Install AlloyDB Omni with AlloyDB AI

This page shows you how to install AlloyDB Omni and integrate AlloyDB AI in it.

AlloyDB AI is a suite of features included with AlloyDB Omni that let you build enterprise generative AI applications. For more information about the ML functionality of AlloyDB, see Build generative AI applications.

Single-server

Configure your AlloyDB Omni instance to query remote models

AlloyDB Omni with AlloyDB AI lets you query remote ML models to work with online predictions and text embeddings generated from ML models. AlloyDB Omni with AlloyDB AI can also process vector embeddings from other content such as an image, for example, if you use the google_ml.predict_row interface and do the translation yourself in the query.

If your machine is air-gapped for security reasons, AlloyDB Omni can also query a model that is hosted on the same or any other machine also accessible from the machine where AlloyDB Omni runs.

To configure AlloyDB Omni to query remote models, follow these steps:

  1. Create a service account with Google Cloud.

  2. Create a service account key, in JSON format, and download it.

  3. Store the key in a permanent location on your file system. It resides at this location for the lifetime of your AlloyDB Omni server.

Note its location on your file system; you need it for the next step.

  1. Add Vertex AI Identity and Access Management (IAM) permissions to the appropriate project and service account.

    gcloud projects add-iam-policy-binding PROJECT_ID \
    --member="serviceAccount:SERVICE_ACCOUNT_ID" \
    --role="roles/aiplatform.user"

    Replace the following:

    • PROJECT_ID: the ID of your Google Cloud project.

    • SERVICE_ACCOUNT_ID: the ID of the service account that you created in the previous step. This includes the full @PROJECT_ID.iam.gserviceaccount.com suffix—for example, my-service@my-project.iam-gserviceaccount.com.

Install AlloyDB Omni with AlloyDB AI

To install AlloyDB Omni and integrate AlloyDB AI, follow these steps:

  1. Ensure you completed all of the steps listed in Configure your AlloyDB Omni to query cloud-based models.

  2. Make a local copy of the default AlloyDB Omni configuration file:

    docker run -i --rm google/alloydbomni cat /usr/share/postgresql/postgresql.conf.sample > my-postgres.conf

  3. Edit the configuration file copy to add directives for AlloyDB AI integration:

    echo "omni_enable_ml_agent_process = 'on'" >> my-postgres.conf
echo "omni_google_cloud_private_key_file_path = '/etc/postgresql/private-key.json'" >> my-postgres.conf

  4. Adjust the file system permissions of the key and configuration files:

    sudo chmod +r my-postgres.conf
sudo chmod +r KEY_PATH

    Replace KEY_PATH with the path to the service account private key file on your host file system. This is the key that you created and downloaded earlier in this procedure.

  5. Install the key and configuration files mounted onto the container:

    docker run --name CONTAINER_NAME -e POSTGRES_PASSWORD=NEW_PASSWORD -p HOST_PORT:5432 -v "$PWD/my-postgres.conf":/etc/postgresql/postgresql.conf -v "FULL_KEY_PATH":/etc/postgresql/private-key.json -d google/alloydbomni -c 'config_file=/etc/postgresql/postgresql.conf'

    Replace the following:

    • CONTAINER_NAME: the name to assign this new simplified AlloyDB Omni installation method container in your host machine's container registry—for example, my-omni-1.

    • NEW_PASSWORD: the password assigned to new container's postgres user after its creation.

    • HOST_PORT: the TCP port on the host machine that the container should publish its own port 5432 to. To use the PostgreSQL default port on the host machine as well, specify 5432.

    • FULL_KEY_PATH: the full file system path to the service account private key file on your host system.

Verify AlloyDB Omni with AlloyDB AI installation

To verify your installation is successful and uses model prediction, enter the following:

CREATE EXTENSION google_ml_integration VERSION '1.3';

SELECT array_dims(google_ml.embedding('textembedding-gecko', 'AlloyDB AI'));
array_dims

The output looks similar to the following:

[1:768]

In the previous query, the google_ml.embedding() call generates embeddings for the input text AlloyDB AI. array_dims returns the dimensions of the array returned by google_ml.embedding(). Since the pre-registered textembedding-gecko model returns an output with 768 dimensions, the output is [1:768].

What's next