@google-cloud/discoveryengine 1.12.0 → 1.14.0

package/build/protos/google/cloud/discoveryengine/v1/import_config.proto

@@ -82,7 +82,7 @@ message BigQuerySource {
     google.type.Date partition_date = 5;
   }
 
-  // The project ID (can be project # or ID) that the BigQuery source is in with
+  // The project ID or the project number that contains the BigQuery source. Has
   // a length limit of 128 characters. If not specified, inherits the project
   // ID from the parent request.
   string project_id = 1;
@@ -124,7 +124,7 @@ message BigQuerySource {
 
 // The Spanner source for importing data
 message SpannerSource {
-  // The project ID that the Spanner source is in with a length limit of 128
+  // The project ID that contains the Spanner source. Has a length limit of 128
   // characters. If not specified, inherits the project ID from the parent
   // request.
   string project_id = 1;
@@ -258,7 +258,7 @@ message BigtableOptions {
 
 // The Cloud Bigtable source for importing data.
 message BigtableSource {
-  // The project ID that the Bigtable source is in with a length limit of 128
+  // The project ID that contains the Bigtable source. Has a length limit of 128
   // characters. If not specified, inherits the project ID from the parent
   // request.
   string project_id = 1;
@@ -290,12 +290,18 @@ message FhirStoreSource {
   // limit of 2,000 characters. Can be specified if one wants to have the
   // FhirStore export to a specific Cloud Storage directory.
   string gcs_staging_dir = 2;
+
+  // The FHIR resource types to import. The resource types should be a subset of
+  // all [supported FHIR resource
+  // types](https://cloud.google.com/generative-ai-app-builder/docs/fhir-schema-reference#resource-level-specification).
+  // Default to all supported FHIR resource types if empty.
+  repeated string resource_types = 3;
 }
 
 // Cloud SQL source import data from.
 message CloudSqlSource {
-  // The project ID that the Cloud SQL source is in with a length limit of 128
-  // characters. If not specified, inherits the project ID from the parent
+  // The project ID that contains the Cloud SQL source. Has a length limit of
+  // 128 characters. If not specified, inherits the project ID from the parent
   // request.
   string project_id = 1;
 
@@ -327,8 +333,8 @@ message CloudSqlSource {
 
 // AlloyDB source import data from.
 message AlloyDbSource {
-  // The project ID that the AlloyDB source is in
-  // with a length limit of 128 characters. If not specified, inherits the
+  // The project ID that contains the AlloyDB source.
+  // Has a length limit of 128 characters. If not specified, inherits the
   // project ID from the parent request.
   string project_id = 1;
 

package/build/protos/google/cloud/discoveryengine/v1/purge_config.proto

@@ -18,6 +18,7 @@ package google.cloud.discoveryengine.v1;
 
 import "google/api/field_behavior.proto";
 import "google/api/resource.proto";
+import "google/cloud/discoveryengine/v1/import_config.proto";
 import "google/protobuf/timestamp.proto";
 import "google/rpc/status.proto";
 
@@ -30,10 +31,123 @@ option objc_class_prefix = "DISCOVERYENGINE";
 option php_namespace = "Google\\Cloud\\DiscoveryEngine\\V1";
 option ruby_package = "Google::Cloud::DiscoveryEngine::V1";
 
+// Request message for PurgeUserEvents method.
+message PurgeUserEventsRequest {
+  // Required. The resource name of the catalog under which the events are
+  // created. The format is
+  // `projects/{project}/locations/global/collections/{collection}/dataStores/{dataStore}`
+  string parent = 1 [
+    (google.api.field_behavior) = REQUIRED,
+    (google.api.resource_reference) = {
+      type: "discoveryengine.googleapis.com/DataStore"
+    }
+  ];
+
+  // Required. The filter string to specify the events to be deleted with a
+  // length limit of 5,000 characters. The eligible fields for filtering are:
+  //
+  // * `eventType`: Double quoted
+  // [UserEvent.event_type][google.cloud.discoveryengine.v1.UserEvent.event_type]
+  // string.
+  // * `eventTime`: in ISO 8601 "zulu" format.
+  // * `userPseudoId`: Double quoted string. Specifying this will delete all
+  //   events associated with a visitor.
+  // * `userId`: Double quoted string. Specifying this will delete all events
+  //   associated with a user.
+  //
+  // Examples:
+  //
+  // * Deleting all events in a time range:
+  //   `eventTime > "2012-04-23T18:25:43.511Z"
+  //   eventTime < "2012-04-23T18:30:43.511Z"`
+  // * Deleting specific eventType:
+  //   `eventType = "search"`
+  // * Deleting all events for a specific visitor:
+  //   `userPseudoId = "visitor1024"`
+  // * Deleting all events inside a DataStore:
+  //   `*`
+  //
+  // The filtering fields are assumed to have an implicit AND.
+  string filter = 2 [(google.api.field_behavior) = REQUIRED];
+
+  // The `force` field is currently not supported. Purge user event requests
+  // will permanently delete all purgeable events. Once the development is
+  // complete:
+  // If `force` is set to false, the method will return the expected
+  // purge count without deleting any user events. This field will default to
+  // false if not included in the request.
+  bool force = 3;
+}
+
+// Response of the PurgeUserEventsRequest. If the long running operation is
+// successfully done, then this message is returned by the
+// google.longrunning.Operations.response field.
+message PurgeUserEventsResponse {
+  // The total count of events purged as a result of the operation.
+  int64 purge_count = 1;
+}
+
+// Metadata related to the progress of the PurgeUserEvents operation.
+// This will be returned by the google.longrunning.Operation.metadata field.
+message PurgeUserEventsMetadata {
+  // Operation create time.
+  google.protobuf.Timestamp create_time = 1;
+
+  // Operation last update time. If the operation is done, this is also the
+  // finish time.
+  google.protobuf.Timestamp update_time = 2;
+
+  // Count of entries that were deleted successfully.
+  int64 success_count = 3;
+
+  // Count of entries that encountered errors while processing.
+  int64 failure_count = 4;
+}
+
+// Configuration of destination for Purge related errors.
+message PurgeErrorConfig {
+  // Required. Errors destination.
+  oneof destination {
+    // Cloud Storage prefix for purge errors. This must be an empty,
+    // existing Cloud Storage directory. Purge errors are written to
+    // sharded files in this directory, one per line, as a JSON-encoded
+    // `google.rpc.Status` message.
+    string gcs_prefix = 1;
+  }
+}
+
 // Request message for
 // [DocumentService.PurgeDocuments][google.cloud.discoveryengine.v1.DocumentService.PurgeDocuments]
 // method.
 message PurgeDocumentsRequest {
+  // The inline source for the input config for
+  // [DocumentService.PurgeDocuments][google.cloud.discoveryengine.v1.DocumentService.PurgeDocuments]
+  // method.
+  message InlineSource {
+    // Required. A list of full resource name of documents to purge. In the
+    // format
+    // `projects/*/locations/*/collections/*/dataStores/*/branches/*/documents/*`.
+    // Recommended max of 100 items.
+    repeated string documents = 1 [
+      (google.api.field_behavior) = REQUIRED,
+      (google.api.resource_reference) = {
+        type: "discoveryengine.googleapis.com/Document"
+      }
+    ];
+  }
+
+  // The desired input source for the purging documents based on document IDs.
+  oneof source {
+    // Cloud Storage location for the input content.
+    // Supported `data_schema`:
+    // * `document_id`: One valid
+    // [Document.id][google.cloud.discoveryengine.v1.Document.id] per line.
+    GcsSource gcs_source = 5;
+
+    // Inline source for the input content for purge.
+    InlineSource inline_source = 6;
+  }
+
   // Required. The parent resource name, such as
   // `projects/{project}/locations/{location}/collections/{collection}/dataStores/{data_store}/branches/{branch}`.
   string parent = 1 [
@@ -48,6 +162,9 @@ message PurgeDocumentsRequest {
   // `*` (all items).
   string filter = 2 [(google.api.field_behavior) = REQUIRED];
 
+  // The desired location of errors incurred during the purge.
+  PurgeErrorConfig error_config = 7;
+
   // Actually performs the purge. If `force` is set to false, return the
   // expected purge count without deleting any documents.
   bool force = 3;

package/build/protos/google/cloud/discoveryengine/v1/recommendation_service.proto

@@ -58,7 +58,8 @@ service RecommendationService {
 
 // Request message for Recommend method.
 message RecommendRequest {
-  // Required. Full resource name of a [ServingConfig][]:
+  // Required. Full resource name of a
+  // [ServingConfig][google.cloud.discoveryengine.v1.ServingConfig]:
   // `projects/*/locations/global/collections/*/engines/*/servingConfigs/*`, or
   // `projects/*/locations/global/collections/*/dataStores/*/servingConfigs/*`
   //

package/build/protos/google/cloud/discoveryengine/v1/search_service.proto

@@ -420,6 +420,14 @@ message SearchRequest {
       // fallback messages instead.
       bool ignore_non_summary_seeking_query = 4;
 
+      // Specifies whether to filter out queries that have low relevance. The
+      // default value is `false`.
+      //
+      // If this field is set to `false`, all search results are used regardless
+      // of relevance to generate answers. If set to `true`, only queries with
+      // high relevance search results will generate answers.
+      bool ignore_low_relevant_content = 9;
+
       // If specified, the spec will be used to modify the prompt provided to
       // the LLM.
       ModelPromptSpec model_prompt_spec = 5;
@@ -514,11 +522,7 @@ message SearchRequest {
     }
 
     // Specifies the search result mode. If unspecified, the
-    // search result mode is based on
-    // [DataStore.DocumentProcessingConfig.chunking_config][]:
-    // * If [DataStore.DocumentProcessingConfig.chunking_config][] is specified,
-    //   it defaults to `CHUNKS`.
-    // * Otherwise, it defaults to `DOCUMENTS`.
+    // search result mode defaults to `DOCUMENTS`.
     enum SearchResultMode {
       // Default value.
       SEARCH_RESULT_MODE_UNSPECIFIED = 0;
@@ -544,11 +548,7 @@ message SearchRequest {
     ExtractiveContentSpec extractive_content_spec = 3;
 
     // Specifies the search result mode. If unspecified, the
-    // search result mode is based on
-    // [DataStore.DocumentProcessingConfig.chunking_config][]:
-    // * If [DataStore.DocumentProcessingConfig.chunking_config][] is specified,
-    //   it defaults to `CHUNKS`.
-    // * Otherwise, it defaults to `DOCUMENTS`.
+    // search result mode defaults to `DOCUMENTS`.
     SearchResultMode search_result_mode = 4;
 
     // Specifies the chunk spec to be returned from the search response.
@@ -724,9 +724,12 @@ message SearchRequest {
   // Leave it unset if ordered by relevance. `order_by` expression is
   // case-sensitive.
   //
-  // For more information on ordering for retail search, see
-  // [Ordering](https://cloud.google.com/retail/docs/filter-and-order#order)
-  //
+  // For more information on ordering the website search results, see
+  // [Order web search
+  // results](https://cloud.google.com/generative-ai-app-builder/docs/order-web-search-results).
+  // For more information on ordering the healthcare search results, see
+  // [Order healthcare search
+  // results](https://cloud.google.com/generative-ai-app-builder/docs/order-hc-results).
   // If this field is unrecognizable, an `INVALID_ARGUMENT` is returned.
   string order_by = 8;
 
@@ -1003,14 +1006,14 @@ message SearchResponse {
 
       // The adversarial query ignored case.
       //
-      // Only populated when
+      // Only used when
       // [SummarySpec.ignore_adversarial_query][google.cloud.discoveryengine.v1.SearchRequest.ContentSearchSpec.SummarySpec.ignore_adversarial_query]
       // is set to `true`.
       ADVERSARIAL_QUERY_IGNORED = 1;
 
       // The non-summary seeking query ignored case.
       //
-      // Only populated when
+      // Only used when
       // [SummarySpec.ignore_non_summary_seeking_query][google.cloud.discoveryengine.v1.SearchRequest.ContentSearchSpec.SummarySpec.ignore_non_summary_seeking_query]
       // is set to `true`.
       NON_SUMMARY_SEEKING_QUERY_IGNORED = 2;
@@ -1032,6 +1035,26 @@ message SearchResponse {
       //
       // Google skips the summary if the LLM addon is not enabled.
       LLM_ADDON_NOT_ENABLED = 5;
+
+      // The no relevant content case.
+      //
+      // Google skips the summary if there is no relevant content in the
+      // retrieved search results.
+      NO_RELEVANT_CONTENT = 6;
+
+      // The jail-breaking query ignored case.
+      //
+      // For example, "Reply in the tone of a competing company's CEO".
+      // Only used when
+      // [SearchRequest.ContentSearchSpec.SummarySpec.ignore_jail_breaking_query]
+      // is set to `true`.
+      JAIL_BREAKING_QUERY_IGNORED = 7;
+
+      // The customer policy violation case.
+      //
+      // Google skips the summary if there is a customer policy violation
+      // detected. The policy is defined by the customer.
+      CUSTOMER_POLICY_VIOLATION = 8;
     }
 
     // The summary content.
@@ -1095,7 +1118,8 @@ message SearchResponse {
   // A unique search token. This should be included in the
   // [UserEvent][google.cloud.discoveryengine.v1.UserEvent] logs resulting from
   // this search, which enables accurate attribution of search model
-  // performance.
+  // performance. This also helps to identify a request during the customer
+  // support scenarios.
   string attribution_token = 4;
 
   // The URI of a customer-defined redirect page. If redirect action is

package/build/protos/google/cloud/discoveryengine/v1/search_tuning_service.proto

@@ -0,0 +1,196 @@
+// Copyright 2024 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.discoveryengine.v1;
+
+import "google/api/annotations.proto";
+import "google/api/client.proto";
+import "google/api/field_behavior.proto";
+import "google/api/resource.proto";
+import "google/cloud/discoveryengine/v1/custom_tuning_model.proto";
+import "google/cloud/discoveryengine/v1/import_config.proto";
+import "google/longrunning/operations.proto";
+import "google/protobuf/timestamp.proto";
+import "google/rpc/status.proto";
+
+option csharp_namespace = "Google.Cloud.DiscoveryEngine.V1";
+option go_package = "cloud.google.com/go/discoveryengine/apiv1/discoveryenginepb;discoveryenginepb";
+option java_multiple_files = true;
+option java_outer_classname = "SearchTuningServiceProto";
+option java_package = "com.google.cloud.discoveryengine.v1";
+option objc_class_prefix = "DISCOVERYENGINE";
+option php_namespace = "Google\\Cloud\\DiscoveryEngine\\V1";
+option ruby_package = "Google::Cloud::DiscoveryEngine::V1";
+
+// Service for search tuning.
+service SearchTuningService {
+  option (google.api.default_host) = "discoveryengine.googleapis.com";
+  option (google.api.oauth_scopes) =
+      "https://www.googleapis.com/auth/cloud-platform";
+
+  // Trains a custom model.
+  rpc TrainCustomModel(TrainCustomModelRequest)
+      returns (google.longrunning.Operation) {
+    option (google.api.http) = {
+      post: "/v1/{data_store=projects/*/locations/*/collections/*/dataStores/*}:trainCustomModel"
+      body: "*"
+    };
+    option (google.longrunning.operation_info) = {
+      response_type: "google.cloud.discoveryengine.v1.TrainCustomModelResponse"
+      metadata_type: "google.cloud.discoveryengine.v1.TrainCustomModelMetadata"
+    };
+  }
+
+  // Gets a list of all the custom models.
+  rpc ListCustomModels(ListCustomModelsRequest)
+      returns (ListCustomModelsResponse) {
+    option (google.api.http) = {
+      get: "/v1/{data_store=projects/*/locations/*/collections/*/dataStores/*}/customModels"
+    };
+  }
+}
+
+// Request message for
+// [SearchTuningService.ListCustomModels][google.cloud.discoveryengine.v1.SearchTuningService.ListCustomModels]
+// method.
+message ListCustomModelsRequest {
+  // Required. The resource name of the parent Data Store, such as
+  // `projects/*/locations/global/collections/default_collection/dataStores/default_data_store`.
+  // This field is used to identify the data store where to fetch the models
+  // from.
+  string data_store = 1 [
+    (google.api.field_behavior) = REQUIRED,
+    (google.api.resource_reference) = {
+      type: "discoveryengine.googleapis.com/DataStore"
+    }
+  ];
+}
+
+// Response message for
+// [SearchTuningService.ListCustomModels][google.cloud.discoveryengine.v1.SearchTuningService.ListCustomModels]
+// method.
+message ListCustomModelsResponse {
+  // List of custom tuning models.
+  repeated CustomTuningModel models = 1;
+}
+
+// Request message for
+// [SearchTuningService.TrainCustomModel][google.cloud.discoveryengine.v1.SearchTuningService.TrainCustomModel]
+// method.
+message TrainCustomModelRequest {
+  // Cloud Storage training data input.
+  message GcsTrainingInput {
+    // The Cloud Storage corpus data which could be associated in train data.
+    // The data path format is `gs://<bucket_to_data>/<jsonl_file_name>`.
+    // A newline delimited jsonl/ndjson file.
+    //
+    // For search-tuning model, each line should have the _id, title
+    // and text. Example:
+    // `{"_id": "doc1", title: "relevant doc", "text": "relevant text"}`
+    string corpus_data_path = 1;
+
+    // The gcs query data which could be associated in train data.
+    // The data path format is `gs://<bucket_to_data>/<jsonl_file_name>`.
+    // A newline delimited jsonl/ndjson file.
+    //
+    // For search-tuning model, each line should have the _id
+    // and text. Example: {"_id": "query1",  "text": "example query"}
+    string query_data_path = 2;
+
+    // Cloud Storage training data path whose format should be
+    // `gs://<bucket_to_data>/<tsv_file_name>`. The file should be in tsv
+    // format. Each line should have the doc_id and query_id and score (number).
+    //
+    // For search-tuning model, it should have the query-id corpus-id
+    // score as tsv file header. The score should be a number in `[0, inf+)`.
+    // The larger the number is, the more relevant the pair is. Example:
+    //
+    // * `query-id\tcorpus-id\tscore`
+    // * `query1\tdoc1\t1`
+    string train_data_path = 3;
+
+    // Cloud Storage test data. Same format as train_data_path. If not provided,
+    // a random 80/20 train/test split will be performed on train_data_path.
+    string test_data_path = 4;
+  }
+
+  // Model training input.
+  oneof training_input {
+    // Cloud Storage training input.
+    GcsTrainingInput gcs_training_input = 2;
+  }
+
+  // Required. The resource name of the Data Store, such as
+  // `projects/*/locations/global/collections/default_collection/dataStores/default_data_store`.
+  // This field is used to identify the data store where to train the models.
+  string data_store = 1 [
+    (google.api.field_behavior) = REQUIRED,
+    (google.api.resource_reference) = {
+      type: "discoveryengine.googleapis.com/DataStore"
+    }
+  ];
+
+  // Model to be trained. Supported values are:
+  //
+  //  * **search-tuning**: Fine tuning the search system based on data provided.
+  string model_type = 3;
+
+  // The desired location of errors incurred during the data ingestion and
+  // training.
+  ImportErrorConfig error_config = 4;
+
+  // If not provided, a UUID will be generated.
+  string model_id = 5;
+}
+
+// Response of the
+// [TrainCustomModelRequest][google.cloud.discoveryengine.v1.TrainCustomModelRequest].
+// This message is returned by the google.longrunning.Operations.response field.
+message TrainCustomModelResponse {
+  // A sample of errors encountered while processing the data.
+  repeated google.rpc.Status error_samples = 1;
+
+  // Echoes the destination for the complete errors in the request if set.
+  ImportErrorConfig error_config = 2;
+
+  // The trained model status. Possible values are:
+  //
+  //  * **bad-data**: The training data quality is bad.
+  //  * **no-improvement**: Tuning didn't improve performance. Won't deploy.
+  //  * **in-progress**: Model training job creation is in progress.
+  //  * **training**: Model is actively training.
+  //  * **evaluating**: The model is evaluating trained metrics.
+  //  * **indexing**: The model trained metrics are indexing.
+  //  * **ready**: The model is ready for serving.
+  string model_status = 3;
+
+  // The metrics of the trained model.
+  map<string, double> metrics = 4;
+
+  // Fully qualified name of the CustomTuningModel.
+  string model_name = 5;
+}
+
+// Metadata related to the progress of the TrainCustomModel operation. This is
+// returned by the google.longrunning.Operation.metadata field.
+message TrainCustomModelMetadata {
+  // Operation create time.
+  google.protobuf.Timestamp create_time = 1;
+
+  // Operation last update time. If the operation is done, this is also the
+  // finish time.
+  google.protobuf.Timestamp update_time = 2;
+}

package/build/protos/google/cloud/discoveryengine/v1/user_event.proto

@@ -453,6 +453,10 @@ message DocumentInfo {
   // The promotion IDs associated with this Document.
   // Currently, this field is restricted to at most one ID.
   repeated string promotion_ids = 4;
+
+  // Output only. Whether the referenced Document can be found in the data
+  // store.
+  bool joined = 5 [(google.api.field_behavior) = OUTPUT_ONLY];
 }
 
 // Detailed panel information associated with a user event.

package/build/protos/google/cloud/discoveryengine/v1/user_event_service.proto

@@ -22,6 +22,7 @@ import "google/api/field_behavior.proto";
 import "google/api/httpbody.proto";
 import "google/api/resource.proto";
 import "google/cloud/discoveryengine/v1/import_config.proto";
+import "google/cloud/discoveryengine/v1/purge_config.proto";
 import "google/cloud/discoveryengine/v1/user_event.proto";
 import "google/longrunning/operations.proto";
 
@@ -73,6 +74,26 @@ service UserEventService {
     };
   }
 
+  // Deletes permanently all user events specified by the filter provided.
+  // Depending on the number of events specified by the filter, this operation
+  // could take hours or days to complete. To test a filter, use the list
+  // command first.
+  rpc PurgeUserEvents(PurgeUserEventsRequest)
+      returns (google.longrunning.Operation) {
+    option (google.api.http) = {
+      post: "/v1/{parent=projects/*/locations/*/dataStores/*}/userEvents:purge"
+      body: "*"
+      additional_bindings {
+        post: "/v1/{parent=projects/*/locations/*/collections/*/dataStores/*}/userEvents:purge"
+        body: "*"
+      }
+    };
+    option (google.longrunning.operation_info) = {
+      response_type: "google.cloud.discoveryengine.v1.PurgeUserEventsResponse"
+      metadata_type: "google.cloud.discoveryengine.v1.PurgeUserEventsMetadata"
+    };
+  }
+
   // Bulk import of user events. Request processing might be
   // synchronous. Events that already exist are skipped.
   // Use this method for backfilling historical user events.

package/build/protos/google/cloud/discoveryengine/v1alpha/acl_config_service.proto

@@ -37,7 +37,7 @@ service AclConfigService {
   option (google.api.oauth_scopes) =
       "https://www.googleapis.com/auth/cloud-platform";
 
-  // Default Acl Configuration for use in a location of a customer's project.
+  // Default ACL configuration for use in a location of a customer's project.
   // Updates will only reflect to new data stores. Existing data stores will
   // still use the old value.
   rpc UpdateAclConfig(UpdateAclConfigRequest) returns (AclConfig) {