Generate text embeddings by using the ML.GENERATE_EMBEDDING function
This document shows you how to create a BigQuery ML
remote model
that references a Vertex AI embedding
model.
You then use that model with the
ML.GENERATE_EMBEDDING
function
to create text embeddings by using data from a BigQuery
standard table.
Required roles
To create a connection, you need membership in the following Identity and Access Management (IAM) role:
roles/bigquery.connectionAdmin
To grant permissions to the connection's service account, you need the following permission:
resourcemanager.projects.setIamPolicy
To create the model using BigQuery ML, you need the following IAM permissions:
bigquery.jobs.create
bigquery.models.create
bigquery.models.getData
bigquery.models.updateData
bigquery.models.updateMetadata
To run inference, you need the following permissions:
bigquery.tables.getData
on the tablebigquery.models.getData
on the modelbigquery.jobs.create
Before you begin
-
In the Google Cloud console, on the project selector page, select or create a Google Cloud project.
-
Make sure that billing is enabled for your Google Cloud project.
-
Enable the BigQuery, BigQuery Connection, and Vertex AI APIs.
Create a dataset
Create a BigQuery dataset to store your ML model:
In the Google Cloud console, go to the BigQuery page.
In the Explorer pane, click your project name.
Click
View actions > Create dataset.On the Create dataset page, do the following:
For Dataset ID, enter
bqml_tutorial
.For Location type, select Multi-region, and then select US (multiple regions in United States).
The public datasets are stored in the
US
multi-region. For simplicity, store your dataset in the same location.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. Create the connection in the same location as the dataset you created in the previous step.
Select one of the following options:
Console
Go to the BigQuery page.
To create a connection, click
Add, and then click Connections to external data sources.In the Connection type list, select Vertex AI remote models, remote functions and BigLake (Cloud Resource).
In the Connection ID field, enter a name for your connection.
Click Create connection.
Click Go to connection.
In the Connection info pane, copy the service account ID for use in a later step.
bq
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 regionPROJECT_ID
: your Google Cloud project IDCONNECTION_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...
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 {} }
CONNECTION_ID
: an ID for your connectionPROJECT_ID
: your Google Cloud project IDREGION
: your connection region
Give the service account access
Grant the connection's service account the Vertex AI User role.
If you plan to specify the endpoint as a URL when you create the remote model, for example endpoint = 'https://us-central1-aiplatform.googleapis.com/v1/projects/myproject/locations/us-central1/publishers/google/models/text-embedding-004'
, grant this role in the same project you specify in the URL.
If you plan to specify the endpoint by using the model name when you create the remote model, for example endpoint = 'text-embedding-004'
, grant this role in the same project where you plan to create the remote model.
Granting the role in a different project results in the error bqcx-1234567890-xxxx@gcp-sa-bigquery-condel.iam.gserviceaccount.com does not have the permission to access resource
.
To grant the role, follow these steps:
Console
Go to the IAM & Admin page.
Click
Grant access.The Add principals dialog opens.
In the New principals field, enter the service account ID that you copied earlier.
In the Select a role field, select Vertex AI, and then select Vertex AI User.
Click Save.
gcloud
Use the
gcloud projects add-iam-policy-binding
command:
gcloud projects add-iam-policy-binding 'PROJECT_NUMBER' --member='serviceAccount:MEMBER' --role='roles/aiplatform.user' --condition=None
Replace the following:
PROJECT_NUMBER
: your project numberMEMBER
: the service account ID that you copied earlier
Create a model
In the Google Cloud console, go to the BigQuery page.
Using the SQL editor, create a remote model:
CREATE OR REPLACE MODEL `PROJECT_ID.DATASET_ID.MODEL_NAME` REMOTE WITH CONNECTION `CONNECTION_ID` OPTIONS (ENDPOINT = 'ENDPOINT');
Replace the following:
PROJECT_ID
: your project IDDATASET_ID
: the ID of the dataset to contain the modelMODEL_NAME
: the name of the modelCONNECTION_ID
: the ID of your BigQuery connectionWhen 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
: the embedding model to use.
Generate text embeddings by using data from a table
Generate text embeddings with the
ML.GENERATE_EMBEDDING
function
by using text data from a table column.
Typically, you want to use a text-embedding
or
text-multilingual-embedding
model for text-only use cases, and
use a multimodalembedding
model for cross-modal search use cases, where
embeddings for text and visual content are generated in the same semantic space.
text embedding
Generate text embeddings by using a remote model over an embedding model:
SELECT * FROM ML.GENERATE_EMBEDDING( MODEL `PROJECT_ID.DATASET_ID.MODEL_NAME`, TABLE PROJECT_ID.DATASET_ID.TABLE_NAME, STRUCT(FLATTEN_JSON AS flatten_json_output, TASK_TYPE AS task_type, OUTPUT_DIMENSIONALITY AS output_dimensionality) );
Replace the following:
PROJECT_ID
: your project ID.DATASET_ID
: the ID of the dataset that contains the model.MODEL_NAME
: the name of the remote model over an embedding model.TABLE_NAME
: the name of the table that contains the text to embed. This table must have a column that's namedcontent
, or you can use an alias to use a differently named column.FLATTEN_JSON
: aBOOL
value that indicates whether to parse the embedding into a separate column. The default value isTRUE
.TASK_TYPE
: aSTRING
literal that specifies the intended downstream application to help the model produce better quality embeddings.TASK_TYPE
accepts the following values:RETRIEVAL_QUERY
: specifies that the given text is a query in a search or retrieval setting.RETRIEVAL_DOCUMENT
: specifies that the given text is a document in a search or retrieval setting.When using this task type, it is helpful to include the document title in the query statement in order to improve embedding quality. You can use the
title
option to specify the name of the column that contains the document title, otherwise the document title must be in a column either namedtitle
or aliased astitle
, for example:SELECT * FROM ML.GENERATE_EMBEDDING( MODEL
mydataset.embedding_model
, (SELECT abstract as content, header as title, publication_number FROMmydataset.publications
), STRUCT(TRUE AS flatten_json_output, 'RETRIEVAL_DOCUMENT' as task_type) );SEMANTIC_SIMILARITY
: specifies that the given text will be used for Semantic Textual Similarity (STS).CLASSIFICATION
: specifies that the embeddings will be used for classification.CLUSTERING
: specifies that the embeddings will be used for clustering.
OUTPUT_DIMENSIONALITY
: anINT64
value that specifies the number of dimensions to use when generating embeddings. For example, if you specify256 AS output_dimensionality
, then theml_generate_embedding_result
output column contains 256 embeddings for each input value.You can only use this argument if the remote model that you specify in the
model
argument uses one of the following models as an endpoint:text-embedding-004
or latertext-multilingual-embedding-002
or later
multimodal embedding
Generate text embeddings by using a remote model over the
multimodalembedding
model:
SELECT * FROM ML.GENERATE_EMBEDDING( MODEL `PROJECT_ID.DATASET_ID.MODEL_NAME`, TABLE PROJECT_ID.DATASET_ID.TABLE_NAME, STRUCT(FLATTEN_JSON AS flatten_json_output, OUTPUT_DIMENSIONALITY AS output_dimensionality) );
Replace the following:
PROJECT_ID
: your project ID.DATASET_ID
: the ID of the dataset that contains the model.MODEL_NAME
: the name of the remote model over amultimodalembedding@001
model.TABLE_NAME
: the name of the table that contains the text to embed. This table must have a column that's namedcontent
, or you can use an alias to use a differently named column.FLATTEN_JSON
: aBOOL
that indicates whether to parse the embedding into a separate column. The default value isTRUE
.OUTPUT_DIMENSIONALITY
: anINT64
value that specifies the number of dimensions to use when generating embeddings. Valid values are128
,256
,512
, and1408
. The default value is1408
. For example, if you specify256 AS output_dimensionality
, then theml_generate_embedding_result
output column contains 256 embeddings for each input value.
Generate text embeddings by using data from a query
Generate text embeddings with the
ML.GENERATE_EMBEDDING
function
by using text data provided by a query and a remote model over an embedding
model.
Typically, you want to use a text-embedding
or
text-multilingual-embedding
model for text-only use cases, and
use a multimodalembedding
model for cross-modal search use cases, where
embeddings for text and visual content are generated in the same semantic space.
text embedding
Generate text embeddings by using a remote model over the embedding model:
SELECT * FROM ML.GENERATE_EMBEDDING( MODEL `PROJECT_ID.DATASET_ID.MODEL_NAME`, (CONTENT_QUERY), STRUCT(FLATTEN_JSON AS flatten_json_output, TASK_TYPE AS task_type, OUTPUT_DIMENSIONALITY AS output_dimensionality) );
Replace the following:
PROJECT_ID
: your project ID.DATASET_ID
: the ID of the dataset that contains the model.MODEL_NAME
: the name of the remote model over an embedding model.CONTENT_QUERY
: a query whose result contains aSTRING
column calledcontent
.FLATTEN_JSON
: aBOOL
value that indicates whether to parse the embedding into a separate column. The default value isTRUE
.TASK_TYPE
: aSTRING
literal that specifies the intended downstream application to help the model produce better quality embeddings.TASK_TYPE
accepts the following values:RETRIEVAL_QUERY
: specifies that the given text is a query in a search or retrieval setting.RETRIEVAL_DOCUMENT
: specifies that the given text is a document in a search or retrieval setting.When using this task type, it is helpful to include the document title in the query statement in order to improve embedding quality. You can use the
title
option to specify the name of the column that contains the document title, otherwise the document title must be in a column either namedtitle
or aliased astitle
, for example:SELECT * FROM ML.GENERATE_EMBEDDING( MODEL
mydataset.embedding_model
, (SELECT abstract as content, header as title, publication_number FROMmydataset.publications
), STRUCT(TRUE AS flatten_json_output, 'RETRIEVAL_DOCUMENT' as task_type) );SEMANTIC_SIMILARITY
: specifies that the given text will be used for Semantic Textual Similarity (STS).CLASSIFICATION
: specifies that the embeddings will be used for classification.CLUSTERING
: specifies that the embeddings will be used for clustering.
OUTPUT_DIMENSIONALITY
: anINT64
value that specifies the number of dimensions to use when generating embeddings. For example, if you specify256 AS output_dimensionality
, then theml_generate_embedding_result
output column contains 256 embeddings for each input value.You can only use this argument if the remote model that you specify in the
model
argument uses one of the following models as an endpoint:text-embedding-004
or latertext-multilingual-embedding-002
or later
multimodal embedding
Generate text embeddings by using a remote model over the
multimodalembedding
model:
SELECT * FROM ML.GENERATE_EMBEDDING( MODEL `PROJECT_ID.DATASET_ID.MODEL_NAME`, (CONTENT_QUERY), STRUCT(FLATTEN_JSON AS flatten_json_output, OUTPUT_DIMENSIONALITY AS output_dimensionality) );
Replace the following:
PROJECT_ID
: your project ID.DATASET_ID
: the ID of the dataset that contains the model.MODEL_NAME
: the name of the remote model over amultimodalembedding@001
model.CONTENT_QUERY
: a query whose result contains aSTRING
column calledcontent
.FLATTEN_JSON
: aBOOL
that indicates whether to parse the embedding into a separate column. The default value isTRUE
.OUTPUT_DIMENSIONALITY
: anINT64
value that specifies the number of dimensions to use when generating embeddings. Valid values are128
,256
,512
, and1408
. The default value is1408
. For example, if you specify256 AS output_dimensionality
, then theml_generate_embedding_result
output column contains 256 embeddings for each input value.
Examples
The following examples show how to call the ML.GENERATE_EMBEDDING
function on a table and a query.
Embed text in a table
The following example shows a request to embed the content
column
of the text_data
table:
SELECT * FROM ML.GENERATE_EMBEDDING( MODEL `mydataset.embedding_model`, TABLE mydataset.text_data, STRUCT(TRUE AS flatten_json_output, 'CLASSIFICATION' AS task_type) );
Use embeddings to rank semantic similarity
The following example embeds a collection of movie reviews and orders them by
cosine distance to the review "This movie was average" using the
ML.DISTANCE
function.
A smaller distance indicates more semantic similarity.
WITH movie_review_embeddings AS ( SELECT * FROM ML.GENERATE_EMBEDDING( MODEL `bqml_tutorial.embedding_model`, ( SELECT "Movie 1" AS title, "This movie was fantastic" AS content UNION ALL SELECT "Movie 2" AS title, "This was the best movie I've ever seen!!" AS content UNION ALL SELECT "Movie 3" AS title, "This movie was just okay..." AS content UNION ALL SELECT "Movie 4" AS title, "This movie was terrible." AS content ), STRUCT(TRUE AS flatten_json_output) ) ), average_review_embedding AS ( SELECT ml_generate_embedding_result FROM ML.GENERATE_EMBEDDING( MODEL `bqml_tutorial.embedding_model`, (SELECT "This movie was average" AS content), STRUCT(TRUE AS flatten_json_output) ) ) SELECT content, ML.DISTANCE( (SELECT ml_generate_embedding_result FROM average_review_embedding), ml_generate_embedding_result, 'COSINE' ) AS distance_to_average_review FROM movie_review_embeddings ORDER BY distance_to_average_review;
The result is the following:
+------------------------------------------+----------------------------+ | content | distance_to_average_review | +------------------------------------------+----------------------------+ | This movie was just okay... | 0.062789813467745592 | | This movie was fantastic | 0.18579561313064263 | | This movie was terrible. | 0.35707466240930985 | | This was the best movie I've ever seen!! | 0.41844932504542975 | +------------------------------------------+----------------------------+