Document converter
This is an automatic generated API reference of the main components of Docling.
Classes:
-
DocumentConverter– -
ConversionResult– -
ConversionStatus– -
FormatOption– -
InputFormat–A document format supported by document backend parsers.
-
PdfFormatOption– -
ImageFormatOption– -
StandardPdfPipeline–High-performance PDF pipeline with multi-threaded stages.
-
WordFormatOption– -
PowerpointFormatOption– -
MarkdownFormatOption– -
AsciiDocFormatOption– -
HTMLFormatOption– -
SimplePipeline–SimpleModelPipeline.
DocumentConverter(allowed_formats: Optional[list[InputFormat]] = None, format_options: Optional[dict[InputFormat, FormatOption]] = None)
Methods:
-
convert– -
convert_all– -
convert_string– -
initialize_pipeline–Initialize the conversion pipeline for the selected format.
Attributes:
-
allowed_formats– -
format_to_options(dict[InputFormat, FormatOption]) – -
initialized_pipelines(dict[tuple[Type[BasePipeline], str], BasePipeline]) –
instance-attribute
allowed_formats = allowed_formats if allowed_formats is not None else list(InputFormat)
instance-attribute
format_to_options: dict[InputFormat, FormatOption] = {format: (_get_default_option(format=format) if (custom_option := (get(format))) is None else custom_option) for format in (allowed_formats)}
instance-attribute
initialized_pipelines: dict[tuple[Type[BasePipeline], str], BasePipeline] = {}
convert(source: Union[Path, str, DocumentStream], headers: Optional[dict[str, str]] = None, raises_on_error: bool = True, max_num_pages: int = maxsize, max_file_size: int = maxsize, page_range: PageRange = DEFAULT_PAGE_RANGE) -> ConversionResult
convert_all(source: Iterable[Union[Path, str, DocumentStream]], headers: Optional[dict[str, str]] = None, raises_on_error: bool = True, max_num_pages: int = maxsize, max_file_size: int = maxsize, page_range: PageRange = DEFAULT_PAGE_RANGE) -> Iterator[ConversionResult]
convert_string(content: str, format: InputFormat, name: Optional[str] = None) -> ConversionResult
initialize_pipeline(format: InputFormat)
Initialize the conversion pipeline for the selected format.
pydantic-model
Bases: ConversionAssets
Show JSON schema:
{
"$defs": {
"AssembledUnit": {
"properties": {
"elements": {
"default": [],
"items": {
"anyOf": [
{
"$ref": "#/$defs/TextElement"
},
{
"$ref": "#/$defs/Table"
},
{
"$ref": "#/$defs/FigureElement"
},
{
"$ref": "#/$defs/ContainerElement"
}
]
},
"title": "Elements",
"type": "array"
},
"body": {
"default": [],
"items": {
"anyOf": [
{
"$ref": "#/$defs/TextElement"
},
{
"$ref": "#/$defs/Table"
},
{
"$ref": "#/$defs/FigureElement"
},
{
"$ref": "#/$defs/ContainerElement"
}
]
},
"title": "Body",
"type": "array"
},
"headers": {
"default": [],
"items": {
"anyOf": [
{
"$ref": "#/$defs/TextElement"
},
{
"$ref": "#/$defs/Table"
},
{
"$ref": "#/$defs/FigureElement"
},
{
"$ref": "#/$defs/ContainerElement"
}
]
},
"title": "Headers",
"type": "array"
}
},
"title": "AssembledUnit",
"type": "object"
},
"BaseMeta": {
"additionalProperties": true,
"description": "Base class for metadata.",
"properties": {
"summary": {
"anyOf": [
{
"$ref": "#/$defs/SummaryMetaField"
},
{
"type": "null"
}
],
"default": null
}
},
"title": "BaseMeta",
"type": "object"
},
"BitmapResource": {
"description": "Model representing a bitmap resource with positioning and URI information.",
"properties": {
"index": {
"default": -1,
"title": "Index",
"type": "integer"
},
"rect": {
"$ref": "#/$defs/BoundingRectangle"
},
"uri": {
"anyOf": [
{
"format": "uri",
"minLength": 1,
"type": "string"
},
{
"type": "null"
}
],
"default": null,
"title": "Uri"
}
},
"required": [
"rect"
],
"title": "BitmapResource",
"type": "object"
},
"BoundingBox": {
"description": "BoundingBox.",
"properties": {
"l": {
"title": "L",
"type": "number"
},
"t": {
"title": "T",
"type": "number"
},
"r": {
"title": "R",
"type": "number"
},
"b": {
"title": "B",
"type": "number"
},
"coord_origin": {
"$ref": "#/$defs/CoordOrigin",
"default": "TOPLEFT"
}
},
"required": [
"l",
"t",
"r",
"b"
],
"title": "BoundingBox",
"type": "object"
},
"BoundingRectangle": {
"description": "Model representing a rectangular boundary with four corner points.",
"properties": {
"r_x0": {
"title": "R X0",
"type": "number"
},
"r_y0": {
"title": "R Y0",
"type": "number"
},
"r_x1": {
"title": "R X1",
"type": "number"
},
"r_y1": {
"title": "R Y1",
"type": "number"
},
"r_x2": {
"title": "R X2",
"type": "number"
},
"r_y2": {
"title": "R Y2",
"type": "number"
},
"r_x3": {
"title": "R X3",
"type": "number"
},
"r_y3": {
"title": "R Y3",
"type": "number"
},
"coord_origin": {
"$ref": "#/$defs/CoordOrigin",
"default": "BOTTOMLEFT"
}
},
"required": [
"r_x0",
"r_y0",
"r_x1",
"r_y1",
"r_x2",
"r_y2",
"r_x3",
"r_y3"
],
"title": "BoundingRectangle",
"type": "object"
},
"ChartBar": {
"description": "Represents a bar in a bar chart.\n\nAttributes:\n label (str): The label for the bar.\n values (float): The value associated with the bar.",
"properties": {
"label": {
"title": "Label",
"type": "string"
},
"values": {
"title": "Values",
"type": "number"
}
},
"required": [
"label",
"values"
],
"title": "ChartBar",
"type": "object"
},
"ChartLine": {
"description": "Represents a line in a line chart.\n\nAttributes:\n label (str): The label for the line.\n values (List[Tuple[float, float]]): A list of (x, y) coordinate pairs\n representing the line's data points.",
"properties": {
"label": {
"title": "Label",
"type": "string"
},
"values": {
"items": {
"maxItems": 2,
"minItems": 2,
"prefixItems": [
{
"type": "number"
},
{
"type": "number"
}
],
"type": "array"
},
"title": "Values",
"type": "array"
}
},
"required": [
"label",
"values"
],
"title": "ChartLine",
"type": "object"
},
"ChartPoint": {
"description": "Represents a point in a scatter chart.\n\nAttributes:\n value (Tuple[float, float]): A (x, y) coordinate pair representing a point in a\n chart.",
"properties": {
"value": {
"maxItems": 2,
"minItems": 2,
"prefixItems": [
{
"type": "number"
},
{
"type": "number"
}
],
"title": "Value",
"type": "array"
}
},
"required": [
"value"
],
"title": "ChartPoint",
"type": "object"
},
"ChartSlice": {
"description": "Represents a slice in a pie chart.\n\nAttributes:\n label (str): The label for the slice.\n value (float): The value represented by the slice.",
"properties": {
"label": {
"title": "Label",
"type": "string"
},
"value": {
"title": "Value",
"type": "number"
}
},
"required": [
"label",
"value"
],
"title": "ChartSlice",
"type": "object"
},
"ChartStackedBar": {
"description": "Represents a stacked bar in a stacked bar chart.\n\nAttributes:\n label (List[str]): The labels for the stacked bars. Multiple values are stored\n in cases where the chart is \"double stacked,\" meaning bars are stacked both\n horizontally and vertically.\n values (List[Tuple[str, int]]): A list of values representing different segments\n of the stacked bar along with their label.",
"properties": {
"label": {
"items": {
"type": "string"
},
"title": "Label",
"type": "array"
},
"values": {
"items": {
"maxItems": 2,
"minItems": 2,
"prefixItems": [
{
"type": "string"
},
{
"type": "integer"
}
],
"type": "array"
},
"title": "Values",
"type": "array"
}
},
"required": [
"label",
"values"
],
"title": "ChartStackedBar",
"type": "object"
},
"Cluster": {
"properties": {
"id": {
"title": "Id",
"type": "integer"
},
"label": {
"$ref": "#/$defs/DocItemLabel"
},
"bbox": {
"$ref": "#/$defs/BoundingBox"
},
"confidence": {
"default": 1.0,
"title": "Confidence",
"type": "number"
},
"cells": {
"default": [],
"items": {
"$ref": "#/$defs/TextCell"
},
"title": "Cells",
"type": "array"
},
"children": {
"default": [],
"items": {
"$ref": "#/$defs/Cluster"
},
"title": "Children",
"type": "array"
}
},
"required": [
"id",
"label",
"bbox"
],
"title": "Cluster",
"type": "object"
},
"CodeItem": {
"additionalProperties": false,
"description": "CodeItem.",
"properties": {
"self_ref": {
"pattern": "^#(?:/([\\w-]+)(?:/(\\d+))?)?$",
"title": "Self Ref",
"type": "string"
},
"parent": {
"anyOf": [
{
"$ref": "#/$defs/RefItem"
},
{
"type": "null"
}
],
"default": null
},
"children": {
"default": [],
"items": {
"$ref": "#/$defs/RefItem"
},
"title": "Children",
"type": "array"
},
"content_layer": {
"$ref": "#/$defs/ContentLayer",
"default": "body"
},
"meta": {
"anyOf": [
{
"$ref": "#/$defs/FloatingMeta"
},
{
"type": "null"
}
],
"default": null
},
"label": {
"const": "code",
"default": "code",
"title": "Label",
"type": "string"
},
"prov": {
"default": [],
"items": {
"$ref": "#/$defs/ProvenanceItem"
},
"title": "Prov",
"type": "array"
},
"orig": {
"title": "Orig",
"type": "string"
},
"text": {
"title": "Text",
"type": "string"
},
"formatting": {
"anyOf": [
{
"$ref": "#/$defs/Formatting"
},
{
"type": "null"
}
],
"default": null
},
"hyperlink": {
"anyOf": [
{
"format": "uri",
"minLength": 1,
"type": "string"
},
{
"format": "path",
"type": "string"
},
{
"type": "null"
}
],
"default": null,
"title": "Hyperlink"
},
"captions": {
"default": [],
"items": {
"$ref": "#/$defs/RefItem"
},
"title": "Captions",
"type": "array"
},
"references": {
"default": [],
"items": {
"$ref": "#/$defs/RefItem"
},
"title": "References",
"type": "array"
},
"footnotes": {
"default": [],
"items": {
"$ref": "#/$defs/RefItem"
},
"title": "Footnotes",
"type": "array"
},
"image": {
"anyOf": [
{
"$ref": "#/$defs/ImageRef"
},
{
"type": "null"
}
],
"default": null
},
"code_language": {
"$ref": "#/$defs/CodeLanguageLabel",
"default": "unknown"
}
},
"required": [
"self_ref",
"orig",
"text"
],
"title": "CodeItem",
"type": "object"
},
"CodeLanguageLabel": {
"description": "CodeLanguageLabel.",
"enum": [
"Ada",
"Awk",
"Bash",
"bc",
"C",
"C#",
"C++",
"CMake",
"COBOL",
"CSS",
"Ceylon",
"Clojure",
"Crystal",
"Cuda",
"Cython",
"D",
"Dart",
"dc",
"Dockerfile",
"Elixir",
"Erlang",
"FORTRAN",
"Forth",
"Go",
"HTML",
"Haskell",
"Haxe",
"Java",
"JavaScript",
"JSON",
"Julia",
"Kotlin",
"Lisp",
"Lua",
"Matlab",
"MoonScript",
"Nim",
"OCaml",
"ObjectiveC",
"Octave",
"PHP",
"Pascal",
"Perl",
"Prolog",
"Python",
"Racket",
"Ruby",
"Rust",
"SML",
"SQL",
"Scala",
"Scheme",
"Swift",
"TypeScript",
"unknown",
"VisualBasic",
"XML",
"YAML"
],
"title": "CodeLanguageLabel",
"type": "string"
},
"ColorRGBA": {
"description": "Model representing an RGBA color value.",
"properties": {
"r": {
"maximum": 255,
"minimum": 0,
"title": "R",
"type": "integer"
},
"g": {
"maximum": 255,
"minimum": 0,
"title": "G",
"type": "integer"
},
"b": {
"maximum": 255,
"minimum": 0,
"title": "B",
"type": "integer"
},
"a": {
"default": 255,
"maximum": 255,
"minimum": 0,
"title": "A",
"type": "integer"
}
},
"required": [
"r",
"g",
"b"
],
"title": "ColorRGBA",
"type": "object"
},
"ConfidenceReport": {
"properties": {
"parse_score": {
"default": NaN,
"title": "Parse Score",
"type": "number"
},
"layout_score": {
"default": NaN,
"title": "Layout Score",
"type": "number"
},
"table_score": {
"default": NaN,
"title": "Table Score",
"type": "number"
},
"ocr_score": {
"default": NaN,
"title": "Ocr Score",
"type": "number"
},
"pages": {
"additionalProperties": {
"$ref": "#/$defs/PageConfidenceScores"
},
"title": "Pages",
"type": "object"
}
},
"title": "ConfidenceReport",
"type": "object"
},
"ContainerElement": {
"properties": {
"label": {
"$ref": "#/$defs/DocItemLabel"
},
"id": {
"title": "Id",
"type": "integer"
},
"page_no": {
"title": "Page No",
"type": "integer"
},
"cluster": {
"$ref": "#/$defs/Cluster"
},
"text": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"default": null,
"title": "Text"
}
},
"required": [
"label",
"id",
"page_no",
"cluster"
],
"title": "ContainerElement",
"type": "object"
},
"ContentLayer": {
"description": "ContentLayer.",
"enum": [
"body",
"furniture",
"background",
"invisible",
"notes"
],
"title": "ContentLayer",
"type": "string"
},
"ConversionStatus": {
"enum": [
"pending",
"started",
"failure",
"success",
"partial_success",
"skipped"
],
"title": "ConversionStatus",
"type": "string"
},
"Coord2D": {
"maxItems": 2,
"minItems": 2,
"prefixItems": [
{
"title": "X",
"type": "number"
},
{
"title": "Y",
"type": "number"
}
],
"type": "array"
},
"CoordOrigin": {
"description": "CoordOrigin.",
"enum": [
"TOPLEFT",
"BOTTOMLEFT"
],
"title": "CoordOrigin",
"type": "string"
},
"DeclarativeBackendOptions": {
"description": "Default backend options for a declarative document backend.",
"properties": {
"enable_remote_fetch": {
"default": false,
"description": "Enable remote resource fetching.",
"title": "Enable Remote Fetch",
"type": "boolean"
},
"enable_local_fetch": {
"default": false,
"description": "Enable local resource fetching.",
"title": "Enable Local Fetch",
"type": "boolean"
},
"kind": {
"const": "declarative",
"default": "declarative",
"title": "Kind",
"type": "string"
}
},
"title": "DeclarativeBackendOptions",
"type": "object"
},
"DescriptionAnnotation": {
"description": "DescriptionAnnotation.",
"properties": {
"kind": {
"const": "description",
"default": "description",
"title": "Kind",
"type": "string"
},
"text": {
"title": "Text",
"type": "string"
},
"provenance": {
"title": "Provenance",
"type": "string"
}
},
"required": [
"text",
"provenance"
],
"title": "DescriptionAnnotation",
"type": "object"
},
"DescriptionMetaField": {
"additionalProperties": true,
"description": "Description metadata field.",
"properties": {
"confidence": {
"anyOf": [
{
"maximum": 1,
"minimum": 0,
"type": "number"
},
{
"type": "null"
}
],
"default": null,
"description": "The confidence of the prediction.",
"examples": [
0.9,
0.42
],
"title": "Confidence"
},
"created_by": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"default": null,
"description": "The origin of the prediction.",
"examples": [
"ibm-granite/granite-docling-258M"
],
"title": "Created By"
},
"text": {
"title": "Text",
"type": "string"
}
},
"required": [
"text"
],
"title": "DescriptionMetaField",
"type": "object"
},
"DocItemLabel": {
"description": "DocItemLabel.",
"enum": [
"caption",
"chart",
"footnote",
"formula",
"list_item",
"page_footer",
"page_header",
"picture",
"section_header",
"table",
"text",
"title",
"document_index",
"code",
"checkbox_selected",
"checkbox_unselected",
"form",
"key_value_region",
"grading_scale",
"handwritten_text",
"empty_value",
"paragraph",
"reference"
],
"title": "DocItemLabel",
"type": "string"
},
"DoclingComponentType": {
"enum": [
"document_backend",
"model",
"doc_assembler",
"user_input",
"pipeline"
],
"title": "DoclingComponentType",
"type": "string"
},
"DoclingDocument": {
"description": "DoclingDocument.",
"properties": {
"schema_name": {
"const": "DoclingDocument",
"default": "DoclingDocument",
"title": "Schema Name",
"type": "string"
},
"version": {
"default": "1.8.0",
"pattern": "^(?P<major>0|[1-9]\\d*)\\.(?P<minor>0|[1-9]\\d*)\\.(?P<patch>0|[1-9]\\d*)(?:-(?P<prerelease>(?:0|[1-9]\\d*|\\d*[a-zA-Z-][0-9a-zA-Z-]*)(?:\\.(?:0|[1-9]\\d*|\\d*[a-zA-Z-][0-9a-zA-Z-]*))*))?(?:\\+(?P<buildmetadata>[0-9a-zA-Z-]+(?:\\.[0-9a-zA-Z-]+)*))?$",
"title": "Version",
"type": "string"
},
"name": {
"title": "Name",
"type": "string"
},
"origin": {
"anyOf": [
{
"$ref": "#/$defs/DocumentOrigin"
},
{
"type": "null"
}
],
"default": null
},
"furniture": {
"$ref": "#/$defs/GroupItem",
"default": {
"self_ref": "#/furniture",
"parent": null,
"children": [],
"content_layer": "furniture",
"meta": null,
"name": "_root_",
"label": "unspecified"
},
"deprecated": true
},
"body": {
"$ref": "#/$defs/GroupItem",
"default": {
"self_ref": "#/body",
"parent": null,
"children": [],
"content_layer": "body",
"meta": null,
"name": "_root_",
"label": "unspecified"
}
},
"groups": {
"default": [],
"items": {
"anyOf": [
{
"$ref": "#/$defs/ListGroup"
},
{
"$ref": "#/$defs/InlineGroup"
},
{
"$ref": "#/$defs/GroupItem"
}
]
},
"title": "Groups",
"type": "array"
},
"texts": {
"default": [],
"items": {
"anyOf": [
{
"$ref": "#/$defs/TitleItem"
},
{
"$ref": "#/$defs/SectionHeaderItem"
},
{
"$ref": "#/$defs/ListItem"
},
{
"$ref": "#/$defs/CodeItem"
},
{
"$ref": "#/$defs/FormulaItem"
},
{
"$ref": "#/$defs/TextItem"
}
]
},
"title": "Texts",
"type": "array"
},
"pictures": {
"default": [],
"items": {
"$ref": "#/$defs/PictureItem"
},
"title": "Pictures",
"type": "array"
},
"tables": {
"default": [],
"items": {
"$ref": "#/$defs/TableItem"
},
"title": "Tables",
"type": "array"
},
"key_value_items": {
"default": [],
"items": {
"$ref": "#/$defs/KeyValueItem"
},
"title": "Key Value Items",
"type": "array"
},
"form_items": {
"default": [],
"items": {
"$ref": "#/$defs/FormItem"
},
"title": "Form Items",
"type": "array"
},
"pages": {
"additionalProperties": {
"$ref": "#/$defs/PageItem"
},
"default": {},
"title": "Pages",
"type": "object"
}
},
"required": [
"name"
],
"title": "DoclingDocument",
"type": "object"
},
"DoclingVersion": {
"properties": {
"docling_version": {
"default": "2.64.1",
"title": "Docling Version",
"type": "string"
},
"docling_core_version": {
"default": "2.51.1",
"title": "Docling Core Version",
"type": "string"
},
"docling_ibm_models_version": {
"default": "3.10.2",
"title": "Docling Ibm Models Version",
"type": "string"
},
"docling_parse_version": {
"default": "4.7.1",
"title": "Docling Parse Version",
"type": "string"
},
"platform_str": {
"default": "Linux-6.11.0-1018-azure-x86_64-with-glibc2.39",
"title": "Platform Str",
"type": "string"
},
"py_impl_version": {
"default": "cpython-312",
"title": "Py Impl Version",
"type": "string"
},
"py_lang_version": {
"default": "3.12.3",
"title": "Py Lang Version",
"type": "string"
}
},
"title": "DoclingVersion",
"type": "object"
},
"DocumentLimits": {
"properties": {
"max_num_pages": {
"default": 9223372036854775807,
"title": "Max Num Pages",
"type": "integer"
},
"max_file_size": {
"default": 9223372036854775807,
"title": "Max File Size",
"type": "integer"
},
"page_range": {
"default": [
1,
9223372036854775807
],
"title": "Page Range"
}
},
"title": "DocumentLimits",
"type": "object"
},
"DocumentOrigin": {
"description": "FileSource.",
"properties": {
"mimetype": {
"title": "Mimetype",
"type": "string"
},
"binary_hash": {
"maximum": 18446744073709551615,
"minimum": 0,
"title": "Binary Hash",
"type": "integer"
},
"filename": {
"title": "Filename",
"type": "string"
},
"uri": {
"anyOf": [
{
"format": "uri",
"minLength": 1,
"type": "string"
},
{
"type": "null"
}
],
"default": null,
"title": "Uri"
}
},
"required": [
"mimetype",
"binary_hash",
"filename"
],
"title": "DocumentOrigin",
"type": "object"
},
"EquationPrediction": {
"properties": {
"equation_count": {
"default": 0,
"title": "Equation Count",
"type": "integer"
},
"equation_map": {
"additionalProperties": {
"$ref": "#/$defs/TextElement"
},
"default": {},
"title": "Equation Map",
"type": "object"
}
},
"title": "EquationPrediction",
"type": "object"
},
"ErrorItem": {
"properties": {
"component_type": {
"$ref": "#/$defs/DoclingComponentType"
},
"module_name": {
"title": "Module Name",
"type": "string"
},
"error_message": {
"title": "Error Message",
"type": "string"
}
},
"required": [
"component_type",
"module_name",
"error_message"
],
"title": "ErrorItem",
"type": "object"
},
"FigureClassificationPrediction": {
"properties": {
"figure_count": {
"default": 0,
"title": "Figure Count",
"type": "integer"
},
"figure_map": {
"additionalProperties": {
"$ref": "#/$defs/FigureElement"
},
"default": {},
"title": "Figure Map",
"type": "object"
}
},
"title": "FigureClassificationPrediction",
"type": "object"
},
"FigureElement": {
"properties": {
"label": {
"$ref": "#/$defs/DocItemLabel"
},
"id": {
"title": "Id",
"type": "integer"
},
"page_no": {
"title": "Page No",
"type": "integer"
},
"cluster": {
"$ref": "#/$defs/Cluster"
},
"text": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"default": null,
"title": "Text"
},
"annotations": {
"default": [],
"items": {
"discriminator": {
"mapping": {
"bar_chart_data": "#/$defs/PictureBarChartData",
"classification": "#/$defs/PictureClassificationData",
"description": "#/$defs/DescriptionAnnotation",
"line_chart_data": "#/$defs/PictureLineChartData",
"misc": "#/$defs/MiscAnnotation",
"molecule_data": "#/$defs/PictureMoleculeData",
"pie_chart_data": "#/$defs/PicturePieChartData",
"scatter_chart_data": "#/$defs/PictureScatterChartData",
"stacked_bar_chart_data": "#/$defs/PictureStackedBarChartData",
"tabular_chart_data": "#/$defs/PictureTabularChartData"
},
"propertyName": "kind"
},
"oneOf": [
{
"$ref": "#/$defs/DescriptionAnnotation"
},
{
"$ref": "#/$defs/MiscAnnotation"
},
{
"$ref": "#/$defs/PictureClassificationData"
},
{
"$ref": "#/$defs/PictureMoleculeData"
},
{
"$ref": "#/$defs/PictureTabularChartData"
},
{
"$ref": "#/$defs/PictureLineChartData"
},
{
"$ref": "#/$defs/PictureBarChartData"
},
{
"$ref": "#/$defs/PictureStackedBarChartData"
},
{
"$ref": "#/$defs/PicturePieChartData"
},
{
"$ref": "#/$defs/PictureScatterChartData"
}
]
},
"title": "Annotations",
"type": "array"
},
"provenance": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"default": null,
"title": "Provenance"
},
"predicted_class": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"default": null,
"title": "Predicted Class"
},
"confidence": {
"anyOf": [
{
"type": "number"
},
{
"type": "null"
}
],
"default": null,
"title": "Confidence"
}
},
"required": [
"label",
"id",
"page_no",
"cluster"
],
"title": "FigureElement",
"type": "object"
},
"FloatingMeta": {
"additionalProperties": true,
"description": "Metadata model for floating.",
"properties": {
"summary": {
"anyOf": [
{
"$ref": "#/$defs/SummaryMetaField"
},
{
"type": "null"
}
],
"default": null
},
"description": {
"anyOf": [
{
"$ref": "#/$defs/DescriptionMetaField"
},
{
"type": "null"
}
],
"default": null
}
},
"title": "FloatingMeta",
"type": "object"
},
"FormItem": {
"additionalProperties": false,
"description": "FormItem.",
"properties": {
"self_ref": {
"pattern": "^#(?:/([\\w-]+)(?:/(\\d+))?)?$",
"title": "Self Ref",
"type": "string"
},
"parent": {
"anyOf": [
{
"$ref": "#/$defs/RefItem"
},
{
"type": "null"
}
],
"default": null
},
"children": {
"default": [],
"items": {
"$ref": "#/$defs/RefItem"
},
"title": "Children",
"type": "array"
},
"content_layer": {
"$ref": "#/$defs/ContentLayer",
"default": "body"
},
"meta": {
"anyOf": [
{
"$ref": "#/$defs/FloatingMeta"
},
{
"type": "null"
}
],
"default": null
},
"label": {
"const": "form",
"default": "form",
"title": "Label",
"type": "string"
},
"prov": {
"default": [],
"items": {
"$ref": "#/$defs/ProvenanceItem"
},
"title": "Prov",
"type": "array"
},
"captions": {
"default": [],
"items": {
"$ref": "#/$defs/RefItem"
},
"title": "Captions",
"type": "array"
},
"references": {
"default": [],
"items": {
"$ref": "#/$defs/RefItem"
},
"title": "References",
"type": "array"
},
"footnotes": {
"default": [],
"items": {
"$ref": "#/$defs/RefItem"
},
"title": "Footnotes",
"type": "array"
},
"image": {
"anyOf": [
{
"$ref": "#/$defs/ImageRef"
},
{
"type": "null"
}
],
"default": null
},
"graph": {
"$ref": "#/$defs/GraphData"
}
},
"required": [
"self_ref",
"graph"
],
"title": "FormItem",
"type": "object"
},
"Formatting": {
"description": "Formatting.",
"properties": {
"bold": {
"default": false,
"title": "Bold",
"type": "boolean"
},
"italic": {
"default": false,
"title": "Italic",
"type": "boolean"
},
"underline": {
"default": false,
"title": "Underline",
"type": "boolean"
},
"strikethrough": {
"default": false,
"title": "Strikethrough",
"type": "boolean"
},
"script": {
"$ref": "#/$defs/Script",
"default": "baseline"
}
},
"title": "Formatting",
"type": "object"
},
"FormulaItem": {
"additionalProperties": false,
"description": "FormulaItem.",
"properties": {
"self_ref": {
"pattern": "^#(?:/([\\w-]+)(?:/(\\d+))?)?$",
"title": "Self Ref",
"type": "string"
},
"parent": {
"anyOf": [
{
"$ref": "#/$defs/RefItem"
},
{
"type": "null"
}
],
"default": null
},
"children": {
"default": [],
"items": {
"$ref": "#/$defs/RefItem"
},
"title": "Children",
"type": "array"
},
"content_layer": {
"$ref": "#/$defs/ContentLayer",
"default": "body"
},
"meta": {
"anyOf": [
{
"$ref": "#/$defs/BaseMeta"
},
{
"type": "null"
}
],
"default": null
},
"label": {
"const": "formula",
"default": "formula",
"title": "Label",
"type": "string"
},
"prov": {
"default": [],
"items": {
"$ref": "#/$defs/ProvenanceItem"
},
"title": "Prov",
"type": "array"
},
"orig": {
"title": "Orig",
"type": "string"
},
"text": {
"title": "Text",
"type": "string"
},
"formatting": {
"anyOf": [
{
"$ref": "#/$defs/Formatting"
},
{
"type": "null"
}
],
"default": null
},
"hyperlink": {
"anyOf": [
{
"format": "uri",
"minLength": 1,
"type": "string"
},
{
"format": "path",
"type": "string"
},
{
"type": "null"
}
],
"default": null,
"title": "Hyperlink"
}
},
"required": [
"self_ref",
"orig",
"text"
],
"title": "FormulaItem",
"type": "object"
},
"GraphCell": {
"description": "GraphCell.",
"properties": {
"label": {
"$ref": "#/$defs/GraphCellLabel"
},
"cell_id": {
"title": "Cell Id",
"type": "integer"
},
"text": {
"title": "Text",
"type": "string"
},
"orig": {
"title": "Orig",
"type": "string"
},
"prov": {
"anyOf": [
{
"$ref": "#/$defs/ProvenanceItem"
},
{
"type": "null"
}
],
"default": null
},
"item_ref": {
"anyOf": [
{
"$ref": "#/$defs/RefItem"
},
{
"type": "null"
}
],
"default": null
}
},
"required": [
"label",
"cell_id",
"text",
"orig"
],
"title": "GraphCell",
"type": "object"
},
"GraphCellLabel": {
"description": "GraphCellLabel.",
"enum": [
"unspecified",
"key",
"value",
"checkbox"
],
"title": "GraphCellLabel",
"type": "string"
},
"GraphData": {
"description": "GraphData.",
"properties": {
"cells": {
"items": {
"$ref": "#/$defs/GraphCell"
},
"title": "Cells",
"type": "array"
},
"links": {
"items": {
"$ref": "#/$defs/GraphLink"
},
"title": "Links",
"type": "array"
}
},
"title": "GraphData",
"type": "object"
},
"GraphLink": {
"description": "GraphLink.",
"properties": {
"label": {
"$ref": "#/$defs/GraphLinkLabel"
},
"source_cell_id": {
"title": "Source Cell Id",
"type": "integer"
},
"target_cell_id": {
"title": "Target Cell Id",
"type": "integer"
}
},
"required": [
"label",
"source_cell_id",
"target_cell_id"
],
"title": "GraphLink",
"type": "object"
},
"GraphLinkLabel": {
"description": "GraphLinkLabel.",
"enum": [
"unspecified",
"to_value",
"to_key",
"to_parent",
"to_child"
],
"title": "GraphLinkLabel",
"type": "string"
},
"GroupItem": {
"additionalProperties": false,
"description": "GroupItem.",
"properties": {
"self_ref": {
"pattern": "^#(?:/([\\w-]+)(?:/(\\d+))?)?$",
"title": "Self Ref",
"type": "string"
},
"parent": {
"anyOf": [
{
"$ref": "#/$defs/RefItem"
},
{
"type": "null"
}
],
"default": null
},
"children": {
"default": [],
"items": {
"$ref": "#/$defs/RefItem"
},
"title": "Children",
"type": "array"
},
"content_layer": {
"$ref": "#/$defs/ContentLayer",
"default": "body"
},
"meta": {
"anyOf": [
{
"$ref": "#/$defs/BaseMeta"
},
{
"type": "null"
}
],
"default": null
},
"name": {
"default": "group",
"title": "Name",
"type": "string"
},
"label": {
"$ref": "#/$defs/GroupLabel",
"default": "unspecified"
}
},
"required": [
"self_ref"
],
"title": "GroupItem",
"type": "object"
},
"GroupLabel": {
"description": "GroupLabel.",
"enum": [
"unspecified",
"list",
"ordered_list",
"chapter",
"section",
"sheet",
"slide",
"form_area",
"key_value_area",
"comment_section",
"inline",
"picture_area"
],
"title": "GroupLabel",
"type": "string"
},
"HTMLBackendOptions": {
"description": "Options specific to the HTML backend.\n\nThis class can be extended to include options specific to HTML processing.",
"properties": {
"enable_remote_fetch": {
"default": false,
"description": "Enable remote resource fetching.",
"title": "Enable Remote Fetch",
"type": "boolean"
},
"enable_local_fetch": {
"default": false,
"description": "Enable local resource fetching.",
"title": "Enable Local Fetch",
"type": "boolean"
},
"kind": {
"const": "html",
"default": "html",
"title": "Kind",
"type": "string"
},
"fetch_images": {
"default": false,
"description": "Whether the backend should access remote or local resources to parse images in an HTML document.",
"title": "Fetch Images",
"type": "boolean"
},
"source_uri": {
"anyOf": [
{
"format": "uri",
"minLength": 1,
"type": "string"
},
{
"format": "path",
"type": "string"
},
{
"type": "null"
}
],
"default": null,
"description": "The URI that originates the HTML document. If provided, the backend will use it to resolve relative paths in the HTML document.",
"title": "Source Uri"
}
},
"title": "HTMLBackendOptions",
"type": "object"
},
"ImageRef": {
"description": "ImageRef.",
"properties": {
"mimetype": {
"title": "Mimetype",
"type": "string"
},
"dpi": {
"title": "Dpi",
"type": "integer"
},
"size": {
"$ref": "#/$defs/Size"
},
"uri": {
"anyOf": [
{
"format": "uri",
"minLength": 1,
"type": "string"
},
{
"format": "path",
"type": "string"
}
],
"title": "Uri"
}
},
"required": [
"mimetype",
"dpi",
"size",
"uri"
],
"title": "ImageRef",
"type": "object"
},
"InlineGroup": {
"additionalProperties": false,
"description": "InlineGroup.",
"properties": {
"self_ref": {
"pattern": "^#(?:/([\\w-]+)(?:/(\\d+))?)?$",
"title": "Self Ref",
"type": "string"
},
"parent": {
"anyOf": [
{
"$ref": "#/$defs/RefItem"
},
{
"type": "null"
}
],
"default": null
},
"children": {
"default": [],
"items": {
"$ref": "#/$defs/RefItem"
},
"title": "Children",
"type": "array"
},
"content_layer": {
"$ref": "#/$defs/ContentLayer",
"default": "body"
},
"meta": {
"anyOf": [
{
"$ref": "#/$defs/BaseMeta"
},
{
"type": "null"
}
],
"default": null
},
"name": {
"default": "group",
"title": "Name",
"type": "string"
},
"label": {
"const": "inline",
"default": "inline",
"title": "Label",
"type": "string"
}
},
"required": [
"self_ref"
],
"title": "InlineGroup",
"type": "object"
},
"InputDocument": {
"description": "A document as an input of a Docling conversion.",
"properties": {
"file": {
"description": "A path representation the input document.",
"format": "path",
"title": "File",
"type": "string"
},
"document_hash": {
"description": "A stable hash of the path or stream of the input document.",
"title": "Document Hash",
"type": "string"
},
"valid": {
"default": true,
"description": "Whether this is is a valid input document.",
"title": "Valid",
"type": "boolean"
},
"backend_options": {
"anyOf": [
{
"discriminator": {
"mapping": {
"declarative": "#/$defs/DeclarativeBackendOptions",
"html": "#/$defs/HTMLBackendOptions",
"md": "#/$defs/MarkdownBackendOptions",
"pdf": "#/$defs/PdfBackendOptions",
"xlsx": "#/$defs/MsExcelBackendOptions"
},
"propertyName": "kind"
},
"oneOf": [
{
"$ref": "#/$defs/DeclarativeBackendOptions"
},
{
"$ref": "#/$defs/HTMLBackendOptions"
},
{
"$ref": "#/$defs/MarkdownBackendOptions"
},
{
"$ref": "#/$defs/PdfBackendOptions"
},
{
"$ref": "#/$defs/MsExcelBackendOptions"
}
]
},
{
"type": "null"
}
],
"default": null,
"description": "Custom options for backends.",
"title": "Backend Options"
},
"limits": {
"$ref": "#/$defs/DocumentLimits",
"default": {
"max_num_pages": 9223372036854775807,
"max_file_size": 9223372036854775807,
"page_range": [
1,
9223372036854775807
]
},
"description": "Limits in the input document for the conversion."
},
"format": {
"$ref": "#/$defs/InputFormat",
"description": "The document format."
},
"filesize": {
"anyOf": [
{
"type": "integer"
},
{
"type": "null"
}
],
"default": null,
"description": "Size of the input file, in bytes.",
"title": "Filesize"
},
"page_count": {
"default": 0,
"description": "Number of pages in the input document.",
"title": "Page Count",
"type": "integer"
}
},
"required": [
"file",
"document_hash",
"format"
],
"title": "InputDocument",
"type": "object"
},
"InputFormat": {
"description": "A document format supported by document backend parsers.",
"enum": [
"docx",
"pptx",
"html",
"image",
"pdf",
"asciidoc",
"md",
"csv",
"xlsx",
"xml_uspto",
"xml_jats",
"mets_gbs",
"json_docling",
"audio",
"vtt"
],
"title": "InputFormat",
"type": "string"
},
"KeyValueItem": {
"additionalProperties": false,
"description": "KeyValueItem.",
"properties": {
"self_ref": {
"pattern": "^#(?:/([\\w-]+)(?:/(\\d+))?)?$",
"title": "Self Ref",
"type": "string"
},
"parent": {
"anyOf": [
{
"$ref": "#/$defs/RefItem"
},
{
"type": "null"
}
],
"default": null
},
"children": {
"default": [],
"items": {
"$ref": "#/$defs/RefItem"
},
"title": "Children",
"type": "array"
},
"content_layer": {
"$ref": "#/$defs/ContentLayer",
"default": "body"
},
"meta": {
"anyOf": [
{
"$ref": "#/$defs/FloatingMeta"
},
{
"type": "null"
}
],
"default": null
},
"label": {
"const": "key_value_region",
"default": "key_value_region",
"title": "Label",
"type": "string"
},
"prov": {
"default": [],
"items": {
"$ref": "#/$defs/ProvenanceItem"
},
"title": "Prov",
"type": "array"
},
"captions": {
"default": [],
"items": {
"$ref": "#/$defs/RefItem"
},
"title": "Captions",
"type": "array"
},
"references": {
"default": [],
"items": {
"$ref": "#/$defs/RefItem"
},
"title": "References",
"type": "array"
},
"footnotes": {
"default": [],
"items": {
"$ref": "#/$defs/RefItem"
},
"title": "Footnotes",
"type": "array"
},
"image": {
"anyOf": [
{
"$ref": "#/$defs/ImageRef"
},
{
"type": "null"
}
],
"default": null
},
"graph": {
"$ref": "#/$defs/GraphData"
}
},
"required": [
"self_ref",
"graph"
],
"title": "KeyValueItem",
"type": "object"
},
"LayoutPrediction": {
"properties": {
"clusters": {
"default": [],
"items": {
"$ref": "#/$defs/Cluster"
},
"title": "Clusters",
"type": "array"
}
},
"title": "LayoutPrediction",
"type": "object"
},
"ListGroup": {
"additionalProperties": false,
"description": "ListGroup.",
"properties": {
"self_ref": {
"pattern": "^#(?:/([\\w-]+)(?:/(\\d+))?)?$",
"title": "Self Ref",
"type": "string"
},
"parent": {
"anyOf": [
{
"$ref": "#/$defs/RefItem"
},
{
"type": "null"
}
],
"default": null
},
"children": {
"default": [],
"items": {
"$ref": "#/$defs/RefItem"
},
"title": "Children",
"type": "array"
},
"content_layer": {
"$ref": "#/$defs/ContentLayer",
"default": "body"
},
"meta": {
"anyOf": [
{
"$ref": "#/$defs/BaseMeta"
},
{
"type": "null"
}
],
"default": null
},
"name": {
"default": "group",
"title": "Name",
"type": "string"
},
"label": {
"const": "list",
"default": "list",
"title": "Label",
"type": "string"
}
},
"required": [
"self_ref"
],
"title": "ListGroup",
"type": "object"
},
"ListItem": {
"additionalProperties": false,
"description": "SectionItem.",
"properties": {
"self_ref": {
"pattern": "^#(?:/([\\w-]+)(?:/(\\d+))?)?$",
"title": "Self Ref",
"type": "string"
},
"parent": {
"anyOf": [
{
"$ref": "#/$defs/RefItem"
},
{
"type": "null"
}
],
"default": null
},
"children": {
"default": [],
"items": {
"$ref": "#/$defs/RefItem"
},
"title": "Children",
"type": "array"
},
"content_layer": {
"$ref": "#/$defs/ContentLayer",
"default": "body"
},
"meta": {
"anyOf": [
{
"$ref": "#/$defs/BaseMeta"
},
{
"type": "null"
}
],
"default": null
},
"label": {
"const": "list_item",
"default": "list_item",
"title": "Label",
"type": "string"
},
"prov": {
"default": [],
"items": {
"$ref": "#/$defs/ProvenanceItem"
},
"title": "Prov",
"type": "array"
},
"orig": {
"title": "Orig",
"type": "string"
},
"text": {
"title": "Text",
"type": "string"
},
"formatting": {
"anyOf": [
{
"$ref": "#/$defs/Formatting"
},
{
"type": "null"
}
],
"default": null
},
"hyperlink": {
"anyOf": [
{
"format": "uri",
"minLength": 1,
"type": "string"
},
{
"format": "path",
"type": "string"
},
{
"type": "null"
}
],
"default": null,
"title": "Hyperlink"
},
"enumerated": {
"default": false,
"title": "Enumerated",
"type": "boolean"
},
"marker": {
"default": "-",
"title": "Marker",
"type": "string"
}
},
"required": [
"self_ref",
"orig",
"text"
],
"title": "ListItem",
"type": "object"
},
"MarkdownBackendOptions": {
"description": "Options specific to the Markdown backend.",
"properties": {
"enable_remote_fetch": {
"default": false,
"description": "Enable remote resource fetching.",
"title": "Enable Remote Fetch",
"type": "boolean"
},
"enable_local_fetch": {
"default": false,
"description": "Enable local resource fetching.",
"title": "Enable Local Fetch",
"type": "boolean"
},
"kind": {
"const": "md",
"default": "md",
"title": "Kind",
"type": "string"
},
"fetch_images": {
"default": false,
"description": "Whether the backend should access remote or local resources to parse images in the markdown document.",
"title": "Fetch Images",
"type": "boolean"
},
"source_uri": {
"anyOf": [
{
"format": "uri",
"minLength": 1,
"type": "string"
},
{
"format": "path",
"type": "string"
},
{
"type": "null"
}
],
"default": null,
"description": "The URI that originates the markdown document. If provided, the backend will use it to resolve relative paths in the markdown document.",
"title": "Source Uri"
}
},
"title": "MarkdownBackendOptions",
"type": "object"
},
"MiscAnnotation": {
"description": "MiscAnnotation.",
"properties": {
"kind": {
"const": "misc",
"default": "misc",
"title": "Kind",
"type": "string"
},
"content": {
"additionalProperties": true,
"title": "Content",
"type": "object"
}
},
"required": [
"content"
],
"title": "MiscAnnotation",
"type": "object"
},
"MoleculeMetaField": {
"additionalProperties": true,
"description": "Molecule metadata field.",
"properties": {
"confidence": {
"anyOf": [
{
"maximum": 1,
"minimum": 0,
"type": "number"
},
{
"type": "null"
}
],
"default": null,
"description": "The confidence of the prediction.",
"examples": [
0.9,
0.42
],
"title": "Confidence"
},
"created_by": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"default": null,
"description": "The origin of the prediction.",
"examples": [
"ibm-granite/granite-docling-258M"
],
"title": "Created By"
},
"smi": {
"description": "The SMILES representation of the molecule.",
"title": "Smi",
"type": "string"
}
},
"required": [
"smi"
],
"title": "MoleculeMetaField",
"type": "object"
},
"MsExcelBackendOptions": {
"description": "Options specific to the MS Excel backend.",
"properties": {
"enable_remote_fetch": {
"default": false,
"description": "Enable remote resource fetching.",
"title": "Enable Remote Fetch",
"type": "boolean"
},
"enable_local_fetch": {
"default": false,
"description": "Enable local resource fetching.",
"title": "Enable Local Fetch",
"type": "boolean"
},
"kind": {
"const": "xlsx",
"default": "xlsx",
"title": "Kind",
"type": "string"
},
"treat_singleton_as_text": {
"default": false,
"description": "Whether to treat singleton cells (1x1 tables with empty neighboring cells) as TextItem instead of TableItem.",
"title": "Treat Singleton As Text",
"type": "boolean"
}
},
"title": "MsExcelBackendOptions",
"type": "object"
},
"Page": {
"properties": {
"page_no": {
"title": "Page No",
"type": "integer"
},
"size": {
"anyOf": [
{
"$ref": "#/$defs/Size"
},
{
"type": "null"
}
],
"default": null
},
"parsed_page": {
"anyOf": [
{
"$ref": "#/$defs/SegmentedPdfPage"
},
{
"type": "null"
}
],
"default": null
},
"predictions": {
"$ref": "#/$defs/PagePredictions",
"default": {
"layout": null,
"tablestructure": null,
"figures_classification": null,
"equations_prediction": null,
"vlm_response": null
}
},
"assembled": {
"anyOf": [
{
"$ref": "#/$defs/AssembledUnit"
},
{
"type": "null"
}
],
"default": null
}
},
"required": [
"page_no"
],
"title": "Page",
"type": "object"
},
"PageConfidenceScores": {
"properties": {
"parse_score": {
"default": NaN,
"title": "Parse Score",
"type": "number"
},
"layout_score": {
"default": NaN,
"title": "Layout Score",
"type": "number"
},
"table_score": {
"default": NaN,
"title": "Table Score",
"type": "number"
},
"ocr_score": {
"default": NaN,
"title": "Ocr Score",
"type": "number"
}
},
"title": "PageConfidenceScores",
"type": "object"
},
"PageItem": {
"description": "PageItem.",
"properties": {
"size": {
"$ref": "#/$defs/Size"
},
"image": {
"anyOf": [
{
"$ref": "#/$defs/ImageRef"
},
{
"type": "null"
}
],
"default": null
},
"page_no": {
"title": "Page No",
"type": "integer"
}
},
"required": [
"size",
"page_no"
],
"title": "PageItem",
"type": "object"
},
"PagePredictions": {
"properties": {
"layout": {
"anyOf": [
{
"$ref": "#/$defs/LayoutPrediction"
},
{
"type": "null"
}
],
"default": null
},
"tablestructure": {
"anyOf": [
{
"$ref": "#/$defs/TableStructurePrediction"
},
{
"type": "null"
}
],
"default": null
},
"figures_classification": {
"anyOf": [
{
"$ref": "#/$defs/FigureClassificationPrediction"
},
{
"type": "null"
}
],
"default": null
},
"equations_prediction": {
"anyOf": [
{
"$ref": "#/$defs/EquationPrediction"
},
{
"type": "null"
}
],
"default": null
},
"vlm_response": {
"anyOf": [
{
"$ref": "#/$defs/VlmPrediction"
},
{
"type": "null"
}
],
"default": null
}
},
"title": "PagePredictions",
"type": "object"
},
"PdfBackendOptions": {
"description": "Backend options for pdf document backends.",
"properties": {
"enable_remote_fetch": {
"default": false,
"description": "Enable remote resource fetching.",
"title": "Enable Remote Fetch",
"type": "boolean"
},
"enable_local_fetch": {
"default": false,
"description": "Enable local resource fetching.",
"title": "Enable Local Fetch",
"type": "boolean"
},
"kind": {
"const": "pdf",
"default": "pdf",
"title": "Kind",
"type": "string"
},
"password": {
"anyOf": [
{
"format": "password",
"type": "string",
"writeOnly": true
},
{
"type": "null"
}
],
"default": null,
"title": "Password"
}
},
"title": "PdfBackendOptions",
"type": "object"
},
"PdfCellRenderingMode": {
"description": "Text Rendering Mode, according to PDF32000.",
"enum": [
0,
1,
2,
3,
4,
5,
6,
7,
-1
],
"title": "PdfCellRenderingMode",
"type": "integer"
},
"PdfLine": {
"description": "Model representing a line in a PDF document.",
"properties": {
"index": {
"default": -1,
"title": "Index",
"type": "integer"
},
"rgba": {
"$ref": "#/$defs/ColorRGBA",
"default": {
"r": 0,
"g": 0,
"b": 0,
"a": 255
}
},
"parent_id": {
"title": "Parent Id",
"type": "integer"
},
"points": {
"items": {
"$ref": "#/$defs/Coord2D"
},
"title": "Points",
"type": "array"
},
"width": {
"default": 1.0,
"title": "Width",
"type": "number"
},
"coord_origin": {
"$ref": "#/$defs/CoordOrigin",
"default": "BOTTOMLEFT"
}
},
"required": [
"parent_id",
"points"
],
"title": "PdfLine",
"type": "object"
},
"PdfPageBoundaryType": {
"description": "Enumeration of PDF page boundary types.",
"enum": [
"art_box",
"bleed_box",
"crop_box",
"media_box",
"trim_box"
],
"title": "PdfPageBoundaryType",
"type": "string"
},
"PdfPageGeometry": {
"description": "Extended dimensions model specific to PDF pages with boundary types.",
"properties": {
"angle": {
"title": "Angle",
"type": "number"
},
"rect": {
"$ref": "#/$defs/BoundingRectangle"
},
"boundary_type": {
"$ref": "#/$defs/PdfPageBoundaryType"
},
"art_bbox": {
"$ref": "#/$defs/BoundingBox"
},
"bleed_bbox": {
"$ref": "#/$defs/BoundingBox"
},
"crop_bbox": {
"$ref": "#/$defs/BoundingBox"
},
"media_bbox": {
"$ref": "#/$defs/BoundingBox"
},
"trim_bbox": {
"$ref": "#/$defs/BoundingBox"
}
},
"required": [
"angle",
"rect",
"boundary_type",
"art_bbox",
"bleed_bbox",
"crop_bbox",
"media_bbox",
"trim_bbox"
],
"title": "PdfPageGeometry",
"type": "object"
},
"PdfTextCell": {
"description": "Specialized text cell for PDF documents with font information.",
"properties": {
"index": {
"default": -1,
"title": "Index",
"type": "integer"
},
"rgba": {
"$ref": "#/$defs/ColorRGBA",
"default": {
"r": 0,
"g": 0,
"b": 0,
"a": 255
}
},
"rect": {
"$ref": "#/$defs/BoundingRectangle"
},
"text": {
"title": "Text",
"type": "string"
},
"orig": {
"title": "Orig",
"type": "string"
},
"text_direction": {
"$ref": "#/$defs/TextDirection",
"default": "left_to_right"
},
"confidence": {
"default": 1.0,
"title": "Confidence",
"type": "number"
},
"from_ocr": {
"const": false,
"default": false,
"title": "From Ocr",
"type": "boolean"
},
"rendering_mode": {
"$ref": "#/$defs/PdfCellRenderingMode"
},
"widget": {
"title": "Widget",
"type": "boolean"
},
"font_key": {
"title": "Font Key",
"type": "string"
},
"font_name": {
"title": "Font Name",
"type": "string"
}
},
"required": [
"rect",
"text",
"orig",
"rendering_mode",
"widget",
"font_key",
"font_name"
],
"title": "PdfTextCell",
"type": "object"
},
"PictureBarChartData": {
"description": "Represents data of a bar chart.\n\nAttributes:\n kind (Literal[\"bar_chart_data\"]): The type of the chart.\n x_axis_label (str): The label for the x-axis.\n y_axis_label (str): The label for the y-axis.\n bars (List[ChartBar]): A list of bars in the chart.",
"properties": {
"kind": {
"const": "bar_chart_data",
"default": "bar_chart_data",
"title": "Kind",
"type": "string"
},
"title": {
"title": "Title",
"type": "string"
},
"x_axis_label": {
"title": "X Axis Label",
"type": "string"
},
"y_axis_label": {
"title": "Y Axis Label",
"type": "string"
},
"bars": {
"items": {
"$ref": "#/$defs/ChartBar"
},
"title": "Bars",
"type": "array"
}
},
"required": [
"title",
"x_axis_label",
"y_axis_label",
"bars"
],
"title": "PictureBarChartData",
"type": "object"
},
"PictureClassificationClass": {
"description": "PictureClassificationData.",
"properties": {
"class_name": {
"title": "Class Name",
"type": "string"
},
"confidence": {
"title": "Confidence",
"type": "number"
}
},
"required": [
"class_name",
"confidence"
],
"title": "PictureClassificationClass",
"type": "object"
},
"PictureClassificationData": {
"description": "PictureClassificationData.",
"properties": {
"kind": {
"const": "classification",
"default": "classification",
"title": "Kind",
"type": "string"
},
"provenance": {
"title": "Provenance",
"type": "string"
},
"predicted_classes": {
"items": {
"$ref": "#/$defs/PictureClassificationClass"
},
"title": "Predicted Classes",
"type": "array"
}
},
"required": [
"provenance",
"predicted_classes"
],
"title": "PictureClassificationData",
"type": "object"
},
"PictureClassificationMetaField": {
"additionalProperties": true,
"description": "Picture classification metadata field.",
"properties": {
"predictions": {
"items": {
"$ref": "#/$defs/PictureClassificationPrediction"
},
"minItems": 1,
"title": "Predictions",
"type": "array"
}
},
"title": "PictureClassificationMetaField",
"type": "object"
},
"PictureClassificationPrediction": {
"additionalProperties": true,
"description": "Picture classification instance.",
"properties": {
"confidence": {
"anyOf": [
{
"maximum": 1,
"minimum": 0,
"type": "number"
},
{
"type": "null"
}
],
"default": null,
"description": "The confidence of the prediction.",
"examples": [
0.9,
0.42
],
"title": "Confidence"
},
"created_by": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"default": null,
"description": "The origin of the prediction.",
"examples": [
"ibm-granite/granite-docling-258M"
],
"title": "Created By"
},
"class_name": {
"title": "Class Name",
"type": "string"
}
},
"required": [
"class_name"
],
"title": "PictureClassificationPrediction",
"type": "object"
},
"PictureItem": {
"additionalProperties": false,
"description": "PictureItem.",
"properties": {
"self_ref": {
"pattern": "^#(?:/([\\w-]+)(?:/(\\d+))?)?$",
"title": "Self Ref",
"type": "string"
},
"parent": {
"anyOf": [
{
"$ref": "#/$defs/RefItem"
},
{
"type": "null"
}
],
"default": null
},
"children": {
"default": [],
"items": {
"$ref": "#/$defs/RefItem"
},
"title": "Children",
"type": "array"
},
"content_layer": {
"$ref": "#/$defs/ContentLayer",
"default": "body"
},
"meta": {
"anyOf": [
{
"$ref": "#/$defs/PictureMeta"
},
{
"type": "null"
}
],
"default": null
},
"label": {
"default": "picture",
"enum": [
"picture",
"chart"
],
"title": "Label",
"type": "string"
},
"prov": {
"default": [],
"items": {
"$ref": "#/$defs/ProvenanceItem"
},
"title": "Prov",
"type": "array"
},
"captions": {
"default": [],
"items": {
"$ref": "#/$defs/RefItem"
},
"title": "Captions",
"type": "array"
},
"references": {
"default": [],
"items": {
"$ref": "#/$defs/RefItem"
},
"title": "References",
"type": "array"
},
"footnotes": {
"default": [],
"items": {
"$ref": "#/$defs/RefItem"
},
"title": "Footnotes",
"type": "array"
},
"image": {
"anyOf": [
{
"$ref": "#/$defs/ImageRef"
},
{
"type": "null"
}
],
"default": null
},
"annotations": {
"default": [],
"deprecated": true,
"items": {
"discriminator": {
"mapping": {
"bar_chart_data": "#/$defs/PictureBarChartData",
"classification": "#/$defs/PictureClassificationData",
"description": "#/$defs/DescriptionAnnotation",
"line_chart_data": "#/$defs/PictureLineChartData",
"misc": "#/$defs/MiscAnnotation",
"molecule_data": "#/$defs/PictureMoleculeData",
"pie_chart_data": "#/$defs/PicturePieChartData",
"scatter_chart_data": "#/$defs/PictureScatterChartData",
"stacked_bar_chart_data": "#/$defs/PictureStackedBarChartData",
"tabular_chart_data": "#/$defs/PictureTabularChartData"
},
"propertyName": "kind"
},
"oneOf": [
{
"$ref": "#/$defs/DescriptionAnnotation"
},
{
"$ref": "#/$defs/MiscAnnotation"
},
{
"$ref": "#/$defs/PictureClassificationData"
},
{
"$ref": "#/$defs/PictureMoleculeData"
},
{
"$ref": "#/$defs/PictureTabularChartData"
},
{
"$ref": "#/$defs/PictureLineChartData"
},
{
"$ref": "#/$defs/PictureBarChartData"
},
{
"$ref": "#/$defs/PictureStackedBarChartData"
},
{
"$ref": "#/$defs/PicturePieChartData"
},
{
"$ref": "#/$defs/PictureScatterChartData"
}
]
},
"title": "Annotations",
"type": "array"
}
},
"required": [
"self_ref"
],
"title": "PictureItem",
"type": "object"
},
"PictureLineChartData": {
"description": "Represents data of a line chart.\n\nAttributes:\n kind (Literal[\"line_chart_data\"]): The type of the chart.\n x_axis_label (str): The label for the x-axis.\n y_axis_label (str): The label for the y-axis.\n lines (List[ChartLine]): A list of lines in the chart.",
"properties": {
"kind": {
"const": "line_chart_data",
"default": "line_chart_data",
"title": "Kind",
"type": "string"
},
"title": {
"title": "Title",
"type": "string"
},
"x_axis_label": {
"title": "X Axis Label",
"type": "string"
},
"y_axis_label": {
"title": "Y Axis Label",
"type": "string"
},
"lines": {
"items": {
"$ref": "#/$defs/ChartLine"
},
"title": "Lines",
"type": "array"
}
},
"required": [
"title",
"x_axis_label",
"y_axis_label",
"lines"
],
"title": "PictureLineChartData",
"type": "object"
},
"PictureMeta": {
"additionalProperties": true,
"description": "Metadata model for pictures.",
"properties": {
"summary": {
"anyOf": [
{
"$ref": "#/$defs/SummaryMetaField"
},
{
"type": "null"
}
],
"default": null
},
"description": {
"anyOf": [
{
"$ref": "#/$defs/DescriptionMetaField"
},
{
"type": "null"
}
],
"default": null
},
"classification": {
"anyOf": [
{
"$ref": "#/$defs/PictureClassificationMetaField"
},
{
"type": "null"
}
],
"default": null
},
"molecule": {
"anyOf": [
{
"$ref": "#/$defs/MoleculeMetaField"
},
{
"type": "null"
}
],
"default": null
},
"tabular_chart": {
"anyOf": [
{
"$ref": "#/$defs/TabularChartMetaField"
},
{
"type": "null"
}
],
"default": null
}
},
"title": "PictureMeta",
"type": "object"
},
"PictureMoleculeData": {
"description": "PictureMoleculeData.",
"properties": {
"kind": {
"const": "molecule_data",
"default": "molecule_data",
"title": "Kind",
"type": "string"
},
"smi": {
"title": "Smi",
"type": "string"
},
"confidence": {
"title": "Confidence",
"type": "number"
},
"class_name": {
"title": "Class Name",
"type": "string"
},
"segmentation": {
"items": {
"maxItems": 2,
"minItems": 2,
"prefixItems": [
{
"type": "number"
},
{
"type": "number"
}
],
"type": "array"
},
"title": "Segmentation",
"type": "array"
},
"provenance": {
"title": "Provenance",
"type": "string"
}
},
"required": [
"smi",
"confidence",
"class_name",
"segmentation",
"provenance"
],
"title": "PictureMoleculeData",
"type": "object"
},
"PicturePieChartData": {
"description": "Represents data of a pie chart.\n\nAttributes:\n kind (Literal[\"pie_chart_data\"]): The type of the chart.\n slices (List[ChartSlice]): A list of slices in the pie chart.",
"properties": {
"kind": {
"const": "pie_chart_data",
"default": "pie_chart_data",
"title": "Kind",
"type": "string"
},
"title": {
"title": "Title",
"type": "string"
},
"slices": {
"items": {
"$ref": "#/$defs/ChartSlice"
},
"title": "Slices",
"type": "array"
}
},
"required": [
"title",
"slices"
],
"title": "PicturePieChartData",
"type": "object"
},
"PictureScatterChartData": {
"description": "Represents data of a scatter chart.\n\nAttributes:\n kind (Literal[\"scatter_chart_data\"]): The type of the chart.\n x_axis_label (str): The label for the x-axis.\n y_axis_label (str): The label for the y-axis.\n points (List[ChartPoint]): A list of points in the scatter chart.",
"properties": {
"kind": {
"const": "scatter_chart_data",
"default": "scatter_chart_data",
"title": "Kind",
"type": "string"
},
"title": {
"title": "Title",
"type": "string"
},
"x_axis_label": {
"title": "X Axis Label",
"type": "string"
},
"y_axis_label": {
"title": "Y Axis Label",
"type": "string"
},
"points": {
"items": {
"$ref": "#/$defs/ChartPoint"
},
"title": "Points",
"type": "array"
}
},
"required": [
"title",
"x_axis_label",
"y_axis_label",
"points"
],
"title": "PictureScatterChartData",
"type": "object"
},
"PictureStackedBarChartData": {
"description": "Represents data of a stacked bar chart.\n\nAttributes:\n kind (Literal[\"stacked_bar_chart_data\"]): The type of the chart.\n x_axis_label (str): The label for the x-axis.\n y_axis_label (str): The label for the y-axis.\n stacked_bars (List[ChartStackedBar]): A list of stacked bars in the chart.",
"properties": {
"kind": {
"const": "stacked_bar_chart_data",
"default": "stacked_bar_chart_data",
"title": "Kind",
"type": "string"
},
"title": {
"title": "Title",
"type": "string"
},
"x_axis_label": {
"title": "X Axis Label",
"type": "string"
},
"y_axis_label": {
"title": "Y Axis Label",
"type": "string"
},
"stacked_bars": {
"items": {
"$ref": "#/$defs/ChartStackedBar"
},
"title": "Stacked Bars",
"type": "array"
}
},
"required": [
"title",
"x_axis_label",
"y_axis_label",
"stacked_bars"
],
"title": "PictureStackedBarChartData",
"type": "object"
},
"PictureTabularChartData": {
"description": "Base class for picture chart data.\n\nAttributes:\n title (str): The title of the chart.\n chart_data (TableData): Chart data in the table format.",
"properties": {
"kind": {
"const": "tabular_chart_data",
"default": "tabular_chart_data",
"title": "Kind",
"type": "string"
},
"title": {
"title": "Title",
"type": "string"
},
"chart_data": {
"$ref": "#/$defs/TableData"
}
},
"required": [
"title",
"chart_data"
],
"title": "PictureTabularChartData",
"type": "object"
},
"ProfilingItem": {
"properties": {
"scope": {
"$ref": "#/$defs/ProfilingScope"
},
"count": {
"default": 0,
"title": "Count",
"type": "integer"
},
"times": {
"default": [],
"items": {
"type": "number"
},
"title": "Times",
"type": "array"
},
"start_timestamps": {
"default": [],
"items": {
"format": "date-time",
"type": "string"
},
"title": "Start Timestamps",
"type": "array"
}
},
"required": [
"scope"
],
"title": "ProfilingItem",
"type": "object"
},
"ProfilingScope": {
"enum": [
"page",
"document"
],
"title": "ProfilingScope",
"type": "string"
},
"ProvenanceItem": {
"description": "ProvenanceItem.",
"properties": {
"page_no": {
"title": "Page No",
"type": "integer"
},
"bbox": {
"$ref": "#/$defs/BoundingBox"
},
"charspan": {
"maxItems": 2,
"minItems": 2,
"prefixItems": [
{
"type": "integer"
},
{
"type": "integer"
}
],
"title": "Charspan",
"type": "array"
}
},
"required": [
"page_no",
"bbox",
"charspan"
],
"title": "ProvenanceItem",
"type": "object"
},
"RefItem": {
"description": "RefItem.",
"properties": {
"$ref": {
"pattern": "^#(?:/([\\w-]+)(?:/(\\d+))?)?$",
"title": "$Ref",
"type": "string"
}
},
"required": [
"$ref"
],
"title": "RefItem",
"type": "object"
},
"RichTableCell": {
"description": "RichTableCell.",
"properties": {
"bbox": {
"anyOf": [
{
"$ref": "#/$defs/BoundingBox"
},
{
"type": "null"
}
],
"default": null
},
"row_span": {
"default": 1,
"title": "Row Span",
"type": "integer"
},
"col_span": {
"default": 1,
"title": "Col Span",
"type": "integer"
},
"start_row_offset_idx": {
"title": "Start Row Offset Idx",
"type": "integer"
},
"end_row_offset_idx": {
"title": "End Row Offset Idx",
"type": "integer"
},
"start_col_offset_idx": {
"title": "Start Col Offset Idx",
"type": "integer"
},
"end_col_offset_idx": {
"title": "End Col Offset Idx",
"type": "integer"
},
"text": {
"title": "Text",
"type": "string"
},
"column_header": {
"default": false,
"title": "Column Header",
"type": "boolean"
},
"row_header": {
"default": false,
"title": "Row Header",
"type": "boolean"
},
"row_section": {
"default": false,
"title": "Row Section",
"type": "boolean"
},
"fillable": {
"default": false,
"title": "Fillable",
"type": "boolean"
},
"ref": {
"$ref": "#/$defs/RefItem"
}
},
"required": [
"start_row_offset_idx",
"end_row_offset_idx",
"start_col_offset_idx",
"end_col_offset_idx",
"text",
"ref"
],
"title": "RichTableCell",
"type": "object"
},
"Script": {
"description": "Text script position.",
"enum": [
"baseline",
"sub",
"super"
],
"title": "Script",
"type": "string"
},
"SectionHeaderItem": {
"additionalProperties": false,
"description": "SectionItem.",
"properties": {
"self_ref": {
"pattern": "^#(?:/([\\w-]+)(?:/(\\d+))?)?$",
"title": "Self Ref",
"type": "string"
},
"parent": {
"anyOf": [
{
"$ref": "#/$defs/RefItem"
},
{
"type": "null"
}
],
"default": null
},
"children": {
"default": [],
"items": {
"$ref": "#/$defs/RefItem"
},
"title": "Children",
"type": "array"
},
"content_layer": {
"$ref": "#/$defs/ContentLayer",
"default": "body"
},
"meta": {
"anyOf": [
{
"$ref": "#/$defs/BaseMeta"
},
{
"type": "null"
}
],
"default": null
},
"label": {
"const": "section_header",
"default": "section_header",
"title": "Label",
"type": "string"
},
"prov": {
"default": [],
"items": {
"$ref": "#/$defs/ProvenanceItem"
},
"title": "Prov",
"type": "array"
},
"orig": {
"title": "Orig",
"type": "string"
},
"text": {
"title": "Text",
"type": "string"
},
"formatting": {
"anyOf": [
{
"$ref": "#/$defs/Formatting"
},
{
"type": "null"
}
],
"default": null
},
"hyperlink": {
"anyOf": [
{
"format": "uri",
"minLength": 1,
"type": "string"
},
{
"format": "path",
"type": "string"
},
{
"type": "null"
}
],
"default": null,
"title": "Hyperlink"
},
"level": {
"default": 1,
"maximum": 100,
"minimum": 1,
"title": "Level",
"type": "integer"
}
},
"required": [
"self_ref",
"orig",
"text"
],
"title": "SectionHeaderItem",
"type": "object"
},
"SegmentedPdfPage": {
"description": "Extended segmented page model specific to PDF documents.",
"properties": {
"dimension": {
"$ref": "#/$defs/PdfPageGeometry"
},
"bitmap_resources": {
"default": [],
"items": {
"$ref": "#/$defs/BitmapResource"
},
"title": "Bitmap Resources",
"type": "array"
},
"char_cells": {
"items": {
"anyOf": [
{
"$ref": "#/$defs/PdfTextCell"
},
{
"$ref": "#/$defs/TextCell"
}
]
},
"title": "Char Cells",
"type": "array"
},
"word_cells": {
"items": {
"anyOf": [
{
"$ref": "#/$defs/PdfTextCell"
},
{
"$ref": "#/$defs/TextCell"
}
]
},
"title": "Word Cells",
"type": "array"
},
"textline_cells": {
"items": {
"anyOf": [
{
"$ref": "#/$defs/PdfTextCell"
},
{
"$ref": "#/$defs/TextCell"
}
]
},
"title": "Textline Cells",
"type": "array"
},
"has_chars": {
"default": false,
"title": "Has Chars",
"type": "boolean"
},
"has_words": {
"default": false,
"title": "Has Words",
"type": "boolean"
},
"has_lines": {
"default": false,
"title": "Has Lines",
"type": "boolean"
},
"image": {
"anyOf": [
{
"$ref": "#/$defs/ImageRef"
},
{
"type": "null"
}
],
"default": null
},
"lines": {
"default": [],
"items": {
"$ref": "#/$defs/PdfLine"
},
"title": "Lines",
"type": "array"
}
},
"required": [
"dimension",
"char_cells",
"word_cells",
"textline_cells"
],
"title": "SegmentedPdfPage",
"type": "object"
},
"Size": {
"description": "Size.",
"properties": {
"width": {
"default": 0.0,
"title": "Width",
"type": "number"
},
"height": {
"default": 0.0,
"title": "Height",
"type": "number"
}
},
"title": "Size",
"type": "object"
},
"SummaryMetaField": {
"additionalProperties": true,
"description": "Summary data.",
"properties": {
"confidence": {
"anyOf": [
{
"maximum": 1,
"minimum": 0,
"type": "number"
},
{
"type": "null"
}
],
"default": null,
"description": "The confidence of the prediction.",
"examples": [
0.9,
0.42
],
"title": "Confidence"
},
"created_by": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"default": null,
"description": "The origin of the prediction.",
"examples": [
"ibm-granite/granite-docling-258M"
],
"title": "Created By"
},
"text": {
"title": "Text",
"type": "string"
}
},
"required": [
"text"
],
"title": "SummaryMetaField",
"type": "object"
},
"Table": {
"properties": {
"label": {
"$ref": "#/$defs/DocItemLabel"
},
"id": {
"title": "Id",
"type": "integer"
},
"page_no": {
"title": "Page No",
"type": "integer"
},
"cluster": {
"$ref": "#/$defs/Cluster"
},
"text": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"default": null,
"title": "Text"
},
"otsl_seq": {
"items": {
"type": "string"
},
"title": "Otsl Seq",
"type": "array"
},
"num_rows": {
"default": 0,
"title": "Num Rows",
"type": "integer"
},
"num_cols": {
"default": 0,
"title": "Num Cols",
"type": "integer"
},
"table_cells": {
"items": {
"$ref": "#/$defs/TableCell"
},
"title": "Table Cells",
"type": "array"
}
},
"required": [
"label",
"id",
"page_no",
"cluster",
"otsl_seq",
"table_cells"
],
"title": "Table",
"type": "object"
},
"TableCell": {
"description": "TableCell.",
"properties": {
"bbox": {
"anyOf": [
{
"$ref": "#/$defs/BoundingBox"
},
{
"type": "null"
}
],
"default": null
},
"row_span": {
"default": 1,
"title": "Row Span",
"type": "integer"
},
"col_span": {
"default": 1,
"title": "Col Span",
"type": "integer"
},
"start_row_offset_idx": {
"title": "Start Row Offset Idx",
"type": "integer"
},
"end_row_offset_idx": {
"title": "End Row Offset Idx",
"type": "integer"
},
"start_col_offset_idx": {
"title": "Start Col Offset Idx",
"type": "integer"
},
"end_col_offset_idx": {
"title": "End Col Offset Idx",
"type": "integer"
},
"text": {
"title": "Text",
"type": "string"
},
"column_header": {
"default": false,
"title": "Column Header",
"type": "boolean"
},
"row_header": {
"default": false,
"title": "Row Header",
"type": "boolean"
},
"row_section": {
"default": false,
"title": "Row Section",
"type": "boolean"
},
"fillable": {
"default": false,
"title": "Fillable",
"type": "boolean"
}
},
"required": [
"start_row_offset_idx",
"end_row_offset_idx",
"start_col_offset_idx",
"end_col_offset_idx",
"text"
],
"title": "TableCell",
"type": "object"
},
"TableData": {
"description": "BaseTableData.",
"properties": {
"table_cells": {
"default": [],
"items": {
"anyOf": [
{
"$ref": "#/$defs/RichTableCell"
},
{
"$ref": "#/$defs/TableCell"
}
]
},
"title": "Table Cells",
"type": "array"
},
"num_rows": {
"default": 0,
"title": "Num Rows",
"type": "integer"
},
"num_cols": {
"default": 0,
"title": "Num Cols",
"type": "integer"
}
},
"title": "TableData",
"type": "object"
},
"TableItem": {
"additionalProperties": false,
"description": "TableItem.",
"properties": {
"self_ref": {
"pattern": "^#(?:/([\\w-]+)(?:/(\\d+))?)?$",
"title": "Self Ref",
"type": "string"
},
"parent": {
"anyOf": [
{
"$ref": "#/$defs/RefItem"
},
{
"type": "null"
}
],
"default": null
},
"children": {
"default": [],
"items": {
"$ref": "#/$defs/RefItem"
},
"title": "Children",
"type": "array"
},
"content_layer": {
"$ref": "#/$defs/ContentLayer",
"default": "body"
},
"meta": {
"anyOf": [
{
"$ref": "#/$defs/FloatingMeta"
},
{
"type": "null"
}
],
"default": null
},
"label": {
"default": "table",
"enum": [
"document_index",
"table"
],
"title": "Label",
"type": "string"
},
"prov": {
"default": [],
"items": {
"$ref": "#/$defs/ProvenanceItem"
},
"title": "Prov",
"type": "array"
},
"captions": {
"default": [],
"items": {
"$ref": "#/$defs/RefItem"
},
"title": "Captions",
"type": "array"
},
"references": {
"default": [],
"items": {
"$ref": "#/$defs/RefItem"
},
"title": "References",
"type": "array"
},
"footnotes": {
"default": [],
"items": {
"$ref": "#/$defs/RefItem"
},
"title": "Footnotes",
"type": "array"
},
"image": {
"anyOf": [
{
"$ref": "#/$defs/ImageRef"
},
{
"type": "null"
}
],
"default": null
},
"data": {
"$ref": "#/$defs/TableData"
},
"annotations": {
"default": [],
"deprecated": true,
"items": {
"discriminator": {
"mapping": {
"description": "#/$defs/DescriptionAnnotation",
"misc": "#/$defs/MiscAnnotation"
},
"propertyName": "kind"
},
"oneOf": [
{
"$ref": "#/$defs/DescriptionAnnotation"
},
{
"$ref": "#/$defs/MiscAnnotation"
}
]
},
"title": "Annotations",
"type": "array"
}
},
"required": [
"self_ref",
"data"
],
"title": "TableItem",
"type": "object"
},
"TableStructurePrediction": {
"properties": {
"table_map": {
"additionalProperties": {
"$ref": "#/$defs/Table"
},
"default": {},
"title": "Table Map",
"type": "object"
}
},
"title": "TableStructurePrediction",
"type": "object"
},
"TabularChartMetaField": {
"additionalProperties": true,
"description": "Tabular chart metadata field.",
"properties": {
"confidence": {
"anyOf": [
{
"maximum": 1,
"minimum": 0,
"type": "number"
},
{
"type": "null"
}
],
"default": null,
"description": "The confidence of the prediction.",
"examples": [
0.9,
0.42
],
"title": "Confidence"
},
"created_by": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"default": null,
"description": "The origin of the prediction.",
"examples": [
"ibm-granite/granite-docling-258M"
],
"title": "Created By"
},
"title": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"default": null,
"title": "Title"
},
"chart_data": {
"$ref": "#/$defs/TableData"
}
},
"required": [
"chart_data"
],
"title": "TabularChartMetaField",
"type": "object"
},
"TextCell": {
"description": "Model representing a text cell with positioning and content information.",
"properties": {
"index": {
"default": -1,
"title": "Index",
"type": "integer"
},
"rgba": {
"$ref": "#/$defs/ColorRGBA",
"default": {
"r": 0,
"g": 0,
"b": 0,
"a": 255
}
},
"rect": {
"$ref": "#/$defs/BoundingRectangle"
},
"text": {
"title": "Text",
"type": "string"
},
"orig": {
"title": "Orig",
"type": "string"
},
"text_direction": {
"$ref": "#/$defs/TextDirection",
"default": "left_to_right"
},
"confidence": {
"default": 1.0,
"title": "Confidence",
"type": "number"
},
"from_ocr": {
"title": "From Ocr",
"type": "boolean"
}
},
"required": [
"rect",
"text",
"orig",
"from_ocr"
],
"title": "TextCell",
"type": "object"
},
"TextDirection": {
"description": "Enumeration for text direction options.",
"enum": [
"left_to_right",
"right_to_left",
"unspecified"
],
"title": "TextDirection",
"type": "string"
},
"TextElement": {
"properties": {
"label": {
"$ref": "#/$defs/DocItemLabel"
},
"id": {
"title": "Id",
"type": "integer"
},
"page_no": {
"title": "Page No",
"type": "integer"
},
"cluster": {
"$ref": "#/$defs/Cluster"
},
"text": {
"title": "Text",
"type": "string"
}
},
"required": [
"label",
"id",
"page_no",
"cluster",
"text"
],
"title": "TextElement",
"type": "object"
},
"TextItem": {
"additionalProperties": false,
"description": "TextItem.",
"properties": {
"self_ref": {
"pattern": "^#(?:/([\\w-]+)(?:/(\\d+))?)?$",
"title": "Self Ref",
"type": "string"
},
"parent": {
"anyOf": [
{
"$ref": "#/$defs/RefItem"
},
{
"type": "null"
}
],
"default": null
},
"children": {
"default": [],
"items": {
"$ref": "#/$defs/RefItem"
},
"title": "Children",
"type": "array"
},
"content_layer": {
"$ref": "#/$defs/ContentLayer",
"default": "body"
},
"meta": {
"anyOf": [
{
"$ref": "#/$defs/BaseMeta"
},
{
"type": "null"
}
],
"default": null
},
"label": {
"enum": [
"caption",
"checkbox_selected",
"checkbox_unselected",
"footnote",
"page_footer",
"page_header",
"paragraph",
"reference",
"text",
"empty_value"
],
"title": "Label",
"type": "string"
},
"prov": {
"default": [],
"items": {
"$ref": "#/$defs/ProvenanceItem"
},
"title": "Prov",
"type": "array"
},
"orig": {
"title": "Orig",
"type": "string"
},
"text": {
"title": "Text",
"type": "string"
},
"formatting": {
"anyOf": [
{
"$ref": "#/$defs/Formatting"
},
{
"type": "null"
}
],
"default": null
},
"hyperlink": {
"anyOf": [
{
"format": "uri",
"minLength": 1,
"type": "string"
},
{
"format": "path",
"type": "string"
},
{
"type": "null"
}
],
"default": null,
"title": "Hyperlink"
}
},
"required": [
"self_ref",
"label",
"orig",
"text"
],
"title": "TextItem",
"type": "object"
},
"TitleItem": {
"additionalProperties": false,
"description": "TitleItem.",
"properties": {
"self_ref": {
"pattern": "^#(?:/([\\w-]+)(?:/(\\d+))?)?$",
"title": "Self Ref",
"type": "string"
},
"parent": {
"anyOf": [
{
"$ref": "#/$defs/RefItem"
},
{
"type": "null"
}
],
"default": null
},
"children": {
"default": [],
"items": {
"$ref": "#/$defs/RefItem"
},
"title": "Children",
"type": "array"
},
"content_layer": {
"$ref": "#/$defs/ContentLayer",
"default": "body"
},
"meta": {
"anyOf": [
{
"$ref": "#/$defs/BaseMeta"
},
{
"type": "null"
}
],
"default": null
},
"label": {
"const": "title",
"default": "title",
"title": "Label",
"type": "string"
},
"prov": {
"default": [],
"items": {
"$ref": "#/$defs/ProvenanceItem"
},
"title": "Prov",
"type": "array"
},
"orig": {
"title": "Orig",
"type": "string"
},
"text": {
"title": "Text",
"type": "string"
},
"formatting": {
"anyOf": [
{
"$ref": "#/$defs/Formatting"
},
{
"type": "null"
}
],
"default": null
},
"hyperlink": {
"anyOf": [
{
"format": "uri",
"minLength": 1,
"type": "string"
},
{
"format": "path",
"type": "string"
},
{
"type": "null"
}
],
"default": null,
"title": "Hyperlink"
}
},
"required": [
"self_ref",
"orig",
"text"
],
"title": "TitleItem",
"type": "object"
},
"VlmPrediction": {
"properties": {
"text": {
"default": "",
"title": "Text",
"type": "string"
},
"generated_tokens": {
"default": [],
"items": {
"$ref": "#/$defs/VlmPredictionToken"
},
"title": "Generated Tokens",
"type": "array"
},
"generation_time": {
"default": -1,
"title": "Generation Time",
"type": "number"
},
"num_tokens": {
"anyOf": [
{
"type": "integer"
},
{
"type": "null"
}
],
"default": null,
"title": "Num Tokens"
},
"stop_reason": {
"$ref": "#/$defs/VlmStopReason",
"default": "unspecified"
},
"input_prompt": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"default": null,
"title": "Input Prompt"
}
},
"title": "VlmPrediction",
"type": "object"
},
"VlmPredictionToken": {
"properties": {
"text": {
"default": "",
"title": "Text",
"type": "string"
},
"token": {
"default": -1,
"title": "Token",
"type": "integer"
},
"logprob": {
"default": -1,
"title": "Logprob",
"type": "number"
}
},
"title": "VlmPredictionToken",
"type": "object"
},
"VlmStopReason": {
"enum": [
"length",
"stop_sequence",
"end_of_sequence",
"unspecified"
],
"title": "VlmStopReason",
"type": "string"
}
},
"properties": {
"version": {
"$ref": "#/$defs/DoclingVersion",
"default": {
"docling_version": "2.64.1",
"docling_core_version": "2.51.1",
"docling_ibm_models_version": "3.10.2",
"docling_parse_version": "4.7.1",
"platform_str": "Linux-6.11.0-1018-azure-x86_64-with-glibc2.39",
"py_impl_version": "cpython-312",
"py_lang_version": "3.12.3"
}
},
"timestamp": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"default": null,
"title": "Timestamp"
},
"status": {
"$ref": "#/$defs/ConversionStatus",
"default": "pending"
},
"errors": {
"default": [],
"items": {
"$ref": "#/$defs/ErrorItem"
},
"title": "Errors",
"type": "array"
},
"pages": {
"default": [],
"items": {
"$ref": "#/$defs/Page"
},
"title": "Pages",
"type": "array"
},
"timings": {
"additionalProperties": {
"$ref": "#/$defs/ProfilingItem"
},
"default": {},
"title": "Timings",
"type": "object"
},
"confidence": {
"$ref": "#/$defs/ConfidenceReport"
},
"document": {
"$ref": "#/$defs/DoclingDocument",
"default": {
"schema_name": "DoclingDocument",
"version": "1.8.0",
"name": "dummy",
"origin": null,
"furniture": {
"children": [],
"content_layer": "furniture",
"label": "unspecified",
"meta": null,
"name": "_root_",
"parent": null,
"self_ref": "#/furniture"
},
"body": {
"children": [],
"content_layer": "body",
"label": "unspecified",
"meta": null,
"name": "_root_",
"parent": null,
"self_ref": "#/body"
},
"groups": [],
"texts": [],
"pictures": [],
"tables": [],
"key_value_items": [],
"form_items": [],
"pages": {}
}
},
"input": {
"$ref": "#/$defs/InputDocument"
},
"assembled": {
"$ref": "#/$defs/AssembledUnit",
"default": {
"elements": [],
"body": [],
"headers": []
}
}
},
"required": [
"input"
],
"title": "ConversionResult",
"type": "object"
}
Fields:
-
version(DoclingVersion) -
timestamp(Optional[str]) -
status(ConversionStatus) -
errors(list[ErrorItem]) -
pages(list[Page]) -
timings(dict[str, ProfilingItem]) -
confidence(ConfidenceReport) -
document(DoclingDocument) -
input(InputDocument) -
assembled(AssembledUnit)
pydantic-field
assembled: AssembledUnit
pydantic-field
confidence: ConfidenceReport
pydantic-field
errors: list[ErrorItem] = []
pydantic-field
input: InputDocument
property
legacy_document
pydantic-field
pages: list[Page] = []
pydantic-field
timestamp: Optional[str] = None
pydantic-field
timings: dict[str, ProfilingItem] = {}
pydantic-field
version: DoclingVersion
classmethod
load(filename: Union[str, Path]) -> ConversionAssets
Load a ConversionAssets.
save(*, filename: Union[str, Path], indent: Optional[int] = 2)
Serialize the full ConversionAssets to JSON.
Bases: str, Enum
Attributes:
class-attribute
instance-attribute
FAILURE = 'failure'
class-attribute
instance-attribute
PARTIAL_SUCCESS = 'partial_success'
class-attribute
instance-attribute
PENDING = 'pending'
class-attribute
instance-attribute
SKIPPED = 'skipped'
class-attribute
instance-attribute
STARTED = 'started'
class-attribute
instance-attribute
SUCCESS = 'success'
pydantic-model
Bases: BaseFormatOption
Show JSON schema:
{
"$defs": {
"AcceleratorDevice": {
"description": "Devices to run model inference",
"enum": [
"auto",
"cpu",
"cuda",
"mps"
],
"title": "AcceleratorDevice",
"type": "string"
},
"AcceleratorOptions": {
"additionalProperties": false,
"properties": {
"num_threads": {
"default": 4,
"title": "Num Threads",
"type": "integer"
},
"device": {
"anyOf": [
{
"type": "string"
},
{
"$ref": "#/$defs/AcceleratorDevice"
}
],
"default": "auto",
"title": "Device"
},
"cuda_use_flash_attention2": {
"default": false,
"title": "Cuda Use Flash Attention2",
"type": "boolean"
}
},
"title": "AcceleratorOptions",
"type": "object"
},
"DeclarativeBackendOptions": {
"description": "Default backend options for a declarative document backend.",
"properties": {
"enable_remote_fetch": {
"default": false,
"description": "Enable remote resource fetching.",
"title": "Enable Remote Fetch",
"type": "boolean"
},
"enable_local_fetch": {
"default": false,
"description": "Enable local resource fetching.",
"title": "Enable Local Fetch",
"type": "boolean"
},
"kind": {
"const": "declarative",
"default": "declarative",
"title": "Kind",
"type": "string"
}
},
"title": "DeclarativeBackendOptions",
"type": "object"
},
"HTMLBackendOptions": {
"description": "Options specific to the HTML backend.\n\nThis class can be extended to include options specific to HTML processing.",
"properties": {
"enable_remote_fetch": {
"default": false,
"description": "Enable remote resource fetching.",
"title": "Enable Remote Fetch",
"type": "boolean"
},
"enable_local_fetch": {
"default": false,
"description": "Enable local resource fetching.",
"title": "Enable Local Fetch",
"type": "boolean"
},
"kind": {
"const": "html",
"default": "html",
"title": "Kind",
"type": "string"
},
"fetch_images": {
"default": false,
"description": "Whether the backend should access remote or local resources to parse images in an HTML document.",
"title": "Fetch Images",
"type": "boolean"
},
"source_uri": {
"anyOf": [
{
"format": "uri",
"minLength": 1,
"type": "string"
},
{
"format": "path",
"type": "string"
},
{
"type": "null"
}
],
"default": null,
"description": "The URI that originates the HTML document. If provided, the backend will use it to resolve relative paths in the HTML document.",
"title": "Source Uri"
}
},
"title": "HTMLBackendOptions",
"type": "object"
},
"MarkdownBackendOptions": {
"description": "Options specific to the Markdown backend.",
"properties": {
"enable_remote_fetch": {
"default": false,
"description": "Enable remote resource fetching.",
"title": "Enable Remote Fetch",
"type": "boolean"
},
"enable_local_fetch": {
"default": false,
"description": "Enable local resource fetching.",
"title": "Enable Local Fetch",
"type": "boolean"
},
"kind": {
"const": "md",
"default": "md",
"title": "Kind",
"type": "string"
},
"fetch_images": {
"default": false,
"description": "Whether the backend should access remote or local resources to parse images in the markdown document.",
"title": "Fetch Images",
"type": "boolean"
},
"source_uri": {
"anyOf": [
{
"format": "uri",
"minLength": 1,
"type": "string"
},
{
"format": "path",
"type": "string"
},
{
"type": "null"
}
],
"default": null,
"description": "The URI that originates the markdown document. If provided, the backend will use it to resolve relative paths in the markdown document.",
"title": "Source Uri"
}
},
"title": "MarkdownBackendOptions",
"type": "object"
},
"MsExcelBackendOptions": {
"description": "Options specific to the MS Excel backend.",
"properties": {
"enable_remote_fetch": {
"default": false,
"description": "Enable remote resource fetching.",
"title": "Enable Remote Fetch",
"type": "boolean"
},
"enable_local_fetch": {
"default": false,
"description": "Enable local resource fetching.",
"title": "Enable Local Fetch",
"type": "boolean"
},
"kind": {
"const": "xlsx",
"default": "xlsx",
"title": "Kind",
"type": "string"
},
"treat_singleton_as_text": {
"default": false,
"description": "Whether to treat singleton cells (1x1 tables with empty neighboring cells) as TextItem instead of TableItem.",
"title": "Treat Singleton As Text",
"type": "boolean"
}
},
"title": "MsExcelBackendOptions",
"type": "object"
},
"PdfBackendOptions": {
"description": "Backend options for pdf document backends.",
"properties": {
"enable_remote_fetch": {
"default": false,
"description": "Enable remote resource fetching.",
"title": "Enable Remote Fetch",
"type": "boolean"
},
"enable_local_fetch": {
"default": false,
"description": "Enable local resource fetching.",
"title": "Enable Local Fetch",
"type": "boolean"
},
"kind": {
"const": "pdf",
"default": "pdf",
"title": "Kind",
"type": "string"
},
"password": {
"anyOf": [
{
"format": "password",
"type": "string",
"writeOnly": true
},
{
"type": "null"
}
],
"default": null,
"title": "Password"
}
},
"title": "PdfBackendOptions",
"type": "object"
},
"PipelineOptions": {
"description": "Base pipeline options.",
"properties": {
"document_timeout": {
"anyOf": [
{
"type": "number"
},
{
"type": "null"
}
],
"default": null,
"description": "Maximum allowed processing time for a document before timing out. If None, no timeout is enforced.",
"examples": [
10.0,
20.0
],
"title": "Document Timeout"
},
"accelerator_options": {
"$ref": "#/$defs/AcceleratorOptions",
"default": {
"num_threads": 4,
"device": "auto",
"cuda_use_flash_attention2": false
},
"description": "Configuration options for hardware acceleration (e.g., GPU or optimized execution settings)."
},
"enable_remote_services": {
"default": false,
"description": "Enable calling external APIs or cloud services during pipeline execution.",
"examples": [
false
],
"title": "Enable Remote Services",
"type": "boolean"
},
"allow_external_plugins": {
"default": false,
"description": "Allow loading external third-party plugins or modules. Disabled by default for safety.",
"examples": [
false
],
"title": "Allow External Plugins",
"type": "boolean"
},
"artifacts_path": {
"anyOf": [
{
"format": "path",
"type": "string"
},
{
"type": "string"
},
{
"type": "null"
}
],
"default": null,
"description": "Filesystem path where pipeline artifacts should be stored. If None, artifacts will be fetched. You can use the utility `docling-tools models download` to pre-fetch the model artifacts.",
"examples": [
"./artifacts",
"/tmp/docling_outputs"
],
"title": "Artifacts Path"
}
},
"title": "PipelineOptions",
"type": "object"
}
},
"properties": {
"pipeline_options": {
"anyOf": [
{
"$ref": "#/$defs/PipelineOptions"
},
{
"type": "null"
}
],
"default": null
},
"backend": {
"title": "Backend"
},
"pipeline_cls": {
"title": "Pipeline Cls"
},
"backend_options": {
"anyOf": [
{
"discriminator": {
"mapping": {
"declarative": "#/$defs/DeclarativeBackendOptions",
"html": "#/$defs/HTMLBackendOptions",
"md": "#/$defs/MarkdownBackendOptions",
"pdf": "#/$defs/PdfBackendOptions",
"xlsx": "#/$defs/MsExcelBackendOptions"
},
"propertyName": "kind"
},
"oneOf": [
{
"$ref": "#/$defs/DeclarativeBackendOptions"
},
{
"$ref": "#/$defs/HTMLBackendOptions"
},
{
"$ref": "#/$defs/MarkdownBackendOptions"
},
{
"$ref": "#/$defs/PdfBackendOptions"
},
{
"$ref": "#/$defs/MsExcelBackendOptions"
}
]
},
{
"type": "null"
}
],
"default": null,
"title": "Backend Options"
}
},
"required": [
"backend",
"pipeline_cls"
],
"title": "FormatOption",
"type": "object"
}
Config:
arbitrary_types_allowed:True
Fields:
-
pipeline_options(Optional[PipelineOptions]) -
backend(Type[AbstractDocumentBackend]) -
pipeline_cls(Type[BasePipeline]) -
backend_options(Optional[BackendOptions])
Validators:
pydantic-field
backend: Type[AbstractDocumentBackend]
pydantic-field
backend_options: Optional[BackendOptions] = None
class-attribute
instance-attribute
model_config = ConfigDict(arbitrary_types_allowed=True)
pydantic-field
pipeline_cls: Type[BasePipeline]
pydantic-validator
set_optional_field_default() -> Self
Bases: str, Enum
A document format supported by document backend parsers.
Attributes:
-
ASCIIDOC– -
AUDIO– -
CSV– -
DOCX– -
HTML– -
IMAGE– -
JSON_DOCLING– -
MD– -
METS_GBS– -
PDF– -
PPTX– -
VTT– -
XLSX– -
XML_JATS– -
XML_USPTO–
class-attribute
instance-attribute
ASCIIDOC = 'asciidoc'
class-attribute
instance-attribute
AUDIO = 'audio'
class-attribute
instance-attribute
CSV = 'csv'
class-attribute
instance-attribute
DOCX = 'docx'
class-attribute
instance-attribute
HTML = 'html'
class-attribute
instance-attribute
IMAGE = 'image'
class-attribute
instance-attribute
JSON_DOCLING = 'json_docling'
class-attribute
instance-attribute
MD = 'md'
class-attribute
instance-attribute
METS_GBS = 'mets_gbs'
class-attribute
instance-attribute
PDF = 'pdf'
class-attribute
instance-attribute
PPTX = 'pptx'
class-attribute
instance-attribute
VTT = 'vtt'
class-attribute
instance-attribute
XLSX = 'xlsx'
class-attribute
instance-attribute
XML_JATS = 'xml_jats'
class-attribute
instance-attribute
XML_USPTO = 'xml_uspto'
pydantic-model
Bases: FormatOption
Fields:
-
pipeline_options(Optional[PipelineOptions]) -
pipeline_cls(Type) -
backend(Type[AbstractDocumentBackend]) -
backend_options(Optional[PdfBackendOptions])
Validators:
pydantic-field
backend: Type[AbstractDocumentBackend] = DoclingParseV4DocumentBackend
pydantic-field
backend_options: Optional[PdfBackendOptions] = None
class-attribute
instance-attribute
model_config = ConfigDict(arbitrary_types_allowed=True)
pydantic-validator
set_optional_field_default() -> Self
pydantic-model
Bases: FormatOption
Fields:
-
pipeline_options(Optional[PipelineOptions]) -
backend_options(Optional[BackendOptions]) -
pipeline_cls(Type) -
backend(Type[AbstractDocumentBackend])
Validators:
pydantic-field
backend: Type[AbstractDocumentBackend] = ImageDocumentBackend
pydantic-field
backend_options: Optional[BackendOptions] = None
class-attribute
instance-attribute
model_config = ConfigDict(arbitrary_types_allowed=True)
pydantic-validator
set_optional_field_default() -> Self
StandardPdfPipeline(pipeline_options: ThreadedPdfPipelineOptions)
Bases: ConvertPipeline
High-performance PDF pipeline with multi-threaded stages.
Methods:
Attributes:
-
artifacts_path(Optional[Path]) – -
build_pipe(List[Callable]) – -
enrichment_pipe– -
keep_images– -
pipeline_options(ThreadedPdfPipelineOptions) –
instance-attribute
artifacts_path: Optional[Path] = None
instance-attribute
build_pipe: List[Callable] = []
instance-attribute
enrichment_pipe = [DocumentPictureClassifier(enabled=do_picture_classification, artifacts_path=artifacts_path, options=DocumentPictureClassifierOptions(), accelerator_options=accelerator_options), picture_description_model]
instance-attribute
keep_images = False
classmethod
is_backend_supported(backend: AbstractDocumentBackend) -> bool
pydantic-model
Bases: FormatOption
Fields:
-
pipeline_options(Optional[PipelineOptions]) -
backend_options(Optional[BackendOptions]) -
pipeline_cls(Type) -
backend(Type[AbstractDocumentBackend])
Validators:
pydantic-field
backend: Type[AbstractDocumentBackend] = MsWordDocumentBackend
pydantic-field
backend_options: Optional[BackendOptions] = None
class-attribute
instance-attribute
model_config = ConfigDict(arbitrary_types_allowed=True)
pydantic-validator
set_optional_field_default() -> Self
pydantic-model
Bases: FormatOption
Fields:
-
pipeline_options(Optional[PipelineOptions]) -
backend_options(Optional[BackendOptions]) -
pipeline_cls(Type) -
backend(Type[AbstractDocumentBackend])
Validators:
pydantic-field
backend: Type[AbstractDocumentBackend] = MsPowerpointDocumentBackend
pydantic-field
backend_options: Optional[BackendOptions] = None
class-attribute
instance-attribute
model_config = ConfigDict(arbitrary_types_allowed=True)
pydantic-validator
set_optional_field_default() -> Self
pydantic-model
Bases: FormatOption
Fields:
-
pipeline_options(Optional[PipelineOptions]) -
pipeline_cls(Type) -
backend(Type[AbstractDocumentBackend]) -
backend_options(Optional[MarkdownBackendOptions])
Validators:
pydantic-field
backend: Type[AbstractDocumentBackend] = MarkdownDocumentBackend
pydantic-field
backend_options: Optional[MarkdownBackendOptions] = None
class-attribute
instance-attribute
model_config = ConfigDict(arbitrary_types_allowed=True)
pydantic-validator
set_optional_field_default() -> Self
pydantic-model
Bases: FormatOption
Fields:
-
pipeline_options(Optional[PipelineOptions]) -
backend_options(Optional[BackendOptions]) -
pipeline_cls(Type) -
backend(Type[AbstractDocumentBackend])
Validators:
pydantic-field
backend: Type[AbstractDocumentBackend] = AsciiDocBackend
pydantic-field
backend_options: Optional[BackendOptions] = None
class-attribute
instance-attribute
model_config = ConfigDict(arbitrary_types_allowed=True)
pydantic-validator
set_optional_field_default() -> Self
pydantic-model
Bases: FormatOption
Fields:
-
pipeline_options(Optional[PipelineOptions]) -
pipeline_cls(Type) -
backend(Type[AbstractDocumentBackend]) -
backend_options(Optional[HTMLBackendOptions])
Validators:
pydantic-field
backend: Type[AbstractDocumentBackend] = HTMLDocumentBackend
pydantic-field
backend_options: Optional[HTMLBackendOptions] = None
class-attribute
instance-attribute
model_config = ConfigDict(arbitrary_types_allowed=True)
pydantic-validator
set_optional_field_default() -> Self
SimplePipeline(pipeline_options: ConvertPipelineOptions)
Bases: ConvertPipeline
SimpleModelPipeline.
This class is used at the moment for formats / backends which produce straight DoclingDocument output.
Methods:
Attributes:
-
artifacts_path(Optional[Path]) – -
build_pipe(List[Callable]) – -
enrichment_pipe– -
keep_images– -
pipeline_options(ConvertPipelineOptions) –
instance-attribute
artifacts_path: Optional[Path] = None
instance-attribute
build_pipe: List[Callable] = []
instance-attribute
enrichment_pipe = [DocumentPictureClassifier(enabled=do_picture_classification, artifacts_path=artifacts_path, options=DocumentPictureClassifierOptions(), accelerator_options=accelerator_options), picture_description_model]
instance-attribute
keep_images = False
classmethod
is_backend_supported(backend: AbstractDocumentBackend)