feat: support extractive content in search

feat: add redirected uri in search response
feat: support docx/pptx/txt/csv in allowed data format
docs: keep the API doc up-to-date with recent changes

PiperOrigin-RevId: 541013898

google/cloud/discoveryengine/v1beta/completion_service.proto

@@ -74,6 +74,8 @@ message CompleteQueryRequest {
   // API calls. Do not use it when there is no traffic for Search API.
   // * `user-event` - Using suggestions generated from user-imported search
   // events.
+  // * `document-completable` - Using suggestions taken directly from
+  // user-imported document fields marked as completable.
   //
   // Default values:
   //

google/cloud/discoveryengine/v1beta/document.proto

@@ -59,8 +59,11 @@ message Document {
 
     // The MIME type of the content. Supported types:
     //
-    // * `application/pdf` (PDF)
+    // * `application/pdf` (PDF, only native PDFs are supported for now)
     // * `text/html` (HTML)
+    // * `application/vnd.openxmlformats-officedocument.wordprocessingml.document` (DOCX)
+    // * `application/vnd.openxmlformats-officedocument.presentationml.presentation` (PPTX)
+    // * `text/plain` (TXT)
     //
     // See https://www.iana.org/assignments/media-types/media-types.xhtml.
     string mime_type = 1;

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
@@ -290,7 +294,7 @@ message ImportDocumentsRequest {
   // [GcsSource.data_schema][google.cloud.discoveryengine.v1beta.GcsSource.data_schema]
   // or
   // [BigQuerySource.data_schema][google.cloud.discoveryengine.v1beta.BigQuerySource.data_schema]
-  // is `custom`. Otherwise, an INVALID_ARGUMENT error is thrown.
+  // 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

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
@@ -549,6 +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