// Copyright 2020 Google LLC // // Licensed under the Apache License, Version 2.0 (the "License"); // you may not use this file except in compliance with the License. // You may obtain a copy of the License at // // http://www.apache.org/licenses/LICENSE-2.0 // // Unless required by applicable law or agreed to in writing, software // distributed under the License is distributed on an "AS IS" BASIS, // WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. // See the License for the specific language governing permissions and // limitations under the License. syntax = "proto3"; package google.cloud.aiplatform.v1beta1; import "google/api/annotations.proto"; import "google/api/client.proto"; import "google/api/field_behavior.proto"; import "google/api/resource.proto"; import "google/cloud/aiplatform/v1beta1/explanation.proto"; import "google/protobuf/struct.proto"; option go_package = "google.golang.org/genproto/googleapis/cloud/aiplatform/v1beta1;aiplatform"; option java_multiple_files = true; option java_outer_classname = "PredictionServiceProto"; option java_package = "com.google.cloud.aiplatform.v1beta1"; // A service for online predictions and explanations. service PredictionService { option (google.api.default_host) = "aiplatform.googleapis.com"; option (google.api.oauth_scopes) = "https://www.googleapis.com/auth/cloud-platform"; // Perform an online prediction. rpc Predict(PredictRequest) returns (PredictResponse) { option (google.api.http) = { post: "/v1beta1/{endpoint=projects/*/locations/*/endpoints/*}:predict" body: "*" }; option (google.api.method_signature) = "endpoint,instances,parameters"; } // 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. Only deployed AutoML tabular Models have // explanation_spec. rpc Explain(ExplainRequest) returns (ExplainResponse) { option (google.api.http) = { post: "/v1beta1/{endpoint=projects/*/locations/*/endpoints/*}:explain" body: "*" }; option (google.api.method_signature) = "endpoint,instances,parameters,deployed_model_id"; } } // Request message for [PredictionService.Predict][google.cloud.aiplatform.v1beta1.PredictionService.Predict]. message PredictRequest { // Required. The name of the Endpoint requested to serve the prediction. // Format: // `projects/{project}/locations/{location}/endpoints/{endpoint}` string endpoint = 1 [ (google.api.field_behavior) = REQUIRED, (google.api.resource_reference) = { type: "aiplatform.googleapis.com/Endpoint" } ]; // Required. The instances that are the input to the prediction call. // A DeployedModel may have an upper limit on the number of instances it // supports per request, and when it is exceeded the prediction call errors // in case of AutoML Models, or, in case of customer created Models, the // behaviour is as documented by that Model. // The schema of any single instance may be specified via Endpoint's // DeployedModels' [Model's][google.cloud.aiplatform.v1beta1.DeployedModel.model] // [PredictSchemata's][google.cloud.aiplatform.v1beta1.Model.predict_schemata] // [instance_schema_uri][google.cloud.aiplatform.v1beta1.PredictSchemata.instance_schema_uri]. repeated google.protobuf.Value instances = 2 [(google.api.field_behavior) = REQUIRED]; // The parameters that govern the prediction. The schema of the parameters may // be specified via Endpoint's DeployedModels' [Model's ][google.cloud.aiplatform.v1beta1.DeployedModel.model] // [PredictSchemata's][google.cloud.aiplatform.v1beta1.Model.predict_schemata] // [parameters_schema_uri][google.cloud.aiplatform.v1beta1.PredictSchemata.parameters_schema_uri]. google.protobuf.Value parameters = 3; } // Response message for [PredictionService.Predict][google.cloud.aiplatform.v1beta1.PredictionService.Predict]. message PredictResponse { // The predictions that are the output of the predictions call. // The schema of any single prediction may be specified via Endpoint's // DeployedModels' [Model's ][google.cloud.aiplatform.v1beta1.DeployedModel.model] // [PredictSchemata's][google.cloud.aiplatform.v1beta1.Model.predict_schemata] // [prediction_schema_uri][google.cloud.aiplatform.v1beta1.PredictSchemata.prediction_schema_uri]. repeated google.protobuf.Value predictions = 1; // ID of the Endpoint's DeployedModel that served this prediction. string deployed_model_id = 2; } // Request message for [PredictionService.Explain][google.cloud.aiplatform.v1beta1.PredictionService.Explain]. message ExplainRequest { // Required. The name of the Endpoint requested to serve the explanation. // Format: // `projects/{project}/locations/{location}/endpoints/{endpoint}` string endpoint = 1 [ (google.api.field_behavior) = REQUIRED, (google.api.resource_reference) = { type: "aiplatform.googleapis.com/Endpoint" } ]; // Required. The instances that are the input to the explanation call. // A DeployedModel may have an upper limit on the number of instances it // supports per request, and when it is exceeded the explanation call errors // in case of AutoML Models, or, in case of customer created Models, the // behaviour is as documented by that Model. // The schema of any single instance may be specified via Endpoint's // DeployedModels' [Model's][google.cloud.aiplatform.v1beta1.DeployedModel.model] // [PredictSchemata's][google.cloud.aiplatform.v1beta1.Model.predict_schemata] // [instance_schema_uri][google.cloud.aiplatform.v1beta1.PredictSchemata.instance_schema_uri]. repeated google.protobuf.Value instances = 2 [(google.api.field_behavior) = REQUIRED]; // The parameters that govern the prediction. The schema of the parameters may // be specified via Endpoint's DeployedModels' [Model's ][google.cloud.aiplatform.v1beta1.DeployedModel.model] // [PredictSchemata's][google.cloud.aiplatform.v1beta1.Model.predict_schemata] // [parameters_schema_uri][google.cloud.aiplatform.v1beta1.PredictSchemata.parameters_schema_uri]. google.protobuf.Value parameters = 4; // If specified, this ExplainRequest will be served by the chosen // DeployedModel, overriding [Endpoint.traffic_split][google.cloud.aiplatform.v1beta1.Endpoint.traffic_split]. string deployed_model_id = 3; } // Response message for [PredictionService.Explain][google.cloud.aiplatform.v1beta1.PredictionService.Explain]. message ExplainResponse { // The explanations of the Model's [PredictResponse.predictions][google.cloud.aiplatform.v1beta1.PredictResponse.predictions]. // // It has the same number of elements as [instances][google.cloud.aiplatform.v1beta1.ExplainRequest.instances] // to be explained. repeated Explanation explanations = 1; // ID of the Endpoint's DeployedModel that served this explanation. string deployed_model_id = 2; // The predictions that are the output of the predictions call. // Same as [PredictResponse.predictions][google.cloud.aiplatform.v1beta1.PredictResponse.predictions]. repeated google.protobuf.Value predictions = 3; }