Embed text with pretrained TensorFlow models

SQL

Use the CREATE SCHEMA statement:

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

   Go to BigQuery

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

   CREATE SCHEMA `PROJECT_ID.tf_models_tutorial`;

   Replace PROJECT_ID with your project ID.

3. Click play_circle Run.

For more information about how to run queries, see Run an interactive query.

bq

1. In the Google Cloud console, activate Cloud Shell.

   Activate Cloud Shell

2. To create the dataset, run the bq mk command:

   bq mk --dataset --location=us PROJECT_ID:tf_models_tutorial

   Replace PROJECT_ID with your project ID.

NNLM

1. Install the bigquery-ml-utils library using pip:

   pip install bigquery-ml-utils
   

2. Generate an NNLM model. The following Python code loads an NNLM model from TensorFlow Hub and prepares it for BigQuery:

   from bigquery_ml_utils import model_generator
   
   # Establish an instance of TextEmbeddingModelGenerator.
   text_embedding_model_generator = model_generator.TextEmbeddingModelGenerator()
   
   # Generate an NNLM model.
   text_embedding_model_generator.generate_text_embedding_model('nnlm', OUTPUT_MODEL_PATH)
   

   Replace OUTPUT_MODEL_PATH with a path to a local folder where you can temporarily store the model.

3. Optional: Print the generated model's signature:

   import tensorflow as tf
   
   reload_embedding_model = tf.saved_model.load(OUTPUT_MODEL_PATH)
   print(reload_embedding_model.signatures["serving_default"])
   

4. To copy the generated model from your local folder to a Cloud Storage bucket, use the Google Cloud CLI:

   gcloud storage cp OUTPUT_MODEL_PATH gs://BUCKET_PATH/nnlm_model --recursive
   

   Replace BUCKET_PATH with the name of the Cloud Storage bucket to which you are copying the model.

SWIVEL

1. Install the bigquery-ml-utils library using pip:

   pip install bigquery-ml-utils
   

2. Generate a SWIVEL model. The following Python code loads a SWIVEL model from TensorFlow Hub and prepares it for BigQuery:

   from bigquery_ml_utils import model_generator
   
   # Establish an instance of TextEmbeddingModelGenerator.
   text_embedding_model_generator = model_generator.TextEmbeddingModelGenerator()
   
   # Generate a SWIVEL model.
   text_embedding_model_generator.generate_text_embedding_model('swivel', OUTPUT_MODEL_PATH)
   

   Replace OUTPUT_MODEL_PATH with a path to a local folder where you can temporarily store the model.

3. Optional: Print the generated model's signature:

   import tensorflow as tf
   
   reload_embedding_model = tf.saved_model.load(OUTPUT_MODEL_PATH)
   print(reload_embedding_model.signatures["serving_default"])
   

4. To copy the generated model from your local folder to a Cloud Storage bucket, use the Google Cloud CLI:

   gcloud storage cp OUTPUT_MODEL_PATH gs://BUCKET_PATH/swivel_model --recursive
   

   Replace BUCKET_PATH with the name of the Cloud Storage bucket to which you are copying the model.

BERT

1. Install the bigquery-ml-utils library using pip:

   pip install bigquery-ml-utils
   

2. Generate a BERT model. The following Python code loads a BERT model from TensorFlow Hub and prepares it for BigQuery:

   from bigquery_ml_utils import model_generator
   
   # Establish an instance of TextEmbeddingModelGenerator.
   text_embedding_model_generator = model_generator.TextEmbeddingModelGenerator()
   
   # Generate a BERT model.
   text_embedding_model_generator.generate_text_embedding_model('bert', OUTPUT_MODEL_PATH)
   

   Replace OUTPUT_MODEL_PATH with a path to a local folder where you can temporarily store the model.

3. Optional: Print the generated model's signature:

   import tensorflow as tf
   
   reload_embedding_model = tf.saved_model.load(OUTPUT_MODEL_PATH)
   print(reload_embedding_model.signatures["serving_default"])
   

4. To copy the generated model from your local folder to a Cloud Storage bucket, use the Google Cloud CLI:

   gcloud storage cp OUTPUT_MODEL_PATH gs://BUCKET_PATH/bert_model --recursive
   

   Replace BUCKET_PATH with the name of the Cloud Storage bucket to which you are copying the model.

NNLM

Use the CREATE MODEL statement:

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

   Go to BigQuery

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

   CREATE OR REPLACE MODEL tf_models_tutorial.nnlm_model
   OPTIONS (
     model_type = 'TENSORFLOW',
     model_path = 'gs://BUCKET_NAME/nnlm_model/*');

   Replace BUCKET_NAME with the name of the bucket that you previously created.

3. Click play_circle Run.

For more information about how to run queries, see Run an interactive query.

SWIVEL

Use the CREATE MODEL statement:

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

   Go to BigQuery

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

   CREATE OR REPLACE MODEL tf_models_tutorial.swivel_model
   OPTIONS (
     model_type = 'TENSORFLOW',
     model_path = 'gs://BUCKET_NAME/swivel_model/*');

   Replace BUCKET_NAME with the name of the bucket that you previously created.

3. Click play_circle Run.

For more information about how to run queries, see Run an interactive query.

BERT

To load the BERT model into BigQuery, import the BERT model to Vertex AI, deploy the model to a Vertex AI endpoint, create a connection, and then create a remote model in BigQuery.

To import the BERT model to Vertex AI, follow these steps:

1. In the Google Cloud console, go to the Vertex AI Model registry page.

   Go to Model registry

2. Click Import, and then do the following:

   • For Name, enter BERT.
   • For Region, select a region that matches your Cloud Storage bucket's region.

3. Click Continue, and then do the following:

   • For Model framework version, select 2.8.
   • For Model artifact location, enter the path to the Cloud Storage bucket where you stored the model file. For example, gs://BUCKET_PATH/bert_model.

4. Click Import. After the import is complete, your model appears on the Model registry page.

To deploy the BERT model to a Vertex AI endpoint and connect it to BigQuery, follow these steps:

1. In the Google Cloud console, go to the Vertex AI Model registry page.

   Go to Model registry

2. Click on the name of your model.

3. Click Deploy & test.

4. Click Deploy to endpoint.

5. For Endpoint name, enter bert_model_endpoint.

6. Click Continue.

7. Select your compute resources.

8. Click Deploy.

9. Create a BigQuery Cloud resource connection and grant access to the connection's service account.

To create a remote model based on the Vertex AI endpoint, use the CREATE MODEL statement:

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

   Go to BigQuery

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

   CREATE OR REPLACE MODEL tf_models_tutorial.bert_model
   INPUT(content STRING)
   OUTPUT(embedding ARRAY<FLOAT64>)
   REMOTE WITH CONNECTION `PROJECT_ID.CONNECTION_LOCATION.CONNECTION_ID`
   OPTIONS (
     ENDPOINT = "https://ENDPOINT_LOCATION-aiplatform.googleapis.com/v1/projects/PROJECT_ID/locations/ENDPOINT_LOCATION/endpoints/ENDPOINT_ID");

   Replace the following:

   • PROJECT_ID: the project ID
   • CONNECTION_LOCATION: the location of your BigQuery connection
   • 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

   • ENDPOINT_LOCATION: the location of your Vertex AI endpoint. For example: "us-central1".
   • ENDPOINT_ID: the ID of your model endpoint

3. Click play_circle Run.

For more information about how to run queries, see Run an interactive query.

NNLM

SELECT
  *
FROM
  ML.PREDICT(
    MODEL `tf_models_tutorial.nnlm_model`,
    (
    SELECT
      review AS content
    FROM
      `bigquery-public-data.imdb.reviews`
    LIMIT
      500)
  );

The result is similar to the following:

+-----------------------+----------------------------------------+
| embedding             | content                                |
+-----------------------+----------------------------------------+
|  0.08599445223808289  | Isabelle Huppert must be one of the... |
| -0.04862852394580841  |                                        |
| -0.017750458791851997 |                                        |
|  0.8658871650695801   |                                        |
| ...                   |                                        |
+-----------------------+----------------------------------------+

SWIVEL

SELECT
  *
FROM
  ML.PREDICT(
    MODEL `tf_models_tutorial.swivel_model`,
    (
    SELECT
      review AS content
    FROM
      `bigquery-public-data.imdb.reviews`
    LIMIT
      500)
  );

The result is similar to the following:

+----------------------+----------------------------------------+
| embedding            | content                                |
+----------------------+----------------------------------------+
|  2.5952553749084473  | Isabelle Huppert must be one of the... |
| -4.015787601470947   |                                        |
|  3.6275434494018555  |                                        |
| -6.045154333114624   |                                        |
| ...                  |                                        |
+----------------------+----------------------------------------+

BERT

SELECT
  *
FROM
  ML.PREDICT(
    MODEL `tf_models_tutorial.bert_model`,
    (
    SELECT
      review AS content
    FROM
      `bigquery-public-data.imdb.reviews`
    LIMIT
      500)
  );

The result is similar to the following:

+--------------+---------------------+----------------------------------------+
| embedding    | remote_model_status | content                                |
+--------------+---------------------+----------------------------------------+
| -0.694072425 | null                | Isabelle Huppert must be one of the... |
|  0.439208865 |                     |                                        |
|  0.99988997  |                     |                                        |
| -0.993487895 |                     |                                        |
| ...          |                     |                                        |
+--------------+---------------------+----------------------------------------+