Add Cloud Firestore and Authentication to your Google AI Studio app

Google AI Studio integrates directly with Cloud Firestore and Firebase Authentication, allowing you to build applications with persistent data and secure login flows. When you use the "Add Firebase backend" feature in Google AI Studio, the agent generates the required code and connects your app to a Firebase project.

Overview: Add a backend to your Google AI Studio app

1. Describe your idea: Create a new app in Google AI Studio and describe a feature that requires a database or authentication (for example, "Build a shared to-do list").

2. Enable the Firebase integration: Select the Add Firebase backend chip. The agent generates the necessary code, including a /src/lib/firebase.ts file and a firestore.rules file, and then connects your app to Cloud Firestore and Firebase Authentication.

3. Deploy: Once ready, use the Share > Publish option to deploy your app to Cloud Run.

Understand the shared quota for Cloud Firestore

All the Cloud Firestore databases provisioned by the agent in Google AI Studio are placed in the same "group" of databases in your Firebase project. They all share these characteristics:

• Shared quota: All databases in the group share a usage quota (see details below).
• No Cloud Billing account required: You can build and test your app without adding billing. See details below about optionally adding billing.
• Daily resets: If you hit a daily quota limit (for example, 50k reads/day), the service will pause for all databases within the group and resume the following day at around midnight Pacific Time.

Cloud Firestore databases in the shared quota group share the following limits:

(Optional) Add billing to get more Cloud Firestore quota

If your app gains traction and you need to move beyond the no-cost limits for Cloud Firestore, you can upgrade your project to the pay-as-you-go Blaze pricing plan.

1. Add billing (if you haven't already): Navigate to the Firebase console and link a billing account to your project.

2. Upgrade the database: By default, Cloud Firestore databases created by the Google AI Studio agent continue to use the shared quota even after you upgrade your pricing plan. To enable full paid scaling for a specific database, you must manually move it out of the group by using a curl command.

   • PROJECT_ID : Firebase project ID; find this ID in the Project Settings of the Firebase console.
   • DATABASE_ID : Cloud Firestore database ID, which will match your applet ID; find this database ID in the Name column on the Cloud Firestore databases page in the Firebase console.

   curl -X PATCH \
   -H "Authorization: Bearer $(gcloud auth print-access-token)" \
   -H "Content-Type: application/json" \
   "https://firestore.googleapis.com/v1/projects/PROJECT_ID/databases/DATABASE_ID?updateMask=limited_free_tier" \
   -d '{"limited_free_tier": false}'
   

Security Rules generation

Google AI Studio automatically generates Firebase Security Rules based on your app's logic. These Security Rules are designed to be "default deny," meaning end-users of your app can only access the data they own.

Note that if you manually adjust your Security Rules directly in the Firebase console, the Google AI Studio agent won't know about the changes, and they will be overwritten during subsequent app iterations. We recommend using the Google AI Studio agent to adjust your Firebase Security Rules to ensure your changes are preserved and aligned with your app's logic.

Use an existing project

You can also ask for the Google AI Studio agent to provision Cloud Firestore into an existing Google Cloud project that you own. Instruct the agent to use your existing project with a prompt such as:

Add Firestore to this app using project PROJECT_ID.

• A new Cloud Firestore database will be provisioned into that project using the shared quota.
• Firebase Authentication with Google Sign-In will be configured.
• A service account will be granted access to your Cloud Firestore database. To allow administrator access from Google AI Studio, a new service account named ais-sandbox@PROJECT_ID.iam.gservice.com will be granted permission to access your Cloud Firestore database. This account is associated only with your Google AI Studio apps.
• Limitations: If the Firebase project already has a Cloud Firestore database, the agent won't be able to add an additional one. You'll need to create a new, empty project to use.

Use the Firebase console

You can view your app's data and settings in the Firebase console. To access your projects associated with Google AI Studio, follow these steps:

1. Navigate to the Firebase console and select the project labeled AI Studio.
2. In the left navigation pane, click Build > Cloud Firestore Database to view and edit your data in Cloud Firestore, or click Build > Authentication to configure your Authentication settings and data.

Troubleshooting and FAQ

Find answers to common questions and learn how to resolve issues when integrating Firebase with your Google AI Studio app.

What authentication methods are supported?

The Google AI Studio agent sets up Google Sign-In when you use the Add Firebase backend feature. To set up additional methods, enable them in the Firebase console and ask the Google AI Studio agent for assistance updating your codebase.

What is the firebase-blueprint.json file?

This is an intermediate file used by the Google AI Studio agent to understand your app's codebase. Don't modify this file manually, as it may cause the agent to generate incorrect code or insecure Security Rules.

What should I do if I get a "Quota exceeded" error?

Hitting a Cloud Firestore quota limit means your app has reached its daily usage cap for your Cloud Firestore database shared quota group. There are two ways to resolve this:

• Option 1: Wait: Quotas reset daily around midnight Pacific Time.
• Option 2: Upgrade: Upgrade to the pay-as-you-go Blaze pricing plan.
  • If the Google AI Studio agent set up Cloud Firestore for you, you must then use the curl command described in Add billing to get more Cloud Firestore quota to move your database into a regular paid state. If you set up Cloud Firestore manually, then running the curl command isn't necessary.

What should I do if I get a "Missing or insufficient permissions" error?

This error occurs when your app attempts to read or write data to your Cloud Firestore database, but the request is rejected by your Security Rules. It indicates that the Security Rules are not allowing the attempted operation based on the current authentication state or data path. Click the Fix error button to prompt the Google AI Studio agent to attempt to correct the Security Rules.

What happens to my Firebase backend when I delete my Google AI Studio app?

Deleting your application in Google AI Studio doesn't automatically delete the connected Firebase project, Cloud Firestore database, or Firebase Authentication configurations.

If you added a Firebase backend, you must manually go to the Firebase console and delete the project or clean up individual resources (such as the Cloud Firestore database instance and Authentication providers) to ensure all data and configurations are removed.

Can the Google AI Studio agent delete or edit data in my Cloud Firestore database?

The Google AI Studio agent is designed to help provision the necessary backend resources and generate code and Security Rules. While the agent itself can't directly delete, edit, or manipulate data entries within your Cloud Firestore database, it can write code into your applet that is designed to perform these actions. To perform data management tasks, such as deleting entries, navigate to the Cloud Firestore database page in the Firebase console.

I belong to an organization that uses Google Cloud; can I connect my Google AI Studio app to an existing project within my organization's Google Cloud environment?

Ensure your Firebase project is placed within a particular Google Cloud organization folder:

1. Create your Firebase project manually ahead of time.

2. When setting up your Firebase backend in Google AI Studio, instruct the agent to use your existing project:

   Add Firestore to this app using project PROJECT_ID.
   

Why can't I find certain documents in the Firebase console?

When the AI Studio agent saves data to a nested path (like /users/user1/messages/msg1) without first creating the parent document (user1), it creates what is known as a non-existent parent document. These documents aren't displayed in the Firebase console, which can make them difficult to find when browsing your Cloud Firestore database. While this doesn't affect how your app runs, you can often describe the issue to the AI Studio agent to prompt it to create the missing parent documents.

For more details, see Non-existent parent documents.

How is the location for my Cloud Firestore database chosen?

Currently, the location for your Cloud Firestore database is automatically selected based on your location, and it can't be changed or manually specified. If you'd like the capability to choose a specific location, let us know by going to Settings > Send feedback within Google AI Studio.

How does Google use my data (for example, code and prompts) in Google AI Studio?

Refer to the Gemini API Additional Terms of Service for details on how your data is used.