Manage context sets in Cloud SQL for PostgreSQL Studio
MySQL | PostgreSQL | SQL Server
This document describes how to create context sets in Cloud SQL for PostgreSQL Studio using a context set file. Context set names must be unique within a database.
To learn about context sets, see Context sets overview.
Before you begin
Complete the following prerequisites before creating an agent.
Enable required services
Enable the following services for your project:
Prepare a Cloud SQL instance
Make sure that you have access to an existing Cloud SQL instance or create a new one. For more information, see Create instances for Cloud SQL.
This tutorial requires you to have a database in your Cloud SQL instance. For more information, see Create a database on the Cloud SQL instance
Required roles and permissions
- Add an IAM user or service account to the instance. For more information, see Manage users with IAM database authentication for Cloud SQL.
- Grant the
cloudsql.studioUser,cloudsql.instanceUser, andgeminidataanalytics.queryDataUserroles to the IAM user at the project level. For more information, see Add IAM policy binding for a project. - You must also grant read-only database privileges to an IAM user or
service account by logging in as a user with superuser privileges, such as the
postgresuser.GRANT SELECT ON ALL TABLES IN SCHEMA public TO USER_NAME;Replace USER_NAME with the email address for the user. You must use quotes around the email because it contains special characters (@ and .).
For more information, see Grant database privileges to an individual IAM user or service account.
Grant executesql permission to Cloud SQL instance
To grant the executesql permission to Cloud SQL instance and enable the Cloud SQL
Data API, run the following command:
gcloud config set project PROJECT_ID gcloud components update gcloud beta sql instances patch INSTANCE_ID --data-api-access=ALLOW_DATA_API
Replace the following:
PROJECT_ID: The ID of your Google Cloud project.INSTANCE_ID: The ID of your Cloud SQL instance.
To perform steps in this tutorial, sign in to Google Cloud, and then authenticate to the database using IAM authentication.
Create a context set
To create a context set, perform the following steps:
In the Google Cloud console, go to the Cloud SQL page.
Select an instance from the list.
In the navigation menu, click Cloud SQL Studio.
Sign in to Studio using IAM authentication.
In the Explorer pane, next to Context sets, click View actions.
Click Create context set.
In Context set name, provide a unique context set name. The context set name is case-sensitive and can contain letters, numbers, hyphens, and underscores.
Optional. In Context set description, add a description for your context set.
Click Create.
Build context sets
After creating a context set, follow the steps in Build contexts using Gemini CLI to create a context set file. You can then edit your context set to upload the context set file.
Edit a context set
To edit a context set, perform the following steps:
In the Google Cloud console, go to the Cloud SQL page.
Select an instance from the list.
In the navigation menu, click Cloud SQL Studio.
Sign in to Studio using Identity and Access Management authentication.
In the Explorer pane, next to Context sets, click View actions.
Click Edit context set.
Optional: Edit Context set description.
Click Browse in the Upload context set file section, and select the context set file.
Click Save.
Delete a context set
To delete a context set, perform the following steps:
In the Google Cloud console, go to the Cloud SQL page.
Select an instance from the list.
In the navigation menu, click Cloud SQL Studio.
Sign in to Studio using Identity and Access Management authentication.
In the Explorer pane, next to Context sets, click View actions.
Click Delete context set.
In the Delete context set confirmation dialog, enter the name of the context set.
Click Confirm to delete the context set.
What's next
- Learn more about context sets.
- Learn how to test a context set.
- Learn how to build contexts using Gemini CLI.