export GOOGLE_CLOUD_LOCATION=global
export GOOGLE_GENAI_USE_VERTEXAI=True
    

REST

Imposta le variabili di ambiente:

GOOGLE_CLOUD_PROJECT=GOOGLE_CLOUD_PROJECT_ID
GOOGLE_CLOUD_LOCATION="global"
API_ENDPOINT="https://aiplatform.googleapis.com"
MODEL_ID="gemini-2.5-flash"
GENERATE_CONTENT_API="generateContent"
    

Sostituisci GOOGLE_CLOUD_PROJECT_ID con l'ID progetto Google Cloud .

Effettua la tua prima richiesta

Utilizza il metodo generateContent per inviare una richiesta all'API Gemini in Vertex AI:

Python

from google import genai
from google.genai.types import HttpOptions

client = genai.Client(http_options=HttpOptions(api_version="v1"))
response = client.models.generate_content(
    model="gemini-2.5-flash",
    contents="How does AI work?",
)
print(response.text)
# Example response:
# Okay, let's break down how AI works. It's a broad field, so I'll focus on the ...
#
# Here's a simplified overview:
# ...

Go

import (
	"context"
	"fmt"
	"io"

	"google.golang.org/genai"
)

// generateWithText shows how to generate text using a text prompt.
func generateWithText(w io.Writer) error {
	ctx := context.Background()

	client, err := genai.NewClient(ctx, &genai.ClientConfig{
		HTTPOptions: genai.HTTPOptions{APIVersion: "v1"},
	})
	if err != nil {
		return fmt.Errorf("failed to create genai client: %w", err)
	}

	resp, err := client.Models.GenerateContent(ctx,
		"gemini-2.5-flash",
		genai.Text("How does AI work?"),
		nil,
	)
	if err != nil {
		return fmt.Errorf("failed to generate content: %w", err)
	}

	respText := resp.Text()

	fmt.Fprintln(w, respText)
	// Example response:
	// That's a great question! Understanding how AI works can feel like ...
	// ...
	// **1. The Foundation: Data and Algorithms**
	// ...

	return nil
}

Node.js

const {GoogleGenAI} = require('@google/genai');

const GOOGLE_CLOUD_PROJECT = process.env.GOOGLE_CLOUD_PROJECT;
const GOOGLE_CLOUD_LOCATION = process.env.GOOGLE_CLOUD_LOCATION || 'global';

async function generateContent(
  projectId = GOOGLE_CLOUD_PROJECT,
  location = GOOGLE_CLOUD_LOCATION
) {
  const client = new GoogleGenAI({
    vertexai: true,
    project: projectId,
    location: location,
  });

  const response = await client.models.generateContent({
    model: 'gemini-3-flash-preview',
    contents: 'How does AI work?',
  });

  console.log(response.text);

  return response.text;
}

Java

import com.google.genai.Client;
import com.google.genai.types.GenerateContentResponse;
import com.google.genai.types.HttpOptions;

public class TextGenerationWithText {

  public static void main(String[] args) {
    // TODO(developer): Replace these variables before running the sample.
    String modelId = "gemini-2.5-flash";
    generateContent(modelId);
  }

  // Generates text with text input
  public static String generateContent(String modelId) {
    // Initialize client that will be used to send requests. This client only needs to be created
    // once, and can be reused for multiple requests.
    try (Client client =
        Client.builder()
            .location("global")
            .vertexAI(true)
            .httpOptions(HttpOptions.builder().apiVersion("v1").build())
            .build()) {

      GenerateContentResponse response =
          client.models.generateContent(modelId, "How does AI work?", null);

      System.out.print(response.text());
      // Example response:
      // Okay, let's break down how AI works. It's a broad field, so I'll focus on the ...
      //
      // Here's a simplified overview:
      // ...
      return response.text();
    }
  }
}

C#

using Google.GenAI;
using Google.GenAI.Types;
using System;
using System.Threading.Tasks;

public class TextGenWithTxt
{
    public async Task<string> GenerateContent(
        string projectId = "your-project-id",
        string location = "global",
        string model = "gemini-2.5-flash")
    {
        await using var client = new Client(
            project: projectId,
            location: location,
            vertexAI: true,
            httpOptions: new HttpOptions { ApiVersion = "v1" });

        GenerateContentResponse response = await client.Models.GenerateContentAsync(model: model, contents: "How does AI work?");

        string responseText = response.Candidates[0].Content.Parts[0].Text;
        Console.WriteLine(responseText);
        // Example response:
        // AI, or Artificial Intelligence, at its core, is about creating machines that can perform...
        // Here's a breakdown of how it generally works...
        return responseText;
    }
}

REST

Per inviare questa richiesta di prompt, esegui il comando curl dalla riga di comando o includi la chiamata REST nella tua applicazione.

curl \
-X POST \
-H "Content-Type: application/json" \
-H "Authorization: Bearer $(gcloud auth print-access-token)" \
"${API_ENDPOINT}/v1/projects/${GOOGLE_CLOUD_PROJECT}/locations/${GOOGLE_CLOUD_LOCATION}/publishers/google/models/${MODEL_ID}:${GENERATE_CONTENT_API}" -d \
$'{
  "contents": {
    "role": "user",
    "parts": {
      "text": "Explain how AI works in a few words"
    }
  }
}'

Il modello restituisce una risposta. Tieni presente che la risposta viene generata in sezioni e ogni sezione viene valutata separatamente per la sicurezza.

Quando utilizzi un endpoint API regionale (ad esempio, us-central1), la regione dell'URL dell'endpoint determina dove viene elaborata la richiesta. Qualsiasi località in conflitto nel percorso della risorsa viene ignorata.

Genera immagini

Nota: la generazione di immagini con Gemini è in anteprima. Se hai bisogno di funzionalità di generazione di immagini pronte per la produzione, utilizza Imagen. Per ulteriori informazioni, consulta la guida rapida di Imagen su Vertex AI.

Gemini può generare ed elaborare immagini in modo conversazionale. Puoi fornire prompt a Gemini con testo, immagini o una combinazione di entrambi per eseguire varie attività correlate alle immagini, come la generazione e la modifica di immagini. Il seguente codice mostra come generare un'immagine in base a un prompt descrittivo:

Devi includere responseModalities: ["TEXT", "IMAGE"] nella configurazione. L'output solo immagine non è supportato con questi modelli.

Python

import os
from io import BytesIO

from google import genai
from google.genai.types import GenerateContentConfig, Modality
from PIL import Image

client = genai.Client()

response = client.models.generate_content(
    model="gemini-3-pro-image-preview",
    contents=("Generate an image of the Eiffel tower with fireworks in the background."),
    config=GenerateContentConfig(
        response_modalities=[Modality.TEXT, Modality.IMAGE],
    ),
)
for part in response.candidates[0].content.parts:
    if part.text:
        print(part.text)
    elif part.inline_data:
        image = Image.open(BytesIO((part.inline_data.data)))
        # Ensure the output directory exists
        output_dir = "output_folder"
        os.makedirs(output_dir, exist_ok=True)
        image.save(os.path.join(output_dir, "example-image-eiffel-tower.png"))

Go

import (
	"context"
	"fmt"
	"io"
	"os"

	"google.golang.org/genai"
)

// generateMMFlashWithText demonstrates how to generate both text and image outputs.
func generateMMFlashWithText(w io.Writer) error {
	ctx := context.Background()

	client, err := genai.NewClient(ctx, &genai.ClientConfig{
		HTTPOptions: genai.HTTPOptions{APIVersion: "v1"},
	})
	if err != nil {
		return fmt.Errorf("failed to create genai client: %w", err)
	}

	modelName := "gemini-2.5-flash-image"
	contents := []*genai.Content{
		{
			Parts: []*genai.Part{
				{Text: "Generate an image of the Eiffel tower with fireworks in the background."},
			},
			Role: genai.RoleUser,
		},
	}

	resp, err := client.Models.GenerateContent(ctx,
		modelName,
		contents,
		&genai.GenerateContentConfig{
			ResponseModalities: []string{
				string(genai.ModalityText),
				string(genai.ModalityImage),
			},
			CandidateCount: int32(1),
			SafetySettings: []*genai.SafetySetting{
				{Method: genai.HarmBlockMethodProbability},
				{Category: genai.HarmCategoryDangerousContent},
				{Threshold: genai.HarmBlockThresholdBlockMediumAndAbove},
			},
		},
	)
	if err != nil {
		return fmt.Errorf("failed to generate content: %w", err)
	}

	if len(resp.Candidates) == 0 || resp.Candidates[0].Content == nil {
		return fmt.Errorf("no candidates returned")
	}
	var fileName string
	for _, part := range resp.Candidates[0].Content.Parts {
		if part.Text != "" {
			fmt.Fprintln(w, part.Text)
		} else if part.InlineData != nil {
			fileName = "example-image-eiffel-tower.png"
			if err := os.WriteFile(fileName, part.InlineData.Data, 0o644); err != nil {
				return fmt.Errorf("failed to save image: %w", err)
			}
		}
	}
	fmt.Fprintln(w, fileName)

	// Example response:
	// I will generate an image of the Eiffel Tower at night, with a vibrant display of
	// colorful fireworks exploding in the dark sky behind it.
	// ....
	return nil
}

Node.js

const fs = require('fs');
const {GoogleGenAI, Modality} = require('@google/genai');

const GOOGLE_CLOUD_PROJECT = process.env.GOOGLE_CLOUD_PROJECT;
const GOOGLE_CLOUD_LOCATION =
  process.env.GOOGLE_CLOUD_LOCATION || 'us-central1';

async function generateImage(
  projectId = GOOGLE_CLOUD_PROJECT,
  location = GOOGLE_CLOUD_LOCATION
) {
  const client = new GoogleGenAI({
    vertexai: true,
    project: projectId,
    location: location,
  });

  const response = await client.models.generateContentStream({
    model: 'gemini-2.5-flash-image',
    contents:
      'Generate an image of the Eiffel tower with fireworks in the background.',
    config: {
      responseModalities: [Modality.TEXT, Modality.IMAGE],
    },
  });

  const generatedFileNames = [];
  let imageIndex = 0;

  for await (const chunk of response) {
    const text = chunk.text;
    const data = chunk.data;
    if (text) {
      console.debug(text);
    } else if (data) {
      const outputDir = 'output-folder';
      if (!fs.existsSync(outputDir)) {
        fs.mkdirSync(outputDir, {recursive: true});
      }
      const fileName = `${outputDir}/generate_content_streaming_image_${imageIndex++}.png`;
      console.debug(`Writing response image to file: ${fileName}.`);
      try {
        fs.writeFileSync(fileName, data);
        generatedFileNames.push(fileName);
      } catch (error) {
        console.error(`Failed to write image file ${fileName}:`, error);
      }
    }
  }

  // Example response:
  //  I will generate an image of the Eiffel Tower at night, with a vibrant display of
  //  colorful fireworks exploding in the dark sky behind it. The tower will be
  //  illuminated, standing tall as the focal point of the scene, with the bursts of
  //  light from the fireworks creating a festive atmosphere.

  return generatedFileNames;
}

Java

import com.google.genai.Client;
import com.google.genai.types.Blob;
import com.google.genai.types.Candidate;
import com.google.genai.types.Content;
import com.google.genai.types.GenerateContentConfig;
import com.google.genai.types.GenerateContentResponse;
import com.google.genai.types.Part;
import com.google.genai.types.SafetySetting;
import java.awt.image.BufferedImage;
import java.io.ByteArrayInputStream;
import java.io.File;
import java.io.IOException;
import java.util.ArrayList;
import java.util.List;
import javax.imageio.ImageIO;

public class ImageGenMmFlashWithText {

  public static void main(String[] args) throws IOException {
    // TODO(developer): Replace these variables before running the sample.
    String modelId = "gemini-2.5-flash-image";
    String outputFile = "resources/output/example-image-eiffel-tower.png";
    generateContent(modelId, outputFile);
  }

  // Generates an image with text input
  public static void generateContent(String modelId, String outputFile) throws IOException {
    // Client Initialization. Once created, it can be reused for multiple requests.
    try (Client client = Client.builder().location("global").vertexAI(true).build()) {

      GenerateContentConfig contentConfig =
          GenerateContentConfig.builder()
              .responseModalities("TEXT", "IMAGE")
              .candidateCount(1)
              .safetySettings(
                  SafetySetting.builder()
                      .method("PROBABILITY")
                      .category("HARM_CATEGORY_DANGEROUS_CONTENT")
                      .threshold("BLOCK_MEDIUM_AND_ABOVE")
                      .build())
              .build();

      GenerateContentResponse response =
          client.models.generateContent(
              modelId,
              "Generate an image of the Eiffel tower with fireworks in the background.",
              contentConfig);

      // Get parts of the response
      List<Part> parts =
          response
              .candidates()
              .flatMap(candidates -> candidates.stream().findFirst())
              .flatMap(Candidate::content)
              .flatMap(Content::parts)
              .orElse(new ArrayList<>());

      // For each part print text if present, otherwise read image data if present and
      // write it to the output file
      for (Part part : parts) {
        if (part.text().isPresent()) {
          System.out.println(part.text().get());
        } else if (part.inlineData().flatMap(Blob::data).isPresent()) {
          BufferedImage image =
              ImageIO.read(new ByteArrayInputStream(part.inlineData().flatMap(Blob::data).get()));
          ImageIO.write(image, "png", new File(outputFile));
        }
      }

      System.out.println("Content written to: " + outputFile);
      // Example response:
      // Here is the Eiffel Tower with fireworks in the background...
      //
      // Content written to: resources/output/example-image-eiffel-tower.png
    }
  }
}

Comprensione delle immagini

Gemini può comprendere anche le immagini. Il seguente codice utilizza l'immagine generata nella sezione precedente e un modello diverso per dedurre informazioni sull'immagine:

Python

from google import genai
from google.genai.types import HttpOptions, Part

client = genai.Client(http_options=HttpOptions(api_version="v1"))
response = client.models.generate_content(
    model="gemini-2.5-flash",
    contents=[
        "What is shown in this image?",
        Part.from_uri(
            file_uri="gs://cloud-samples-data/generative-ai/image/scones.jpg",
            mime_type="image/jpeg",
        ),
    ],
)
print(response.text)
# Example response:
# The image shows a flat lay of blueberry scones arranged on parchment paper. There are ...

Go

import (
	"context"
	"fmt"
	"io"

	genai "google.golang.org/genai"
)

// generateWithTextImage shows how to generate text using both text and image input
func generateWithTextImage(w io.Writer) error {
	ctx := context.Background()

	client, err := genai.NewClient(ctx, &genai.ClientConfig{
		HTTPOptions: genai.HTTPOptions{APIVersion: "v1"},
	})
	if err != nil {
		return fmt.Errorf("failed to create genai client: %w", err)
	}

	modelName := "gemini-2.5-flash"
	contents := []*genai.Content{
		{Parts: []*genai.Part{
			{Text: "What is shown in this image?"},
			{FileData: &genai.FileData{
				// Image source: https://storage.googleapis.com/cloud-samples-data/generative-ai/image/scones.jpg
				FileURI:  "gs://cloud-samples-data/generative-ai/image/scones.jpg",
				MIMEType: "image/jpeg",
			}},
		},
			Role: genai.RoleUser},
	}

	resp, err := client.Models.GenerateContent(ctx, modelName, contents, nil)
	if err != nil {
		return fmt.Errorf("failed to generate content: %w", err)
	}

	respText := resp.Text()

	fmt.Fprintln(w, respText)

	// Example response:
	// The image shows an overhead shot of a rustic, artistic arrangement on a surface that ...

	return nil
}

Node.js

const {GoogleGenAI} = require('@google/genai');

const GOOGLE_CLOUD_PROJECT = process.env.GOOGLE_CLOUD_PROJECT;
const GOOGLE_CLOUD_LOCATION = process.env.GOOGLE_CLOUD_LOCATION || 'global';

async function generateContent(
  projectId = GOOGLE_CLOUD_PROJECT,
  location = GOOGLE_CLOUD_LOCATION
) {
  const client = new GoogleGenAI({
    vertexai: true,
    project: projectId,
    location: location,
  });

  const image = {
    fileData: {
      fileUri: 'gs://cloud-samples-data/generative-ai/image/scones.jpg',
      mimeType: 'image/jpeg',
    },
  };

  const response = await client.models.generateContent({
    model: 'gemini-2.5-flash',
    contents: [image, 'What is shown in this image?'],
  });

  console.log(response.text);

  return response.text;
}

Java

import com.google.genai.Client;
import com.google.genai.types.Content;
import com.google.genai.types.GenerateContentResponse;
import com.google.genai.types.HttpOptions;
import com.google.genai.types.Part;

public class TextGenerationWithTextAndImage {

  public static void main(String[] args) {
    // TODO(developer): Replace these variables before running the sample.
    String modelId = "gemini-2.5-flash";
    generateContent(modelId);
  }

  // Generates text with text and image input
  public static String generateContent(String modelId) {
    // Initialize client that will be used to send requests. This client only needs to be created
    // once, and can be reused for multiple requests.
    try (Client client =
        Client.builder()
            .location("global")
            .vertexAI(true)
            .httpOptions(HttpOptions.builder().apiVersion("v1").build())
            .build()) {

      GenerateContentResponse response =
          client.models.generateContent(
              modelId,
              Content.fromParts(
                  Part.fromText("What is shown in this image?"),
                  Part.fromUri(
                      "gs://cloud-samples-data/generative-ai/image/scones.jpg", "image/jpeg")),
              null);

      System.out.print(response.text());
      // Example response:
      // The image shows a flat lay of blueberry scones arranged on parchment paper. There are ...
      return response.text();
    }
  }
}

Esecuzione del codice

La funzionalità di esecuzione del codice dell'API Gemini in Vertex AI consente al modello di generare ed eseguire codice Python e di apprendere in modo iterativo dai risultati fino a ottenere un output finale. Vertex AI fornisce l'esecuzione del codice come strumento, in modo simile alle chiamate di funzione. Puoi utilizzare questa funzionalità di esecuzione del codice per creare applicazioni che sfruttano il ragionamento basato sul codice e che producono output di testo. Ad esempio:

Python

from google import genai
from google.genai.types import (
    HttpOptions,
    Tool,
    ToolCodeExecution,
    GenerateContentConfig,
)

client = genai.Client(http_options=HttpOptions(api_version="v1"))
model_id = "gemini-2.5-flash"

code_execution_tool = Tool(code_execution=ToolCodeExecution())
response = client.models.generate_content(
    model=model_id,
    contents="Calculate 20th fibonacci number. Then find the nearest palindrome to it.",
    config=GenerateContentConfig(
        tools=[code_execution_tool],
        temperature=0,
    ),
)
print("# Code:")
print(response.executable_code)
print("# Outcome:")
print(response.code_execution_result)

# Example response:
# # Code:
# def fibonacci(n):
#     if n <= 0:
#         return 0
#     elif n == 1:
#         return 1
#     else:
#         a, b = 0, 1
#         for _ in range(2, n + 1):
#             a, b = b, a + b
#         return b
#
# fib_20 = fibonacci(20)
# print(f'{fib_20=}')
#
# # Outcome:
# fib_20=6765

Go

import (
	"context"
	"fmt"
	"io"

	genai "google.golang.org/genai"
)

// generateWithCodeExec shows how to generate text using the code execution tool.
func generateWithCodeExec(w io.Writer) error {
	ctx := context.Background()

	client, err := genai.NewClient(ctx, &genai.ClientConfig{
		HTTPOptions: genai.HTTPOptions{APIVersion: "v1"},
	})
	if err != nil {
		return fmt.Errorf("failed to create genai client: %w", err)
	}

	prompt := "Calculate 20th fibonacci number. Then find the nearest palindrome to it."
	contents := []*genai.Content{
		{Parts: []*genai.Part{
			{Text: prompt},
		},
			Role: genai.RoleUser},
	}
	config := &genai.GenerateContentConfig{
		Tools: []*genai.Tool{
			{CodeExecution: &genai.ToolCodeExecution{}},
		},
		Temperature: genai.Ptr(float32(0.0)),
	}
	modelName := "gemini-2.5-flash"

	resp, err := client.Models.GenerateContent(ctx, modelName, contents, config)
	if err != nil {
		return fmt.Errorf("failed to generate content: %w", err)
	}

	for _, p := range resp.Candidates[0].Content.Parts {
		if p.Text != "" {
			fmt.Fprintf(w, "Gemini: %s", p.Text)
		}
		if p.ExecutableCode != nil {
			fmt.Fprintf(w, "Language: %s\n%s\n", p.ExecutableCode.Language, p.ExecutableCode.Code)
		}
		if p.CodeExecutionResult != nil {
			fmt.Fprintf(w, "Outcome: %s\n%s\n", p.CodeExecutionResult.Outcome, p.CodeExecutionResult.Output)
		}
	}

	// Example response:
	// Gemini: Okay, I can do that. First, I'll calculate the 20th Fibonacci number. Then, I need ...
	//
	// Language: PYTHON
	//
	// def fibonacci(n):
	//    ...
	//
	// fib_20 = fibonacci(20)
	// print(f'{fib_20=}')
	//
	// Outcome: OUTCOME_OK
	// fib_20=6765
	//
	// Now that I have the 20th Fibonacci number (6765), I need to find the nearest palindrome. ...
	// ...

	return nil
}

Node.js

const {GoogleGenAI} = require('@google/genai');

const GOOGLE_CLOUD_PROJECT = process.env.GOOGLE_CLOUD_PROJECT;
const GOOGLE_CLOUD_LOCATION = process.env.GOOGLE_CLOUD_LOCATION || 'global';

async function generateAndExecuteCode(
  projectId = GOOGLE_CLOUD_PROJECT,
  location = GOOGLE_CLOUD_LOCATION
) {
  const client = new GoogleGenAI({
    vertexai: true,
    project: projectId,
    location: location,
  });

  const response = await client.models.generateContent({
    model: 'gemini-2.5-flash',
    contents:
      'Calculate 20th fibonacci number. Then find the nearest palindrome to it.',
    config: {
      tools: [{codeExecution: {}}],
      temperature: 0,
    },
  });

  console.debug(response.executableCode);

  // Example response:
  // Code:
  // function fibonacci(n) {
  //   if (n <= 0) {
  //     return 0;
  //   } else if (n === 1) {
  //     return 1;
  //   } else {
  //     let a = 0, b = 1;
  //     for (let i = 2; i <= n; i++) {
  //       [a, b] = [b, a + b];
  //     }
  //     return b;
  //   }
  // }
  //
  // const fib20 = fibonacci(20);
  // console.log(`fib20=${fib20}`);

  console.debug(response.codeExecutionResult);

  // Outcome:
  // fib20=6765

  return response.codeExecutionResult;
}

Java

import com.google.genai.Client;
import com.google.genai.types.GenerateContentConfig;
import com.google.genai.types.GenerateContentResponse;
import com.google.genai.types.HttpOptions;
import com.google.genai.types.Tool;
import com.google.genai.types.ToolCodeExecution;

public class ToolsCodeExecWithText {

  public static void main(String[] args) {
    // TODO(developer): Replace these variables before running the sample.
    String modelId = "gemini-2.5-flash";
    generateContent(modelId);
  }

  // Generates text using the Code Execution tool
  public static String generateContent(String modelId) {
    // Initialize client that will be used to send requests. This client only needs to be created
    // once, and can be reused for multiple requests.
    try (Client client =
        Client.builder()
            .location("global")
            .vertexAI(true)
            .httpOptions(HttpOptions.builder().apiVersion("v1").build())
            .build()) {

      // Create a GenerateContentConfig and set codeExecution tool
      GenerateContentConfig contentConfig =
          GenerateContentConfig.builder()
              .tools(Tool.builder().codeExecution(ToolCodeExecution.builder().build()).build())
              .temperature(0.0F)
              .build();

      GenerateContentResponse response =
          client.models.generateContent(
              modelId,
              "Calculate 20th fibonacci number. Then find the nearest palindrome to it.",
              contentConfig);

      System.out.println("Code: \n" + response.executableCode());
      System.out.println("Outcome: \n" + response.codeExecutionResult());
      // Example response
      // Code:
      // def fibonacci(n):
      //    if n <= 0:
      //        return 0
      //    elif n == 1:
      //        return 1
      //    else:
      //        a, b = 1, 1
      //        for _ in range(2, n):
      //            a, b = b, a + b
      //        return b
      //
      // fib_20 = fibonacci(20)
      // print(f'{fib_20=}')
      //
      // Outcome:
      // fib_20=6765
      return response.executableCode();
    }
  }
}

Per altri esempi di esecuzione del codice, consulta la documentazione sull'esecuzione del codice.

Passaggi successivi

Ora che hai effettuato la tua prima richiesta API, ti consigliamo di consultare le seguenti guide che mostrano come configurare funzionalità di Vertex AI più avanzate per il codice di produzione:

Guida

Librerie Google Gen AI

Scarica e installa le librerie più recenti per l'API Gemini.

Guida

Accedi ai modelli Gemini utilizzando le librerie OpenAI

Scopri come utilizzare le librerie OpenAI per implementare e chiamare i modelli Gemini in Vertex AI.

Guida

Inizia a usare Gemini 3

Scopri Gemini 3, la nostra famiglia di modelli più intelligente di sempre, basata su un ragionamento all'avanguardia.

Panoramica

Esplora i modelli Google

Esplora gli ultimi modelli Google supportati in Vertex AI, tra cui Gemini, Imagen, Veo e Gemma.