PredictionServiceClient(
transport=None,
channel=None,
credentials=None,
client_config=None,
client_info=None,
client_options=None,
)
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(
transport=None,
channel=None,
credentials=None,
client_config=None,
client_info=None,
client_options=None,
)
Constructor.
Name | Description |
channel |
grpc.Channel
DEPRECATED. A |
credentials |
google.auth.credentials.Credentials
The authorization credentials to attach to requests. These credentials identify this application to the service. If none are specified, the client will attempt to ascertain the credentials from the environment. This argument is mutually exclusive with providing a transport instance to |
client_config |
dict
DEPRECATED. A dictionary of call options for each method. If not specified, the default configuration is used. |
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 |
client_options |
Union[dict, google.api_core.client_options.ClientOptions]
Client options used to set user options on the client. API Endpoint should be set through client_options. |
batch_predict
batch_predict(name, input_config, output_config, params=None, retry=<_MethodDefault._DEFAULT_VALUE: <object object>>, timeout=<_MethodDefault._DEFAULT_VALUE: <object object>>, metadata=None)
Perform a batch prediction. Unlike the online 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
method. Once the operation is
done, BatchPredictResult
is returned in the response
field.
Available for following ML problems:
- Image Classification
- Image Object Detection
- Video Classification
- Video Object Tracking * Text Extraction
- Tables
.. rubric:: Example
from google.cloud import automl_v1beta1
client = automl_v1beta1.PredictionServiceClient()
name = client.model_path('[PROJECT]', '[LOCATION]', '[MODEL]')
TODO: Initialize
input_config
:input_config = {}
TODO: Initialize
output_config
:output_config = {}
response = client.batch_predict(name, input_config, output_config)
def callback(operation_future): ... # Handle result. ... result = operation_future.result()
response.add_done_callback(callback)
Handle metadata.
metadata = response.metadata()
Name | Description |
name |
str
Name of the model requested to serve the batch prediction. |
input_config |
Union[dict, BatchPredictInputConfig]
Required. The input configuration for batch prediction. If a dict is provided, it must be of the same form as the protobuf message BatchPredictInputConfig |
output_config |
Union[dict, BatchPredictOutputConfig]
Required. The Configuration specifying where output predictions should be written. If a dict is provided, it must be of the same form as the protobuf message BatchPredictOutputConfig |
params |
dict[str -> str]
Additional domain-specific parameters for the predictions, any string must be up to 25000 characters long. - For Text Classification: |
retry |
Optional[google.api_core.retry.Retry]
A retry object used to retry requests. If |
timeout |
Optional[float]
The amount of time, in seconds, to wait for the request to complete. Note that if |
metadata |
Optional[Sequence[Tuple[str, str]]]
Additional metadata that is provided to the method. |
Type | Description |
google.api_core.exceptions.GoogleAPICallError | If the request failed for any reason. |
google.api_core.exceptions.RetryError | If the request failed due to a retryable error and retry attempts failed. |
ValueError | If the parameters are invalid. |
from_service_account_file
from_service_account_file(filename, *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 |
PredictionServiceClient | The constructed client. |
from_service_account_json
from_service_account_json(filename, *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 |
PredictionServiceClient | The constructed client. |
model_path
model_path(project, location, model)
Return a fully-qualified model string.
predict
predict(name, payload, params=None, retry=<_MethodDefault._DEFAULT_VALUE: <object object>>, timeout=<_MethodDefault._DEFAULT_VALUE: <object object>>, metadata=None)
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
prediction_type
.
- Text Sentiment - TextSnippet, content up 500 characters, UTF-8 encoded.
.. rubric:: Example
from google.cloud import automl_v1beta1
client = automl_v1beta1.PredictionServiceClient()
name = client.model_path('[PROJECT]', '[LOCATION]', '[MODEL]')
TODO: Initialize
payload
:payload = {}
response = client.predict(name, payload)
Name | Description |
name |
str
Name of the model requested to serve the prediction. |
payload |
Union[dict, ExamplePayload]
Required. Payload to perform a prediction on. The payload must match the problem type that the model was trained to solve. If a dict is provided, it must be of the same form as the protobuf message ExamplePayload |
params |
dict[str -> str]
Additional domain-specific parameters, any string must be up to 25000 characters long. - For Image Classification: |
retry |
Optional[google.api_core.retry.Retry]
A retry object used to retry requests. If |
timeout |
Optional[float]
The amount of time, in seconds, to wait for the request to complete. Note that if |
metadata |
Optional[Sequence[Tuple[str, str]]]
Additional metadata that is provided to the method. |
Type | Description |
google.api_core.exceptions.GoogleAPICallError | If the request failed for any reason. |
google.api_core.exceptions.RetryError | If the request failed due to a retryable error and retry attempts failed. |
ValueError | If the parameters are invalid. |