This page describes the basic start-up tasks that you must complete before using Vertex AI Search.
For information about setting up Vertex AI Agents, see Create and use a data store agent.
Create a project
To create a Google Cloud project for your Vertex AI Search apps and data stores, follow these steps:
In the Google Cloud console, on the project selector page, select or create a Google Cloud project.
Make sure that billing is enabled for your Google Cloud project. Learn how to check if billing is enabled on a project.
If you plan to use the API, install the Google Cloud CLI.
To initialize the Google Cloud CLI, run the following command:
gcloud init
Turn on Vertex AI Agent Builder
To use Vertex AI Agent Builder, you must activate the Vertex AI Agent Builder service and accept the Discovery Solutions data use terms.
To turn on Vertex AI Agent Builder, follow these steps:
In the Google Cloud console, go to the Agent Builder page.
Read and agree to the Terms of Service, then click Continue and activate the API.
Access control in Vertex AI Agent Builder
You can configure access control for Vertex AI Agent Builder at the project level. To grant access to Vertex AI Agent Builder using the console, grant the Discovery Engine Admin role to a principal for the project that contains the Vertex AI Agent Builder engine.
To grant access to Vertex AI Agent Builder, follow the instructions at Grant a single role in the IAM documentation using the following guidance:
- In step 2, select a project.
- In step 4, when selecting a role, enter Discovery Engine in the filter and then click Discovery Engine Admin.
If you are an owner of the project, you automatically have the Discovery Engine Admin role for that project.
To grant access to Vertex AI Agent Builder for other users, groups, and service accounts, see Access control with IAM.
If you are using the API, see Set up authentication on Google Cloud for authentication and access control.