This page details how to set up the integration between AlloyDB for PostgreSQL and Vertex AI, letting you apply queries to cloud-stored large language models (LLMs) to your data.
These instructions are specific to using AlloyDB, and not AlloyDB Omni. To instead integrate a local installation of AlloyDB Omni using Vertex AI, see Install AlloyDB Omni with AlloyDB AI.
For more information about using ML models with AlloyDB, see Build generative AI applications using AlloyDB AI.
For more information about Vertex AI, see Introduction to Vertex AI.
Before you begin
- 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.
-
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.
-
Enable the Vertex AI API.
- Install the Google Cloud CLI.
-
To initialize the gcloud CLI, run the following command:
gcloud init
-
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.
-
Enable the Vertex AI API.
- Install the Google Cloud CLI.
-
To initialize the gcloud CLI, run the following command:
gcloud init
Grant Vertex AI user permission to AlloyDB service agent
To enable database integration with Vertex AI, follow these steps to grant the AlloyDB service agent Identity and Access Management (IAM) permissions to access Vertex AI:
Add Vertex AI permissions to the AlloyDB service agent for the project where the AlloyDB database's cluster is located:
Console
Go to the Welcome page in the Google Cloud console, and copy the project number of the project that has AlloyDB clusters or instances. You will use this project number in the next steps.
In the Google Cloud console, go to the IAM page.
Select the project that has Vertex AI endpoints.
Enable Include Google-provided role grants.
Click
Grant Access.In the New principals field, enter the following:
service-PROJECT_NUMBER@gcp-sa-alloydb.iam.gserviceaccount.com
Replace PROJECT_NUMBER with the project number.
In the Role field, enter Vertex AI User.
Click Save.
gcloud
-
To use the gcloud CLI, you can install and initialize the Google Cloud CLI, or you can use Cloud Shell.
gcloud projects add-iam-policy-binding PROJECT_ID
Replace the following:
--member="serviceAccount:service-PROJECT_NUMBER@gcp-sa-alloydb.iam.gserviceaccount.com"
--role="roles/aiplatform.user"
- PROJECT_ID: The ID of the project that has the Vertex AI endpoint.
- PROJECT_NUMBER: The project number of the project that has AlloyDB clusters or instances.
Verify installed extension
Verify if the google_ml_integration
is installed in the database
that contains the data that you want to run predictions on:
Connect a
psql
client to the cluster's primary instance, as described in Connect a psql client to an instance.At the
psql
command prompt, connect to the database:\c DB_NAME
Replace
DB_NAME
with the name of the database on which you want to install the extension.Verify the
google_ml_integration
extension version 1.4.2 or later is installed:SELECT extversion FROM pg_extension WHERE extname = 'google_ml_integration';
Optional. Install the latest version of the extension manually:
CREATE EXTENSION google_ml_integration VERSION '1.4.2';
Optional. If you're using an extension older than 1.4.2, then update the extension to the latest version:
ALTER EXTENSION google_ml_integration UPDATE TO '1.4.2'