Batch Prediction¶
Serve batch predictions from your models using Vertex AI Batch Predictions.
Components:
|
Creates a Google Cloud Vertex BatchPredictionJob and waits for it to complete. |
-
v1.batch_predict_job.ModelBatchPredictOp(job_display_name: str, gcp_resources: dsl.OutputPath(str), batchpredictionjob: dsl.Output[google.VertexBatchPredictionJob], bigquery_output_table: dsl.Output[google.BQTable], gcs_output_directory: dsl.Output[system.Artifact], model: dsl.Input[google.VertexModel] =
None
, unmanaged_container_model: dsl.Input[google.UnmanagedContainerModel] =None
, location: str ='us-central1'
, instances_format: str ='jsonl'
, predictions_format: str ='jsonl'
, gcs_source_uris: list[str] =[]
, bigquery_source_input_uri: str =''
, instance_type: str =''
, key_field: str =''
, included_fields: list[str] =[]
, excluded_fields: list[str] =[]
, model_parameters: dict[str, str] ={}
, gcs_destination_output_uri_prefix: str =''
, bigquery_destination_output_uri: str =''
, machine_type: str =''
, accelerator_type: str =''
, accelerator_count: int =0
, starting_replica_count: int =0
, max_replica_count: int =0
, service_account: str =''
, manual_batch_tuning_parameters_batch_size: int =0
, generate_explanation: bool =False
, explanation_metadata: dict[str, str] ={}
, explanation_parameters: dict[str, str] ={}
, labels: dict[str, str] ={}
, encryption_spec_key_name: str =''
, project: str ='{{$.pipeline_google_cloud_project_id}}'
)¶ Creates a Google Cloud Vertex BatchPredictionJob and waits for it to complete. For more details, see BatchPredictionJob.Create.
- Parameters¶:
- job_display_name: str¶
The user-defined name of this BatchPredictionJob.
- location: str =
'us-central1'
¶ Location for creating the BatchPredictionJob.
- instances_format: str =
'jsonl'
¶ The format in which instances are given, must be one of the Model’s supportedInputStorageFormats. For more details about this input config, see InputConfig
- predictions_format: str =
'jsonl'
¶ The format in which Vertex AI gives the predictions. Must be one of the Model’s supportedOutputStorageFormats. For more details about this output config, see OutputConfig.
- model: dsl.Input[google.VertexModel] =
None
¶ The Model used to get predictions via this job. Must share the same ancestor Location. Starting this job has no impact on any existing deployments of the Model and their resources. Either this or
unmanaged_container_model
must be specified.- unmanaged_container_model: dsl.Input[google.UnmanagedContainerModel] =
None
¶ The unmanaged container model used to get predictions via this job. This should be used for models that are not uploaded to Vertex. Either this or model must be specified.
- gcs_source_uris: list[str] =
[]
¶ Google Cloud Storage URI(-s) to your instances to run batch prediction on. They must match
instances_format
. May contain wildcards. For more information on wildcards, see WildcardNames. For more details about this input config, see InputConfig.- bigquery_source_input_uri: str =
''
¶ BigQuery URI to a table, up to 2000 characters long. For example:
projectId.bqDatasetId.bqTableId
For more details about this input config, see https://cloud.google.com/vertex-ai/docs/reference/rest/v1/projects.locations.batchPredictionJobs#InputConfig.- model_parameters: dict[str, str] =
{}
¶ The parameters that govern the predictions. The schema of the parameters
- instance_type: str =
''
¶ The format of the instance that the Model accepts. Vertex AI will convert compatible InstancesFormat to the specified format. Supported values are:
object
: Each input is converted to JSON object format. * Forbigquery
, each row is converted to an object. * Forjsonl
, each line of the JSONL input must be an object. * Does not apply tocsv
,file-list
,tf-record
, ortf-record-gzip
.array
: Each input is converted to JSON array format. * Forbigquery
, each row is converted to an array. The order of columns is determined by the BigQuery column order, unless included_fields is populated.included_fields
must be populated for specifying field orders. * Forjsonl
, if each line of the JSONL input is an object,included_fields
must be populated for specifying field orders. * Does not apply tocsv
,file-list
,tf-record
, ortf-record-gzip
. If not specified, Vertex AI converts the batch prediction input as follows: * Forbigquery
andcsv
, the behavior is the same asarray
. The order of columns is the same as defined in the file or table, unless included_fields is populated. * Forjsonl
, the prediction instance format is determined by each line of the input. * Fortf-record
/tf-record-gzip
, each record will be converted to an object in the format of{"b64": <value>}
, where<value>
is the Base64-encoded string of the content of the record. * Forfile-list
, each file in the list will be converted to an object in the format of{"b64": <value>}
, where<value>
is the Base64-encoded string of the content of the file.- key_field: str =
''
¶ The name of the field that is considered as a key. The values identified by the key field is not included in the transformed instances that is sent to the Model. This is similar to specifying this name of the field in excluded_fields. In addition, the batch prediction output will not include the instances. Instead the output will only include the value of the key field, in a field named
key
in the output: * Forjsonl
output format, the output will have akey
field instead of theinstance
field. * Forcsv
/bigquery
output format, the output will have have akey
column instead of the instance feature columns. The input must be JSONL with objects at each line, CSV, BigQuery or TfRecord.- included_fields: list[str] =
[]
¶ Fields that will be included in the prediction instance that is sent to the Model. If
instance_type
isarray
, the order of field names inincluded_fields
also determines the order of the values in the array. Whenincluded_fields
is populated,excluded_fields
must be empty. The input must be JSONL with objects at each line, CSV, BigQuery or TfRecord.- excluded_fields: list[str] =
[]
¶ Fields that will be excluded in the prediction instance that is sent to the Model. Excluded will be attached to the batch prediction output if key_field is not specified. When
excluded_fields
is populated,included_fields
must be empty. The input must be JSONL with objects at each line, CSV, BigQuery or TfRecord. may be specified via the Model’sparameters_schema_uri
.- gcs_destination_output_uri_prefix: str =
''
¶ The Google Cloud Storage location of the directory where the output is to be written to. In the given directory a new directory is created. Its name is
prediction-<model-display-name>-<job-create-time>
, where timestamp is in YYYY-MM-DDThh:mm:ss.sssZ ISO-8601 format. Inside of it filespredictions_0001.<extension>
,predictions_0002.<extension>
, …,predictions_N.<extension>
are created where<extension>
depends on chosenpredictions_format
, and N may equal 0001 and depends on the total number of successfully predicted instances. If the Model has bothinstance
andprediction
schemata defined then each such file contains predictions as per thepredictions_format
. If prediction for any instance failed (partially or completely), then an additionalerrors_0001.<extension>
,errors_0002.<extension>
,…,errors_N.<extension>
files are created (N depends on total number of failed predictions). These files contain the failed instances, as per their schema, followed by an additionalerror
field which as value hasgoogle.rpc.Status
containing onlycode
andmessage
fields. For more details about this output config, see https://cloud.google.com/vertex-ai/docs/reference/rest/v1/projects.locations.batchPredictionJobs#OutputConfig.- bigquery_destination_output_uri: str =
''
¶ The BigQuery project location where the output is to be written to. In the given project a new dataset is created with name
prediction_<model-display-name>_<job-create-time>
where is made BigQuery-dataset-name compatible (for example, most special characters become underscores), and timestamp is in YYYY_MM_DDThh_mm_ss_sssZ “based on ISO-8601” format. In the dataset two tables will be created,predictions
, anderrors
. If the Model has bothinstance
andprediction
schemata defined then the tables have columns as follows: Thepredictions
table contains instances for which the prediction succeeded, it has columns as per a concatenation of the Model’s instance and prediction schemata. Theerrors
table contains rows for which the prediction has failed, it has instance columns, as per the instance schema, followed by a single “errors” column, which as values has google.rpc.Status represented as a STRUCT, and containing onlycode
andmessage
. For more details about this output config, see https://cloud.google.com/vertex-ai/docs/reference/rest/v1/projects.locations.batchPredictionJobs#OutputConfig.- machine_type: str =
''
¶ The type of machine for running batch prediction on dedicated resources. If the Model supports DEDICATED_RESOURCES this config may be provided (and the job will use these resources). If the Model doesn’t support AUTOMATIC_RESOURCES, this config must be provided. For more details about the BatchDedicatedResources, see https://cloud.google.com/vertex-ai/docs/reference/rest/v1/projects.locations.batchPredictionJobs#BatchDedicatedResources. For more details about the machine spec, see https://cloud.google.com/vertex-ai/docs/reference/rest/v1/MachineSpec
- accelerator_type: str =
''
¶ The type of accelerator(s) that may be attached to the machine as per
accelerator_count
. Only used ifmachine_type
is set. For more details about the machine spec, see https://cloud.google.com/vertex-ai/docs/reference/rest/v1/MachineSpec- accelerator_count: int =
0
¶ The number of accelerators to attach to the
machine_type
. Only used ifmachine_type
is set. For more details about the machine spec, see https://cloud.google.com/vertex-ai/docs/reference/rest/v1/MachineSpec- starting_replica_count: int =
0
¶ The number of machine replicas used at the start of the batch operation. If not set, Vertex AI decides starting number, not greater than
max_replica_count
. Only used ifmachine_type
is set.- max_replica_count: int =
0
¶ The maximum number of machine replicas the batch operation may be scaled to. Only used if
machine_type
is set.- service_account: str =
''
¶ The service account that the DeployedModel’s container runs as. If not specified, a system generated one will be used, which has minimal permissions and the custom container, if used, may not have enough permission to access other Google Cloud resources. Users deploying the Model must have the iam.serviceAccounts.actAs permission on this service account.
- manual_batch_tuning_parameters_batch_size: int =
0
¶ The number of the records (e.g. instances) of the operation given in each batch to a machine replica. Machine type, and size of a single record should be considered when setting this parameter, higher value speeds up the batch operation’s execution, but too high value will result in a whole batch not fitting in a machine’s memory, and the whole operation will fail.
- generate_explanation: bool =
False
¶ Generate explanation along with the batch prediction results. This will cause the batch prediction output to include explanations based on the
prediction_format
: -bigquery
: output includes a column namedexplanation
. The value is a struct that conforms to the [aiplatform.gapic.Explanation] object. -jsonl
: The JSON objects on each line include an additional entry keyedexplanation
. The value of the entry is a JSON object that conforms to the [aiplatform.gapic.Explanation] object. -csv
: Generating explanations for CSV format is not supported. If this field is set to true, either the Model.explanation_spec or explanation_metadata and explanation_parameters must be populated.- explanation_metadata: dict[str, str] =
{}
¶ Explanation metadata configuration for this BatchPredictionJob. Can be specified only if
generate_explanation
is set toTrue
. This value overrides the value ofModel.explanation_metadata
. All fields ofexplanation_metadata
are optional in the request. If a field of theexplanation_metadata
object is not populated, the corresponding field of theModel.explanation_metadata
object is inherited. For more details, see https://cloud.google.com/vertex-ai/docs/reference/rest/v1/ExplanationSpec#explanationmetadata.- explanation_parameters: dict[str, str] =
{}
¶ Parameters to configure explaining for Model’s predictions. Can be specified only if
generate_explanation
is set toTrue
. This value overrides the value ofModel.explanation_parameters
. All fields ofexplanation_parameters
are optional in the request. If a field of theexplanation_parameters
object is not populated, the corresponding field of theModel.explanation_parameters
object is inherited. For more details, see https://cloud.google.com/vertex-ai/docs/reference/rest/v1/ExplanationSpec#ExplanationParameters.- labels: dict[str, str] =
{}
¶ The labels with user-defined metadata to organize your BatchPredictionJobs. Label keys and values can be no longer than 64 characters (Unicode codepoints), can only contain lowercase letters, numeric characters, underscores and dashes. International characters are allowed. See https://goo.gl/xmQnxf for more information and examples of labels.
- encryption_spec_key_name: str =
''
¶ Customer-managed encryption key options for a BatchPredictionJob. If this is set, then all resources created by the BatchPredictionJob will be encrypted with the provided encryption key. Has the form:
projects/my-project/locations/my-location/keyRings/my-kr/cryptoKeys/my-key
. The key needs to be in the same region as where the compute resource is created.- project: str =
'{{$.pipeline_google_cloud_project_id}}'
¶ Project to create the BatchPredictionJob. Defaults to the project in which the PipelineJob is run.
- Returns¶:
batchpredictionjob: dsl.Output[google.VertexBatchPredictionJob]
[Deprecated. Use gcs_output_directory and bigquery_output_table instead.] Artifact representation of the created batch prediction job.
gcs_output_directory: dsl.Output[system.Artifact]
Artifact tracking the batch prediction job output. This is only available if gcs_destination_output_uri_prefix is specified.
bigquery_output_table: dsl.Output[google.BQTable]
Artifact tracking the batch prediction job output. This is only available if bigquery_output_table is specified.
gcp_resources: dsl.OutputPath(str)
Serialized gcp_resources proto tracking the batch prediction job. For more details, see https://github.com/kubeflow/pipelines/blob/master/components/google-cloud/google_cloud_pipeline_components/proto/README.md.