Google Cloud Ai Platform V1 Client - Class PredictionServiceClient (0.30.0)

Reference documentation and code samples for the Google Cloud Ai Platform V1 Client class PredictionServiceClient.

Service Description: A service for online predictions and explanations.

This class provides the ability to make remote calls to the backing service through method calls that map to API methods. Sample code to get started:

$predictionServiceClient = new PredictionServiceClient();
try {
    $formattedEndpoint = $predictionServiceClient->endpointName('[PROJECT]', '[LOCATION]', '[ENDPOINT]');
    $response = $predictionServiceClient->directPredict($formattedEndpoint);
} finally {
    $predictionServiceClient->close();
}

Many parameters require resource names to be formatted in a particular way. To assist with these names, this class includes a format method for each type of name, and additionally a parseName method to extract the individual identifiers contained within formatted names that are returned by the API.

This service has a new (beta) implementation. See Google\Cloud\AIPlatform\V1\Client\PredictionServiceClient to use the new surface.

Namespace

Google \ Cloud \ AIPlatform \ V1

Methods

__construct

Constructor.

Parameters
Name	Description
`options`	`array` Optional. Options for configuring the service API wrapper.
`↳ apiEndpoint`	`string` The address of the API remote host. May optionally include the port, formatted as "
`↳ credentials`	`string\|array\|FetchAuthTokenInterface\|CredentialsWrapper` The credentials to be used by the client to authorize API calls. This option accepts either a path to a credentials file, or a decoded credentials file as a PHP array. Advanced usage: In addition, this option can also accept a pre-constructed Google\Auth\FetchAuthTokenInterface object or Google\ApiCore\CredentialsWrapper object. Note that when one of these objects are provided, any settings in $credentialsConfig will be ignored.
`↳ credentialsConfig`	`array` Options used to configure credentials, including auth token caching, for the client. For a full list of supporting configuration options, see Google\ApiCore\CredentialsWrapper::build() .
`↳ disableRetries`	`bool` Determines whether or not retries defined by the client configuration should be disabled. Defaults to `false`.
`↳ clientConfig`	`string\|array` Client method configuration, including retry settings. This option can be either a path to a JSON file, or a PHP array containing the decoded JSON data. By default this settings points to the default client config file, which is provided in the resources folder.
`↳ transport`	`string\|TransportInterface` The transport used for executing network requests. May be either the string `rest` or `grpc`. Defaults to `grpc` if gRPC support is detected on the system. Advanced usage: Additionally, it is possible to pass in an already instantiated Google\ApiCore\Transport\TransportInterface object. Note that when this object is provided, any settings in $transportConfig, and any $apiEndpoint setting, will be ignored.
`↳ transportConfig`	`array` Configuration options that will be used to construct the transport. Options for each supported transport type should be passed in a key for that transport. For example: $transportConfig = [ 'grpc' => [...], 'rest' => [...], ]; See the Google\ApiCore\Transport\GrpcTransport::build() and Google\ApiCore\Transport\RestTransport::build() methods for the supported options.
`↳ clientCertSource`	`callable` A callable which returns the client cert as a string. This can be used to provide a certificate and private key to the transport layer for mTLS.

directPredict

Perform an unary online prediction request for Vertex first-party products and frameworks.

Parameters
Name	Description
`endpoint`	`string` Required. The name of the Endpoint requested to serve the prediction. Format: `projects/{project}/locations/{location}/endpoints/{endpoint}`
`optionalArgs`	`array` Optional.
`↳ inputs`	`Tensor[]` The prediction input.
`↳ parameters`	`Tensor` The parameters that govern the prediction.
`↳ retrySettings`	`RetrySettings\|array` Retry settings to use for this call. Can be a Google\ApiCore\RetrySettings object, or an associative array of retry settings parameters. See the documentation on Google\ApiCore\RetrySettings for example usage.

Returns
Type	Description
`Google\Cloud\AIPlatform\V1\DirectPredictResponse`

Example

use Google\ApiCore\ApiException;
use Google\Cloud\AIPlatform\V1\Client\PredictionServiceClient;
use Google\Cloud\AIPlatform\V1\DirectPredictRequest;
use Google\Cloud\AIPlatform\V1\DirectPredictResponse;

/**
 * @param string $formattedEndpoint The name of the Endpoint requested to serve the prediction.
 *                                  Format:
 *                                  `projects/{project}/locations/{location}/endpoints/{endpoint}`
 *                                  Please see {@see PredictionServiceClient::endpointName()} for help formatting this field.
 */
function direct_predict_sample(string $formattedEndpoint): void
{
    // Create a client.
    $predictionServiceClient = new PredictionServiceClient();

    // Prepare the request message.
    $request = (new DirectPredictRequest())
        ->setEndpoint($formattedEndpoint);

    // Call the API and handle any network failures.
    try {
        /** @var DirectPredictResponse $response */
        $response = $predictionServiceClient->directPredict($request);
        printf('Response data: %s' . PHP_EOL, $response->serializeToJsonString());
    } catch (ApiException $ex) {
        printf('Call failed with message: %s' . PHP_EOL, $ex->getMessage());
    }
}

/**
 * Helper to execute the sample.
 *
 * This sample 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.
 *  - It may require specifying regional endpoints when creating the service client,
 *    please see the apiEndpoint client configuration option for more details.
 */
function callSample(): void
{
    $formattedEndpoint = PredictionServiceClient::endpointName('[PROJECT]', '[LOCATION]', '[ENDPOINT]');

    direct_predict_sample($formattedEndpoint);
}

directRawPredict

Perform an online prediction request through gRPC.

Parameters
Name	Description
`endpoint`	`string` Required. The name of the Endpoint requested to serve the prediction. Format: `projects/{project}/locations/{location}/endpoints/{endpoint}`
`optionalArgs`	`array` Optional.
`↳ methodName`	`string` Fully qualified name of the API method being invoked to perform predictions. Format: `/namespace.Service/Method/` Example: `/tensorflow.serving.PredictionService/Predict`
`↳ input`	`string` The prediction input.
`↳ retrySettings`	`RetrySettings\|array` Retry settings to use for this call. Can be a Google\ApiCore\RetrySettings object, or an associative array of retry settings parameters. See the documentation on Google\ApiCore\RetrySettings for example usage.

Returns
Type	Description
`Google\Cloud\AIPlatform\V1\DirectRawPredictResponse`

Example

use Google\ApiCore\ApiException;
use Google\Cloud\AIPlatform\V1\Client\PredictionServiceClient;
use Google\Cloud\AIPlatform\V1\DirectRawPredictRequest;
use Google\Cloud\AIPlatform\V1\DirectRawPredictResponse;

/**
 * @param string $formattedEndpoint The name of the Endpoint requested to serve the prediction.
 *                                  Format:
 *                                  `projects/{project}/locations/{location}/endpoints/{endpoint}`
 *                                  Please see {@see PredictionServiceClient::endpointName()} for help formatting this field.
 */
function direct_raw_predict_sample(string $formattedEndpoint): void
{
    // Create a client.
    $predictionServiceClient = new PredictionServiceClient();

    // Prepare the request message.
    $request = (new DirectRawPredictRequest())
        ->setEndpoint($formattedEndpoint);

    // Call the API and handle any network failures.
    try {
        /** @var DirectRawPredictResponse $response */
        $response = $predictionServiceClient->directRawPredict($request);
        printf('Response data: %s' . PHP_EOL, $response->serializeToJsonString());
    } catch (ApiException $ex) {
        printf('Call failed with message: %s' . PHP_EOL, $ex->getMessage());
    }
}

/**
 * Helper to execute the sample.
 *
 * This sample 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.
 *  - It may require specifying regional endpoints when creating the service client,
 *    please see the apiEndpoint client configuration option for more details.
 */
function callSample(): void
{
    $formattedEndpoint = PredictionServiceClient::endpointName('[PROJECT]', '[LOCATION]', '[ENDPOINT]');

    direct_raw_predict_sample($formattedEndpoint);
}

explain

Perform an online explanation.

If deployed_model_id is specified, the corresponding DeployModel must have explanation_spec populated. If deployed_model_id is not specified, all DeployedModels must have explanation_spec populated.

Parameters
Name	Description
`endpoint`	`string` Required. The name of the Endpoint requested to serve the explanation. Format: `projects/{project}/locations/{location}/endpoints/{endpoint}`
`instances`	`array<Google\Protobuf\Value>` Required. The instances that are the input to the explanation call. A DeployedModel may have an upper limit on the number of instances it supports per request, and when it is exceeded the explanation call errors in case of AutoML Models, or, in case of customer created Models, the behaviour is as documented by that Model. The schema of any single instance may be specified via Endpoint's DeployedModels' Model's PredictSchemata's instance_schema_uri.
`optionalArgs`	`array` Optional.
`↳ parameters`	`Value` The parameters that govern the prediction. The schema of the parameters may be specified via Endpoint's DeployedModels' Model's PredictSchemata's parameters_schema_uri.
`↳ explanationSpecOverride`	`ExplanationSpecOverride` If specified, overrides the explanation_spec of the DeployedModel. Can be used for explaining prediction results with different configurations, such as: - Explaining top-5 predictions results as opposed to top-1; - Increasing path count or step count of the attribution methods to reduce approximate errors; - Using different baselines for explaining the prediction results.
`↳ deployedModelId`	`string` If specified, this ExplainRequest will be served by the chosen DeployedModel, overriding Endpoint.traffic_split.
`↳ retrySettings`	`RetrySettings\|array` Retry settings to use for this call. Can be a Google\ApiCore\RetrySettings object, or an associative array of retry settings parameters. See the documentation on Google\ApiCore\RetrySettings for example usage.

Returns
Type	Description
`Google\Cloud\AIPlatform\V1\ExplainResponse`

Example

use Google\ApiCore\ApiException;
use Google\Cloud\AIPlatform\V1\Client\PredictionServiceClient;
use Google\Cloud\AIPlatform\V1\ExplainRequest;
use Google\Cloud\AIPlatform\V1\ExplainResponse;
use Google\Protobuf\Value;

/**
 * @param string $formattedEndpoint The name of the Endpoint requested to serve the explanation.
 *                                  Format:
 *                                  `projects/{project}/locations/{location}/endpoints/{endpoint}`
 *                                  Please see {@see PredictionServiceClient::endpointName()} for help formatting this field.
 */
function explain_sample(string $formattedEndpoint): void
{
    // Create a client.
    $predictionServiceClient = new PredictionServiceClient();

    // Prepare the request message.
    $instances = [new Value()];
    $request = (new ExplainRequest())
        ->setEndpoint($formattedEndpoint)
        ->setInstances($instances);

    // Call the API and handle any network failures.
    try {
        /** @var ExplainResponse $response */
        $response = $predictionServiceClient->explain($request);
        printf('Response data: %s' . PHP_EOL, $response->serializeToJsonString());
    } catch (ApiException $ex) {
        printf('Call failed with message: %s' . PHP_EOL, $ex->getMessage());
    }
}

/**
 * Helper to execute the sample.
 *
 * This sample 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.
 *  - It may require specifying regional endpoints when creating the service client,
 *    please see the apiEndpoint client configuration option for more details.
 */
function callSample(): void
{
    $formattedEndpoint = PredictionServiceClient::endpointName('[PROJECT]', '[LOCATION]', '[ENDPOINT]');

    explain_sample($formattedEndpoint);
}

predict

Perform an online prediction.

Parameters
Name	Description
`endpoint`	`string` Required. The name of the Endpoint requested to serve the prediction. Format: `projects/{project}/locations/{location}/endpoints/{endpoint}`
`instances`	`array<Google\Protobuf\Value>` Required. The instances that are the input to the prediction call. A DeployedModel may have an upper limit on the number of instances it supports per request, and when it is exceeded the prediction call errors in case of AutoML Models, or, in case of customer created Models, the behaviour is as documented by that Model. The schema of any single instance may be specified via Endpoint's DeployedModels' Model's PredictSchemata's instance_schema_uri.
`optionalArgs`	`array` Optional.
`↳ parameters`	`Value` The parameters that govern the prediction. The schema of the parameters may be specified via Endpoint's DeployedModels' Model's PredictSchemata's parameters_schema_uri.
`↳ retrySettings`	`RetrySettings\|array` Retry settings to use for this call. Can be a Google\ApiCore\RetrySettings object, or an associative array of retry settings parameters. See the documentation on Google\ApiCore\RetrySettings for example usage.

Returns
Type	Description
`Google\Cloud\AIPlatform\V1\PredictResponse`

Example

use Google\ApiCore\ApiException;
use Google\Cloud\AIPlatform\V1\Client\PredictionServiceClient;
use Google\Cloud\AIPlatform\V1\PredictRequest;
use Google\Cloud\AIPlatform\V1\PredictResponse;
use Google\Protobuf\Value;

/**
 * @param string $formattedEndpoint The name of the Endpoint requested to serve the prediction.
 *                                  Format:
 *                                  `projects/{project}/locations/{location}/endpoints/{endpoint}`
 *                                  Please see {@see PredictionServiceClient::endpointName()} for help formatting this field.
 */
function predict_sample(string $formattedEndpoint): void
{
    // Create a client.
    $predictionServiceClient = new PredictionServiceClient();

    // Prepare the request message.
    $instances = [new Value()];
    $request = (new PredictRequest())
        ->setEndpoint($formattedEndpoint)
        ->setInstances($instances);

    // Call the API and handle any network failures.
    try {
        /** @var PredictResponse $response */
        $response = $predictionServiceClient->predict($request);
        printf('Response data: %s' . PHP_EOL, $response->serializeToJsonString());
    } catch (ApiException $ex) {
        printf('Call failed with message: %s' . PHP_EOL, $ex->getMessage());
    }
}

/**
 * Helper to execute the sample.
 *
 * This sample 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.
 *  - It may require specifying regional endpoints when creating the service client,
 *    please see the apiEndpoint client configuration option for more details.
 */
function callSample(): void
{
    $formattedEndpoint = PredictionServiceClient::endpointName('[PROJECT]', '[LOCATION]', '[ENDPOINT]');

    predict_sample($formattedEndpoint);
}

rawPredict

Perform an online prediction with an arbitrary HTTP payload.

The response includes the following HTTP headers:

X-Vertex-AI-Endpoint-Id: ID of the Endpoint that served this prediction.
X-Vertex-AI-Deployed-Model-Id: ID of the Endpoint's DeployedModel that served this prediction.

Parameters
Name	Description
`endpoint`	`string` Required. The name of the Endpoint requested to serve the prediction. Format: `projects/{project}/locations/{location}/endpoints/{endpoint}`
`optionalArgs`	`array` Optional.
`↳ httpBody`	`HttpBody` The prediction input. Supports HTTP headers and arbitrary data payload. A DeployedModel may have an upper limit on the number of instances it supports per request. When this limit it is exceeded for an AutoML model, the RawPredict method returns an error. When this limit is exceeded for a custom-trained model, the behavior varies depending on the model. You can specify the schema for each instance in the predict_schemata.instance_schema_uri field when you create a Model. This schema applies when you deploy the `Model` as a `DeployedModel` to an Endpoint and use the `RawPredict` method.
`↳ retrySettings`	`RetrySettings\|array` Retry settings to use for this call. Can be a Google\ApiCore\RetrySettings object, or an associative array of retry settings parameters. See the documentation on Google\ApiCore\RetrySettings for example usage.

Returns
Type	Description
`Google\Api\HttpBody`

Example

use Google\ApiCore\ApiException;
use Google\Api\HttpBody;
use Google\Cloud\AIPlatform\V1\Client\PredictionServiceClient;
use Google\Cloud\AIPlatform\V1\RawPredictRequest;

/**
 * @param string $formattedEndpoint The name of the Endpoint requested to serve the prediction.
 *                                  Format:
 *                                  `projects/{project}/locations/{location}/endpoints/{endpoint}`
 *                                  Please see {@see PredictionServiceClient::endpointName()} for help formatting this field.
 */
function raw_predict_sample(string $formattedEndpoint): void
{
    // Create a client.
    $predictionServiceClient = new PredictionServiceClient();

    // Prepare the request message.
    $request = (new RawPredictRequest())
        ->setEndpoint($formattedEndpoint);

    // Call the API and handle any network failures.
    try {
        /** @var HttpBody $response */
        $response = $predictionServiceClient->rawPredict($request);
        printf('Response data: %s' . PHP_EOL, $response->serializeToJsonString());
    } catch (ApiException $ex) {
        printf('Call failed with message: %s' . PHP_EOL, $ex->getMessage());
    }
}

/**
 * Helper to execute the sample.
 *
 * This sample 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.
 *  - It may require specifying regional endpoints when creating the service client,
 *    please see the apiEndpoint client configuration option for more details.
 */
function callSample(): void
{
    $formattedEndpoint = PredictionServiceClient::endpointName('[PROJECT]', '[LOCATION]', '[ENDPOINT]');

    raw_predict_sample($formattedEndpoint);
}

serverStreamingPredict

Perform a server-side streaming online prediction request for Vertex LLM streaming.

Parameters
Name	Description
`endpoint`	`string` Required. The name of the Endpoint requested to serve the prediction. Format: `projects/{project}/locations/{location}/endpoints/{endpoint}`
`optionalArgs`	`array` Optional.
`↳ inputs`	`Tensor[]` The prediction input.
`↳ parameters`	`Tensor` The parameters that govern the prediction.
`↳ timeoutMillis`	`int` Timeout to use for this call.

Returns
Type	Description
`Google\ApiCore\ServerStream`

Example

use Google\ApiCore\ApiException;
use Google\ApiCore\ServerStream;
use Google\Cloud\AIPlatform\V1\Client\PredictionServiceClient;
use Google\Cloud\AIPlatform\V1\StreamingPredictRequest;
use Google\Cloud\AIPlatform\V1\StreamingPredictResponse;

/**
 * @param string $formattedEndpoint The name of the Endpoint requested to serve the prediction.
 *                                  Format:
 *                                  `projects/{project}/locations/{location}/endpoints/{endpoint}`
 *                                  Please see {@see PredictionServiceClient::endpointName()} for help formatting this field.
 */
function server_streaming_predict_sample(string $formattedEndpoint): void
{
    // Create a client.
    $predictionServiceClient = new PredictionServiceClient();

    // Prepare the request message.
    $request = (new StreamingPredictRequest())
        ->setEndpoint($formattedEndpoint);

    // Call the API and handle any network failures.
    try {
        /** @var ServerStream $stream */
        $stream = $predictionServiceClient->serverStreamingPredict($request);

        /** @var StreamingPredictResponse $element */
        foreach ($stream->readAll() as $element) {
            printf('Element data: %s' . PHP_EOL, $element->serializeToJsonString());
        }
    } catch (ApiException $ex) {
        printf('Call failed with message: %s' . PHP_EOL, $ex->getMessage());
    }
}

/**
 * Helper to execute the sample.
 *
 * This sample 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.
 *  - It may require specifying regional endpoints when creating the service client,
 *    please see the apiEndpoint client configuration option for more details.
 */
function callSample(): void
{
    $formattedEndpoint = PredictionServiceClient::endpointName('[PROJECT]', '[LOCATION]', '[ENDPOINT]');

    server_streaming_predict_sample($formattedEndpoint);
}

streamGenerateContent

Generate content with multimodal inputs with streaming support.

Parameters
Name	Description
`model`	`string` Required. The name of the publisher model requested to serve the prediction. Format: `projects/{project}/locations/{location}/publishers//models/`
`contents`	`array<Google\Cloud\AIPlatform\V1\Content>` Required. The content of the current conversation with the model. For single-turn queries, this is a single instance. For multi-turn queries, this is a repeated field that contains conversation history + latest request.
`optionalArgs`	`array` Optional.
`↳ tools`	`Tool[]` Optional. A list of `Tools` the model may use to generate the next response. A `Tool` is a piece of code that enables the system to interact with external systems to perform an action, or set of actions, outside of knowledge and scope of the model. The only supported tool is currently `Function`
`↳ safetySettings`	`SafetySetting[]` Optional. Per request settings for blocking unsafe content. Enforced on GenerateContentResponse.candidates.
`↳ generationConfig`	`GenerationConfig` Optional. Generation config.
`↳ timeoutMillis`	`int` Timeout to use for this call.

Returns
Type	Description
`Google\ApiCore\ServerStream`

Example

use Google\ApiCore\ApiException;
use Google\ApiCore\ServerStream;
use Google\Cloud\AIPlatform\V1\Client\PredictionServiceClient;
use Google\Cloud\AIPlatform\V1\Content;
use Google\Cloud\AIPlatform\V1\GenerateContentRequest;
use Google\Cloud\AIPlatform\V1\GenerateContentResponse;
use Google\Cloud\AIPlatform\V1\Part;

/**
 * @param string $model The name of the publisher model requested to serve the
 *                      prediction. Format:
 *                      `projects/{project}/locations/{location}/publishers/&#42;/models/*`
 */
function stream_generate_content_sample(string $model): void
{
    // Create a client.
    $predictionServiceClient = new PredictionServiceClient();

    // Prepare the request message.
    $contentsParts = [new Part()];
    $content = (new Content())
        ->setParts($contentsParts);
    $contents = [$content,];
    $request = (new GenerateContentRequest())
        ->setModel($model)
        ->setContents($contents);

    // Call the API and handle any network failures.
    try {
        /** @var ServerStream $stream */
        $stream = $predictionServiceClient->streamGenerateContent($request);

        /** @var GenerateContentResponse $element */
        foreach ($stream->readAll() as $element) {
            printf('Element data: %s' . PHP_EOL, $element->serializeToJsonString());
        }
    } catch (ApiException $ex) {
        printf('Call failed with message: %s' . PHP_EOL, $ex->getMessage());
    }
}

/**
 * Helper to execute the sample.
 *
 * This sample 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.
 *  - It may require specifying regional endpoints when creating the service client,
 *    please see the apiEndpoint client configuration option for more details.
 */
function callSample(): void
{
    $model = '[MODEL]';

    stream_generate_content_sample($model);
}

streamingPredict

Perform a streaming online prediction request for Vertex first-party products and frameworks.

Parameters
Name	Description
`optionalArgs`	`array` Optional.
`↳ timeoutMillis`	`int` Timeout to use for this call.

Returns
Type	Description
`Google\ApiCore\BidiStream`

Example

use Google\ApiCore\ApiException;
use Google\ApiCore\BidiStream;
use Google\Cloud\AIPlatform\V1\Client\PredictionServiceClient;
use Google\Cloud\AIPlatform\V1\StreamingPredictRequest;
use Google\Cloud\AIPlatform\V1\StreamingPredictResponse;

/**
 * @param string $formattedEndpoint The name of the Endpoint requested to serve the prediction.
 *                                  Format:
 *                                  `projects/{project}/locations/{location}/endpoints/{endpoint}`
 *                                  Please see {@see PredictionServiceClient::endpointName()} for help formatting this field.
 */
function streaming_predict_sample(string $formattedEndpoint): void
{
    // Create a client.
    $predictionServiceClient = new PredictionServiceClient();

    // Prepare the request message.
    $request = (new StreamingPredictRequest())
        ->setEndpoint($formattedEndpoint);

    // Call the API and handle any network failures.
    try {
        /** @var BidiStream $stream */
        $stream = $predictionServiceClient->streamingPredict();
        $stream->writeAll([$request,]);

        /** @var StreamingPredictResponse $element */
        foreach ($stream->closeWriteAndReadAll() as $element) {
            printf('Element data: %s' . PHP_EOL, $element->serializeToJsonString());
        }
    } catch (ApiException $ex) {
        printf('Call failed with message: %s' . PHP_EOL, $ex->getMessage());
    }
}

/**
 * Helper to execute the sample.
 *
 * This sample 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.
 *  - It may require specifying regional endpoints when creating the service client,
 *    please see the apiEndpoint client configuration option for more details.
 */
function callSample(): void
{
    $formattedEndpoint = PredictionServiceClient::endpointName('[PROJECT]', '[LOCATION]', '[ENDPOINT]');

    streaming_predict_sample($formattedEndpoint);
}

streamingRawPredict

Perform a streaming online prediction request through gRPC.

Parameters
Name	Description
`optionalArgs`	`array` Optional.
`↳ timeoutMillis`	`int` Timeout to use for this call.

Returns
Type	Description
`Google\ApiCore\BidiStream`

Example

use Google\ApiCore\ApiException;
use Google\ApiCore\BidiStream;
use Google\Cloud\AIPlatform\V1\Client\PredictionServiceClient;
use Google\Cloud\AIPlatform\V1\StreamingRawPredictRequest;
use Google\Cloud\AIPlatform\V1\StreamingRawPredictResponse;

/**
 * @param string $formattedEndpoint The name of the Endpoint requested to serve the prediction.
 *                                  Format:
 *                                  `projects/{project}/locations/{location}/endpoints/{endpoint}`
 *                                  Please see {@see PredictionServiceClient::endpointName()} for help formatting this field.
 */
function streaming_raw_predict_sample(string $formattedEndpoint): void
{
    // Create a client.
    $predictionServiceClient = new PredictionServiceClient();

    // Prepare the request message.
    $request = (new StreamingRawPredictRequest())
        ->setEndpoint($formattedEndpoint);

    // Call the API and handle any network failures.
    try {
        /** @var BidiStream $stream */
        $stream = $predictionServiceClient->streamingRawPredict();
        $stream->writeAll([$request,]);

        /** @var StreamingRawPredictResponse $element */
        foreach ($stream->closeWriteAndReadAll() as $element) {
            printf('Element data: %s' . PHP_EOL, $element->serializeToJsonString());
        }
    } catch (ApiException $ex) {
        printf('Call failed with message: %s' . PHP_EOL, $ex->getMessage());
    }
}

/**
 * Helper to execute the sample.
 *
 * This sample 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.
 *  - It may require specifying regional endpoints when creating the service client,
 *    please see the apiEndpoint client configuration option for more details.
 */
function callSample(): void
{
    $formattedEndpoint = PredictionServiceClient::endpointName('[PROJECT]', '[LOCATION]', '[ENDPOINT]');

    streaming_raw_predict_sample($formattedEndpoint);
}

getLocation

Gets information about a location.

Parameters
Name	Description
`optionalArgs`	`array` Optional.
`↳ name`	`string` Resource name for the location.
`↳ retrySettings`	`RetrySettings\|array` Retry settings to use for this call. Can be a Google\ApiCore\RetrySettings object, or an associative array of retry settings parameters. See the documentation on Google\ApiCore\RetrySettings for example usage.

Returns
Type	Description
`Google\Cloud\Location\Location`

Example

use Google\ApiCore\ApiException;
use Google\Cloud\AIPlatform\V1\Client\PredictionServiceClient;
use Google\Cloud\Location\GetLocationRequest;
use Google\Cloud\Location\Location;

/**
 * This sample 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.
 *  - It may require specifying regional endpoints when creating the service client,
 *    please see the apiEndpoint client configuration option for more details.
 */
function get_location_sample(): void
{
    // Create a client.
    $predictionServiceClient = new PredictionServiceClient();

    // Prepare the request message.
    $request = new GetLocationRequest();

    // Call the API and handle any network failures.
    try {
        /** @var Location $response */
        $response = $predictionServiceClient->getLocation($request);
        printf('Response data: %s' . PHP_EOL, $response->serializeToJsonString());
    } catch (ApiException $ex) {
        printf('Call failed with message: %s' . PHP_EOL, $ex->getMessage());
    }
}

listLocations

Lists information about the supported locations for this service.

Parameters
Name	Description
`optionalArgs`	`array` Optional.
`↳ name`	`string` The resource that owns the locations collection, if applicable.
`↳ filter`	`string` The standard list filter.
`↳ pageSize`	`int` The maximum number of resources contained in the underlying API response. The API may return fewer values in a page, even if there are additional values to be retrieved.
`↳ pageToken`	`string` A page token is used to specify a page of values to be returned. If no page token is specified (the default), the first page of values will be returned. Any page token used here must have been generated by a previous call to the API.
`↳ retrySettings`	`RetrySettings\|array` Retry settings to use for this call. Can be a Google\ApiCore\RetrySettings object, or an associative array of retry settings parameters. See the documentation on Google\ApiCore\RetrySettings for example usage.

Returns
Type	Description
`Google\ApiCore\PagedListResponse`

Example

use Google\ApiCore\ApiException;
use Google\ApiCore\PagedListResponse;
use Google\Cloud\AIPlatform\V1\Client\PredictionServiceClient;
use Google\Cloud\Location\ListLocationsRequest;
use Google\Cloud\Location\Location;

/**
 * This sample 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.
 *  - It may require specifying regional endpoints when creating the service client,
 *    please see the apiEndpoint client configuration option for more details.
 */
function list_locations_sample(): void
{
    // Create a client.
    $predictionServiceClient = new PredictionServiceClient();

    // Prepare the request message.
    $request = new ListLocationsRequest();

    // Call the API and handle any network failures.
    try {
        /** @var PagedListResponse $response */
        $response = $predictionServiceClient->listLocations($request);

        /** @var Location $element */
        foreach ($response as $element) {
            printf('Element data: %s' . PHP_EOL, $element->serializeToJsonString());
        }
    } catch (ApiException $ex) {
        printf('Call failed with message: %s' . PHP_EOL, $ex->getMessage());
    }
}

getIamPolicy

Gets the access control policy for a resource. Returns an empty policy if the resource exists and does not have a policy set.

Parameters
Name	Description
`resource`	`string` REQUIRED: The resource for which the policy is being requested. See the operation documentation for the appropriate value for this field.
`optionalArgs`	`array` Optional.
`↳ options`	`GetPolicyOptions` OPTIONAL: A `GetPolicyOptions` object for specifying options to `GetIamPolicy`.
`↳ retrySettings`	`RetrySettings\|array` Retry settings to use for this call. Can be a Google\ApiCore\RetrySettings object, or an associative array of retry settings parameters. See the documentation on Google\ApiCore\RetrySettings for example usage.

Returns
Type	Description
`Google\Cloud\Iam\V1\Policy`

Example

use Google\ApiCore\ApiException;
use Google\Cloud\AIPlatform\V1\Client\PredictionServiceClient;
use Google\Cloud\Iam\V1\GetIamPolicyRequest;
use Google\Cloud\Iam\V1\Policy;

/**
 * @param string $resource REQUIRED: The resource for which the policy is being requested.
 *                         See the operation documentation for the appropriate value for this field.
 */
function get_iam_policy_sample(string $resource): void
{
    // Create a client.
    $predictionServiceClient = new PredictionServiceClient();

    // Prepare the request message.
    $request = (new GetIamPolicyRequest())
        ->setResource($resource);

    // Call the API and handle any network failures.
    try {
        /** @var Policy $response */
        $response = $predictionServiceClient->getIamPolicy($request);
        printf('Response data: %s' . PHP_EOL, $response->serializeToJsonString());
    } catch (ApiException $ex) {
        printf('Call failed with message: %s' . PHP_EOL, $ex->getMessage());
    }
}

/**
 * Helper to execute the sample.
 *
 * This sample 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.
 *  - It may require specifying regional endpoints when creating the service client,
 *    please see the apiEndpoint client configuration option for more details.
 */
function callSample(): void
{
    $resource = '[RESOURCE]';

    get_iam_policy_sample($resource);
}

setIamPolicy

Sets the access control policy on the specified resource. Replaces any existing policy.

Can return NOT_FOUND, INVALID_ARGUMENT, and PERMISSION_DENIED errors.

Parameters
Name	Description
`resource`	`string` REQUIRED: The resource for which the policy is being specified. See the operation documentation for the appropriate value for this field.
`policy`	`Google\Cloud\Iam\V1\Policy` REQUIRED: The complete policy to be applied to the `resource`. The size of the policy is limited to a few 10s of KB. An empty policy is a valid policy but certain Cloud Platform services (such as Projects) might reject them.
`optionalArgs`	`array` Optional.
`↳ updateMask`	`FieldMask` OPTIONAL: A FieldMask specifying which fields of the policy to modify. Only the fields in the mask will be modified. If no mask is provided, the following default mask is used: `paths: "bindings, etag"`
`↳ retrySettings`	`RetrySettings\|array` Retry settings to use for this call. Can be a Google\ApiCore\RetrySettings object, or an associative array of retry settings parameters. See the documentation on Google\ApiCore\RetrySettings for example usage.

Returns
Type	Description
`Google\Cloud\Iam\V1\Policy`

Example

use Google\ApiCore\ApiException;
use Google\Cloud\AIPlatform\V1\Client\PredictionServiceClient;
use Google\Cloud\Iam\V1\Policy;
use Google\Cloud\Iam\V1\SetIamPolicyRequest;

/**
 * @param string $resource REQUIRED: The resource for which the policy is being specified.
 *                         See the operation documentation for the appropriate value for this field.
 */
function set_iam_policy_sample(string $resource): void
{
    // Create a client.
    $predictionServiceClient = new PredictionServiceClient();

    // Prepare the request message.
    $policy = new Policy();
    $request = (new SetIamPolicyRequest())
        ->setResource($resource)
        ->setPolicy($policy);

    // Call the API and handle any network failures.
    try {
        /** @var Policy $response */
        $response = $predictionServiceClient->setIamPolicy($request);
        printf('Response data: %s' . PHP_EOL, $response->serializeToJsonString());
    } catch (ApiException $ex) {
        printf('Call failed with message: %s' . PHP_EOL, $ex->getMessage());
    }
}

/**
 * Helper to execute the sample.
 *
 * This sample 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.
 *  - It may require specifying regional endpoints when creating the service client,
 *    please see the apiEndpoint client configuration option for more details.
 */
function callSample(): void
{
    $resource = '[RESOURCE]';

    set_iam_policy_sample($resource);
}

testIamPermissions

Returns permissions that a caller has on the specified resource. If the resource does not exist, this will return an empty set of permissions, not a NOT_FOUND error.

Note: This operation is designed to be used for building permission-aware UIs and command-line tools, not for authorization checking. This operation may "fail open" without warning.

Parameters
Name	Description
`resource`	`string` REQUIRED: The resource for which the policy detail is being requested. See the operation documentation for the appropriate value for this field.
`permissions`	`string[]` The set of permissions to check for the `resource`. Permissions with wildcards (such as '' or 'storage.') are not allowed. For more information see IAM Overview.
`optionalArgs`	`array` Optional.
`↳ retrySettings`	`RetrySettings\|array` Retry settings to use for this call. Can be a Google\ApiCore\RetrySettings object, or an associative array of retry settings parameters. See the documentation on Google\ApiCore\RetrySettings for example usage.

Returns
Type	Description
`Google\Cloud\Iam\V1\TestIamPermissionsResponse`

Example

use Google\ApiCore\ApiException;
use Google\Cloud\AIPlatform\V1\Client\PredictionServiceClient;
use Google\Cloud\Iam\V1\TestIamPermissionsRequest;
use Google\Cloud\Iam\V1\TestIamPermissionsResponse;

/**
 * @param string $resource           REQUIRED: The resource for which the policy detail is being requested.
 *                                   See the operation documentation for the appropriate value for this field.
 * @param string $permissionsElement The set of permissions to check for the `resource`. Permissions with
 *                                   wildcards (such as '*' or 'storage.*') are not allowed. For more
 *                                   information see
 *                                   [IAM Overview](https://cloud.google.com/iam/docs/overview#permissions).
 */
function test_iam_permissions_sample(string $resource, string $permissionsElement): void
{
    // Create a client.
    $predictionServiceClient = new PredictionServiceClient();

    // Prepare the request message.
    $permissions = [$permissionsElement,];
    $request = (new TestIamPermissionsRequest())
        ->setResource($resource)
        ->setPermissions($permissions);

    // Call the API and handle any network failures.
    try {
        /** @var TestIamPermissionsResponse $response */
        $response = $predictionServiceClient->testIamPermissions($request);
        printf('Response data: %s' . PHP_EOL, $response->serializeToJsonString());
    } catch (ApiException $ex) {
        printf('Call failed with message: %s' . PHP_EOL, $ex->getMessage());
    }
}

/**
 * Helper to execute the sample.
 *
 * This sample 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.
 *  - It may require specifying regional endpoints when creating the service client,
 *    please see the apiEndpoint client configuration option for more details.
 */
function callSample(): void
{
    $resource = '[RESOURCE]';
    $permissionsElement = '[PERMISSIONS]';

    test_iam_permissions_sample($resource, $permissionsElement);
}

static::endpointName

Formats a string containing the fully-qualified path to represent a endpoint resource.

Parameters
Name	Description
`project`	`string`
`location`	`string`
`endpoint`	`string`

Returns
Type	Description
`string`	The formatted endpoint resource.

static::projectLocationEndpointName

Formats a string containing the fully-qualified path to represent a project_location_endpoint resource.

Parameters
Name	Description
`project`	`string`
`location`	`string`
`endpoint`	`string`

Returns
Type	Description
`string`	The formatted project_location_endpoint resource.

static::projectLocationPublisherModelName

Formats a string containing the fully-qualified path to represent a project_location_publisher_model resource.

Parameters
Name	Description
`project`	`string`
`location`	`string`
`publisher`	`string`
`model`	`string`

Returns
Type	Description
`string`	The formatted project_location_publisher_model resource.

static::parseName

Parses a formatted name string and returns an associative array of the components in the name.

The following name formats are supported: Template: Pattern

endpoint: projects/{project}/locations/{location}/endpoints/{endpoint}
projectLocationEndpoint: projects/{project}/locations/{location}/endpoints/{endpoint}
projectLocationPublisherModel: projects/{project}/locations/{location}/publishers/{publisher}/models/{model}

The optional $template argument can be supplied to specify a particular pattern, and must match one of the templates listed above. If no $template argument is provided, or if the $template argument does not match one of the templates listed, then parseName will check each of the supported templates, and return the first match.

Parameters
Name	Description
`formattedName`	`string` The formatted name string
`template`	`string` Optional name of template to match

Returns
Type	Description
`array`	An associative array from name component IDs to component values.

Constants

SERVICE_NAME

Value: 'google.cloud.aiplatform.v1.PredictionService'

The name of the service.

SERVICE_ADDRESS

Value: 'aiplatform.googleapis.com'

The default address of the service.

DEFAULT_SERVICE_PORT

Value: 443

The default port of the service.

CODEGEN_NAME

Value: 'gapic'

The name of the code generator, to be included in the agent header.