Cloud AI Platform v1 API - Class PredictionService.PredictionServiceClient (2.20.0)

public class PredictionService.PredictionServiceClient : ClientBase<PredictionService.PredictionServiceClient>

Reference documentation and code samples for the Cloud AI Platform v1 API class PredictionService.PredictionServiceClient.

Client for PredictionService

Inheritance

object > ClientBase > ClientBasePredictionServicePredictionServiceClient > PredictionService.PredictionServiceClient

Namespace

Google.Cloud.AIPlatform.V1

Assembly

Google.Cloud.AIPlatform.V1.dll

Constructors

PredictionServiceClient()

protected PredictionServiceClient()

Protected parameterless constructor to allow creation of test doubles.

PredictionServiceClient(CallInvoker)

public PredictionServiceClient(CallInvoker callInvoker)

Creates a new client for PredictionService that uses a custom CallInvoker.

Parameter
NameDescription
callInvokerCallInvoker

The callInvoker to use to make remote calls.

PredictionServiceClient(ChannelBase)

public PredictionServiceClient(ChannelBase channel)

Creates a new client for PredictionService

Parameter
NameDescription
channelChannelBase

The channel to use to make remote calls.

PredictionServiceClient(ClientBaseConfiguration)

protected PredictionServiceClient(ClientBase.ClientBaseConfiguration configuration)

Protected constructor to allow creation of configured clients.

Parameter
NameDescription
configurationClientBaseClientBaseConfiguration

The client configuration.

Methods

CreateIAMPolicyClient()

public virtual IAMPolicy.IAMPolicyClient CreateIAMPolicyClient()

Creates a new instance of IAMPolicy.IAMPolicyClient using the same call invoker as this client.

Returns
TypeDescription
IAMPolicyIAMPolicyClient

A new IAMPolicy.IAMPolicyClient for the same target as this client.

CreateLocationsClient()

public virtual Locations.LocationsClient CreateLocationsClient()

Creates a new instance of Locations.LocationsClient using the same call invoker as this client.

Returns
TypeDescription
LocationsLocationsClient

A new Locations.LocationsClient for the same target as this client.

Explain(ExplainRequest, CallOptions)

public virtual ExplainResponse Explain(ExplainRequest request, CallOptions options)

Perform an online explanation.

If [deployed_model_id][google.cloud.aiplatform.v1.ExplainRequest.deployed_model_id] is specified, the corresponding DeployModel must have [explanation_spec][google.cloud.aiplatform.v1.DeployedModel.explanation_spec] populated. If [deployed_model_id][google.cloud.aiplatform.v1.ExplainRequest.deployed_model_id] is not specified, all DeployedModels must have [explanation_spec][google.cloud.aiplatform.v1.DeployedModel.explanation_spec] populated.

Parameters
NameDescription
requestExplainRequest

The request to send to the server.

optionsCallOptions

The options for the call.

Returns
TypeDescription
ExplainResponse

The response received from the server.

Explain(ExplainRequest, Metadata, DateTime?, CancellationToken)

public virtual ExplainResponse Explain(ExplainRequest request, Metadata headers = null, DateTime? deadline = null, CancellationToken cancellationToken = default)

Perform an online explanation.

If [deployed_model_id][google.cloud.aiplatform.v1.ExplainRequest.deployed_model_id] is specified, the corresponding DeployModel must have [explanation_spec][google.cloud.aiplatform.v1.DeployedModel.explanation_spec] populated. If [deployed_model_id][google.cloud.aiplatform.v1.ExplainRequest.deployed_model_id] is not specified, all DeployedModels must have [explanation_spec][google.cloud.aiplatform.v1.DeployedModel.explanation_spec] populated.

Parameters
NameDescription
requestExplainRequest

The request to send to the server.

headersMetadata

The initial metadata to send with the call. This parameter is optional.

deadlineDateTime

An optional deadline for the call. The call will be cancelled if deadline is hit.

cancellationTokenCancellationToken

An optional token for canceling the call.

Returns
TypeDescription
ExplainResponse

The response received from the server.

ExplainAsync(ExplainRequest, CallOptions)

public virtual AsyncUnaryCall<ExplainResponse> ExplainAsync(ExplainRequest request, CallOptions options)

Perform an online explanation.

If [deployed_model_id][google.cloud.aiplatform.v1.ExplainRequest.deployed_model_id] is specified, the corresponding DeployModel must have [explanation_spec][google.cloud.aiplatform.v1.DeployedModel.explanation_spec] populated. If [deployed_model_id][google.cloud.aiplatform.v1.ExplainRequest.deployed_model_id] is not specified, all DeployedModels must have [explanation_spec][google.cloud.aiplatform.v1.DeployedModel.explanation_spec] populated.

Parameters
NameDescription
requestExplainRequest

The request to send to the server.

optionsCallOptions

The options for the call.

Returns
TypeDescription
AsyncUnaryCallExplainResponse

The call object.

ExplainAsync(ExplainRequest, Metadata, DateTime?, CancellationToken)

public virtual AsyncUnaryCall<ExplainResponse> ExplainAsync(ExplainRequest request, Metadata headers = null, DateTime? deadline = null, CancellationToken cancellationToken = default)

Perform an online explanation.

If [deployed_model_id][google.cloud.aiplatform.v1.ExplainRequest.deployed_model_id] is specified, the corresponding DeployModel must have [explanation_spec][google.cloud.aiplatform.v1.DeployedModel.explanation_spec] populated. If [deployed_model_id][google.cloud.aiplatform.v1.ExplainRequest.deployed_model_id] is not specified, all DeployedModels must have [explanation_spec][google.cloud.aiplatform.v1.DeployedModel.explanation_spec] populated.

Parameters
NameDescription
requestExplainRequest

The request to send to the server.

headersMetadata

The initial metadata to send with the call. This parameter is optional.

deadlineDateTime

An optional deadline for the call. The call will be cancelled if deadline is hit.

cancellationTokenCancellationToken

An optional token for canceling the call.

Returns
TypeDescription
AsyncUnaryCallExplainResponse

The call object.

NewInstance(ClientBaseConfiguration)

protected override PredictionService.PredictionServiceClient NewInstance(ClientBase.ClientBaseConfiguration configuration)

Creates a new instance of client from given ClientBaseConfiguration.

Parameter
NameDescription
configurationClientBaseClientBaseConfiguration
Returns
TypeDescription
PredictionServicePredictionServiceClient
Overrides

Predict(PredictRequest, CallOptions)

public virtual PredictResponse Predict(PredictRequest request, CallOptions options)

Perform an online prediction.

Parameters
NameDescription
requestPredictRequest

The request to send to the server.

optionsCallOptions

The options for the call.

Returns
TypeDescription
PredictResponse

The response received from the server.

Predict(PredictRequest, Metadata, DateTime?, CancellationToken)

public virtual PredictResponse Predict(PredictRequest request, Metadata headers = null, DateTime? deadline = null, CancellationToken cancellationToken = default)

Perform an online prediction.

Parameters
NameDescription
requestPredictRequest

The request to send to the server.

headersMetadata

The initial metadata to send with the call. This parameter is optional.

deadlineDateTime

An optional deadline for the call. The call will be cancelled if deadline is hit.

cancellationTokenCancellationToken

An optional token for canceling the call.

Returns
TypeDescription
PredictResponse

The response received from the server.

PredictAsync(PredictRequest, CallOptions)

public virtual AsyncUnaryCall<PredictResponse> PredictAsync(PredictRequest request, CallOptions options)

Perform an online prediction.

Parameters
NameDescription
requestPredictRequest

The request to send to the server.

optionsCallOptions

The options for the call.

Returns
TypeDescription
AsyncUnaryCallPredictResponse

The call object.

PredictAsync(PredictRequest, Metadata, DateTime?, CancellationToken)

public virtual AsyncUnaryCall<PredictResponse> PredictAsync(PredictRequest request, Metadata headers = null, DateTime? deadline = null, CancellationToken cancellationToken = default)

Perform an online prediction.

Parameters
NameDescription
requestPredictRequest

The request to send to the server.

headersMetadata

The initial metadata to send with the call. This parameter is optional.

deadlineDateTime

An optional deadline for the call. The call will be cancelled if deadline is hit.

cancellationTokenCancellationToken

An optional token for canceling the call.

Returns
TypeDescription
AsyncUnaryCallPredictResponse

The call object.

RawPredict(RawPredictRequest, CallOptions)

public virtual HttpBody RawPredict(RawPredictRequest request, CallOptions options)

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][google.cloud.aiplatform.v1.Endpoint] that served this prediction.

  • X-Vertex-AI-Deployed-Model-Id: ID of the Endpoint's [DeployedModel][google.cloud.aiplatform.v1.DeployedModel] that served this prediction.

Parameters
NameDescription
requestRawPredictRequest

The request to send to the server.

optionsCallOptions

The options for the call.

Returns
TypeDescription
HttpBody

The response received from the server.

RawPredict(RawPredictRequest, Metadata, DateTime?, CancellationToken)

public virtual HttpBody RawPredict(RawPredictRequest request, Metadata headers = null, DateTime? deadline = null, CancellationToken cancellationToken = default)

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][google.cloud.aiplatform.v1.Endpoint] that served this prediction.

  • X-Vertex-AI-Deployed-Model-Id: ID of the Endpoint's [DeployedModel][google.cloud.aiplatform.v1.DeployedModel] that served this prediction.

Parameters
NameDescription
requestRawPredictRequest

The request to send to the server.

headersMetadata

The initial metadata to send with the call. This parameter is optional.

deadlineDateTime

An optional deadline for the call. The call will be cancelled if deadline is hit.

cancellationTokenCancellationToken

An optional token for canceling the call.

Returns
TypeDescription
HttpBody

The response received from the server.

RawPredictAsync(RawPredictRequest, CallOptions)

public virtual AsyncUnaryCall<HttpBody> RawPredictAsync(RawPredictRequest request, CallOptions options)

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][google.cloud.aiplatform.v1.Endpoint] that served this prediction.

  • X-Vertex-AI-Deployed-Model-Id: ID of the Endpoint's [DeployedModel][google.cloud.aiplatform.v1.DeployedModel] that served this prediction.

Parameters
NameDescription
requestRawPredictRequest

The request to send to the server.

optionsCallOptions

The options for the call.

Returns
TypeDescription
AsyncUnaryCallHttpBody

The call object.

RawPredictAsync(RawPredictRequest, Metadata, DateTime?, CancellationToken)

public virtual AsyncUnaryCall<HttpBody> RawPredictAsync(RawPredictRequest request, Metadata headers = null, DateTime? deadline = null, CancellationToken cancellationToken = default)

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][google.cloud.aiplatform.v1.Endpoint] that served this prediction.

  • X-Vertex-AI-Deployed-Model-Id: ID of the Endpoint's [DeployedModel][google.cloud.aiplatform.v1.DeployedModel] that served this prediction.

Parameters
NameDescription
requestRawPredictRequest

The request to send to the server.

headersMetadata

The initial metadata to send with the call. This parameter is optional.

deadlineDateTime

An optional deadline for the call. The call will be cancelled if deadline is hit.

cancellationTokenCancellationToken

An optional token for canceling the call.

Returns
TypeDescription
AsyncUnaryCallHttpBody

The call object.

ServerStreamingPredict(StreamingPredictRequest, CallOptions)

public virtual AsyncServerStreamingCall<StreamingPredictResponse> ServerStreamingPredict(StreamingPredictRequest request, CallOptions options)

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

Parameters
NameDescription
requestStreamingPredictRequest

The request to send to the server.

optionsCallOptions

The options for the call.

Returns
TypeDescription
AsyncServerStreamingCallStreamingPredictResponse

The call object.

ServerStreamingPredict(StreamingPredictRequest, Metadata, DateTime?, CancellationToken)

public virtual AsyncServerStreamingCall<StreamingPredictResponse> ServerStreamingPredict(StreamingPredictRequest request, Metadata headers = null, DateTime? deadline = null, CancellationToken cancellationToken = default)

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

Parameters
NameDescription
requestStreamingPredictRequest

The request to send to the server.

headersMetadata

The initial metadata to send with the call. This parameter is optional.

deadlineDateTime

An optional deadline for the call. The call will be cancelled if deadline is hit.

cancellationTokenCancellationToken

An optional token for canceling the call.

Returns
TypeDescription
AsyncServerStreamingCallStreamingPredictResponse

The call object.