Constructor

PredictionServiceClient

new PredictionServiceClient(options)

Construct an instance of PredictionServiceClient.

Parameter

options

Optional

object

The configuration object. See the subsequent parameters for more details.

Values in options have the following properties:

Parameter

credentials

Optional

object

Credentials object.

credentials.client_email

Optional

string

credentials.private_key

Optional

string

email

Optional

string

Account email address. Required when using a .pem or .p12 keyFilename.

keyFilename

Optional

string

Full path to the a .json, .pem, or .p12 key downloaded from the Google Developers Console. If you provide a path to a JSON file, the projectId option below is not necessary. NOTE: .pem and .p12 require you to specify options.email as well.

port

Optional

number

The port on which to connect to the remote host.

projectId

Optional

string

The project ID from the Google Developer's Console, e.g. 'grape-spaceship-123'. We will also check the environment variable GCLOUD_PROJECT for your project ID. If your app is running in an environment which supports Application Default Credentials, your project ID will be detected automatically.

promise

Optional

function()

Custom promise module to use instead of native Promises.

servicePath

Optional

string

The domain name of the API remote host.

Properties

port

static

The port for this API service.

scopes

static

The scopes needed to make gRPC calls for every method defined in this service.

servicePath

static

The DNS address for this API service.

Methods

getProjectId

getProjectId(callback)

Return the project ID used by this class.

Parameter

callback

function(Error, string)

the callback to be called with the current project Id.

matchLocationFromModelName

matchLocationFromModelName(modelName) returns String

Parse the modelName from a model resource.

Parameter

modelName

String

A fully-qualified path representing a model resources.

Returns

String 

  • A string representing the location.

matchModelFromModelName

matchModelFromModelName(modelName) returns String

Parse the modelName from a model resource.

Parameter

modelName

String

A fully-qualified path representing a model resources.

Returns

String 

  • A string representing the model.

matchProjectFromModelName

matchProjectFromModelName(modelName) returns String

Parse the modelName from a model resource.

Parameter

modelName

String

A fully-qualified path representing a model resources.

Returns

String 

  • A string representing the project.

modelPath

modelPath(project, location, model) returns String

Return a fully-qualified model resource name string.

Parameter

project

String

location

String

model

String

Returns

String 

predict

predict(request, options, callback) returns Promise

Perform a prediction.

Parameter

request

Object

The request object that will be sent.

Values in request have the following properties:

Parameter

name

string

Name of the model requested to serve the prediction.

payload

Object

Required. Payload to perform a prediction on. The payload must match the problem type that the model was trained to solve.

This object should have the same structure as ExamplePayload

params

Optional

Object with string properties

Additional domain-specific parameters, any string must be up to 25000 characters long.

  • For Image 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 threshold. The default is 0.5.

options

Optional

Object

Optional parameters. You can override the default settings for this call, e.g, timeout, retries, paginations, etc. See gax.CallOptions for the details.

callback

Optional

function(nullable Error, nullable Object)

The function which will be called with the result of the API call.

The second parameter to the callback is an object representing PredictResponse.

Returns

Promise 

  • The promise which resolves to an array. The first element of the array is an object representing PredictResponse. The promise has a method named "cancel" which cancels the ongoing API call.

Example

const automl = require('@google-cloud/automl');

const client = new automl.v1beta1.PredictionServiceClient({
  // optional auth parameters.
});

const formattedName = client.modelPath('[PROJECT]', '[LOCATION]', '[MODEL]');
const payload = {};
const request = {
  name: formattedName,
  payload: payload,
};
client.predict(request)
  .then(responses => {
    const response = responses[0];
    // doThingsWith(response)
  })
  .catch(err => {
    console.error(err);
  });