PredictionServiceClient(*, credentials: Optional[google.auth.credentials.Credentials] = None, transport: Optional[Union[str, google.cloud.automl_v1beta1.services.prediction_service.transports.base.PredictionServiceTransport]] = None, client_options: Optional[google.api_core.client_options.ClientOptions] = None, client_info: google.api_core.gapic_v1.client_info.ClientInfo = <google.api_core.gapic_v1.client_info.ClientInfo object>)
AutoML Prediction API.
On any input that is documented to expect a string parameter in snake_case or kebab-case, either of those cases is accepted.
Methods
PredictionServiceClient
PredictionServiceClient(*, credentials: Optional[google.auth.credentials.Credentials] = None, transport: Optional[Union[str, google.cloud.automl_v1beta1.services.prediction_service.transports.base.PredictionServiceTransport]] = None, client_options: Optional[google.api_core.client_options.ClientOptions] = None, client_info: google.api_core.gapic_v1.client_info.ClientInfo = <google.api_core.gapic_v1.client_info.ClientInfo object>)
Instantiate the prediction service client.
Name | Description |
credentials |
Optional[google.auth.credentials.Credentials]
The authorization credentials to attach to requests. These credentials identify the application to the service; if none are specified, the client will attempt to ascertain the credentials from the environment. |
transport |
Union[str,
The transport to use. If set to None, a transport is chosen automatically. |
client_options |
client_options_lib.ClientOptions
Custom options for the client. It won't take effect if a |
client_info |
google.api_core.gapic_v1.client_info.ClientInfo
The client info used to send a user-agent string along with API requests. If |
Type | Description |
google.auth.exceptions.MutualTLSChannelError | If mutual TLS transport creation failed for any reason. |
batch_predict
batch_predict(request: Optional[google.cloud.automl_v1beta1.types.prediction_service.BatchPredictRequest] = None, *, name: Optional[str] = None, input_config: Optional[google.cloud.automl_v1beta1.types.io.BatchPredictInputConfig] = None, output_config: Optional[google.cloud.automl_v1beta1.types.io.BatchPredictOutputConfig] = None, params: Optional[Sequence[google.cloud.automl_v1beta1.types.prediction_service.BatchPredictRequest.ParamsEntry]] = None, retry: google.api_core.retry.Retry = <_MethodDefault._DEFAULT_VALUE: <object object>>, timeout: Optional[float] = None, metadata: Sequence[Tuple[str, str]] = ())
Perform a batch prediction. Unlike the online
xref_Predict,
batch prediction result won't be immediately available in the
response. Instead, a long running operation object is returned.
User can poll the operation result via
GetOperation][google.longrunning.Operations.GetOperation]
method. Once the operation is done,
xref_BatchPredictResult
is returned in the
response][google.longrunning.Operation.response]
field.
Available for following ML problems:
- Image Classification
- Image Object Detection
- Video Classification
- Video Object Tracking * Text Extraction
- Tables
Name | Description |
request |
The request object. Request message for PredictionService.BatchPredict. |
name |
Required. Name of the model requested to serve the batch prediction. This corresponds to the |
input_config |
Required. The input configuration for batch prediction. This corresponds to the |
output_config |
Required. The Configuration specifying where output predictions should be written. This corresponds to the |
params |
:class:
Required. Additional domain-specific parameters for the predictions, any string must be up to 25000 characters long. - For Text Classification: |
retry |
google.api_core.retry.Retry
Designation of what errors, if any, should be retried. |
timeout |
float
The timeout for this request. |
metadata |
Sequence[Tuple[str, str]]
Strings which should be sent along with the request as metadata. |
Type | Description |
| An object representing a long-running operation. The result type for the operation will be .prediction_service.BatchPredictResult response][google.longrunning.Operation.response] of the operation returned by the PredictionService.BatchPredict. |
from_service_account_file
from_service_account_file(filename: str, *args, **kwargs)
Creates an instance of this client using the provided credentials file.
Name | Description |
filename |
str
The path to the service account private key json file. |
Type | Description |
{@api.name} | The constructed client. |
from_service_account_json
from_service_account_json(filename: str, *args, **kwargs)
Creates an instance of this client using the provided credentials file.
Name | Description |
filename |
str
The path to the service account private key json file. |
Type | Description |
{@api.name} | The constructed client. |
predict
predict(request: Optional[google.cloud.automl_v1beta1.types.prediction_service.PredictRequest] = None, *, name: Optional[str] = None, payload: Optional[google.cloud.automl_v1beta1.types.data_items.ExamplePayload] = None, params: Optional[Sequence[google.cloud.automl_v1beta1.types.prediction_service.PredictRequest.ParamsEntry]] = None, retry: google.api_core.retry.Retry = <_MethodDefault._DEFAULT_VALUE: <object object>>, timeout: Optional[float] = None, metadata: Sequence[Tuple[str, str]] = ())
Perform an online prediction. The prediction result will be directly returned in the response. Available for following ML problems, and their expected request payloads:
- Image Classification - Image in .JPEG, .GIF or .PNG format, image_bytes up to 30MB.
- Image Object Detection - Image in .JPEG, .GIF or .PNG format, image_bytes up to 30MB.
- Text Classification - TextSnippet, content up to 60,000 characters, UTF-8 encoded.
- Text Extraction - TextSnippet, content up to 30,000 characters, UTF-8 NFC encoded.
- Translation - TextSnippet, content up to 25,000 characters, UTF-8 encoded.
- Tables - Row, with column values matching the columns of the model, up to 5MB. Not available for FORECASTING
xref_prediction_type.
- Text Sentiment - TextSnippet, content up 500 characters, UTF-8 encoded.
Name | Description |
request |
The request object. Request message for PredictionService.Predict. |
name |
Required. Name of the model requested to serve the prediction. This corresponds to the |
payload |
Required. Payload to perform a prediction on. The payload must match the problem type that the model was trained to solve. This corresponds to the |
params |
:class:
Additional domain-specific parameters, any string must be up to 25000 characters long. - For Image Classification: |
retry |
google.api_core.retry.Retry
Designation of what errors, if any, should be retried. |
timeout |
float
The timeout for this request. |
metadata |
Sequence[Tuple[str, str]]
Strings which should be sent along with the request as metadata. |
Type | Description |
| Response message for PredictionService.Predict. |