Démarrage rapide : Utiliser des bibliothèques

Cette page explique comment utiliser l'API Vertex AI Agent Builder dans votre langage de programmation favori.

Avant de commencer

Sign in to your Google Cloud account. If you're new to Google Cloud, create an account to evaluate how our products perform in real-world scenarios. New customers also get $300 in free credits to run, test, and deploy workloads.

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 Agent Builder 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

Create a service account:

1. Ensure that you have the Create Service Accounts IAM role (roles/iam.serviceAccountCreator) and the Project IAM Admin role (roles/resourcemanager.projectIamAdmin). Learn how to grant roles.

2. In the Google Cloud console, go to the Create service account page.

   Go to Create service account
3. Select your project.

4. In the Service account name field, enter a name. The Google Cloud console fills in the Service account ID field based on this name.

   In the Service account description field, enter a description. For example, Service account for quickstart.

5. Click Create and continue.

6. Grant the Project > Owner role to the service account.

   To grant the role, find the Select a role list, then select Project > Owner.

   Note: The Role field affects which resources the service account can access in your project. You can revoke these roles or grant additional roles later. In production environments, do not grant the Owner, Editor, or Viewer roles. Instead, grant a predefined role or custom role that meets your needs.
7. Click Continue.

8. Click Done to finish creating the service account.

   Do not close your browser window. You will use it in the next step.

Create a service account key:

1. In the Google Cloud console, click the email address for the service account that you created.
2. Click Keys.
3. Click Add key, and then click Create new key.
4. Click Create. A JSON key file is downloaded to your computer.
5. Click Close.

Set the environment variable GOOGLE_APPLICATION_CREDENTIALS to the path of the JSON file that contains your credentials. This variable applies only to your current shell session, so if you open a new session, set the variable again.

Example: Linux or macOS

export GOOGLE_APPLICATION_CREDENTIALS="KEY_PATH"

Replace KEY_PATH with the path of the JSON file that contains your credentials.

For example:

export GOOGLE_APPLICATION_CREDENTIALS="/home/user/Downloads/service-account-file.json"

Example: Windows

For PowerShell:

$env:GOOGLE_APPLICATION_CREDENTIALS="KEY_PATH"

Replace KEY_PATH with the path of the JSON file that contains your credentials.

For example:

$env:GOOGLE_APPLICATION_CREDENTIALS="C:\Users\username\Downloads\service-account-file.json"

For command prompt:

set GOOGLE_APPLICATION_CREDENTIALS=KEY_PATH

Replace KEY_PATH with the path of the JSON file that contains your credentials.

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 Agent Builder 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

Create a service account:

1. Ensure that you have the Create Service Accounts IAM role (roles/iam.serviceAccountCreator) and the Project IAM Admin role (roles/resourcemanager.projectIamAdmin). Learn how to grant roles.

2. In the Google Cloud console, go to the Create service account page.

   Go to Create service account
3. Select your project.

4. In the Service account name field, enter a name. The Google Cloud console fills in the Service account ID field based on this name.

   In the Service account description field, enter a description. For example, Service account for quickstart.

5. Click Create and continue.

6. Grant the Project > Owner role to the service account.

   To grant the role, find the Select a role list, then select Project > Owner.

   Note: The Role field affects which resources the service account can access in your project. You can revoke these roles or grant additional roles later. In production environments, do not grant the Owner, Editor, or Viewer roles. Instead, grant a predefined role or custom role that meets your needs.
7. Click Continue.

8. Click Done to finish creating the service account.

   Do not close your browser window. You will use it in the next step.

Create a service account key:

1. In the Google Cloud console, click the email address for the service account that you created.
2. Click Keys.
3. Click Add key, and then click Create new key.
4. Click Create. A JSON key file is downloaded to your computer.
5. Click Close.

Set the environment variable GOOGLE_APPLICATION_CREDENTIALS to the path of the JSON file that contains your credentials. This variable applies only to your current shell session, so if you open a new session, set the variable again.

Example: Linux or macOS

export GOOGLE_APPLICATION_CREDENTIALS="KEY_PATH"

Replace KEY_PATH with the path of the JSON file that contains your credentials.

For example:

export GOOGLE_APPLICATION_CREDENTIALS="/home/user/Downloads/service-account-file.json"

Example: Windows

For PowerShell:

$env:GOOGLE_APPLICATION_CREDENTIALS="KEY_PATH"

Replace KEY_PATH with the path of the JSON file that contains your credentials.

For example:

$env:GOOGLE_APPLICATION_CREDENTIALS="C:\Users\username\Downloads\service-account-file.json"

For command prompt:

set GOOGLE_APPLICATION_CREDENTIALS=KEY_PATH

Replace KEY_PATH with the path of the JSON file that contains your credentials.

Installer la bibliothèque cliente

C#

Pour savoir comment configurer votre environnement de développement C#, consultez le guide de configuration d'un environnement de développement C#.

Install-Package Google.Cloud.PubSub.V1 -Pre

Go

go get cloud.google.com/go/pubsub

Java

Pour savoir comment configurer votre environnement de développement Java, consultez le guide de configuration d'un environnement de développement Java.

If you are using Maven, add the following to your pom.xml file. For more information about BOMs, see The Google Cloud Platform Libraries BOM.

<dependencyManagement>
  <dependencies>
    <dependency>
      <groupId>com.google.cloud</groupId>
      <artifactId>libraries-bom</artifactId>
      <version>26.71.0</version>
      <type>pom</type>
      <scope>import</scope>
    </dependency>
  </dependencies>
</dependencyManagement>

<dependencies>
  <dependency>
    <groupId>com.google.cloud</groupId>
    <artifactId>google-cloud-pubsub</artifactId>
  </dependency>

</dependencies>

If you are using Gradle, add the following to your dependencies:

implementation platform('com.google.cloud:libraries-bom:26.72.0')

implementation 'com.google.cloud:google-cloud-pubsub'

If you are using sbt, add the following to your dependencies:

libraryDependencies += "com.google.cloud" % "google-cloud-pubsub" % "1.143.1"

If you're using Visual Studio Code or IntelliJ, you can add client libraries to your project using the following IDE plugins:

• Cloud Code for VS Code
• Cloud Code for IntelliJ

The plugins provide additional functionality, such as key management for service accounts. Refer to each plugin's documentation for details.

Note: Cloud Java client libraries do not currently support Android.

Node.js

Pour savoir comment configurer votre environnement de développement Node.js, consultez le guide de configuration d'un environnement de développement Node.js.

npm install @google-cloud/pubsub

PHP

composer require google/cloud-pubsub

Python

Pour savoir comment configurer votre environnement de développement Python, consultez le guide de configuration d'un environnement de développement Python.

pip install --upgrade google-cloud-pubsub

Ruby

Pour savoir comment configurer votre environnement de développement Ruby, consultez le guide de configuration d'un environnement de développement Ruby.

gem install google-cloud-pubsub

Faire quelque chose

Vous pouvez maintenant utiliser Vertex AI Agent Builder pour effectuer une action. Exécutez le code suivant pour effectuer votre première opération :

C#

Pour vous authentifier auprès de Vertex AI Agent Builder, configurez les Identifiants par défaut de l'application. Pour en savoir plus, consultez Configurer l'authentification pour un environnement de développement local.

using Google.Cloud.PubSub.V1;
using Grpc.Core;
using System;

public class CreateTopicSample
{
    public Topic CreateTopic(string projectId, string topicId)
    {
        PublisherServiceApiClient publisher = PublisherServiceApiClient.Create();
        var topicName = TopicName.FromProjectTopic(projectId, topicId);
        Topic topic = null;

        try
        {
            topic = publisher.CreateTopic(topicName);
            Console.WriteLine($"Topic {topic.Name} created.");
        }
        catch (RpcException e) when (e.Status.StatusCode == StatusCode.AlreadyExists)
        {
            Console.WriteLine($"Topic {topicName} already exists.");
        }
        return topic;
    }
}

Go

Pour vous authentifier auprès de Vertex AI Agent Builder, configurez les Identifiants par défaut de l'application. Pour en savoir plus, consultez Configurer l'authentification pour un environnement de développement local.

// Sample pubsub-quickstart creates a Google Cloud Pub/Sub topic.
package main

import (
	"context"
	"fmt"
	"log"

	"cloud.google.com/go/pubsub/v2"
	"cloud.google.com/go/pubsub/v2/apiv1/pubsubpb"
)

func main() {
	ctx := context.Background()

	// Sets your Google Cloud Platform project ID.
	projectID := "YOUR_PROJECT_ID"

	// Creates a client.
	client, err := pubsub.NewClient(ctx, projectID)
	if err != nil {
		log.Fatalf("Failed to create client: %v", err)
	}
	defer client.Close()

	// Sets the id for the new topic.
	topicID := "my-topic"
	pbTopic := &pubsubpb.Topic{
		Name: fmt.Sprintf("projects/%s/topics/%s", projectID, topicID),
	}

	// Creates the new topic.
	topic, err := client.TopicAdminClient.CreateTopic(ctx, pbTopic)
	if err != nil {
		log.Fatalf("Failed to create topic: %v", err)
	}

	fmt.Printf("Topic %v created.\n", topic)
}

Java

Pour vous authentifier auprès de Vertex AI Agent Builder, configurez les Identifiants par défaut de l'application. Pour en savoir plus, consultez Configurer l'authentification pour un environnement de développement local.

import com.google.cloud.pubsub.v1.TopicAdminClient;
import com.google.pubsub.v1.Topic;
import com.google.pubsub.v1.TopicName;
import java.io.IOException;

public class CreateTopicExample {
  public static void main(String... args) throws Exception {
    // TODO(developer): Replace these variables before running the sample.
    String projectId = "your-project-id";
    String topicId = "your-topic-id";

    createTopicExample(projectId, topicId);
  }

  public static void createTopicExample(String projectId, String topicId) throws IOException {
    try (TopicAdminClient topicAdminClient = TopicAdminClient.create()) {
      TopicName topicName = TopicName.of(projectId, topicId);
      Topic topic = topicAdminClient.createTopic(topicName);
      System.out.println("Created topic: " + topic.getName());
    }
  }
}

Node.js

Pour vous authentifier auprès de Vertex AI Agent Builder, configurez les Identifiants par défaut de l'application. Pour en savoir plus, consultez Configurer l'authentification pour un environnement de développement local.

// Imports the Google Cloud client library
const {PubSub} = require('@google-cloud/pubsub');

async function quickstart(
  projectId = 'your-project-id', // Your Google Cloud Platform project ID
  topicNameOrId = 'my-topic', // Name for the new topic to create
  subscriptionName = 'my-sub', // Name for the new subscription to create
) {
  // Instantiates a client
  const pubsub = new PubSub({projectId});

  // Creates a new topic
  const [topic] = await pubsub.createTopic(topicNameOrId);
  console.log(`Topic ${topic.name} created.`);

  // Creates a subscription on that new topic
  const [subscription] = await topic.createSubscription(subscriptionName);

  // Receive callbacks for new messages on the subscription
  subscription.on('message', message => {
    console.log('Received message:', message.data.toString());
    process.exit(0);
  });

  // Receive callbacks for errors on the subscription
  subscription.on('error', error => {
    console.error('Received error:', error);
    process.exit(1);
  });

  // Send a message to the topic
  await topic.publishMessage({data: Buffer.from('Test message!')});
}

PHP

Pour vous authentifier auprès de Vertex AI Agent Builder, configurez les Identifiants par défaut de l'application. Pour en savoir plus, consultez Configurer l'authentification pour un environnement de développement local.

# Includes the autoloader for libraries installed with composer
require __DIR__ . '/vendor/autoload.php';

# Imports the Google Cloud client library
use Google\Cloud\PubSub\PubSubClient;

# Your Google Cloud Platform project ID
$projectId = 'YOUR_PROJECT_ID';

# Instantiates a client
$pubsub = new PubSubClient([
    'projectId' => $projectId
]);

# The name for the new topic
$topicName = 'my-new-topic-2';

# Creates the new topic
$topic = $pubsub->createTopic($topicName);

echo 'Topic ' . $topic->name() . ' created.';

Python

Pour vous authentifier auprès de Vertex AI Agent Builder, configurez les Identifiants par défaut de l'application. Pour en savoir plus, consultez Configurer l'authentification pour un environnement de développement local.

from google.cloud import pubsub_v1

# TODO(developer)
# project_id = "your-project-id"
# topic_id = "your-topic-id"

publisher = pubsub_v1.PublisherClient()
topic_path = publisher.topic_path(project_id, topic_id)

topic = publisher.create_topic(request={"name": topic_path})

print(f"Created topic: {topic.name}")

Ruby

Pour vous authentifier auprès de Vertex AI Agent Builder, configurez les Identifiants par défaut de l'application. Pour en savoir plus, consultez Configurer l'authentification pour un environnement de développement local.

# Imports the Google Cloud client library
require "google/cloud/pubsub"

# Instantiates a client
pubsub = Google::Cloud::PubSub.new
topic_admin = pubsub.topic_admin

# The name for the new topic
# topic_id = "your-topic-id"

# Creates the new topic
topic = topic_admin.create_topic name: pubsub.topic_path(topic_id)

puts "Topic #{topic.name} created."

Félicitations ! Vous avez envoyé votre première requête à Vertex AI Agent Builder.

Comment ça s'est passé ?

Ça a marché !

Parfait ! Qu'avez-vous apprécié dans ce guide de démarrage rapide ? Que pourrions-nous améliorer ? N'hésitez pas à nous donner votre avis !

J'ai rencontré un problème.

Nous le regrettons. Expliquez-nous ce qu'il s'est passé. Notre objectif est de le corriger.

Effectuer un nettoyage

Afin d'éviter que des frais ne soient facturés sur votre compte Google pour les ressources utilisées dans ce guide de démarrage rapide, procédez comme suit :

• Utilisez Google Cloud console pour supprimer votre projet si vous n'en avez plus besoin.

Étapes suivantes

En savoir plus sur les bibliothèques clientes de l'API Vertex AI Agent Builder