feat: [google-cloud-documentai] Added a field for enabling returning images and bounding boxes from layout parser processor (#13822)

- [ ] Regenerate this pull request now. PiperOrigin-RevId: 750248234 Source-Link: googleapis/googleapis@3bc2597 Source-Link: googleapis/googleapis-gen@fca4dd3 Copy-Tag: eyJwIjoicGFja2FnZXMvZ29vZ2xlLWNsb3VkLWRvY3VtZW50YWkvLk93bEJvdC55YW1sIiwiaCI6ImZjYTRkZDNjNmQ5ZTY1NTViODc5ODY3OTc1MjljNjdjZTllODA4NjcifQ== --------- Co-authored-by: Owl Bot <gcf-owl-bot[bot]@users.noreply.github.com>

Author: gcf-owl-bot[bot]

packages/google-cloud-documentai/google/cloud/documentai_v1/types/document.py

@@ -66,6 +66,9 @@ class Document(proto.Message):
  representations use base64.
 
  This field is a member of `oneof`_ ``source``.
+ docid (str):
+ Optional. An internal identifier for
+ document. Should be loggable (no PII).
  mime_type (str):
  An IANA published `media type (MIME
  type) <https://www.iana.org/assignments/media-types/media-types.xhtml>`__.
@@ -1851,6 +1854,8 @@ class DocumentLayoutBlock(proto.Message):
  ID of the block.
  page_span (google.cloud.documentai_v1.types.Document.DocumentLayout.DocumentLayoutBlock.LayoutPageSpan):
  Page span of the block.
+ bounding_box (google.cloud.documentai_v1.types.BoundingPoly):
+ Identifies the bounding box for the block.
  """
 
  class LayoutPageSpan(proto.Message):
@@ -2050,6 +2055,11 @@ class LayoutListEntry(proto.Message):
  number=5,
  message="Document.DocumentLayout.DocumentLayoutBlock.LayoutPageSpan",
  )
+ bounding_box: geometry.BoundingPoly = proto.Field(
+ proto.MESSAGE,
+ number=6,
+ message=geometry.BoundingPoly,
+ )
 
  blocks: MutableSequence[
  "Document.DocumentLayout.DocumentLayoutBlock"
@@ -2192,6 +2202,10 @@ class ChunkPageFooter(proto.Message):
  number=2,
  oneof="source",
  )
+ docid: str = proto.Field(
+ proto.STRING,
+ number=15,
+ )
  mime_type: str = proto.Field(
  proto.STRING,
  number=3,

packages/google-cloud-documentai/google/cloud/documentai_v1/types/document_processor_service.py

@@ -135,6 +135,12 @@ class LayoutConfig(proto.Message):
  chunking_config (google.cloud.documentai_v1.types.ProcessOptions.LayoutConfig.ChunkingConfig):
  Optional. Config for chunking in layout
  parser processor.
+ return_images (bool):
+ Optional. Whether to include images in layout
+ parser processor response.
+ return_bounding_boxes (bool):
+ Optional. Whether to include bounding boxes
+ in layout parser processor response.
  """
 
  class ChunkingConfig(proto.Message):
@@ -163,6 +169,14 @@ class ChunkingConfig(proto.Message):
  number=1,
  message="ProcessOptions.LayoutConfig.ChunkingConfig",
  )
+ return_images: bool = proto.Field(
+ proto.BOOL,
+ number=2,
+ )
+ return_bounding_boxes: bool = proto.Field(
+ proto.BOOL,
+ number=3,
+ )
 
  class IndividualPageSelector(proto.Message):
  r"""A list of individual page numbers.