Connect a third-party data source

This page describes how to connect third-party data sources to Vertex AI Search. Third-party data source support is in preview with allowlist. If you want to use these connectors, contact your Google account team and ask to be added to the allowlist.

To connect a third-party data source, go to the section for the source you plan to use:

Third-party connectors are not CMEK-compliant.

To import data from a Google data source instead, see Create a search data store.

Connect Confluence

Use the following procedure to sync data from Confluence to Vertex AI Search.

After you set up your data source and import data the first time, the data store syncs data from that source at a frequency that you select during setup.

Before setting up your connection:

  • Set up access control for your data source. For information about setting up access control, see Use data source access control.

  • Have the following authentication information ready:

    • Instance URL. In the form https://EXAMPLE.atlassian.net—for example, https://google.atlassian.net.

    • Instance ID. This is the cloudid and can be found by going to https://EXAMPLE.atlassian.net/_edge/tenant_info and copying the value of cloudId.

  • Enable OAuth 2.0 and get the client ID and client secret.

    Use https://vertexaisearch.cloud.google.com/console/oauth/confluence_oauth.html as the callback URL. For information about enabling OAuth 2.0 for Confluence and getting the client ID and client secret, see OAuth 2.0 (3LO) apps in the Atlassian Developer documentation.

  • When setting OAuth 2.0 permission scopes, configure the following scopes:

  • For user permissions to apply correctly, each Confluence user must make their email visible to all users. To do so, change the email visibility settings in Confluence and set the visibility to Anyone. For more information, see Set your email visibility in the Atlassian documentation.

Console

To use the Google Cloud console to sync data from Confluence to Vertex AI Search, follow these steps:

  1. In the Google Cloud console, go to the Agent Builder page.

    Agent Builder

  2. In the navigation menu, click Data Stores.

  3. Click New data store.

  4. On the Select a data source page, go to the Third-party sources section and select Confluence.

  5. Enter your authentication information and click Authenticate.

  6. A new window appears. Enter the instance username and password. Check that the authentication succeeded before returning to the Specify the Confluence source for your data store page.

  7. Select which entities to sync, then click Continue.

  8. Select a region for your data connector.

  9. Enter a name for your data connector.

  10. Select a synchronization frequency.

  11. Click Create. Vertex AI Search creates your data store and displays your data stores on the Data Stores page.

  12. To check the status of your ingestion, go to the Data Stores page and click your data store name to see details about it on its Data page. The Connector state changes from Creating to Running when it starts synchronizing data. When ingestion is complete, the state changes to Active to indicate that the connection to your data source is set up and awaiting the next scheduled synchronization.

    Depending on the size of your data, ingestion can take several minutes or several hours.

Next steps

Connect Jira

Use the following procedure to sync data from Jira Cloud to Vertex AI Search.

After you set up your data source and import data the first time, the data store syncs data from that source at a frequency that you select during setup.

Before setting up your connection:

  • Set up access control for your data source. For information about setting up access control, see Use data source access control.

  • Prepare the following authentication information:

    • Instance URL. In the form https://EXAMPLE.atlassian.net—for example, https://google.atlassian.net.

    • Instance ID. This is the cloudid and can be found by going to https://EXAMPLE.atlassian.net/_edge/tenant_info and copying the value of cloudId.

    • Enable OAuth 2.0 to get the client ID and client secret.

      Use https://vertexaisearch.cloud.google.com/console/oauth/jira_oauth.html as the callback URL. For information about enabling OAuth 2.0 and getting the client ID and client secret, see OAuth 2.0 (3LO) apps in the Atlassian Developer documentation.

  • When setting OAuth 2.0 permission scopes, configure the following scopes:

  • The minimum required user role is Org Admin.

The following limitation applies:

  • For user permissions to apply correctly, Jira users must provide sharing consent.

Console

To use the Google Cloud console to sync data from Jira to Vertex AI Search, follow these steps:

  1. In the Google Cloud console, go to the Agent Builder page.

    Agent Builder

  2. In the navigation menu, click Data Stores.

  3. Click Create data store.

  4. On the Select a data source page, go to the Third-party sources section and select Confluence.

  5. Enter your authentication information and click Authenticate.

  6. A new window appears. Enter the instance username and password. Check that the authentication succeeded before returning to the Specify the Jira source for your data store page.

  7. Select which entities to sync, then click Continue.

  8. Select a region for your data store.

  9. Enter a name for your data store.

  10. Select a synchronization frequency.

  11. Click Create. Vertex AI Search creates your data store and displays your data stores on the Data Stores page.

  12. To check the status of your ingestion, go to the Data Stores page and click your data store name to see details about it on its Data page. The Connector state changes from Creating to Running when it starts synchronizing data. When ingestion is complete, the state changes to Active to indicate that the connection to your data source is set up and awaiting the next scheduled synchronization.

    Depending on the size of your data, ingestion can take several minutes or several hours.

Next steps

Connect Salesforce

Use the following procedure to sync data from Salesforce to Vertex AI Search.

After you set up your data source and import data the first time, the data store syncs data from that source at a frequency that you select during setup.

Before setting up your connection:

  • Set up access control for your data source. For information about setting up access control, see Use data source access control.

  • Have the following authentication information ready:

    • Instance URL
    • Consumer ID
    • Consumer Secret

The following limitation applies:

  • To sync a user as an entity, the user must provide sharing consent.

Console

To use the Google Cloud console to sync data from Salesforce to Vertex AI Search, follow these steps:

  1. Add Google Cloud to your Salesforce CORS allowlist. If you have already done this, skip to the next step.

    1. Follow the instructions in the Salesforce documentation to configure the CORS allowlist.

    2. Enter https://console.cloud.google.com/ as an origin URL and save your configuration.

  2. In the Google Cloud console, go to the Agent Builder page.

    Agent Builder

  3. In the navigation menu, click Data Stores.

  4. Click Create data store.

  5. On the Select a data source page, go to the Third-party sources section and select Salesforce.

  6. Enter your Salesforce authentication information.

  7. Select which entities to sync and click Continue.

  8. Select a region for your data store.

  9. Enter a name for your data store.

  10. Select a synchronization frequency.

  11. Click Create. Vertex AI Search creates your data store and displays your data stores on the Data Stores page.

  12. To check the status of your ingestion, go to the Data Stores page and click your data store name to see details about it on its Data page. The Connector state changes from Creating to Running when it starts synchronizing data. When ingestion is complete, the state changes to Active to indicate that the connection to your data source is set up and awaiting the next scheduled synchronization.

    Depending on the size of your data, ingestion can take several minutes or several hours.

Next steps

Connect ServiceNow

Use the following procedure to sync data from ServiceNow to Vertex AI Search.

After you set up your data source and import data the first time, the data store syncs data from that source at a frequency that you select during setup.

Before setting up your connection:

  • Set up access control for your data source. For information about setting up access control, see Use data source access control.

  • Have the following authentication information ready:

    • Instance URL in the form of https://<domain-name>.service-now.com/.
    • Client ID and client secret. For information about endpoint setup and getting the client ID and client secret, see Create an endpoint for clients to access the instance in the ServiceNow documentation.
    • Username and password for the ServiceNow administrator role. See Base system roles in the ServiceNow documentation.

Console

To use the Google Cloud console to sync data from ServiceNow to Vertex AI Search, follow these steps:

  1. In the Google Cloud console, go to the Agent Builder page.

    Agent Builder

  2. In the navigation menu, click Data Stores.

  3. Click Create data store.

  4. On the Select a data source page, go to the Third-party sources section and select ServiceNow.

  5. Enter your ServiceNow authentication information.

  6. Select which entities to sync and click Continue.

  7. Select a region for your data connector.

  8. Enter a name for your data connector.

  9. Select a synchronization frequency.

  10. Click Create. Vertex AI Search creates your data store and displays your data stores on the Data Stores page.

  11. To check the status of your ingestion, go to the Data Stores page and click your data connector name to see details about it on its Data page. The Connector state changes from Creating to Running when it starts synchronizing data. When ingestion is complete, the state changes to Active to indicate that the connection to your data source is set up and awaiting the next scheduled synchronization.

    Depending on the size of your data, ingestion can take several minutes or several hours.

Next steps

Connect Sharepoint Online

Use the following procedure to sync data from Sharepoint Online to Vertex AI Search.

After you set up your data source and import data the first time, the data store syncs data from that source at a frequency that you select during setup.

Before setting up your connection:

  • Set up access control for your data source. For information about setting up access control, see Use data source access control.

  • Two-factor authentication (2FA) must be turned off for the Sharepoint account. Only basic Oauth2 password authentication is supported.

  • Grant administrator consent. For information about how to grant consent, see Grant tenant-wide admin consent to an application in the Microsoft documentation.

  • Prepare the following Sharepoint Online authentication information to use during setup:

    • Instance URL. In the form http://DOMAIN_OR_SERVER/[sites/]WEBSITE. For more information about URLs, see URLs and tokens in SharePoint in the Sharepoint documentation.
    • Tenant ID, client ID, and client secret. To register the application, select Accounts in this organizational directory only for the sign-in audience, and then locate this authentication information. For more information, see Quickstart: Register an application with the Microsoft identity platform in the Microsoft documentation.
    • Username and password. These must correspond to either a Sharepoint Site Admin or a Sharepoint Site Collection Admin with 2FA disabled.

  • The following table describes the roles that are recommended for configuration and their limitations.

Console

To use the Google Cloud console to sync data from Sharepoint Online to Vertex AI Search, follow these steps:

  1. In the Google Cloud console, go to the Agent Builder page.

    Agent Builder

  2. In the navigation menu, click Data Stores.

  3. Click Create data store.

  4. On the Select a data source page, go to the Third-party sources section and select Sharepoint Online.

  5. Enter your Sharepoint Online authentication information.

  6. Select the entities to sync and click Continue.

  7. Select a region for your data store.

  8. Enter a name for your data store.

  9. Select a synchronization frequency for your data store.

  10. Click Create. Vertex AI Search creates your data store and displays your data stores on the Data Stores page.

  11. To check the status of your ingestion, go to the Data Stores page and click your data store name to see details about it on its Data page. The Connector state changes from Creating to Running when it starts synchronizing data. When ingestion is complete, the state changes to Active to indicate that the connection to your data source is set up and awaiting the next scheduled synchronization.

    Depending on the size of your data, ingestion can take several minutes or several hours.

Next steps

Connect Slack

Use the following procedure to sync data from Slack to Vertex AI Search.

After you set up your data source and import data the first time, the data store syncs data from that source at a frequency that you select during setup.

Before setting up your connection:

  • Set up access control for your data source. For information about setting up access control, see Use data source access control.

  • Have the following Slack authentication information ready:

    • Workspace ID. For information about getting workspace IDs, see Specify the Slack source for your data store in the Slack documentation.
    • Access token. For information about creating a client app and defining scopes, see Quickstart and How to quickly get and use a Slack API token in the Slack documentation.
    • When setting OAuth 2.0 permission scopes, configure the following scopes:

The following limitation applies:

  • Slack's default behavior restricts the crawling and syncing of content from private channels, multi-party instant messages, and 1:1 instant messages.

Console

To use the Google Cloud console to sync data from Slack to Vertex AI Search, follow these steps:

  1. In the Google Cloud console, go to the Agent Builder page.

    Agent Builder

  2. In the navigation menu, click Data Stores.

  3. Click Create data store.

  4. On the Select a data source page, go to the Third-party sources section and select Slack.

  5. Enter your Slack authentication information.

  6. Select which entities to sync and click Continue.

  7. Select a region for your data store.

  8. Enter a name for your data store.

  9. Select a synchronization frequency for your data store.

  10. Click Create. Vertex AI Search creates your data store and displays your data stores on the Data Stores page.

  11. To check the status of your ingestion, go to the Data Stores page and click your data store name to see details about it on its Data page. The Connector state changes from Creating to Running when it starts synchronizing data. When ingestion is complete, the state changes to Active to indicate that the connection to your data source is set up and awaiting the next scheduled synchronization.

    Depending on the size of your data, ingestion can take several minutes or several hours.

Next steps

Connect Dropbox

Use the following procedure to sync data from Dropbox to Vertex AI Search.

After you set up your data source and import data the first time, the data store syncs data from that source at a frequency that you select during setup.

Before you begin

Before setting up your connection:

  • Set up access control for your data source. For more information, see Use data source access control.

  • Have the following Dropbox authentication information ready. For information about setting up these parameters, see the OAuth Guide in the Dropbox documentation.

    • Client ID
    • Client secret
    • Refresh token

Console

To use the Google Cloud console to sync data from Dropbox to Vertex AI Search, follow these steps:

  1. In the Google Cloud console, go to the Agent Builder page.

    Agent Builder

  2. In the navigation menu, click Data Stores.

  3. Click Create data store.

  4. On the Select a data source page, go to the Third-party sources section and select Dropbox.

  5. Enter your Dropbox authentication information and click Authenticate. A new window appears.

  6. Authenticate your account and confirm that it succeeded before returning to the Specify the Dropbox source for your data store page.

  7. Select which entities to sync and click Continue.

  8. Select a location for your data store.

  9. Enter a name for your data store.

  10. Select a synchronization frequency for your data store.

  11. Click Create. Vertex AI Search creates your data store and displays your data stores on the Data stores page.

  12. To check the status of your ingestion, go to the Data stores page and click your data store name to see details about it on its Data page. The Connector state changes from Creating to Running when it starts synchronizing data. When ingestion is complete, the state changes to Active to indicate that the connection to your data source is set up and awaiting the next scheduled synchronization. Check the Documents tab to make sure your entities have been ingested correctly.

    Depending on the size of your data, ingestion can take several minutes or several hours.

Next steps

Connect Box

Use the following procedure to sync data from Box to Vertex AI Search.

After you set up your data source and import data the first time, the data store syncs data from that source at a frequency that you select during setup.

Before you begin

Before setting up your connection:

  • Set up access control for your data source. For information about setting up access control, see Use data source access control.

  • Have the following Box authentication information ready. For information about setting up these parameters, see JWT Auth in the Box developer documentation.

    • Enterprise ID
    • Client ID
    • Client secret
    • Public key ID
    • Private key
    • Passphrase

  • When creating the JWT endpoint, configure the following scopes:

The following limitations apply:

  • Incremental changes for comments might take longer to sync than the configured frequency interval.
  • If a folder containing an entity is copied or moved, then incremental changes might take longer to sync than the configured frequency interval.

Console

To use the Google Cloud console to sync data from Box to Vertex AI Search, follow these steps:

  1. In the Google Cloud console, go to the Agent Builder page.

    Agent Builder

  2. In the navigation menu, click Data stores.

  3. Click Create data store.

  4. On the Select a data source page, go to the Third-party sources section and select Box.

  5. Enter your authentication information.

  6. Select which entities to sync and click Continue.

  7. Select a region for your data store.

  8. Enter a name for your data store.

  9. Select a synchronization frequency for your data store.

  10. Click Create. Vertex AI Search creates your data store and displays your data stores on the Data stores page.

  11. To check the status of your ingestion, go to the Data stores page and click your data store name to see details about it on its Data page. The Connector state changes from Creating to Running when it starts synchronizing data. When ingestion is complete, the state changes to Active to indicate that the connection to your data source is set up and awaiting the next scheduled synchronization.

    Depending on the size of your data, ingestion can take several minutes or several hours.

Next steps

Connect OneDrive

Use the following procedure to sync data from OneDrive to Vertex AI Search.

After you set up your data source and import data the first time, the data store syncs data from that source at a frequency that you select during setup.

Before you begin

Before setting up your connection:

Console

To use the Google Cloud console to sync data from OneDrive to Vertex AI Search, follow these steps:

  1. In the Google Cloud console, go to the Agent Builder page.

    Agent Builder

  2. In the navigation menu, click Data stores.

  3. Click Create data store.

  4. On the Select a data source page, go to the Third-party sources section and select OneDrive.

  5. Enter your OneDrive authentication information.

  6. Select which entities to sync and cick Continue.

  7. Select a region for your data store.

  8. Enter a name for your data store.

  9. Select a synchronization frequency for your data store.

  10. Click Create. Vertex AI Search creates your data store and displays your data stores on the Data stores page.

  11. To check the status of your ingestion, go to the Data stores page and click your data store name to see details about it on its Data page. The Connector state changes from Creating to Running when it starts synchronizing data. When ingestion is complete, the state changes to Active to indicate that the connection to your data source is set up and awaiting the next scheduled synchronization.

    Depending on the size of your data, ingestion can take several minutes or several hours.

Next steps