Create a Vertex Data Store in Agent Builder to store your source documents for RAG (RAG). This is a required prerequisite before creating a Grounded by data store Model connection in AI Agent Studio.

Note: The examples and graphics on this page are for representation purposes only and may not accurately reflect your specific instance. We do not assume responsibility for their maintenance or accuracy. The Google Cloud Storage mark and logo, and the Google Agent Builder mark and logo are trademarks or registered trademarks of Google LLC and are used for identification purposes only.

To use the Google Vertex AI RAG capability in AI Agent Studio, first create a Google Cloud Storage bucket and upload your documents to it, then create a Vertex Data Store in Agent Builder. The data store vectorizes and chunks those documents for use in RAG queries. The Vertex Data Store supports PDF, HTML, TXT, and other document formats.

Create a bucket in Google Cloud

Before creating a Data Store you would create a bucket in Google Cloud and upload your data to it.

Create a bucket in Google Cloud

  1. Log in to your Google Cloud account and navigate to Cloud Storage and click Create Bucket.
  2. Provide a name for your bucket, keep the remaining parameters as per default settings and click Continue.
  3. Next, upload your documents into this new bucket. This could comprise of any document format the Vertex Data Store supports, such as: PDF, HTML, TXT, and others.

Create a Vertex Data Store

Once you have completed creating a bucket, you would navigate to the Agent Builder > Data Stores tab to create a data store.

  1. In the Create Data Store > Select a data source screen, select Cloud Storage.
    Note: You have already created a bucket in Cloud Storage in the earlier steps.

    Create a Data Store in Agent Builder

  2. Select Import data from Cloud Storage > What kind of data are you importing? > Unstructured documents (PDF, HTML, TXT, and more).
  3. Keep all other parameters as per default selection, but specify the folder.
  4. Click Folder and select the bucket you created earlier, and click Continue.

    Configure a Data Store

  5. In the Configure your data store screen, keep the default options for Location of your data store field.
  6. Provide a name for the Your data store name field.
    Note: The data store comprises of vectorized data that is chunked and encoded, and used for RAG solutions. If you want to chunk your content then you would configure it at this point.
  7. Expand the Document Processing Options section.

    Configure document parsing for the Data Store

  8. In the Document parsing section, we recommend selecting Layout Parser as it works well for most document types.
    Note: See Parse and chunk documents.
  9. Selecting the Layout Parser option enables Document chunking.
  10. Next, check the Include ancestor headings in chunks option as this helps return a more comprehensive response picked from multiple chunks with overlapping data. Checking this option is optional, as per your requirement.
  11. Click Create to complete configuring the data store.

Google Data Store summary

In the Agent Builder, navigate to Apps > Data Stores and click the data store you created. You would see a summary screen of your data store with information that you would reference when creating a Grounded by data store Model connection in AI Agent Studio.

Figure 1. Data Store summary in Agent Builder
Data Store summary view
Project ID
This is the ID of the project as it appears in the Google Data Store. You would require this value when creating a Grounded by data store Model connection in AI Agent Studio. You would find this ID when you select your data store.
Figure 2. Project ID location in Agent Builder
Where to locate your Project ID
Data store ID
Use this ID to define the authentication details when creating a Grounded by data store Model connection in AI Agent Studio.
Region
The region where the data store is deployed. Select a region from the drop-down list to authenticate the Model connection. You can also specify a region that you configured when creating a data source in Agent Builder. See Create a data store.
Connected apps
Shows the Apps the data store is connected to.
Note: To test the data source directly in Google Data Store, create an App in Google Data Store and connect it to the data store.
Figure 3. Authentication details for Google Vertex AI Model connection configuration in AI Agent Studio
Authentication details needed for creating Google Vertex AI Model connection in AI Agent Studio

After creating a data store, uploading documents takes time. To check upload status, navigate to Data Store > Activity.