Setting Up Vertex AI Beginner

Before you can start training and deploying models on Vertex AI, you need to set up your Google Cloud environment. This lesson walks you through creating a GCP account, setting up a project, enabling the necessary APIs, and configuring Vertex AI Workbench.

Prerequisites

• A Google account (Gmail or Google Workspace)
• A credit card for GCP billing (Google offers $300 free credits for new users)
• Basic familiarity with the command line

Step 1: Create a GCP Account

1. Go to the Google Cloud Console

   Visit console.cloud.google.com and sign in with your Google account.

2. Activate the free trial

   New users receive $300 in free credits valid for 90 days. Click "Try Free" to activate your trial. You will need to provide billing information, but you won't be charged until you manually upgrade.

Step 2: Create a Project

Every resource in GCP belongs to a project. Create a dedicated project for your Vertex AI work:

# Using the gcloud CLI
gcloud projects create my-vertex-ai-project --name="Vertex AI Project"
gcloud config set project my-vertex-ai-project

# Enable billing for the project
gcloud billing accounts list
gcloud billing projects link my-vertex-ai-project --billing-account=BILLING_ACCOUNT_ID

Step 3: Enable Vertex AI APIs

Enable the required APIs for Vertex AI:

# Enable Vertex AI API
gcloud services enable aiplatform.googleapis.com

# Enable additional useful APIs
gcloud services enable compute.googleapis.com
gcloud services enable storage.googleapis.com
gcloud services enable notebooks.googleapis.com
gcloud services enable containerregistry.googleapis.com

Step 4: Install the Google Cloud SDK

If you haven't already, install the Google Cloud SDK and the Vertex AI Python client:

# Install the Vertex AI Python SDK
pip install google-cloud-aiplatform

# Authenticate with your Google account
gcloud auth application-default login

# Set your default region
gcloud config set compute/region us-central1

Step 5: Set Up Vertex AI Workbench

Vertex AI Workbench provides managed JupyterLab instances pre-configured with ML frameworks and the Vertex AI SDK:

1. Navigate to Vertex AI Workbench

   In the Cloud Console, go to Vertex AI > Workbench.

2. Create a new instance

   Click "Create New" and select "Instances." Choose a machine type (e.g., n1-standard-4 for general use) and optionally add a GPU.

3. Open JupyterLab

   Once the instance is running, click "Open JupyterLab" to launch your development environment with all Vertex AI libraries pre-installed.

Step 6: Verify Your Setup

from google.cloud import aiplatform

# Initialize the Vertex AI SDK
aiplatform.init(
    project="my-vertex-ai-project",
    location="us-central1"
)

# List existing models (should be empty initially)
models = aiplatform.Model.list()
print(f"Models in project: {len(models)}")
print("Vertex AI setup complete!")