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

[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

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
NameDescription
requestExplainRequest

The request received from the client.

contextServerCallContext

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

Returns
TypeDescription
TaskExplainResponse

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
NameDescription
requestPredictRequest

The request received from the client.

contextServerCallContext

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

Returns
TypeDescription
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
NameDescription
requestRawPredictRequest

The request received from the client.

contextServerCallContext

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

Returns
TypeDescription
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
NameDescription
requestStreamingPredictRequest

The request received from the client.

responseStreamIServerStreamWriterStreamingPredictResponse

Used for sending responses back to the client.

contextServerCallContext

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

Returns
TypeDescription
Task

A task indicating completion of the handler.