Generate text embeddings by using an open model and the ML.GENERATE_EMBEDDING function

This tutorial shows you how to create a remote model that's based on the open-source text embedding model Qwen3-Embedding-0.6B, and then how to use that model with the ML.GENERATE_EMBEDDING function to embed movie reviews from the bigquery-public-data.imdb.reviews public table.

Required permissions

To run this tutorial, you need the following Identity and Access Management (IAM) roles:

• Create and use BigQuery datasets, connections, and models: BigQuery Admin (roles/bigquery.admin).
• Grant permissions to the connection's service account: Project IAM Admin (roles/resourcemanager.projectIamAdmin).
• Deploy and undeploy models in Vertex AI: Vertex AI Administrator (roles/aiplatform.admin).

These predefined roles contain the permissions required to perform the tasks in this document. To see the exact permissions that are required, expand the Required permissions section:

You might also be able to get these permissions with custom roles or other predefined roles.

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 that's represented by the remote model.

To generate a cost estimate based on your projected usage, use the pricing calculator.

For more information about BigQuery pricing, see BigQuery pricing in the BigQuery documentation.

Open models that you deploy to Vertex AI are charged per machine-hour. This means billing starts as soon as the endpoint is fully set up, and continues until you un-deploy it. For more information about Vertex AI pricing, see the Vertex AI pricing page.

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. Verify that billing is enabled for your Google Cloud project.

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

   Enable the APIs

Deploy a Qwen3-Embedding-0.6B model on Vertex AI

Deploy the Qwen/Qwen3-Embedding-0.6B model from Hugging Face to Vertex AI, following the instructions in Deploy Hugging Face models. During deployment, you must select Public (shared endpoint) as the value for the Endpoint access field in the deployment workflow.

Create a dataset

Create a BigQuery dataset to store your ML model.

{
  "datasetReference": {
     "datasetId": "bqml_tutorial"
  }
}

import google.cloud.bigquery

bqclient = google.cloud.bigquery.Client()
bqclient.create_dataset("bqml_tutorial", exists_ok=True)

Create the remote model

Create a remote model that represents a hosted Vertex AI 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 `bqml_tutorial.qwen3_embedding_model`
REMOTE WITH CONNECTION DEFAULT
OPTIONS (ENDPOINT = 'https://ENDPOINT_REGION-aiplatform.googleapis.com/v1/projects/ENDPOINT_PROJECT_ID/locations/ENDPOINT_REGION/endpoints/ENDPOINT_ID');

Replace the following:

• ENDPOINT_REGION: the region in which the open model is deployed.
• ENDPOINT_PROJECT_ID: the project in which the open model is deployed.
• ENDPOINT_ID: the ID of the HTTPS endpoint used by the open model. You can get the endpoint ID by locating the open model on the Online prediction page and copying the value in the ID field.

The following example shows the format of a valid HTTP endpoint:

https://us-central1-aiplatform.googleapis.com/v1/projects/myproject/locations/us-central1/endpoints/1234.

The query takes several seconds to complete, after which the qwen3_embedding_model model appears in the bqml_tutorial dataset in the Explorer pane. Because the query uses a CREATE MODEL statement to create a model, there are no query results.

Perform text embedding

Perform text embedding on IMDB movie reviews by using the remote model and the ML.GENERATE_EMBEDDING function:

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

   Go to BigQuery

2. In the query editor, enter the following statement to perform text embedding on five movie reviews:

   SELECT
     *
   FROM
     ML.GENERATE_EMBEDDING(
       MODEL `bqml_tutorial.qwen3_embedding_model`,
       (
         SELECT
           review AS content,
           *
         FROM
           `bigquery-public-data.imdb.reviews`
         LIMIT 5
       )
     );

   The results include the following columns:

   • ml_generate_embedding_result: an array of double to represent the generated embeddings.
   • ml_generate_embedding_status: the API response status for the corresponding row. If the operation was successful, this value is empty.
   • content: the input text from which to extract embeddings.
   • All of the columns from the bigquery-public-data.imdb.reviews table.

Undeploy model

If you choose not to delete your project as recommended, make sure to undeploy the Qwen3 embedding model in Vertex AI to avoid continued billing for it.

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.

What's next

• Learn how to use text embeddings for semantic search and retrieval-augmented generation (RAG).