Handle quota errors by calling ML.GENERATE_EMBEDDING iteratively

This tutorial shows you how to use the BigQuery bqutil.procedure.bqml_generate_embeddings public stored procedure to iterate through calls to the ML.GENERATE_EMBEDDING function. Calling the function iteratively lets you address any retryable errors that occur due to exceeding the quotas and limits that apply to the function.

To review the source code for the bqutil.procedure.bqml_generate_embeddings stored procedure in GitHub, see bqml_generate_embeddings.sqlx. For more information about the stored procedure parameters and usage, see the README file.

This tutorial guides you through the following tasks:

  • Creating a remote model over a text-embedding-004 model.
  • Iterating through calls to the ML.GENERATE_EMBEDDING function, using the remote model and the bigquery-public-data.bbc_news.fulltext public data table with the bqutil.procedure.bqml_generate_embeddings stored procedure.

Required permissions

  • To create the dataset, you need the bigquery.datasets.create Identity and Access Management (IAM) permission.
  • To create the connection resource, you need the following IAM permissions:

    • bigquery.connections.create
    • bigquery.connections.get
  • To grant permissions to the connection's service account, you need the following permission:

    • resourcemanager.projects.setIamPolicy
  • To create the model, you need the following permissions:

    • bigquery.jobs.create
    • bigquery.models.create
    • bigquery.models.getData
    • bigquery.models.updateData
    • bigquery.connections.delegate
  • To run inference, you need the following permissions:

    • bigquery.models.getData
    • bigquery.jobs.create

Costs

In this document, you use the following billable components of Google Cloud:

  • BigQuery ML: You incur costs for the data that you process in BigQuery.
  • Vertex AI: You incur costs for calls to the Vertex AI model.

To generate a cost estimate based on your projected usage, use the pricing calculator. New Google Cloud users might be eligible for a free trial.

For more information about BigQuery pricing, see BigQuery pricing.

For more information about Vertex AI pricing, see Vertex AI pricing.

Before you begin

  1. In the Google Cloud console, on the project selector page, select or create a Google Cloud project.

    Go to project selector

  2. Make sure that billing is enabled for your Google Cloud project.

  3. Enable the BigQuery, BigQuery Connection, and Vertex AI APIs.

    Enable the APIs

Create a dataset

Create a BigQuery dataset to store your models and sample data:

  1. In the Google Cloud console, go to the BigQuery page.

    Go to the BigQuery page

  2. In the Explorer pane, click your project name.

  3. Click View actions > Create dataset.

  4. On the Create dataset page, do the following:

    1. For Dataset ID, enter target_dataset.

    2. For Location type, select Multi-region, and then select US (multiple regions in United States).

    3. Leave the remaining default settings as they are, and click Create dataset.

Create a connection

Create a Cloud resource connection and get the connection's service account ID. Create the connection in the same location as the dataset that you created in the previous step.

Select one of the following options:

Console

  1. Go to the BigQuery page.

    Go to BigQuery

  2. To create a connection, click Add, and then click Connections to external data sources.

  3. In the Connection type list, select Vertex AI remote models, remote functions and BigLake (Cloud Resource).

  4. In the Connection ID field, enter a name for your connection.

  5. Click Create connection.

  6. Click Go to connection.

  7. In the Connection info pane, copy the service account ID for use in a later step.

bq

  1. In a command-line environment, create a connection:

    bq mk --connection --location=REGION --project_id=PROJECT_ID \
        --connection_type=CLOUD_RESOURCE CONNECTION_ID

    The --project_id parameter overrides the default project.

    Replace the following:

    • REGION: your connection region
    • PROJECT_ID: your Google Cloud project ID
    • CONNECTION_ID: an ID for your connection

    When you create a connection resource, BigQuery creates a unique system service account and associates it with the connection.

    Troubleshooting: If you get the following connection error, update the Google Cloud SDK:

    Flags parsing error: flag --connection_type=CLOUD_RESOURCE: value should be one of...
    
  2. Retrieve and copy the service account ID for use in a later step:

    bq show --connection PROJECT_ID.REGION.CONNECTION_ID

    The output is similar to the following:

    name                          properties
    1234.REGION.CONNECTION_ID     {"serviceAccountId": "connection-1234-9u56h9@gcp-sa-bigquery-condel.iam.gserviceaccount.com"}
    

Terraform

Append the following section into your main.tf file.

 ## This creates a cloud resource connection.
 ## Note: The cloud resource nested object has only one output only field - serviceAccountId.
 resource "google_bigquery_connection" "connection" {
    connection_id = "CONNECTION_ID"
    project = "PROJECT_ID"
    location = "REGION"
    cloud_resource {}
}        
Replace the following:

  • CONNECTION_ID: an ID for your connection
  • PROJECT_ID: your Google Cloud project ID
  • REGION: your connection region

Grant permissions to the connection's service account

To grant the connection's service account appropriate roles to access the Cloud Storage and Vertex AI services, follow these steps:

  1. Go to the IAM & Admin page.

    Go to IAM & Admin

  2. Click Grant access.

  3. In the New principals field, enter the service account ID that you copied earlier.

  4. In the Select a role menu, choose Vertex AI > Vertex AI User.

  5. Click Save.

Create the text embedding generation model

Create a remote model that represents a hosted Vertex AI text-embedding-004 model:

  1. In the Google Cloud console, go to the BigQuery page.

    Go to BigQuery

  2. In the query editor, run the following statement:

    CREATE OR REPLACE MODEL `target_dataset.embedding_model`
      REMOTE WITH CONNECTION `LOCATION.CONNECTION_ID`
      OPTIONS (ENDPOINT = 'text-embedding-004');

    Replace the following:

    • LOCATION: the connection location.
    • CONNECTION_ID: the ID of your BigQuery connection.

      When you view the connection details in the Google Cloud console, this is the value in the last section of the fully qualified connection ID that is shown in Connection ID, for example projects/myproject/locations/connection_location/connections/myconnection.

    The query takes several seconds to complete, after which the embedding model appears in the sample dataset in the Explorer pane. Because the query uses a CREATE MODEL statement to create a model, there are no query results.

Run the stored procedure

Run the bqutil.procedure.bqml_generate_embeddings stored procedure, which iterates through calls to the ML.GENERATE_EMBEDDING function using the target_dataset.embedding_model model and the bigquery-public-data.bbc_news.fulltext public data table:

  1. In the Google Cloud console, go to the BigQuery page.

    Go to BigQuery

  2. In the query editor, run the following statement:

    CALL `bqutil.procedure.bqml_generate_embeddings`(
        "bigquery-public-data.bbc_news.fulltext",            -- source table
        "PROJECT_ID.target_dataset.news_body_embeddings",  -- destination table
        "PROJECT_ID.target_dataset.embedding_model",       -- model
        "body",                                              -- content column
        ["filename"],                                        -- key columns
        '{}'                                                 -- optional arguments encoded as a JSON string
    );

    Replace PROJECT_ID with the project ID of the project you are using for this tutorial.

    The stored procedure creates a target_dataset.news_body_embeddings table to contain the output of the ML.GENERATE_EMBEDDING function.

  3. When the query is finished running, confirm that there are no rows in the target_dataset.news_body_embeddings table that contain a retryable error. In the query editor, run the following statement:

    SELECT *
    FROM `target_dataset.news_body_embeddings`
    WHERE ml_generate_embedding_status LIKE '%A retryable error occurred%';

    The query returns the message No data to display.

Clean up

  1. In the Google Cloud console, go to the Manage resources page.

    Go to Manage resources

  2. In the project list, select the project that you want to delete, and then click Delete.
  3. In the dialog, type the project ID, and then click Shut down to delete the project.