The ML.ANNOTATE_IMAGE function

This document describes the ML.ANNOTATE_IMAGE function, which lets you annotate images that are stored in BigQuery object tables by using the Cloud Vision API.

Syntax

ML.ANNOTATE_IMAGE(
 MODEL `PROJECT_ID.DATASET.MODEL_NAME`,
 TABLE `PROJECT_ID.DATASET.OBJECT_TABLE`,
 STRUCT( [VISION_FEATURES] AS vision_features )
)

Arguments

ML.ANNOTATE_IMAGE takes the following arguments:

PROJECT_ID: the project that contains the resource.
DATASET: the BigQuery dataset that contains the resource.
MODEL_NAME: the name of a remote model with a REMOTE_SERVICE_TYPE argument of CLOUD_AI_VISION_V1.
OBJECT_TABLE : the name of the object table that contains URIs of the images.
VISION_FEATURES: a ARRAY<STRING> value that specifies one or more feature names of supported Vision API features, in the format ['feature_name_1', 'feature_name_2', ...]. The supported features are as follows:

Output

ML.ANNOTATE_IMAGE returns the input table plus the following columns:

ml_annotate_image_result: a JSON value that contains the image annotation result from the Vision API.
ml_annotate_image_status: a STRING value that contains the API response status for the corresponding row. This value is empty if the operation was successful.

Quotas

See Cloud AI service functions quotas and limits.

Known issues

Sometimes after a query job that uses this function finishes successfully, some returned rows contain the following error message:

Aretryableerroroccurred:RESOURCEEXHAUSTEDerrorfrom<remoteendpoint>

This issue occurs because BigQuery query jobs finish successfully even if the function fails for some of the rows. The function fails when the volume of API calls to the remote endpoint exceeds the quota limits for that service. This issue occurs most often when you are running multiple parallel batch queries. BigQuery retries these calls, but if the retries fail, the resource exhausted error message is returned.

To iterate through inference calls until all rows are successfully processed, you can use the BigQuery remote inference SQL scripts or the BigQuery remote inference pipeline Dataform package.

Locations

ML.ANNOTATE_IMAGE must run in the same region as the remote model that the function references. For more information about supported locations for models based on the Vision API, see Locations for remote models.

Examples

Example 1

The following example performs label detection on the object table mytable in mydataset:

#Createmodel
CREATEORREPLACEMODEL
`myproject.mydataset.myvisionmodel`
REMOTEWITHCONNECTION`myproject.myregion.myconnection`
OPTIONS(remote_service_type='cloud_ai_vision_v1');

#Annotateimage
SELECT*
FROMML.ANNOTATE_IMAGE(
MODEL`mydataset.myvisionmodel`,
TABLE`mydataset.mytable`,
STRUCT(['label_detection']ASvision_features)
);

The result is similar to the following:

ml_annotate_image_result|ml_annotate_image_status|uri|generation|content_type|size|md5_hash|updated|metadata|
-------|--------|--------|--------|--------|--------|--------|--------|--------
{"label_annotations":[{"description":"Food","mid":"/m/02wbm","score":0.97591567,"topicality":0.97591567}]}||gs://my-bucket/images/Cheeseburger.jpg|1661921874516197|image/jpeg|174600|a259a5076c22696848a1bc10b7162cc2|2022-08-3104:57:54|[]

Example 2

The following example annotates images in the object table mytable, selects the rows where the detected label is food and the score is higher than 0.97, and then returns the results in separate columns:

CREATETABLE
`mydataset.label_score`AS(
SELECT
uriAS`Inputimagepath`,
STRING(ml_annotate_image_result.label_annotations[0].description)AS`Detectedlabel`,
FLOAT64(ml_annotate_image_result.label_annotations[0].score)ASScore,
FLOAT64(ml_annotate_image_result.label_annotations[0].topicality)ASTopicality,
ml_annotate_image_statusASStatus
FROM
ML.ANNOTATE_IMAGE(MODEL`mydataset.myvisionmodel`,
TABLE`mydataset.mytable`,
STRUCT(['label_detection']ASvision_features))
);
SELECT
*
FROM
`mydataset.label_score`
WHERE
`Detectedlabel`='Food'
ANDScore>0.97;

The result is similar to the following:

Inputimagepath|Detectedlabel|Score|Topicality|Status|
-------|--------|--------|--------|--------
gs://my-bucket/images/Cheeseburger.jpg|Food|0.97591567|0.97591567||

If you get an error like query limit exceeded, you might have exceeded the quota for this function, which can leave you with unprocessed rows. Use the following query to complete processing the unprocessed rows:

CREATETABLE
`mydataset.label_score_next`AS(
SELECT
uriAS`Inputimagepath`,
STRING(ml_annotate_image_result.label_annotations[0].description)AS`Detectedlabel`,
FLOAT64(ml_annotate_image_result.label_annotations[0].score)ASScore,
FLOAT64(ml_annotate_image_result.label_annotations[0].topicality)ASTopicality,
ml_annotate_image_statusASStatus
FROM
ML.ANNOTATE_IMAGE(MODEL`mydataset.myvisionmodel`,
TABLE`mydataset.mytable`,
STRUCT(['label_detection']ASvision_features))
WHEREuriNOTIN(
SELECT`Inputimagepath`FROM`mydataset.label_score`
WHERESTATUS='')
);
SELECT*FROM`mydataset.label_score_next`;

What's next

Get step-by-step instructions on how to annotate images in an object table using the ML.ANNOTATE_IMAGE function.
Learn more about other functions you can use to analyze BigQuery data.
For information about model inference, see Model inference overview.
For more information about supported SQL statements and functions for generative AI models, see End-to-end user journeys for generative AI models.