Get started with Agentspace Enterprise

Get started with Agentspace Enterprise

Google Agentspace Enterprise brings together the power of deep information retrieval, state-of-the-art natural language processing, and the latest in large language processing to understand user intent and return the most relevant results for the user.

Before following this tutorial, make sure you have done the steps in Before you begin.

Before you begin

1. Sign in to your Google Cloud account. If you're new to Google Cloud, create an account to evaluate how our products perform in real-world scenarios. New customers also get $300 in free credits to run, test, and deploy workloads.

2. In the Google Cloud console, on the project selector page, select or create a Google Cloud project.

   Note: If you don't plan to keep the resources that you create in this procedure, create a project instead of selecting an existing project. After you finish these steps, you can delete the project, removing all resources associated with the project.

   Go to project selector

3. Make sure that billing is enabled for your Google Cloud project.

4. Enable the Vertex AI, Agentspace Enterprise (Discovery Engine), BigQuery, Cloud Storage, Identity and Access Management, user-managed notebooks APIs.

   Enable the APIs

5. In the Google Cloud console, on the project selector page, select or create a Google Cloud project.

   Note: If you don't plan to keep the resources that you create in this procedure, create a project instead of selecting an existing project. After you finish these steps, you can delete the project, removing all resources associated with the project.

   Go to project selector

6. Make sure that billing is enabled for your Google Cloud project.

7. Enable the Vertex AI, Agentspace Enterprise (Discovery Engine), BigQuery, Cloud Storage, Identity and Access Management, user-managed notebooks APIs.

   Enable the APIs

Create an Enterprise search and assistant app

1. In the Google Cloud console, go to the Agentspace page.

   Agentspace

2. Under the Agentspace card, select Manage. This opens up Vertex AI Agent Builder in the Google Cloud console.

3. Click Create app.

4. Under Enterprise search and assistant, click Create.

5. Under Your app name, enter a name for your app. Your app ID appears under the app name.

6. Under External name of your company or organization, enter the company or organization name. For this tutorial, you can use Cymbal Bank.

7. Select global (Global) as the location for your app.

8. Select Search + Assistant as the tier.

9. Click Continue.

Create a data store

1. Click Create data store.

2. Under Cloud Storage, click Select.

3. Under What kind of data are you importing?, make sure Unstructured documents (PDF, HTML, TXT and more) is selected.

4. Under Synchronization frequency, make sure One time is selected.

5. Under Select a folder or a file you want to import, make sure Folder is selected.

6. Enter the following value in the gs:// field:

   cloud-samples-data/gen-app-builder/search/cymbal-bank-employee
   

   This Cloud Storage bucket contains PDF files for internal use by a fictional bank, Cymbal Bank.

7. Click Continue.

8. Under Your data store name, enter a name for your data store, and then click Create.

9. Select the data store that you just created, and then click Create at the bottom of the page.

Preview your app

Note: Because it takes a few minutes for the data stores to index and sync with the app, the preview isn't available immediately.

1. In the navigation menu, click Preview to test the search app.

2. Optional: Click the view icons to switch between mobile view and desktop view.

3. In the search bar, ask a question about the data that we imported; for example, ask How do I book business travel?

   If the answer to this question doesn't specifically reference Cymbal Bank, wait a few more minutes and try again.

4. Ask additional questions such as: Who founded Cymbal Bank? or Where are the headquarters of Cymbal Bank?

Configure the search web app

1. In the navigation menu, click Configurations.

2. On the UI tab, configure settings for the search app.

   Different UI configurations are available for different data types. For more information, see Configure results for the UI.

3. If you change configurations on the UI tab, click Save and publish.

4. Go to the Autocomplete tab to configure specific settings for autocomplete.

   Make sure to set Enable autocomplete to Now and expect to wait a day or two before you see autocomplete suggestions.

5. Go to the Control tab to configure serving controls.

6. Go to the Assistant tab to configure settings for the search assistant.

View the search web app

1. In the navigation menu, click Integration.

2. Make sure that Enable the Web App is enabled.

3. Under The link to your web app, click Open to view the search web app in your browser.

Clean up

To avoid incurring charges to your Google Cloud account for the resources used on this page, follow these steps.

1. To avoid unnecessary Google Cloud charges, use the Google Cloud console to delete your project if you don't need it.
2. If you created a new project to learn about Agentspace Enterprise and you no longer need the project, delete the project.
3. If you used an existing Google Cloud project, delete the resources you created to avoid incurring charges to your account. For more information, see Delete an app and delete a data store.
4. Follow the steps in Turn off Agentspace Enterprise.

What's next

• Learn more about Agentspace Enterprise.
• Learn more about apps and data stores.