feat: A new message FoundationModelTuningOptions is added

feat: A new field foundation_model_tuning_options is added to message TrainProcessorVersionRequest
feat: A new field `labels` is added to messages `ProcessRequest` and `BatchProcessRequest`
feat: A new field `display_name` is added to message `DocumentSchema`
fix: deprecate `Dataset.document_warehouse_config`
docs: updated comments

PiperOrigin-RevId: 607358355

google/cloud/documentai/v1beta3/dataset.proto

@@ -94,9 +94,10 @@ message Dataset {
     GCSManagedConfig gcs_managed_config = 3
         [(google.api.field_behavior) = OPTIONAL];
 
-    // Optional. Document AI Warehouse-based dataset configuration.
+    // Optional. Deprecated. Warehouse-based dataset configuration is not
+    // supported.
     DocumentWarehouseConfig document_warehouse_config = 5
-        [(google.api.field_behavior) = OPTIONAL];
+        [deprecated = true, (google.api.field_behavior) = OPTIONAL];
 
     // Optional. Unmanaged dataset configuration. Use this configuration if the
     // dataset documents are managed by the document service internally (not

google/cloud/documentai/v1beta3/document.proto

@@ -758,7 +758,8 @@ message Document {
           [deprecated = true, (google.api.field_behavior) = OPTIONAL];
 
       // Optional. Identifies the bounding polygon of a layout element on the
-      // page.
+      // page. If `layout_type` is set, the bounding polygon must be exactly the
+      // same to the layout element it's referring to.
       BoundingPoly bounding_poly = 4 [(google.api.field_behavior) = OPTIONAL];
 
       // Optional. Confidence of detected page element, if applicable. Range

google/cloud/documentai/v1beta3/document_processor_service.proto

@@ -349,12 +349,11 @@ message ProcessOptions {
   }
 
   // A subset of pages to process. If not specified, all pages are processed.
-  //  If a page range is set, only the given pages are extracted and processed
-  //  from the document. In the output document,
-  //  [Document.Page.page_number][google.cloud.documentai.v1beta3.Document.Page.page_number]
-  //  refers to the page number in the original document. This configuration
-  //  only applies to sync requests. `page_range` can be only one of the
-  //  following:
+  // If a page range is set, only the given pages are extracted and processed
+  // from the document. In the output document,
+  // [Document.Page.page_number][google.cloud.documentai.v1beta3.Document.Page.page_number]
+  // refers to the page number in the original document. This configuration
+  // only applies to sync requests.
   oneof page_range {
     // Which pages to process (1-indexed).
     IndividualPageSelector individual_page_selector = 5;
@@ -367,8 +366,8 @@ message ProcessOptions {
     int32 from_end = 7;
   }
 
-  // Only applicable to `OCR_PROCESSOR`. Returns error if set on other
-  // processor types.
+  // Only applicable to `OCR_PROCESSOR` and `FORM_PARSER_PROCESSOR`.
+  // Returns error if set on other processor types.
   OcrConfig ocr_config = 1;
 
   // Optional. Override the schema of the
@@ -428,6 +427,14 @@ message ProcessRequest {
 
   // Inference-time options for the process API
   ProcessOptions process_options = 7;
+
+  // Optional. The labels with user-defined metadata for the request.
+  //
+  // Label keys and values can be no longer than 63 characters
+  // (Unicode codepoints) and can only contain lowercase letters, numeric
+  // characters, underscores, and dashes. International characters are allowed.
+  // Label values are optional. Label keys must start with a letter.
+  map<string, string> labels = 10 [(google.api.field_behavior) = OPTIONAL];
 }
 
 // The status of human review on a processed document.
@@ -550,6 +557,14 @@ message BatchProcessRequest {
 
   // Inference-time options for the process API
   ProcessOptions process_options = 7;
+
+  // Optional. The labels with user-defined metadata for the request.
+  //
+  // Label keys and values can be no longer than 63 characters
+  // (Unicode codepoints) and can only contain lowercase letters, numeric
+  // characters, underscores, and dashes. International characters are allowed.
+  // Label values are optional. Label keys must start with a letter.
+  map<string, string> labels = 9 [(google.api.field_behavior) = OPTIONAL];
 }
 
 // Response message for
@@ -878,7 +893,8 @@ message CreateProcessorRequest {
 
   // Required. The processor to be created, requires
   // [Processor.type][google.cloud.documentai.v1beta3.Processor.type] and
-  // [Processor.display_name]][] to be set. Also, the
+  // [Processor.display_name][google.cloud.documentai.v1beta3.Processor.display_name]
+  // to be set. Also, the
   // [Processor.kms_key_name][google.cloud.documentai.v1beta3.Processor.kms_key_name]
   // field must be set if the processor is under CMEK.
   Processor processor = 2 [(google.api.field_behavior) = REQUIRED];
@@ -1027,9 +1043,24 @@ message TrainProcessorVersionRequest {
     TrainingMethod training_method = 3;
   }
 
+  // Options to control foundation model tuning of the processor.
+  message FoundationModelTuningOptions {
+    // Optional. The number of steps to run for model tuning. Valid values are
+    // between 1 and 400. If not provided, recommended steps will be used.
+    int32 train_steps = 2 [(google.api.field_behavior) = OPTIONAL];
+
+    // Optional. The multiplier to apply to the recommended learning rate. Valid
+    // values are between 0.1 and 10. If not provided, recommended learning rate
+    // will be used.
+    float learning_rate_multiplier = 3 [(google.api.field_behavior) = OPTIONAL];
+  }
+
   oneof processor_flags {
     // Options to control Custom Document Extraction (CDE) Processor.
     CustomDocumentExtractionOptions custom_document_extraction_options = 5;
+
+    // Options to control foundation model tuning of a processor.
+    FoundationModelTuningOptions foundation_model_tuning_options = 12;
   }
 
   // Required. The parent (project, location and processor) to create the new

google/cloud/documentai/v1beta3/document_schema.proto

@@ -96,14 +96,14 @@ message DocumentSchema {
     // Defines properties that can be part of the entity type.
     message Property {
       // Types of occurrences of the entity type in the document.  This
-      // represents the number of instances of instances of an entity, not
-      // number of mentions of an entity.  For example, a bank statement may
-      // only have one `account_number`, but this account number may be
-      // mentioned in several places on the document.  In this case the
-      // 'account_number' would be considered a `REQUIRED_ONCE` entity type. If,
-      // on the other hand, we expect a bank statement to contain the status of
-      // multiple different accounts for the customers, the occurrence type will
-      // be set to `REQUIRED_MULTIPLE`.
+      // represents the number of instances, not mentions, of an entity.
+      // For example, a bank statement might only have one
+      // `account_number`, but this account number can be mentioned in several
+      // places on the document.  In this case, the `account_number` is
+      // considered a `REQUIRED_ONCE` entity type. If, on the other hand, we
+      // expect a bank statement to contain the status of multiple different
+      // accounts for the customers, the occurrence type is set to
+      // `REQUIRED_MULTIPLE`.
       enum OccurrenceType {
         // Unspecified occurrence type.
         OCCURRENCE_TYPE_UNSPECIFIED = 0;
@@ -127,6 +127,9 @@ message DocumentSchema {
       // EntityType name.
       string name = 1;
 
+      // User defined name for the property.
+      string display_name = 6;
+
       // A reference to the value type of the property.  This type is subject
       // to the same conventions as the `Entity.base_types` field.
       string value_type = 2;

google/cloud/documentai/v1beta3/document_service.proto

@@ -135,18 +135,18 @@ enum DatasetSplitType {
   DATASET_SPLIT_UNASSIGNED = 3;
 }
 
-// Describes the labelling status of a document.
+// Describes the labeling status of a document.
 enum DocumentLabelingState {
   // Default value if the enum is not set.
   DOCUMENT_LABELING_STATE_UNSPECIFIED = 0;
 
-  // Document has been labelled.
+  // Document has been labeled.
   DOCUMENT_LABELED = 1;
 
-  // Document has not been labelled.
+  // Document has not been labeled.
   DOCUMENT_UNLABELED = 2;
 
-  // Document has been auto-labelled.
+  // Document has been auto-labeled.
   DOCUMENT_AUTO_LABELED = 3;
 }
 
@@ -315,8 +315,9 @@ message ListDocumentsRequest {
   // - String match is case sensitive (for filter `DisplayName` & `EntityType`).
   string filter = 4 [(google.api.field_behavior) = OPTIONAL];
 
-  // Optional. Controls if the ListDocuments request requires a total size
-  // of matched documents. See ListDocumentsResponse.total_size.
+  // Optional. Controls if the request requires a total size of matched
+  // documents. See
+  // [ListDocumentsResponse.total_size][google.cloud.documentai.v1beta3.ListDocumentsResponse.total_size].
   //
   // Enabling this flag may adversely impact performance.
   //
@@ -325,19 +326,24 @@ message ListDocumentsRequest {
 
   // Optional. Number of results to skip beginning from the `page_token` if
   // provided. https://google.aip.dev/158#skipping-results. It must be a
-  // non-negative integer. Negative values wil be rejected. Note that this is
+  // non-negative integer. Negative values will be rejected. Note that this is
   // not the number of pages to skip. If this value causes the cursor to move
-  // past the end of results, `ListDocumentsResponse.document_metadata` and
-  // `ListDocumentsResponse.next_page_token` will be empty.
+  // past the end of results,
+  // [ListDocumentsResponse.document_metadata][google.cloud.documentai.v1beta3.ListDocumentsResponse.document_metadata]
+  // and
+  // [ListDocumentsResponse.next_page_token][google.cloud.documentai.v1beta3.ListDocumentsResponse.next_page_token]
+  // will be empty.
   int32 skip = 8 [(google.api.field_behavior) = OPTIONAL];
 }
 
 message ListDocumentsResponse {
   // Document metadata corresponding to the listed documents.
   repeated DocumentMetadata document_metadata = 1;
 
-  // A token, which can be sent as `page_token` to retrieve the next page.
-  // If this field is omitted, there are no subsequent pages.
+  // A token, which can be sent as
+  // [ListDocumentsRequest.page_token][google.cloud.documentai.v1beta3.ListDocumentsRequest.page_token]
+  // to retrieve the next page. If this field is omitted, there are no
+  // subsequent pages.
   string next_page_token = 2;
 
   // Total count of documents queried.
@@ -430,7 +436,7 @@ message DocumentMetadata {
   // Type of the dataset split to which the document belongs.
   DatasetSplitType dataset_type = 3;
 
-  // Labelling state of the document.
+  // Labeling state of the document.
   DocumentLabelingState labeling_state = 5;
 
   // The display name of the document.