Google Cloud Ai Platform V1 Client - Class PredictionServiceClient (1.13.0)

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.

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.

Namespace

Google \ Cloud \ AIPlatform \ V1 \ Client

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 to a gRPC model server for Vertex first-party products and frameworks.

The async variant is PredictionServiceClient::directPredictAsync() .

Parameters
Name	Description
`request`	`Google\Cloud\AIPlatform\V1\DirectPredictRequest` A request to house fields associated with the call.
`callOptions`	`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\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 unary online prediction request to a gRPC model server for custom containers.

The async variant is PredictionServiceClient::directRawPredictAsync() .

Parameters
Name	Description
`request`	`Google\Cloud\AIPlatform\V1\DirectRawPredictRequest` A request to house fields associated with the call.
`callOptions`	`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\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.

The async variant is PredictionServiceClient::explainAsync() .

Parameters
Name	Description
`request`	`Google\Cloud\AIPlatform\V1\ExplainRequest` A request to house fields associated with the call.
`callOptions`	`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\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);
}

generateContent

Generate content with multimodal inputs.

The async variant is PredictionServiceClient::generateContentAsync() .

Parameters
Name	Description
`request`	`Google\Cloud\AIPlatform\V1\GenerateContentRequest` A request to house fields associated with the call.
`callOptions`	`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\AIPlatform\V1\GenerateContentResponse`

Example

use Google\ApiCore\ApiException;
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 fully qualified name of the publisher model or tuned model
 *                      endpoint to use.
 *
 *                      Publisher model format:
 *                      `projects/{project}/locations/{location}/publishers/&#42;/models/*`
 *
 *                      Tuned model endpoint format:
 *                      `projects/{project}/locations/{location}/endpoints/{endpoint}`
 */
function 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 GenerateContentResponse $response */
        $response = $predictionServiceClient->generateContent($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
{
    $model = '[MODEL]';

    generate_content_sample($model);
}

predict

Perform an online prediction.

The async variant is PredictionServiceClient::predictAsync() .

Parameters
Name	Description
`request`	`Google\Cloud\AIPlatform\V1\PredictRequest` A request to house fields associated with the call.
`callOptions`	`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\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.

The async variant is PredictionServiceClient::rawPredictAsync() .

Parameters
Name	Description
`request`	`Google\Cloud\AIPlatform\V1\RawPredictRequest` A request to house fields associated with the call.
`callOptions`	`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\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
`request`	`Google\Cloud\AIPlatform\V1\StreamingPredictRequest` A request to house fields associated with the call.
`callOptions`	`array` Optional.
`↳ 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);
}

streamDirectPredict

Perform a streaming online prediction request to a gRPC model server for Vertex first-party products and frameworks.

Parameters
Name	Description
`callOptions`	`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\StreamDirectPredictRequest;
use Google\Cloud\AIPlatform\V1\StreamDirectPredictResponse;

/**
 * @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 stream_direct_predict_sample(string $formattedEndpoint): void
{
    // Create a client.
    $predictionServiceClient = new PredictionServiceClient();

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

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

        /** @var StreamDirectPredictResponse $element */
        foreach ($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]');

    stream_direct_predict_sample($formattedEndpoint);
}

streamDirectRawPredict

Perform a streaming online prediction request to a gRPC model server for custom containers.

Parameters
Name	Description
`callOptions`	`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\StreamDirectRawPredictRequest;
use Google\Cloud\AIPlatform\V1\StreamDirectRawPredictResponse;

/**
 * @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 stream_direct_raw_predict_sample(string $formattedEndpoint): void
{
    // Create a client.
    $predictionServiceClient = new PredictionServiceClient();

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

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

        /** @var StreamDirectRawPredictResponse $element */
        foreach ($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]');

    stream_direct_raw_predict_sample($formattedEndpoint);
}

streamGenerateContent

Generate content with multimodal inputs with streaming support.

Parameters
Name	Description
`request`	`Google\Cloud\AIPlatform\V1\GenerateContentRequest` A request to house fields associated with the call.
`callOptions`	`array` Optional.
`↳ 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 fully qualified name of the publisher model or tuned model
 *                      endpoint to use.
 *
 *                      Publisher model format:
 *                      `projects/{project}/locations/{location}/publishers/&#42;/models/*`
 *
 *                      Tuned model endpoint format:
 *                      `projects/{project}/locations/{location}/endpoints/{endpoint}`
 */
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);
}

streamRawPredict

Perform a streaming online prediction with an arbitrary HTTP payload.

Parameters
Name	Description
`request`	`Google\Cloud\AIPlatform\V1\StreamRawPredictRequest` A request to house fields associated with the call.
`callOptions`	`array` Optional.
`↳ 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\Api\HttpBody;
use Google\Cloud\AIPlatform\V1\Client\PredictionServiceClient;
use Google\Cloud\AIPlatform\V1\StreamRawPredictRequest;

/**
 * @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 stream_raw_predict_sample(string $formattedEndpoint): void
{
    // Create a client.
    $predictionServiceClient = new PredictionServiceClient();

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

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

        /** @var HttpBody $element */
        foreach ($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]');

    stream_raw_predict_sample($formattedEndpoint);
}

streamingPredict

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

Parameters
Name	Description
`callOptions`	`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
`callOptions`	`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.

The async variant is PredictionServiceClient::getLocationAsync() .

Parameters
Name	Description
`request`	`Google\Cloud\Location\GetLocationRequest` A request to house fields associated with the call.
`callOptions`	`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\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.

The async variant is PredictionServiceClient::listLocationsAsync() .

Parameters
Name	Description
`request`	`Google\Cloud\Location\ListLocationsRequest` A request to house fields associated with the call.
`callOptions`	`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\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.

The async variant is PredictionServiceClient::getIamPolicyAsync() .

Parameters
Name	Description
`request`	`Google\Cloud\Iam\V1\GetIamPolicyRequest` A request to house fields associated with the call.
`callOptions`	`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\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.

The async variant is PredictionServiceClient::setIamPolicyAsync() .

Parameters
Name	Description
`request`	`Google\Cloud\Iam\V1\SetIamPolicyRequest` A request to house fields associated with the call.
`callOptions`	`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\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.

The async variant is PredictionServiceClient::testIamPermissionsAsync() .

Parameters
Name	Description
`request`	`Google\Cloud\Iam\V1\TestIamPermissionsRequest` A request to house fields associated with the call.
`callOptions`	`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);
}

directPredictAsync

Parameters
Name	Description
`request`	`Google\Cloud\AIPlatform\V1\DirectPredictRequest`
`optionalArgs`	`array`

Returns
Type	Description
`GuzzleHttp\Promise\PromiseInterface<Google\Cloud\AIPlatform\V1\DirectPredictResponse>`

directRawPredictAsync

Parameters
Name	Description
`request`	`Google\Cloud\AIPlatform\V1\DirectRawPredictRequest`
`optionalArgs`	`array`

Returns
Type	Description
`GuzzleHttp\Promise\PromiseInterface<Google\Cloud\AIPlatform\V1\DirectRawPredictResponse>`

explainAsync

Parameters
Name	Description
`request`	`Google\Cloud\AIPlatform\V1\ExplainRequest`
`optionalArgs`	`array`

Returns
Type	Description
`GuzzleHttp\Promise\PromiseInterface<Google\Cloud\AIPlatform\V1\ExplainResponse>`

generateContentAsync

Parameters
Name	Description
`request`	`Google\Cloud\AIPlatform\V1\GenerateContentRequest`
`optionalArgs`	`array`

Returns
Type	Description
`GuzzleHttp\Promise\PromiseInterface<Google\Cloud\AIPlatform\V1\GenerateContentResponse>`

predictAsync

Parameters
Name	Description
`request`	`Google\Cloud\AIPlatform\V1\PredictRequest`
`optionalArgs`	`array`

Returns
Type	Description
`GuzzleHttp\Promise\PromiseInterface<Google\Cloud\AIPlatform\V1\PredictResponse>`

rawPredictAsync

Parameters
Name	Description
`request`	`Google\Cloud\AIPlatform\V1\RawPredictRequest`
`optionalArgs`	`array`

Returns
Type	Description
`GuzzleHttp\Promise\PromiseInterface<Google\Api\HttpBody>`

getLocationAsync

Parameters
Name	Description
`request`	`Google\Cloud\Location\GetLocationRequest`
`optionalArgs`	`array`

Returns
Type	Description
`GuzzleHttp\Promise\PromiseInterface<Google\Cloud\Location\Location>`

listLocationsAsync

Parameters
Name	Description
`request`	`Google\Cloud\Location\ListLocationsRequest`
`optionalArgs`	`array`

Returns
Type	Description
`GuzzleHttp\Promise\PromiseInterface<Google\ApiCore\PagedListResponse>`

getIamPolicyAsync

Parameters
Name	Description
`request`	`Google\Cloud\Iam\V1\GetIamPolicyRequest`
`optionalArgs`	`array`

Returns
Type	Description
`GuzzleHttp\Promise\PromiseInterface<Google\Cloud\Iam\V1\Policy>`

setIamPolicyAsync

Parameters
Name	Description
`request`	`Google\Cloud\Iam\V1\SetIamPolicyRequest`
`optionalArgs`	`array`

Returns
Type	Description
`GuzzleHttp\Promise\PromiseInterface<Google\Cloud\Iam\V1\Policy>`

testIamPermissionsAsync

Parameters
Name	Description
`request`	`Google\Cloud\Iam\V1\TestIamPermissionsRequest`
`optionalArgs`	`array`

Returns
Type	Description
`GuzzleHttp\Promise\PromiseInterface<Google\Cloud\Iam\V1\TestIamPermissionsResponse>`

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::ragCorpusName

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

Parameters
Name	Description
`project`	`string`
`location`	`string`
`ragCorpus`	`string`

Returns
Type	Description
`string`	The formatted rag_corpus 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}
ragCorpus: projects/{project}/locations/{location}/ragCorpora/{rag_corpus}

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.