Package google.cloud.documentai.v1

The basic metadata of the long-running operation.

DeleteProcessorRequest

Request message for the DeleteProcessor method.

Fields

Fields
`name`	`string` Required. The processor resource name to be deleted. Authorization requires the following IAM permission on the specified resource `name`: `documentai.processors.delete`

name

string

Required. The processor resource name to be deleted.

Authorization requires the following IAM permission on the specified resource name:

documentai.processors.delete

DeleteProcessorVersionMetadata

The long-running operation metadata for the DeleteProcessorVersion method.

Fields

common_metadata

The basic metadata of the long-running operation.

DeleteProcessorVersionRequest

Request message for the DeleteProcessorVersion method.

Fields

Fields
`name`	`string` Required. The processor version resource name to be deleted. Authorization requires the following IAM permission on the specified resource `name`: `documentai.processorVersions.delete`

name

string

Required. The processor version resource name to be deleted.

Authorization requires the following IAM permission on the specified resource name:

documentai.processorVersions.delete

DeployProcessorVersionMetadata

The long-running operation metadata for the DeployProcessorVersion method.

Fields

common_metadata

The basic metadata of the long-running operation.

DeployProcessorVersionRequest

Request message for the DeployProcessorVersion method.

Fields

Fields
`name`	`string` Required. The processor version resource name to be deployed. Authorization requires the following IAM permission on the specified resource `name`: `documentai.processorVersions.update`

name

string

Required. The processor version resource name to be deployed.

Authorization requires the following IAM permission on the specified resource name:

documentai.processorVersions.update

DeployProcessorVersionResponse

This type has no fields.

Response message for the DeployProcessorVersion method.

DisableProcessorMetadata

The long-running operation metadata for the DisableProcessor method.

Fields

common_metadata

The basic metadata of the long-running operation.

DisableProcessorRequest

Request message for the DisableProcessor method.

Fields

Fields
`name`	`string` Required. The processor resource name to be disabled. Authorization requires the following IAM permission on the specified resource `name`: `documentai.processors.update`

name

string

Required. The processor resource name to be disabled.

Authorization requires the following IAM permission on the specified resource name:

documentai.processors.update

DisableProcessorResponse

This type has no fields.

Response message for the DisableProcessor method. Intentionally empty proto for adding fields in future.

Document

Document represents the canonical document resource in Document AI. It is an interchange format that provides insights into documents and allows for collaboration between users and Document AI to iterate and optimize for quality.

Fields
`mime_type`	`string` An IANA published media type (MIME type).
`text`	`string` Optional. UTF-8 encoded text in reading order from the document.
`text_styles[] (deprecated)`	`Style` This item is deprecated! Styles for the `Document.text`.
`pages[]`	`Page` Visual page layout for the `Document`.
`entities[]`	`Entity` A list of entities detected on `Document.text`. For document shards, entities in this list may cross shard boundaries.
`entity_relations[]`	`EntityRelation` Placeholder. Relationship among `Document.entities`.
`text_changes[]`	`TextChange` Placeholder. A list of text corrections made to `Document.text`. This is usually used for annotating corrections to OCR mistakes. Text changes for a given revision may not overlap with each other.
`shard_info`	`ShardInfo` Information about the sharding if this document is sharded part of a larger document. If the document is not sharded, this message is not specified.
`error`	`Status` Any error that occurred while processing this document.
`revisions[]`	`Revision` Placeholder. Revision history of this document.
`document_layout`	`DocumentLayout` Parsed layout of the document.
`chunked_document`	`ChunkedDocument` Document chunked based on chunking config.
Union field `source`. Original source document from the user. `source` can be only one of the following:
`uri`	`string` Optional. Currently supports Google Cloud Storage URI of the form `gs://bucket_name/object_name`. Object versioning is not supported. For more information, refer to Google Cloud Storage Request URIs.
`content`	`bytes` Optional. Inline document content, represented as a stream of bytes. Note: As with all `bytes` fields, protobuffers use a pure binary representation, whereas JSON representations use base64.

ChunkedDocument

Represents the chunks that the document is divided into.

Fields

Fields
`chunks[]`	`Chunk` List of chunks.

chunks[]

Chunk

List of chunks.

Chunk

Represents a chunk.

Fields
`chunk_id`	`string` ID of the chunk.
`source_block_ids[]`	`string` Unused.
`content`	`string` Text content of the chunk.
`page_span`	`ChunkPageSpan` Page span of the chunk.
`page_headers[]`	`ChunkPageHeader` Page headers associated with the chunk.
`page_footers[]`	`ChunkPageFooter` Page footers associated with the chunk.

ChunkPageFooter

Represents the page footer associated with the chunk.

Fields

Fields
`text`	`string` Footer in text format.
`page_span`	`ChunkPageSpan` Page span of the footer.

text

string

Footer in text format.

page_span

ChunkPageSpan

Page span of the footer.

ChunkPageHeader

Represents the page header associated with the chunk.

Fields

Fields
`text`	`string` Header in text format.
`page_span`	`ChunkPageSpan` Page span of the header.

text

string

Header in text format.

page_span

ChunkPageSpan

Page span of the header.

ChunkPageSpan

Represents where the chunk starts and ends in the document.

Fields

Fields
`page_start`	`int32` Page where chunk starts in the document.
`page_end`	`int32` Page where chunk ends in the document.

page_start

int32

Page where chunk starts in the document.

page_end

int32

Page where chunk ends in the document.

DocumentLayout

Represents the parsed layout of a document as a collection of blocks that the document is divided into.

Fields

Fields
`blocks[]`	`DocumentLayoutBlock` List of blocks in the document.

blocks[]

List of blocks in the document.

DocumentLayoutBlock

Represents a block. A block could be one of the various types (text, table, list) supported.

Fields
`block_id`	`string` ID of the block.
`page_span`	`LayoutPageSpan` Page span of the block.
Union field `block`. `block` can be only one of the following:
`text_block`	`LayoutTextBlock` Block consisting of text content.
`table_block`	`LayoutTableBlock` Block consisting of table content/structure.
`list_block`	`LayoutListBlock` Block consisting of list content/structure.

LayoutListBlock

Represents a list type block.

Fields

Fields
`list_entries[]`	`LayoutListEntry` List entries that constitute a list block.
`type`	`string` Type of the list_entries (if exist). Available options are `ordered` and `unordered`.

list_entries[]

LayoutListEntry

List entries that constitute a list block.

type

string

Type of the list_entries (if exist). Available options are ordered and unordered.

LayoutListEntry

Represents an entry in the list.

Fields

Fields
`blocks[]`	`DocumentLayoutBlock` A list entry is a list of blocks. Repeated blocks support further hierarchies and nested blocks.

blocks[]

A list entry is a list of blocks. Repeated blocks support further hierarchies and nested blocks.

LayoutPageSpan

Represents where the block starts and ends in the document.

Fields

page_start

int32

Page where block starts in the document.

page_end

int32

Page where block ends in the document.

LayoutTableBlock

Represents a table type block.

Fields

header_rows[]

LayoutTableRow

Header rows at the top of the table.

body_rows[]

LayoutTableRow

Body rows containing main table content.

caption

string

Table caption/title.

LayoutTableCell

Represents a cell in a table row.

Fields

blocks[]

A table cell is a list of blocks. Repeated blocks support further hierarchies and nested blocks.

row_span

int32

How many rows this cell spans.

col_span

int32

How many columns this cell spans.

LayoutTableRow

Represents a row in a table.

Fields

cells[]

LayoutTableCell

A table row is a list of table cells.

LayoutTextBlock

Represents a text type block.

Fields

text

string

Text content stored in the block.

type

string

Type of the text in the block. Available options are: paragraph, subtitle, heading-1, heading-2, heading-3, heading-4, heading-5, header, footer.

blocks[]

A text block could further have child blocks. Repeated blocks support further hierarchies and nested blocks.

Entity

An entity that could be a phrase in the text or a property that belongs to the document. It is a known entity type, such as a person, an organization, or location.

Fields
`text_anchor`	`TextAnchor` Optional. Provenance of the entity. Text anchor indexing into the `Document.text`.
`type`	`string` Required. Entity type from a schema e.g. `Address`.
`mention_text`	`string` Optional. Text value of the entity e.g. `1600 Amphitheatre Pkwy`.
`mention_id`	`string` Optional. Deprecated. Use `id` field instead.
`confidence`	`float` Optional. Confidence of detected Schema entity. Range `[0, 1]`.
`page_anchor`	`PageAnchor` Optional. Represents the provenance of this entity wrt. the location on the page where it was found.
`id`	`string` Optional. Canonical id. This will be a unique value in the entity list for this document.
`normalized_value`	`NormalizedValue` Optional. Normalized entity value. Absent if the extracted value could not be converted or the type (e.g. address) is not supported for certain parsers. This field is also only populated for certain supported document types.
`properties[]`	`Entity` Optional. Entities can be nested to form a hierarchical data structure representing the content in the document.
`provenance`	`Provenance` Optional. The history of this annotation.
`redacted`	`bool` Optional. Whether the entity will be redacted for de-identification purposes.

NormalizedValue

Parsed and normalized entity value.

Fields
`text`	`string` Optional. An optional field to store a normalized string. For some entity types, one of respective `structured_value` fields may also be populated. Also not all the types of `structured_value` will be normalized. For example, some processors may not generate `float` or `integer` normalized text by default. Below are sample formats mapped to structured values. Money/Currency type (`money_value`) is in the ISO 4217 text format. Date type (`date_value`) is in the ISO 8601 text format. Datetime type (`datetime_value`) is in the ISO 8601 text format.
Union field `structured_value`. An optional structured entity value. Must match entity type defined in schema if known. If this field is present, the `text` field could also be populated. `structured_value` can be only one of the following:
`money_value`	`Money` Money value. See also: https://github.com/googleapis/googleapis/blob/master/google/type/money.proto
`date_value`	`Date` Date value. Includes year, month, day. See also: https://github.com/googleapis/googleapis/blob/master/google/type/date.proto
`datetime_value`	`DateTime` DateTime value. Includes date, time, and timezone. See also: https://github.com/googleapis/googleapis/blob/master/google/type/datetime.proto
`address_value`	`PostalAddress` Postal address. See also: https://github.com/googleapis/googleapis/blob/master/google/type/postal_address.proto
`boolean_value`	`bool` Boolean value. Can be used for entities with binary values, or for checkboxes.
`integer_value`	`int32` Integer value.
`float_value`	`float` Float value.

EntityRelation

Relationship between Entities.

Fields

subject_id

string

Subject entity id.

object_id

string

Object entity id.

relation

string

Relationship description.

Page

A page in a Document.

Fields
`page_number`	`int32` 1-based index for current `Page` in a parent `Document`. Useful when a page is taken out of a `Document` for individual processing.
`image`	`Image` Rendered image for this page. This image is preprocessed to remove any skew, rotation, and distortions such that the annotation bounding boxes can be upright and axis-aligned.
`transforms[]`	`Matrix` Transformation matrices that were applied to the original document image to produce `Page.image`.
`dimension`	`Dimension` Physical dimension of the page.
`layout`	`Layout` `Layout` for the page.
`detected_languages[]`	`DetectedLanguage` A list of detected languages together with confidence.
`blocks[]`	`Block` A list of visually detected text blocks on the page. A block has a set of lines (collected into paragraphs) that have a common line-spacing and orientation.
`paragraphs[]`	`Paragraph` A list of visually detected text paragraphs on the page. A collection of lines that a human would perceive as a paragraph.
`lines[]`	`Line` A list of visually detected text lines on the page. A collection of tokens that a human would perceive as a line.
`tokens[]`	`Token` A list of visually detected tokens on the page.
`visual_elements[]`	`VisualElement` A list of detected non-text visual elements e.g. checkbox, signature etc. on the page.
`tables[]`	`Table` A list of visually detected tables on the page.
`form_fields[]`	`FormField` A list of visually detected form fields on the page.
`symbols[]`	`Symbol` A list of visually detected symbols on the page.
`detected_barcodes[]`	`DetectedBarcode` A list of detected barcodes.
`image_quality_scores`	`ImageQualityScores` Image quality scores.
`provenance (deprecated)`	`Provenance` This item is deprecated! The history of this page.

Block

A block has a set of lines (collected into paragraphs) that have a common line-spacing and orientation.

Fields

layout

Layout for Block.

detected_languages[]

A list of detected languages together with confidence.

provenance
(deprecated)

The history of this annotation.

DetectedBarcode

A detected barcode.

Fields

layout

Layout for DetectedBarcode.

barcode

Barcode

Detailed barcode information of the DetectedBarcode.

DetectedLanguage

Detected language for a structural component.

Fields

language_code

string

The BCP-47 language code, such as en-US or sr-Latn.

confidence

float

Confidence of detected language. Range [0, 1].

Dimension

Dimension for the page.

Fields

width

float

Page width.

height

float

Page height.

unit

string

Dimension unit.

FormField

A form field detected on the page.

Fields
`field_name`	`Layout` `Layout` for the `FormField` name. e.g. `Address`, `Email`, `Grand total`, `Phone number`, etc.
`field_value`	`Layout` `Layout` for the `FormField` value.
`name_detected_languages[]`	`DetectedLanguage` A list of detected languages for name together with confidence.
`value_detected_languages[]`	`DetectedLanguage` A list of detected languages for value together with confidence.
`value_type`	`string` If the value is non-textual, this field represents the type. Current valid values are: blank (this indicates the `field_value` is normal text) `unfilled_checkbox` `filled_checkbox`
`corrected_key_text`	`string` Created for Labeling UI to export key text. If corrections were made to the text identified by the `field_name.text_anchor`, this field will contain the correction.
`corrected_value_text`	`string` Created for Labeling UI to export value text. If corrections were made to the text identified by the `field_value.text_anchor`, this field will contain the correction.
`provenance`	`Provenance` The history of this annotation.

Image

Rendered image contents for this page.

Fields
`content`	`bytes` Raw byte content of the image.
`mime_type`	`string` Encoding media type (MIME type) for the image.
`width`	`int32` Width of the image in pixels.
`height`	`int32` Height of the image in pixels.

ImageQualityScores

Image quality scores for the page image.

Fields

quality_score

float

The overall quality score. Range [0, 1] where 1 is perfect quality.

detected_defects[]

DetectedDefect

A list of detected defects.

DetectedDefect

Image Quality Defects

Fields

type

string

Name of the defect type. Supported values are:

quality/defect_blurry
quality/defect_noisy
quality/defect_dark
quality/defect_faint
quality/defect_text_too_small
quality/defect_document_cutoff
quality/defect_text_cutoff
quality/defect_glare

confidence

float

Confidence of detected defect. Range [0, 1] where 1 indicates strong confidence that the defect exists.

Layout

Visual element describing a layout unit on a page.

Fields
`text_anchor`	`TextAnchor` Text anchor indexing into the `Document.text`.
`confidence`	`float` Confidence of the current `Layout` within context of the object this layout is for. e.g. confidence can be for a single token, a table, a visual element, etc. depending on context. Range `[0, 1]`.
`bounding_poly`	`BoundingPoly` The bounding polygon for the `Layout`.
`orientation`	`Orientation` Detected orientation for the `Layout`.

Orientation

Detected human reading orientation.

Enums
`ORIENTATION_UNSPECIFIED`	Unspecified orientation.
`PAGE_UP`	Orientation is aligned with page up.
`PAGE_RIGHT`	Orientation is aligned with page right. Turn the head 90 degrees clockwise from upright to read.
`PAGE_DOWN`	Orientation is aligned with page down. Turn the head 180 degrees from upright to read.
`PAGE_LEFT`	Orientation is aligned with page left. Turn the head 90 degrees counterclockwise from upright to read.

Line

A collection of tokens that a human would perceive as a line. Does not cross column boundaries, can be horizontal, vertical, etc.

Fields

layout

Layout for Line.

detected_languages[]

A list of detected languages together with confidence.

provenance
(deprecated)

The history of this annotation.

Matrix

Representation for transformation matrix, intended to be compatible and used with OpenCV format for image manipulation.

Fields
`rows`	`int32` Number of rows in the matrix.
`cols`	`int32` Number of columns in the matrix.
`type`	`int32` This encodes information about what data type the matrix uses. For example, 0 (CV_8U) is an unsigned 8-bit image. For the full list of OpenCV primitive data types, please refer to https://docs.opencv.org/4.3.0/d1/d1b/group__core__hal__interface.html
`data`	`bytes` The matrix data.

Paragraph

A collection of lines that a human would perceive as a paragraph.

Fields

layout

Layout for Paragraph.

detected_languages[]

A list of detected languages together with confidence.

provenance
(deprecated)

The history of this annotation.

Symbol

A detected symbol.

Fields

layout

Layout for Symbol.

detected_languages[]

A list of detected languages together with confidence.

Table

A table representation similar to HTML table structure.

Fields
`layout`	`Layout` `Layout` for `Table`.
`header_rows[]`	`TableRow` Header rows of the table.
`body_rows[]`	`TableRow` Body rows of the table.
`detected_languages[]`	`DetectedLanguage` A list of detected languages together with confidence.
`provenance (deprecated)`	`Provenance` This item is deprecated! The history of this table.

TableCell

A cell representation inside the table.

Fields
`layout`	`Layout` `Layout` for `TableCell`.
`row_span`	`int32` How many rows this cell spans.
`col_span`	`int32` How many columns this cell spans.
`detected_languages[]`	`DetectedLanguage` A list of detected languages together with confidence.

TableRow

A row of table cells.

Fields

cells[]

TableCell

Cells that make up this row.

Token

A detected token.

Fields
`layout`	`Layout` `Layout` for `Token`.
`detected_break`	`DetectedBreak` Detected break at the end of a `Token`.
`detected_languages[]`	`DetectedLanguage` A list of detected languages together with confidence.
`provenance (deprecated)`	`Provenance` This item is deprecated! The history of this annotation.
`style_info`	`StyleInfo` Text style attributes.

DetectedBreak

Detected break at the end of a Token.

Fields

type

Type

Detected break type.

Type

Enum to denote the type of break found.

Enums
`TYPE_UNSPECIFIED`	Unspecified break type.
`SPACE`	A single whitespace.
`WIDE_SPACE`	A wider whitespace.
`HYPHEN`	A hyphen that indicates that a token has been split across lines.

StyleInfo

Font and other text style attributes.

Fields
`font_size`	`int32` Font size in points (`1` point is `¹⁄₇₂` inches).
`pixel_font_size`	`double` Font size in pixels, equal to unrounded `font_size` * resolution ÷ `72.0`.
`letter_spacing`	`double` Letter spacing in points.
`font_type`	`string` Name or style of the font.
`bold`	`bool` Whether the text is bold (equivalent to `font_weight` is at least `700`).
`italic`	`bool` Whether the text is italic.
`underlined`	`bool` Whether the text is underlined.
`strikeout`	`bool` Whether the text is strikethrough. This feature is not supported yet.
`subscript`	`bool` Whether the text is a subscript. This feature is not supported yet.
`superscript`	`bool` Whether the text is a superscript. This feature is not supported yet.
`smallcaps`	`bool` Whether the text is in small caps. This feature is not supported yet.
`font_weight`	`int32` TrueType weight on a scale `100` (thin) to `1000` (ultra-heavy). Normal is `400`, bold is `700`.
`handwritten`	`bool` Whether the text is handwritten.
`text_color`	`Color` Color of the text.
`background_color`	`Color` Color of the background.

VisualElement

Detected non-text visual elements e.g. checkbox, signature etc. on the page.

Fields

layout

Layout for VisualElement.

type

string

Type of the VisualElement.

detected_languages[]

A list of detected languages together with confidence.

PageAnchor

Referencing the visual context of the entity in the Document.pages. Page anchors can be cross-page, consist of multiple bounding polygons and optionally reference specific layout element types.

Fields

page_refs[]

PageRef

One or more references to visual page elements

PageRef

Represents a weak reference to a page element within a document.

Fields
`page`	`int64` Required. Index into the `Document.pages` element, for example using `[Document.pages][page_refs.page]` to locate the related page element. This field is skipped when its value is the default `0`. See https://developers.google.com/protocol-buffers/docs/proto3#json.
`layout_type`	`LayoutType` Optional. The type of the layout element that is being referenced if any.
`layout_id (deprecated)`	`string` This item is deprecated! Optional. Deprecated. Use `PageRef.bounding_poly` instead.
`bounding_poly`	`BoundingPoly` Optional. Identifies the bounding polygon of a layout element on the page. If `layout_type` is set, the bounding polygon must be exactly the same to the layout element it's referring to.
`confidence`	`float` Optional. Confidence of detected page element, if applicable. Range `[0, 1]`.

LayoutType

The type of layout that is being referenced.

Enums
`LAYOUT_TYPE_UNSPECIFIED`	Layout Unspecified.
`BLOCK`	References a `Page.blocks` element.
`PARAGRAPH`	References a `Page.paragraphs` element.
`LINE`	References a `Page.lines` element.
`TOKEN`	References a `Page.tokens` element.
`VISUAL_ELEMENT`	References a `Page.visual_elements` element.
`TABLE`	Refrrences a `Page.tables` element.
`FORM_FIELD`	References a `Page.form_fields` element.

Provenance

Structure to identify provenance relationships between annotations in different revisions.

Fields
`revision (deprecated)`	`int32` This item is deprecated! The index of the revision that produced this element.
`id (deprecated)`	`int32` This item is deprecated! The Id of this operation. Needs to be unique within the scope of the revision.
`parents[]`	`Parent` References to the original elements that are replaced.
`type`	`OperationType` The type of provenance operation.

OperationType

If a processor or agent does an explicit operation on existing elements.

Enums
`OPERATION_TYPE_UNSPECIFIED`	Operation type unspecified. If no operation is specified a provenance entry is simply used to match against a `parent`.
`ADD`	Add an element.
`REMOVE`	Remove an element identified by `parent`.
`UPDATE`	Updates any fields within the given provenance scope of the message. It overwrites the fields rather than replacing them. Use this when you want to update a field value of an entity without also updating all the child properties.
`REPLACE`	Currently unused. Replace an element identified by `parent`.
`EVAL_REQUESTED`	Deprecated. Request human review for the element identified by `parent`. This item is deprecated!
`EVAL_APPROVED`	Deprecated. Element is reviewed and approved at human review, confidence will be set to 1.0. This item is deprecated!
`EVAL_SKIPPED`	Deprecated. Element is skipped in the validation process. This item is deprecated!

Parent

The parent element the current element is based on. Used for referencing/aligning, removal and replacement operations.

Fields

revision

int32

The index of the index into current revision's parent_ids list.

index

int32

The index of the parent item in the corresponding item list (eg. list of entities, properties within entities, etc.) in the parent revision.

id
(deprecated)

int32

The id of the parent provenance.

Revision

Contains past or forward revisions of this document.

Fields
`id`	`string` Id of the revision, internally generated by doc proto storage. Unique within the context of the document.
`parent[] (deprecated)`	`int32` This item is deprecated! The revisions that this revision is based on. This can include one or more parent (when documents are merged.) This field represents the index into the `revisions` field.
`parent_ids[]`	`string` The revisions that this revision is based on. Must include all the ids that have anything to do with this revision - eg. there are `provenance.parent.revision` fields that index into this field.
`create_time`	`Timestamp` The time that the revision was created, internally generated by doc proto storage at the time of create.
`human_review`	`HumanReview` Human Review information of this revision.
Union field `source`. Who/what made the change `source` can be only one of the following:
`agent`	`string` If the change was made by a person specify the name or id of that person.
`processor`	`string` If the annotation was made by processor identify the processor by its resource name.

HumanReview

Human Review information of the document.

Fields

state

string

Human review state. e.g. requested, succeeded, rejected.

state_message

string

A message providing more details about the current state of processing. For example, the rejection reason when the state is rejected.

ShardInfo

For a large document, sharding may be performed to produce several document shards. Each document shard contains this field to detail which shard it is.

Fields

shard_index

int64

The 0-based index of this shard.

shard_count

int64

Total number of shards.

text_offset

int64

The index of the first character in Document.text in the overall document global text.

Style

Annotation for common text style attributes. This adheres to CSS conventions as much as possible.

Fields
`text_anchor`	`TextAnchor` Text anchor indexing into the `Document.text`.
`color`	`Color` Text color.
`background_color`	`Color` Text background color.
`font_weight`	`string` Font weight. Possible values are `normal`, `bold`, `bolder`, and `lighter`.
`text_style`	`string` Text style. Possible values are `normal`, `italic`, and `oblique`.
`text_decoration`	`string` Text decoration. Follows CSS standard.
`font_size`	`FontSize` Font size.
`font_family`	`string` Font family such as `Arial`, `Times New Roman`. https://www.w3schools.com/cssref/pr_font_font-family.asp

TextAnchor

Text reference indexing into the Document.text.

Fields

text_segments[]

TextSegment

The text segments from the Document.text.

content

string

Contains the content of the text span so that users do not have to look it up in the text_segments. It is always populated for formFields.

TextSegment

A text segment in the Document.text. The indices may be out of bounds which indicate that the text extends into another document shard for large sharded documents. See ShardInfo.text_offset

Fields

start_index

int64

TextSegment start UTF-8 char index in the Document.text.

end_index

int64

TextSegment half open end UTF-8 char index in the Document.text.

TextChange

This message is used for text changes aka. OCR corrections.

Fields

text_anchor

TextAnchor

Provenance of the correction. Text anchor indexing into the Document.text. There can only be a single TextAnchor.text_segments element. If the start and end index of the text segment are the same, the text change is inserted before that index.

changed_text

string

The text that replaces the text identified in the text_anchor.

provenance[]
(deprecated)

The history of this annotation.

DocumentOutputConfig

Config that controls the output of documents. All documents will be written as a JSON file.

Fields

Union field destination. The destination of the results. destination can be only one of the following:

gcs_output_config

GcsOutputConfig

Output config to write the results to Cloud Storage.

GcsOutputConfig

The configuration used when outputting documents.

Fields

gcs_uri

string

The Cloud Storage uri (a directory) of the output.

field_mask

FieldMask

Specifies which fields to include in the output documents. Only supports top level document and pages field so it must be in the form of {document_field_name} or pages.{page_field_name}.

sharding_config

ShardingConfig

Specifies the sharding config for the output document.

ShardingConfig

The sharding config for the output document.

Fields

pages_per_shard

int32

The number of pages per shard.

pages_overlap

int32

The number of overlapping pages between consecutive shards.

DocumentSchema

The schema defines the output of the processed document by a processor.

Fields
`display_name`	`string` Display name to show to users.
`description`	`string` Description of the schema.
`entity_types[]`	`EntityType` Entity types of the schema.
`metadata`	`Metadata` Metadata of the schema.

EntityType

EntityType is the wrapper of a label of the corresponding model with detailed attributes and limitations for entity-based processors. Multiple types can also compose a dependency tree to represent nested types.

Fields
`display_name`	`string` User defined name for the type.
`name`	`string` Name of the type. It must be unique within the schema file and cannot be a "Common Type". The following naming conventions are used: Use `snake_casing`. Name matching is case-sensitive. Maximum 64 characters. Must start with a letter. Allowed characters: ASCII letters `[a-z0-9_-]`. (For backward compatibility internal infrastructure and tooling can handle any ascii character.) The `/` is sometimes used to denote a property of a type. For example `line_item/amount`. This convention is deprecated, but will still be honored for backward compatibility.
`base_types[]`	`string` The entity type that this type is derived from. For now, one and only one should be set.
`properties[]`	`Property` Description the nested structure, or composition of an entity.
Union field `value_source`. `value_source` can be only one of the following:
`enum_values`	`EnumValues` If specified, lists all the possible values for this entity. This should not be more than a handful of values. If the number of values is >10 or could change frequently use the `EntityType.value_ontology` field and specify a list of all possible values in a value ontology file.

EnumValues

Defines the a list of enum values.

Fields

values[]

string

The individual values that this enum values type can include.

Property

Defines properties that can be part of the entity type.

Fields
`name`	`string` The name of the property. Follows the same guidelines as the EntityType name.
`display_name`	`string` User defined name for the property.
`value_type`	`string` A reference to the value type of the property. This type is subject to the same conventions as the `Entity.base_types` field.
`occurrence_type`	`OccurrenceType` Occurrence type limits the number of instances an entity type appears in the document.

OccurrenceType

Types of occurrences of the entity type in the document. This 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.

Enums
`OCCURRENCE_TYPE_UNSPECIFIED`	Unspecified occurrence type.
`OPTIONAL_ONCE`	There will be zero or one instance of this entity type. The same entity instance may be mentioned multiple times.
`OPTIONAL_MULTIPLE`	The entity type will appear zero or multiple times.
`REQUIRED_ONCE`	The entity type will only appear exactly once. The same entity instance may be mentioned multiple times.
`REQUIRED_MULTIPLE`	The entity type will appear once or more times.

Metadata

Metadata for global schema behavior.

Fields
`document_splitter`	`bool` If true, a `document` entity type can be applied to subdocument (splitting). Otherwise, it can only be applied to the entire document (classification).
`document_allow_multiple_labels`	`bool` If true, on a given page, there can be multiple `document` annotations covering it.
`prefixed_naming_on_properties`	`bool` If set, all the nested entities must be prefixed with the parents.
`skip_naming_validation`	`bool` If set, we will skip the naming format validation in the schema. So the string values in `DocumentSchema.EntityType.name` and `DocumentSchema.EntityType.Property.name` will not be checked.

EnableProcessorMetadata

The long-running operation metadata for the EnableProcessor method.

Fields

common_metadata

The basic metadata of the long-running operation.

EnableProcessorRequest

Request message for the EnableProcessor method.

Fields

name

string

Required. The processor resource name to be enabled.

Authorization requires the following IAM permission on the specified resource name:

documentai.processors.update

EnableProcessorResponse

This type has no fields.

Response message for the EnableProcessor method. Intentionally empty proto for adding fields in future.

EvaluateProcessorVersionMetadata

Metadata of the EvaluateProcessorVersion method.

Fields

common_metadata

BatchDocumentsInputConfig

The basic metadata of the long-running operation.

EvaluateProcessorVersionRequest

Evaluates the given ProcessorVersion against the supplied documents.

Fields

processor_version

string

Required. The resource name of the ProcessorVersion to evaluate. projects/{project}/locations/{location}/processors/{processor}/processorVersions/{processorVersion}

Authorization requires the following IAM permission on the specified resource processorVersion:

documentai.evaluations.create

evaluation_documents

Optional. The documents used in the evaluation. If unspecified, use the processor's dataset as evaluation input.

EvaluateProcessorVersionResponse

Response of the EvaluateProcessorVersion method.

Fields

evaluation

string

The resource name of the created evaluation.

Evaluation

An evaluation of a ProcessorVersion's performance.

Fields
`name`	`string` The resource name of the evaluation. Format: `projects/{project}/locations/{location}/processors/{processor}/processorVersions/{processor_version}/evaluations/{evaluation}`
`create_time`	`Timestamp` The time that the evaluation was created.
`document_counters`	`Counters` Counters for the documents used in the evaluation.
`all_entities_metrics`	`MultiConfidenceMetrics` Metrics for all the entities in aggregate.
`entity_metrics`	`map<string, MultiConfidenceMetrics>` Metrics across confidence levels, for different entities.
`kms_key_name`	`string` The KMS key name used for encryption.
`kms_key_version_name`	`string` The KMS key version with which data is encrypted.

ConfidenceLevelMetrics

Evaluations metrics, at a specific confidence level.

Fields

confidence_level

float

The confidence level.

metrics

Metrics

The metrics at the specific confidence level.

Counters

Evaluation counters for the documents that were used.

Fields
`input_documents_count`	`int32` How many documents were sent for evaluation.
`invalid_documents_count`	`int32` How many documents were not included in the evaluation as they didn't pass validation.
`failed_documents_count`	`int32` How many documents were not included in the evaluation as Document AI failed to process them.
`evaluated_documents_count`	`int32` How many documents were used in the evaluation.

Metrics

Evaluation metrics, either in aggregate or about a specific entity.

Fields
`precision`	`float` The calculated precision.
`recall`	`float` The calculated recall.
`f1_score`	`float` The calculated f1 score.
`predicted_occurrences_count`	`int32` The amount of occurrences in predicted documents.
`ground_truth_occurrences_count`	`int32` The amount of occurrences in ground truth documents.
`predicted_document_count`	`int32` The amount of documents with a predicted occurrence.
`ground_truth_document_count`	`int32` The amount of documents with a ground truth occurrence.
`true_positives_count`	`int32` The amount of true positives.
`false_positives_count`	`int32` The amount of false positives.
`false_negatives_count`	`int32` The amount of false negatives.
`total_documents_count`	`int32` The amount of documents that had an occurrence of this label.

MultiConfidenceMetrics

Metrics across multiple confidence levels.

Fields
`confidence_level_metrics[]`	`ConfidenceLevelMetrics` Metrics across confidence levels with fuzzy matching enabled.
`confidence_level_metrics_exact[]`	`ConfidenceLevelMetrics` Metrics across confidence levels with only exact matching.
`auprc`	`float` The calculated area under the precision recall curve (AUPRC), computed by integrating over all confidence thresholds.
`estimated_calibration_error`	`float` The Estimated Calibration Error (ECE) of the confidence of the predicted entities.
`auprc_exact`	`float` The AUPRC for metrics with fuzzy matching disabled, i.e., exact matching only.
`estimated_calibration_error_exact`	`float` The ECE for the predicted entities with fuzzy matching disabled, i.e., exact matching only.
`metrics_type`	`MetricsType` The metrics type for the label.

MetricsType

A type that determines how metrics should be interpreted.

Enums
`METRICS_TYPE_UNSPECIFIED`	The metrics type is unspecified. By default, metrics without a particular specification are for leaf entity types (i.e., top-level entity types without child types, or child types which are not parent types themselves).
`AGGREGATE`	Indicates whether metrics for this particular label type represent an aggregate of metrics for other types instead of being based on actual TP/FP/FN values for the label type. Metrics for parent (i.e., non-leaf) entity types are an aggregate of metrics for their children.

EvaluationReference

Gives a short summary of an evaluation, and links to the evaluation itself.

Fields
`operation`	`string` The resource name of the Long Running Operation for the evaluation.
`evaluation`	`string` The resource name of the evaluation.
`aggregate_metrics`	`Metrics` An aggregate of the statistics for the evaluation with fuzzy matching on.
`aggregate_metrics_exact`	`Metrics` An aggregate of the statistics for the evaluation with fuzzy matching off.

FetchProcessorTypesRequest

Request message for the FetchProcessorTypes method. Some processor types may require the project be added to an allowlist.

Fields

parent

string

Required. The location of processor types to list. Format: projects/{project}/locations/{location}.

Authorization requires the following IAM permission on the specified resource parent:

documentai.processorTypes.list

FetchProcessorTypesResponse

Response message for the FetchProcessorTypes method.

Fields

processor_types[]

ProcessorType

The list of processor types.

GcsDocument

Specifies a document stored on Cloud Storage.

Fields

gcs_uri

string

The Cloud Storage object uri.

mime_type

string

An IANA MIME type (RFC6838) of the content.

GcsDocuments

Specifies a set of documents on Cloud Storage.

Fields

documents[]

GcsDocument

The list of documents.

GcsPrefix

Specifies all documents on Cloud Storage with a common prefix.

Fields

gcs_uri_prefix

string

The URI prefix.

GetEvaluationRequest

Retrieves a specific Evaluation.

Fields

name

string

Required. The resource name of the Evaluation to get. projects/{project}/locations/{location}/processors/{processor}/processorVersions/{processorVersion}/evaluations/{evaluation}

Authorization requires the following IAM permission on the specified resource name:

documentai.evaluations.get

GetProcessorRequest

Request message for the GetProcessor method.

Fields

name

string

Required. The processor resource name.

Authorization requires the following IAM permission on the specified resource name:

documentai.processors.get

GetProcessorTypeRequest

Request message for the GetProcessorType method.

Fields

name

string

Required. The processor type resource name.

Authorization requires the following IAM permission on the specified resource name:

documentai.processorTypes.get

GetProcessorVersionRequest

Request message for the GetProcessorVersion method.

Fields

name

string

Required. The processor resource name.

Authorization requires the following IAM permission on the specified resource name:

documentai.processorVersions.get

HumanReviewStatus

The status of human review on a processed document.

Fields

state

State

The state of human review on the processing request.

state_message

string

A message providing more details about the human review state.

human_review_operation

string

The name of the operation triggered by the processed document. This field is populated only when the state is HUMAN_REVIEW_IN_PROGRESS. It has the same response type and metadata as the long-running operation returned by ReviewDocument.

State

The final state of human review on a processed document.

Enums
`STATE_UNSPECIFIED`	Human review state is unspecified. Most likely due to an internal error.
`SKIPPED`	Human review is skipped for the document. This can happen because human review isn't enabled on the processor or the processing request has been set to skip this document.
`VALIDATION_PASSED`	Human review validation is triggered and passed, so no review is needed.
`IN_PROGRESS`	Human review validation is triggered and the document is under review.
`ERROR`	Some error happened during triggering human review, see the `state_message` for details.

ListEvaluationsRequest

Retrieves a list of evaluations for a given ProcessorVersion.

Fields

parent

string

Required. The resource name of the ProcessorVersion to list evaluations for. projects/{project}/locations/{location}/processors/{processor}/processorVersions/{processorVersion}

Authorization requires the following IAM permission on the specified resource parent:

documentai.evaluations.list

page_size

int32

The standard list page size. If unspecified, at most 5 evaluations are returned. The maximum value is 100. Values above 100 are coerced to 100.

page_token

string

A page token, received from a previous ListEvaluations call. Provide this to retrieve the subsequent page.

ListEvaluationsResponse

The response from ListEvaluations.

Fields

evaluations[]

Evaluation

The evaluations requested.

next_page_token

string

A token, which can be sent as page_token to retrieve the next page. If this field is omitted, there are no subsequent pages.

ListProcessorTypesRequest

Request message for the ListProcessorTypes method. Some processor types may require the project be added to an allowlist.

Fields

parent

string

Required. The location of processor types to list. Format: projects/{project}/locations/{location}.

Authorization requires the following IAM permission on the specified resource parent:

documentai.processorTypes.list

page_size

int32

The maximum number of processor types to return. If unspecified, at most 100 processor types will be returned. The maximum value is 500. Values above 500 will be coerced to 500.

page_token

string

Used to retrieve the next page of results, empty if at the end of the list.

ListProcessorTypesResponse

Response message for the ListProcessorTypes method.

Fields

processor_types[]

ProcessorType

The processor types.

next_page_token

string

Points to the next page, otherwise empty.

ListProcessorVersionsRequest

Request message for list all processor versions belongs to a processor.

Fields

parent

string

Required. The parent (project, location and processor) to list all versions. Format: projects/{project}/locations/{location}/processors/{processor}

Authorization requires the following IAM permission on the specified resource parent:

documentai.processorVersions.list

page_size

int32

The maximum number of processor versions to return. If unspecified, at most 10 processor versions will be returned. The maximum value is 20. Values above 20 will be coerced to 20.

page_token

string

We will return the processor versions sorted by creation time. The page token will point to the next processor version.

ListProcessorVersionsResponse

Response message for the ListProcessorVersions method.

Fields

processor_versions[]

ProcessorVersion

The list of processors.

next_page_token

string

Points to the next processor, otherwise empty.

ListProcessorsRequest

Request message for list all processors belongs to a project.

Fields

parent

string

Required. The parent (project and location) which owns this collection of Processors. Format: projects/{project}/locations/{location}

Authorization requires the following IAM permission on the specified resource parent:

documentai.processors.list

page_size

int32

The maximum number of processors to return. If unspecified, at most 50 processors will be returned. The maximum value is 100. Values above 100 will be coerced to 100.

page_token

string

We will return the processors sorted by creation time. The page token will point to the next processor.

ListProcessorsResponse

Response message for the ListProcessors method.

Fields

processors[]

Processor

The list of processors.

next_page_token

string

Points to the next processor, otherwise empty.

NormalizedVertex

A vertex represents a 2D point in the image. NOTE: the normalized vertex coordinates are relative to the original image and range from 0 to 1.

Fields

x

float

X coordinate.

y

float

Y coordinate (starts from the top of the image).

OcrConfig

Config for Document OCR.

Fields
`hints`	`Hints` Hints for the OCR model.
`enable_native_pdf_parsing`	`bool` Enables special handling for PDFs with existing text information. Results in better text extraction quality in such PDF inputs.
`enable_image_quality_scores`	`bool` Enables intelligent document quality scores after OCR. Can help with diagnosing why OCR responses are of poor quality for a given input. Adds additional latency comparable to regular OCR to the process call.
`advanced_ocr_options[]`	`string` A list of advanced OCR options to further fine-tune OCR behavior. Current valid values are: `legacy_layout`: a heuristics layout detection algorithm, which serves as an alternative to the current ML-based layout detection algorithm. Customers can choose the best suitable layout algorithm based on their situation.
`enable_symbol`	`bool` Includes symbol level OCR information if set to true.
`compute_style_info (deprecated)`	`bool` This item is deprecated! Turn on font identification model and return font style information. Deprecated, use `PremiumFeatures.compute_style_info` instead.
`disable_character_boxes_detection`	`bool` Turn off character box detector in OCR engine. Character box detection is enabled by default in OCR 2.0 (and later) processors.
`premium_features`	`PremiumFeatures` Configurations for premium OCR features.

Hints

Hints for OCR Engine

Fields

language_hints[]

string

List of BCP-47 language codes to use for OCR. In most cases, not specifying it yields the best results since it enables automatic language detection. For languages based on the Latin alphabet, setting hints is not needed. In rare cases, when the language of the text in the image is known, setting a hint will help get better results (although it will be a significant hindrance if the hint is wrong).

PremiumFeatures

Configurations for premium OCR features.

Fields

enable_selection_mark_detection

bool

Turn on selection mark detector in OCR engine. Only available in OCR 2.0 (and later) processors.

compute_style_info

bool

Turn on font identification model and return font style information.

enable_math_ocr

bool

Turn on the model that can extract LaTeX math formulas.

ProcessOptions

Options for Process API

Fields
`ocr_config`	`OcrConfig` Only applicable to `OCR_PROCESSOR` and `FORM_PARSER_PROCESSOR`. Returns error if set on other processor types.
`layout_config`	`LayoutConfig` Optional. Only applicable to `LAYOUT_PARSER_PROCESSOR`. Returns error if set on other processor types.
`schema_override`	`DocumentSchema` Optional. Override the schema of the `ProcessorVersion`. Will return an Invalid Argument error if this field is set when the underlying `ProcessorVersion` doesn't support schema override.
Union field `page_range`. 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` refers to the page number in the original document. This configuration only applies to online processing with `ProcessDocument`. `page_range` can be only one of the following:
`individual_page_selector`	`IndividualPageSelector` Which pages to process (1-indexed).
`from_start`	`int32` Only process certain pages from the start. Process all if the document has fewer pages.
`from_end`	`int32` Only process certain pages from the end, same as above.

IndividualPageSelector

A list of individual page numbers.

Fields

pages[]

int32

Optional. Indices of the pages (starting from 1).

LayoutConfig

Serving config for layout parser processor.

Fields

chunking_config

ChunkingConfig

Optional. Config for chunking in layout parser processor.

ChunkingConfig

Serving config for chunking.

Fields

chunk_size

int32

Optional. The chunk sizes to use when splitting documents, in order of level.

include_ancestor_headings

bool

Optional. Whether or not to include ancestor headings when splitting.

ProcessRequest

Request message for the ProcessDocument method.

Fields
`name`	`string` Required. The resource name of the `Processor` or `ProcessorVersion` to use for processing. If a `Processor` is specified, the server will use its `default version`. Format: `projects/{project}/locations/{location}/processors/{processor}`, or `projects/{project}/locations/{location}/processors/{processor}/processorVersions/{processorVersion}` Authorization requires one or more of the following IAM permissions on the specified resource `name`: `documentai.processors.processOnline` `documentai.processorVersions.processOnline`
`skip_human_review`	`bool` Whether human review should be skipped for this request. Default to `false`.
`field_mask`	`FieldMask` Specifies which fields to include in the `ProcessResponse.document` output. Only supports top-level document and pages field, so it must be in the form of `{document_field_name}` or `pages.{page_field_name}`.
`process_options`	`ProcessOptions` Inference-time options for the process API
`labels`	`map<string, string>` 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.
`imageless_mode`	`bool` Optional. Option to remove images from the document.
Union field `source`. The document payload. `source` can be only one of the following:
`inline_document`	`Document` An inline document proto.
`raw_document`	`RawDocument` A raw document content (bytes).
`gcs_document`	`GcsDocument` A raw document on Google Cloud Storage.

ProcessResponse

Response message for the ProcessDocument method.

Fields

document

Document

The document payload, will populate fields based on the processor's behavior.

human_review_status

HumanReviewStatus

The status of human review on the processed document.

Processor

The first-class citizen for Document AI. Each processor defines how to extract structural information from a document.

Fields
`name`	`string` Output only. Immutable. The resource name of the processor. Format: `projects/{project}/locations/{location}/processors/{processor}`
`type`	`string` The processor type, such as: `OCR_PROCESSOR`, `INVOICE_PROCESSOR`. To get a list of processor types, see `FetchProcessorTypes`.
`display_name`	`string` The display name of the processor.
`state`	`State` Output only. The state of the processor.
`default_processor_version`	`string` The default processor version.
`processor_version_aliases[]`	`ProcessorVersionAlias` Output only. The processor version aliases.
`process_endpoint`	`string` Output only. Immutable. The http endpoint that can be called to invoke processing.
`create_time`	`Timestamp` The time the processor was created.
`kms_key_name`	`string` The KMS key used for encryption and decryption in CMEK scenarios.
`satisfies_pzs`	`bool` Output only. Reserved for future use.
`satisfies_pzi`	`bool` Output only. Reserved for future use.

State

The possible states of the processor.

Enums
`STATE_UNSPECIFIED`	The processor is in an unspecified state.
`ENABLED`	The processor is enabled, i.e., has an enabled version which can currently serve processing requests and all the feature dependencies have been successfully initialized.
`DISABLED`	The processor is disabled.
`ENABLING`	The processor is being enabled, will become `ENABLED` if successful.
`DISABLING`	The processor is being disabled, will become `DISABLED` if successful.
`CREATING`	The processor is being created, will become either `ENABLED` (for successful creation) or `FAILED` (for failed ones). Once a processor is in this state, it can then be used for document processing, but the feature dependencies of the processor might not be fully created yet.
`FAILED`	The processor failed during creation or initialization of feature dependencies. The user should delete the processor and recreate one as all the functionalities of the processor are disabled.
`DELETING`	The processor is being deleted, will be removed if successful.

ProcessorType

A processor type is responsible for performing a certain document understanding task on a certain type of document.

Fields
`name`	`string` The resource name of the processor type. Format: `projects/{project}/processorTypes/{processor_type}`
`type`	`string` The processor type, such as: `OCR_PROCESSOR`, `INVOICE_PROCESSOR`.
`category`	`string` The processor category, used by UI to group processor types.
`available_locations[]`	`LocationInfo` The locations in which this processor is available.
`allow_creation`	`bool` Whether the processor type allows creation. If true, users can create a processor of this processor type. Otherwise, users need to request access.
`launch_stage`	`LaunchStage` Launch stage of the processor type
`sample_document_uris[]`	`string` A set of Cloud Storage URIs of sample documents for this processor.

LocationInfo

The location information about where the processor is available.

Fields

location_id

string

The location ID. For supported locations, refer to regional and multi-regional support.

ProcessorVersion

A processor version is an implementation of a processor. Each processor can have multiple versions, pretrained by Google internally or uptrained by the customer. A processor can only have one default version at a time. Its document-processing behavior is defined by that version.

Fields
`name`	`string` Identifier. The resource name of the processor version. Format: `projects/{project}/locations/{location}/processors/{processor}/processorVersions/{processor_version}`
`display_name`	`string` The display name of the processor version.
`document_schema`	`DocumentSchema` The schema of the processor version. Describes the output.
`state`	`State` Output only. The state of the processor version.
`create_time`	`Timestamp` The time the processor version was created.
`latest_evaluation`	`EvaluationReference` The most recently invoked evaluation for the processor version.
`kms_key_name`	`string` The KMS key name used for encryption.
`kms_key_version_name`	`string` The KMS key version with which data is encrypted.
`google_managed`	`bool` Output only. Denotes that this `ProcessorVersion` is managed by Google.
`deprecation_info`	`DeprecationInfo` If set, information about the eventual deprecation of this version.
`model_type`	`ModelType` Output only. The model type of this processor version.
`satisfies_pzs`	`bool` Output only. Reserved for future use.
`satisfies_pzi`	`bool` Output only. Reserved for future use.
`gen_ai_model_info`	`GenAiModelInfo` Output only. Information about Generative AI model-based processor versions.

DeprecationInfo

Information about the upcoming deprecation of this processor version.

Fields

deprecation_time

Timestamp

The time at which this processor version will be deprecated.

replacement_processor_version

string

If set, the processor version that will be used as a replacement.

GenAiModelInfo

Information about Generative AI model-based processor versions.

Fields

Union field model_info. The processor version is either a pretrained Google-managed foundation model or a custom Generative AI model created by the user. model_info can be only one of the following:

foundation_gen_ai_model_info

FoundationGenAiModelInfo

Information for a pretrained Google-managed foundation model.

custom_gen_ai_model_info

CustomGenAiModelInfo

Information for a custom Generative AI model created by the user.

CustomGenAiModelInfo

Information for a custom Generative AI model created by the user. These are created with Create New Version in either the Call foundation model or Fine tuning tabs.

Fields

custom_model_type

CustomModelType

The type of custom model created by the user.

base_processor_version_id

string

The base processor version ID for the custom model.

CustomModelType

The type of custom model created by the user.

Enums
`CUSTOM_MODEL_TYPE_UNSPECIFIED`	The model type is unspecified.
`VERSIONED_FOUNDATION`	The model is a versioned foundation model.
`FINE_TUNED`	The model is a finetuned foundation model.

FoundationGenAiModelInfo

Information for a pretrained Google-managed foundation model.

Fields

finetuning_allowed

bool

Whether finetuning is allowed for this base processor version.

min_train_labeled_documents

int32

The minimum number of labeled documents in the training dataset required for finetuning.

ModelType

The possible model types of the processor version.

Enums
`MODEL_TYPE_UNSPECIFIED`	The processor version has unspecified model type.
`MODEL_TYPE_GENERATIVE`	The processor version has generative model type.
`MODEL_TYPE_CUSTOM`	The processor version has custom model type.

State

The possible states of the processor version.

Enums
`STATE_UNSPECIFIED`	The processor version is in an unspecified state.
`DEPLOYED`	The processor version is deployed and can be used for processing.
`DEPLOYING`	The processor version is being deployed.
`UNDEPLOYED`	The processor version is not deployed and cannot be used for processing.
`UNDEPLOYING`	The processor version is being undeployed.
`CREATING`	The processor version is being created.
`DELETING`	The processor version is being deleted.
`FAILED`	The processor version failed and is in an indeterminate state.
`IMPORTING`	The processor version is being imported.

ProcessorVersionAlias

Contains the alias and the aliased resource name of processor version.

Fields

alias

string

The alias in the form of processor_version resource name.

processor_version

string

The resource name of aliased processor version.

RawDocument

Payload message of raw document content (bytes).

Fields

content

bytes

Inline document content.

mime_type

string

An IANA MIME type (RFC6838) indicating the nature and format of the content.

display_name

string

The display name of the document, it supports all Unicode characters except the following: *, ?, [, ], %, {, },', \", , ~, = and : are reserved. If not specified, a default ID is generated.

ReviewDocumentOperationMetadata

The long-running operation metadata for the ReviewDocument method.

Fields

common_metadata

The basic metadata of the long-running operation.

question_id

string

The Crowd Compute question ID.

ReviewDocumentRequest

Request message for the ReviewDocument method.

Fields
`human_review_config`	`string` Required. The resource name of the `HumanReviewConfig` that the document will be reviewed with. Authorization requires the following IAM permission on the specified resource `humanReviewConfig`: `documentai.humanReviewConfigs.review`
`enable_schema_validation`	`bool` Whether the validation should be performed on the ad-hoc review request.
`priority`	`Priority` The priority of the human review task.
`document_schema`	`DocumentSchema` The document schema of the human review task.
Union field `source`. The document payload. `source` can be only one of the following:
`inline_document`	`Document` An inline document proto.

Priority

The priority level of the human review task.

Enums
`DEFAULT`	The default priority level.
`URGENT`	The urgent priority level. The labeling manager should allocate labeler resource to the urgent task queue to respect this priority level.

ReviewDocumentResponse

Response message for the ReviewDocument method.

Fields

gcs_destination

string

The Cloud Storage uri for the human reviewed document if the review is succeeded.

state

State

The state of the review operation.

rejection_reason

string

The reason why the review is rejected by reviewer.

State

Possible states of the review operation.

Enums
`STATE_UNSPECIFIED`	The default value. This value is used if the state is omitted.
`REJECTED`	The review operation is rejected by the reviewer.
`SUCCEEDED`	The review operation is succeeded.

SetDefaultProcessorVersionMetadata

The long-running operation metadata for the SetDefaultProcessorVersion method.

Fields

common_metadata

The basic metadata of the long-running operation.

SetDefaultProcessorVersionRequest

Request message for the SetDefaultProcessorVersion method.

Fields

processor

string

Required. The resource name of the Processor to change default version.

Authorization requires the following IAM permission on the specified resource processor:

documentai.processors.processBatch

default_processor_version

string

Required. The resource name of child ProcessorVersion to use as default. Format: projects/{project}/locations/{location}/processors/{processor}/processorVersions/{version}

SetDefaultProcessorVersionResponse

This type has no fields.

Response message for the SetDefaultProcessorVersion method.

TrainProcessorVersionMetadata

The metadata that represents a processor version being created.

Fields

common_metadata

BatchDocumentsInputConfig

The basic metadata of the long-running operation.

training_dataset_validation

DatasetValidation

The training dataset validation information.

test_dataset_validation

DatasetValidation

The test dataset validation information.

DatasetValidation

The dataset validation information. This includes any and all errors with documents and the dataset.

Fields
`document_error_count`	`int32` The total number of document errors.
`dataset_error_count`	`int32` The total number of dataset errors.
`document_errors[]`	`Status` Error information pertaining to specific documents. A maximum of 10 document errors will be returned. Any document with errors will not be used throughout training.
`dataset_errors[]`	`Status` Error information for the dataset as a whole. A maximum of 10 dataset errors will be returned. A single dataset error is terminal for training.

TrainProcessorVersionRequest

Request message for the TrainProcessorVersion method.

Fields
`parent`	`string` Required. The parent (project, location and processor) to create the new version for. Format: `projects/{project}/locations/{location}/processors/{processor}`.
`processor_version`	`ProcessorVersion` Required. The processor version to be created. Authorization requires the following IAM permission on the specified resource `processorVersion`: `documentai.processorVersions.create`
`document_schema`	`DocumentSchema` Optional. The schema the processor version will be trained with.
`input_data`	`InputData` Optional. The input data used to train the `ProcessorVersion`.
`base_processor_version`	`string` Optional. The processor version to use as a base for training. This processor version must be a child of `parent`. Format: `projects/{project}/locations/{location}/processors/{processor}/processorVersions/{processorVersion}`.
Union field `processor_flags`. `processor_flags` can be only one of the following:
`custom_document_extraction_options`	`CustomDocumentExtractionOptions` Options to control Custom Document Extraction (CDE) Processor.
`foundation_model_tuning_options`	`FoundationModelTuningOptions` Options to control foundation model tuning of a processor.

CustomDocumentExtractionOptions

Options to control the training of the Custom Document Extraction (CDE) Processor.

Fields

training_method

TrainingMethod

Training method to use for CDE training.

TrainingMethod

Training Method for CDE. TRAINING_METHOD_UNSPECIFIED will fall back to MODEL_BASED.

Enums
`TRAINING_METHOD_UNSPECIFIED`
`MODEL_BASED`
`TEMPLATE_BASED`

FoundationModelTuningOptions

Options to control foundation model tuning of the processor.

Fields

train_steps

int32

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.

learning_rate_multiplier

float

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.

InputData

The input data used to train a new ProcessorVersion.

Fields

training_documents

The documents used for training the new version.

test_documents

BatchDocumentsInputConfig

The documents used for testing the trained version.

TrainProcessorVersionResponse

The response for TrainProcessorVersion.

Fields

processor_version

string

The resource name of the processor version produced by training.

UndeployProcessorVersionMetadata

The long-running operation metadata for the UndeployProcessorVersion method.

Fields

common_metadata