AutoML Prediction API.
On any input that is documented to expect a string parameter in snake_case or dash-case, either of those cases is accepted. v1
Package
@google-cloud/automlConstructors
(constructor)(opts, gaxInstance)
constructor
(
opts
?:
ClientOptions
,
gaxInstance
?:
typeof
gax
|
typeof
gax
.
fallback
);
Construct an instance of PredictionServiceClient.
opts
ClientOptions
gaxInstance
typeof gax | typeof gax.fallback
: loaded instance of google-gax
. Useful if you need to avoid loading the default gRPC version and want to use the fallback HTTP implementation. Load only fallback version and pass it to the constructor: ``` const gax = require('google-gax/build/src/fallback'); // avoids loading google-gax with gRPC const client = new PredictionServiceClient({fallback: 'rest'}, gax); ```
Properties
apiEndpoint
static
get
apiEndpoint
()
:
string
;
The DNS address for this API service - same as servicePath(), exists for compatibility reasons.
auth
auth
:
gax
.
GoogleAuth
;
descriptors
descriptors
:
Descriptors
;
innerApiCalls
innerApiCalls
:
{
[
name
:
string
]
:
Function
;
};
operationsClient
operationsClient
:
gax
.
OperationsClient
;
pathTemplates
pathTemplates
:
{
[
name
:
string
]
:
gax
.
PathTemplate
;
};
port
static
get
port
()
:
number
;
The port for this API service.
predictionServiceStub
predictionServiceStub
?:
Promise
< {
[
name
:
string
]
:
Function
;
}>;
scopes
static
get
scopes
()
:
string
[];
The scopes needed to make gRPC calls for every method defined in this service.
servicePath
static
get
servicePath
()
:
string
;
The DNS address for this API service.
warn
warn
:
(
code
:
string
,
message
:
string
,
warnType
?:
string
)
=
>
void
;
Methods
annotationSpecPath(project, location, dataset, annotationSpec)
annotationSpecPath
(
project
:
string
,
location
:
string
,
dataset
:
string
,
annotationSpec
:
string
)
:
string
;
Return a fully-qualified annotationSpec resource name string.
project
string
location
string
dataset
string
annotationSpec
string
string
{string} Resource name string.
batchPredict(request, options)
batchPredict
(
request
?:
protos
.
google
.
cloud
.
automl
.
v1
.
IBatchPredictRequest
,
options
?:
CallOptions
)
:
Promise
< [
LROperation<protos
.
google
.
cloud
.
automl
.
v1
.
IBatchPredictResult
,
protos
.
google
.
cloud
.
automl
.
v1
.
IOperationMetadata
> ,
protos
.
google
.
longrunning
.
IOperation
|
undefined
,
{}
|
undefined
]>;
Perform a batch prediction. Unlike the online , 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 method. Once the operation is done, is returned in the field. Available for following ML scenarios:
* AutoML Vision Classification * AutoML Vision Object Detection * AutoML Video Intelligence Classification * AutoML Video Intelligence Object Tracking * AutoML Natural Language Classification * AutoML Natural Language Entity Extraction * AutoML Natural Language Sentiment Analysis * AutoML Tables
request
protos. google.cloud.automl.v1.IBatchPredictRequest
The request object that will be sent.
options
Promise
<[ LROperation
<protos. google.cloud.automl.v1.IBatchPredictResult
, protos. google.cloud.automl.v1.IOperationMetadata
>,
protos. google.longrunning.IOperation
| undefined,
{} | undefined
]>
{Promise} - The promise which resolves to an array. The first element of the array is an object representing a long running operation. Its promise()
method returns a promise you can await
for. Please see the [documentation](https://github.com/googleapis/gax-nodejs/blob/master/client-libraries.md#long-running-operations) for more details and examples.
/**
* This snippet has been automatically generated and should be regarded as a code template only.
* It will require modifications to work.
* It may require correct/in-range values for request initialization.
* TODO(developer): Uncomment these variables before running the sample.
*/
/**
* Required. Name of the model requested to serve the batch prediction.
*/
// const name = 'abc123'
/**
* Required. The input configuration for batch prediction.
*/
// const inputConfig = {}
/**
* Required. The Configuration specifying where output predictions should
* be written.
*/
// const outputConfig = {}
/**
* Additional domain-specific parameters for the predictions, any string must
* be up to 25000 characters long.
* AutoML Natural Language Classification
* `score_threshold`
* : (float) A value from 0.0 to 1.0. When the model
* makes predictions for a text snippet, it will only produce results
* that have at least this confidence score. The default is 0.5.
* AutoML Vision Classification
* `score_threshold`
* : (float) A value from 0.0 to 1.0. When the model
* makes predictions for an image, it will only produce results that
* have at least this confidence score. The default is 0.5.
* AutoML Vision Object Detection
* `score_threshold`
* : (float) When Model detects objects on the image,
* it will only produce bounding boxes which have at least this
* confidence score. Value in 0 to 1 range, default is 0.5.
* `max_bounding_box_count`
* : (int64) The maximum number of bounding
* boxes returned per image. The default is 100, the
* number of bounding boxes returned might be limited by the server.
* AutoML Video Intelligence Classification
* `score_threshold`
* : (float) A value from 0.0 to 1.0. When the model
* makes predictions for a video, it will only produce results that
* have at least this confidence score. The default is 0.5.
* `segment_classification`
* : (boolean) Set to true to request
* segment-level classification. AutoML Video Intelligence returns
* labels and their confidence scores for the entire segment of the
* video that user specified in the request configuration.
* The default is true.
* `shot_classification`
* : (boolean) Set to true to request shot-level
* classification. AutoML Video Intelligence determines the boundaries
* for each camera shot in the entire segment of the video that user
* specified in the request configuration. AutoML Video Intelligence
* then returns labels and their confidence scores for each detected
* shot, along with the start and end time of the shot.
* The default is false.
* WARNING: Model evaluation is not done for this classification type,
* the quality of it depends on training data, but there are no metrics
* provided to describe that quality.
* `1s_interval_classification`
* : (boolean) Set to true to request
* classification for a video at one-second intervals. AutoML Video
* Intelligence returns labels and their confidence scores for each
* second of the entire segment of the video that user specified in the
* request configuration. The default is false.
* WARNING: Model evaluation is not done for this classification
* type, the quality of it depends on training data, but there are no
* metrics provided to describe that quality.
* AutoML Video Intelligence Object Tracking
* `score_threshold`
* : (float) When Model detects objects on video frames,
* it will only produce bounding boxes which have at least this
* confidence score. Value in 0 to 1 range, default is 0.5.
* `max_bounding_box_count`
* : (int64) The maximum number of bounding
* boxes returned per image. The default is 100, the
* number of bounding boxes returned might be limited by the server.
* `min_bounding_box_size`
* : (float) Only bounding boxes with shortest edge
* at least that long as a relative value of video frame size are
* returned. Value in 0 to 1 range. Default is 0.
*/
// const params = 1234
// Imports the Automl library
const
{
PredictionServiceClient
}
=
require
(
' @google-cloud/automl
'
).
v1
;
// Instantiates a client
const
automlClient
=
new
PredictionServiceClient
();
async
function
callBatchPredict
()
{
// Construct request
const
request
=
{
name
,
inputConfig
,
outputConfig
,
};
// Run request
const
[
operation
]
=
await
automlClient
.
batchPredict
(
request
);
const
[
response
]
=
await
operation
.
promise
();
console
.
log
(
response
);
}
callBatchPredict
();
batchPredict(request, options, callback)
batchPredict
(
request
:
protos
.
google
.
cloud
.
automl
.
v1
.
IBatchPredictRequest
,
options
:
CallOptions
,
callback
:
Callback<LROperation<protos
.
google
.
cloud
.
automl
.
v1
.
IBatchPredictResult
,
protos
.
google
.
cloud
.
automl
.
v1
.
IOperationMetadata
> ,
protos
.
google
.
longrunning
.
IOperation
|
null
|
undefined
,
{}
|
null
|
undefined
> )
:
void
;
request
protos. google.cloud.automl.v1.IBatchPredictRequest
options
CallOptions
callback
Callback
< LROperation
<protos. google.cloud.automl.v1.IBatchPredictResult
, protos. google.cloud.automl.v1.IOperationMetadata
>, protos. google.longrunning.IOperation
| null | undefined, {} | null | undefined>
void
batchPredict(request, callback)
batchPredict
(
request
:
protos
.
google
.
cloud
.
automl
.
v1
.
IBatchPredictRequest
,
callback
:
Callback<LROperation<protos
.
google
.
cloud
.
automl
.
v1
.
IBatchPredictResult
,
protos
.
google
.
cloud
.
automl
.
v1
.
IOperationMetadata
> ,
protos
.
google
.
longrunning
.
IOperation
|
null
|
undefined
,
{}
|
null
|
undefined
> )
:
void
;
request
protos. google.cloud.automl.v1.IBatchPredictRequest
callback
Callback
< LROperation
<protos. google.cloud.automl.v1.IBatchPredictResult
, protos. google.cloud.automl.v1.IOperationMetadata
>, protos. google.longrunning.IOperation
| null | undefined, {} | null | undefined>
void
checkBatchPredictProgress(name)
checkBatchPredictProgress
(
name
:
string
)
:
Promise<LROperation<protos
.
google
.
cloud
.
automl
.
v1
.
BatchPredictResult
,
protos
.
google
.
cloud
.
automl
.
v1
.
OperationMetadata
>> ;
Check the status of the long running operation returned by batchPredict()
.
name
string
The operation name that will be passed.
Promise
< LROperation
<protos. google.cloud.automl.v1.BatchPredictResult
, protos. google.cloud.automl.v1.OperationMetadata
>>
{Promise} - The promise which resolves to an object. The decoded operation object has result and metadata field to get information from. Please see the [documentation](https://github.com/googleapis/gax-nodejs/blob/master/client-libraries.md#long-running-operations) for more details and examples.
/**
* This snippet has been automatically generated and should be regarded as a code template only.
* It will require modifications to work.
* It may require correct/in-range values for request initialization.
* TODO(developer): Uncomment these variables before running the sample.
*/
/**
* Required. Name of the model requested to serve the batch prediction.
*/
// const name = 'abc123'
/**
* Required. The input configuration for batch prediction.
*/
// const inputConfig = {}
/**
* Required. The Configuration specifying where output predictions should
* be written.
*/
// const outputConfig = {}
/**
* Additional domain-specific parameters for the predictions, any string must
* be up to 25000 characters long.
* AutoML Natural Language Classification
* `score_threshold`
* : (float) A value from 0.0 to 1.0. When the model
* makes predictions for a text snippet, it will only produce results
* that have at least this confidence score. The default is 0.5.
* AutoML Vision Classification
* `score_threshold`
* : (float) A value from 0.0 to 1.0. When the model
* makes predictions for an image, it will only produce results that
* have at least this confidence score. The default is 0.5.
* AutoML Vision Object Detection
* `score_threshold`
* : (float) When Model detects objects on the image,
* it will only produce bounding boxes which have at least this
* confidence score. Value in 0 to 1 range, default is 0.5.
* `max_bounding_box_count`
* : (int64) The maximum number of bounding
* boxes returned per image. The default is 100, the
* number of bounding boxes returned might be limited by the server.
* AutoML Video Intelligence Classification
* `score_threshold`
* : (float) A value from 0.0 to 1.0. When the model
* makes predictions for a video, it will only produce results that
* have at least this confidence score. The default is 0.5.
* `segment_classification`
* : (boolean) Set to true to request
* segment-level classification. AutoML Video Intelligence returns
* labels and their confidence scores for the entire segment of the
* video that user specified in the request configuration.
* The default is true.
* `shot_classification`
* : (boolean) Set to true to request shot-level
* classification. AutoML Video Intelligence determines the boundaries
* for each camera shot in the entire segment of the video that user
* specified in the request configuration. AutoML Video Intelligence
* then returns labels and their confidence scores for each detected
* shot, along with the start and end time of the shot.
* The default is false.
* WARNING: Model evaluation is not done for this classification type,
* the quality of it depends on training data, but there are no metrics
* provided to describe that quality.
* `1s_interval_classification`
* : (boolean) Set to true to request
* classification for a video at one-second intervals. AutoML Video
* Intelligence returns labels and their confidence scores for each
* second of the entire segment of the video that user specified in the
* request configuration. The default is false.
* WARNING: Model evaluation is not done for this classification
* type, the quality of it depends on training data, but there are no
* metrics provided to describe that quality.
* AutoML Video Intelligence Object Tracking
* `score_threshold`
* : (float) When Model detects objects on video frames,
* it will only produce bounding boxes which have at least this
* confidence score. Value in 0 to 1 range, default is 0.5.
* `max_bounding_box_count`
* : (int64) The maximum number of bounding
* boxes returned per image. The default is 100, the
* number of bounding boxes returned might be limited by the server.
* `min_bounding_box_size`
* : (float) Only bounding boxes with shortest edge
* at least that long as a relative value of video frame size are
* returned. Value in 0 to 1 range. Default is 0.
*/
// const params = 1234
// Imports the Automl library
const
{
PredictionServiceClient
}
=
require
(
' @google-cloud/automl
'
).
v1
;
// Instantiates a client
const
automlClient
=
new
PredictionServiceClient
();
async
function
callBatchPredict
()
{
// Construct request
const
request
=
{
name
,
inputConfig
,
outputConfig
,
};
// Run request
const
[
operation
]
=
await
automlClient
.
batchPredict
(
request
);
const
[
response
]
=
await
operation
.
promise
();
console
.
log
(
response
);
}
callBatchPredict
();
close()
close
()
:
Promise<void>
;
Terminate the gRPC channel and close the client.
The client will no longer be usable and all future behavior is undefined.
Promise
<void>
{Promise} A promise that resolves when the client is closed.
datasetPath(project, location, dataset)
datasetPath
(
project
:
string
,
location
:
string
,
dataset
:
string
)
:
string
;
Return a fully-qualified dataset resource name string.
project
string
location
string
dataset
string
string
{string} Resource name string.
getProjectId()
getProjectId
()
:
Promise<string>
;
Promise
<string>
getProjectId(callback)
getProjectId
(
callback
:
Callback<string
,
undefined
,
undefined
> )
:
void
;
callback
Callback
<string, undefined, undefined>
void
initialize()
initialize
()
:
Promise
< {
[
name
:
string
]
:
Function
;
}>;
Initialize the client. Performs asynchronous operations (such as authentication) and prepares the client. This function will be called automatically when any class method is called for the first time, but if you need to initialize it before calling an actual method, feel free to call initialize() directly.
You can await on this method if you want to make sure the client is initialized.
Promise
<{
[name: string]: Function
;
}>
{Promise} A promise that resolves to an authenticated service stub.
matchAnnotationSpecFromAnnotationSpecName(annotationSpecName)
matchAnnotationSpecFromAnnotationSpecName
(
annotationSpecName
:
string
)
:
string
|
number
;
Parse the annotation_spec from AnnotationSpec resource.
annotationSpecName
string
A fully-qualified path representing AnnotationSpec resource.
string | number
{string} A string representing the annotation_spec.
matchDatasetFromAnnotationSpecName(annotationSpecName)
matchDatasetFromAnnotationSpecName
(
annotationSpecName
:
string
)
:
string
|
number
;
Parse the dataset from AnnotationSpec resource.
annotationSpecName
string
A fully-qualified path representing AnnotationSpec resource.
string | number
{string} A string representing the dataset.
matchDatasetFromDatasetName(datasetName)
matchDatasetFromDatasetName
(
datasetName
:
string
)
:
string
|
number
;
Parse the dataset from Dataset resource.
datasetName
string
A fully-qualified path representing Dataset resource.
string | number
{string} A string representing the dataset.
matchLocationFromAnnotationSpecName(annotationSpecName)
matchLocationFromAnnotationSpecName
(
annotationSpecName
:
string
)
:
string
|
number
;
Parse the location from AnnotationSpec resource.
annotationSpecName
string
A fully-qualified path representing AnnotationSpec resource.
string | number
{string} A string representing the location.
matchLocationFromDatasetName(datasetName)
matchLocationFromDatasetName
(
datasetName
:
string
)
:
string
|
number
;
Parse the location from Dataset resource.
datasetName
string
A fully-qualified path representing Dataset resource.
string | number
{string} A string representing the location.
matchLocationFromModelEvaluationName(modelEvaluationName)
matchLocationFromModelEvaluationName
(
modelEvaluationName
:
string
)
:
string
|
number
;
Parse the location from ModelEvaluation resource.
modelEvaluationName
string
A fully-qualified path representing ModelEvaluation resource.
string | number
{string} A string representing the location.
matchLocationFromModelName(modelName)
matchLocationFromModelName
(
modelName
:
string
)
:
string
|
number
;
Parse the location from Model resource.
modelName
string
A fully-qualified path representing Model resource.
string | number
{string} A string representing the location.
matchModelEvaluationFromModelEvaluationName(modelEvaluationName)
matchModelEvaluationFromModelEvaluationName
(
modelEvaluationName
:
string
)
:
string
|
number
;
Parse the model_evaluation from ModelEvaluation resource.
modelEvaluationName
string
A fully-qualified path representing ModelEvaluation resource.
string | number
{string} A string representing the model_evaluation.
matchModelFromModelEvaluationName(modelEvaluationName)
matchModelFromModelEvaluationName
(
modelEvaluationName
:
string
)
:
string
|
number
;
Parse the model from ModelEvaluation resource.
modelEvaluationName
string
A fully-qualified path representing ModelEvaluation resource.
string | number
{string} A string representing the model.
matchModelFromModelName(modelName)
matchModelFromModelName
(
modelName
:
string
)
:
string
|
number
;
Parse the model from Model resource.
modelName
string
A fully-qualified path representing Model resource.
string | number
{string} A string representing the model.
matchProjectFromAnnotationSpecName(annotationSpecName)
matchProjectFromAnnotationSpecName
(
annotationSpecName
:
string
)
:
string
|
number
;
Parse the project from AnnotationSpec resource.
annotationSpecName
string
A fully-qualified path representing AnnotationSpec resource.
string | number
{string} A string representing the project.
matchProjectFromDatasetName(datasetName)
matchProjectFromDatasetName
(
datasetName
:
string
)
:
string
|
number
;
Parse the project from Dataset resource.
datasetName
string
A fully-qualified path representing Dataset resource.
string | number
{string} A string representing the project.
matchProjectFromModelEvaluationName(modelEvaluationName)
matchProjectFromModelEvaluationName
(
modelEvaluationName
:
string
)
:
string
|
number
;
Parse the project from ModelEvaluation resource.
modelEvaluationName
string
A fully-qualified path representing ModelEvaluation resource.
string | number
{string} A string representing the project.
matchProjectFromModelName(modelName)
matchProjectFromModelName
(
modelName
:
string
)
:
string
|
number
;
Parse the project from Model resource.
modelName
string
A fully-qualified path representing Model resource.
string | number
{string} A string representing the project.
modelEvaluationPath(project, location, model, modelEvaluation)
modelEvaluationPath
(
project
:
string
,
location
:
string
,
model
:
string
,
modelEvaluation
:
string
)
:
string
;
Return a fully-qualified modelEvaluation resource name string.
project
string
location
string
model
string
modelEvaluation
string
string
{string} Resource name string.
modelPath(project, location, model)
modelPath
(
project
:
string
,
location
:
string
,
model
:
string
)
:
string
;
Return a fully-qualified model resource name string.
project
string
location
string
model
string
string
{string} Resource name string.
predict(request, options)
predict
(
request
?:
protos
.
google
.
cloud
.
automl
.
v1
.
IPredictRequest
,
options
?:
CallOptions
)
:
Promise
< [
protos
.
google
.
cloud
.
automl
.
v1
.
IPredictResponse
,
protos
.
google
.
cloud
.
automl
.
v1
.
IPredictRequest
|
undefined
,
{}
|
undefined
]>;
Perform an online prediction. The prediction result is directly returned in the response. Available for following ML scenarios, and their expected request payloads:
AutoML Vision Classification
* An image in .JPEG, .GIF or .PNG format, image_bytes up to 30MB.
AutoML Vision Object Detection
* An image in .JPEG, .GIF or .PNG format, image_bytes up to 30MB.
AutoML Natural Language Classification
* A TextSnippet up to 60,000 characters, UTF-8 encoded or a document in .PDF, .TIF or .TIFF format with size upto 2MB.
AutoML Natural Language Entity Extraction
* A TextSnippet up to 10,000 characters, UTF-8 NFC encoded or a document in .PDF, .TIF or .TIFF format with size upto 20MB.
AutoML Natural Language Sentiment Analysis
* A TextSnippet up to 60,000 characters, UTF-8 encoded or a document in .PDF, .TIF or .TIFF format with size upto 2MB.
AutoML Translation
* A TextSnippet up to 25,000 characters, UTF-8 encoded.
AutoML Tables
* A row with column values matching the columns of the model, up to 5MB. Not available for FORECASTING prediction_type
.
request
protos. google.cloud.automl.v1.IPredictRequest
The request object that will be sent.
options
Promise
<[
protos. google.cloud.automl.v1.IPredictResponse
,
protos. google.cloud.automl.v1.IPredictRequest
| undefined,
{} | undefined
]>
{Promise} - The promise which resolves to an array. The first element of the array is an object representing [PredictResponse]. Please see the [documentation](https://github.com/googleapis/gax-nodejs/blob/master/client-libraries.md#regular-methods) for more details and examples.
/**
* This snippet has been automatically generated and should be regarded as a code template only.
* It will require modifications to work.
* It may require correct/in-range values for request initialization.
* TODO(developer): Uncomment these variables before running the sample.
*/
/**
* Required. Name of the model requested to serve the prediction.
*/
// const name = 'abc123'
/**
* Required. Payload to perform a prediction on. The payload must match the
* problem type that the model was trained to solve.
*/
// const payload = {}
/**
* Additional domain-specific parameters, any string must be up to 25000
* characters long.
* AutoML Vision Classification
* `score_threshold`
* : (float) A value from 0.0 to 1.0. When the model
* makes predictions for an image, it will only produce results that have
* at least this confidence score. The default is 0.5.
* AutoML Vision Object Detection
* `score_threshold`
* : (float) When Model detects objects on the image,
* it will only produce bounding boxes which have at least this
* confidence score. Value in 0 to 1 range, default is 0.5.
* `max_bounding_box_count`
* : (int64) The maximum number of bounding
* boxes returned. The default is 100. The
* number of returned bounding boxes might be limited by the server.
* AutoML Tables
* `feature_importance`
* : (boolean) Whether
* feature_importance google.cloud.automl.v1.TablesModelColumnInfo.feature_importance
* is populated in the returned list of
* TablesAnnotation google.cloud.automl.v1.TablesAnnotation
* objects. The default is false.
*/
// const params = 1234
// Imports the Automl library
const
{
PredictionServiceClient
}
=
require
(
' @google-cloud/automl
'
).
v1
;
// Instantiates a client
const
automlClient
=
new
PredictionServiceClient
();
async
function
callPredict
()
{
// Construct request
const
request
=
{
name
,
payload
,
};
// Run request
const
response
=
await
automlClient
.
predict
(
request
);
console
.
log
(
response
);
}
callPredict
();
predict(request, options, callback)
predict
(
request
:
protos
.
google
.
cloud
.
automl
.
v1
.
IPredictRequest
,
options
:
CallOptions
,
callback
:
Callback<protos
.
google
.
cloud
.
automl
.
v1
.
IPredictResponse
,
protos
.
google
.
cloud
.
automl
.
v1
.
IPredictRequest
|
null
|
undefined
,
{}
|
null
|
undefined
> )
:
void
;
request
protos. google.cloud.automl.v1.IPredictRequest
options
CallOptions
callback
Callback
<protos. google.cloud.automl.v1.IPredictResponse
, protos. google.cloud.automl.v1.IPredictRequest
| null | undefined, {} | null | undefined>
void
predict(request, callback)
predict
(
request
:
protos
.
google
.
cloud
.
automl
.
v1
.
IPredictRequest
,
callback
:
Callback<protos
.
google
.
cloud
.
automl
.
v1
.
IPredictResponse
,
protos
.
google
.
cloud
.
automl
.
v1
.
IPredictRequest
|
null
|
undefined
,
{}
|
null
|
undefined
> )
:
void
;
request
protos. google.cloud.automl.v1.IPredictRequest
callback
Callback
<protos. google.cloud.automl.v1.IPredictResponse
, protos. google.cloud.automl.v1.IPredictRequest
| null | undefined, {} | null | undefined>
void
