Struct google_api_proto::google::cloud::aiplatform::v1beta1::prediction_service_client::PredictionServiceClient

pub struct PredictionServiceClient<T> { /* private fields */ }

A service for online predictions and explanations.

Implementations

impl<T> PredictionServiceClient<T>

where T: GrpcService<BoxBody>, T::Error: Into<StdError>, T::ResponseBody: Body<Data = Bytes> + Send + 'static, <T::ResponseBody as Body>::Error: Into<StdError> + Send,

pub fn new(inner: T) -> Self

pub fn with_origin(inner: T, origin: Uri) -> Self

pub fn with_interceptor<F>( inner: T, interceptor: F, ) -> PredictionServiceClient<InterceptedService<T, F>>

where F: Interceptor, T::ResponseBody: Default, T: Service<Request<BoxBody>, Response = Response<<T as GrpcService<BoxBody>>::ResponseBody>>, <T as Service<Request<BoxBody>>>::Error: Into<StdError> + Send + Sync,

pub fn send_compressed(self, encoding: CompressionEncoding) -> Self

Compress requests with the given encoding.

This requires the server to support it otherwise it might respond with an error.

pub fn accept_compressed(self, encoding: CompressionEncoding) -> Self

Enable decompressing responses.

pub fn max_decoding_message_size(self, limit: usize) -> Self

Limits the maximum size of a decoded message.

Default: 4MB

pub fn max_encoding_message_size(self, limit: usize) -> Self

Limits the maximum size of an encoded message.

Default: usize::MAX

pub async fn predict( &mut self, request: impl IntoRequest<PredictRequest>, ) -> Result<Response<PredictResponse>, Status>

Perform an online prediction.

pub async fn raw_predict( &mut self, request: impl IntoRequest<RawPredictRequest>, ) -> Result<Response<HttpBody>, Status>

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.

pub async fn stream_raw_predict( &mut self, request: impl IntoRequest<StreamRawPredictRequest>, ) -> Result<Response<Streaming<HttpBody>>, Status>

Perform a streaming online prediction with an arbitrary HTTP payload.

pub async fn direct_predict( &mut self, request: impl IntoRequest<DirectPredictRequest>, ) -> Result<Response<DirectPredictResponse>, Status>

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

pub async fn direct_raw_predict( &mut self, request: impl IntoRequest<DirectRawPredictRequest>, ) -> Result<Response<DirectRawPredictResponse>, Status>

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

pub async fn stream_direct_predict( &mut self, request: impl IntoStreamingRequest<Message = StreamDirectPredictRequest>, ) -> Result<Response<Streaming<StreamDirectPredictResponse>>, Status>

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

pub async fn stream_direct_raw_predict( &mut self, request: impl IntoStreamingRequest<Message = StreamDirectRawPredictRequest>, ) -> Result<Response<Streaming<StreamDirectRawPredictResponse>>, Status>

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

pub async fn streaming_predict( &mut self, request: impl IntoStreamingRequest<Message = StreamingPredictRequest>, ) -> Result<Response<Streaming<StreamingPredictResponse>>, Status>

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

pub async fn server_streaming_predict( &mut self, request: impl IntoRequest<StreamingPredictRequest>, ) -> Result<Response<Streaming<StreamingPredictResponse>>, Status>

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

pub async fn streaming_raw_predict( &mut self, request: impl IntoStreamingRequest<Message = StreamingRawPredictRequest>, ) -> Result<Response<Streaming<StreamingRawPredictResponse>>, Status>

Perform a streaming online prediction request through gRPC.

pub async fn explain( &mut self, request: impl IntoRequest<ExplainRequest>, ) -> Result<Response<ExplainResponse>, Status>

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.

pub async fn count_tokens( &mut self, request: impl IntoRequest<CountTokensRequest>, ) -> Result<Response<CountTokensResponse>, Status>

Perform a token counting.

pub async fn generate_content( &mut self, request: impl IntoRequest<GenerateContentRequest>, ) -> Result<Response<GenerateContentResponse>, Status>

Generate content with multimodal inputs.

pub async fn stream_generate_content( &mut self, request: impl IntoRequest<GenerateContentRequest>, ) -> Result<Response<Streaming<GenerateContentResponse>>, Status>

Generate content with multimodal inputs with streaming support.

pub async fn chat_completions( &mut self, request: impl IntoRequest<ChatCompletionsRequest>, ) -> Result<Response<Streaming<HttpBody>>, Status>

Exposes an OpenAI-compatible endpoint for chat completions.

Trait Implementations

impl<T: Clone> Clone for PredictionServiceClient<T>

fn clone(&self) -> PredictionServiceClient<T>

Returns a copy of the value.

fn clone_from(&mut self, source: &Self)

Performs copy-assignment from source.

impl<T: Debug> Debug for PredictionServiceClient<T>

fn fmt(&self, f: &mut Formatter<'_>) -> Result

Formats the value using the given formatter.