Vertex AI v1beta1 API - Class PredictionService.PredictionServiceClient (1.0.0-beta55) 

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

Reference documentation and code samples for the Vertex AI v1beta1 API class PredictionService.PredictionServiceClient.

Client for PredictionService

Inheritance

object > ClientBase > ClientBasePredictionServicePredictionServiceClient > PredictionService.PredictionServiceClient

Namespace

Google.Cloud.AIPlatform.V1Beta1

Assembly

Google.Cloud.AIPlatform.V1Beta1.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
Name Description
callInvoker CallInvoker

The callInvoker to use to make remote calls.

PredictionServiceClient(ChannelBase)

public PredictionServiceClient(ChannelBase channel)

Creates a new client for PredictionService

Parameter
Name Description
channel ChannelBase

The channel to use to make remote calls.

PredictionServiceClient(ClientBaseConfiguration)

protected PredictionServiceClient(ClientBase.ClientBaseConfiguration configuration)

Protected constructor to allow creation of configured clients.

Parameter
Name Description
configuration ClientBaseClientBaseConfiguration

The client configuration.

Methods

ChatCompletions(ChatCompletionsRequest, CallOptions)

public virtual AsyncServerStreamingCall<HttpBody> ChatCompletions(ChatCompletionsRequest request, CallOptions options)

Exposes an OpenAI-compatible endpoint for chat completions.

Parameters
Name Description
request ChatCompletionsRequest

The request to send to the server.
options CallOptions

The options for the call.
Returns
Type Description
AsyncServerStreamingCallHttpBody

The call object.

ChatCompletions(ChatCompletionsRequest, Metadata, DateTime?, CancellationToken)

public virtual AsyncServerStreamingCall<HttpBody> ChatCompletions(ChatCompletionsRequest request, Metadata headers = null, DateTime? deadline = null, CancellationToken cancellationToken = default)

Exposes an OpenAI-compatible endpoint for chat completions.

Parameters
Name Description
request ChatCompletionsRequest

The request to send to the server.
headers Metadata

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

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

An optional token for canceling the call.
Returns
Type Description
AsyncServerStreamingCallHttpBody

The call object.

CountTokens(CountTokensRequest, CallOptions)

public virtual CountTokensResponse CountTokens(CountTokensRequest request, CallOptions options)

Perform a token counting.

Parameters
Name Description
request CountTokensRequest

The request to send to the server.
options CallOptions

The options for the call.
Returns
Type Description
CountTokensResponse

The response received from the server.

CountTokens(CountTokensRequest, Metadata, DateTime?, CancellationToken)

public virtual CountTokensResponse CountTokens(CountTokensRequest request, Metadata headers = null, DateTime? deadline = null, CancellationToken cancellationToken = default)

Perform a token counting.

Parameters
Name Description
request CountTokensRequest

The request to send to the server.
headers Metadata

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

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

An optional token for canceling the call.
Returns
Type Description
CountTokensResponse

The response received from the server.

CountTokensAsync(CountTokensRequest, CallOptions)

public virtual AsyncUnaryCall<CountTokensResponse> CountTokensAsync(CountTokensRequest request, CallOptions options)

Perform a token counting.

Parameters
Name Description
request CountTokensRequest

The request to send to the server.
options CallOptions

The options for the call.
Returns
Type Description
AsyncUnaryCallCountTokensResponse

The call object.

CountTokensAsync(CountTokensRequest, Metadata, DateTime?, CancellationToken)

public virtual AsyncUnaryCall<CountTokensResponse> CountTokensAsync(CountTokensRequest request, Metadata headers = null, DateTime? deadline = null, CancellationToken cancellationToken = default)

Perform a token counting.

Parameters
Name Description
request CountTokensRequest

The request to send to the server.
headers Metadata

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

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

An optional token for canceling the call.
Returns
Type Description
AsyncUnaryCallCountTokensResponse

The call object.

CreateIAMPolicyClient()

public virtual IAMPolicy.IAMPolicyClient CreateIAMPolicyClient()

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

Returns
Type Description
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
Type Description
LocationsLocationsClient

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

DirectPredict(DirectPredictRequest, CallOptions)

public virtual DirectPredictResponse DirectPredict(DirectPredictRequest request, CallOptions options)

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

Parameters
Name Description
request DirectPredictRequest

The request to send to the server.
options CallOptions

The options for the call.
Returns
Type Description
DirectPredictResponse

The response received from the server.

DirectPredict(DirectPredictRequest, Metadata, DateTime?, CancellationToken)

public virtual DirectPredictResponse DirectPredict(DirectPredictRequest request, Metadata headers = null, DateTime? deadline = null, CancellationToken cancellationToken = default)

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

Parameters
Name Description
request DirectPredictRequest

The request to send to the server.
headers Metadata

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

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

An optional token for canceling the call.
Returns
Type Description
DirectPredictResponse

The response received from the server.

DirectPredictAsync(DirectPredictRequest, CallOptions)

public virtual AsyncUnaryCall<DirectPredictResponse> DirectPredictAsync(DirectPredictRequest request, CallOptions options)

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

Parameters
Name Description
request DirectPredictRequest

The request to send to the server.
options CallOptions

The options for the call.
Returns
Type Description
AsyncUnaryCallDirectPredictResponse

The call object.

DirectPredictAsync(DirectPredictRequest, Metadata, DateTime?, CancellationToken)

public virtual AsyncUnaryCall<DirectPredictResponse> DirectPredictAsync(DirectPredictRequest request, Metadata headers = null, DateTime? deadline = null, CancellationToken cancellationToken = default)

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

Parameters
Name Description
request DirectPredictRequest

The request to send to the server.
headers Metadata

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

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

An optional token for canceling the call.
Returns
Type Description
AsyncUnaryCallDirectPredictResponse

The call object.

DirectRawPredict(DirectRawPredictRequest, CallOptions)

public virtual DirectRawPredictResponse DirectRawPredict(DirectRawPredictRequest request, CallOptions options)

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

Parameters
Name Description
request DirectRawPredictRequest

The request to send to the server.
options CallOptions

The options for the call.
Returns
Type Description
DirectRawPredictResponse

The response received from the server.

DirectRawPredict(DirectRawPredictRequest, Metadata, DateTime?, CancellationToken)

public virtual DirectRawPredictResponse DirectRawPredict(DirectRawPredictRequest request, Metadata headers = null, DateTime? deadline = null, CancellationToken cancellationToken = default)

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

Parameters
Name Description
request DirectRawPredictRequest

The request to send to the server.
headers Metadata

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

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

An optional token for canceling the call.
Returns
Type Description
DirectRawPredictResponse

The response received from the server.

DirectRawPredictAsync(DirectRawPredictRequest, CallOptions)

public virtual AsyncUnaryCall<DirectRawPredictResponse> DirectRawPredictAsync(DirectRawPredictRequest request, CallOptions options)

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

Parameters
Name Description
request DirectRawPredictRequest

The request to send to the server.
options CallOptions

The options for the call.
Returns
Type Description
AsyncUnaryCallDirectRawPredictResponse

The call object.

DirectRawPredictAsync(DirectRawPredictRequest, Metadata, DateTime?, CancellationToken)

public virtual AsyncUnaryCall<DirectRawPredictResponse> DirectRawPredictAsync(DirectRawPredictRequest request, Metadata headers = null, DateTime? deadline = null, CancellationToken cancellationToken = default)

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

Parameters
Name Description
request DirectRawPredictRequest

The request to send to the server.
headers Metadata

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

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

An optional token for canceling the call.
Returns
Type Description
AsyncUnaryCallDirectRawPredictResponse

The call object.

Explain(ExplainRequest, CallOptions)

public virtual ExplainResponse Explain(ExplainRequest request, CallOptions options)

Perform an online explanation.

If [deployed_model_id][google.cloud.aiplatform.v1beta1.ExplainRequest.deployed_model_id] is specified, the corresponding DeployModel must have [explanation_spec][google.cloud.aiplatform.v1beta1.DeployedModel.explanation_spec] populated. If [deployed_model_id][google.cloud.aiplatform.v1beta1.ExplainRequest.deployed_model_id] is not specified, all DeployedModels must have [explanation_spec][google.cloud.aiplatform.v1beta1.DeployedModel.explanation_spec] populated.

Parameters
Name Description
request ExplainRequest

The request to send to the server.
options CallOptions

The options for the call.
Returns
Type Description
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.v1beta1.ExplainRequest.deployed_model_id] is specified, the corresponding DeployModel must have [explanation_spec][google.cloud.aiplatform.v1beta1.DeployedModel.explanation_spec] populated. If [deployed_model_id][google.cloud.aiplatform.v1beta1.ExplainRequest.deployed_model_id] is not specified, all DeployedModels must have [explanation_spec][google.cloud.aiplatform.v1beta1.DeployedModel.explanation_spec] populated.

Parameters
Name Description
request ExplainRequest

The request to send to the server.
headers Metadata

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

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

An optional token for canceling the call.
Returns
Type Description
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.v1beta1.ExplainRequest.deployed_model_id] is specified, the corresponding DeployModel must have [explanation_spec][google.cloud.aiplatform.v1beta1.DeployedModel.explanation_spec] populated. If [deployed_model_id][google.cloud.aiplatform.v1beta1.ExplainRequest.deployed_model_id] is not specified, all DeployedModels must have [explanation_spec][google.cloud.aiplatform.v1beta1.DeployedModel.explanation_spec] populated.

Parameters
Name Description
request ExplainRequest

The request to send to the server.
options CallOptions

The options for the call.
Returns
Type Description
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.v1beta1.ExplainRequest.deployed_model_id] is specified, the corresponding DeployModel must have [explanation_spec][google.cloud.aiplatform.v1beta1.DeployedModel.explanation_spec] populated. If [deployed_model_id][google.cloud.aiplatform.v1beta1.ExplainRequest.deployed_model_id] is not specified, all DeployedModels must have [explanation_spec][google.cloud.aiplatform.v1beta1.DeployedModel.explanation_spec] populated.

Parameters
Name Description
request ExplainRequest

The request to send to the server.
headers Metadata

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

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

An optional token for canceling the call.
Returns
Type Description
AsyncUnaryCallExplainResponse

The call object.

GenerateContent(GenerateContentRequest, CallOptions)

public virtual GenerateContentResponse GenerateContent(GenerateContentRequest request, CallOptions options)

Generate content with multimodal inputs.

Parameters
Name Description
request GenerateContentRequest

The request to send to the server.
options CallOptions

The options for the call.
Returns
Type Description
GenerateContentResponse

The response received from the server.

GenerateContent(GenerateContentRequest, Metadata, DateTime?, CancellationToken)

public virtual GenerateContentResponse GenerateContent(GenerateContentRequest request, Metadata headers = null, DateTime? deadline = null, CancellationToken cancellationToken = default)

Generate content with multimodal inputs.

Parameters
Name Description
request GenerateContentRequest

The request to send to the server.
headers Metadata

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

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

An optional token for canceling the call.
Returns
Type Description
GenerateContentResponse

The response received from the server.

GenerateContentAsync(GenerateContentRequest, CallOptions)

public virtual AsyncUnaryCall<GenerateContentResponse> GenerateContentAsync(GenerateContentRequest request, CallOptions options)

Generate content with multimodal inputs.

Parameters
Name Description
request GenerateContentRequest

The request to send to the server.
options CallOptions

The options for the call.
Returns
Type Description
AsyncUnaryCallGenerateContentResponse

The call object.

GenerateContentAsync(GenerateContentRequest, Metadata, DateTime?, CancellationToken)

public virtual AsyncUnaryCall<GenerateContentResponse> GenerateContentAsync(GenerateContentRequest request, Metadata headers = null, DateTime? deadline = null, CancellationToken cancellationToken = default)

Generate content with multimodal inputs.

Parameters
Name Description
request GenerateContentRequest

The request to send to the server.
headers Metadata

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

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

An optional token for canceling the call.
Returns
Type Description
AsyncUnaryCallGenerateContentResponse

The call object.

NewInstance(ClientBaseConfiguration)

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

Creates a new instance of client from given ClientBaseConfiguration.

Parameter
Name Description
configuration ClientBaseClientBaseConfiguration
Returns
Type Description
PredictionServicePredictionServiceClient
Overrides
Grpc.Core.ClientBase<Google.Cloud.AIPlatform.V1Beta1.PredictionService.PredictionServiceClient>.NewInstance(Grpc.Core.ClientBase.ClientBaseConfiguration)

Predict(PredictRequest, CallOptions)

public virtual PredictResponse Predict(PredictRequest request, CallOptions options)

Perform an online prediction.

Parameters
Name Description
request PredictRequest

The request to send to the server.
options CallOptions

The options for the call.
Returns
Type Description
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
Name Description
request PredictRequest

The request to send to the server.
headers Metadata

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

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

An optional token for canceling the call.
Returns
Type Description
PredictResponse

The response received from the server.

PredictAsync(PredictRequest, CallOptions)

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

Perform an online prediction.

Parameters
Name Description
request PredictRequest

The request to send to the server.
options CallOptions

The options for the call.
Returns
Type Description
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
Name Description
request PredictRequest

The request to send to the server.
headers Metadata

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

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

An optional token for canceling the call.
Returns
Type Description
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.v1beta1.Endpoint] that served this prediction.

  • X-Vertex-AI-Deployed-Model-Id: ID of the Endpoint's [DeployedModel][google.cloud.aiplatform.v1beta1.DeployedModel] that served this prediction.

Parameters
Name Description
request RawPredictRequest

The request to send to the server.
options CallOptions

The options for the call.
Returns
Type Description
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.v1beta1.Endpoint] that served this prediction.

  • X-Vertex-AI-Deployed-Model-Id: ID of the Endpoint's [DeployedModel][google.cloud.aiplatform.v1beta1.DeployedModel] that served this prediction.

Parameters
Name Description
request RawPredictRequest

The request to send to the server.
headers Metadata

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

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

An optional token for canceling the call.
Returns
Type Description
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.v1beta1.Endpoint] that served this prediction.

  • X-Vertex-AI-Deployed-Model-Id: ID of the Endpoint's [DeployedModel][google.cloud.aiplatform.v1beta1.DeployedModel] that served this prediction.

Parameters
Name Description
request RawPredictRequest

The request to send to the server.
options CallOptions

The options for the call.
Returns
Type Description
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.v1beta1.Endpoint] that served this prediction.

  • X-Vertex-AI-Deployed-Model-Id: ID of the Endpoint's [DeployedModel][google.cloud.aiplatform.v1beta1.DeployedModel] that served this prediction.

Parameters
Name Description
request RawPredictRequest

The request to send to the server.
headers Metadata

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

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

An optional token for canceling the call.
Returns
Type Description
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
Name Description
request StreamingPredictRequest

The request to send to the server.
options CallOptions

The options for the call.
Returns
Type Description
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
Name Description
request StreamingPredictRequest

The request to send to the server.
headers Metadata

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

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

An optional token for canceling the call.
Returns
Type Description
AsyncServerStreamingCallStreamingPredictResponse

The call object.

StreamDirectPredict(CallOptions)

public virtual AsyncDuplexStreamingCall<StreamDirectPredictRequest, StreamDirectPredictResponse> StreamDirectPredict(CallOptions options)

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

Parameter
Name Description
options CallOptions

The options for the call.
Returns
Type Description
AsyncDuplexStreamingCallStreamDirectPredictRequestStreamDirectPredictResponse

The call object.

StreamDirectPredict(Metadata, DateTime?, CancellationToken)

public virtual AsyncDuplexStreamingCall<StreamDirectPredictRequest, StreamDirectPredictResponse> StreamDirectPredict(Metadata headers = null, DateTime? deadline = null, CancellationToken cancellationToken = default)

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

Parameters
Name Description
headers Metadata

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

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

An optional token for canceling the call.
Returns
Type Description
AsyncDuplexStreamingCallStreamDirectPredictRequestStreamDirectPredictResponse

The call object.

StreamDirectRawPredict(CallOptions)

public virtual AsyncDuplexStreamingCall<StreamDirectRawPredictRequest, StreamDirectRawPredictResponse> StreamDirectRawPredict(CallOptions options)

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

Parameter
Name Description
options CallOptions

The options for the call.
Returns
Type Description
AsyncDuplexStreamingCallStreamDirectRawPredictRequestStreamDirectRawPredictResponse

The call object.

StreamDirectRawPredict(Metadata, DateTime?, CancellationToken)

public virtual AsyncDuplexStreamingCall<StreamDirectRawPredictRequest, StreamDirectRawPredictResponse> StreamDirectRawPredict(Metadata headers = null, DateTime? deadline = null, CancellationToken cancellationToken = default)

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

Parameters
Name Description
headers Metadata

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

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

An optional token for canceling the call.
Returns
Type Description
AsyncDuplexStreamingCallStreamDirectRawPredictRequestStreamDirectRawPredictResponse

The call object.

StreamGenerateContent(GenerateContentRequest, CallOptions)

public virtual AsyncServerStreamingCall<GenerateContentResponse> StreamGenerateContent(GenerateContentRequest request, CallOptions options)

Generate content with multimodal inputs with streaming support.

Parameters
Name Description
request GenerateContentRequest

The request to send to the server.
options CallOptions

The options for the call.
Returns
Type Description
AsyncServerStreamingCallGenerateContentResponse

The call object.

StreamGenerateContent(GenerateContentRequest, Metadata, DateTime?, CancellationToken)

public virtual AsyncServerStreamingCall<GenerateContentResponse> StreamGenerateContent(GenerateContentRequest request, Metadata headers = null, DateTime? deadline = null, CancellationToken cancellationToken = default)

Generate content with multimodal inputs with streaming support.

Parameters
Name Description
request GenerateContentRequest

The request to send to the server.
headers Metadata

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

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

An optional token for canceling the call.
Returns
Type Description
AsyncServerStreamingCallGenerateContentResponse

The call object.

StreamRawPredict(StreamRawPredictRequest, CallOptions)

public virtual AsyncServerStreamingCall<HttpBody> StreamRawPredict(StreamRawPredictRequest request, CallOptions options)

Perform a streaming online prediction with an arbitrary HTTP payload.

Parameters
Name Description
request StreamRawPredictRequest

The request to send to the server.
options CallOptions

The options for the call.
Returns
Type Description
AsyncServerStreamingCallHttpBody

The call object.

StreamRawPredict(StreamRawPredictRequest, Metadata, DateTime?, CancellationToken)

public virtual AsyncServerStreamingCall<HttpBody> StreamRawPredict(StreamRawPredictRequest request, Metadata headers = null, DateTime? deadline = null, CancellationToken cancellationToken = default)

Perform a streaming online prediction with an arbitrary HTTP payload.

Parameters
Name Description
request StreamRawPredictRequest

The request to send to the server.
headers Metadata

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

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

An optional token for canceling the call.
Returns
Type Description
AsyncServerStreamingCallHttpBody

The call object.

StreamingPredict(CallOptions)

public virtual AsyncDuplexStreamingCall<StreamingPredictRequest, StreamingPredictResponse> StreamingPredict(CallOptions options)

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

Parameter
Name Description
options CallOptions

The options for the call.
Returns
Type Description
AsyncDuplexStreamingCallStreamingPredictRequestStreamingPredictResponse

The call object.

StreamingPredict(Metadata, DateTime?, CancellationToken)

public virtual AsyncDuplexStreamingCall<StreamingPredictRequest, StreamingPredictResponse> StreamingPredict(Metadata headers = null, DateTime? deadline = null, CancellationToken cancellationToken = default)

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

Parameters
Name Description
headers Metadata

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

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

An optional token for canceling the call.
Returns
Type Description
AsyncDuplexStreamingCallStreamingPredictRequestStreamingPredictResponse

The call object.

StreamingRawPredict(CallOptions)

public virtual AsyncDuplexStreamingCall<StreamingRawPredictRequest, StreamingRawPredictResponse> StreamingRawPredict(CallOptions options)

Perform a streaming online prediction request through gRPC.

Parameter
Name Description
options CallOptions

The options for the call.
Returns
Type Description
AsyncDuplexStreamingCallStreamingRawPredictRequestStreamingRawPredictResponse

The call object.

StreamingRawPredict(Metadata, DateTime?, CancellationToken)

public virtual AsyncDuplexStreamingCall<StreamingRawPredictRequest, StreamingRawPredictResponse> StreamingRawPredict(Metadata headers = null, DateTime? deadline = null, CancellationToken cancellationToken = default)

Perform a streaming online prediction request through gRPC.

Parameters
Name Description
headers Metadata

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

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

An optional token for canceling the call.
Returns
Type Description
AsyncDuplexStreamingCallStreamingRawPredictRequestStreamingRawPredictResponse

The call object.