Update ADK doc according to issue #1587 - 12

[adk-bot]

Update the adk create instructions to explain the new interactive prompt: users can now choose between Google AI, Vertex AI, or "Login with Google". Explain that "Login with Google" uses Application Default Credentials (ADC) and can automatically provision a Vertex AI Express Mode project. Also, add a note echoing the CLI's new security warning: users must ensure the generated .env file is added to their .gitignore to prevent accidentally committing secrets like GOOGLE_API_KEY.

[netlify]

✅ Deploy Preview for adk-docs-preview ready!

Name	Link
🔨 Latest commit	f0f22f7
🔍 Latest deploy log	https://app.netlify.com/projects/adk-docs-preview/deploys/69d80bb0a0d9b500080a684d
😎 Deploy Preview	https://deploy-preview-1608--adk-docs-preview.netlify.app
📱 Preview on mobile	Toggle QR Code... Use your smartphone camera to open QR code link.

---

To edit notification comments on pull requests, go to your Netlify project configuration.

[jcwriter74]

8. adk create instructions update-new interactive prompt

Current: not found
Proposed:

> Update the adk create instructions to explain the new interactive prompt: users can now choose between Google AI, Vertex AI, or "Login with Google".

There is a new interactive prompt available for the adk create command allowing you to choose between different models: Google AI, Vertex AI or “Login with Google”:

Google AI (Gemini API Key)

• Designed for developers searching for fast ways of using Gemini Models.
• Uses Google AI Studio as backend, and asks for a Google AI API Key, also given by Google AI Studio.
• Builds an .env file with the entry GOOGLE_API_KEY=your_key_here.
• Fast prototyping.
• No billing or Google Cloud Console needed.

Vertex AI (Enterprise/Manual Setup)

• Enterprise path for users already possessing a Google Cloud environment.
• Uses Google Cloud credentials, necessary to be authenticated with gcloud CLI and having a project.
• Specialized on integrating with the complete Google environment.
• Asks for a Google Cloud Project ID and Location.
  .env file with:
  GOOGLE_GENAI_USE_VERTEXAI=1
  GOOGLE_CLOUD_PROJECT=YOUR_PROJECT_ID
  GOOGLE_CLOUD_LOCATION=YOUR_GCP_LOCATION
  Prerequisites:
• Google Cloud Project with billing enabled.
• gcloud CLI installed and authenticated (gcloud auth login).
• Required APIs enabled (e.g., aiplatform.googleapis.com).

“Login with Google” (The New "Express Mode")

> Explain that "Login with Google" uses Application Default Credentials (ADC) and can automatically provision a Vertex AI Express Mode project.

• Uses ADC, CLI triggers an OAuth flow for you to enter your Google account credentials.
• Automatic provisioning of a Vertex AI Express Mode.
• Backend auto provisioning, based on your Google login: no onboarding configuration needed.
• Using all Vertex AI tools for 90 days before billing or the tenancy of a GCP project.
• Environment setup to directly talk to Vertex AI.

> Also, add a note echoing the CLI's new security warning: users must ensure the generated .env file is added to their .gitignore to prevent accidentally committing secrets like GOOGLE_API_KEY.

CLI’s new security warning:
Remember to add the generated .env file to your .gitignore for preventing exposure of secrets like GOOGLE_API_KEY.

Pro Tip:
If you ever need to change your backend later, you can simply update the values in the generated .env file, and the ADK will automatically switch its internal client logic to match the new configuration.

Reviewed by:
Duckie
Google AI Studio