# Set permissions for generative AI functions that call Gemini Enterprise Agent Platform LLMs

This document shows you how to set up permissions for running generative AI
queries. Generative AI queries contain `AI.*` functions that call foundation
models in Gemini Enterprise Agent Platform; for example, `AI.GENERATE`.

There are two ways to set up permissions to run queries that use `AI.*`
functions:

- Run the query using your Google Account user credentials
- Create a BigQuery connection to run the query using a service account

In most cases, you can use Google Account user credentials and leave the
`CONNECTION` argument blank. If your query job is
expected to run for 48 hours or longer, you should use a BigQuery
connection and include it in the `CONNECTION` argument.

## Run generative AI queries with Google Account user credentials

To run generative AI queries using Google Account user credentials, configure
the necessary permissions
using the Google Cloud console. Note that if you are the project owner,
you already have all the required permissions so you don't need to do anything.

### Required roles


To get the permissions that
you need to run a query job that calls an Agent Platform model,

ask your administrator to grant you the
following IAM roles on the project:

- Run query jobs: [BigQuery Job User](https://docs.cloud.google.com/iam/docs/roles-permissions/bigquery.md.txt#bigquery.jobUser) (`roles/bigquery.jobUser`)
- Access a foundation model in Gemini Enterprise Agent Platform: [Agent Platform User](https://docs.cloud.google.com/iam/docs/roles-permissions/aiplatform.md.txt#aiplatform.user) (`roles/aiplatform.user`)


For more information about granting roles, see [Manage access to projects, folders, and organizations](https://docs.cloud.google.com/iam/docs/granting-changing-revoking-access.md.txt).


You might also be able to get
the required permissions through [custom
roles](https://docs.cloud.google.com/iam/docs/creating-custom-roles) or other [predefined
roles](https://docs.cloud.google.com/iam/docs/roles-overview#predefined).

### Grant the required roles to the user or group

You can use the Google Cloud console or SQL to grant the required roles for a
principal. The principal is the user or group that runs the query that uses
`AI.*` functions to call a Gemini Enterprise Agent Platform foundation model.

### Console

1. In the Google Cloud console, go to the **IAM** page.

   [Go to IAM](https://console.cloud.google.com/projectselector/iam-admin/iam?supportedpurview=project,folder,organizationId)
2. Select your project.

3. To grant roles to a principal, do the following:

   1. Go to the **IAM \& Admin** page.

      [Go to IAM \& Admin](https://console.cloud.google.com/project/_/iam-admin)
   2. Click **Grant access**.

      The **Add principals** dialog opens.
   3. In the **New principals** field, enter the
      [principal identifier](https://docs.cloud.google.com/iam/docs/principal-identifiers.md.txt)---
      for example, `my-user@example.com`
      or `//iam.googleapis.com/locations/global/workforcePools/example-pool/group/example-group@example.com`.

   4. In the **Assign roles** section, for **Select a role**, click the
      drop-down arrow.

   5. Search for the **Agent Platform User** role and select it.

   6. Click **Add another role**.

   7. In the **Assign roles** section, for **Select a role**, click the
      drop-down arrow.

   8. Search for or browse to the **BigQuery Job User** role and select it.

   9. Click **Save**.

### SQL

Use the [`GRANT` statement](https://docs.cloud.google.com/bigquery/docs/reference/standard-sql/data-control-language.md.txt#grant_statement):


1. In the Google Cloud console, go to the **BigQuery** page.

   [Go to BigQuery](https://console.cloud.google.com/bigquery)
2. In the query editor, enter the following statement:

   ```googlesql
   GRANT `roles/aiplatform.user`, `roles/bigquery.jobUser`
   ON PROJECT `PROJECT_ID`
   TO "USER_OR_GROUP";
   ```


   Replace the following:
   - `PROJECT_ID`: the project where you plan to use `AI.*` functions.
   - `USER_OR_GROUP`: the user or group to grant access to, in the `user:USER@DOMAIN` or `group:GROUP@DOMAIN` format.

   <br />

3. Click **Run**.

   <br />

For more information about how to run queries, see [Run an interactive query](https://docs.cloud.google.com/bigquery/docs/running-queries.md.txt#queries).

To modify roles for a principal who already has roles on the project,
see [Grant additional roles to the same principal](https://docs.cloud.google.com/iam/docs/grant-role-console.md.txt#grant-other-roles).

For information on other methods of granting project-level roles to a principal,
see [Grant or revoke multiple IAM roles programmatically](https://docs.cloud.google.com/iam/docs/granting-changing-revoking-access.md.txt#multiple-roles-programmatic).

## Run generative AI queries with a BigQuery Connection

To run generative AI queries using a connection, create the connection, and then
grant access to the service account created by the connection.

### Create a connection

You can set up a Cloud Resource Connection to run all generative AI queries that
contain `AI.*` functions. When you create a connection, you grant permissions to
run queries to a service account.
Select one of the following options:

<br />

### Console

1. Go to the **BigQuery** page.

   [Go to BigQuery](https://console.cloud.google.com/bigquery)
2. In the left pane, click
   **Explorer**:

   ![Highlighted button for the Explorer pane.](https://docs.cloud.google.com/static/bigquery/images/explorer-tab.png)

   If you don't see the left pane, click
   **Expand left pane** to open the pane.
3. In the **Explorer** pane, expand your project name, and then click
   **Connections**.

4. On the **Connections** page, click **Create connection**.

5. For **Connection type** , choose **Vertex AI remote models, remote
   functions, BigLake and Spanner (Cloud Resource)**.

6. In the **Connection ID** field, enter a name for your connection.

7. For **Location type**, select a location for your connection. The
   connection should be colocated with your other resources such as
   datasets.

8. Click **Create connection**.

9. Click **Go to connection**.

10. In the **Connection info** pane, copy the service account ID for use in
    a later step.

### SQL

Use the [`CREATE CONNECTION` statement](https://docs.cloud.google.com/bigquery/docs/reference/standard-sql/data-definition-language.md.txt#create_connection_statement):


1. In the Google Cloud console, go to the **BigQuery** page.

   [Go to BigQuery](https://console.cloud.google.com/bigquery)
2. In the query editor, enter the following statement:

   ```googlesql
   CREATE CONNECTION [IF NOT EXISTS] `CONNECTION_NAME`
   OPTIONS (
     connection_type = "CLOUD_RESOURCE",
     friendly_name = "FRIENDLY_NAME",
     description = "DESCRIPTION"
     );
   ```


   Replace the following:
   - `CONNECTION_NAME`: the name of the connection in either the `PROJECT_ID.LOCATION.CONNECTION_ID`, `LOCATION.CONNECTION_ID`, or `CONNECTION_ID` format. If the project or location are omitted, then they are inferred from the project and location where the statement is run.
   - `FRIENDLY_NAME` (optional): a descriptive name for the connection.
   - `DESCRIPTION` (optional): a description of the connection.

   <br />

3. Click **Run**.

   <br />

For more information about how to run queries, see [Run an interactive query](https://docs.cloud.google.com/bigquery/docs/running-queries.md.txt#queries).

### bq

1. In a command-line environment, create a connection:

   ```bash
   bq mk --connection --location=REGION --project_id=PROJECT_ID \
       --connection_type=CLOUD_RESOURCE CONNECTION_ID
   ```

   The `--project_id` parameter overrides the default project.

   Replace the following:
   - `REGION`: your [connection region](https://docs.cloud.google.com/bigquery/docs/locations.md.txt#supported_locations)
   - `PROJECT_ID`: your Google Cloud project ID
   - `CONNECTION_ID`: an ID for your connection

   When you create a connection resource, BigQuery creates a
   unique system service account and associates it with the connection.

   **Troubleshooting** : If you get the following connection error,
   [update the Google Cloud SDK](https://docs.cloud.google.com/sdk/docs/quickstart):

   ```
   Flags parsing error: flag --connection_type=CLOUD_RESOURCE: value should be one of...
   ```
2. Retrieve and copy the service account ID for use in a later
   step:

   ```bash
   bq show --connection PROJECT_ID.REGION.CONNECTION_ID
   ```

   The output is similar to the following:

   ```
   name                          properties
   1234.REGION.CONNECTION_ID     {"serviceAccountId": "connection-1234-9u56h9@gcp-sa-bigquery-condel.iam.gserviceaccount.com"}
   ```

### Python


Before trying this sample, follow the Python setup instructions in the
[BigQuery quickstart using
client libraries](https://docs.cloud.google.com/bigquery/docs/quickstarts/quickstart-client-libraries).


For more information, see the
[BigQuery Python API
reference documentation](https://docs.cloud.google.com/python/docs/reference/bigquery/latest).


To authenticate to BigQuery, set up Application Default Credentials.
For more information, see

[Set up authentication for client libraries](https://docs.cloud.google.com/bigquery/docs/authentication.md.txt#client-libs).

```python
import google.api_core.exceptions
from google.cloud import bigquery_connection_v1

client = bigquery_connection_v1.ConnectionServiceClient()


def create_connection(
    project_id: str,
    location: str,
    connection_id: str,
):
    """Creates a BigQuery connection to a Cloud Resource.

    Cloud Resource connection creates a service account which can then be
    granted access to other Google Cloud resources for federated queries.

    Args:
        project_id: The Google Cloud project ID.
        location: The location of the connection (for example, "us-central1").
        connection_id: The ID of the connection to create.
    """

    parent = client.common_location_path(project_id, location)

    connection = bigquery_connection_v1.Connection(
        friendly_name="Example Connection",
        description="A sample connection for a Cloud Resource.",
        cloud_resource=bigquery_connection_v1.CloudResourceProperties(),
    )

    try:
        created_connection = client.create_connection(
            parent=parent, connection_id=connection_id, connection=connection
        )
        print(f"Successfully created connection: {created_connection.name}")
        print(f"Friendly name: {created_connection.friendly_name}")
        print(
            f"Service Account: {created_connection.cloud_resource.service_account_id}"
        )

    except google.api_core.exceptions.AlreadyExists:
        print(f"Connection with ID '{connection_id}' already exists.")
        print("Please use a different connection ID.")
    except Exception as e:
        print(f"An unexpected error occurred while creating the connection: {e}")

```

### Node.js


Before trying this sample, follow the Node.js setup instructions in the
[BigQuery quickstart using
client libraries](https://docs.cloud.google.com/bigquery/docs/quickstarts/quickstart-client-libraries).


For more information, see the
[BigQuery Node.js API
reference documentation](https://googleapis.dev/nodejs/bigquery/latest/index.html).


To authenticate to BigQuery, set up Application Default Credentials.
For more information, see

[Set up authentication for client libraries](https://docs.cloud.google.com/bigquery/docs/authentication.md.txt#client-libs).

```javascript
const {ConnectionServiceClient} =
  require('@google-cloud/bigquery-connection').v1;
const {status} = require('@grpc/grpc-js');

const client = new ConnectionServiceClient();

/**
 * Creates a new BigQuery connection to a Cloud Resource.
 *
 * A Cloud Resource connection creates a service account that can be granted access
 * to other Google Cloud resources.
 *
 * @param {string} projectId The Google Cloud project ID. for example, 'example-project-id'
 * @param {string} location The location of the project to create the connection in. for example, 'us-central1'
 * @param {string} connectionId The ID of the connection to create. for example, 'example-connection-id'
 */
async function createConnection(projectId, location, connectionId) {
  const parent = client.locationPath(projectId, location);

  const connection = {
    friendlyName: 'Example Connection',
    description: 'A sample connection for a Cloud Resource',
    // The service account for this cloudResource will be created by the API.
    // Its ID will be available in the response.
    cloudResource: {},
  };

  const request = {
    parent,
    connectionId,
    connection,
  };

  try {
    const [response] = await client.createConnection(request);

    console.log(`Successfully created connection: ${response.name}`);
    console.log(`Friendly name: ${response.friendlyName}`);

    console.log(`Service Account: ${response.cloudResource.serviceAccountId}`);
  } catch (err) {
    if (err.code === status.ALREADY_EXISTS) {
      console.log(`Connection '${connectionId}' already exists.`);
    } else {
      console.error(`Error creating connection: ${err.message}`);
    }
  }
}
```

### Java


Before trying this sample, follow the Java setup instructions in the
[BigQuery quickstart using
client libraries](https://docs.cloud.google.com/bigquery/docs/quickstarts/quickstart-client-libraries).


For more information, see the
[BigQuery Java API
reference documentation](https://docs.cloud.google.com/java/docs/reference/google-cloud-bigquery/latest/overview).


To authenticate to BigQuery, set up Application Default Credentials.
For more information, see

[Set up authentication for client libraries](https://docs.cloud.google.com/bigquery/docs/authentication.md.txt#client-libs).

```java
import com.google.api.gax.rpc.AlreadyExistsException;
import com.google.api.gax.rpc.ApiException;
import com.google.cloud.bigquery.connection.v1.CloudResourceProperties;
import com.google.cloud.bigquery.connection.v1.Connection;
import com.google.cloud.bigquery.connection.v1.CreateConnectionRequest;
import com.google.cloud.bigquery.connection.v1.LocationName;
import com.google.cloud.bigqueryconnection.v1.ConnectionServiceClient;
import java.io.IOException;

public class CreateConnection {

  /**
   * Creates a BigQuery connection to a Cloud Resource. A Cloud Resource connection provisions a
   * service account that can be granted access to other Google Cloud resources for federated
   * queries.
   *
   * @param projectId The Google Cloud project ID (for example, "example-project-id").
   * @param location The geographic location of the connection (for example, "us-central1").
   * @param connectionId The ID of the connection to create (for example, "example-connection-id").
   */
  public static void createConnection(String projectId, String location, String connectionId) {
    LocationName parent = LocationName.of(projectId, location);

    // CloudResourceProperties provisions a managed Google Cloud service account on creation.
    CloudResourceProperties cloudResourceProperties = CloudResourceProperties.newBuilder().build();
    Connection connection =
        Connection.newBuilder()
            .setFriendlyName("Example Connection")
            .setDescription("Cloud Resource connection for federated queries.")
            .setCloudResource(cloudResourceProperties)
            .build();

    CreateConnectionRequest request =
        CreateConnectionRequest.newBuilder()
            .setParent(parent.toString())
            .setConnectionId(connectionId)
            .setConnection(connection)
            .build();

    try (ConnectionServiceClient client = ConnectionServiceClient.create()) {
      Connection response = client.createConnection(request);

      System.out.printf("Successfully created connection: %s%n", response.getName());
      System.out.printf("Friendly name: %s%n", response.getFriendlyName());
      System.out.printf(
          "Service Account: %s%n", response.getCloudResource().getServiceAccountId());
    } catch (AlreadyExistsException err) {
      System.err.printf(
          "error: connection '%s' already exists in location '%s' for project '%s': %s%n",
          connectionId, location, projectId, err.getMessage());
    } catch (ApiException | IOException err) {
      System.err.printf(
          "error: failed to create connection '%s' in location '%s' for project '%s': %s%n",
          connectionId, location, projectId, err.getMessage());
    }
  }
```

### Terraform

Use the
[`google_bigquery_connection`](https://registry.terraform.io/providers/hashicorp/google/latest/docs/resources/bigquery_connection)
resource.

> [!NOTE]
> **Note:** To create BigQuery objects using Terraform, you must enable the [Cloud Resource Manager API](https://docs.cloud.google.com/resource-manager/reference/rest.md.txt).

To authenticate to BigQuery, set up Application Default
Credentials. For more information, see
[Set up authentication for client libraries](https://docs.cloud.google.com/bigquery/docs/authentication.md.txt#client-libs).

The following example creates a Cloud resource connection named
`my_cloud_resource_connection` in the `US` region:

```terraform

# This queries the provider for project information.
data "google_project" "default" {}

# This creates a cloud resource connection in the US region named my_cloud_resource_connection.
# Note: The cloud resource nested object has only one output field - serviceAccountId.
resource "google_bigquery_connection" "default" {
  connection_id = "my_cloud_resource_connection"
  project       = data.google_project.default.project_id
  location      = "US"
  cloud_resource {}
}
```

To apply your Terraform configuration in a Google Cloud project, complete the steps in the
following sections.

## Prepare Cloud Shell

1. Launch [Cloud Shell](https://shell.cloud.google.com/).
2. Set the default Google Cloud project
   where you want to apply your Terraform configurations.

   You only need to run this command once per project, and you can run it in any directory.

   ```
   export GOOGLE_CLOUD_PROJECT=PROJECT_ID
   ```

   Environment variables are overridden if you set explicit values in the Terraform
   configuration file.

## Prepare the directory

Each Terraform configuration file must have its own directory (also
called a *root module*).

1. In [Cloud Shell](https://shell.cloud.google.com/), create a directory and a new file within that directory. The filename must have the `.tf` extension---for example `main.tf`. In this tutorial, the file is referred to as `main.tf`.

   ```
   mkdir DIRECTORY && cd DIRECTORY && touch main.tf
   ```
2. If you are following a tutorial, you can copy the sample code in each section or step.

   Copy the sample code into the newly created `main.tf`.

   Optionally, copy the code from GitHub. This is recommended
   when the Terraform snippet is part of an end-to-end solution.
3. Review and modify the sample parameters to apply to your environment.
4. Save your changes.
5. Initialize Terraform. You only need to do this once per directory.

   ```
   terraform init
   ```

   Optionally, to use the latest Google provider version, include the `-upgrade`
   option:

   ```
   terraform init -upgrade
   ```

## Apply the changes

1. Review the configuration and verify that the resources that Terraform is going to create or update match your expectations:

   ```
   terraform plan
   ```

   Make corrections to the configuration as necessary.
2. Apply the Terraform configuration by running the following command and entering `yes` at the prompt:

   ```
   terraform apply
   ```

   Wait until Terraform displays the "Apply complete!" message.
3. [Open your Google Cloud project](https://console.cloud.google.com/) to view the results. In the Google Cloud console, navigate to your resources in the UI to make sure that Terraform has created or updated them.

> [!NOTE]
> **Note:** Terraform samples typically assume that the required APIs are enabled in your Google Cloud project.

For more information, see [Create and set up a Cloud resource connection](https://docs.cloud.google.com/bigquery/docs/create-cloud-resource-connection.md.txt).

### Grant access to the service account

To run queries that use generative `AI.*` functions that call Gemini Enterprise Agent Platform
models, you must grant appropriate permissions to the service account that was
created when you created your connection. To run functions that call a
Gemini Enterprise Agent Platform foundation model, the [Agent Platform User role](https://docs.cloud.google.com/iam/docs/roles-permissions/aiplatform.md.txt#aiplatform.user)
(`roles/aiplatform.user`) is required.

Select one of the following options:

### Console

1. Go to the **IAM \& Admin** page.

   [Go to IAM \& Admin](https://console.cloud.google.com/project/_/iam-admin)
2. Click **Grant access**.

   The **Add principals** dialog opens.
3. In the **New principals** field, enter the service account ID that you
   copied earlier.

4. In the **Assign roles** section, click **Add roles**.

5. Search for the **Agent Platform User** role, select it, and then
   click **Apply**.

6. Click **Save**.

### SQL

Use the [`GRANT` statement](https://docs.cloud.google.com/bigquery/docs/reference/standard-sql/data-control-language.md.txt#grant_statement):


1. In the Google Cloud console, go to the **BigQuery** page.

   [Go to BigQuery](https://console.cloud.google.com/bigquery)
2. In the query editor, enter the following statement:

   ```googlesql
   GRANT `roles/aiplatform.user`
   ON PROJECT `PROJECT_ID`
   TO "connection:CONNECTION_NAME";
   ```


   Replace the following:
   - `PROJECT_ID`: the project where you plan to use Agent Platform.
   - `CONNECTION_NAME`: the name of the connection in either the `PROJECT_ID.LOCATION.CONNECTION_ID` or `LOCATION.CONNECTION_ID` format. If the project is omitted, then it is inferred from the project where the statement is run.

   <br />

3. Click **Run**.

   <br />

For more information about how to run queries, see [Run an interactive query](https://docs.cloud.google.com/bigquery/docs/running-queries.md.txt#queries).

### gcloud

Use the [`gcloud projects add-iam-policy-binding` command](https://docs.cloud.google.com/sdk/gcloud/reference/projects/add-iam-policy-binding):

```
gcloud projects add-iam-policy-binding PROJECT_ID \
--member="serviceAccount:$(bq show --format=prettyjson --connection $PROJECT_ID.$REGION.$CONNECTION_ID | jq -r .cloudResource.serviceAccountId)"
--role=roles/aiplatform.user
```

Replace the following:

- `PROJECT_ID`: the name of your project.
- `REGION`: the location where the connection was created.
- `CONNECTION_ID`: The name of the connection you created.

### Terraform

Use the
[`google_bigquery_connection`](https://registry.terraform.io/providers/hashicorp/google/latest/docs/resources/bigquery_connection)
resource.

> [!NOTE]
> **Note:** To create BigQuery objects using Terraform, you must enable the [Cloud Resource Manager API](https://docs.cloud.google.com/resource-manager/reference/rest.md.txt).

To authenticate to BigQuery, set up Application Default
Credentials. For more information, see
[Set up authentication for client libraries](https://docs.cloud.google.com/bigquery/docs/authentication.md.txt#client-libs).

The following example grants IAM role access to the service
account of the Cloud resource connection:

```terraform
## This grants IAM role access to the service account of the connection created in the previous step.
resource "google_project_iam_member" "aiplatformpermission" {
  project = data.google_project.default.project_id
  role    = "roles/aiplatform.user"
  member  = "serviceAccount:${google_bigquery_connection.default.cloud_resource[0].service_account_id}"
}
```

To apply your Terraform configuration in a Google Cloud project, complete the steps in the
following sections.

## Prepare Cloud Shell

1. Launch [Cloud Shell](https://shell.cloud.google.com/).
2. Set the default Google Cloud project
   where you want to apply your Terraform configurations.

   You only need to run this command once per project, and you can run it in any directory.

   ```
   export GOOGLE_CLOUD_PROJECT=PROJECT_ID
   ```

   Environment variables are overridden if you set explicit values in the Terraform
   configuration file.

## Prepare the directory

Each Terraform configuration file must have its own directory (also
called a *root module*).

1. In [Cloud Shell](https://shell.cloud.google.com/), create a directory and a new file within that directory. The filename must have the `.tf` extension---for example `main.tf`. In this tutorial, the file is referred to as `main.tf`.

   ```
   mkdir DIRECTORY && cd DIRECTORY && touch main.tf
   ```
2. If you are following a tutorial, you can copy the sample code in each section or step.

   Copy the sample code into the newly created `main.tf`.

   Optionally, copy the code from GitHub. This is recommended
   when the Terraform snippet is part of an end-to-end solution.
3. Review and modify the sample parameters to apply to your environment.
4. Save your changes.
5. Initialize Terraform. You only need to do this once per directory.

   ```
   terraform init
   ```

   Optionally, to use the latest Google provider version, include the `-upgrade`
   option:

   ```
   terraform init -upgrade
   ```

## Apply the changes

1. Review the configuration and verify that the resources that Terraform is going to create or update match your expectations:

   ```
   terraform plan
   ```

   Make corrections to the configuration as necessary.
2. Apply the Terraform configuration by running the following command and entering `yes` at the prompt:

   ```
   terraform apply
   ```

   Wait until Terraform displays the "Apply complete!" message.
3. [Open your Google Cloud project](https://console.cloud.google.com/) to view the results. In the Google Cloud console, navigate to your resources in the UI to make sure that Terraform has created or updated them.

> [!NOTE]
> **Note:** Terraform samples typically assume that the required APIs are enabled in your Google Cloud project.