feat: allow users to specify id field in documents gcs import

feat: add LRO API for schema service
docs: keep the API doc up-to-date with recent changes

PiperOrigin-RevId: 534894398

google/cloud/discoveryengine/v1beta/discoveryengine_v1beta.yaml

@@ -55,6 +55,7 @@ http:
     additional_bindings:
     - get: '/v1beta/{name=projects/*/locations/*/collections/*/dataStores/*/models/*/operations/*}'
     - get: '/v1beta/{name=projects/*/locations/*/collections/*/dataStores/*/operations/*}'
+    - get: '/v1beta/{name=projects/*/locations/*/collections/*/dataStores/*/schemas/*/operations/*}'
     - get: '/v1beta/{name=projects/*/locations/*/collections/*/operations/*}'
     - get: '/v1beta/{name=projects/*/locations/*/dataStores/*/branches/*/operations/*}'
     - get: '/v1beta/{name=projects/*/locations/*/dataStores/*/models/*/operations/*}'
@@ -65,6 +66,7 @@ http:
     get: '/v1beta/{name=projects/*/locations/*/collections/*/dataStores/*/branches/*}/operations'
     additional_bindings:
     - get: '/v1beta/{name=projects/*/locations/*/collections/*/dataStores/*/models/*}/operations'
+    - get: '/v1beta/{name=projects/*/locations/*/collections/*/dataStores/*/schemas/*}/operations'
     - get: '/v1beta/{name=projects/*/locations/*/collections/*/dataStores/*}/operations'
     - get: '/v1beta/{name=projects/*/locations/*/collections/*}/operations'
     - get: '/v1beta/{name=projects/*/locations/*/dataStores/*/branches/*}/operations'

google/cloud/discoveryengine/v1beta/import_config.proto

@@ -269,6 +269,60 @@ 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`. 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

google/cloud/discoveryengine/v1beta/search_service.proto

@@ -398,9 +398,7 @@ 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.