This document describes how to create a
[data store](https://docs.cloud.google.com/gemini/enterprise/docs/concepts.md.txt) that connects to Spanner
data. You can link this data store to a Gemini Enterprise app to allow
the agents to analyze your data.

To connect to Spanner data using a Gemini Enterprise
data store, you can use one of the following modes:

- **Federated query (recommended)**
  \[[Preview](https://cloud.google.com/products#product-launch-stages)\]:
  Connect to Spanner data in place without incurring egress
  costs for copying and moving the data. Federated query sends your query
  directly to Spanner across all databases and tables that your
  identity has Identity and Access Management (IAM) permission to access, which is more
  efficient for analytical queries. When you use federated query mode,
  [Knowledge Catalog](https://docs.cloud.google.com/gemini/enterprise/docs/connectors/connect-knowledge-catalog.md.txt)
  is automatically enabled on the **Assistant** tab of your
  Gemini Enterprise app to give the agent tools to search for data
  that the user has access to and look up context.

  > [!CAUTION]
  > **Caution:** **High-accuracy database queries:** Federated query mode provides broad access across all databases and tables accessible by the user, but query accuracy can vary on complex transactional schemas. For workloads requiring high accuracy, deterministic table scoping, and verified queries (golden SQL), create a scoped data agent in [Spanner](https://docs.cloud.google.com/gemini/data-agents/conversational-analytics/spanner/create-data-agents.md.txt#publish-agent-gemini-enterprise) and publish it to Gemini Enterprise.

- **Data ingestion**: Copy data from a specific
  Spanner table to the Gemini Enterprise data store. Data
  must be manually refreshed to reflect changes in the Spanner
  table. This mode incurs egress costs for moving data to a new location, and
  existing IAM permissions aren't replicated into the data
  store.

## Before you begin

To create a Spanner data store in Gemini Enterprise, you
must have the
[Gemini Enterprise Admin](https://docs.cloud.google.com/gemini/enterprise/docs/access-control.md.txt#discoveryengine.agentspaceAdmin)
(`roles/discoveryengine.agentspaceAdmin`) or
[Discovery Engine Admin](https://docs.cloud.google.com/iam/docs/roles-permissions/discoveryengine.md.txt#discoveryengine.admin)
(`roles/discoveryengine.admin`) role. For more information, see
[Grant permissions to admins](https://docs.cloud.google.com/gemini/enterprise/docs/access-control.md.txt#grant-permissions-to-admins).

If your project is protected by a VPC Service Controls perimeter or has organization
policy enforcement enabled, ensure that your organization policy allows the
connector:

- Add `spanner` to the `allowedDataSources` parameter in the `discoveryengine.managed.allowedDataSources` managed constraint (**Restrict
  allowed data sources for data connectors** ). For more information, see [Overview of managed policy constraints](https://docs.cloud.google.com/gemini/enterprise/docs/connectors/managed-policy-constraints-overview.md.txt) and [Configure allowed data sources](https://docs.cloud.google.com/gemini/enterprise/docs/connectors/configure-allowed-data-sources.md.txt).

In addition, configure the required Spanner IAM
permissions for the [connector mode](https://docs.cloud.google.com/gemini/enterprise/docs/connectors/connect-spanner.md.txt#connector-mode) that you plan to use:

### Federated query


> [!WARNING]
>
> **Preview**
>
>
> This product or feature is
>
> subject to the "Pre-GA Offerings Terms" in the General Service Terms section
> of the [Service Specific
> Terms](https://docs.cloud.google.com/terms/service-terms#1).
>
> Pre-GA products and features are available "as is" and might have limited support.
>
> For more information, see the
> [launch stage descriptions](https://cloud.google.com/products/#product-launch-stages).

<br />

To connect to Spanner using
[federated query](https://docs.cloud.google.com/gemini/enterprise/docs/connectors/connect-spanner.md.txt#federated-query) mode, grant the following IAM roles to
users who query or perform actions through the connector in the
Google Cloud project that contains your Spanner database:

- **Database access** :
  - [Cloud Spanner Database Reader (`roles/spanner.databaseReader`)](https://docs.cloud.google.com/spanner/docs/iam.md.txt#roles) for read-only queries and tools.
  - [Cloud Spanner Database User (`roles/spanner.databaseUser`)](https://docs.cloud.google.com/spanner/docs/iam.md.txt#roles) or [Cloud Spanner Database Admin (`roles/spanner.databaseAdmin`)](https://docs.cloud.google.com/spanner/docs/iam.md.txt#roles) if write or DDL [actions](https://docs.cloud.google.com/gemini/enterprise/docs/connectors/connect-spanner.md.txt#actions) are enabled.
- **MCP tool access** :
  - [MCP Tool User (`roles/mcp.toolUser`)](https://docs.cloud.google.com/iam/docs/roles-permissions/mcp.md.txt#mcp.toolUser) in the project where the Spanner database lives to invoke Spanner MCP tools.

### Data ingestion

To [ingest](https://docs.cloud.google.com/gemini/enterprise/docs/connectors/connect-spanner.md.txt#data-ingestion) data from a source Google Cloud project that's
different from the Google Cloud project that contains the Gemini Enterprise data
store that you're creating, grant one of the following IAM roles on the
source Spanner project to the
`service-PROJECT_NUMBER@gcp-sa-discoveryengine.iam.gserviceaccount.com`
service account (where `PROJECT_NUMBER` is the project number of the
Google Cloud project that contains the Gemini Enterprise data store):

- **Without Data Boost** : [Cloud Spanner Database Reader (`roles/spanner.databaseReader`)](https://docs.cloud.google.com/spanner/docs/iam.md.txt#roles)
- **With Data Boost** : [Cloud Spanner Database Admin (`roles/spanner.databaseAdmin`)](https://docs.cloud.google.com/spanner/docs/iam.md.txt#roles), or a custom role with the permissions of **Cloud Spanner Database Reader** and `spanner.databases.useDataBoost`. For more information, see [Data Boost overview](https://docs.cloud.google.com/spanner/docs/databoost/databoost-overview.md.txt).

> [!CAUTION]
> **Caution:** If you choose to [ingest](https://docs.cloud.google.com/gemini/enterprise/docs/connectors/connect-spanner.md.txt#data-ingestion) data from Spanner into a Gemini Enterprise data store, Spanner permissions aren't imported with the data. After import, any user with [sufficient Gemini Enterprise permissions](https://docs.cloud.google.com/gemini/enterprise/docs/access-control.md.txt#roles) can view the data, even if they don't have permission to view the data in Spanner.

## Create a Spanner data store

To create a data store that connects data from Spanner
to Gemini Enterprise, follow these steps:

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

   [Gemini Enterprise](https://console.cloud.google.com/gemini-enterprise/)
2. Go to the **Data stores** page.

3. Click **Create data store**.

4. On the **Source** page, choose a data source for your data
   store. Search for "Spanner" in the **Select a data source**
   search field, or find Spanner in the list of **First-party
   data sources** . Select **Add data source**.

5. On the **Data** page, select the connector mode for how to connect to your data. Select from the following tabs for further instructions based on the mode that you have chosen.

   ### Federated query


   > [!WARNING]
   >
   > **Preview**
   >
   >
   > This product or feature is
   >
   > subject to the "Pre-GA Offerings Terms" in the General Service Terms section
   > of the [Service Specific
   > Terms](https://docs.cloud.google.com/terms/service-terms#1).
   >
   > Pre-GA products and features are available "as is" and might have limited support.
   >
   > For more information, see the
   > [launch stage descriptions](https://cloud.google.com/products/#product-launch-stages).

   <br />

   1. Select **Federated query (recommended)** . Click **Continue**.
   2. On the **Actions** page, select the Spanner actions that you want to enable for your data store. You can edit these settings later. Click **Continue**.

   ### Data ingestion

   1. Select **Data ingestion**.
   2. Specify details about the data that you want to import. Under **Import data from your Spanner table**, specify the following information:

      - **Project ID**: The Google Cloud project that contains the Spanner table. This is a required field.
      - **Instance ID**: The Spanner instance ID that contains the data you want to import. This is a required field.
      - **Database ID**: The Spanner database ID that contains the data you want to import. This is a required field.
      - **Table ID**: The Spanner table ID that contains the data you want to import. This is a required field.

      Optionally, select **Enable Data Boost** to use [Spanner Data Boost](https://docs.cloud.google.com/spanner/docs/databoost/databoost-overview.md.txt) for faster queries. Enabling Data Boost will incur additional cost. See [Spanner Data Boost pricing](https://cloud.google.com/spanner/pricing#spanner-data-boost-pricing).
   3. Click **Continue**.

6. On the **Configuration** page, configure your data store settings.

   - **Location of your data connector** : Choose a region for where to store the metadata of your data store. You cannot change the location after the data store is created. For important information about multi-regions, see [Gemini Enterprise locations](https://docs.cloud.google.com/gemini/enterprise/docs/locations.md.txt).
   - **Your data connector name** : In the **Data connector name** field, enter a name for your data connector. You cannot change the name after the data connector is created. Entering a name generates a unique ID for your data connector. Optionally, in the **Tag (optional)** field, enter a tag for your data connector, which serves as a stable identifier for the connector across all versions.
   - **Sensitive data protection policy** : Select a [sensitive data protection policy](https://docs.cloud.google.com/gemini/enterprise/docs/protect-sensitive-data.md.txt) for your data store. The format should follow: `projects/{project}/locations/{location}/contentPolicies/{policy}`. You can edit this setting later.
7. Click **Create**.

Now you're ready to attach your data store to a Gemini Enterprise app. In federated query mode, queries incur Spanner usage costs when users run queries through the attached app; in data ingestion mode, importing data incurs Spanner and Gemini Enterprise indexing costs even before the data store is attached to an app. To learn more about these charges, see [Gemini Enterprise pricing](https://cloud.google.com/generative-ai-app-builder/pricing).

## Next steps

- To attach your data store to an app, create an app and select your data store
  following the steps on
  [Create a Gemini Enterprise app](https://docs.cloud.google.com/gemini/enterprise/docs/create-app.md.txt).

- Learn how
  [Knowledge Catalog works with Data Cloud connectors](https://docs.cloud.google.com/gemini/enterprise/docs/connectors/connect-knowledge-catalog.md.txt)
  (automatically enabled when you use federated query mode) to help the agent
  search for data that the user has access to and look up organizational
  context.

- To build a high-accuracy, scoped agent with verified queries, see
  [Publish a Spanner data agent](https://docs.cloud.google.com/gemini/data-agents/conversational-analytics/spanner/create-data-agents.md.txt#publish-agent-gemini-enterprise)
  to Gemini Enterprise.