This document provides technical guidance for US Federal agencies and DoD
departments on deploying and using Gemini for Government in compliance
with FedRAMP High and DoD Impact Level 4 (IL4) requirements. This document
describes which services and features are included in the authorization
boundaries and the steps to help you meet your compliance obligations.

Gemini for Government uses
[Assured Workloads](https://docs.cloud.google.com/assured-workloads/docs/overview) to help with
compliance requirements. You must deploy all Gemini for
Government resources within an Assured Workloads folder that's
configured for your specific compliance regime (FedRAMP High or IL4).

## Core product dependencies

Gemini for Government relies on several
Google Cloud services. The following table lists the compliance
status for each service.

| Google Cloud service | FedRAMP High status | IL4 status |
|---|---|---|
| Gemini Enterprise | Authorized | Authorized |
| Generative AI on Gemini Enterprise Agent Platform (formerly Generative AI on Vertex AI) | Authorized | Authorized |
| BigQuery | Authorized | Authorized |
| Cloud Storage | Authorized | Authorized |
| Looker (Google Cloud core) | Authorized | Submitted |

> [!NOTE]
> **Note:** Because Looker (Google Cloud core) isn't yet IL4 authorized, dependent features like Gemini in Looker aren't authorized for IL4, as described in [Unauthorized features that you should disable
> manually](https://docs.cloud.google.com/docs/security/compliance/deploy-gemini-gov#unauthorized-features).

## Authorized services and features

The following table lists the services and features that you can use within
Gemini for Government for FedRAMP High and IL4 deployments.

| Feature | FedRAMP High | IL4 |
|---|---|---|
| [Autocomplete](https://docs.cloud.google.com/gemini/enterprise/docs/configure-autocomplete) | Authorized | Authorized |
| [Serving controls](https://docs.cloud.google.com/gemini/enterprise/docs/configure-serving-controls) | Authorized | Authorized |
| Authorized data stores such as [Cloud Storage](https://docs.cloud.google.com/gemini/enterprise/docs/connect-cloud-storage) and [BigQuery](https://docs.cloud.google.com/gemini/enterprise/docs/connect-bigquery) | Authorized | Authorized |
| [Web Grounding for Enterprise](https://docs.cloud.google.com/gemini-enterprise-agent-platform/models/grounding/web-grounding-enterprise) | Authorized | Authorized |
| [Uploading documents](https://docs.cloud.google.com/gemini/enterprise/docs/assistant-chat#upload_and_chat_about_files) from local machines | Authorized | Authorized |
| Ability for end users to [select models](https://docs.cloud.google.com/gemini/enterprise/docs/answer-generation-models) | Authorized | Authorized |
| [In-memory data caching](https://docs.cloud.google.com/gemini-enterprise-agent-platform/resources/zero-data-retention#in-memory-caching) | Authorized | Authorized |
| [Deep Research agent](https://docs.cloud.google.com/gemini/enterprise/docs/research-assistant) | Authorized | DISA review |
| No-code agent creation using [Agent Designer](https://docs.cloud.google.com/gemini/enterprise/docs/agent-designer) | Authorized | DISA review |
| [Agent Gallery](https://docs.cloud.google.com/gemini/enterprise/docs/agent-gallery) | Authorized | DISA review |
| [Image generation using Nano Banana](https://docs.cloud.google.com/gemini/enterprise/docs/assistant-analyze#generate_an_image) | Authorized | DISA review |
| [Gemini Notebook Enterprise](https://docs.cloud.google.com/gemini/enterprise/notebooklm-enterprise/docs/overview) (excludes Audio Overview, Infographic, Slide Deck, and Video Overview) | Authorized | DISA review |
| [Model Armor](https://docs.cloud.google.com/gemini/enterprise/docs/enable-model-armor) | Authorized | DISA review |
| Google Workspace federated connectors (includes [Gmail](https://docs.cloud.google.com/gemini/enterprise/docs/connectors/gmail), [Google Drive](https://docs.cloud.google.com/gemini/enterprise/docs/connectors/gdrive), and [Google Calendar](https://docs.cloud.google.com/gemini/enterprise/docs/connectors/gcal)) | Authorized | DISA review |
| Third-party federated connectors (such as Microsoft Office 365 Government Community Cloud (GCC), Office GCC High and DoD, and [Salesforce](https://docs.cloud.google.com/gemini/enterprise/docs/connectors/salesforce)) | Authorized | DISA review |
| [Canvas](https://docs.cloud.google.com/gemini/enterprise/docs/assistant-canvas) | Authorized | DISA review |
| [Projects](https://docs.cloud.google.com/gemini/enterprise/docs/projects) | Authorized | DISA review |
| [Skills](https://docs.cloud.google.com/gemini/enterprise/docs/skills) | Authorized | DISA review |

## Model support

This section describes support for built-in and third-party models.

### Built-in model support

You can use certain built-in models that support [US multi-regional
endpoints](https://docs.cloud.google.com/gemini-enterprise-agent-platform/resources/data-residency#ml-processing-google-models),
are generally available, and support data residency (DRZ) commitments.

If you require DRZ commitments, it is your responsibility to restrict access to
models that only support global endpoints. See [Restrict endpoint
usage](https://docs.cloud.google.com/docs/security/compliance/restrict-endpoint-usage) for more information
on how to restrict access to these models.

The following table lists the built-in models that support FedRAMP High, IL4,
IL5, ITAR, and CJIS.

| Model | FedRAMP High | IL4 and IL5 | ITAR | CJIS |
|---|---|---|---|---|
| Gemini 4 Argon (`gemini-4-argon`) | Yes | Yes | Yes | Yes |
| Gemini 3.8 Flash (`gemini-3.8-flash`) | Yes | Yes | Yes | Yes |
| Gemini 3.7 Flash (`gemini-3.7-flash`) | Yes | Yes | Yes | Yes |
| Gemini 3.6 Flash (`gemini-3.6-flash`) | Yes | Yes | Yes | Yes |
| Gemini 3.5 Flash-Lite (`gemini-3.5-flash-lite`) | Yes | Yes | Yes | Yes |
| Gemini 3.5 Flash (`gemini-3.5-flash`) | Yes | Yes | Yes | Yes |
| Gemini 3.1 Flash Image (`gemini-3.1-flash-image`) | Yes | Yes | Yes | Yes |
| Gemini 3.1 Flash-Lite (`gemini-3.1-flash-lite`) | Yes | Yes | Yes | Yes |
| Anthropic's Claude Haiku 5.5 on Google Cloud | Yes |   |   |   |
| Anthropic's Claude Opus 5.5 on Google Cloud | Yes |   |   |   |
| Anthropic's Claude Sonnet 5.5 on Google Cloud | Yes |   |   |   |
| Anthropic's Claude Sonnet 5 on Google Cloud | Yes |   |   |   |
| Anthropic's Claude Opus 5 on Google Cloud | Yes |   |   |   |
| Anthropic's Claude Fable 5.1 on Google Cloud | Yes |   |   |   |
| Anthropic's Claude Fable 5 on Google Cloud | Yes |   |   |   |
| Anthropic's Claude Haiku 4.5 on Google Cloud | Yes |   |   |   |
| Anthropic's Claude Opus 4.5 on Google Cloud | Yes |   |   |   |
| Anthropic's Claude Opus 4.8 on Google Cloud | Yes |   |   |   |
| Anthropic's Claude Opus 4.7 on Google Cloud | Yes |   |   |   |
| Anthropic's Claude Opus 4.6 on Google Cloud | Yes |   |   |   |
| Anthropic's Claude Sonnet 4.6 on Google Cloud | Yes |   |   |   |

### Third-party model support

Google Cloud is responsible for maintaining authorizations for its serving
infrastructure and custom-built containers so that you can deploy your own
third-party models for FedRAMP High and DoD IL4 and IL5.

Although Google doesn't validate the compliance status of third-party model
deployments or usage of these third-party models, you can use authorized
services (such as Generative AI on Gemini Enterprise Agent Platform and
Gemini Enterprise Agent Platform Inference: Batch and Online) to
interact with more than 200 first-party, third-party, and open-source large
language models (LLMs) available in Model Garden. It is your
responsibility to ensure third-party models are deployed, configured, and
secured in compliance with your FedRAMP and DoD IL4 and IL5 compliance
requirements. For more information, see [Overview of self-deployed
models](https://docs.cloud.google.com/gemini-enterprise-agent-platform/models/model-garden/self-deployed-models)
and [Control access to Model Garden
models](https://docs.cloud.google.com/gemini-enterprise-agent-platform/models/control-model-access).

## Connector support

Connectors retrieve data from Google or third-party data sources into
Gemini Enterprise. The two types of available connectors are
federated connectors and ingestion connectors.

Federated connectors retrieve data from supported Google or third-party data
sources. When a user runs a query, Gemini Enterprise federates
the request to the connected data source, retrieves matching results in real
time, and returns them in the query response. Data from the connected data
source is not persisted in the Gemini Enterprise index.

Ingestion connectors copy and index data from the source system into
Google Cloud. When a user runs a query, Gemini Enterprise
retrieves results from this persisted index to deliver the response. The
ingested data remains in the index until explicitly [removed or
updated](https://docs.cloud.google.com/gemini-enterprise-agent-platform/build/vector-search/create-manage-index).

You can enable and configure connectors from the
Gemini Enterprise console. To restrict which data sources and
egress destinations are permitted, you can use organization policy constraints.

### Third-party connector support

[Third-party federated connectors](https://docs.cloud.google.com/gemini/enterprise/docs/connectors/connect-third-party-data-source)
(available at GA or Public Preview) are in-scope for Google's FedRAMP High
authorization. IL5 authorization for federated connectors using
Gemini Enterprise is pending.

### Google connector support

The Google federated connector for Google Workspace (which includes
Gmail, Google Drive, and Google Calendar) is in-scope for Google's
FedRAMP High authorization. IL5 authorization is pending.

Additionally, you can use the following Google ingestion connectors to comply
with FedRAMP High and IL5 requirements:

- [BigQuery](https://docs.cloud.google.com/gemini/enterprise/docs/connectors/connect-bigquery)
- [Cloud Storage](https://docs.cloud.google.com/gemini/enterprise/docs/connectors/connect-cloud-storage)

To ensure compliance, create a connection that uses regional endpoints and that
is within the same organization and VPC Service Controls boundary.

For more information about connectors, see [Introduction to connectors and data
stores](https://docs.cloud.google.com/gemini/enterprise/docs/connectors/introduction-to-connectors-and-data-stores).

## Unauthorized features that you should disable manually

The following services and features aren't authorized for FedRAMP High or IL4.
However, they aren't blocked by the Assured Workloads control
packages and are available in your project. As part of your risk assessment, you
might need to evaluate service usage relative to sensitive data and any
mitigating controls available to you. You may need to manually disable the
features on this list in your Gemini Enterprise app configuration
based on your assessment.

| Agents and galleries | - [Prompt gallery](https://docs.cloud.google.com/vertex-ai/generative-ai/docs/prompt-gallery) |
| Grounding | - [Grounding with Google Maps Platform](https://docs.cloud.google.com/gemini-enterprise-agent-platform/models/grounding/grounding-with-google-maps) - [Grounding with Google Search](https://docs.cloud.google.com/gemini-enterprise-agent-platform/models/grounding/grounding-with-google-search) - Grounding using Google Drive uploads (for IL4 use cases) - Grounding using Microsoft OneDrive uploads (for IL4 use cases) |
| Generative features | - [Generate images using Imagen](https://ai.google.dev/gemini-api/docs/imagen) - [Generate video with Veo](https://ai.google.dev/gemini-api/docs/video) |
| User, session, and UI features | - [User events for Gemini Enterprise apps](https://docs.cloud.google.com/gemini/enterprise/docs/user-events) - [Personalization and memory in Gemini Enterprise](https://docs.cloud.google.com/gemini/enterprise/docs/configure-personalization) - [Gemini Notebook Enterprise (for IL4 and IL5 use cases)](https://docs.cloud.google.com/gemini/enterprise/notebooklm-enterprise/docs/overview) - [Standalone Gemini Notebook Enterprise](https://docs.cloud.google.com/gemini/enterprise/notebooklm-enterprise/docs/overview#notebooklm-availability) |
| Other features | - [Private Knowledge Graph in Gemini Enterprise](https://docs.cloud.google.com/gemini/enterprise/docs/use-knowledge-graph-search) - [Model Armor (for IL4 and IL5 use cases)](https://docs.cloud.google.com/gemini/enterprise/docs/enable-model-armor) - [Durable caching](https://docs.cloud.google.com/gemini-enterprise-agent-platform/resources/zero-data-retention#durable-data-caching) |
|---|---|

For more information about durable caching, see [Gemini Enterprise Agent Platform and zero data
retention](https://docs.cloud.google.com/gemini-enterprise-agent-platform/resources/zero-data-retention).

## Unauthorized features that you can't disable

The following services and features are available in the
Assured Workloads control package. You can't disable them. If you
use these features, we recommend that you conduct a proper risk assessment prior
to granting your authorization to make sure service usage is appropriate for
your FedRAMP High or IL4 deployment. For example, you can assess service usage
relative to data sensitivity. You can also evaluate if any mitigating controls
based on data encryption are available to you to establish sole control over
data access.

| Analytics and dependent features | - [View analytics data](https://docs.cloud.google.com/gemini/enterprise/docs/view-analytics) - [Data agent context for Looker data sources](https://docs.cloud.google.com/gemini/docs/conversational-analytics-api/data-agent-authored-context-looker) - [Data agent context for BigQuery data sources](https://docs.cloud.google.com/gemini/docs/conversational-analytics-api/data-agent-authored-context-bq) - [Data agents that you create](https://docs.cloud.google.com/gemini/docs/conversational-analytics-api/overview#build-and-interact-with-a-data-agent) using the Conversational Analytics API - [Gemini in BigQuery](https://docs.cloud.google.com/bigquery/docs/gemini-overview) - [Gemini in Looker](https://docs.cloud.google.com/gemini/docs/looker/overview) |
| Data connectors and stores | - Google Cloud data stores such as Cloud SQL and Firestore |
| User, session, and UI features | - [Prompt chips](https://docs.cloud.google.com/gemini/enterprise/docs/configure-prompt-chips) |
| Other features | - [Gemini Code Assist](https://docs.cloud.google.com/gemini/docs/codeassist/overview) |
|---|---|

## Deploy your environment

Follow these steps for assistance with deploying an environment that meets your
compliance obligations:

1. Deploy Assured Workloads:
   1. [Create an Assured Workloads
      folder](https://docs.cloud.google.com/assured-workloads/docs/create-folder) that uses Data Boundary for FedRAMP High or Data Boundary for IL4.
   2. [Create your Google Cloud project](https://docs.cloud.google.com/resource-manager/docs/creating-managing-projects) inside this folder.
   3. [Verify that all users and service accounts](https://docs.cloud.google.com/resource-manager/docs/access-control-proj) have the required Identity and Access Management (IAM) permissions.
2. Configure your FedRAMP High or IL4 network. For more information, see [Configure network for FedRAMP and DoD on
   Google Cloud](https://docs.cloud.google.com/architecture/configure-networks-fedramp-dod-google-cloud).
   1. Create a [Gemini Enterprise
      app](https://docs.cloud.google.com/gemini/enterprise/docs/create-app). Select **US Multi-region** as the location. The Assured Workloads data residency policy enforces this option.
3. Connect to a [Google data source](https://docs.cloud.google.com/gemini/enterprise/docs/create-data-store)
   that's located within your Assured Workloads folder. The
   authorized data stores for FedRAMP High and IL4 are Cloud Storage
   buckets and BigQuery datasets.

   > [!NOTE]
   > **Note:** Don't connect to an unauthorized data source (for example, Cloud SQL or Google Drive) or a resource that's outside your Assured Workloads folder.

4. Configure authorized compliance features.

5. [Turn off the unauthorized features](https://docs.cloud.google.com/docs/security/compliance/deploy-gemini-gov#turn-off-unauthorized-features) that
   are described in [unauthorized features that you should disable
   manually](https://docs.cloud.google.com/docs/security/compliance/deploy-gemini-gov#unauthorized-features).

6. Train your personnel not to use [unauthorized features that you can't
   disable](https://docs.cloud.google.com/docs/security/compliance/deploy-gemini-gov#unauthorized-features-cant).

## Turn off unauthorized features

Complete the tasks in this section to turn off [unauthorized
features](https://docs.cloud.google.com/docs/security/compliance/deploy-gemini-gov#unauthorized-features) that you can disable manually.

### Disable the prompt gallery

Complete this task for each app that you deploy in Gemini Enterprise.

Ensure that you have one of the following roles:

- **Discovery Engine Admin** (`roles/discoveryengine.admin`)
- **Gemini Enterprise Admin** (`roles/discoveryengine.agentspaceAdmin`)
- A custom role with the `discoveryengine.engines.update` permission

### Console

1. In the Google Cloud console, go to the **Gemini Enterprise apps** page.


[Go to Apps](https://console.cloud.google.com/gemini-enterprise/apps)

<br />

1. Select the app.
2. In the navigation menu, click **Configurations** and then select the **Feature Management** tab.
3. Turn off **Enable prompt gallery**.
4. Click **Save**.

### REST

To update the feature control map of your app, use the `engines.patch`
method on the `discoveryengine.googleapis.com` API endpoint.

Set the `prompt-gallery` key to `FEATURE_STATE_OFF` in your engine's
[`features`
configuration](https://docs.cloud.google.com/generative-ai-app-builder/docs/reference/rest/v1/projects.locations.collections.engines).


Before using any of the request data,
make the following replacements:

- `PROJECT_ID`: the ID of your project
- `APP_ID`: the ID of your app


HTTP method and URL:

```
PATCH https://discoveryengine.googleapis.com/v1/projects/PROJECT_ID/locations/global/collections/default_collection/engines/APP_ID?updateMask=features
```


Request JSON body:

```
{
  "features": {
    "prompt-gallery": "FEATURE_STATE_OFF"
  }
}
```

To send your request, expand one of these options:

#### curl (Linux, macOS, or Cloud Shell)

> [!NOTE]
> **Note:** The following command assumes that you have logged in to the `gcloud` CLI with your user account by running [`gcloud init`](https://docs.cloud.google.com/sdk/gcloud/reference/init) or [`gcloud auth login`](https://docs.cloud.google.com/sdk/gcloud/reference/auth/login) , or by using [Cloud Shell](https://docs.cloud.google.com/shell/docs), which automatically logs you into the `gcloud` CLI . You can check the currently active account by running [`gcloud auth list`](https://docs.cloud.google.com/sdk/gcloud/reference/auth/list).


Save the request body in a file named `request.json`,
and execute the following command:

```
curl -X PATCH \
     -H "Authorization: Bearer $(gcloud auth print-access-token)" \
     -H "x-goog-user-project: PROJECT_ID" \
     -H "Content-Type: application/json; charset=utf-8" \
     -d @request.json \
     "https://discoveryengine.googleapis.com/v1/projects/PROJECT_ID/locations/global/collections/default_collection/engines/APP_ID?updateMask=features"
```

#### PowerShell (Windows)

> [!NOTE]
> **Note:** The following command assumes that you have logged in to the `gcloud` CLI with your user account by running [`gcloud init`](https://docs.cloud.google.com/sdk/gcloud/reference/init) or [`gcloud auth login`](https://docs.cloud.google.com/sdk/gcloud/reference/auth/login) . You can check the currently active account by running [`gcloud auth list`](https://docs.cloud.google.com/sdk/gcloud/reference/auth/list).


Save the request body in a file named `request.json`,
and execute the following command:

```
$cred = gcloud auth print-access-token
$headers = @{ "Authorization" = "Bearer $cred"; "x-goog-user-project" = "PROJECT_ID" }

Invoke-WebRequest `
    -Method PATCH `
    -Headers $headers `
    -ContentType: "application/json; charset=utf-8" `
    -InFile request.json `
    -Uri "https://discoveryengine.googleapis.com/v1/projects/PROJECT_ID/locations/global/collections/default_collection/engines/APP_ID?updateMask=features" | Select-Object -Expand Content
```

You should receive a JSON response similar to the following:

```
{
  "name": "projects/PROJECT_ID/locations/global/collections/default_collection/engines/APP_ID",
  "features": {
    "prompt-gallery": "FEATURE_STATE_OFF"
  }
}
```

<br />

### Turn off grounding with Google Maps Platform

To turn off grounding with Google Maps Platform for all requests, you can
disable the **Maps Grounding API** (`mapsgrounding.googleapis.com`) using one of
the following methods:

- In the **APIs \& Services** page on the console, locate the **Map Grounding
  API** (`mapsgrounding.googleapis.com`), and select **Disable API** . For more
  information, see [Enable and disable
  services](https://docs.cloud.google.com/service-usage/docs/enable-disable#before).

- In the Google Cloud CLI, run:

      gcloud services disable mapsgrounding.googleapis.com

### Turn off grounding with Google Search

To turn off grounding with Google Search for all requests, set the
`constraints/vertexai.disableGenAIGoogleSearchGrounding` organization policy
boolean constraint to `true` at the Assured Workloads folder
level. For more information, see [Updating policies with boolean
rules](https://docs.cloud.google.com/organization-policy/apply-policies#boolean_constraints).

### Turn off grounding using Google Drive uploads (IL4 only)

This section applies to DoD IL4 customers only.

Grounding with Google Drive is only enabled when you connect a Google Drive
data store to your app. To disable grounding with Google Drive uploads,
complete the following:

- Ensure that no Google Drive data stores are configured in your
  Gemini Enterprise apps. If an app is already connected to a
  Google Drive data store, remove it from the app's settings in the console,
  or delete the data store using the [`dataStores.delete`
  method](https://docs.cloud.google.com/generative-ai-app-builder/docs/reference/rest/v1beta/projects.locations.collections.dataStores/delete)
  in the Discovery Engine API.

- Disable Workspace data-sharing capabilities in the Google Admin console,
  or disable [**Smart features and
  personalization**](https://knowledge.workspace.google.com/admin/security/manage-google-workspace-smart-features-for-your-users)
  in Google Workspace to block the connector from accessing user documents
  in Google Drive.

### Turn off grounding using Microsoft OneDrive uploads (IL4 only)

This section applies to DoD IL4 customers only.

Grounding with Microsoft OneDrive is only enabled when you connect a Microsoft
OneDrive data store to your app. To disable grounding with Microsoft OneDrive
uploads, complete the following:

- Ensure that no Microsoft OneDrive data stores are configured in your Gemini Enterprise apps. If an app is already connected to a Microsoft OneDrive data store, remove it from the [app's settings in the
  console](https://docs.cloud.google.com/gemini/enterprise/docs/connectors/connect-existing-data-store), or delete the data store using the [`dataStores.delete`
  method](https://docs.cloud.google.com/generative-ai-app-builder/docs/reference/rest/v1/projects.locations.collections.dataStores/delete) in the Discovery Engine API.
- To block the connector's access, revoke the credentials or delete the registered OAuth 2.0 application client ID and credentials in Microsoft Entra ID (Azure AD) that is used for Microsoft OneDrive connectivity.

### Turn off Imagen and Veo

To turn off image generation using Imagen and video generation using Veo,
complete the following:

- Set the `constraints/vertexai.allowedModels` or `constraints/vertexai.allowedGenAIModels` organization policy list constraint at the folder or organization level to deny the `imagen` and `veo` models (for example, `publishers/google/models/imagen-4.0-ultra-generate-001`) or to permit only approved models. For more information, see [Control access to
  Model Garden
  models](https://docs.cloud.google.com/gemini-enterprise-agent-platform/models/control-model-access).
- To restrict prediction access on Imagen or Veo models, configure an [IAM deny policy](https://docs.cloud.google.com/iam/docs/deny-overview) that denies the
  `aiplatform.endpoints.predict` IAM permission on the resource
  path for the model. The model resource path is `projects/PROJECT_ID/locations/LOCATION/publishers/google/models/MODEL_NAME`.

  Replace the following:
  - <var translate="no">PROJECT_ID</var>: the ID of your project
  - <var translate="no">LOCATION</var>: the location of the app
  - <var translate="no">MODEL_NAME</var>: the name of the model to allow or deny

### Turn off user events for Gemini Enterprise apps

User events are sent by client-side event trackers or imported in bulk. To
disable user events collection, complete one of the following:

- When configuring the search widget for your application, disable event
  logging by setting the `disableUserEventsCollection` property to `true`
  inside the [`uiSettings` configuration
  namespace](https://docs.cloud.google.com/gemini/enterprise/docs/reference/rest/v1/projects.locations.collections.dataStores.widgetConfigs#uisettings).
  For example:

      "uiSettings": {
      "disableUserEventsCollection": true
      }

- Don't call the event injection endpoints (specifically the
  [`userEvents.collect` method](https://docs.cloud.google.com/gemini/enterprise/docs/reference/rest/v1/projects.locations.userEvents/collect)
  and the [`userEvents.write`
  method](https://docs.cloud.google.com/gemini/enterprise/docs/reference/rest/v1/projects.locations.userEvents/write))
  and ensure that search pixel scripts (such as `v1beta_event.js`) are not
  active on your client pages.

- Update the setting at the application level, as follows:

  1. In the Google Cloud console, go to the **Gemini Enterprise apps** page.


  [Go to Apps](https://console.cloud.google.com/gemini-enterprise/apps)

  <br />

  1. Select the app.
  2. In the navigation menu, click **Configurations**.
  3. Turn off **Enable user event collection**.
  4. Click **Save**.

### Turn off personalization and memory in Gemini Enterprise

Complete this task for each app that you deploy in Gemini Enterprise.

Ensure that you have one of the following roles:

- **Discovery Engine Admin** (`roles/discoveryengine.admin`)
- **Gemini Enterprise Admin** (`roles/discoveryengine.agentspaceAdmin`)
- A custom role with the `discoveryengine.engines.update` permission

### Console

For instructions, see [Turn off personalization and
memory](https://docs.cloud.google.com/gemini/enterprise/docs/configure-personalization#disable-personalization-and-memory).

### REST

To update the feature control map of your app, use the `engines.patch`
method on the `discoveryengine.googleapis.com` API endpoint.

Set the `personalization-memory` and `personalization-suggested-highlights`
keys to `FEATURE_STATE_OFF` in your engine's [`features`
configuration](https://docs.cloud.google.com/generative-ai-app-builder/docs/reference/rpc/google.cloud.discoveryengine.v1#engine).


Before using any of the request data,
make the following replacements:

- `PROJECT_ID`: the ID of your project
- `APP_ID`: the ID of your app


HTTP method and URL:

```
PATCH https://discoveryengine.googleapis.com/v1/projects/PROJECT_ID/locations/global/collections/default_collection/engines/APP_ID?updateMask=features
```


Request JSON body:

```
{
  "features": {
    "personalization-memory": "FEATURE_STATE_OFF",
    "personalization-suggested-highlights": "FEATURE_STATE_OFF"
  }
}
```

To send your request, expand one of these options:

#### curl (Linux, macOS, or Cloud Shell)

> [!NOTE]
> **Note:** The following command assumes that you have logged in to the `gcloud` CLI with your user account by running [`gcloud init`](https://docs.cloud.google.com/sdk/gcloud/reference/init) or [`gcloud auth login`](https://docs.cloud.google.com/sdk/gcloud/reference/auth/login) , or by using [Cloud Shell](https://docs.cloud.google.com/shell/docs), which automatically logs you into the `gcloud` CLI . You can check the currently active account by running [`gcloud auth list`](https://docs.cloud.google.com/sdk/gcloud/reference/auth/list).


Save the request body in a file named `request.json`,
and execute the following command:

```
curl -X PATCH \
     -H "Authorization: Bearer $(gcloud auth print-access-token)" \
     -H "x-goog-user-project: PROJECT_ID" \
     -H "Content-Type: application/json; charset=utf-8" \
     -d @request.json \
     "https://discoveryengine.googleapis.com/v1/projects/PROJECT_ID/locations/global/collections/default_collection/engines/APP_ID?updateMask=features"
```

#### PowerShell (Windows)

> [!NOTE]
> **Note:** The following command assumes that you have logged in to the `gcloud` CLI with your user account by running [`gcloud init`](https://docs.cloud.google.com/sdk/gcloud/reference/init) or [`gcloud auth login`](https://docs.cloud.google.com/sdk/gcloud/reference/auth/login) . You can check the currently active account by running [`gcloud auth list`](https://docs.cloud.google.com/sdk/gcloud/reference/auth/list).


Save the request body in a file named `request.json`,
and execute the following command:

```
$cred = gcloud auth print-access-token
$headers = @{ "Authorization" = "Bearer $cred"; "x-goog-user-project" = "PROJECT_ID" }

Invoke-WebRequest `
    -Method PATCH `
    -Headers $headers `
    -ContentType: "application/json; charset=utf-8" `
    -InFile request.json `
    -Uri "https://discoveryengine.googleapis.com/v1/projects/PROJECT_ID/locations/global/collections/default_collection/engines/APP_ID?updateMask=features" | Select-Object -Expand Content
```

You should receive a JSON response similar to the following:

```
{
  "name": "projects/PROJECT_ID/locations/global/collections/default_collection/engines/APP_ID",
  "features": {
    "prompt-gallery": "FEATURE_STATE_OFF",
    "personalization-memory": "FEATURE_STATE_OFF",
    "personalization-suggested-highlights": "FEATURE_STATE_OFF"
  }
}
```

<br />

### Turn off Private Knowledge Graph

To turn off the Private Knowledge Graph, you can use the console or the API.

Ensure that you have one of the following roles:

- **Discovery Engine Admin** (`roles/discoveryengine.admin`)
- **Gemini Enterprise Admin** (`roles/discoveryengine.agentspaceAdmin`)
- A custom role with the `discoveryengine.engines.update` permission

### Console

For instructions, see [Manage Knowledge Graph
configuration](https://docs.cloud.google.com/gemini/enterprise/docs/use-knowledge-graph-search#manage-kg-config).

### REST

To update your app configuration, use the `engines.patch` method on the
`discoveryengine.googleapis.com` API endpoint.

Set `enablePrivateKnowledgeGraph` and `enableCloudKnowledgeGraph` to `false`
inside the [`knowledgeGraphConfig`
parameter](https://docs.cloud.google.com/generative-ai-app-builder/docs/reference/rest/v1/projects.locations.collections.engines#knowledgegraphconfig).


Before using any of the request data,
make the following replacements:

- `PROJECT_ID`: the ID of your project
- `APP_ID`: the ID of your app


HTTP method and URL:

```
PATCH https://discoveryengine.googleapis.com/v1/projects/PROJECT_ID/locations/global/collections/default_collection/engines/APP_ID?updateMask=knowledgeGraphConfig
```


Request JSON body:

```
{
  "knowledgeGraphConfig": {
    "enableCloudKnowledgeGraph": false,
    "enablePrivateKnowledgeGraph": false
  }
}
```

To send your request, expand one of these options:

#### curl (Linux, macOS, or Cloud Shell)

> [!NOTE]
> **Note:** The following command assumes that you have logged in to the `gcloud` CLI with your user account by running [`gcloud init`](https://docs.cloud.google.com/sdk/gcloud/reference/init) or [`gcloud auth login`](https://docs.cloud.google.com/sdk/gcloud/reference/auth/login) , or by using [Cloud Shell](https://docs.cloud.google.com/shell/docs), which automatically logs you into the `gcloud` CLI . You can check the currently active account by running [`gcloud auth list`](https://docs.cloud.google.com/sdk/gcloud/reference/auth/list).


Save the request body in a file named `request.json`,
and execute the following command:

```
curl -X PATCH \
     -H "Authorization: Bearer $(gcloud auth print-access-token)" \
     -H "x-goog-user-project: PROJECT_ID" \
     -H "Content-Type: application/json; charset=utf-8" \
     -d @request.json \
     "https://discoveryengine.googleapis.com/v1/projects/PROJECT_ID/locations/global/collections/default_collection/engines/APP_ID?updateMask=knowledgeGraphConfig"
```

#### PowerShell (Windows)

> [!NOTE]
> **Note:** The following command assumes that you have logged in to the `gcloud` CLI with your user account by running [`gcloud init`](https://docs.cloud.google.com/sdk/gcloud/reference/init) or [`gcloud auth login`](https://docs.cloud.google.com/sdk/gcloud/reference/auth/login) . You can check the currently active account by running [`gcloud auth list`](https://docs.cloud.google.com/sdk/gcloud/reference/auth/list).


Save the request body in a file named `request.json`,
and execute the following command:

```
$cred = gcloud auth print-access-token
$headers = @{ "Authorization" = "Bearer $cred"; "x-goog-user-project" = "PROJECT_ID" }

Invoke-WebRequest `
    -Method PATCH `
    -Headers $headers `
    -ContentType: "application/json; charset=utf-8" `
    -InFile request.json `
    -Uri "https://discoveryengine.googleapis.com/v1/projects/PROJECT_ID/locations/global/collections/default_collection/engines/APP_ID?updateMask=knowledgeGraphConfig" | Select-Object -Expand Content
```

You should receive a JSON response similar to the following:

```
{
  "name": "projects/PROJECT_ID/locations/global/collections/default_collection/engines/APP_ID",
  "knowledgeGraphConfig": {
    "enableCloudKnowledgeGraph": false,
    "enablePrivateKnowledgeGraph": false
  }
}
```

<br />

### Turn off Model Armor (IL4 only)

This section applies to DoD IL4 customers only.

To turn off Model Armor for DOD IL4 environments, remove its
templates from your apps and then disable the API.

To remove the templates, see [Remove the Model Armor templates
from a Gemini Enterprise
app](https://docs.cloud.google.com/gemini/enterprise/docs/enable-model-armor#remove-model-armor-templates).

To disable the **Model Armor API** (`modelarmor.googleapis.com`), use one of the
following methods:

- In the **APIs \& Services** page on the console, locate **Model Armor API**
  (`modelarmor.googleapis.com`), and select **Disable API** . For more
  information, see [Enable and disable
  services](https://docs.cloud.google.com/service-usage/docs/enable-disable#before).

- In Google Cloud CLI, run:

      gcloud services disable modelarmor.googleapis.com

### Turn off durable caching

To turn off durable caching, see [Turn off durable
caching](https://docs.cloud.google.com/gemini-enterprise-agent-platform/resources/zero-data-retention#expandable-4).

### Turn off Gemini Notebook Enterprise (IL4 and IL5 only)

This section applies to DoD IL4 and IL5 customers only.

Complete this task for each app that you deploy in Gemini Enterprise.

Ensure that you have one of the following roles:

- **Discovery Engine Admin** (`roles/discoveryengine.admin`)
- **Gemini Enterprise Admin** (`roles/discoveryengine.agentspaceAdmin`)
- A custom role with the `discoveryengine.engines.update` permission

### Console

1. In the Google Cloud console, go to the **Gemini Enterprise apps** page.


[Go to Apps](https://console.cloud.google.com/gemini-enterprise/apps)

<br />

1. Select the app.
2. In the navigation menu, click **Configurations** and then select the **Feature Management** tab.
3. Turn off **Notebook**.
4. Click **Save**.

### REST

To update the feature control map of your app, use the `engines.patch`
method on the `discoveryengine.googleapis.com` API endpoint. Set the
`notebook-lm` key to `FEATURE_STATE_OFF` in your engine's [`features`
configuration](https://docs.cloud.google.com/generative-ai-app-builder/docs/reference/rest/v1/projects.locations.collections.engines).


Before using any of the request data,
make the following replacements:

- `PROJECT_ID`: the ID of your project
- `APP_ID`: the ID of your app


HTTP method and URL:

```
PATCH https://discoveryengine.googleapis.com/v1/projects/PROJECT_ID/locations/global/collections/default_collection/engines/APP_ID?updateMask=features
```


Request JSON body:

```
{
  "features": {
    "notebook-lm": "FEATURE_STATE_OFF"
  }
}
```

To send your request, expand one of these options:

#### curl (Linux, macOS, or Cloud Shell)

> [!NOTE]
> **Note:** The following command assumes that you have logged in to the `gcloud` CLI with your user account by running [`gcloud init`](https://docs.cloud.google.com/sdk/gcloud/reference/init) or [`gcloud auth login`](https://docs.cloud.google.com/sdk/gcloud/reference/auth/login) , or by using [Cloud Shell](https://docs.cloud.google.com/shell/docs), which automatically logs you into the `gcloud` CLI . You can check the currently active account by running [`gcloud auth list`](https://docs.cloud.google.com/sdk/gcloud/reference/auth/list).


Save the request body in a file named `request.json`,
and execute the following command:

```
curl -X PATCH \
     -H "Authorization: Bearer $(gcloud auth print-access-token)" \
     -H "x-goog-user-project: PROJECT_ID" \
     -H "Content-Type: application/json; charset=utf-8" \
     -d @request.json \
     "https://discoveryengine.googleapis.com/v1/projects/PROJECT_ID/locations/global/collections/default_collection/engines/APP_ID?updateMask=features"
```

#### PowerShell (Windows)

> [!NOTE]
> **Note:** The following command assumes that you have logged in to the `gcloud` CLI with your user account by running [`gcloud init`](https://docs.cloud.google.com/sdk/gcloud/reference/init) or [`gcloud auth login`](https://docs.cloud.google.com/sdk/gcloud/reference/auth/login) . You can check the currently active account by running [`gcloud auth list`](https://docs.cloud.google.com/sdk/gcloud/reference/auth/list).


Save the request body in a file named `request.json`,
and execute the following command:

```
$cred = gcloud auth print-access-token
$headers = @{ "Authorization" = "Bearer $cred"; "x-goog-user-project" = "PROJECT_ID" }

Invoke-WebRequest `
    -Method PATCH `
    -Headers $headers `
    -ContentType: "application/json; charset=utf-8" `
    -InFile request.json `
    -Uri "https://discoveryengine.googleapis.com/v1/projects/PROJECT_ID/locations/global/collections/default_collection/engines/APP_ID?updateMask=features" | Select-Object -Expand Content
```

You should receive a JSON response similar to the following:

```
{
  "name": "projects/PROJECT_ID/locations/global/collections/default_collection/engines/APP_ID",
  "features": {
    "prompt-gallery": "FEATURE_STATE_OFF",
    "notebook-lm": "FEATURE_STATE_OFF"
  }
}
```

<br />

### Remove access to the standalone Gemini Notebook Enterprise

To remove access to the standalone Gemini Notebook Enterprise
(`https://notebooklm.cloud.google.com/`), revoke the following
IAM roles from all users and groups:

- **Cloud NotebookLM User** (`roles/discoveryengine.notebookLmUser`)
- **Cloud NotebookLM Admin** (`roles/discoveryengine.notebookLmOwner`)

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

Optionally, if your organization purchased a separate standalone
Gemini Notebook Enterprise subscription (rather than a
Gemini Enterprise subscription), turn off auto-renewal:

1. In the Google Cloud console, go to the **Gemini Enterprise \> Manage
   subscriptions** page.


   [Go to Gemini Enterprise](https://console.cloud.google.com/gemini-enterprise/start)

   <br />

2. Click the name of your standalone subscription.

3. Click **Edit**.

4. Clear the **Auto renew subscription** checkbox.

5. Click **Submit**.