@google-cloud/discoveryengine 1.4.0 → 1.4.1

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

@@ -0,0 +1,130 @@
+// 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.discoveryengine.v1alpha;
+
+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/v1alpha/import_config.proto";
+import "google/longrunning/operations.proto";
+import "google/protobuf/timestamp.proto";
+
+option csharp_namespace = "Google.Cloud.DiscoveryEngine.V1Alpha";
+option go_package = "cloud.google.com/go/discoveryengine/apiv1alpha/discoveryenginepb;discoveryenginepb";
+option java_multiple_files = true;
+option java_outer_classname = "EstimateBillingServiceProto";
+option java_package = "com.google.cloud.discoveryengine.v1alpha";
+option objc_class_prefix = "DISCOVERYENGINE";
+option php_namespace = "Google\\Cloud\\DiscoveryEngine\\V1alpha";
+option ruby_package = "Google::Cloud::DiscoveryEngine::V1alpha";
+
+// Service for managing billing estimations resources.
+service EstimateBillingService {
+  option (google.api.default_host) = "discoveryengine.googleapis.com";
+  option (google.api.oauth_scopes) =
+      "https://www.googleapis.com/auth/cloud-platform";
+
+  // Estimates the data size to be used by a customer.
+  rpc EstimateDataSize(EstimateDataSizeRequest)
+      returns (google.longrunning.Operation) {
+    option (google.api.http) = {
+      post: "/v1alpha/{location=projects/*/locations/*}:estimateDataSize"
+      body: "*"
+    };
+    option (google.longrunning.operation_info) = {
+      response_type: "google.cloud.discoveryengine.v1alpha.EstimateDataSizeResponse"
+      metadata_type: "google.cloud.discoveryengine.v1alpha.EstimateDataSizeMetadata"
+    };
+  }
+}
+
+// Request message for
+// [EstimateBillingService.EstimateDataSize][google.cloud.discoveryengine.v1alpha.EstimateBillingService.EstimateDataSize]
+// method
+message EstimateDataSizeRequest {
+  // Data source is a set of website patterns that we crawl to get
+  // the total number of websites.
+  message WebsiteDataSource {
+    // URI patterns that we use to crawl.
+    message EstimatorUriPattern {
+      // User provided URI pattern. For example, `foo.com/bar/*`.
+      string provided_uri_pattern = 1;
+
+      // Whether we infer the generated URI or use the exact provided one.
+      bool exact_match = 2;
+
+      // Whether the pattern is exclusive or not. If set to true, the pattern is
+      // considered exclusive. If unset or set to false, the pattern is
+      // considered inclusive by default.
+      bool exclusive = 3;
+    }
+
+    // Required. The URI patterns to estimate the data sizes. At most 10
+    // patterns are allowed, otherwise an INVALID_ARGUMENT error is thrown.
+    repeated EstimatorUriPattern estimator_uri_patterns = 1
+        [(google.api.field_behavior) = REQUIRED];
+  }
+
+  // Data source contains files either in Cloud Storage or BigQuery.
+  message FileDataSource {
+    // Which source contains the files to be used.
+    oneof source {
+      // Cloud Storage location for the input content.
+      GcsSource gcs_source = 1;
+
+      // BigQuery input source.
+      BigQuerySource bigquery_source = 2;
+    }
+  }
+
+  // Data source for which we are estimating its size.
+  oneof data_source {
+    // Website data.
+    WebsiteDataSource website_data_source = 2;
+
+    // Structured or unstructured data.
+    FileDataSource file_data_source = 3;
+  }
+
+  // Required. Full resource name of the location, such as
+  // `projects/{project}/locations/{location}`.
+  string location = 1 [
+    (google.api.field_behavior) = REQUIRED,
+    (google.api.resource_reference) = {
+      type: "discoveryengine.googleapis.com/Location"
+    }
+  ];
+}
+
+// Response of the EstimateDataSize request. If the long running
+// operation was successful, then this message is returned by the
+// google.longrunning.Operations.response field if the operation was successful.
+message EstimateDataSizeResponse {
+  // Data size in terms of bytes.
+  int64 data_size_bytes = 1;
+
+  // Total number of documents.
+  int64 document_count = 2;
+}
+
+// Metadata related to the progress of the EstimateDataSize operation. This is
+// returned by the google.longrunning.Operation.metadata field.
+message EstimateDataSizeMetadata {
+  // Operation create time.
+  google.protobuf.Timestamp create_time = 1;
+}

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

@@ -18,6 +18,7 @@ package google.cloud.discoveryengine.v1alpha;
 
 import "google/api/field_behavior.proto";
 import "google/api/resource.proto";
+import "google/cloud/discoveryengine/v1alpha/completion.proto";
 import "google/cloud/discoveryengine/v1alpha/document.proto";
 import "google/cloud/discoveryengine/v1alpha/user_event.proto";
 import "google/protobuf/timestamp.proto";
@@ -341,3 +342,66 @@ message ImportDocumentsResponse {
   // Echoes the destination for the complete errors in the request if set.
   ImportErrorConfig error_config = 2;
 }
+
+// Request message for
+// [CompletionService.ImportSuggestionDenyListEntries][google.cloud.discoveryengine.v1alpha.CompletionService.ImportSuggestionDenyListEntries]
+// method.
+message ImportSuggestionDenyListEntriesRequest {
+  // The inline source for SuggestionDenyListEntry.
+  message InlineSource {
+    // Required. A list of all denylist entries to import. Max of 1000 items.
+    repeated SuggestionDenyListEntry entries = 1
+        [(google.api.field_behavior) = REQUIRED];
+  }
+
+  // The source of the updated SuggestionDenyList.
+  oneof source {
+    // The Inline source for the input content for suggestion deny list entries.
+    InlineSource inline_source = 2;
+
+    // Cloud Storage location for the input content.
+    //
+    // Only 1 file can be specified that contains all entries to import.
+    // Supported values `gcs_source.schema` for autocomplete suggestion deny
+    // list entry imports:
+    //
+    // * `suggestion_deny_list` (default): One JSON [SuggestionDenyListEntry]
+    // per line.
+    GcsSource gcs_source = 3;
+  }
+
+  // Required. The parent data store resource name for which to import denylist
+  // entries. Follows pattern projects/*/locations/*/collections/*/dataStores/*.
+  string parent = 1 [
+    (google.api.field_behavior) = REQUIRED,
+    (google.api.resource_reference) = {
+      type: "discoveryengine.googleapis.com/DataStore"
+    }
+  ];
+}
+
+// Response message for
+// [CompletionService.ImportSuggestionDenyListEntries][google.cloud.discoveryengine.v1alpha.CompletionService.ImportSuggestionDenyListEntries]
+// method.
+message ImportSuggestionDenyListEntriesResponse {
+  // A sample of errors encountered while processing the request.
+  repeated google.rpc.Status error_samples = 1;
+
+  // Count of deny list entries successfully imported.
+  int64 imported_entries_count = 2;
+
+  // Count of deny list entries that failed to be imported.
+  int64 failed_entries_count = 3;
+}
+
+// Metadata related to the progress of the ImportSuggestionDenyListEntries
+// operation. This is returned by the google.longrunning.Operation.metadata
+// field.
+message ImportSuggestionDenyListEntriesMetadata {
+  // 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/v1alpha/purge_config.proto

@@ -18,7 +18,9 @@ package google.cloud.discoveryengine.v1alpha;
 
 import "google/api/field_behavior.proto";
 import "google/api/resource.proto";
+import "google/cloud/discoveryengine/v1alpha/import_config.proto";
 import "google/protobuf/timestamp.proto";
+import "google/rpc/status.proto";
 
 option csharp_namespace = "Google.Cloud.DiscoveryEngine.V1Alpha";
 option go_package = "cloud.google.com/go/discoveryengine/apiv1alpha/discoveryenginepb;discoveryenginepb";
@@ -102,10 +104,31 @@ message PurgeUserEventsMetadata {
   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.v1alpha.DocumentService.PurgeDocuments]
 // method.
 message PurgeDocumentsRequest {
+  // 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.v1alpha.Document.id] per line.
+    GcsSource gcs_source = 5;
+  }
+
   // Required. The parent resource name, such as
   // `projects/{project}/locations/{location}/collections/{collection}/dataStores/{data_store}/branches/{branch}`.
   string parent = 1 [
@@ -120,6 +143,9 @@ 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;
@@ -156,4 +182,44 @@ message PurgeDocumentsMetadata {
 
   // Count of entries that encountered errors while processing.
   int64 failure_count = 4;
+
+  // Count of entries that were ignored as entries were not found.
+  int64 ignored_count = 5;
+}
+
+// Request message for
+// [CompletionService.PurgeSuggestionDenyListEntries][google.cloud.discoveryengine.v1alpha.CompletionService.PurgeSuggestionDenyListEntries]
+// method.
+message PurgeSuggestionDenyListEntriesRequest {
+  // Required. The parent data store resource name for which to import denylist
+  // entries. Follows pattern projects/*/locations/*/collections/*/dataStores/*.
+  string parent = 1 [
+    (google.api.field_behavior) = REQUIRED,
+    (google.api.resource_reference) = {
+      type: "discoveryengine.googleapis.com/DataStore"
+    }
+  ];
+}
+
+// Response message for
+// [CompletionService.PurgeSuggestionDenyListEntries][google.cloud.discoveryengine.v1alpha.CompletionService.PurgeSuggestionDenyListEntries]
+// method.
+message PurgeSuggestionDenyListEntriesResponse {
+  // Number of suggestion deny list entries purged.
+  int64 purge_count = 1;
+
+  // A sample of errors encountered while processing the request.
+  repeated google.rpc.Status error_samples = 2;
+}
+
+// Metadata related to the progress of the PurgeSuggestionDenyListEntries
+// operation. This is returned by the google.longrunning.Operation.metadata
+// field.
+message PurgeSuggestionDenyListEntriesMetadata {
+  // 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/v1alpha/recommendation_service.proto

@@ -68,7 +68,9 @@ message RecommendRequest {
   // config. For example, for Engine
   // `projects/*/locations/global/collections/*/engines/my-engine`, you can use
   // `projects/*/locations/global/collections/*/engines/my-engine/servingConfigs/my-engine`
-  // for your [Recommend][] requests.
+  // for your
+  // [RecommendationService.Recommend][google.cloud.discoveryengine.v1alpha.RecommendationService.Recommend]
+  // requests.
   string serving_config = 1 [
     (google.api.field_behavior) = REQUIRED,
     (google.api.resource_reference) = {

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

@@ -86,6 +86,9 @@ message FieldConfig {
 
     // Field value type is Geolocation.
     GEOLOCATION = 6;
+
+    // Field value type is Datetime.
+    DATETIME = 7;
   }
 
   // The setting of Indexable options in schema.

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

@@ -20,6 +20,7 @@ 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/v1alpha/chunk.proto";
 import "google/cloud/discoveryengine/v1alpha/common.proto";
 import "google/cloud/discoveryengine/v1alpha/document.proto";
 import "google/protobuf/struct.proto";
@@ -69,6 +70,19 @@ message SearchRequest {
     }
   }
 
+  // A struct to define data stores to filter on in a search call.
+  message DataStoreSpec {
+    // Required. Full resource name of
+    // [DataStore][google.cloud.discoveryengine.v1alpha.DataStore], such as
+    // `projects/{project}/locations/{location}/collections/{collection_id}/dataStores/{data_store_id}`.
+    string data_store = 1 [
+      (google.api.field_behavior) = REQUIRED,
+      (google.api.resource_reference) = {
+        type: "discoveryengine.googleapis.com/DataStore"
+      }
+    ];
+  }
+
   // A facet specification to perform faceted search.
   message FacetSpec {
     // Specifies how a facet is computed.
@@ -212,9 +226,8 @@ message SearchRequest {
       // Examples:
       //
       // * To boost documents with document ID "doc_1" or "doc_2", and
-      // color
-      //   "Red" or "Blue":
-      //     * (id: ANY("doc_1", "doc_2")) AND (color: ANY("Red","Blue"))
+      // color "Red" or "Blue":
+      // `(document_id: ANY("doc_1", "doc_2")) AND (color: ANY("Red", "Blue"))`
       string condition = 1;
 
       // Strength of the condition boost, which should be in [-1, 1]. Negative
@@ -330,8 +343,16 @@ message SearchRequest {
 
       // Specification of the model.
       message ModelSpec {
-        // The string format of the model version.
-        // e.g. stable, preview, etc.
+        // The model version used to generate the summary.
+        //
+        // Supported values are:
+        //
+        // * `stable`: string. Default value when no value is specified. Uses a
+        //   generally available, fine-tuned version of the text-bison@001
+        //   model.
+        // * `preview`: string. (Public preview) Uses a fine-tuned version of
+        //   the text-bison@002 model. This model works only for summaries in
+        //   English.
         string version = 1;
       }
 
@@ -339,7 +360,7 @@ message SearchRequest {
       // of results returned is less than `summaryResultCount`, the summary is
       // generated from all of the results.
       //
-      // At most five results can be used to generate a summary.
+      // At most 10 results can be used to generate a summary.
       int32 summary_result_count = 1;
 
       // Specifies whether to include citations in the summary. The default
@@ -414,7 +435,7 @@ message SearchRequest {
       // `max_extractive_answer_count`, return all of the answers. Otherwise,
       // return the `max_extractive_answer_count`.
       //
-      // At most one answer is returned for each
+      // At most five answers are returned for each
       // [SearchResult][google.cloud.discoveryengine.v1alpha.SearchResponse.SearchResult].
       int32 max_extractive_answer_count = 1;
 
@@ -455,6 +476,24 @@ message SearchRequest {
       int32 num_next_segments = 5;
     }
 
+    // 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`.
+    enum SearchResultMode {
+      // Default value.
+      SEARCH_RESULT_MODE_UNSPECIFIED = 0;
+
+      // Returns documents in the search result.
+      DOCUMENTS = 1;
+
+      // Returns chunks in the search result. Only available if the
+      // [DataStore.DocumentProcessingConfig.chunking_config][] is specified.
+      CHUNKS = 2;
+    }
+
     // If `snippetSpec` is not specified, snippets are not included in the
     // search response.
     SnippetSpec snippet_spec = 1;
@@ -466,6 +505,14 @@ message SearchRequest {
     // If there is no extractive_content_spec provided, there will be no
     // extractive answer in the search response.
     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`.
+    SearchResultMode search_result_mode = 4;
   }
 
   // The specification that uses customized query embedding vector to do
@@ -540,6 +587,9 @@ message SearchRequest {
   // If this field is negative, an  `INVALID_ARGUMENT`  is returned.
   int32 offset = 6;
 
+  // A list of data store specs to apply on a search call.
+  repeated DataStoreSpec data_store_specs = 32;
+
   // The filter syntax consists of an expression language for constructing a
   // predicate from one or more fields of the documents being filtered. Filter
   // expression is case-sensitive.
@@ -645,12 +695,13 @@ message SearchRequest {
 
   // Uses the provided embedding to do additional semantic document retrieval.
   // The retrieval is based on the dot product of
-  // [SearchRequest.embedding_spec.embedding_vectors.vector][] and the document
-  // embedding that is provided in
-  // [SearchRequest.embedding_spec.embedding_vectors.field_path][].
+  // [SearchRequest.EmbeddingSpec.EmbeddingVector.vector][google.cloud.discoveryengine.v1alpha.SearchRequest.EmbeddingSpec.EmbeddingVector.vector]
+  // and the document embedding that is provided in
+  // [SearchRequest.EmbeddingSpec.EmbeddingVector.field_path][google.cloud.discoveryengine.v1alpha.SearchRequest.EmbeddingSpec.EmbeddingVector.field_path].
   //
-  // If [SearchRequest.embedding_spec.embedding_vectors.field_path][] is not
-  // provided, it will use [ServingConfig.embedding_config.field_paths][].
+  // If
+  // [SearchRequest.EmbeddingSpec.EmbeddingVector.field_path][google.cloud.discoveryengine.v1alpha.SearchRequest.EmbeddingSpec.EmbeddingVector.field_path]
+  // is not provided, it will use [ServingConfig.EmbeddingConfig.field_path][].
   EmbeddingSpec embedding_spec = 23;
 
   // The ranking expression controls the customized ranking on retrieval
@@ -697,6 +748,9 @@ message SearchRequest {
   // Document](https://cloud.google.com/resource-manager/docs/creating-managing-labels#requirements)
   // for more details.
   map<string, string> user_labels = 22;
+
+  // Custom fine tuning configs.
+  CustomFineTuningSpec custom_fine_tuning_spec = 34;
 }
 
 // Response message for
@@ -713,6 +767,12 @@ message SearchResponse {
     // marked as retrievable are populated.
     Document document = 2;
 
+    // The chunk data in the search response if the
+    // [SearchRequest.ContentSearchSpec.search_result_mode][google.cloud.discoveryengine.v1alpha.SearchRequest.ContentSearchSpec.search_result_mode]
+    // is set to
+    // [CHUNKS][google.cloud.discoveryengine.v1alpha.SearchRequest.ContentSearchSpec.SearchResultMode.CHUNKS].
+    Chunk chunk = 18;
+
     // Google provided available scores.
     map<string, DoubleList> model_scores = 4;
   }
@@ -822,7 +882,7 @@ message SearchResponse {
         }
       ];
 
-      // GCS or HTTP uri for the document.
+      // Cloud Storage or HTTP uri for the document.
       string uri = 3;
     }
 
@@ -887,6 +947,7 @@ message SearchResponse {
     // confidence scores.
     SafetyAttributes safety_attributes = 3;
 
+    // Summary with metadata information.
     SummaryWithMetadata summary_with_metadata = 4;
   }
 

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

@@ -58,41 +58,45 @@ service SearchTuningService {
 // [SearchTuningService.TrainCustomModel][google.cloud.discoveryengine.v1alpha.SearchTuningService.TrainCustomModel]
 // method.
 message TrainCustomModelRequest {
-  // Gcs training data input.
+  // Cloud Storage training data input.
   message GcsTrainingInput {
-    // The gcs corpus data which could be associated in train data.
-    // The data path format is gs://<bucket_to_data>/<jsonl_file_name>.
+    // 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"}
+    //
+    // 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>.
+    // 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"}
+    //
+    // For search-tuning model, each line should have the _id
+    // and text. Example: {"_id": "query1",  "text": "example query"}
     string query_data_path = 2;
 
-    // Gcs 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
+    // 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;
 
-    // Gcs 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.
+    // 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 {
-    // Gcs training input.
+    // Cloud Storage training input.
     GcsTrainingInput gcs_training_input = 2;
   }