@google-cloud/discoveryengine 0.6.0 → 0.8.0

package/build/protos/google/cloud/discoveryengine/v1beta/import_config.proto

@@ -60,6 +60,10 @@ message GcsSource {
   // * `custom`: One custom data JSON per row in arbitrary format that conforms
   //   the defined [Schema][google.cloud.discoveryengine.v1beta.Schema] of the
   //   data store. This can only be used by the GENERIC Data Store vertical.
+  // * `csv`: A CSV file with header conforming the defined
+  // [Schema][google.cloud.discoveryengine.v1beta.Schema] of the
+  //   data store. Each entry after the header will be imported as a Document.
+  //   This can only be used by the GENERIC Data Store vertical.
   //
   // Supported values for user even imports:
   //
@@ -137,16 +141,16 @@ message ImportUserEventsRequest {
     repeated UserEvent user_events = 1 [(google.api.field_behavior) = REQUIRED];
   }
 
-  // The desired input source of the user event data.
+  // Required - The desired input source of the user event data.
   oneof source {
-    // Required. The Inline source for the input content for UserEvents.
-    InlineSource inline_source = 2 [(google.api.field_behavior) = REQUIRED];
+    // The Inline source for the input content for UserEvents.
+    InlineSource inline_source = 2;
 
-    // Required. Cloud Storage location for the input content.
-    GcsSource gcs_source = 3 [(google.api.field_behavior) = REQUIRED];
+    // Cloud Storage location for the input content.
+    GcsSource gcs_source = 3;
 
-    // Required. BigQuery input source.
-    BigQuerySource bigquery_source = 4 [(google.api.field_behavior) = REQUIRED];
+    // BigQuery input source.
+    BigQuerySource bigquery_source = 4;
   }
 
   // Required. Parent DataStore resource name, of the form
@@ -269,6 +273,60 @@ message ImportDocumentsRequest {
   // be imported. Defaults to
   // [ReconciliationMode.INCREMENTAL][google.cloud.discoveryengine.v1beta.ImportDocumentsRequest.ReconciliationMode.INCREMENTAL].
   ReconciliationMode reconciliation_mode = 6;
+
+  // Whether to automatically generate IDs for the documents if absent.
+  //
+  // If set to `true`,
+  // [Document.id][google.cloud.discoveryengine.v1beta.Document.id]s are
+  // automatically generated based on the hash of the payload, where IDs may not
+  // be consistent during multiple imports. In which case
+  // [ReconciliationMode.FULL][google.cloud.discoveryengine.v1beta.ImportDocumentsRequest.ReconciliationMode.FULL]
+  // is highly recommended to avoid duplicate contents. If unset or set to
+  // `false`, [Document.id][google.cloud.discoveryengine.v1beta.Document.id]s
+  // have to be specified using
+  // [id_field][google.cloud.discoveryengine.v1beta.ImportDocumentsRequest.id_field],
+  // otherwises, documents without IDs will fail to be imported.
+  //
+  // Only set this field when using
+  // [GcsSource][google.cloud.discoveryengine.v1beta.GcsSource] or
+  // [BigQuerySource][google.cloud.discoveryengine.v1beta.BigQuerySource], and
+  // when
+  // [GcsSource.data_schema][google.cloud.discoveryengine.v1beta.GcsSource.data_schema]
+  // or
+  // [BigQuerySource.data_schema][google.cloud.discoveryengine.v1beta.BigQuerySource.data_schema]
+  // is `custom` or `csv`. Otherwise, an INVALID_ARGUMENT error is thrown.
+  bool auto_generate_ids = 8;
+
+  // The field in the Cloud Storage and BigQuery sources that indicates the
+  // unique IDs of the documents.
+  //
+  // For [GcsSource][google.cloud.discoveryengine.v1beta.GcsSource] it is the
+  // key of the JSON field. For instance, `my_id` for JSON `{"my_id":
+  // "some_uuid"}`. For
+  // [BigQuerySource][google.cloud.discoveryengine.v1beta.BigQuerySource] it is
+  // the column name of the BigQuery table where the unique ids are stored.
+  //
+  // The values of the JSON field or the BigQuery column will be used as the
+  // [Document.id][google.cloud.discoveryengine.v1beta.Document.id]s. The JSON
+  // field or the BigQuery column must be of string type, and the values must be
+  // set as valid strings conform to
+  // [RFC-1034](https://tools.ietf.org/html/rfc1034) with 1-63 characters.
+  // Otherwise, documents without valid IDs will fail to be imported.
+  //
+  // Only set this field when using
+  // [GcsSource][google.cloud.discoveryengine.v1beta.GcsSource] or
+  // [BigQuerySource][google.cloud.discoveryengine.v1beta.BigQuerySource], and
+  // when
+  // [GcsSource.data_schema][google.cloud.discoveryengine.v1beta.GcsSource.data_schema]
+  // or
+  // [BigQuerySource.data_schema][google.cloud.discoveryengine.v1beta.BigQuerySource.data_schema]
+  // is `custom`. And only set this field when
+  // [auto_generate_ids][google.cloud.discoveryengine.v1beta.ImportDocumentsRequest.auto_generate_ids]
+  // is unset or set as `false`. Otherwise, an INVALID_ARGUMENT error is thrown.
+  //
+  // If it is unset, a default value `_id` is used when importing from the
+  // allowed data sources.
+  string id_field = 9;
 }
 
 // Response of the

package/build/protos/google/cloud/discoveryengine/v1beta/search_service.proto

@@ -287,6 +287,10 @@ message SearchRequest {
     // The specification that configs the snippet in the search results.
     message SnippetSpec {
       // Max number of snippets returned in each search result.
+      //
+      // A snippet is an infomartive summary of a content with highlighting for
+      // UI rendering.
+      //
       // If the matching snippets is less than the max_snippet_count, return all
       // of the snippets; otherwise, return the max_snippet_count.
       //
@@ -308,6 +312,36 @@ message SearchRequest {
       int32 summary_result_count = 1;
     }
 
+    // The specification that configs the extractive content in search results.
+    message ExtractiveContentSpec {
+      // The max number of extractive answers returned in each search result.
+      //
+      // An extractive answer is a verbatim answer extracted from the original
+      // document, which provides precise and contextually relevant answer to
+      // the search query.
+      //
+      // If the number of matching answers is less than the
+      // extractive_answer_count, return all of the answers; otherwise, return
+      // the extractive_answer_count.
+      //
+      // At most 5 answers will be returned for each SearchResult.
+      int32 max_extractive_answer_count = 1;
+
+      // The max number of extractive segments returned in each search result.
+      //
+      // An extractive segment is a text segment extracted from the original
+      // document which is relevant to the search query and in general more
+      // verbose than an extrative answer. The segment could then be used as
+      // input for LLMs to generate summaries and answers.
+      //
+      // If the number of matching segments is less than the
+      // max_extractive_segment_count, return all of the segments; otherwise,
+      // return the max_extractive_segment_count.
+      //
+      // Currently one segment will be returned for each SearchResult.
+      int32 max_extractive_segment_count = 2;
+    }
+
     // If there is no snippet spec provided, there will be no snippet in the
     // search result.
     SnippetSpec snippet_spec = 1;
@@ -315,6 +349,10 @@ message SearchRequest {
     // If there is no summary spec provided, there will be no summary in the
     // search response.
     SummarySpec summary_spec = 2;
+
+    // If there is no extractive_content_spec provided, there will be no
+    // extractive answer in the search response.
+    ExtractiveContentSpec extractive_content_spec = 3;
   }
 
   // Required. The resource name of the Search serving config, such as
@@ -382,6 +420,11 @@ message SearchRequest {
   // If this field is unrecognizable, an  `INVALID_ARGUMENT`  is returned.
   string order_by = 8;
 
+  // Information about the end user.
+  // Highly recommended for analytics. The user_agent string in UserInfo will
+  // be used to deduce device_type for analytics.
+  UserInfo user_info = 21;
+
   // Facet specifications for faceted search. If empty, no facets are returned.
   //
   // A maximum of 100 values are allowed. Otherwise, an  `INVALID_ARGUMENT`
@@ -393,16 +436,13 @@ message SearchRequest {
 
   // Additional search parameters.
   //
-  // For
-  // [IndustryVertical.SITE_SEARCH][google.cloud.discoveryengine.v1beta.IndustryVertical.SITE_SEARCH]
-  // vertical, supported values are:
+  // For public website search only, supported values are:
   //
   // * `user_country_code`: string. Default empty. If set to non-empty, results
   //    are restricted or boosted based on the location provided.
   // * `search_type`: double. Default empty. Enables non-webpage searching
   //   depending on the value. The only valid non-default value is 1,
   //   which enables image searching.
-  // This field is ignored for other verticals.
   map<string, google.protobuf.Value> params = 11;
 
   // The query expansion specification that specifies the conditions under which
@@ -432,6 +472,29 @@ message SearchRequest {
   // The content search spec that configs the desired behavior of content
   // search.
   ContentSearchSpec content_search_spec = 24;
+
+  // Whether to turn on safe search. This is only supported for
+  // [ContentConfig.PUBLIC_WEBSITE][].
+  bool safe_search = 20;
+
+  // The user labels applied to a resource must meet the following requirements:
+  //
+  // * Each resource can have multiple labels, up to a maximum of 64.
+  // * Each label must be a key-value pair.
+  // * Keys have a minimum length of 1 character and a maximum length of 63
+  //   characters and cannot be empty. Values can be empty and have a maximum
+  //   length of 63 characters.
+  // * Keys and values can contain only lowercase letters, numeric characters,
+  //   underscores, and dashes. All characters must use UTF-8 encoding, and
+  //   international characters are allowed.
+  // * The key portion of a label must be unique. However, you can use the same
+  //   key with multiple resources.
+  // * Keys must start with a lowercase letter or international character.
+  //
+  // See [Google Cloud
+  // Document](https://cloud.google.com/resource-manager/docs/creating-managing-labels#requirements)
+  // for more details.
+  map<string, string> user_labels = 22;
 }
 
 // Response message for
@@ -524,6 +587,14 @@ message SearchResponse {
   // performance.
   string attribution_token = 4;
 
+  // The URI of a customer-defined redirect page. If redirect action is
+  // triggered, no search is performed, and only
+  // [redirect_uri][google.cloud.discoveryengine.v1beta.SearchResponse.redirect_uri]
+  // and
+  // [attribution_token][google.cloud.discoveryengine.v1beta.SearchResponse.attribution_token]
+  // are set in the response.
+  string redirect_uri = 12;
+
   // A token that can be sent as
   // [SearchRequest.page_token][google.cloud.discoveryengine.v1beta.SearchRequest.page_token]
   // to retrieve the next page. If this field is omitted, there are no