Generate multimodal embeddings

This page describes how to generate multimodal embeddings using the supported Vertex AI multimodal model, multimodalembedding@001.

You can use the Vertex AI multimodal embedding models referred to in Supported models.

This page assumes that you're familiar with AlloyDB for PostgreSQL and generative AI concepts. For more information about embeddings, see What are embeddings.

Before you begin

Before you use multimodal embeddings, do the following:

Integrate with Vertex AI and install the extension

  1. Integrate with Vertex AI.
  2. Ensure that the latest version of google_ml_integration is installed.

    1. To check the installed version, run the following command:

              SELECT extversion FROM pg_extension WHERE extname = 'google_ml_integration';
        extversion
        ------------
        1.4.3
        (1 row)

    2. If the extension isn't installed or if the installed version is earlier than 1.4.3, update the extension by running the following commands:

              CREATE EXTENSION IF NOT EXISTS google_ml_integration;
        ALTER EXTENSION google_ml_integration UPDATE;

      If you experience issues when you run the preceding commands, or if the extension isn't updated to version 1.4.3 after you run the preceding commands, contact AlloyDB support.

    3. After you ensure that the version is current, install the preview functionality by running the upgrade_to_preview_version procedure:

              CALL google_ml.upgrade_to_preview_version();
        SELECT extversion FROM pg_extension WHERE extname = 'google_ml_integration';
        extversion
        ------------
        1.4.4
        (1 row)

Access data in Cloud Storage to generate multimodal embeddings

  • To generate multimodal embeddings, refer to content in Cloud Storage using a gs:// URI.
  • Access Cloud Storage content through your current project's Vertex AI service agent. By default, the Vertex AI service agent already has permission to access the bucket in the same project. For more information, see IAM roles and permissions index.

  • To access data in a Cloud Storage bucket in another Google Cloud project, run the following gcloud CLI command to grant the Storage Object Viewer role (roles/storage.objectViewer) to the Vertex AI service agent of your AlloyDB project.

    gcloud projects add-iam-policy-binding <ANOTHER_PROJECT_ID> \
--member="serviceAccount:service-<PROJECT_ID>@gcp-sa-aiplatform.iam.gserviceaccount.com" \
--role="roles/storage.objectViewer"

    For more information, see Set and manage IAM policies on buckets.

To generate multimodal embeddings, select one of the following schemas.

Generate multimodal embeddings

To generate text embeddings for a multimodalembedding@001 model endpoint, run the following statement:

SELECT
  ai.text_embedding(
    model_id => 'multimodalembedding@001',
    content => 'TEXT');

Replace TEXT with the text to generate the embedding for.

To generate image embeddings for a registered multimodalembedding@001 model endpoint where the image mimetype is default image/jpeg, run the following statement:

SELECT
  ai.image_embedding(
    model_id => 'multimodalembedding@001',
    image => 'IMAGE_PATH_OR_TEXT',
    mimetype => MIMETYPE');

Replace the following:

  • IMAGE_PATH_OR_TEXT with the Cloud Storage URI of the image, for example, gs://my-bucket/embeddings/flowers.jpeg, or the base64 string of the image.
  • MIMETYPE with the mimetype of the image, for example, image/jpeg. For the full list of supported mimetypes, see the Multimodal embeddings API.

To generate video embeddings for a registered multimodalembedding@001 model endpoint, run the following statement:

SELECT
  ai.video_embedding(
    model_id => 'multimodalembedding@001',
    video => 'VIDEO_URI');

Replace VIDEO_URI with the Cloud Storage URI of the target video, for example, gs://my-bucket/embeddings/supermarket-video.mp4, or the base64 string of the video.

What's next