tessl/pypi-google-cloud-aiplatform
Comprehensive Python client library for Google Cloud Vertex AI, offering machine learning tools, generative AI models, and MLOps capabilities
—
Pending
batch.mddocs/
Batch Processing
Large-scale batch inference and data processing with distributed computing integration and resource optimization.
Capabilities
Batch Prediction Jobs
Execute large-scale batch inference with automatic scaling and comprehensive monitoring.
class BatchPredictionJob:
@classmethod
def create(
cls,
job_display_name: str,
model_name: str,
instances_format: str,
gcs_source_uris: Optional[List[str]] = None,
bigquery_source_uri: Optional[str] = None,
gcs_destination_output_uri_prefix: Optional[str] = None,
bigquery_destination_output_uri: Optional[str] = None,
predictions_format: str = 'jsonl',
model_parameters: Optional[Dict] = None,
machine_type: Optional[str] = None,
accelerator_type: Optional[str] = None,
accelerator_count: Optional[int] = None,
starting_replica_count: Optional[int] = None,
max_replica_count: Optional[int] = None,
batch_size: Optional[int] = None,
instances_format: str = 'jsonl',
predictions_format: str = 'jsonl',
generate_explanation: bool = False,
explanation_metadata: Optional[explain.ExplanationMetadata] = None,
explanation_parameters: Optional[explain.ExplanationParameters] = None,
labels: Optional[Dict[str, str]] = None,
credentials: Optional[auth_credentials.Credentials] = None,
encryption_spec_key_name: Optional[str] = None,
sync: bool = True,
create_request_timeout: Optional[float] = None,
**kwargs
) -> 'BatchPredictionJob': ...
@classmethod
def create_from_job_spec(
cls,
job_spec: Dict,
**kwargs
) -> 'BatchPredictionJob': ...
@property
def state(self) -> JobState: ...
@property
def output_info(self) -> Optional[Dict]: ...
@property
def partial_failures(self) -> Optional[List[Dict]]: ...Usage Examples
Basic batch prediction:
import google.cloud.aiplatform as aiplatform
aiplatform.init(project='my-project', location='us-central1')
job = aiplatform.BatchPredictionJob.create(
job_display_name='batch-prediction-job',
model_name='projects/my-project/locations/us-central1/models/123456',
instances_format='jsonl',
gcs_source_uris=['gs://my-bucket/input.jsonl'],
gcs_destination_output_uri_prefix='gs://my-bucket/output/',
machine_type='n1-standard-4',
starting_replica_count=1,
max_replica_count=5
)
print(f'Job created: {job.resource_name}')
print(f'Job state: {job.state}')Install with Tessl CLI
npx tessl i tessl/pypi-google-cloud-aiplatform