feat: add ListSavedQueries rpc to aiplatform v1 dataset_service.proto

feat: add saved_query.proto to aiplatform v1
feat: add saved_query_id to InputDataConfig in aiplatform v1 training_pipeline.proto

PiperOrigin-RevId: 456872211

google/cloud/aiplatform/v1/BUILD.bazel

@@ -86,6 +86,7 @@ proto_library(
         "pipeline_service.proto",
         "pipeline_state.proto",
         "prediction_service.proto",
+        "saved_query.proto",
         "specialist_pool.proto",
         "specialist_pool_service.proto",
         "study.proto",

google/cloud/aiplatform/v1/dataset_service.proto

@@ -25,6 +25,7 @@ import "google/cloud/aiplatform/v1/annotation_spec.proto";
 import "google/cloud/aiplatform/v1/data_item.proto";
 import "google/cloud/aiplatform/v1/dataset.proto";
 import "google/cloud/aiplatform/v1/operation.proto";
+import "google/cloud/aiplatform/v1/saved_query.proto";
 import "google/longrunning/operations.proto";
 import "google/protobuf/field_mask.proto";
 
@@ -126,6 +127,14 @@ service DatasetService {
     option (google.api.method_signature) = "parent";
   }
 
+  // Lists SavedQueries in a Dataset.
+  rpc ListSavedQueries(ListSavedQueriesRequest) returns (ListSavedQueriesResponse) {
+    option (google.api.http) = {
+      get: "/v1/{parent=projects/*/locations/*/datasets/*}/savedQueries"
+    };
+    option (google.api.method_signature) = "parent";
+  }
+
   // Gets an AnnotationSpec.
   rpc GetAnnotationSpec(GetAnnotationSpecRequest) returns (AnnotationSpec) {
     option (google.api.http) = {
@@ -357,6 +366,44 @@ message ListDataItemsResponse {
   string next_page_token = 2;
 }
 
+// Request message for [DatasetService.ListSavedQueries][google.cloud.aiplatform.v1.DatasetService.ListSavedQueries].
+message ListSavedQueriesRequest {
+  // Required. The resource name of the Dataset to list SavedQueries from.
+  // Format:
+  // `projects/{project}/locations/{location}/datasets/{dataset}`
+  string parent = 1 [
+    (google.api.field_behavior) = REQUIRED,
+    (google.api.resource_reference) = {
+      type: "aiplatform.googleapis.com/Dataset"
+    }
+  ];
+
+  // The standard list filter.
+  string filter = 2;
+
+  // The standard list page size.
+  int32 page_size = 3;
+
+  // The standard list page token.
+  string page_token = 4;
+
+  // Mask specifying which fields to read.
+  google.protobuf.FieldMask read_mask = 5;
+
+  // A comma-separated list of fields to order by, sorted in ascending order.
+  // Use "desc" after a field name for descending.
+  string order_by = 6;
+}
+
+// Response message for [DatasetService.ListSavedQueries][google.cloud.aiplatform.v1.DatasetService.ListSavedQueries].
+message ListSavedQueriesResponse {
+  // A list of SavedQueries that match the specified filter in the request.
+  repeated SavedQuery saved_queries = 1;
+
+  // The standard List next-page token.
+  string next_page_token = 2;
+}
+
 // Request message for [DatasetService.GetAnnotationSpec][google.cloud.aiplatform.v1.DatasetService.GetAnnotationSpec].
 message GetAnnotationSpecRequest {
   // Required. The name of the AnnotationSpec resource.

google/cloud/aiplatform/v1/pipeline_failure_policy.proto

@@ -24,7 +24,7 @@ option java_package = "com.google.cloud.aiplatform.v1";
 option php_namespace = "Google\\Cloud\\AIPlatform\\V1";
 option ruby_package = "Google::Cloud::AIPlatform::V1";
 
-// Reperesents the failure policy of a pipeline. Currently, the default of a
+// Represents the failure policy of a pipeline. Currently, the default of a
 // pipeline is that the pipeline will continue to run until no more tasks can be
 // executed, also known as PIPELINE_FAILURE_POLICY_FAIL_SLOW. However, if a
 // pipeline is set to PIPELINE_FAILURE_POLICY_FAIL_FAST, it will stop scheduling

google/cloud/aiplatform/v1/saved_query.proto

@@ -0,0 +1,84 @@
+// Copyright 2022 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.v1;
+
+import "google/api/field_behavior.proto";
+import "google/api/resource.proto";
+import "google/protobuf/struct.proto";
+import "google/protobuf/timestamp.proto";
+
+option csharp_namespace = "Google.Cloud.AIPlatform.V1";
+option go_package = "google.golang.org/genproto/googleapis/cloud/aiplatform/v1;aiplatform";
+option java_multiple_files = true;
+option java_outer_classname = "SavedQueryProto";
+option java_package = "com.google.cloud.aiplatform.v1";
+option php_namespace = "Google\\Cloud\\AIPlatform\\V1";
+option ruby_package = "Google::Cloud::AIPlatform::V1";
+
+// A SavedQuery is a view of the dataset. It references a subset of annotations
+// by problem type and filters.
+message SavedQuery {
+  option (google.api.resource) = {
+    type: "aiplatform.googleapis.com/SavedQuery"
+    pattern: "projects/{project}/locations/{location}/datasets/{dataset}/savedQueries/{saved_query}"
+  };
+
+  // Output only. Resource name of the SavedQuery.
+  string name = 1 [(google.api.field_behavior) = OUTPUT_ONLY];
+
+  // Required. The user-defined name of the SavedQuery.
+  // The name can be up to 128 characters long and can consist of any UTF-8
+  // characters.
+  string display_name = 2 [(google.api.field_behavior) = REQUIRED];
+
+  // Some additional information about the SavedQuery.
+  google.protobuf.Value metadata = 12;
+
+  // Output only. Timestamp when this SavedQuery was created.
+  google.protobuf.Timestamp create_time = 3 [(google.api.field_behavior) = OUTPUT_ONLY];
+
+  // Output only. Timestamp when SavedQuery was last updated.
+  google.protobuf.Timestamp update_time = 4 [(google.api.field_behavior) = OUTPUT_ONLY];
+
+  // Output only. Filters on the Annotations in the dataset.
+  string annotation_filter = 5 [(google.api.field_behavior) = OUTPUT_ONLY];
+
+  // Required. Problem type of the SavedQuery.
+  // Allowed values:
+  // * IMAGE_CLASSIFICATION_SINGLE_LABEL
+  // * IMAGE_CLASSIFICATION_MULTI_LABEL
+  // * IMAGE_BOUNDING_POLY
+  // * IMAGE_BOUNDING_BOX
+  // * TEXT_CLASSIFICATION_SINGLE_LABEL
+  // * TEXT_CLASSIFICATION_MULTI_LABEL
+  // * TEXT_EXTRACTION
+  // * TEXT_SENTIMENT
+  // * VIDEO_CLASSIFICATION
+  // * VIDEO_OBJECT_TRACKING
+  string problem_type = 6 [(google.api.field_behavior) = REQUIRED];
+
+  // Output only. Number of AnnotationSpecs in the context of the SavedQuery.
+  int32 annotation_spec_count = 10 [(google.api.field_behavior) = OUTPUT_ONLY];
+
+  // Used to perform a consistent read-modify-write update. If not set, a blind
+  // "overwrite" update happens.
+  string etag = 8;
+
+  // Output only. If the Annotations belonging to the SavedQuery can be used for AutoML
+  // training.
+  bool support_automl_training = 9 [(google.api.field_behavior) = OUTPUT_ONLY];
+}

google/cloud/aiplatform/v1/training_pipeline.proto

@@ -276,6 +276,20 @@ message InputDataConfig {
   // for training are filtered by both [annotations_filter][google.cloud.aiplatform.v1.InputDataConfig.annotations_filter] and
   // [annotation_schema_uri][google.cloud.aiplatform.v1.InputDataConfig.annotation_schema_uri].
   string annotation_schema_uri = 9;
+
+  // Only applicable to Datasets that have SavedQueries.
+  //
+  // The ID of a SavedQuery (annotation set) under the Dataset specified by
+  // [dataset_id][google.cloud.aiplatform.v1.InputDataConfig.dataset_id] used for filtering Annotations for training.
+  //
+  // Only Annotations that are associated with this SavedQuery are used in
+  // respectively training. When used in conjunction with
+  // [annotations_filter][google.cloud.aiplatform.v1.InputDataConfig.annotations_filter], the Annotations used for training are filtered by
+  // both [saved_query_id][google.cloud.aiplatform.v1.InputDataConfig.saved_query_id] and [annotations_filter][google.cloud.aiplatform.v1.InputDataConfig.annotations_filter].
+  //
+  // Only one of [saved_query_id][google.cloud.aiplatform.v1.InputDataConfig.saved_query_id] and [annotation_schema_uri][google.cloud.aiplatform.v1.InputDataConfig.annotation_schema_uri] should be
+  // specified as both of them represent the same thing: problem type.
+  string saved_query_id = 7;
 }
 
 // Assigns the input data to training, validation, and test sets as per the