// 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/field_behavior.proto"; import "google/api/resource.proto"; import "google/cloud/aiplatform/v1beta1/explanation.proto"; import "google/cloud/aiplatform/v1beta1/machine_resources.proto"; import "google/protobuf/timestamp.proto"; import "google/api/annotations.proto"; option go_package = "google.golang.org/genproto/googleapis/cloud/aiplatform/v1beta1;aiplatform"; option java_multiple_files = true; option java_outer_classname = "EndpointProto"; option java_package = "com.google.cloud.aiplatform.v1beta1"; // Models are deployed into it, and afterwards Endpoint is called to obtain // predictions and explanations. message Endpoint { option (google.api.resource) = { type: "aiplatform.googleapis.com/Endpoint" pattern: "projects/{project}/locations/{location}/endpoints/{endpoint}" }; // Output only. The resource name of the Endpoint. string name = 1 [(google.api.field_behavior) = OUTPUT_ONLY]; // Required. The display name of the Endpoint. // The name can be up to 128 characters long and can be consist of any UTF-8 // characters. string display_name = 2 [(google.api.field_behavior) = REQUIRED]; // The description of the Endpoint. string description = 3; // Output only. The models deployed in this Endpoint. // To add or remove DeployedModels use [EndpointService.DeployModel][google.cloud.aiplatform.v1beta1.EndpointService.DeployModel] and // [EndpointService.UndeployModel][google.cloud.aiplatform.v1beta1.EndpointService.UndeployModel] respectively. repeated DeployedModel deployed_models = 4 [(google.api.field_behavior) = OUTPUT_ONLY]; // A map from a DeployedModel's ID to the percentage of this Endpoint's // traffic that should be forwarded to that DeployedModel. // // If a DeployedModel's ID is not listed in this map, then it receives no // traffic. // // The traffic percentage values must add up to 100, or map must be empty if // the Endpoint is to not accept any traffic at a moment. map traffic_split = 5; // Used to perform consistent read-modify-write updates. If not set, a blind // "overwrite" update happens. string etag = 6; // The labels with user-defined metadata to organize your Endpoints. // // Label keys and values can be no longer than 64 characters // (Unicode codepoints), can only contain lowercase letters, numeric // characters, underscores and dashes. International characters are allowed. // // See https://goo.gl/xmQnxf for more information and examples of labels. map labels = 7; // Output only. Timestamp when this Endpoint was created. google.protobuf.Timestamp create_time = 8 [(google.api.field_behavior) = OUTPUT_ONLY]; // Output only. Timestamp when this Endpoint was last updated. google.protobuf.Timestamp update_time = 9 [(google.api.field_behavior) = OUTPUT_ONLY]; } // A deployment of a Model. Endpoints contain one or more DeployedModels. message DeployedModel { // The prediction (for example, the machine) resources that the DeployedModel // uses. The user is billed for the resources (at least their minimal amount) // even if the DeployedModel receives no traffic. // Not all Models support all resources types. See // [Model.supported_deployment_resources_types][google.cloud.aiplatform.v1beta1.Model.supported_deployment_resources_types]. oneof prediction_resources { // A description of resources that are dedicated to the DeployedModel, and // that need a higher degree of manual configuration. DedicatedResources dedicated_resources = 7; // A description of resources that to large degree are decided by AI // Platform, and require only a modest additional configuration. AutomaticResources automatic_resources = 8; } // Output only. The ID of the DeployedModel. string id = 1 [(google.api.field_behavior) = OUTPUT_ONLY]; // Required. The name of the Model this is the deployment of. Note that the Model // may be in a different location than the DeployedModel's Endpoint. string model = 2 [ (google.api.field_behavior) = REQUIRED, (google.api.resource_reference) = { type: "aiplatform.googleapis.com/Model" } ]; // The display name of the DeployedModel. If not provided upon creation, // the Model's display_name is used. string display_name = 3; // Output only. Timestamp when the DeployedModel was created. google.protobuf.Timestamp create_time = 6 [(google.api.field_behavior) = OUTPUT_ONLY]; // Explanation configuration for this DeployedModel. // // When deploying a Model using [EndpointService.DeployModel][google.cloud.aiplatform.v1beta1.EndpointService.DeployModel], this value // overrides the value of [Model.explanation_spec][google.cloud.aiplatform.v1beta1.Model.explanation_spec]. All fields of // [explanation_spec][google.cloud.aiplatform.v1beta1.DeployedModel.explanation_spec] are optional in the request. If a field of // [explanation_spec][google.cloud.aiplatform.v1beta1.DeployedModel.explanation_spec] is not populated, the value of the same field of // [Model.explanation_spec][google.cloud.aiplatform.v1beta1.Model.explanation_spec] is inherited. The corresponding // [Model.explanation_spec][google.cloud.aiplatform.v1beta1.Model.explanation_spec] must be populated, otherwise explanation for // this Model is not allowed. ExplanationSpec explanation_spec = 9; // The service account that the DeployedModel's container runs as. Specify the // email address of the service account. If this service account is not // specified, the container runs as a service account that doesn't have access // to the resource project. // // Users deploying the Model must have the `iam.serviceAccounts.actAs` // permission on this service account. string service_account = 11; // If true, the container of the DeployedModel instances will send `stderr` // and `stdout` streams to Stackdriver Logging. // // Only supported for custom-trained Models and AutoML Tables Models. bool enable_container_logging = 12; // These logs are like standard server access logs, containing // information like timestamp and latency for each prediction request. // // Note that Stackdriver logs may incur a cost, especially if your project // receives prediction requests at a high queries per second rate (QPS). // Estimate your costs before enabling this option. bool enable_access_logging = 13; }