Cloud AI Platform v1 API - Class PredictionService.PredictionServiceBase (3.3.0)

[BindServiceMethod(typeof(PredictionService), "BindService")]
public abstract class PredictionService.PredictionServiceBase

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

Base class for server-side implementations of PredictionService

Inheritance

object > PredictionService.PredictionServiceBase

Namespace

Google.Cloud.AIPlatform.V1

Assembly

Google.Cloud.AIPlatform.V1.dll

Methods

DirectPredict(DirectPredictRequest, ServerCallContext)

public virtual Task<DirectPredictResponse> DirectPredict(DirectPredictRequest request, ServerCallContext context)

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 received from the client.

context ServerCallContext

The context of the server-side call handler being invoked.

Returns
Type Description
TaskDirectPredictResponse

The response to send back to the client (wrapped by a task).

DirectRawPredict(DirectRawPredictRequest, ServerCallContext)

public virtual Task<DirectRawPredictResponse> DirectRawPredict(DirectRawPredictRequest request, ServerCallContext context)

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

Parameters
Name Description
request DirectRawPredictRequest

The request received from the client.

context ServerCallContext

The context of the server-side call handler being invoked.

Returns
Type Description
TaskDirectRawPredictResponse

The response to send back to the client (wrapped by a task).

Explain(ExplainRequest, ServerCallContext)

public virtual Task<ExplainResponse> Explain(ExplainRequest request, ServerCallContext context)

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
Name Description
request ExplainRequest

The request received from the client.

context ServerCallContext

The context of the server-side call handler being invoked.

Returns
Type Description
TaskExplainResponse

The response to send back to the client (wrapped by a task).

GenerateContent(GenerateContentRequest, ServerCallContext)

public virtual Task<GenerateContentResponse> GenerateContent(GenerateContentRequest request, ServerCallContext context)

Generate content with multimodal inputs.

Parameters
Name Description
request GenerateContentRequest

The request received from the client.

context ServerCallContext

The context of the server-side call handler being invoked.

Returns
Type Description
TaskGenerateContentResponse

The response to send back to the client (wrapped by a task).

Predict(PredictRequest, ServerCallContext)

public virtual Task<PredictResponse> Predict(PredictRequest request, ServerCallContext context)

Perform an online prediction.

Parameters
Name Description
request PredictRequest

The request received from the client.

context ServerCallContext

The context of the server-side call handler being invoked.

Returns
Type Description
TaskPredictResponse

The response to send back to the client (wrapped by a task).

RawPredict(RawPredictRequest, ServerCallContext)

public virtual Task<HttpBody> RawPredict(RawPredictRequest request, ServerCallContext context)

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
Name Description
request RawPredictRequest

The request received from the client.

context ServerCallContext

The context of the server-side call handler being invoked.

Returns
Type Description
TaskHttpBody

The response to send back to the client (wrapped by a task).

ServerStreamingPredict(StreamingPredictRequest, IServerStreamWriter<StreamingPredictResponse>, ServerCallContext)

public virtual Task ServerStreamingPredict(StreamingPredictRequest request, IServerStreamWriter<StreamingPredictResponse> responseStream, ServerCallContext context)

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

Parameters
Name Description
request StreamingPredictRequest

The request received from the client.

responseStream IServerStreamWriterStreamingPredictResponse

Used for sending responses back to the client.

context ServerCallContext

The context of the server-side call handler being invoked.

Returns
Type Description
Task

A task indicating completion of the handler.

StreamDirectPredict(IAsyncStreamReader<StreamDirectPredictRequest>, IServerStreamWriter<StreamDirectPredictResponse>, ServerCallContext)

public virtual Task StreamDirectPredict(IAsyncStreamReader<StreamDirectPredictRequest> requestStream, IServerStreamWriter<StreamDirectPredictResponse> responseStream, ServerCallContext context)

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

Parameters
Name Description
requestStream IAsyncStreamReaderStreamDirectPredictRequest

Used for reading requests from the client.

responseStream IServerStreamWriterStreamDirectPredictResponse

Used for sending responses back to the client.

context ServerCallContext

The context of the server-side call handler being invoked.

Returns
Type Description
Task

A task indicating completion of the handler.

StreamDirectRawPredict(IAsyncStreamReader<StreamDirectRawPredictRequest>, IServerStreamWriter<StreamDirectRawPredictResponse>, ServerCallContext)

public virtual Task StreamDirectRawPredict(IAsyncStreamReader<StreamDirectRawPredictRequest> requestStream, IServerStreamWriter<StreamDirectRawPredictResponse> responseStream, ServerCallContext context)

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

Parameters
Name Description
requestStream IAsyncStreamReaderStreamDirectRawPredictRequest

Used for reading requests from the client.

responseStream IServerStreamWriterStreamDirectRawPredictResponse

Used for sending responses back to the client.

context ServerCallContext

The context of the server-side call handler being invoked.

Returns
Type Description
Task

A task indicating completion of the handler.

StreamGenerateContent(GenerateContentRequest, IServerStreamWriter<GenerateContentResponse>, ServerCallContext)

public virtual Task StreamGenerateContent(GenerateContentRequest request, IServerStreamWriter<GenerateContentResponse> responseStream, ServerCallContext context)

Generate content with multimodal inputs with streaming support.

Parameters
Name Description
request GenerateContentRequest

The request received from the client.

responseStream IServerStreamWriterGenerateContentResponse

Used for sending responses back to the client.

context ServerCallContext

The context of the server-side call handler being invoked.

Returns
Type Description
Task

A task indicating completion of the handler.

StreamRawPredict(StreamRawPredictRequest, IServerStreamWriter<HttpBody>, ServerCallContext)

public virtual Task StreamRawPredict(StreamRawPredictRequest request, IServerStreamWriter<HttpBody> responseStream, ServerCallContext context)

Perform a streaming online prediction with an arbitrary HTTP payload.

Parameters
Name Description
request StreamRawPredictRequest

The request received from the client.

responseStream IServerStreamWriterHttpBody

Used for sending responses back to the client.

context ServerCallContext

The context of the server-side call handler being invoked.

Returns
Type Description
Task

A task indicating completion of the handler.

StreamingPredict(IAsyncStreamReader<StreamingPredictRequest>, IServerStreamWriter<StreamingPredictResponse>, ServerCallContext)

public virtual Task StreamingPredict(IAsyncStreamReader<StreamingPredictRequest> requestStream, IServerStreamWriter<StreamingPredictResponse> responseStream, ServerCallContext context)

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

Parameters
Name Description
requestStream IAsyncStreamReaderStreamingPredictRequest

Used for reading requests from the client.

responseStream IServerStreamWriterStreamingPredictResponse

Used for sending responses back to the client.

context ServerCallContext

The context of the server-side call handler being invoked.

Returns
Type Description
Task

A task indicating completion of the handler.

StreamingRawPredict(IAsyncStreamReader<StreamingRawPredictRequest>, IServerStreamWriter<StreamingRawPredictResponse>, ServerCallContext)

public virtual Task StreamingRawPredict(IAsyncStreamReader<StreamingRawPredictRequest> requestStream, IServerStreamWriter<StreamingRawPredictResponse> responseStream, ServerCallContext context)

Perform a streaming online prediction request through gRPC.

Parameters
Name Description
requestStream IAsyncStreamReaderStreamingRawPredictRequest

Used for reading requests from the client.

responseStream IServerStreamWriterStreamingRawPredictResponse

Used for sending responses back to the client.

context ServerCallContext

The context of the server-side call handler being invoked.

Returns
Type Description
Task

A task indicating completion of the handler.