Mit Sammlungen den Überblick behalten
Sie können Inhalte basierend auf Ihren Einstellungen speichern und kategorisieren.
Zum Einstieg in Vertex AI erfahren Sie auf dieser Seite, wie Sie ein Google Cloud -Projekt erstellen und die Vertex AI APIs aktivieren. Wenn Sie nicht die Berechtigungen zum Ausführen dieser Aufgaben haben, bitten Sie einen Administrator, ein Projekt einzurichten und Vertex AI für Sie zu aktivieren. Auf dieser Seite wird auch beschrieben, wie Sie die Google Cloud CLI in Ihrer lokalen Entwicklungsumgebung einrichten.
Projekt einrichten
So richten Sie ein Projekt ein:
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.
At the bottom of the Google Cloud console, a
Cloud Shell
session starts and displays a command-line prompt. Cloud Shell is a shell environment
with the Google Cloud CLI
already installed and with values already set for
your current project. It can take a few seconds for the session to initialize.
Python
Wenn Sie die Python -Beispiele auf dieser Seite in einer lokalen Entwicklungsumgebung verwenden möchten, installieren und initialisieren Sie die gcloud CLI und richten Sie dann die Standardanmeldedaten für Anwendungen mit Ihren Nutzeranmeldedaten ein.
Wenn Sie die REST API-Beispiele auf dieser Seite in einer lokalen Entwicklungsumgebung verwenden möchten, verwenden Sie die Anmeldedaten, die Sie der gcloud CLI bereitstellen.
Bitten Sie einen Administrator, ein Vertex AI-Projekt für Sie einzurichten.
In diesem Abschnitt wird beschrieben, wie ein Administrator die Rollen zuweist, die für die Verwendung von Vertex AI erforderlich sind.
Legen Sie einen aussagekräftigen Projektnamen und eine Projekt-ID fest, um Ihr Projekt zu identifizieren.
Wenn Sie Teil einer Organisation sind oder mehrere Projekte erstellen möchten, sollten Sie sich überlegen, welche Namenskonventionen und Ordnerhierarchien befolgt werden oder befolgt werden könnten, um die Projektorganisation klar zu gestalten.
Erforderliche Rollen:
Der Zugriff auf die meisten Vertex AI-Funktionen wird durch die IAM-Rolle Vertex AI-Nutzer(roles/aiplatform.user) gewährt und sollte für die meisten Vertex AI-Nutzer ausreichend sein. Für uneingeschränkten Zugriff auf Vertex AI-Ressourcen können Sie die Rolle Vertex AI-Administrator(roles/aiplatform.admin) anfordern.
Informationen zu den Unterschieden zwischen diesen und anderen Vertex AI-Rollen finden Sie unter Vertex AI-Zugriffssteuerung mit IAM.
Zum Aktivieren der erforderlichen APIs benötigen Sie außerdem die IAM-Rolle Service Usage-Administrator(roles/serviceusage.serviceUsageAdmin) oder Ihr Administrator muss die APIs über die folgenden ersten Schritte für Sie aktivieren.
Bitten Sie Ihren Administrator, Vertex AI APIs für Sie zu aktivieren.
Wenn Ihnen die IAM-Rolle Service Usage-Administrator(roles/serviceusage.serviceUsageAdmin) zugewiesen ist, können Sie dies selbst tun.
[[["Leicht verständlich","easyToUnderstand","thumb-up"],["Mein Problem wurde gelöst","solvedMyProblem","thumb-up"],["Sonstiges","otherUp","thumb-up"]],[["Schwer verständlich","hardToUnderstand","thumb-down"],["Informationen oder Beispielcode falsch","incorrectInformationOrSampleCode","thumb-down"],["Benötigte Informationen/Beispiele nicht gefunden","missingTheInformationSamplesINeed","thumb-down"],["Problem mit der Übersetzung","translationIssue","thumb-down"],["Sonstiges","otherDown","thumb-down"]],["Zuletzt aktualisiert: 2025-08-19 (UTC)."],[],[],null,["# Set up a project and a development environment\n\nTo get you started using Vertex AI, this page guides you through how to\ncreate a Google Cloud project and enable the Vertex AI APIs. If you\ndon't have the permissions to perform these tasks,\n[ask an administrator](#ask_admin) to setup\na project and enable Vertex AI for you. Also covered in this page is\nhow to set up the Google Cloud CLI in your local development environment.\n\nSet up a project\n----------------\n\nFollow these steps to set up a project:\n\n- Sign in to your Google Cloud account. If you're new to Google Cloud, [create an account](https://console.cloud.google.com/freetrial) to evaluate how our products perform in real-world scenarios. New customers also get $300 in free credits to run, test, and deploy workloads.\n- In the Google Cloud console, on the project selector page,\n select or create a Google Cloud project.\n\n [Go to project selector](https://console.cloud.google.com/projectselector2/home/dashboard)\n-\n [Verify that billing is enabled for your Google Cloud project](/billing/docs/how-to/verify-billing-enabled#confirm_billing_is_enabled_on_a_project).\n\n-\n\n\n Enable the Vertex AI API.\n\n\n [Enable the API](https://console.cloud.google.com/flows/enableapi?apiid=aiplatform.googleapis.com)\n\n- In the Google Cloud console, on the project selector page,\n select or create a Google Cloud project.\n\n [Go to project selector](https://console.cloud.google.com/projectselector2/home/dashboard)\n-\n [Verify that billing is enabled for your Google Cloud project](/billing/docs/how-to/verify-billing-enabled#confirm_billing_is_enabled_on_a_project).\n\n-\n\n\n Enable the Vertex AI API.\n\n\n [Enable the API](https://console.cloud.google.com/flows/enableapi?apiid=aiplatform.googleapis.com)\n\n| **Note:** If you're an administrator setting up a project for a team, see [Set up a project for a team](/vertex-ai/docs/general/set-up-project).\n\nSet up authentication\n---------------------\n\n1. Select the tab for how you plan to use the samples on this page: \n\n### Console\n\n\nWhen you use the Google Cloud console to access Google Cloud services and\nAPIs, you don't need to set up authentication.\n\n### gcloud\n\nIn the Google Cloud console, activate Cloud Shell.\n\n[Activate Cloud Shell](https://console.cloud.google.com/?cloudshell=true)\n\n\nAt the bottom of the Google Cloud console, a\n[Cloud Shell](/shell/docs/how-cloud-shell-works)\nsession starts and displays a command-line prompt. Cloud Shell is a shell environment\nwith the Google Cloud CLI\nalready installed and with values already set for\nyour current project. It can take a few seconds for the session to initialize.\n\n### Python\n\n\nTo use the Python samples on this page in a local\ndevelopment environment, install and initialize the gcloud CLI, and\nthen set up Application Default Credentials with your user credentials.\n\n1.\n [Install](/sdk/docs/install) the Google Cloud CLI.\n\n2. If you're using an external identity provider (IdP), you must first\n [sign in to the gcloud CLI with your federated identity](/iam/docs/workforce-log-in-gcloud).\n\n3.\n After initializing the gcloud CLI, update it and install the required components:\n\n ```bash\n gcloud components update\n gcloud components install beta\n ```\n4. If you're using a local shell, then create local authentication credentials for your user account: \n\n```bash\ngcloud auth application-default login\n```\n5. You don't need to do this if you're using Cloud Shell.\n6. If an authentication error is returned, and you are using an external identity provider (IdP), confirm that you have [signed in to the gcloud CLI with your federated identity](/iam/docs/workforce-log-in-gcloud).\n\n\nFor more information, see\n[Set up ADC for a local development environment](/docs/authentication/set-up-adc-local-dev-environment)\nin the Google Cloud authentication documentation.\n\n### REST\n\n\nTo use the REST API samples on this page in a local development environment, you use the\ncredentials you provide to the gcloud CLI.\n\n1.\n [Install](/sdk/docs/install) the Google Cloud CLI.\n\n2. If you're using an external identity provider (IdP), you must first\n [sign in to the gcloud CLI with your federated identity](/iam/docs/workforce-log-in-gcloud).\n\n3.\n After initializing the gcloud CLI, update it and install the required components:\n\n ```bash\n gcloud components update\n gcloud components install beta\n ```\n\n\nFor more information, see\n[Authenticate for using REST](/docs/authentication/rest)\nin the Google Cloud authentication documentation.\n\n\u003cbr /\u003e\n\nAsk an administrator to set up a Vertex AI project for you\n----------------------------------------------------------\n\nThis section describes how an administrator grants the roles needed to use\nVertex AI.\n\n1. Determine a meaningful project name and project ID to identify your project. If you are part of an organization or plan to create multiple projects, consider what naming conventions and [folder](/resource-manager/docs/cloud-platform-resource-hierarchy#folders) hierarchies are followed, or could be followed, to make project organization clear.\n2. Required roles:\n 1. Access to most Vertex AI capabilities is granted by the [Vertex AI\n User](/vertex-ai/docs/general/access-control#aiplatform.user) `(roles/aiplatform.user)` IAM role and should suffice for most Vertex AI users. For full control of Vertex AI resources, you can request the [Vertex AI\n Administrator](/vertex-ai/docs/general/access-control#aiplatform.admin) `(roles/aiplatform.admin)` role. To explore the differences between these and other Vertex AI roles, see [Vertex AI access control\n with IAM](/vertex-ai/docs/general/access-control).\n 2. If you also intend to use [Vertex AI Workbench\n instances](/vertex-ai/docs/workbench/introduction) in Google Cloud, ask your administrator to grant you the [Notebooks\n Administrator](/iam/docs/understanding-roles#notebooks.admin) `(roles/notebooks.admin)` IAM role for the project, as well as the [Service\n Account User](/iam/docs/understanding-roles#iam.serviceAccountUser) `(roles/iam.serviceAccountUser)` IAM role on either the project or the [Compute Engine\n default service account](/compute/docs/access/service-accounts#default_service_account).\n 3. Additionally, to enable the necessary APIs, you either need the [Service\n Usage Admin](/iam/docs/understanding-roles#serviceusage.serviceUsageAdmin) `(roles/serviceusage.serviceUsageAdmin)` IAM role or your administrator needs to enable the APIs for you by following the first few steps.\n3. Ask your administrator to enable Vertex AI APIs for you. If you're granted the [Service\n Usage Admin](/iam/docs/understanding-roles#serviceusage.serviceUsageAdmin) `(roles/serviceusage.serviceUsageAdmin)` IAM role, then you'll be able to do this on your own.\n\n| **Note:** Certain tasks in Vertex AI require that you use additional Google Cloud products besides Vertex AI. For example, in most cases, you must use Cloud Storage and Artifact Registry when you create a custom training pipeline. You might need to perform additional setup tasks to use other Google Cloud products.\n\nWhat's next\n-----------\n\n- Read an [overview of\n Vertex AI](/vertex-ai/docs/start/introduction-unified-platform).\n\n- Walk through one of the [tutorials for using\n Vertex AI](/vertex-ai/docs/tutorials).\n\n- Learn how to\n [use the Vertex AI SDK for Python](/vertex-ai/docs/python-sdk/use-vertex-ai-python-sdk),\n which provides another way to interact with Vertex AI."]]
