Docling Document
This is an automatic generated API reference of the DoclingDocument type.
Package for models defined by the Document type.
Classes:
-
DoclingDocument–DoclingDocument.
-
DocumentOrigin–FileSource.
-
DocItem–Base type for any element that carries content, can be a leaf node.
-
DocItemLabel–DocItemLabel.
-
ProvenanceItem–Provenance information for elements extracted from a textual document.
-
GroupItem–GroupItem.
-
GroupLabel–GroupLabel.
-
NodeItem–NodeItem.
-
PageItem–PageItem.
-
FloatingItem–FloatingItem.
-
TextItem–TextItem.
-
TableItem–TableItem.
-
TableCell–TableCell.
-
TableData–BaseTableData.
-
TableCellLabel–TableCellLabel.
-
KeyValueItem–KeyValueItem.
-
SectionHeaderItem–SectionItem.
-
PictureItem–PictureItem.
-
ImageRef–ImageRef.
-
PictureClassificationClass–PictureClassificationData.
-
PictureClassificationData–PictureClassificationData.
-
RefItem–RefItem.
-
BoundingBox–BoundingBox.
-
CoordOrigin–CoordOrigin.
-
ImageRefMode–ImageRefMode.
-
Size–Size.
Bases: BaseModel
DoclingDocument.
Show JSON schema:
{
"$defs": {
"BaseMeta": {
"additionalProperties": true,
"description": "Base class for metadata.",
"properties": {
"summary": {
"anyOf": [
{
"$ref": "#/$defs/SummaryMetaField"
},
{
"type": "null"
}
],
"default": null
},
"language": {
"anyOf": [
{
"$ref": "#/$defs/LanguageMetaField"
},
{
"type": "null"
}
],
"default": null
},
"entities": {
"anyOf": [
{
"$ref": "#/$defs/EntitiesMetaField"
},
{
"type": "null"
}
],
"default": null
}
},
"title": "BaseMeta",
"type": "object"
},
"BoundingBox": {
"description": "BoundingBox.",
"properties": {
"l": {
"title": "L",
"type": "number"
},
"t": {
"title": "T",
"type": "number"
},
"r": {
"title": "R",
"type": "number"
},
"b": {
"title": "B",
"type": "number"
},
"coord_origin": {
"$ref": "#/$defs/CoordOrigin",
"default": "TOPLEFT"
}
},
"required": [
"l",
"t",
"r",
"b"
],
"title": "BoundingBox",
"type": "object"
},
"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"
},
"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"
},
"source": {
"default": [],
"description": "The provenance of this document item. Currently, it is only used for media track provenance.",
"items": {
"discriminator": {
"mapping": {
"track": "#/$defs/TrackSource"
},
"propertyName": "kind"
},
"oneOf": [
{
"$ref": "#/$defs/TrackSource"
}
]
},
"title": "Source",
"type": "array"
},
"comments": {
"default": [],
"items": {
"$ref": "#/$defs/FineRef"
},
"title": "Comments",
"type": "array"
},
"orig": {
"title": "Orig",
"type": "string"
},
"text": {
"title": "Text",
"type": "string"
},
"formatting": {
"anyOf": [
{
"$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": "#/$defs/CodeLanguageLabel",
"default": "unknown"
}
},
"required": [
"self_ref",
"orig",
"text"
],
"title": "CodeItem",
"type": "object"
},
"CodeLanguageLabel": {
"description": "CodeLanguageLabel.",
"enum": [
"Ada",
"Awk",
"Bash",
"bc",
"C",
"C#",
"C++",
"CMake",
"COBOL",
"CSS",
"Ceylon",
"Clojure",
"Crystal",
"Cuda",
"Cython",
"D",
"Dart",
"dc",
"Dockerfile",
"DocLang",
"Elixir",
"Erlang",
"FORTRAN",
"Forth",
"Go",
"HTML",
"Haskell",
"Haxe",
"Java",
"JavaScript",
"JSON",
"Julia",
"Kotlin",
"Latex",
"Lisp",
"Lua",
"Matlab",
"MoonScript",
"Nim",
"OCaml",
"ObjectiveC",
"Octave",
"PHP",
"Pascal",
"Perl",
"Prolog",
"Python",
"Racket",
"Ruby",
"Rust",
"SML",
"SQL",
"Scala",
"Scheme",
"Swift",
"Tikz",
"TypeScript",
"unknown",
"VisualBasic",
"XML",
"YAML"
],
"title": "CodeLanguageLabel",
"type": "string"
},
"CodeMetaField": {
"additionalProperties": true,
"description": "Code representation for the respective item.",
"properties": {
"confidence": {
"anyOf": [
{
"maximum": 1,
"minimum": 0,
"type": "number"
},
{
"type": "null"
}
],
"default": null,
"description": "The confidence of the prediction.",
"examples": [
0.9,
0.42
],
"title": "Confidence"
},
"created_by": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"default": null,
"description": "The origin of the prediction.",
"examples": [
"ibm-granite/granite-docling-258M"
],
"title": "Created By"
},
"text": {
"title": "Text",
"type": "string"
},
"language": {
"anyOf": [
{
"$ref": "#/$defs/CodeLanguageLabel"
},
{
"type": "null"
}
],
"default": null
}
},
"required": [
"text"
],
"title": "CodeMetaField",
"type": "object"
},
"ContentLayer": {
"description": "ContentLayer.",
"enum": [
"body",
"furniture",
"background",
"invisible",
"notes"
],
"title": "ContentLayer",
"type": "string"
},
"CoordOrigin": {
"description": "CoordOrigin.",
"enum": [
"TOPLEFT",
"BOTTOMLEFT"
],
"title": "CoordOrigin",
"type": "string"
},
"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"
},
"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"
},
"EntitiesMetaField": {
"additionalProperties": true,
"description": "Container for extracted entity mentions.",
"properties": {
"mentions": {
"items": {
"$ref": "#/$defs/EntityMention"
},
"minItems": 1,
"title": "Mentions",
"type": "array"
}
},
"required": [
"mentions"
],
"title": "EntitiesMetaField",
"type": "object"
},
"EntityMention": {
"additionalProperties": true,
"description": "Entity mention extracted from text.",
"properties": {
"confidence": {
"anyOf": [
{
"maximum": 1,
"minimum": 0,
"type": "number"
},
{
"type": "null"
}
],
"default": null,
"description": "The confidence of the prediction.",
"examples": [
0.9,
0.42
],
"title": "Confidence"
},
"created_by": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"default": null,
"description": "The origin of the prediction.",
"examples": [
"ibm-granite/granite-docling-258M"
],
"title": "Created By"
},
"text": {
"description": "Normalized text of the entity mention.",
"title": "Text",
"type": "string"
},
"orig": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"default": null,
"description": "Exact source text extracted from the original charspan, analogous to TextItem.orig. This may differ from 'text' when the mention has been normalized.",
"title": "Orig"
},
"label": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"default": null,
"description": "Entity type or category.",
"title": "Label"
},
"charspan": {
"anyOf": [
{
"description": "Character span (0-indexed)",
"maxItems": 2,
"minItems": 2,
"prefixItems": [
{
"type": "integer"
},
{
"type": "integer"
}
],
"type": "array"
},
{
"type": "null"
}
],
"default": null,
"description": "Character span (0-indexed) of the entity mention in the source text.",
"title": "Charspan"
}
},
"required": [
"text"
],
"title": "EntityMention",
"type": "object"
},
"FieldHeadingItem": {
"additionalProperties": false,
"properties": {
"self_ref": {
"pattern": "^#(?:/([\\w-]+)(?:/(\\d+))?)?$",
"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": "field_heading",
"default": "field_heading",
"title": "Label",
"type": "string"
},
"prov": {
"default": [],
"items": {
"$ref": "#/$defs/ProvenanceItem"
},
"title": "Prov",
"type": "array"
},
"source": {
"default": [],
"description": "The provenance of this document item. Currently, it is only used for media track provenance.",
"items": {
"discriminator": {
"mapping": {
"track": "#/$defs/TrackSource"
},
"propertyName": "kind"
},
"oneOf": [
{
"$ref": "#/$defs/TrackSource"
}
]
},
"title": "Source",
"type": "array"
},
"comments": {
"default": [],
"items": {
"$ref": "#/$defs/FineRef"
},
"title": "Comments",
"type": "array"
},
"orig": {
"title": "Orig",
"type": "string"
},
"text": {
"title": "Text",
"type": "string"
},
"formatting": {
"anyOf": [
{
"$ref": "#/$defs/Formatting"
},
{
"type": "null"
}
],
"default": null
},
"hyperlink": {
"anyOf": [
{
"format": "uri",
"minLength": 1,
"type": "string"
},
{
"format": "path",
"type": "string"
},
{
"type": "null"
}
],
"default": null,
"title": "Hyperlink"
},
"level": {
"default": 1,
"maximum": 100,
"minimum": 1,
"title": "Level",
"type": "integer"
}
},
"required": [
"self_ref",
"orig",
"text"
],
"title": "FieldHeadingItem",
"type": "object"
},
"FieldItem": {
"additionalProperties": false,
"properties": {
"self_ref": {
"pattern": "^#(?:/([\\w-]+)(?:/(\\d+))?)?$",
"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": "field_item",
"default": "field_item",
"title": "Label",
"type": "string"
},
"prov": {
"default": [],
"items": {
"$ref": "#/$defs/ProvenanceItem"
},
"title": "Prov",
"type": "array"
},
"source": {
"default": [],
"description": "The provenance of this document item. Currently, it is only used for media track provenance.",
"items": {
"discriminator": {
"mapping": {
"track": "#/$defs/TrackSource"
},
"propertyName": "kind"
},
"oneOf": [
{
"$ref": "#/$defs/TrackSource"
}
]
},
"title": "Source",
"type": "array"
},
"comments": {
"default": [],
"items": {
"$ref": "#/$defs/FineRef"
},
"title": "Comments",
"type": "array"
}
},
"required": [
"self_ref"
],
"title": "FieldItem",
"type": "object"
},
"FieldRegionItem": {
"additionalProperties": false,
"properties": {
"self_ref": {
"pattern": "^#(?:/([\\w-]+)(?:/(\\d+))?)?$",
"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": "field_region",
"default": "field_region",
"title": "Label",
"type": "string"
},
"prov": {
"default": [],
"items": {
"$ref": "#/$defs/ProvenanceItem"
},
"title": "Prov",
"type": "array"
},
"source": {
"default": [],
"description": "The provenance of this document item. Currently, it is only used for media track provenance.",
"items": {
"discriminator": {
"mapping": {
"track": "#/$defs/TrackSource"
},
"propertyName": "kind"
},
"oneOf": [
{
"$ref": "#/$defs/TrackSource"
}
]
},
"title": "Source",
"type": "array"
},
"comments": {
"default": [],
"items": {
"$ref": "#/$defs/FineRef"
},
"title": "Comments",
"type": "array"
}
},
"required": [
"self_ref"
],
"title": "FieldRegionItem",
"type": "object"
},
"FieldValueItem": {
"additionalProperties": false,
"properties": {
"self_ref": {
"pattern": "^#(?:/([\\w-]+)(?:/(\\d+))?)?$",
"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": "field_value",
"default": "field_value",
"title": "Label",
"type": "string"
},
"prov": {
"default": [],
"items": {
"$ref": "#/$defs/ProvenanceItem"
},
"title": "Prov",
"type": "array"
},
"source": {
"default": [],
"description": "The provenance of this document item. Currently, it is only used for media track provenance.",
"items": {
"discriminator": {
"mapping": {
"track": "#/$defs/TrackSource"
},
"propertyName": "kind"
},
"oneOf": [
{
"$ref": "#/$defs/TrackSource"
}
]
},
"title": "Source",
"type": "array"
},
"comments": {
"default": [],
"items": {
"$ref": "#/$defs/FineRef"
},
"title": "Comments",
"type": "array"
},
"orig": {
"title": "Orig",
"type": "string"
},
"text": {
"title": "Text",
"type": "string"
},
"formatting": {
"anyOf": [
{
"$ref": "#/$defs/Formatting"
},
{
"type": "null"
}
],
"default": null
},
"hyperlink": {
"anyOf": [
{
"format": "uri",
"minLength": 1,
"type": "string"
},
{
"format": "path",
"type": "string"
},
{
"type": "null"
}
],
"default": null,
"title": "Hyperlink"
},
"kind": {
"default": "read_only",
"enum": [
"read_only",
"fillable"
],
"title": "Kind",
"type": "string"
}
},
"required": [
"self_ref",
"orig",
"text"
],
"title": "FieldValueItem",
"type": "object"
},
"FineRef": {
"description": "Fine-granular reference item that can capture span range info.",
"properties": {
"$ref": {
"pattern": "^#(?:/([\\w-]+)(?:/(\\d+))?)?$",
"title": "$Ref",
"type": "string"
},
"range": {
"anyOf": [
{
"maxItems": 2,
"minItems": 2,
"prefixItems": [
{
"type": "integer"
},
{
"type": "integer"
}
],
"type": "array"
},
{
"type": "null"
}
],
"default": null,
"title": "Range"
}
},
"required": [
"$ref"
],
"title": "FineRef",
"type": "object"
},
"FloatingMeta": {
"additionalProperties": true,
"description": "Metadata model for floating.",
"properties": {
"summary": {
"anyOf": [
{
"$ref": "#/$defs/SummaryMetaField"
},
{
"type": "null"
}
],
"default": null
},
"language": {
"anyOf": [
{
"$ref": "#/$defs/LanguageMetaField"
},
{
"type": "null"
}
],
"default": null
},
"entities": {
"anyOf": [
{
"$ref": "#/$defs/EntitiesMetaField"
},
{
"type": "null"
}
],
"default": null
},
"description": {
"anyOf": [
{
"$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"
},
"source": {
"default": [],
"description": "The provenance of this document item. Currently, it is only used for media track provenance.",
"items": {
"discriminator": {
"mapping": {
"track": "#/$defs/TrackSource"
},
"propertyName": "kind"
},
"oneOf": [
{
"$ref": "#/$defs/TrackSource"
}
]
},
"title": "Source",
"type": "array"
},
"comments": {
"default": [],
"items": {
"$ref": "#/$defs/FineRef"
},
"title": "Comments",
"type": "array"
},
"captions": {
"default": [],
"items": {
"$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"
},
"source": {
"default": [],
"description": "The provenance of this document item. Currently, it is only used for media track provenance.",
"items": {
"discriminator": {
"mapping": {
"track": "#/$defs/TrackSource"
},
"propertyName": "kind"
},
"oneOf": [
{
"$ref": "#/$defs/TrackSource"
}
]
},
"title": "Source",
"type": "array"
},
"comments": {
"default": [],
"items": {
"$ref": "#/$defs/FineRef"
},
"title": "Comments",
"type": "array"
},
"orig": {
"title": "Orig",
"type": "string"
},
"text": {
"title": "Text",
"type": "string"
},
"formatting": {
"anyOf": [
{
"$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"
},
"HumanLanguageLabel": {
"description": "Two-letter human language primary subtags using BCP-47 values.",
"enum": [
"aa",
"ab",
"ae",
"af",
"ak",
"am",
"an",
"ar",
"as",
"av",
"ay",
"az",
"ba",
"be",
"bg",
"bh",
"bi",
"bm",
"bn",
"bo",
"br",
"bs",
"ca",
"ce",
"ch",
"co",
"cr",
"cs",
"cu",
"cv",
"cy",
"da",
"de",
"dv",
"dz",
"ee",
"el",
"en",
"eo",
"es",
"et",
"eu",
"fa",
"ff",
"fi",
"fj",
"fo",
"fr",
"fy",
"ga",
"gd",
"gl",
"gn",
"gu",
"gv",
"ha",
"he",
"hi",
"ho",
"hr",
"ht",
"hu",
"hy",
"hz",
"ia",
"id",
"ie",
"ig",
"ii",
"ik",
"io",
"is",
"it",
"iu",
"ja",
"jv",
"ka",
"kg",
"ki",
"kj",
"kk",
"kl",
"km",
"kn",
"ko",
"kr",
"ks",
"ku",
"kv",
"kw",
"ky",
"la",
"lb",
"lg",
"li",
"ln",
"lo",
"lt",
"lu",
"lv",
"mg",
"mh",
"mi",
"mk",
"ml",
"mn",
"mr",
"ms",
"mt",
"my",
"na",
"nb",
"nd",
"ne",
"ng",
"nl",
"nn",
"no",
"nr",
"nv",
"ny",
"oc",
"oj",
"om",
"or",
"os",
"pa",
"pi",
"pl",
"ps",
"pt",
"qu",
"rm",
"rn",
"ro",
"ru",
"rw",
"sa",
"sc",
"sd",
"se",
"sg",
"sh",
"si",
"sk",
"sl",
"sm",
"sn",
"so",
"sq",
"sr",
"ss",
"st",
"su",
"sv",
"sw",
"ta",
"te",
"tg",
"th",
"ti",
"tk",
"tl",
"tn",
"to",
"tr",
"ts",
"tt",
"tw",
"ty",
"ug",
"uk",
"ur",
"uz",
"ve",
"vi",
"vo",
"wa",
"wo",
"xh",
"yi",
"yo",
"za",
"zh",
"zu"
],
"title": "HumanLanguageLabel",
"type": "string"
},
"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": "#/$defs/BaseMeta"
},
{
"type": "null"
}
],
"default": null
},
"name": {
"default": "group",
"title": "Name",
"type": "string"
},
"label": {
"const": "inline",
"default": "inline",
"title": "Label",
"type": "string"
}
},
"required": [
"self_ref"
],
"title": "InlineGroup",
"type": "object"
},
"KeyValueItem": {
"additionalProperties": false,
"description": "KeyValueItem.",
"properties": {
"self_ref": {
"pattern": "^#(?:/([\\w-]+)(?:/(\\d+))?)?$",
"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"
},
"source": {
"default": [],
"description": "The provenance of this document item. Currently, it is only used for media track provenance.",
"items": {
"discriminator": {
"mapping": {
"track": "#/$defs/TrackSource"
},
"propertyName": "kind"
},
"oneOf": [
{
"$ref": "#/$defs/TrackSource"
}
]
},
"title": "Source",
"type": "array"
},
"comments": {
"default": [],
"items": {
"$ref": "#/$defs/FineRef"
},
"title": "Comments",
"type": "array"
},
"captions": {
"default": [],
"items": {
"$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": "#/$defs/GraphData"
}
},
"required": [
"self_ref",
"graph"
],
"title": "KeyValueItem",
"type": "object"
},
"LanguageMetaField": {
"additionalProperties": true,
"description": "Detected human language.",
"properties": {
"confidence": {
"anyOf": [
{
"maximum": 1,
"minimum": 0,
"type": "number"
},
{
"type": "null"
}
],
"default": null,
"description": "The confidence of the prediction.",
"examples": [
0.9,
0.42
],
"title": "Confidence"
},
"created_by": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"default": null,
"description": "The origin of the prediction.",
"examples": [
"ibm-granite/granite-docling-258M"
],
"title": "Created By"
},
"code": {
"$ref": "#/$defs/HumanLanguageLabel"
}
},
"required": [
"code"
],
"title": "LanguageMetaField",
"type": "object"
},
"ListGroup": {
"additionalProperties": false,
"description": "ListGroup.",
"properties": {
"self_ref": {
"pattern": "^#(?:/([\\w-]+)(?:/(\\d+))?)?$",
"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": "#/$defs/ProvenanceItem"
},
"title": "Prov",
"type": "array"
},
"source": {
"default": [],
"description": "The provenance of this document item. Currently, it is only used for media track provenance.",
"items": {
"discriminator": {
"mapping": {
"track": "#/$defs/TrackSource"
},
"propertyName": "kind"
},
"oneOf": [
{
"$ref": "#/$defs/TrackSource"
}
]
},
"title": "Source",
"type": "array"
},
"comments": {
"default": [],
"items": {
"$ref": "#/$defs/FineRef"
},
"title": "Comments",
"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"
},
"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"
},
"Orientation": {
"description": "Counter-clockwise rotation of a table on the page, in degrees.\n\nFollows the convention used by PIL/Pillow's ``Image.rotate``: positive\nangles rotate the table counter-clockwise. ``ROT_0`` / ``ROT_180`` keep\nrows running horizontally on the page; ``ROT_90`` / ``ROT_270`` turn\nrows into vertical stripes.",
"enum": [
"rot_0",
"rot_90",
"rot_180",
"rot_270"
],
"title": "Orientation",
"type": "string"
},
"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"
},
"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": "#/$defs/ProvenanceItem"
},
"title": "Prov",
"type": "array"
},
"source": {
"default": [],
"description": "The provenance of this document item. Currently, it is only used for media track provenance.",
"items": {
"discriminator": {
"mapping": {
"track": "#/$defs/TrackSource"
},
"propertyName": "kind"
},
"oneOf": [
{
"$ref": "#/$defs/TrackSource"
}
]
},
"title": "Source",
"type": "array"
},
"comments": {
"default": [],
"items": {
"$ref": "#/$defs/FineRef"
},
"title": "Comments",
"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
},
"language": {
"anyOf": [
{
"$ref": "#/$defs/LanguageMetaField"
},
{
"type": "null"
}
],
"default": null
},
"entities": {
"anyOf": [
{
"$ref": "#/$defs/EntitiesMetaField"
},
{
"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
},
"code": {
"anyOf": [
{
"$ref": "#/$defs/CodeMetaField"
},
{
"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"
},
"ProvenanceItem": {
"description": "Provenance information for elements extracted from a textual document.\n\nA `ProvenanceItem` object acts as a lightweight pointer back into the original\ndocument for an extracted element. It applies to documents with an explicity\nor implicit layout, such as PDF, HTML, docx, or pptx.",
"properties": {
"page_no": {
"description": "Page number",
"title": "Page No",
"type": "integer"
},
"bbox": {
"$ref": "#/$defs/BoundingBox",
"description": "Bounding box"
},
"charspan": {
"description": "Character span (0-indexed)",
"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": "#/$defs/ProvenanceItem"
},
"title": "Prov",
"type": "array"
},
"source": {
"default": [],
"description": "The provenance of this document item. Currently, it is only used for media track provenance.",
"items": {
"discriminator": {
"mapping": {
"track": "#/$defs/TrackSource"
},
"propertyName": "kind"
},
"oneOf": [
{
"$ref": "#/$defs/TrackSource"
}
]
},
"title": "Source",
"type": "array"
},
"comments": {
"default": [],
"items": {
"$ref": "#/$defs/FineRef"
},
"title": "Comments",
"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"
},
"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"
},
"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"
},
"orientation": {
"$ref": "#/$defs/Orientation",
"default": "rot_0"
}
},
"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": "#/$defs/ProvenanceItem"
},
"title": "Prov",
"type": "array"
},
"source": {
"default": [],
"description": "The provenance of this document item. Currently, it is only used for media track provenance.",
"items": {
"discriminator": {
"mapping": {
"track": "#/$defs/TrackSource"
},
"propertyName": "kind"
},
"oneOf": [
{
"$ref": "#/$defs/TrackSource"
}
]
},
"title": "Source",
"type": "array"
},
"comments": {
"default": [],
"items": {
"$ref": "#/$defs/FineRef"
},
"title": "Comments",
"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"
},
"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"
},
"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": "#/$defs/BaseMeta"
},
{
"type": "null"
}
],
"default": null
},
"label": {
"enum": [
"caption",
"checkbox_selected",
"checkbox_unselected",
"footnote",
"page_footer",
"page_header",
"paragraph",
"reference",
"text",
"empty_value",
"field_key",
"field_hint",
"marker",
"handwritten_text"
],
"title": "Label",
"type": "string"
},
"prov": {
"default": [],
"items": {
"$ref": "#/$defs/ProvenanceItem"
},
"title": "Prov",
"type": "array"
},
"source": {
"default": [],
"description": "The provenance of this document item. Currently, it is only used for media track provenance.",
"items": {
"discriminator": {
"mapping": {
"track": "#/$defs/TrackSource"
},
"propertyName": "kind"
},
"oneOf": [
{
"$ref": "#/$defs/TrackSource"
}
]
},
"title": "Source",
"type": "array"
},
"comments": {
"default": [],
"items": {
"$ref": "#/$defs/FineRef"
},
"title": "Comments",
"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": "#/$defs/ProvenanceItem"
},
"title": "Prov",
"type": "array"
},
"source": {
"default": [],
"description": "The provenance of this document item. Currently, it is only used for media track provenance.",
"items": {
"discriminator": {
"mapping": {
"track": "#/$defs/TrackSource"
},
"propertyName": "kind"
},
"oneOf": [
{
"$ref": "#/$defs/TrackSource"
}
]
},
"title": "Source",
"type": "array"
},
"comments": {
"default": [],
"items": {
"$ref": "#/$defs/FineRef"
},
"title": "Comments",
"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"
},
"TrackSource": {
"description": "Source metadata for a cue extracted from a media track.\n\nA `TrackSource` instance identifies a cue in a media track (audio, video, subtitles, screen-recording captions,\netc.). A *cue* here refers to any discrete segment that was pulled out of the original asset, e.g., a subtitle\nblock, an audio clip, or a timed marker in a screen-recording.",
"properties": {
"kind": {
"const": "track",
"default": "track",
"description": "Identifies this type of source.",
"title": "Kind",
"type": "string"
},
"start_time": {
"description": "Start time offset of the track cue in seconds",
"examples": [
11.0,
6.5,
5370.0
],
"title": "Start Time",
"type": "number"
},
"end_time": {
"description": "End time offset of the track cue in seconds",
"examples": [
12.0,
8.2,
5370.1
],
"title": "End Time",
"type": "number"
},
"identifier": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"default": null,
"description": "An identifier of the cue",
"examples": [
"test",
"123",
"b72d946"
],
"title": "Identifier"
},
"voice": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"default": null,
"description": "The name of the voice in this track (the speaker)",
"examples": [
"John",
"Mary",
"Speaker 1"
],
"title": "Voice"
}
},
"required": [
"start_time",
"end_time"
],
"title": "TrackSource",
"type": "object"
}
},
"description": "DoclingDocument.",
"properties": {
"schema_name": {
"const": "DoclingDocument",
"default": "DoclingDocument",
"title": "Schema Name",
"type": "string"
},
"version": {
"default": "1.10.0",
"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": "#/$defs/FieldHeadingItem"
},
{
"$ref": "#/$defs/FieldValueItem"
},
{
"$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": "#/$defs/FormItem"
},
"title": "Form Items",
"type": "array"
},
"field_regions": {
"default": [],
"items": {
"$ref": "#/$defs/FieldRegionItem"
},
"title": "Field Regions",
"type": "array"
},
"field_items": {
"default": [],
"items": {
"$ref": "#/$defs/FieldItem"
},
"title": "Field Items",
"type": "array"
},
"pages": {
"additionalProperties": {
"$ref": "#/$defs/PageItem"
},
"default": {},
"title": "Pages",
"type": "object"
}
},
"required": [
"name"
],
"title": "DoclingDocument",
"type": "object"
}
Fields:
-
schema_name(Literal['DoclingDocument']) -
version(str) -
name(str) -
origin(Optional[DocumentOrigin]) -
furniture(GroupItem) -
body(GroupItem) -
groups(list[Union[ListGroup, InlineGroup, GroupItem]]) -
texts(list[Union[TitleItem, SectionHeaderItem, ListItem, CodeItem, FormulaItem, FieldHeadingItem, FieldValueItem, TextItem]]) -
pictures(list[PictureItem]) -
tables(list[TableItem]) -
key_value_items(list[KeyValueItem]) -
form_items(list[FormItem]) -
field_regions(list[FieldRegionItem]) -
field_items(list[FieldItem]) -
pages(dict[int, PageItem])
Validators:
-
transform_to_content_layer -
check_version_is_compatible→version -
_validate_unique_refs -
validate_document -
validate_misplaced_list_items
field_items: list[FieldItem] = []
field_regions: list[FieldRegionItem] = []
form_items: list[FormItem] = []
name: str
schema_name: Literal['DoclingDocument'] = 'DoclingDocument'
texts: list[
Union[
TitleItem,
SectionHeaderItem,
ListItem,
CodeItem,
FormulaItem,
FieldHeadingItem,
FieldValueItem,
TextItem,
]
] = []
version: str = CURRENT_VERSION
add_code(
text: str,
code_language: Optional[CodeLanguageLabel] = None,
orig: Optional[str] = None,
caption: Optional[Union[TextItem, RefItem]] = None,
prov: Optional[ProvenanceItem] = None,
parent: Optional[NodeItem] = None,
content_layer: Optional[ContentLayer] = None,
formatting: Optional[Formatting] = None,
hyperlink: Optional[Union[AnyUrl, Path]] = None,
)
add_code.
:param text: str: :param code_language: Optional[CodeLanguageLabel]: (Default value = None) :param orig: Optional[str]: (Default value = None) :param caption: Optional[Union[TextItem: :param RefItem]]: (Default value = None) :param prov: Optional[ProvenanceItem]: (Default value = None) :param parent: Optional[NodeItem]: (Default value = None)
add_comment(
*,
text: str,
prov: Optional[ProvenanceItem] = None,
parent: Optional[NodeItem] = None,
targets: Optional[
list[
Union[DocItem, tuple[DocItem, tuple[int, int]]]
]
] = None,
)
Adds a comment to the document, assigning it to the given targets.
:param text: str: :param prov: Optional[ProvenanceItem]: (Default value = None) :param parent: Optional[NodeItem]: (Default value = None) :param targets: list[Union[DocItem, tuple[DocItem, tuple[int, int]]]]: (Default value = None) Each list element can be either a single DocItem or a tuple of a DocItem and a span range (start_inclusive, end_exclusive).
add_document(
doc: DoclingDocument, parent: Optional[NodeItem] = None
) -> None
Adds the content from the body of a DoclingDocument to this document under a specific parent.
:param doc: DoclingDocument: The document whose content will be added :param parent: Optional[NodeItem]: The parent NodeItem under which new items are added (Default value = None)
:returns: None
add_field_heading(
text: str,
orig: Optional[str] = None,
level: LevelNumber = 1,
prov: Optional[ProvenanceItem] = None,
parent: Optional[NodeItem] = None,
content_layer: Optional[ContentLayer] = None,
formatting: Optional[Formatting] = None,
hyperlink: Optional[Union[AnyUrl, Path]] = None,
)
add_kv_heading.
:param label: DocItemLabel: :param text: str: :param orig: Optional[str]: (Default value = None) :param level: LevelNumber: (Default value = 1) :param prov: Optional[ProvenanceItem]: (Default value = None) :param parent: Optional[NodeItem]: (Default value = None) :param content_layer: Optional[ContentLayer]: (Default value = None) :param formatting: Optional[Formatting]: (Default value = None) :param hyperlink: Optional[Union[AnyUrl, Path]]: (Default value = None)
add_field_hint(
text: str,
orig: Optional[str] = None,
prov: Optional[ProvenanceItem] = None,
parent: Optional[NodeItem] = None,
content_layer: Optional[ContentLayer] = None,
formatting: Optional[Formatting] = None,
hyperlink: Optional[Union[AnyUrl, Path]] = None,
)
add_field_hint.
:param text: str: :param orig: Optional[str]: (Default value = None) :param prov: Optional[ProvenanceItem]: (Default value = None) :param parent: Optional[NodeItem]: (Default value = None) :param content_layer: Optional[ContentLayer]: (Default value = None) :param formatting: Optional[Formatting]: (Default value = None) :param hyperlink: Optional[Union[AnyUrl, Path]]: (Default value = None)
add_field_item(
prov: Optional[ProvenanceItem] = None,
parent: Optional[NodeItem] = None,
content_layer: Optional[ContentLayer] = None,
) -> FieldItem
add_kv_entry.
add_field_key(
text: str,
orig: Optional[str] = None,
prov: Optional[ProvenanceItem] = None,
parent: Optional[NodeItem] = None,
content_layer: Optional[ContentLayer] = None,
formatting: Optional[Formatting] = None,
hyperlink: Optional[Union[AnyUrl, Path]] = None,
)
add_field_key.
:param label: DocItemLabel: :param text: str: :param orig: Optional[str]: (Default value = None) :param prov: Optional[ProvenanceItem]: (Default value = None) :param parent: Optional[NodeItem]: (Default value = None) :param content_layer: Optional[ContentLayer]: (Default value = None) :param formatting: Optional[Formatting]: (Default value = None) :param hyperlink: Optional[Union[AnyUrl, Path]]: (Default value = None)
add_field_region(
prov: Optional[ProvenanceItem] = None,
parent: Optional[NodeItem] = None,
) -> FieldRegionItem
add_field_region.
:param prov: Optional[ProvenanceItem]: (Default value = None) :param parent: Optional[NodeItem]: (Default value = None)
add_field_value(
text: str,
orig: Optional[str] = None,
prov: Optional[ProvenanceItem] = None,
parent: Optional[NodeItem] = None,
content_layer: Optional[ContentLayer] = None,
formatting: Optional[Formatting] = None,
hyperlink: Optional[Union[AnyUrl, Path]] = None,
kind: Optional[
Literal["read_only", "fillable"]
] = "read_only",
)
add_field_value.
:param label: DocItemLabel: :param text: str: :param orig: Optional[str]: (Default value = None) :param level: LevelNumber: (Default value = 1) :param prov: Optional[ProvenanceItem]: (Default value = None) :param parent: Optional[NodeItem]: (Default value = None) :param content_layer: Optional[ContentLayer]: (Default value = None) :param formatting: Optional[Formatting]: (Default value = None) :param hyperlink: Optional[Union[AnyUrl, Path]]: (Default value = None) :param kind: Optional[typing.Literal["read_only", "fillable", "fillable_with_hint"]]: (Default value = "read_only")
add_form(
graph: GraphData,
prov: Optional[ProvenanceItem] = None,
parent: Optional[NodeItem] = None,
)
add_form.
:param graph: GraphData: :param prov: Optional[ProvenanceItem]: (Default value = None) :param parent: Optional[NodeItem]: (Default value = None)
add_formula(
text: str,
orig: Optional[str] = None,
prov: Optional[ProvenanceItem] = None,
parent: Optional[NodeItem] = None,
content_layer: Optional[ContentLayer] = None,
formatting: Optional[Formatting] = None,
hyperlink: Optional[Union[AnyUrl, Path]] = None,
)
add_formula.
:param text: str: :param orig: Optional[str]: (Default value = None) :param level: LevelNumber: (Default value = 1) :param prov: Optional[ProvenanceItem]: (Default value = None) :param parent: Optional[NodeItem]: (Default value = None)
add_group(
label: Optional[GroupLabel] = None,
name: Optional[str] = None,
parent: Optional[NodeItem] = None,
content_layer: Optional[ContentLayer] = None,
) -> GroupItem
add_group.
:param label: Optional[GroupLabel]: (Default value = None) :param name: Optional[str]: (Default value = None) :param parent: Optional[NodeItem]: (Default value = None)
add_heading(
text: str,
orig: Optional[str] = None,
level: LevelNumber = 1,
prov: Optional[ProvenanceItem] = None,
parent: Optional[NodeItem] = None,
content_layer: Optional[ContentLayer] = None,
formatting: Optional[Formatting] = None,
hyperlink: Optional[Union[AnyUrl, Path]] = None,
)
add_heading.
:param label: DocItemLabel: :param text: str: :param orig: Optional[str]: (Default value = None) :param level: LevelNumber: (Default value = 1) :param prov: Optional[ProvenanceItem]: (Default value = None) :param parent: Optional[NodeItem]: (Default value = None)
add_inline_group(
name: Optional[str] = None,
parent: Optional[NodeItem] = None,
content_layer: Optional[ContentLayer] = None,
) -> InlineGroup
add_inline_group.
add_key_values(
graph: GraphData,
prov: Optional[ProvenanceItem] = None,
parent: Optional[NodeItem] = None,
)
add_key_values.
:param graph: GraphData: :param prov: Optional[ProvenanceItem]: (Default value = None) :param parent: Optional[NodeItem]: (Default value = None)
add_list_group(
name: Optional[str] = None,
parent: Optional[NodeItem] = None,
content_layer: Optional[ContentLayer] = None,
) -> ListGroup
add_list_group.
add_list_item(
text: str,
enumerated: bool = False,
marker: Optional[str] = None,
orig: Optional[str] = None,
prov: Optional[ProvenanceItem] = None,
parent: Optional[NodeItem] = None,
content_layer: Optional[ContentLayer] = None,
formatting: Optional[Formatting] = None,
hyperlink: Optional[Union[AnyUrl, Path]] = None,
)
add_list_item.
:param label: str: :param text: str: :param orig: Optional[str]: (Default value = None) :param prov: Optional[ProvenanceItem]: (Default value = None) :param parent: Optional[NodeItem]: (Default value = None)
add_marker(
text: str,
orig: Optional[str] = None,
prov: Optional[ProvenanceItem] = None,
parent: Optional[NodeItem] = None,
content_layer: Optional[ContentLayer] = None,
formatting: Optional[Formatting] = None,
hyperlink: Optional[Union[AnyUrl, Path]] = None,
)
add_marker.
:param text: str: :param orig: Optional[str]: (Default value = None) :param prov: Optional[ProvenanceItem]: (Default value = None) :param parent: Optional[NodeItem]: (Default value = None) :param content_layer: Optional[ContentLayer]: (Default value = None) :param formatting: Optional[Formatting]: (Default value = None) :param hyperlink: Optional[Union[AnyUrl, Path]]: (Default value = None)
add_node_items(
node_items: list[NodeItem],
doc: DoclingDocument,
parent: Optional[NodeItem] = None,
) -> None
Adds multiple NodeItems and their children under a parent in this document.
:param node_items: list[NodeItem]: The NodeItems to be added :param doc: DoclingDocument: The document to which the NodeItems and their children belong :param parent: Optional[NodeItem]: The parent NodeItem under which new items are added (Default value = None)
:returns: None
add_ordered_list(
name: Optional[str] = None,
parent: Optional[NodeItem] = None,
content_layer: Optional[ContentLayer] = None,
) -> GroupItem
add_ordered_list.
add_page.
:param page_no: int: :param size: Size:
add_picture(
annotations: Optional[list[PictureDataType]] = None,
image: Optional[ImageRef] = None,
caption: Optional[Union[TextItem, RefItem]] = None,
prov: Optional[ProvenanceItem] = None,
parent: Optional[NodeItem] = None,
content_layer: Optional[ContentLayer] = None,
)
add_picture.
:param data: Optional[list[PictureData]]: (Default value = None) :param caption: Optional[Union[TextItem: :param RefItem]]: (Default value = None) :param prov: Optional[ProvenanceItem]: (Default value = None) :param parent: Optional[NodeItem]: (Default value = None)
add_table(
data: TableData,
caption: Optional[Union[TextItem, RefItem]] = None,
prov: Optional[ProvenanceItem] = None,
parent: Optional[NodeItem] = None,
label: DocItemLabel = TABLE,
content_layer: Optional[ContentLayer] = None,
annotations: Optional[list[TableAnnotationType]] = None,
)
add_table.
:param data: TableData: :param caption: Optional[Union[TextItem, RefItem]]: (Default value = None) :param prov: Optional[ProvenanceItem]: (Default value = None) :param parent: Optional[NodeItem]: (Default value = None) :param label: DocItemLabel: (Default value = DocItemLabel.TABLE)
Add a table cell to the table.
add_text(
label: DocItemLabel,
text: str,
orig: Optional[str] = None,
prov: Optional[ProvenanceItem] = None,
parent: Optional[NodeItem] = None,
content_layer: Optional[ContentLayer] = None,
formatting: Optional[Formatting] = None,
hyperlink: Optional[Union[AnyUrl, Path]] = None,
*,
source: Optional[SourceType] = None,
**kwargs: Any,
)
add_text.
:param label: str: :param text: str: :param orig: Optional[str]: (Default value = None) :param prov: Optional[ProvenanceItem]: (Default value = None) :param parent: Optional[NodeItem]: (Default value = None)
add_title(
text: str,
orig: Optional[str] = None,
prov: Optional[ProvenanceItem] = None,
parent: Optional[NodeItem] = None,
content_layer: Optional[ContentLayer] = None,
formatting: Optional[Formatting] = None,
hyperlink: Optional[Union[AnyUrl, Path]] = None,
)
add_title.
:param text: str: :param orig: Optional[str]: (Default value = None) :param level: LevelNumber: (Default value = 1) :param prov: Optional[ProvenanceItem]: (Default value = None) :param parent: Optional[NodeItem]: (Default value = None)
add_unordered_list(
name: Optional[str] = None,
parent: Optional[NodeItem] = None,
content_layer: Optional[ContentLayer] = None,
) -> GroupItem
add_unordered_list.
Adds an item.
check_version_is_compatible(v: str) -> str
Check if this document version is compatible with SDK schema version.
concatenate(
docs: Sequence[DoclingDocument],
) -> DoclingDocument
Concatenate multiple documents into a single document.
delete_items(*, node_items: list[NodeItem]) -> None
Deletes an item, given its instance or ref, and any children it has.
delete_items_range(
*,
start: NodeItem,
end: NodeItem,
start_inclusive: bool = True,
end_inclusive: bool = True,
) -> None
Deletes all NodeItems and their children in the range from the start NodeItem to the end NodeItem.
:param start: NodeItem: The starting NodeItem of the range :param end: NodeItem: The ending NodeItem of the range :param start_inclusive: bool: (Default value = True): If True, the start NodeItem will also be deleted :param end_inclusive: bool: (Default value = True): If True, the end NodeItem will also be deleted
:returns: None
export_to_dict(
mode: str = "json",
by_alias: bool = True,
exclude_none: bool = True,
coord_precision: Optional[int] = None,
confid_precision: Optional[int] = None,
) -> dict[str, Any]
Export to dict.
export_to_doclang() -> str
Export to Doclang.
export_to_doctags(
delim: str = "",
from_element: int = 0,
to_element: int = maxsize,
labels: Optional[set[DocItemLabel]] = None,
xsize: int = 500,
ysize: int = 500,
add_location: bool = True,
add_content: bool = True,
add_page_index: bool = True,
add_table_cell_location: bool = False,
add_table_cell_text: bool = True,
minified: bool = False,
pages: Optional[set[int]] = None,
) -> str
Exports the document content to a DocumentToken format.
Operates on a slice of the document's body as defined through arguments from_element and to_element; defaulting to the whole main_text.
:param delim: str: (Default value = "") Deprecated :param from_element: int: (Default value = 0) :param to_element: Optional[int]: (Default value = None) :param labels: set[DocItemLabel] :param xsize: int: (Default value = 500) :param ysize: int: (Default value = 500) :param add_location: bool: (Default value = True) :param add_content: bool: (Default value = True) :param add_page_index: bool: (Default value = True) :param # table specific flagsadd_table_cell_location: bool :param add_table_cell_text: bool: (Default value = True) :param minified: bool: (Default value = False) :param pages: set[int]: (Default value = None) :returns: The content of the document formatted as a DocTags string. :rtype: str
export_to_document_tokens(*args, **kwargs)
Export to DocTags format.
export_to_element_tree() -> str
Export_to_element_tree.
export_to_html(
from_element: int = 0,
to_element: int = maxsize,
labels: Optional[set[DocItemLabel]] = None,
enable_chart_tables: bool = True,
image_mode: ImageRefMode = PLACEHOLDER,
formula_to_mathml: bool = True,
page_no: Optional[int] = None,
html_lang: str = "en",
html_head: str = "null",
included_content_layers: Optional[
set[ContentLayer]
] = None,
split_page_view: bool = False,
include_annotations: bool = True,
) -> str
Serialize to HTML.
export_to_markdown(
delim: str = "\n\n",
from_element: int = 0,
to_element: int = maxsize,
labels: Optional[set[DocItemLabel]] = None,
strict_text: bool = False,
escape_html: bool = True,
escape_underscores: bool = True,
image_placeholder: str = "<!-- image -->",
enable_chart_tables: bool = True,
image_mode: ImageRefMode = PLACEHOLDER,
indent: int = 4,
text_width: int = -1,
page_no: Optional[int] = None,
included_content_layers: Optional[
set[ContentLayer]
] = None,
page_break_placeholder: Optional[str] = None,
include_annotations: bool = True,
mark_annotations: bool = False,
compact_tables: bool = False,
traverse_pictures: bool = False,
*,
use_legacy_annotations: Optional[bool] = None,
allowed_meta_names: Optional[set[str]] = None,
blocked_meta_names: Optional[set[str]] = None,
mark_meta: bool = False,
) -> str
Serialize to Markdown.
Operates on a slice of the document's body as defined through arguments from_element and to_element; defaulting to the whole document.
:param delim: Deprecated. :type delim: str = "\n\n" :param from_element: Body slicing start index (inclusive). (Default value = 0). :type from_element: int = 0 :param to_element: Body slicing stop index (exclusive). (Default value = maxint). :type to_element: int = sys.maxsize :param labels: The set of document labels to include in the export. None falls back to the system-defined default. :type labels: Optional[set[DocItemLabel]] = None :param strict_text: Deprecated. :type strict_text: bool = False :param escape_html: bool: Whether to escape HTML reserved characters in the text content of the document. (Default value = True). :param escape_underscores: bool: Whether to escape underscores in the text content of the document. (Default value = True). :type escape_underscores: bool = True :param image_placeholder: The placeholder to include to position images in the markdown. (Default value = "\<!-- image -->"). :type image_placeholder: str = "" :param image_mode: The mode to use for including images in the markdown. (Default value = ImageRefMode.PLACEHOLDER). :type image_mode: ImageRefMode = ImageRefMode.PLACEHOLDER :param indent: The indent in spaces of the nested lists. (Default value = 4). :type indent: int = 4 :param included_content_layers: The set of layels to include in the export. None falls back to the system-defined default. :type included_content_layers: Optional[set[ContentLayer]] = None :param page_break_placeholder: The placeholder to include for marking page breaks. None means no page break placeholder will be used. :type page_break_placeholder: Optional[str] = None :param include_annotations: bool: Whether to include annotations in the export; only considered if item does not have meta. (Default value = True). :type include_annotations: bool = True :param mark_annotations: bool: Whether to mark annotations in the export; only considered if item does not have meta. (Default value = False). :type mark_annotations: bool = False :param compact_tables: bool: Whether to use compact table format without column padding. (Default value = False). :type compact_tables: bool = False :param traverse_pictures: bool: Whether to traverse into picture items and serialize their text children. Must be set to True for scanned/image-based PDFs processed with full-page OCR, where the layout model places all OCR text as children of a top-level PictureItem. (Default value = False). :type traverse_pictures: bool = False :param use_legacy_annotations: bool: Deprecated; legacy annotations considered only when meta not present. :type use_legacy_annotations: Optional[bool] = None :param mark_meta: bool: Whether to mark meta in the export :type mark_meta: bool = False :returns: The exported Markdown representation. :rtype: str :param allowed_meta_names: Optional[set[str]]: Meta names to allow; None means all meta names are allowed. :type allowed_meta_names: Optional[set[str]] = None :param blocked_meta_names: Optional[set[str]]: Meta names to block; takes precedence over allowed_meta_names. :type blocked_meta_names: Optional[set[str]] = None
export_to_text(
delim: str = "\n\n",
from_element: int = 0,
to_element: int = maxsize,
labels: Optional[set[DocItemLabel]] = None,
page_no: Optional[int] = None,
included_content_layers: Optional[
set[ContentLayer]
] = None,
page_break_placeholder: Optional[str] = None,
traverse_pictures: bool = False,
) -> str
Export to plain text.
Produces clean plain text without any Markdown decoration. Heading
markers (#), bold/italic markers, and hyperlink syntax are all
stripped. List bullets (-), ordered list numbers, and table-cell
separators (|) are preserved as they aid readability.
:param delim: Deprecated. :type delim: str = "\n\n" :param from_element: Body slicing start index (inclusive). (Default value = 0). :type from_element: int = 0 :param to_element: Body slicing stop index (exclusive). (Default value = maxint). :type to_element: int = sys.maxsize :param labels: The set of document labels to include in the export. None falls back to the system-defined default. :type labels: Optional[set[DocItemLabel]] = None :param page_no: If set, only content from this page is exported. :type page_no: Optional[int] = None :param included_content_layers: The set of layers to include. None falls back to the system-defined default. :type included_content_layers: Optional[set[ContentLayer]] = None :param page_break_placeholder: String inserted at page boundaries. None means no page-break marker is emitted. :type page_break_placeholder: Optional[str] = None :param traverse_pictures: bool: Whether to traverse into picture items and include their text children. Must be set to True for scanned/image-based PDFs processed with full-page OCR, where the layout model places all OCR text as children of a top-level PictureItem. (Default value = False). :type traverse_pictures: bool = False :returns: The exported plain-text representation. :rtype: str
export_to_vtt(
included_content_layers: set[ContentLayer]
| None = None,
omit_hours_if_zero: bool = False,
omit_voice_end: bool = False,
) -> str
Serializes the Docling document to WebVTT format.
Parameters:
-
included_content_layers(set[ContentLayer] | None, default:None) –The content layers to serializes. If ommitted, the
DEFAULT_CONTENT_LAYERSwill be serialized. -
omit_hours_if_zero(bool, default:False) –If True, omit hours when they are 0 in the timings.
-
omit_voice_end(bool, default:False) –If True and cue blocks have a WebVTT cue voice span as the only component, omit the voice end tag for brevity.
Returns:
-
str–A string representation of the Docling document in WebVTT format.
extract_items_range(
*,
start: NodeItem,
end: NodeItem,
start_inclusive: bool = True,
end_inclusive: bool = True,
delete: bool = False,
) -> DoclingDocument
Extracts NodeItems and children in the range from the start NodeItem to the end as a new DoclingDocument.
:param start: NodeItem: The starting NodeItem of the range (must be a direct child of the document body) :param end: NodeItem: The ending NodeItem of the range (must be a direct child of the document body) :param start_inclusive: bool: (Default value = True): If True, the start NodeItem will also be extracted :param end_inclusive: bool: (Default value = True): If True, the end NodeItem will also be extracted :param delete: bool: (Default value = False): If True, extracted items are deleted in the original document
:returns: DoclingDocument: A new document containing the extracted NodeItems and their children
filter(
page_nrs: Optional[set[int]] = None,
) -> DoclingDocument
Create a new document based on the provided filter parameters.
get_visualization(
show_label: bool = True,
show_branch_numbering: bool = False,
viz_mode: Literal[
"reading_order", "key_value"
] = "reading_order",
show_cell_id: bool = False,
) -> dict[Optional[int], Image]
Get visualization of the document as images by page.
:param show_label: Show labels on elements (applies to all visualizers). :type show_label: bool :param show_branch_numbering: Show branch numbering (reading order visualizer only). :type show_branch_numbering: bool :param visualizer: Which visualizer to use. One of 'reading_order' (default), 'key_value'. :type visualizer: str :param show_cell_id: Show cell IDs (key value visualizer only). :type show_cell_id: bool
:returns: Dictionary mapping page numbers to PIL images. :rtype: dict[Optional[int], PILImage.Image]
insert_code(
sibling: NodeItem,
text: str,
code_language: Optional[CodeLanguageLabel] = None,
orig: Optional[str] = None,
caption: Optional[Union[TextItem, RefItem]] = None,
prov: Optional[ProvenanceItem] = None,
content_layer: Optional[ContentLayer] = None,
formatting: Optional[Formatting] = None,
hyperlink: Optional[Union[AnyUrl, Path]] = None,
after: bool = True,
) -> CodeItem
Creates a new CodeItem item and inserts it into the document.
:param sibling: NodeItem: :param text: str: :param code_language: Optional[str]: (Default value = None) :param orig: Optional[str]: (Default value = None) :param caption: Optional[Union[TextItem, RefItem]]: (Default value = None) :param prov: Optional[ProvenanceItem]: (Default value = None) :param content_layer: Optional[ContentLayer]: (Default value = None) :param formatting: Optional[Formatting]: (Default value = None) :param hyperlink: Optional[Union[AnyUrl, Path]]: (Default value = None) :param after: bool: (Default value = True)
:returns: CodeItem: The newly created CodeItem item.
insert_document(
doc: DoclingDocument,
sibling: NodeItem,
after: bool = True,
) -> None
Inserts the content from the body of a DoclingDocument into this document at a specific position.
:param doc: DoclingDocument: The document whose content will be inserted :param sibling: NodeItem: The NodeItem after/before which the new items will be inserted :param after: bool: If True, insert after the sibling; if False, insert before (Default value = True)
:returns: None
insert_form(
sibling: NodeItem,
graph: GraphData,
prov: Optional[ProvenanceItem] = None,
after: bool = True,
) -> FormItem
Creates a new FormItem item and inserts it into the document.
:param sibling: NodeItem: :param graph: GraphData: :param prov: Optional[ProvenanceItem]: (Default value = None) :param after: bool: (Default value = True)
:returns: FormItem: The newly created FormItem item.
insert_formula(
sibling: NodeItem,
text: str,
orig: Optional[str] = None,
prov: Optional[ProvenanceItem] = None,
content_layer: Optional[ContentLayer] = None,
formatting: Optional[Formatting] = None,
hyperlink: Optional[Union[AnyUrl, Path]] = None,
after: bool = True,
) -> FormulaItem
Creates a new FormulaItem item and inserts it into the document.
:param sibling: NodeItem: :param text: str: :param orig: Optional[str]: (Default value = None) :param prov: Optional[ProvenanceItem]: (Default value = None) :param content_layer: Optional[ContentLayer]: (Default value = None) :param formatting: Optional[Formatting]: (Default value = None) :param hyperlink: Optional[Union[AnyUrl, Path]]: (Default value = None) :param after: bool: (Default value = True)
:returns: FormulaItem: The newly created FormulaItem item.
insert_group(
sibling: NodeItem,
label: Optional[GroupLabel] = None,
name: Optional[str] = None,
content_layer: Optional[ContentLayer] = None,
after: bool = True,
) -> GroupItem
Creates a new GroupItem item and inserts it into the document.
:param sibling: NodeItem: :param label: Optional[GroupLabel]: (Default value = None) :param name: Optional[str]: (Default value = None) :param content_layer: Optional[ContentLayer]: (Default value = None) :param after: bool: (Default value = True)
:returns: GroupItem: The newly created GroupItem.
insert_heading(
sibling: NodeItem,
text: str,
orig: Optional[str] = None,
level: LevelNumber = 1,
prov: Optional[ProvenanceItem] = None,
content_layer: Optional[ContentLayer] = None,
formatting: Optional[Formatting] = None,
hyperlink: Optional[Union[AnyUrl, Path]] = None,
after: bool = True,
) -> SectionHeaderItem
Creates a new SectionHeaderItem item and inserts it into the document.
:param sibling: NodeItem: :param text: str: :param orig: Optional[str]: (Default value = None) :param level: LevelNumber: (Default value = 1) :param prov: Optional[ProvenanceItem]: (Default value = None) :param content_layer: Optional[ContentLayer]: (Default value = None) :param formatting: Optional[Formatting]: (Default value = None) :param hyperlink: Optional[Union[AnyUrl, Path]]: (Default value = None) :param after: bool: (Default value = True)
:returns: SectionHeaderItem: The newly created SectionHeaderItem item.
insert_inline_group(
sibling: NodeItem,
name: Optional[str] = None,
content_layer: Optional[ContentLayer] = None,
after: bool = True,
) -> InlineGroup
Creates a new InlineGroup item and inserts it into the document.
:param sibling: NodeItem: :param name: Optional[str]: (Default value = None) :param content_layer: Optional[ContentLayer]: (Default value = None) :param after: bool: (Default value = True)
:returns: InlineGroup: The newly created InlineGroup item.
Inserts an item, given its node_item instance, after other as a sibling.
Inserts an item, given its node_item instance, before other as a sibling.
insert_key_values(
sibling: NodeItem,
graph: GraphData,
prov: Optional[ProvenanceItem] = None,
after: bool = True,
) -> KeyValueItem
Creates a new KeyValueItem item and inserts it into the document.
:param sibling: NodeItem: :param graph: GraphData: :param prov: Optional[ProvenanceItem]: (Default value = None) :param after: bool: (Default value = True)
:returns: KeyValueItem: The newly created KeyValueItem item.
insert_list_group(
sibling: NodeItem,
name: Optional[str] = None,
content_layer: Optional[ContentLayer] = None,
after: bool = True,
) -> ListGroup
Creates a new ListGroup item and inserts it into the document.
:param sibling: NodeItem: :param name: Optional[str]: (Default value = None) :param content_layer: Optional[ContentLayer]: (Default value = None) :param after: bool: (Default value = True)
:returns: ListGroup: The newly created ListGroup item.
insert_list_item(
sibling: NodeItem,
text: str,
enumerated: bool = False,
marker: Optional[str] = None,
orig: Optional[str] = None,
prov: Optional[ProvenanceItem] = None,
content_layer: Optional[ContentLayer] = None,
formatting: Optional[Formatting] = None,
hyperlink: Optional[Union[AnyUrl, Path]] = None,
after: bool = True,
) -> ListItem
Creates a new ListItem item and inserts it into the document.
:param sibling: NodeItem: :param text: str: :param enumerated: bool: (Default value = False) :param marker: Optional[str]: (Default value = None) :param orig: Optional[str]: (Default value = None) :param prov: Optional[ProvenanceItem]: (Default value = None) :param content_layer: Optional[ContentLayer]: (Default value = None) :param formatting: Optional[Formatting]: (Default value = None) :param hyperlink: Optional[Union[AnyUrl, Path]]: (Default value = None) :param after: bool: (Default value = True)
:returns: ListItem: The newly created ListItem item.
insert_node_items(
sibling: NodeItem,
node_items: list[NodeItem],
doc: DoclingDocument,
after: bool = True,
) -> None
Insert multiple NodeItems and their children at a specific position in the document.
:param sibling: NodeItem: The NodeItem after/before which the new items will be inserted :param node_items: list[NodeItem]: The NodeItems to be inserted :param doc: DoclingDocument: The document to which the NodeItems and their children belong :param after: bool: If True, insert after the sibling; if False, insert before (Default value = True)
:returns: None
insert_picture(
sibling: NodeItem,
annotations: Optional[list[PictureDataType]] = None,
image: Optional[ImageRef] = None,
caption: Optional[Union[TextItem, RefItem]] = None,
prov: Optional[ProvenanceItem] = None,
content_layer: Optional[ContentLayer] = None,
after: bool = True,
) -> PictureItem
Creates a new PictureItem item and inserts it into the document.
:param sibling: NodeItem: :param annotations: Optional[list[PictureDataType]]: (Default value = None) :param image: Optional[ImageRef]: (Default value = None) :param caption: Optional[Union[TextItem, RefItem]]: (Default value = None) :param prov: Optional[ProvenanceItem]: (Default value = None) :param content_layer: Optional[ContentLayer]: (Default value = None) :param after: bool: (Default value = True)
:returns: PictureItem: The newly created PictureItem item.
insert_table(
sibling: NodeItem,
data: TableData,
caption: Optional[Union[TextItem, RefItem]] = None,
prov: Optional[ProvenanceItem] = None,
label: DocItemLabel = TABLE,
content_layer: Optional[ContentLayer] = None,
annotations: Optional[list[TableAnnotationType]] = None,
after: bool = True,
) -> TableItem
Creates a new TableItem item and inserts it into the document.
:param sibling: NodeItem: :param data: TableData: :param caption: Optional[Union[TextItem, RefItem]]: (Default value = None) :param prov: Optional[ProvenanceItem]: (Default value = None) :param label: DocItemLabel: (Default value = DocItemLabel.TABLE) :param content_layer: Optional[ContentLayer]: (Default value = None) :param annotations: Optional[list[TableAnnotationType]]: (Default value = None) :param after: bool: (Default value = True)
:returns: TableItem: The newly created TableItem item.
insert_text(
sibling: NodeItem,
label: DocItemLabel,
text: str,
orig: Optional[str] = None,
prov: Optional[ProvenanceItem] = None,
content_layer: Optional[ContentLayer] = None,
formatting: Optional[Formatting] = None,
hyperlink: Optional[Union[AnyUrl, Path]] = None,
after: bool = True,
) -> TextItem
Creates a new TextItem item and inserts it into the document.
:param sibling: NodeItem: :param label: DocItemLabel: :param text: str: :param orig: Optional[str]: (Default value = None) :param prov: Optional[ProvenanceItem]: (Default value = None) :param content_layer: Optional[ContentLayer]: (Default value = None) :param formatting: Optional[Formatting]: (Default value = None) :param hyperlink: Optional[Union[AnyUrl, Path]]: (Default value = None) :param after: bool: (Default value = True)
:returns: TextItem: The newly created TextItem item.
insert_title(
sibling: NodeItem,
text: str,
orig: Optional[str] = None,
prov: Optional[ProvenanceItem] = None,
content_layer: Optional[ContentLayer] = None,
formatting: Optional[Formatting] = None,
hyperlink: Optional[Union[AnyUrl, Path]] = None,
after: bool = True,
) -> TitleItem
Creates a new TitleItem item and inserts it into the document.
:param sibling: NodeItem: :param text: str: :param orig: Optional[str]: (Default value = None) :param prov: Optional[ProvenanceItem]: (Default value = None) :param content_layer: Optional[ContentLayer]: (Default value = None) :param formatting: Optional[Formatting]: (Default value = None) :param hyperlink: Optional[Union[AnyUrl, Path]]: (Default value = None) :param after: bool: (Default value = True)
:returns: TitleItem: The newly created TitleItem item.
iterate_items(
root: Optional[NodeItem] = None,
with_groups: bool = False,
traverse_pictures: bool = False,
page_no: Optional[int] = None,
included_content_layers: Optional[
set[ContentLayer]
] = None,
_level: int = 0,
) -> Iterable[tuple[NodeItem, int]]
Iterate elements with level.
load_from_doctags(
doctag_document: DocTagsDocument,
document_name: str = "Document",
) -> DoclingDocument
Load Docling document from lists of DocTags and Images.
load_from_json(
filename: Union[str, Path],
) -> DoclingDocument
load_from_json.
:param filename: The filename to load a saved DoclingDocument from a .json. :type filename: Path
:returns: The loaded DoclingDocument. :rtype: DoclingDocument
load_from_yaml(
filename: Union[str, Path],
) -> DoclingDocument
load_from_yaml.
Parameters:
-
filename(Union[str, Path]) –The filename to load a YAML-serialized DoclingDocument from.
Returns:
-
DoclingDocument(DoclingDocument) –the loaded DoclingDocument
num_pages()
num_pages.
print_element_tree()
Print_element_tree.
Replace item with new item.
save_as_doclang(filename: Union[str, Path]) -> None
Save the document as Doclang.
save_as_doctags(
filename: Union[str, Path],
delim: str = "",
from_element: int = 0,
to_element: int = maxsize,
labels: Optional[set[DocItemLabel]] = None,
xsize: int = 500,
ysize: int = 500,
add_location: bool = True,
add_content: bool = True,
add_page_index: bool = True,
add_table_cell_location: bool = False,
add_table_cell_text: bool = True,
minified: bool = False,
)
Save the document content to DocTags format.
save_as_document_tokens(*args, **kwargs)
Save the document content to a DocumentToken format.
save_as_html(
filename: Union[str, Path],
artifacts_dir: Optional[Path] = None,
from_element: int = 0,
to_element: int = maxsize,
labels: Optional[set[DocItemLabel]] = None,
image_mode: ImageRefMode = PLACEHOLDER,
formula_to_mathml: bool = True,
page_no: Optional[int] = None,
html_lang: str = "en",
html_head: str = "null",
included_content_layers: Optional[
set[ContentLayer]
] = None,
split_page_view: bool = False,
include_annotations: bool = True,
)
Save to HTML.
save_as_json(
filename: Union[str, Path],
artifacts_dir: Optional[Path] = None,
image_mode: ImageRefMode = EMBEDDED,
indent: int = 2,
coord_precision: Optional[int] = None,
confid_precision: Optional[int] = None,
)
Save as json.
save_as_markdown(
filename: Union[str, Path],
artifacts_dir: Optional[Path] = None,
delim: str = "\n\n",
from_element: int = 0,
to_element: int = maxsize,
labels: Optional[set[DocItemLabel]] = None,
strict_text: bool = False,
escape_html: bool = True,
escaping_underscores: bool = True,
image_placeholder: str = "<!-- image -->",
image_mode: ImageRefMode = PLACEHOLDER,
indent: int = 4,
text_width: int = -1,
page_no: Optional[int] = None,
included_content_layers: Optional[
set[ContentLayer]
] = None,
page_break_placeholder: Optional[str] = None,
include_annotations: bool = True,
compact_tables: bool = False,
*,
mark_meta: bool = False,
use_legacy_annotations: Optional[bool] = None,
)
Save to markdown.
save_as_vtt(
filename: str | Path,
included_content_layers: set[ContentLayer]
| None = None,
omit_hours_if_zero: bool = False,
omit_voice_end: bool = True,
) -> None
Saves the Docling document to a file in WebVTT format.
Parameters:
-
filename(str | Path) –The path to the WebVTT file.
-
included_content_layers(set[ContentLayer] | None, default:None) –The content layers to serializes. If ommitted, the
DEFAULT_CONTENT_LAYERSwill be serialized. -
omit_hours_if_zero(bool, default:False) –If True, omit hours when they are 0 in the timings.
-
omit_voice_end(bool, default:True) –If True and cue blocks have a WebVTT cue voice span as the only component, omit the voice end tag for brevity.
save_as_yaml(
filename: Union[str, Path],
artifacts_dir: Optional[Path] = None,
image_mode: ImageRefMode = EMBEDDED,
default_flow_style: bool = False,
coord_precision: Optional[int] = None,
confid_precision: Optional[int] = None,
)
Save as yaml.
transform_to_content_layer(data: Any) -> Any
transform_to_content_layer.
validate_document() -> Self
validate_document.
validate_misplaced_list_items() -> Self
validate_misplaced_list_items.
Bases: BaseModel
FileSource.
Show JSON schema:
{
"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"
}
Fields:
-
mimetype(str) -
binary_hash(Uint64) -
filename(str) -
uri(Optional[AnyUrl])
Validators:
binary_hash: Uint64
filename: str
mimetype: str
uri: Optional[AnyUrl] = None
parse_hex_string(value)
parse_hex_string.
validate_mimetype(v)
validate_mimetype.
Bases: NodeItem
Base type for any element that carries content, can be a leaf node.
Show JSON schema:
{
"$defs": {
"BaseMeta": {
"additionalProperties": true,
"description": "Base class for metadata.",
"properties": {
"summary": {
"anyOf": [
{
"$ref": "#/$defs/SummaryMetaField"
},
{
"type": "null"
}
],
"default": null
},
"language": {
"anyOf": [
{
"$ref": "#/$defs/LanguageMetaField"
},
{
"type": "null"
}
],
"default": null
},
"entities": {
"anyOf": [
{
"$ref": "#/$defs/EntitiesMetaField"
},
{
"type": "null"
}
],
"default": null
}
},
"title": "BaseMeta",
"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"
},
"ContentLayer": {
"description": "ContentLayer.",
"enum": [
"body",
"furniture",
"background",
"invisible",
"notes"
],
"title": "ContentLayer",
"type": "string"
},
"CoordOrigin": {
"description": "CoordOrigin.",
"enum": [
"TOPLEFT",
"BOTTOMLEFT"
],
"title": "CoordOrigin",
"type": "string"
},
"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",
"field_region",
"field_heading",
"field_item",
"field_key",
"field_value",
"field_hint",
"marker"
],
"title": "DocItemLabel",
"type": "string"
},
"EntitiesMetaField": {
"additionalProperties": true,
"description": "Container for extracted entity mentions.",
"properties": {
"mentions": {
"items": {
"$ref": "#/$defs/EntityMention"
},
"minItems": 1,
"title": "Mentions",
"type": "array"
}
},
"required": [
"mentions"
],
"title": "EntitiesMetaField",
"type": "object"
},
"EntityMention": {
"additionalProperties": true,
"description": "Entity mention extracted from text.",
"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": {
"description": "Normalized text of the entity mention.",
"title": "Text",
"type": "string"
},
"orig": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"default": null,
"description": "Exact source text extracted from the original charspan, analogous to TextItem.orig. This may differ from 'text' when the mention has been normalized.",
"title": "Orig"
},
"label": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"default": null,
"description": "Entity type or category.",
"title": "Label"
},
"charspan": {
"anyOf": [
{
"description": "Character span (0-indexed)",
"maxItems": 2,
"minItems": 2,
"prefixItems": [
{
"type": "integer"
},
{
"type": "integer"
}
],
"type": "array"
},
{
"type": "null"
}
],
"default": null,
"description": "Character span (0-indexed) of the entity mention in the source text.",
"title": "Charspan"
}
},
"required": [
"text"
],
"title": "EntityMention",
"type": "object"
},
"FineRef": {
"description": "Fine-granular reference item that can capture span range info.",
"properties": {
"$ref": {
"pattern": "^#(?:/([\\w-]+)(?:/(\\d+))?)?$",
"title": "$Ref",
"type": "string"
},
"range": {
"anyOf": [
{
"maxItems": 2,
"minItems": 2,
"prefixItems": [
{
"type": "integer"
},
{
"type": "integer"
}
],
"type": "array"
},
{
"type": "null"
}
],
"default": null,
"title": "Range"
}
},
"required": [
"$ref"
],
"title": "FineRef",
"type": "object"
},
"HumanLanguageLabel": {
"description": "Two-letter human language primary subtags using BCP-47 values.",
"enum": [
"aa",
"ab",
"ae",
"af",
"ak",
"am",
"an",
"ar",
"as",
"av",
"ay",
"az",
"ba",
"be",
"bg",
"bh",
"bi",
"bm",
"bn",
"bo",
"br",
"bs",
"ca",
"ce",
"ch",
"co",
"cr",
"cs",
"cu",
"cv",
"cy",
"da",
"de",
"dv",
"dz",
"ee",
"el",
"en",
"eo",
"es",
"et",
"eu",
"fa",
"ff",
"fi",
"fj",
"fo",
"fr",
"fy",
"ga",
"gd",
"gl",
"gn",
"gu",
"gv",
"ha",
"he",
"hi",
"ho",
"hr",
"ht",
"hu",
"hy",
"hz",
"ia",
"id",
"ie",
"ig",
"ii",
"ik",
"io",
"is",
"it",
"iu",
"ja",
"jv",
"ka",
"kg",
"ki",
"kj",
"kk",
"kl",
"km",
"kn",
"ko",
"kr",
"ks",
"ku",
"kv",
"kw",
"ky",
"la",
"lb",
"lg",
"li",
"ln",
"lo",
"lt",
"lu",
"lv",
"mg",
"mh",
"mi",
"mk",
"ml",
"mn",
"mr",
"ms",
"mt",
"my",
"na",
"nb",
"nd",
"ne",
"ng",
"nl",
"nn",
"no",
"nr",
"nv",
"ny",
"oc",
"oj",
"om",
"or",
"os",
"pa",
"pi",
"pl",
"ps",
"pt",
"qu",
"rm",
"rn",
"ro",
"ru",
"rw",
"sa",
"sc",
"sd",
"se",
"sg",
"sh",
"si",
"sk",
"sl",
"sm",
"sn",
"so",
"sq",
"sr",
"ss",
"st",
"su",
"sv",
"sw",
"ta",
"te",
"tg",
"th",
"ti",
"tk",
"tl",
"tn",
"to",
"tr",
"ts",
"tt",
"tw",
"ty",
"ug",
"uk",
"ur",
"uz",
"ve",
"vi",
"vo",
"wa",
"wo",
"xh",
"yi",
"yo",
"za",
"zh",
"zu"
],
"title": "HumanLanguageLabel",
"type": "string"
},
"LanguageMetaField": {
"additionalProperties": true,
"description": "Detected human language.",
"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"
},
"code": {
"$ref": "#/$defs/HumanLanguageLabel"
}
},
"required": [
"code"
],
"title": "LanguageMetaField",
"type": "object"
},
"ProvenanceItem": {
"description": "Provenance information for elements extracted from a textual document.\n\nA `ProvenanceItem` object acts as a lightweight pointer back into the original\ndocument for an extracted element. It applies to documents with an explicity\nor implicit layout, such as PDF, HTML, docx, or pptx.",
"properties": {
"page_no": {
"description": "Page number",
"title": "Page No",
"type": "integer"
},
"bbox": {
"$ref": "#/$defs/BoundingBox",
"description": "Bounding box"
},
"charspan": {
"description": "Character span (0-indexed)",
"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"
},
"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"
},
"TrackSource": {
"description": "Source metadata for a cue extracted from a media track.\n\nA `TrackSource` instance identifies a cue in a media track (audio, video, subtitles, screen-recording captions,\netc.). A *cue* here refers to any discrete segment that was pulled out of the original asset, e.g., a subtitle\nblock, an audio clip, or a timed marker in a screen-recording.",
"properties": {
"kind": {
"const": "track",
"default": "track",
"description": "Identifies this type of source.",
"title": "Kind",
"type": "string"
},
"start_time": {
"description": "Start time offset of the track cue in seconds",
"examples": [
11.0,
6.5,
5370.0
],
"title": "Start Time",
"type": "number"
},
"end_time": {
"description": "End time offset of the track cue in seconds",
"examples": [
12.0,
8.2,
5370.1
],
"title": "End Time",
"type": "number"
},
"identifier": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"default": null,
"description": "An identifier of the cue",
"examples": [
"test",
"123",
"b72d946"
],
"title": "Identifier"
},
"voice": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"default": null,
"description": "The name of the voice in this track (the speaker)",
"examples": [
"John",
"Mary",
"Speaker 1"
],
"title": "Voice"
}
},
"required": [
"start_time",
"end_time"
],
"title": "TrackSource",
"type": "object"
}
},
"additionalProperties": false,
"description": "Base type for any element that carries content, can be a leaf node.",
"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": "#/$defs/BaseMeta"
},
{
"type": "null"
}
],
"default": null
},
"label": {
"$ref": "#/$defs/DocItemLabel"
},
"prov": {
"default": [],
"items": {
"$ref": "#/$defs/ProvenanceItem"
},
"title": "Prov",
"type": "array"
},
"source": {
"default": [],
"description": "The provenance of this document item. Currently, it is only used for media track provenance.",
"items": {
"discriminator": {
"mapping": {
"track": "#/$defs/TrackSource"
},
"propertyName": "kind"
},
"oneOf": [
{
"$ref": "#/$defs/TrackSource"
}
]
},
"title": "Source",
"type": "array"
},
"comments": {
"default": [],
"items": {
"$ref": "#/$defs/FineRef"
},
"title": "Comments",
"type": "array"
}
},
"required": [
"self_ref",
"label"
],
"title": "DocItem",
"type": "object"
}
Fields:
-
self_ref(str) -
parent(Optional[RefItem]) -
children(list[RefItem]) -
content_layer(ContentLayer) -
meta(Optional[BaseMeta]) -
label(DocItemLabel) -
prov(list[ProvenanceItem]) -
source(list[SourceType]) -
comments(list[FineRef])
comments: list[FineRef] = []
content_layer: ContentLayer = BODY
meta: Optional[BaseMeta] = None
model_config = ConfigDict(extra='forbid')
self_ref: str
source: list[SourceType]
The provenance of this document item. Currently, it is only used for media track provenance.
get_annotations() -> Sequence[BaseAnnotation]
Get the annotations of this DocItem.
get_image(
doc: DoclingDocument, prov_index: int = 0
) -> Optional[Image]
Returns the image of this DocItem.
The function returns None if this DocItem has no valid provenance or if a valid image of the page containing this DocItem is not available in doc.
get_location_tokens(
doc: DoclingDocument,
new_line: str = "",
xsize: int = 500,
ysize: int = 500,
self_closing: bool = False,
) -> str
Get the location string for the BaseCell.
Bases: str, Enum
DocItemLabel.
Methods:
-
get_color–Return the RGB color associated with a given label.
Attributes:
-
CAPTION– -
CHART– -
CHECKBOX_SELECTED– -
CHECKBOX_UNSELECTED– -
CODE– -
DOCUMENT_INDEX– -
EMPTY_VALUE– -
FIELD_HEADING– -
FIELD_HINT– -
FIELD_ITEM– -
FIELD_KEY– -
FIELD_REGION– -
FIELD_VALUE– -
FOOTNOTE– -
FORM– -
FORMULA– -
GRADING_SCALE– -
HANDWRITTEN_TEXT– -
KEY_VALUE_REGION– -
LIST_ITEM– -
MARKER– -
PAGE_FOOTER– -
PAGE_HEADER– -
PARAGRAPH– -
PICTURE– -
REFERENCE– -
SECTION_HEADER– -
TABLE– -
TEXT– -
TITLE–
CAPTION = 'caption'
CHART = 'chart'
CHECKBOX_SELECTED = 'checkbox_selected'
CHECKBOX_UNSELECTED = 'checkbox_unselected'
CODE = 'code'
DOCUMENT_INDEX = 'document_index'
EMPTY_VALUE = 'empty_value'
FIELD_HEADING = 'field_heading'
FIELD_HINT = 'field_hint'
FIELD_ITEM = 'field_item'
FIELD_KEY = 'field_key'
FIELD_REGION = 'field_region'
FIELD_VALUE = 'field_value'
FOOTNOTE = 'footnote'
FORM = 'form'
FORMULA = 'formula'
GRADING_SCALE = 'grading_scale'
HANDWRITTEN_TEXT = 'handwritten_text'
KEY_VALUE_REGION = 'key_value_region'
LIST_ITEM = 'list_item'
MARKER = 'marker'
PAGE_FOOTER = 'page_footer'
PAGE_HEADER = 'page_header'
PARAGRAPH = 'paragraph'
PICTURE = 'picture'
REFERENCE = 'reference'
SECTION_HEADER = 'section_header'
TABLE = 'table'
TEXT = 'text'
TITLE = 'title'
get_color(label: DocItemLabel) -> tuple[int, int, int]
Return the RGB color associated with a given label.
Bases: BaseModel
Provenance information for elements extracted from a textual document.
A ProvenanceItem object acts as a lightweight pointer back into the original
document for an extracted element. It applies to documents with an explicity
or implicit layout, such as PDF, HTML, docx, or pptx.
Show JSON schema:
{
"$defs": {
"BoundingBox": {
"description": "BoundingBox.",
"properties": {
"l": {
"title": "L",
"type": "number"
},
"t": {
"title": "T",
"type": "number"
},
"r": {
"title": "R",
"type": "number"
},
"b": {
"title": "B",
"type": "number"
},
"coord_origin": {
"$ref": "#/$defs/CoordOrigin",
"default": "TOPLEFT"
}
},
"required": [
"l",
"t",
"r",
"b"
],
"title": "BoundingBox",
"type": "object"
},
"CoordOrigin": {
"description": "CoordOrigin.",
"enum": [
"TOPLEFT",
"BOTTOMLEFT"
],
"title": "CoordOrigin",
"type": "string"
}
},
"description": "Provenance information for elements extracted from a textual document.\n\nA `ProvenanceItem` object acts as a lightweight pointer back into the original\ndocument for an extracted element. It applies to documents with an explicity\nor implicit layout, such as PDF, HTML, docx, or pptx.",
"properties": {
"page_no": {
"description": "Page number",
"title": "Page No",
"type": "integer"
},
"bbox": {
"$ref": "#/$defs/BoundingBox",
"description": "Bounding box"
},
"charspan": {
"description": "Character span (0-indexed)",
"maxItems": 2,
"minItems": 2,
"prefixItems": [
{
"type": "integer"
},
{
"type": "integer"
}
],
"title": "Charspan",
"type": "array"
}
},
"required": [
"page_no",
"bbox",
"charspan"
],
"title": "ProvenanceItem",
"type": "object"
}
Fields:
-
page_no(int) -
bbox(BoundingBox) -
charspan(CharSpan)
Bases: NodeItem
GroupItem.
Show JSON schema:
{
"$defs": {
"BaseMeta": {
"additionalProperties": true,
"description": "Base class for metadata.",
"properties": {
"summary": {
"anyOf": [
{
"$ref": "#/$defs/SummaryMetaField"
},
{
"type": "null"
}
],
"default": null
},
"language": {
"anyOf": [
{
"$ref": "#/$defs/LanguageMetaField"
},
{
"type": "null"
}
],
"default": null
},
"entities": {
"anyOf": [
{
"$ref": "#/$defs/EntitiesMetaField"
},
{
"type": "null"
}
],
"default": null
}
},
"title": "BaseMeta",
"type": "object"
},
"ContentLayer": {
"description": "ContentLayer.",
"enum": [
"body",
"furniture",
"background",
"invisible",
"notes"
],
"title": "ContentLayer",
"type": "string"
},
"EntitiesMetaField": {
"additionalProperties": true,
"description": "Container for extracted entity mentions.",
"properties": {
"mentions": {
"items": {
"$ref": "#/$defs/EntityMention"
},
"minItems": 1,
"title": "Mentions",
"type": "array"
}
},
"required": [
"mentions"
],
"title": "EntitiesMetaField",
"type": "object"
},
"EntityMention": {
"additionalProperties": true,
"description": "Entity mention extracted from text.",
"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": {
"description": "Normalized text of the entity mention.",
"title": "Text",
"type": "string"
},
"orig": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"default": null,
"description": "Exact source text extracted from the original charspan, analogous to TextItem.orig. This may differ from 'text' when the mention has been normalized.",
"title": "Orig"
},
"label": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"default": null,
"description": "Entity type or category.",
"title": "Label"
},
"charspan": {
"anyOf": [
{
"description": "Character span (0-indexed)",
"maxItems": 2,
"minItems": 2,
"prefixItems": [
{
"type": "integer"
},
{
"type": "integer"
}
],
"type": "array"
},
{
"type": "null"
}
],
"default": null,
"description": "Character span (0-indexed) of the entity mention in the source text.",
"title": "Charspan"
}
},
"required": [
"text"
],
"title": "EntityMention",
"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"
},
"HumanLanguageLabel": {
"description": "Two-letter human language primary subtags using BCP-47 values.",
"enum": [
"aa",
"ab",
"ae",
"af",
"ak",
"am",
"an",
"ar",
"as",
"av",
"ay",
"az",
"ba",
"be",
"bg",
"bh",
"bi",
"bm",
"bn",
"bo",
"br",
"bs",
"ca",
"ce",
"ch",
"co",
"cr",
"cs",
"cu",
"cv",
"cy",
"da",
"de",
"dv",
"dz",
"ee",
"el",
"en",
"eo",
"es",
"et",
"eu",
"fa",
"ff",
"fi",
"fj",
"fo",
"fr",
"fy",
"ga",
"gd",
"gl",
"gn",
"gu",
"gv",
"ha",
"he",
"hi",
"ho",
"hr",
"ht",
"hu",
"hy",
"hz",
"ia",
"id",
"ie",
"ig",
"ii",
"ik",
"io",
"is",
"it",
"iu",
"ja",
"jv",
"ka",
"kg",
"ki",
"kj",
"kk",
"kl",
"km",
"kn",
"ko",
"kr",
"ks",
"ku",
"kv",
"kw",
"ky",
"la",
"lb",
"lg",
"li",
"ln",
"lo",
"lt",
"lu",
"lv",
"mg",
"mh",
"mi",
"mk",
"ml",
"mn",
"mr",
"ms",
"mt",
"my",
"na",
"nb",
"nd",
"ne",
"ng",
"nl",
"nn",
"no",
"nr",
"nv",
"ny",
"oc",
"oj",
"om",
"or",
"os",
"pa",
"pi",
"pl",
"ps",
"pt",
"qu",
"rm",
"rn",
"ro",
"ru",
"rw",
"sa",
"sc",
"sd",
"se",
"sg",
"sh",
"si",
"sk",
"sl",
"sm",
"sn",
"so",
"sq",
"sr",
"ss",
"st",
"su",
"sv",
"sw",
"ta",
"te",
"tg",
"th",
"ti",
"tk",
"tl",
"tn",
"to",
"tr",
"ts",
"tt",
"tw",
"ty",
"ug",
"uk",
"ur",
"uz",
"ve",
"vi",
"vo",
"wa",
"wo",
"xh",
"yi",
"yo",
"za",
"zh",
"zu"
],
"title": "HumanLanguageLabel",
"type": "string"
},
"LanguageMetaField": {
"additionalProperties": true,
"description": "Detected human language.",
"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"
},
"code": {
"$ref": "#/$defs/HumanLanguageLabel"
}
},
"required": [
"code"
],
"title": "LanguageMetaField",
"type": "object"
},
"RefItem": {
"description": "RefItem.",
"properties": {
"$ref": {
"pattern": "^#(?:/([\\w-]+)(?:/(\\d+))?)?$",
"title": "$Ref",
"type": "string"
}
},
"required": [
"$ref"
],
"title": "RefItem",
"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"
}
},
"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": "#/$defs/GroupLabel",
"default": "unspecified"
}
},
"required": [
"self_ref"
],
"title": "GroupItem",
"type": "object"
}
Fields:
-
self_ref(str) -
parent(Optional[RefItem]) -
children(list[RefItem]) -
content_layer(ContentLayer) -
meta(Optional[BaseMeta]) -
name(str) -
label(GroupLabel)
content_layer: ContentLayer = BODY
meta: Optional[BaseMeta] = None
model_config = ConfigDict(extra='forbid')
name: str = 'group'
self_ref: str
Bases: str, Enum
GroupLabel.
Attributes:
-
CHAPTER– -
COMMENT_SECTION– -
FORM_AREA– -
INLINE– -
KEY_VALUE_AREA– -
LIST– -
ORDERED_LIST– -
PICTURE_AREA– -
SECTION– -
SHEET– -
SLIDE– -
UNSPECIFIED–
CHAPTER = 'chapter'
COMMENT_SECTION = 'comment_section'
FORM_AREA = 'form_area'
INLINE = 'inline'
KEY_VALUE_AREA = 'key_value_area'
LIST = 'list'
ORDERED_LIST = 'ordered_list'
PICTURE_AREA = 'picture_area'
SECTION = 'section'
SHEET = 'sheet'
SLIDE = 'slide'
UNSPECIFIED = 'unspecified'
Bases: BaseModel
NodeItem.
Show JSON schema:
{
"$defs": {
"BaseMeta": {
"additionalProperties": true,
"description": "Base class for metadata.",
"properties": {
"summary": {
"anyOf": [
{
"$ref": "#/$defs/SummaryMetaField"
},
{
"type": "null"
}
],
"default": null
},
"language": {
"anyOf": [
{
"$ref": "#/$defs/LanguageMetaField"
},
{
"type": "null"
}
],
"default": null
},
"entities": {
"anyOf": [
{
"$ref": "#/$defs/EntitiesMetaField"
},
{
"type": "null"
}
],
"default": null
}
},
"title": "BaseMeta",
"type": "object"
},
"ContentLayer": {
"description": "ContentLayer.",
"enum": [
"body",
"furniture",
"background",
"invisible",
"notes"
],
"title": "ContentLayer",
"type": "string"
},
"EntitiesMetaField": {
"additionalProperties": true,
"description": "Container for extracted entity mentions.",
"properties": {
"mentions": {
"items": {
"$ref": "#/$defs/EntityMention"
},
"minItems": 1,
"title": "Mentions",
"type": "array"
}
},
"required": [
"mentions"
],
"title": "EntitiesMetaField",
"type": "object"
},
"EntityMention": {
"additionalProperties": true,
"description": "Entity mention extracted from text.",
"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": {
"description": "Normalized text of the entity mention.",
"title": "Text",
"type": "string"
},
"orig": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"default": null,
"description": "Exact source text extracted from the original charspan, analogous to TextItem.orig. This may differ from 'text' when the mention has been normalized.",
"title": "Orig"
},
"label": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"default": null,
"description": "Entity type or category.",
"title": "Label"
},
"charspan": {
"anyOf": [
{
"description": "Character span (0-indexed)",
"maxItems": 2,
"minItems": 2,
"prefixItems": [
{
"type": "integer"
},
{
"type": "integer"
}
],
"type": "array"
},
{
"type": "null"
}
],
"default": null,
"description": "Character span (0-indexed) of the entity mention in the source text.",
"title": "Charspan"
}
},
"required": [
"text"
],
"title": "EntityMention",
"type": "object"
},
"HumanLanguageLabel": {
"description": "Two-letter human language primary subtags using BCP-47 values.",
"enum": [
"aa",
"ab",
"ae",
"af",
"ak",
"am",
"an",
"ar",
"as",
"av",
"ay",
"az",
"ba",
"be",
"bg",
"bh",
"bi",
"bm",
"bn",
"bo",
"br",
"bs",
"ca",
"ce",
"ch",
"co",
"cr",
"cs",
"cu",
"cv",
"cy",
"da",
"de",
"dv",
"dz",
"ee",
"el",
"en",
"eo",
"es",
"et",
"eu",
"fa",
"ff",
"fi",
"fj",
"fo",
"fr",
"fy",
"ga",
"gd",
"gl",
"gn",
"gu",
"gv",
"ha",
"he",
"hi",
"ho",
"hr",
"ht",
"hu",
"hy",
"hz",
"ia",
"id",
"ie",
"ig",
"ii",
"ik",
"io",
"is",
"it",
"iu",
"ja",
"jv",
"ka",
"kg",
"ki",
"kj",
"kk",
"kl",
"km",
"kn",
"ko",
"kr",
"ks",
"ku",
"kv",
"kw",
"ky",
"la",
"lb",
"lg",
"li",
"ln",
"lo",
"lt",
"lu",
"lv",
"mg",
"mh",
"mi",
"mk",
"ml",
"mn",
"mr",
"ms",
"mt",
"my",
"na",
"nb",
"nd",
"ne",
"ng",
"nl",
"nn",
"no",
"nr",
"nv",
"ny",
"oc",
"oj",
"om",
"or",
"os",
"pa",
"pi",
"pl",
"ps",
"pt",
"qu",
"rm",
"rn",
"ro",
"ru",
"rw",
"sa",
"sc",
"sd",
"se",
"sg",
"sh",
"si",
"sk",
"sl",
"sm",
"sn",
"so",
"sq",
"sr",
"ss",
"st",
"su",
"sv",
"sw",
"ta",
"te",
"tg",
"th",
"ti",
"tk",
"tl",
"tn",
"to",
"tr",
"ts",
"tt",
"tw",
"ty",
"ug",
"uk",
"ur",
"uz",
"ve",
"vi",
"vo",
"wa",
"wo",
"xh",
"yi",
"yo",
"za",
"zh",
"zu"
],
"title": "HumanLanguageLabel",
"type": "string"
},
"LanguageMetaField": {
"additionalProperties": true,
"description": "Detected human language.",
"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"
},
"code": {
"$ref": "#/$defs/HumanLanguageLabel"
}
},
"required": [
"code"
],
"title": "LanguageMetaField",
"type": "object"
},
"RefItem": {
"description": "RefItem.",
"properties": {
"$ref": {
"pattern": "^#(?:/([\\w-]+)(?:/(\\d+))?)?$",
"title": "$Ref",
"type": "string"
}
},
"required": [
"$ref"
],
"title": "RefItem",
"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"
}
},
"additionalProperties": false,
"description": "NodeItem.",
"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": "#/$defs/BaseMeta"
},
{
"type": "null"
}
],
"default": null
}
},
"required": [
"self_ref"
],
"title": "NodeItem",
"type": "object"
}
Fields:
Bases: BaseModel
PageItem.
Show JSON schema:
{
"$defs": {
"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"
},
"Size": {
"description": "Size.",
"properties": {
"width": {
"default": 0.0,
"title": "Width",
"type": "number"
},
"height": {
"default": 0.0,
"title": "Height",
"type": "number"
}
},
"title": "Size",
"type": "object"
}
},
"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"
}
Fields:
Bases: DocItem
FloatingItem.
Show JSON schema:
{
"$defs": {
"BoundingBox": {
"description": "BoundingBox.",
"properties": {
"l": {
"title": "L",
"type": "number"
},
"t": {
"title": "T",
"type": "number"
},
"r": {
"title": "R",
"type": "number"
},
"b": {
"title": "B",
"type": "number"
},
"coord_origin": {
"$ref": "#/$defs/CoordOrigin",
"default": "TOPLEFT"
}
},
"required": [
"l",
"t",
"r",
"b"
],
"title": "BoundingBox",
"type": "object"
},
"ContentLayer": {
"description": "ContentLayer.",
"enum": [
"body",
"furniture",
"background",
"invisible",
"notes"
],
"title": "ContentLayer",
"type": "string"
},
"CoordOrigin": {
"description": "CoordOrigin.",
"enum": [
"TOPLEFT",
"BOTTOMLEFT"
],
"title": "CoordOrigin",
"type": "string"
},
"DescriptionMetaField": {
"additionalProperties": true,
"description": "Description metadata field.",
"properties": {
"confidence": {
"anyOf": [
{
"maximum": 1,
"minimum": 0,
"type": "number"
},
{
"type": "null"
}
],
"default": null,
"description": "The confidence of the prediction.",
"examples": [
0.9,
0.42
],
"title": "Confidence"
},
"created_by": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"default": null,
"description": "The origin of the prediction.",
"examples": [
"ibm-granite/granite-docling-258M"
],
"title": "Created By"
},
"text": {
"title": "Text",
"type": "string"
}
},
"required": [
"text"
],
"title": "DescriptionMetaField",
"type": "object"
},
"DocItemLabel": {
"description": "DocItemLabel.",
"enum": [
"caption",
"chart",
"footnote",
"formula",
"list_item",
"page_footer",
"page_header",
"picture",
"section_header",
"table",
"text",
"title",
"document_index",
"code",
"checkbox_selected",
"checkbox_unselected",
"form",
"key_value_region",
"grading_scale",
"handwritten_text",
"empty_value",
"paragraph",
"reference",
"field_region",
"field_heading",
"field_item",
"field_key",
"field_value",
"field_hint",
"marker"
],
"title": "DocItemLabel",
"type": "string"
},
"EntitiesMetaField": {
"additionalProperties": true,
"description": "Container for extracted entity mentions.",
"properties": {
"mentions": {
"items": {
"$ref": "#/$defs/EntityMention"
},
"minItems": 1,
"title": "Mentions",
"type": "array"
}
},
"required": [
"mentions"
],
"title": "EntitiesMetaField",
"type": "object"
},
"EntityMention": {
"additionalProperties": true,
"description": "Entity mention extracted from text.",
"properties": {
"confidence": {
"anyOf": [
{
"maximum": 1,
"minimum": 0,
"type": "number"
},
{
"type": "null"
}
],
"default": null,
"description": "The confidence of the prediction.",
"examples": [
0.9,
0.42
],
"title": "Confidence"
},
"created_by": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"default": null,
"description": "The origin of the prediction.",
"examples": [
"ibm-granite/granite-docling-258M"
],
"title": "Created By"
},
"text": {
"description": "Normalized text of the entity mention.",
"title": "Text",
"type": "string"
},
"orig": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"default": null,
"description": "Exact source text extracted from the original charspan, analogous to TextItem.orig. This may differ from 'text' when the mention has been normalized.",
"title": "Orig"
},
"label": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"default": null,
"description": "Entity type or category.",
"title": "Label"
},
"charspan": {
"anyOf": [
{
"description": "Character span (0-indexed)",
"maxItems": 2,
"minItems": 2,
"prefixItems": [
{
"type": "integer"
},
{
"type": "integer"
}
],
"type": "array"
},
{
"type": "null"
}
],
"default": null,
"description": "Character span (0-indexed) of the entity mention in the source text.",
"title": "Charspan"
}
},
"required": [
"text"
],
"title": "EntityMention",
"type": "object"
},
"FineRef": {
"description": "Fine-granular reference item that can capture span range info.",
"properties": {
"$ref": {
"pattern": "^#(?:/([\\w-]+)(?:/(\\d+))?)?$",
"title": "$Ref",
"type": "string"
},
"range": {
"anyOf": [
{
"maxItems": 2,
"minItems": 2,
"prefixItems": [
{
"type": "integer"
},
{
"type": "integer"
}
],
"type": "array"
},
{
"type": "null"
}
],
"default": null,
"title": "Range"
}
},
"required": [
"$ref"
],
"title": "FineRef",
"type": "object"
},
"FloatingMeta": {
"additionalProperties": true,
"description": "Metadata model for floating.",
"properties": {
"summary": {
"anyOf": [
{
"$ref": "#/$defs/SummaryMetaField"
},
{
"type": "null"
}
],
"default": null
},
"language": {
"anyOf": [
{
"$ref": "#/$defs/LanguageMetaField"
},
{
"type": "null"
}
],
"default": null
},
"entities": {
"anyOf": [
{
"$ref": "#/$defs/EntitiesMetaField"
},
{
"type": "null"
}
],
"default": null
},
"description": {
"anyOf": [
{
"$ref": "#/$defs/DescriptionMetaField"
},
{
"type": "null"
}
],
"default": null
}
},
"title": "FloatingMeta",
"type": "object"
},
"HumanLanguageLabel": {
"description": "Two-letter human language primary subtags using BCP-47 values.",
"enum": [
"aa",
"ab",
"ae",
"af",
"ak",
"am",
"an",
"ar",
"as",
"av",
"ay",
"az",
"ba",
"be",
"bg",
"bh",
"bi",
"bm",
"bn",
"bo",
"br",
"bs",
"ca",
"ce",
"ch",
"co",
"cr",
"cs",
"cu",
"cv",
"cy",
"da",
"de",
"dv",
"dz",
"ee",
"el",
"en",
"eo",
"es",
"et",
"eu",
"fa",
"ff",
"fi",
"fj",
"fo",
"fr",
"fy",
"ga",
"gd",
"gl",
"gn",
"gu",
"gv",
"ha",
"he",
"hi",
"ho",
"hr",
"ht",
"hu",
"hy",
"hz",
"ia",
"id",
"ie",
"ig",
"ii",
"ik",
"io",
"is",
"it",
"iu",
"ja",
"jv",
"ka",
"kg",
"ki",
"kj",
"kk",
"kl",
"km",
"kn",
"ko",
"kr",
"ks",
"ku",
"kv",
"kw",
"ky",
"la",
"lb",
"lg",
"li",
"ln",
"lo",
"lt",
"lu",
"lv",
"mg",
"mh",
"mi",
"mk",
"ml",
"mn",
"mr",
"ms",
"mt",
"my",
"na",
"nb",
"nd",
"ne",
"ng",
"nl",
"nn",
"no",
"nr",
"nv",
"ny",
"oc",
"oj",
"om",
"or",
"os",
"pa",
"pi",
"pl",
"ps",
"pt",
"qu",
"rm",
"rn",
"ro",
"ru",
"rw",
"sa",
"sc",
"sd",
"se",
"sg",
"sh",
"si",
"sk",
"sl",
"sm",
"sn",
"so",
"sq",
"sr",
"ss",
"st",
"su",
"sv",
"sw",
"ta",
"te",
"tg",
"th",
"ti",
"tk",
"tl",
"tn",
"to",
"tr",
"ts",
"tt",
"tw",
"ty",
"ug",
"uk",
"ur",
"uz",
"ve",
"vi",
"vo",
"wa",
"wo",
"xh",
"yi",
"yo",
"za",
"zh",
"zu"
],
"title": "HumanLanguageLabel",
"type": "string"
},
"ImageRef": {
"description": "ImageRef.",
"properties": {
"mimetype": {
"title": "Mimetype",
"type": "string"
},
"dpi": {
"title": "Dpi",
"type": "integer"
},
"size": {
"$ref": "#/$defs/Size"
},
"uri": {
"anyOf": [
{
"format": "uri",
"minLength": 1,
"type": "string"
},
{
"format": "path",
"type": "string"
}
],
"title": "Uri"
}
},
"required": [
"mimetype",
"dpi",
"size",
"uri"
],
"title": "ImageRef",
"type": "object"
},
"LanguageMetaField": {
"additionalProperties": true,
"description": "Detected human language.",
"properties": {
"confidence": {
"anyOf": [
{
"maximum": 1,
"minimum": 0,
"type": "number"
},
{
"type": "null"
}
],
"default": null,
"description": "The confidence of the prediction.",
"examples": [
0.9,
0.42
],
"title": "Confidence"
},
"created_by": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"default": null,
"description": "The origin of the prediction.",
"examples": [
"ibm-granite/granite-docling-258M"
],
"title": "Created By"
},
"code": {
"$ref": "#/$defs/HumanLanguageLabel"
}
},
"required": [
"code"
],
"title": "LanguageMetaField",
"type": "object"
},
"ProvenanceItem": {
"description": "Provenance information for elements extracted from a textual document.\n\nA `ProvenanceItem` object acts as a lightweight pointer back into the original\ndocument for an extracted element. It applies to documents with an explicity\nor implicit layout, such as PDF, HTML, docx, or pptx.",
"properties": {
"page_no": {
"description": "Page number",
"title": "Page No",
"type": "integer"
},
"bbox": {
"$ref": "#/$defs/BoundingBox",
"description": "Bounding box"
},
"charspan": {
"description": "Character span (0-indexed)",
"maxItems": 2,
"minItems": 2,
"prefixItems": [
{
"type": "integer"
},
{
"type": "integer"
}
],
"title": "Charspan",
"type": "array"
}
},
"required": [
"page_no",
"bbox",
"charspan"
],
"title": "ProvenanceItem",
"type": "object"
},
"RefItem": {
"description": "RefItem.",
"properties": {
"$ref": {
"pattern": "^#(?:/([\\w-]+)(?:/(\\d+))?)?$",
"title": "$Ref",
"type": "string"
}
},
"required": [
"$ref"
],
"title": "RefItem",
"type": "object"
},
"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"
},
"TrackSource": {
"description": "Source metadata for a cue extracted from a media track.\n\nA `TrackSource` instance identifies a cue in a media track (audio, video, subtitles, screen-recording captions,\netc.). A *cue* here refers to any discrete segment that was pulled out of the original asset, e.g., a subtitle\nblock, an audio clip, or a timed marker in a screen-recording.",
"properties": {
"kind": {
"const": "track",
"default": "track",
"description": "Identifies this type of source.",
"title": "Kind",
"type": "string"
},
"start_time": {
"description": "Start time offset of the track cue in seconds",
"examples": [
11.0,
6.5,
5370.0
],
"title": "Start Time",
"type": "number"
},
"end_time": {
"description": "End time offset of the track cue in seconds",
"examples": [
12.0,
8.2,
5370.1
],
"title": "End Time",
"type": "number"
},
"identifier": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"default": null,
"description": "An identifier of the cue",
"examples": [
"test",
"123",
"b72d946"
],
"title": "Identifier"
},
"voice": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"default": null,
"description": "The name of the voice in this track (the speaker)",
"examples": [
"John",
"Mary",
"Speaker 1"
],
"title": "Voice"
}
},
"required": [
"start_time",
"end_time"
],
"title": "TrackSource",
"type": "object"
}
},
"additionalProperties": false,
"description": "FloatingItem.",
"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": {
"$ref": "#/$defs/DocItemLabel"
},
"prov": {
"default": [],
"items": {
"$ref": "#/$defs/ProvenanceItem"
},
"title": "Prov",
"type": "array"
},
"source": {
"default": [],
"description": "The provenance of this document item. Currently, it is only used for media track provenance.",
"items": {
"discriminator": {
"mapping": {
"track": "#/$defs/TrackSource"
},
"propertyName": "kind"
},
"oneOf": [
{
"$ref": "#/$defs/TrackSource"
}
]
},
"title": "Source",
"type": "array"
},
"comments": {
"default": [],
"items": {
"$ref": "#/$defs/FineRef"
},
"title": "Comments",
"type": "array"
},
"captions": {
"default": [],
"items": {
"$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": "#/$defs/ImageRef"
},
{
"type": "null"
}
],
"default": null
}
},
"required": [
"self_ref",
"label"
],
"title": "FloatingItem",
"type": "object"
}
Fields:
-
self_ref(str) -
parent(Optional[RefItem]) -
children(list[RefItem]) -
content_layer(ContentLayer) -
label(DocItemLabel) -
prov(list[ProvenanceItem]) -
source(list[SourceType]) -
comments(list[FineRef]) -
meta(Optional[FloatingMeta]) -
captions(list[RefItem]) -
references(list[RefItem]) -
footnotes(list[RefItem]) -
image(Optional[ImageRef])
comments: list[FineRef] = []
content_layer: ContentLayer = BODY
meta: Optional[FloatingMeta] = None
model_config = ConfigDict(extra='forbid')
self_ref: str
source: list[SourceType]
The provenance of this document item. Currently, it is only used for media track provenance.
get_annotations() -> Sequence[BaseAnnotation]
Get the annotations of this DocItem.
get_image(
doc: DoclingDocument, prov_index: int = 0
) -> Optional[Image]
Returns the image corresponding to this FloatingItem.
This function returns the PIL image from self.image if one is available. Otherwise, it uses DocItem.get_image to get an image of this FloatingItem.
In particular, when self.image is None, the function returns None if this FloatingItem has no valid provenance or the doc does not contain a valid image for the required page.
get_location_tokens(
doc: DoclingDocument,
new_line: str = "",
xsize: int = 500,
ysize: int = 500,
self_closing: bool = False,
) -> str
Get the location string for the BaseCell.
Bases: DocItem
TextItem.
Show JSON schema:
{
"$defs": {
"BaseMeta": {
"additionalProperties": true,
"description": "Base class for metadata.",
"properties": {
"summary": {
"anyOf": [
{
"$ref": "#/$defs/SummaryMetaField"
},
{
"type": "null"
}
],
"default": null
},
"language": {
"anyOf": [
{
"$ref": "#/$defs/LanguageMetaField"
},
{
"type": "null"
}
],
"default": null
},
"entities": {
"anyOf": [
{
"$ref": "#/$defs/EntitiesMetaField"
},
{
"type": "null"
}
],
"default": null
}
},
"title": "BaseMeta",
"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"
},
"ContentLayer": {
"description": "ContentLayer.",
"enum": [
"body",
"furniture",
"background",
"invisible",
"notes"
],
"title": "ContentLayer",
"type": "string"
},
"CoordOrigin": {
"description": "CoordOrigin.",
"enum": [
"TOPLEFT",
"BOTTOMLEFT"
],
"title": "CoordOrigin",
"type": "string"
},
"EntitiesMetaField": {
"additionalProperties": true,
"description": "Container for extracted entity mentions.",
"properties": {
"mentions": {
"items": {
"$ref": "#/$defs/EntityMention"
},
"minItems": 1,
"title": "Mentions",
"type": "array"
}
},
"required": [
"mentions"
],
"title": "EntitiesMetaField",
"type": "object"
},
"EntityMention": {
"additionalProperties": true,
"description": "Entity mention extracted from text.",
"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": {
"description": "Normalized text of the entity mention.",
"title": "Text",
"type": "string"
},
"orig": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"default": null,
"description": "Exact source text extracted from the original charspan, analogous to TextItem.orig. This may differ from 'text' when the mention has been normalized.",
"title": "Orig"
},
"label": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"default": null,
"description": "Entity type or category.",
"title": "Label"
},
"charspan": {
"anyOf": [
{
"description": "Character span (0-indexed)",
"maxItems": 2,
"minItems": 2,
"prefixItems": [
{
"type": "integer"
},
{
"type": "integer"
}
],
"type": "array"
},
{
"type": "null"
}
],
"default": null,
"description": "Character span (0-indexed) of the entity mention in the source text.",
"title": "Charspan"
}
},
"required": [
"text"
],
"title": "EntityMention",
"type": "object"
},
"FineRef": {
"description": "Fine-granular reference item that can capture span range info.",
"properties": {
"$ref": {
"pattern": "^#(?:/([\\w-]+)(?:/(\\d+))?)?$",
"title": "$Ref",
"type": "string"
},
"range": {
"anyOf": [
{
"maxItems": 2,
"minItems": 2,
"prefixItems": [
{
"type": "integer"
},
{
"type": "integer"
}
],
"type": "array"
},
{
"type": "null"
}
],
"default": null,
"title": "Range"
}
},
"required": [
"$ref"
],
"title": "FineRef",
"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"
},
"HumanLanguageLabel": {
"description": "Two-letter human language primary subtags using BCP-47 values.",
"enum": [
"aa",
"ab",
"ae",
"af",
"ak",
"am",
"an",
"ar",
"as",
"av",
"ay",
"az",
"ba",
"be",
"bg",
"bh",
"bi",
"bm",
"bn",
"bo",
"br",
"bs",
"ca",
"ce",
"ch",
"co",
"cr",
"cs",
"cu",
"cv",
"cy",
"da",
"de",
"dv",
"dz",
"ee",
"el",
"en",
"eo",
"es",
"et",
"eu",
"fa",
"ff",
"fi",
"fj",
"fo",
"fr",
"fy",
"ga",
"gd",
"gl",
"gn",
"gu",
"gv",
"ha",
"he",
"hi",
"ho",
"hr",
"ht",
"hu",
"hy",
"hz",
"ia",
"id",
"ie",
"ig",
"ii",
"ik",
"io",
"is",
"it",
"iu",
"ja",
"jv",
"ka",
"kg",
"ki",
"kj",
"kk",
"kl",
"km",
"kn",
"ko",
"kr",
"ks",
"ku",
"kv",
"kw",
"ky",
"la",
"lb",
"lg",
"li",
"ln",
"lo",
"lt",
"lu",
"lv",
"mg",
"mh",
"mi",
"mk",
"ml",
"mn",
"mr",
"ms",
"mt",
"my",
"na",
"nb",
"nd",
"ne",
"ng",
"nl",
"nn",
"no",
"nr",
"nv",
"ny",
"oc",
"oj",
"om",
"or",
"os",
"pa",
"pi",
"pl",
"ps",
"pt",
"qu",
"rm",
"rn",
"ro",
"ru",
"rw",
"sa",
"sc",
"sd",
"se",
"sg",
"sh",
"si",
"sk",
"sl",
"sm",
"sn",
"so",
"sq",
"sr",
"ss",
"st",
"su",
"sv",
"sw",
"ta",
"te",
"tg",
"th",
"ti",
"tk",
"tl",
"tn",
"to",
"tr",
"ts",
"tt",
"tw",
"ty",
"ug",
"uk",
"ur",
"uz",
"ve",
"vi",
"vo",
"wa",
"wo",
"xh",
"yi",
"yo",
"za",
"zh",
"zu"
],
"title": "HumanLanguageLabel",
"type": "string"
},
"LanguageMetaField": {
"additionalProperties": true,
"description": "Detected human language.",
"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"
},
"code": {
"$ref": "#/$defs/HumanLanguageLabel"
}
},
"required": [
"code"
],
"title": "LanguageMetaField",
"type": "object"
},
"ProvenanceItem": {
"description": "Provenance information for elements extracted from a textual document.\n\nA `ProvenanceItem` object acts as a lightweight pointer back into the original\ndocument for an extracted element. It applies to documents with an explicity\nor implicit layout, such as PDF, HTML, docx, or pptx.",
"properties": {
"page_no": {
"description": "Page number",
"title": "Page No",
"type": "integer"
},
"bbox": {
"$ref": "#/$defs/BoundingBox",
"description": "Bounding box"
},
"charspan": {
"description": "Character span (0-indexed)",
"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"
},
"Script": {
"description": "Text script position.",
"enum": [
"baseline",
"sub",
"super"
],
"title": "Script",
"type": "string"
},
"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"
},
"TrackSource": {
"description": "Source metadata for a cue extracted from a media track.\n\nA `TrackSource` instance identifies a cue in a media track (audio, video, subtitles, screen-recording captions,\netc.). A *cue* here refers to any discrete segment that was pulled out of the original asset, e.g., a subtitle\nblock, an audio clip, or a timed marker in a screen-recording.",
"properties": {
"kind": {
"const": "track",
"default": "track",
"description": "Identifies this type of source.",
"title": "Kind",
"type": "string"
},
"start_time": {
"description": "Start time offset of the track cue in seconds",
"examples": [
11.0,
6.5,
5370.0
],
"title": "Start Time",
"type": "number"
},
"end_time": {
"description": "End time offset of the track cue in seconds",
"examples": [
12.0,
8.2,
5370.1
],
"title": "End Time",
"type": "number"
},
"identifier": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"default": null,
"description": "An identifier of the cue",
"examples": [
"test",
"123",
"b72d946"
],
"title": "Identifier"
},
"voice": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"default": null,
"description": "The name of the voice in this track (the speaker)",
"examples": [
"John",
"Mary",
"Speaker 1"
],
"title": "Voice"
}
},
"required": [
"start_time",
"end_time"
],
"title": "TrackSource",
"type": "object"
}
},
"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": "#/$defs/BaseMeta"
},
{
"type": "null"
}
],
"default": null
},
"label": {
"enum": [
"caption",
"checkbox_selected",
"checkbox_unselected",
"footnote",
"page_footer",
"page_header",
"paragraph",
"reference",
"text",
"empty_value",
"field_key",
"field_hint",
"marker",
"handwritten_text"
],
"title": "Label",
"type": "string"
},
"prov": {
"default": [],
"items": {
"$ref": "#/$defs/ProvenanceItem"
},
"title": "Prov",
"type": "array"
},
"source": {
"default": [],
"description": "The provenance of this document item. Currently, it is only used for media track provenance.",
"items": {
"discriminator": {
"mapping": {
"track": "#/$defs/TrackSource"
},
"propertyName": "kind"
},
"oneOf": [
{
"$ref": "#/$defs/TrackSource"
}
]
},
"title": "Source",
"type": "array"
},
"comments": {
"default": [],
"items": {
"$ref": "#/$defs/FineRef"
},
"title": "Comments",
"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"
}
Fields:
-
self_ref(str) -
parent(Optional[RefItem]) -
children(list[RefItem]) -
content_layer(ContentLayer) -
meta(Optional[BaseMeta]) -
prov(list[ProvenanceItem]) -
source(list[SourceType]) -
comments(list[FineRef]) -
label(Literal[CAPTION, CHECKBOX_SELECTED, CHECKBOX_UNSELECTED, FOOTNOTE, PAGE_FOOTER, PAGE_HEADER, PARAGRAPH, REFERENCE, TEXT, EMPTY_VALUE, FIELD_KEY, FIELD_HINT, MARKER, HANDWRITTEN_TEXT]) -
orig(str) -
text(str) -
formatting(Optional[Formatting]) -
hyperlink(Optional[Union[AnyUrl, Path]])
comments: list[FineRef] = []
content_layer: ContentLayer = BODY
formatting: Optional[Formatting] = None
hyperlink: Optional[Union[AnyUrl, Path]] = None
label: Literal[
CAPTION,
CHECKBOX_SELECTED,
CHECKBOX_UNSELECTED,
FOOTNOTE,
PAGE_FOOTER,
PAGE_HEADER,
PARAGRAPH,
REFERENCE,
TEXT,
EMPTY_VALUE,
FIELD_KEY,
FIELD_HINT,
MARKER,
HANDWRITTEN_TEXT,
]
meta: Optional[BaseMeta] = None
model_config = ConfigDict(extra='forbid')
orig: str
self_ref: str
source: list[SourceType]
The provenance of this document item. Currently, it is only used for media track provenance.
text: str
export_to_doctags(
doc: DoclingDocument,
new_line: str = "",
xsize: int = 500,
ysize: int = 500,
add_location: bool = True,
add_content: bool = True,
)
Export text element to document tokens format.
:param doc: "DoclingDocument": :param new_line: str (Default value = "") Deprecated :param xsize: int: (Default value = 500) :param ysize: int: (Default value = 500) :param add_location: bool: (Default value = True) :param add_content: bool: (Default value = True)
export_to_document_tokens(*args, **kwargs)
Export to DocTags format.
get_annotations() -> Sequence[BaseAnnotation]
Get the annotations of this DocItem.
get_image(
doc: DoclingDocument, prov_index: int = 0
) -> Optional[Image]
Returns the image of this DocItem.
The function returns None if this DocItem has no valid provenance or if a valid image of the page containing this DocItem is not available in doc.
get_location_tokens(
doc: DoclingDocument,
new_line: str = "",
xsize: int = 500,
ysize: int = 500,
self_closing: bool = False,
) -> str
Get the location string for the BaseCell.
Bases: FloatingItem
TableItem.
Show JSON schema:
{
"$defs": {
"BoundingBox": {
"description": "BoundingBox.",
"properties": {
"l": {
"title": "L",
"type": "number"
},
"t": {
"title": "T",
"type": "number"
},
"r": {
"title": "R",
"type": "number"
},
"b": {
"title": "B",
"type": "number"
},
"coord_origin": {
"$ref": "#/$defs/CoordOrigin",
"default": "TOPLEFT"
}
},
"required": [
"l",
"t",
"r",
"b"
],
"title": "BoundingBox",
"type": "object"
},
"ContentLayer": {
"description": "ContentLayer.",
"enum": [
"body",
"furniture",
"background",
"invisible",
"notes"
],
"title": "ContentLayer",
"type": "string"
},
"CoordOrigin": {
"description": "CoordOrigin.",
"enum": [
"TOPLEFT",
"BOTTOMLEFT"
],
"title": "CoordOrigin",
"type": "string"
},
"DescriptionAnnotation": {
"description": "DescriptionAnnotation.",
"properties": {
"kind": {
"const": "description",
"default": "description",
"title": "Kind",
"type": "string"
},
"text": {
"title": "Text",
"type": "string"
},
"provenance": {
"title": "Provenance",
"type": "string"
}
},
"required": [
"text",
"provenance"
],
"title": "DescriptionAnnotation",
"type": "object"
},
"DescriptionMetaField": {
"additionalProperties": true,
"description": "Description metadata field.",
"properties": {
"confidence": {
"anyOf": [
{
"maximum": 1,
"minimum": 0,
"type": "number"
},
{
"type": "null"
}
],
"default": null,
"description": "The confidence of the prediction.",
"examples": [
0.9,
0.42
],
"title": "Confidence"
},
"created_by": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"default": null,
"description": "The origin of the prediction.",
"examples": [
"ibm-granite/granite-docling-258M"
],
"title": "Created By"
},
"text": {
"title": "Text",
"type": "string"
}
},
"required": [
"text"
],
"title": "DescriptionMetaField",
"type": "object"
},
"EntitiesMetaField": {
"additionalProperties": true,
"description": "Container for extracted entity mentions.",
"properties": {
"mentions": {
"items": {
"$ref": "#/$defs/EntityMention"
},
"minItems": 1,
"title": "Mentions",
"type": "array"
}
},
"required": [
"mentions"
],
"title": "EntitiesMetaField",
"type": "object"
},
"EntityMention": {
"additionalProperties": true,
"description": "Entity mention extracted from text.",
"properties": {
"confidence": {
"anyOf": [
{
"maximum": 1,
"minimum": 0,
"type": "number"
},
{
"type": "null"
}
],
"default": null,
"description": "The confidence of the prediction.",
"examples": [
0.9,
0.42
],
"title": "Confidence"
},
"created_by": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"default": null,
"description": "The origin of the prediction.",
"examples": [
"ibm-granite/granite-docling-258M"
],
"title": "Created By"
},
"text": {
"description": "Normalized text of the entity mention.",
"title": "Text",
"type": "string"
},
"orig": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"default": null,
"description": "Exact source text extracted from the original charspan, analogous to TextItem.orig. This may differ from 'text' when the mention has been normalized.",
"title": "Orig"
},
"label": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"default": null,
"description": "Entity type or category.",
"title": "Label"
},
"charspan": {
"anyOf": [
{
"description": "Character span (0-indexed)",
"maxItems": 2,
"minItems": 2,
"prefixItems": [
{
"type": "integer"
},
{
"type": "integer"
}
],
"type": "array"
},
{
"type": "null"
}
],
"default": null,
"description": "Character span (0-indexed) of the entity mention in the source text.",
"title": "Charspan"
}
},
"required": [
"text"
],
"title": "EntityMention",
"type": "object"
},
"FineRef": {
"description": "Fine-granular reference item that can capture span range info.",
"properties": {
"$ref": {
"pattern": "^#(?:/([\\w-]+)(?:/(\\d+))?)?$",
"title": "$Ref",
"type": "string"
},
"range": {
"anyOf": [
{
"maxItems": 2,
"minItems": 2,
"prefixItems": [
{
"type": "integer"
},
{
"type": "integer"
}
],
"type": "array"
},
{
"type": "null"
}
],
"default": null,
"title": "Range"
}
},
"required": [
"$ref"
],
"title": "FineRef",
"type": "object"
},
"FloatingMeta": {
"additionalProperties": true,
"description": "Metadata model for floating.",
"properties": {
"summary": {
"anyOf": [
{
"$ref": "#/$defs/SummaryMetaField"
},
{
"type": "null"
}
],
"default": null
},
"language": {
"anyOf": [
{
"$ref": "#/$defs/LanguageMetaField"
},
{
"type": "null"
}
],
"default": null
},
"entities": {
"anyOf": [
{
"$ref": "#/$defs/EntitiesMetaField"
},
{
"type": "null"
}
],
"default": null
},
"description": {
"anyOf": [
{
"$ref": "#/$defs/DescriptionMetaField"
},
{
"type": "null"
}
],
"default": null
}
},
"title": "FloatingMeta",
"type": "object"
},
"HumanLanguageLabel": {
"description": "Two-letter human language primary subtags using BCP-47 values.",
"enum": [
"aa",
"ab",
"ae",
"af",
"ak",
"am",
"an",
"ar",
"as",
"av",
"ay",
"az",
"ba",
"be",
"bg",
"bh",
"bi",
"bm",
"bn",
"bo",
"br",
"bs",
"ca",
"ce",
"ch",
"co",
"cr",
"cs",
"cu",
"cv",
"cy",
"da",
"de",
"dv",
"dz",
"ee",
"el",
"en",
"eo",
"es",
"et",
"eu",
"fa",
"ff",
"fi",
"fj",
"fo",
"fr",
"fy",
"ga",
"gd",
"gl",
"gn",
"gu",
"gv",
"ha",
"he",
"hi",
"ho",
"hr",
"ht",
"hu",
"hy",
"hz",
"ia",
"id",
"ie",
"ig",
"ii",
"ik",
"io",
"is",
"it",
"iu",
"ja",
"jv",
"ka",
"kg",
"ki",
"kj",
"kk",
"kl",
"km",
"kn",
"ko",
"kr",
"ks",
"ku",
"kv",
"kw",
"ky",
"la",
"lb",
"lg",
"li",
"ln",
"lo",
"lt",
"lu",
"lv",
"mg",
"mh",
"mi",
"mk",
"ml",
"mn",
"mr",
"ms",
"mt",
"my",
"na",
"nb",
"nd",
"ne",
"ng",
"nl",
"nn",
"no",
"nr",
"nv",
"ny",
"oc",
"oj",
"om",
"or",
"os",
"pa",
"pi",
"pl",
"ps",
"pt",
"qu",
"rm",
"rn",
"ro",
"ru",
"rw",
"sa",
"sc",
"sd",
"se",
"sg",
"sh",
"si",
"sk",
"sl",
"sm",
"sn",
"so",
"sq",
"sr",
"ss",
"st",
"su",
"sv",
"sw",
"ta",
"te",
"tg",
"th",
"ti",
"tk",
"tl",
"tn",
"to",
"tr",
"ts",
"tt",
"tw",
"ty",
"ug",
"uk",
"ur",
"uz",
"ve",
"vi",
"vo",
"wa",
"wo",
"xh",
"yi",
"yo",
"za",
"zh",
"zu"
],
"title": "HumanLanguageLabel",
"type": "string"
},
"ImageRef": {
"description": "ImageRef.",
"properties": {
"mimetype": {
"title": "Mimetype",
"type": "string"
},
"dpi": {
"title": "Dpi",
"type": "integer"
},
"size": {
"$ref": "#/$defs/Size"
},
"uri": {
"anyOf": [
{
"format": "uri",
"minLength": 1,
"type": "string"
},
{
"format": "path",
"type": "string"
}
],
"title": "Uri"
}
},
"required": [
"mimetype",
"dpi",
"size",
"uri"
],
"title": "ImageRef",
"type": "object"
},
"LanguageMetaField": {
"additionalProperties": true,
"description": "Detected human language.",
"properties": {
"confidence": {
"anyOf": [
{
"maximum": 1,
"minimum": 0,
"type": "number"
},
{
"type": "null"
}
],
"default": null,
"description": "The confidence of the prediction.",
"examples": [
0.9,
0.42
],
"title": "Confidence"
},
"created_by": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"default": null,
"description": "The origin of the prediction.",
"examples": [
"ibm-granite/granite-docling-258M"
],
"title": "Created By"
},
"code": {
"$ref": "#/$defs/HumanLanguageLabel"
}
},
"required": [
"code"
],
"title": "LanguageMetaField",
"type": "object"
},
"MiscAnnotation": {
"description": "MiscAnnotation.",
"properties": {
"kind": {
"const": "misc",
"default": "misc",
"title": "Kind",
"type": "string"
},
"content": {
"additionalProperties": true,
"title": "Content",
"type": "object"
}
},
"required": [
"content"
],
"title": "MiscAnnotation",
"type": "object"
},
"Orientation": {
"description": "Counter-clockwise rotation of a table on the page, in degrees.\n\nFollows the convention used by PIL/Pillow's ``Image.rotate``: positive\nangles rotate the table counter-clockwise. ``ROT_0`` / ``ROT_180`` keep\nrows running horizontally on the page; ``ROT_90`` / ``ROT_270`` turn\nrows into vertical stripes.",
"enum": [
"rot_0",
"rot_90",
"rot_180",
"rot_270"
],
"title": "Orientation",
"type": "string"
},
"ProvenanceItem": {
"description": "Provenance information for elements extracted from a textual document.\n\nA `ProvenanceItem` object acts as a lightweight pointer back into the original\ndocument for an extracted element. It applies to documents with an explicity\nor implicit layout, such as PDF, HTML, docx, or pptx.",
"properties": {
"page_no": {
"description": "Page number",
"title": "Page No",
"type": "integer"
},
"bbox": {
"$ref": "#/$defs/BoundingBox",
"description": "Bounding box"
},
"charspan": {
"description": "Character span (0-indexed)",
"maxItems": 2,
"minItems": 2,
"prefixItems": [
{
"type": "integer"
},
{
"type": "integer"
}
],
"title": "Charspan",
"type": "array"
}
},
"required": [
"page_no",
"bbox",
"charspan"
],
"title": "ProvenanceItem",
"type": "object"
},
"RefItem": {
"description": "RefItem.",
"properties": {
"$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": "#/$defs/RefItem"
}
},
"required": [
"start_row_offset_idx",
"end_row_offset_idx",
"start_col_offset_idx",
"end_col_offset_idx",
"text",
"ref"
],
"title": "RichTableCell",
"type": "object"
},
"Size": {
"description": "Size.",
"properties": {
"width": {
"default": 0.0,
"title": "Width",
"type": "number"
},
"height": {
"default": 0.0,
"title": "Height",
"type": "number"
}
},
"title": "Size",
"type": "object"
},
"SummaryMetaField": {
"additionalProperties": true,
"description": "Summary data.",
"properties": {
"confidence": {
"anyOf": [
{
"maximum": 1,
"minimum": 0,
"type": "number"
},
{
"type": "null"
}
],
"default": null,
"description": "The confidence of the prediction.",
"examples": [
0.9,
0.42
],
"title": "Confidence"
},
"created_by": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"default": null,
"description": "The origin of the prediction.",
"examples": [
"ibm-granite/granite-docling-258M"
],
"title": "Created By"
},
"text": {
"title": "Text",
"type": "string"
}
},
"required": [
"text"
],
"title": "SummaryMetaField",
"type": "object"
},
"TableCell": {
"description": "TableCell.",
"properties": {
"bbox": {
"anyOf": [
{
"$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": "#/$defs/TableCell"
}
]
},
"title": "Table Cells",
"type": "array"
},
"num_rows": {
"default": 0,
"title": "Num Rows",
"type": "integer"
},
"num_cols": {
"default": 0,
"title": "Num Cols",
"type": "integer"
},
"orientation": {
"$ref": "#/$defs/Orientation",
"default": "rot_0"
}
},
"title": "TableData",
"type": "object"
},
"TrackSource": {
"description": "Source metadata for a cue extracted from a media track.\n\nA `TrackSource` instance identifies a cue in a media track (audio, video, subtitles, screen-recording captions,\netc.). A *cue* here refers to any discrete segment that was pulled out of the original asset, e.g., a subtitle\nblock, an audio clip, or a timed marker in a screen-recording.",
"properties": {
"kind": {
"const": "track",
"default": "track",
"description": "Identifies this type of source.",
"title": "Kind",
"type": "string"
},
"start_time": {
"description": "Start time offset of the track cue in seconds",
"examples": [
11.0,
6.5,
5370.0
],
"title": "Start Time",
"type": "number"
},
"end_time": {
"description": "End time offset of the track cue in seconds",
"examples": [
12.0,
8.2,
5370.1
],
"title": "End Time",
"type": "number"
},
"identifier": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"default": null,
"description": "An identifier of the cue",
"examples": [
"test",
"123",
"b72d946"
],
"title": "Identifier"
},
"voice": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"default": null,
"description": "The name of the voice in this track (the speaker)",
"examples": [
"John",
"Mary",
"Speaker 1"
],
"title": "Voice"
}
},
"required": [
"start_time",
"end_time"
],
"title": "TrackSource",
"type": "object"
}
},
"additionalProperties": false,
"description": "TableItem.",
"properties": {
"self_ref": {
"pattern": "^#(?:/([\\w-]+)(?:/(\\d+))?)?$",
"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"
},
"source": {
"default": [],
"description": "The provenance of this document item. Currently, it is only used for media track provenance.",
"items": {
"discriminator": {
"mapping": {
"track": "#/$defs/TrackSource"
},
"propertyName": "kind"
},
"oneOf": [
{
"$ref": "#/$defs/TrackSource"
}
]
},
"title": "Source",
"type": "array"
},
"comments": {
"default": [],
"items": {
"$ref": "#/$defs/FineRef"
},
"title": "Comments",
"type": "array"
},
"captions": {
"default": [],
"items": {
"$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"
}
Fields:
-
self_ref(str) -
parent(Optional[RefItem]) -
children(list[RefItem]) -
content_layer(ContentLayer) -
meta(Optional[FloatingMeta]) -
prov(list[ProvenanceItem]) -
source(list[SourceType]) -
comments(list[FineRef]) -
captions(list[RefItem]) -
references(list[RefItem]) -
footnotes(list[RefItem]) -
image(Optional[ImageRef]) -
data(TableData) -
label(Literal[DOCUMENT_INDEX, TABLE]) -
annotations(list[TableAnnotationType])
Validators:
-
_migrate_annotations_to_meta
annotations: list[TableAnnotationType] = []
comments: list[FineRef] = []
content_layer: ContentLayer = BODY
meta: Optional[FloatingMeta] = None
model_config = ConfigDict(extra='forbid')
self_ref: str
source: list[SourceType]
The provenance of this document item. Currently, it is only used for media track provenance.
add_annotation(annotation: TableAnnotationType) -> None
Add an annotation to the table.
export_to_dataframe(
doc: Optional[DoclingDocument] = None,
) -> DataFrame
Export the table as a Pandas DataFrame.
export_to_doctags(
doc: DoclingDocument,
new_line: str = "",
xsize: int = 500,
ysize: int = 500,
add_location: bool = True,
add_cell_location: bool = True,
add_cell_text: bool = True,
add_caption: bool = True,
)
Export table to document tokens format.
:param doc: "DoclingDocument": :param new_line: str (Default value = "") Deprecated :param xsize: int: (Default value = 500) :param ysize: int: (Default value = 500) :param add_location: bool: (Default value = True) :param add_cell_location: bool: (Default value = True) :param add_cell_text: bool: (Default value = True) :param add_caption: bool: (Default value = True)
export_to_document_tokens(*args, **kwargs)
Export to DocTags format.
export_to_html(
doc: Optional[DoclingDocument] = None,
add_caption: bool = True,
) -> str
Export the table as html.
export_to_markdown(
doc: Optional[DoclingDocument] = None,
) -> str
Export the table as markdown.
export_to_otsl(
doc: DoclingDocument,
add_cell_location: bool = True,
add_cell_text: bool = True,
xsize: int = 500,
ysize: int = 500,
self_closing: bool = False,
**kwargs: Any,
) -> str
Export the table as OTSL.
get_annotations() -> Sequence[BaseAnnotation]
Get the annotations of this TableItem.
get_image(
doc: DoclingDocument, prov_index: int = 0
) -> Optional[Image]
Returns the image corresponding to this FloatingItem.
This function returns the PIL image from self.image if one is available. Otherwise, it uses DocItem.get_image to get an image of this FloatingItem.
In particular, when self.image is None, the function returns None if this FloatingItem has no valid provenance or the doc does not contain a valid image for the required page.
get_location_tokens(
doc: DoclingDocument,
new_line: str = "",
xsize: int = 500,
ysize: int = 500,
self_closing: bool = False,
) -> str
Get the location string for the BaseCell.
Bases: BaseModel
TableCell.
Show JSON schema:
{
"$defs": {
"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"
},
"CoordOrigin": {
"description": "CoordOrigin.",
"enum": [
"TOPLEFT",
"BOTTOMLEFT"
],
"title": "CoordOrigin",
"type": "string"
}
},
"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"
}
Fields:
-
bbox(Optional[BoundingBox]) -
row_span(int) -
col_span(int) -
start_row_offset_idx(int) -
end_row_offset_idx(int) -
start_col_offset_idx(int) -
end_col_offset_idx(int) -
text(str) -
column_header(bool) -
row_header(bool) -
row_section(bool) -
fillable(bool)
Validators:
col_span: int = 1
column_header: bool = False
end_col_offset_idx: int
end_row_offset_idx: int
fillable: bool = False
row_header: bool = False
row_section: bool = False
row_span: int = 1
start_col_offset_idx: int
start_row_offset_idx: int
text: str
from_dict_format(data: Any) -> Any
from_dict_format.
Bases: BaseModel
BaseTableData.
Show JSON schema:
{
"$defs": {
"BoundingBox": {
"description": "BoundingBox.",
"properties": {
"l": {
"title": "L",
"type": "number"
},
"t": {
"title": "T",
"type": "number"
},
"r": {
"title": "R",
"type": "number"
},
"b": {
"title": "B",
"type": "number"
},
"coord_origin": {
"$ref": "#/$defs/CoordOrigin",
"default": "TOPLEFT"
}
},
"required": [
"l",
"t",
"r",
"b"
],
"title": "BoundingBox",
"type": "object"
},
"CoordOrigin": {
"description": "CoordOrigin.",
"enum": [
"TOPLEFT",
"BOTTOMLEFT"
],
"title": "CoordOrigin",
"type": "string"
},
"Orientation": {
"description": "Counter-clockwise rotation of a table on the page, in degrees.\n\nFollows the convention used by PIL/Pillow's ``Image.rotate``: positive\nangles rotate the table counter-clockwise. ``ROT_0`` / ``ROT_180`` keep\nrows running horizontally on the page; ``ROT_90`` / ``ROT_270`` turn\nrows into vertical stripes.",
"enum": [
"rot_0",
"rot_90",
"rot_180",
"rot_270"
],
"title": "Orientation",
"type": "string"
},
"RefItem": {
"description": "RefItem.",
"properties": {
"$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": "#/$defs/RefItem"
}
},
"required": [
"start_row_offset_idx",
"end_row_offset_idx",
"start_col_offset_idx",
"end_col_offset_idx",
"text",
"ref"
],
"title": "RichTableCell",
"type": "object"
},
"TableCell": {
"description": "TableCell.",
"properties": {
"bbox": {
"anyOf": [
{
"$ref": "#/$defs/BoundingBox"
},
{
"type": "null"
}
],
"default": null
},
"row_span": {
"default": 1,
"title": "Row Span",
"type": "integer"
},
"col_span": {
"default": 1,
"title": "Col Span",
"type": "integer"
},
"start_row_offset_idx": {
"title": "Start Row Offset Idx",
"type": "integer"
},
"end_row_offset_idx": {
"title": "End Row Offset Idx",
"type": "integer"
},
"start_col_offset_idx": {
"title": "Start Col Offset Idx",
"type": "integer"
},
"end_col_offset_idx": {
"title": "End Col Offset Idx",
"type": "integer"
},
"text": {
"title": "Text",
"type": "string"
},
"column_header": {
"default": false,
"title": "Column Header",
"type": "boolean"
},
"row_header": {
"default": false,
"title": "Row Header",
"type": "boolean"
},
"row_section": {
"default": false,
"title": "Row Section",
"type": "boolean"
},
"fillable": {
"default": false,
"title": "Fillable",
"type": "boolean"
}
},
"required": [
"start_row_offset_idx",
"end_row_offset_idx",
"start_col_offset_idx",
"end_col_offset_idx",
"text"
],
"title": "TableCell",
"type": "object"
}
},
"description": "BaseTableData.",
"properties": {
"table_cells": {
"default": [],
"items": {
"anyOf": [
{
"$ref": "#/$defs/RichTableCell"
},
{
"$ref": "#/$defs/TableCell"
}
]
},
"title": "Table Cells",
"type": "array"
},
"num_rows": {
"default": 0,
"title": "Num Rows",
"type": "integer"
},
"num_cols": {
"default": 0,
"title": "Num Cols",
"type": "integer"
},
"orientation": {
"$ref": "#/$defs/Orientation",
"default": "rot_0"
}
},
"title": "TableData",
"type": "object"
}
Fields:
-
table_cells(list[AnyTableCell]) -
num_rows(int) -
num_cols(int) -
orientation(Orientation)
num_cols: int = 0
num_rows: int = 0
orientation: Orientation = ROT_0
table_cells: list[AnyTableCell] = []
add_row(row: list[str]) -> None
Add a new row to the table from a list of strings.
:param row: list[str]: A list of strings representing the content of the new row.
:returns: None
add_rows(rows: list[list[str]]) -> None
Add multiple new rows to the table from a list of lists of strings.
:param rows: list[list[str]]: A list of lists, where each inner list represents the content of a new row.
:returns: None
from_regions(
table_bbox: BoundingBox,
rows: list[BoundingBox],
cols: list[BoundingBox],
merges: list[BoundingBox],
row_headers: list[BoundingBox] = [],
col_headers: list[BoundingBox] = [],
row_sections: list[BoundingBox] = [],
) -> Self
Converts regions: rows, columns, merged cells into table_data structure.
Adds semantics for regions of row_headers, col_headers, row_section
get_column_bounding_boxes(
*, minimal: bool = True
) -> dict[int, BoundingBox]
Get the bounding box for each column in the table.
Layout follows the table's orientation field: ROT_0 / ROT_180
keep columns running top-to-bottom on the page; ROT_90 / ROT_270
turn columns into horizontal stripes. This affects both the axis along
which span cells extend a column's bbox and, when minimal=False, the
axis equalized across columns.
Parameters:
-
minimal(bool, default:True) –If True (default), returns the minimal bounding box for each column based on its cells. If False, all columns will have a uniform extent perpendicular to the column direction (t/b for ROT_0/ROT_180, l/r for ROT_90/ROT_270).
Returns:
-
dict[int, BoundingBox]–dict[int, BoundingBox]: A dictionary mapping column indices to their
-
dict[int, BoundingBox]–bounding boxes. Only columns with cells that have bounding boxes are included.
get_row_bounding_boxes(
*, minimal: bool = True
) -> dict[int, BoundingBox]
Get the bounding box for each row in the table.
Layout follows the table's orientation field: ROT_0 / ROT_180
keep rows running left-to-right on the page; ROT_90 / ROT_270
turn rows into vertical stripes. This affects both the axis along which
span cells extend a row's bbox and, when minimal=False, the axis
equalized across rows.
Parameters:
-
minimal(bool, default:True) –If True (default), returns the minimal bounding box for each row based on its cells. If False, all rows will have a uniform extent perpendicular to the row direction (l/r for ROT_0/ROT_180, t/b for ROT_90/ROT_270).
Returns:
-
dict[int, BoundingBox]–dict[int, BoundingBox]: A dictionary mapping row indices to their
-
dict[int, BoundingBox]–bounding boxes. Only rows with cells that have bounding boxes are included.
insert_row(
row_index: int, row: list[str], after: bool = False
) -> None
Insert a new row from a list of strings before/after a specific index in the table.
:param row_index: int: The index at which to insert the new row. (Starting from 0) :param row: list[str]: A list of strings representing the content of the new row. :param after: bool: If True, insert the row after the specified index, otherwise before it. (Default is False)
:returns: None
insert_rows(
row_index: int,
rows: list[list[str]],
after: bool = False,
) -> None
Insert multiple new rows from a list of lists of strings before/after a specific index in the table.
:param row_index: int: The index at which to insert the new rows. (Starting from 0) :param rows: list[list[str]]: A list of lists, where each inner list represents the content of a new row. :param after: bool: If True, insert the rows after the specified index, otherwise before it. (Default is False)
:returns: None
pop_row(
doc: Optional[DoclingDocument] = None,
) -> list[TableCell]
Remove and return the last row from the table.
:returns: list[TableCell]: A list of TableCell objects representing the popped row.
remove_row(
row_index: int, doc: Optional[DoclingDocument] = None
) -> list[TableCell]
Remove a row from the table by its index.
:param row_index: int: The index of the row to remove. (Starting from 0)
:returns: list[TableCell]: A list of TableCell objects representing the removed row.
remove_rows(
indices: list[int],
doc: Optional[DoclingDocument] = None,
) -> list[list[TableCell]]
Remove rows from the table by their indices.
:param indices: list[int]: A list of indices of the rows to remove. (Starting from 0)
:return: list[list[TableCell]]: A list representation of the removed rows as lists of TableCell objects.
Bases: str, Enum
TableCellLabel.
Methods:
-
get_color–Return the RGB color associated with a given label.
Attributes:
-
BODY– -
COLUMN_HEADER– -
ROW_HEADER– -
ROW_SECTION–
BODY = 'body'
COLUMN_HEADER = 'col_header'
ROW_HEADER = 'row_header'
ROW_SECTION = 'row_section'
get_color(label: TableCellLabel) -> tuple[int, int, int]
Return the RGB color associated with a given label.
Bases: FloatingItem
KeyValueItem.
Show JSON schema:
{
"$defs": {
"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"
},
"ContentLayer": {
"description": "ContentLayer.",
"enum": [
"body",
"furniture",
"background",
"invisible",
"notes"
],
"title": "ContentLayer",
"type": "string"
},
"CoordOrigin": {
"description": "CoordOrigin.",
"enum": [
"TOPLEFT",
"BOTTOMLEFT"
],
"title": "CoordOrigin",
"type": "string"
},
"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"
},
"EntitiesMetaField": {
"additionalProperties": true,
"description": "Container for extracted entity mentions.",
"properties": {
"mentions": {
"items": {
"$ref": "#/$defs/EntityMention"
},
"minItems": 1,
"title": "Mentions",
"type": "array"
}
},
"required": [
"mentions"
],
"title": "EntitiesMetaField",
"type": "object"
},
"EntityMention": {
"additionalProperties": true,
"description": "Entity mention extracted from text.",
"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": {
"description": "Normalized text of the entity mention.",
"title": "Text",
"type": "string"
},
"orig": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"default": null,
"description": "Exact source text extracted from the original charspan, analogous to TextItem.orig. This may differ from 'text' when the mention has been normalized.",
"title": "Orig"
},
"label": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"default": null,
"description": "Entity type or category.",
"title": "Label"
},
"charspan": {
"anyOf": [
{
"description": "Character span (0-indexed)",
"maxItems": 2,
"minItems": 2,
"prefixItems": [
{
"type": "integer"
},
{
"type": "integer"
}
],
"type": "array"
},
{
"type": "null"
}
],
"default": null,
"description": "Character span (0-indexed) of the entity mention in the source text.",
"title": "Charspan"
}
},
"required": [
"text"
],
"title": "EntityMention",
"type": "object"
},
"FineRef": {
"description": "Fine-granular reference item that can capture span range info.",
"properties": {
"$ref": {
"pattern": "^#(?:/([\\w-]+)(?:/(\\d+))?)?$",
"title": "$Ref",
"type": "string"
},
"range": {
"anyOf": [
{
"maxItems": 2,
"minItems": 2,
"prefixItems": [
{
"type": "integer"
},
{
"type": "integer"
}
],
"type": "array"
},
{
"type": "null"
}
],
"default": null,
"title": "Range"
}
},
"required": [
"$ref"
],
"title": "FineRef",
"type": "object"
},
"FloatingMeta": {
"additionalProperties": true,
"description": "Metadata model for floating.",
"properties": {
"summary": {
"anyOf": [
{
"$ref": "#/$defs/SummaryMetaField"
},
{
"type": "null"
}
],
"default": null
},
"language": {
"anyOf": [
{
"$ref": "#/$defs/LanguageMetaField"
},
{
"type": "null"
}
],
"default": null
},
"entities": {
"anyOf": [
{
"$ref": "#/$defs/EntitiesMetaField"
},
{
"type": "null"
}
],
"default": null
},
"description": {
"anyOf": [
{
"$ref": "#/$defs/DescriptionMetaField"
},
{
"type": "null"
}
],
"default": null
}
},
"title": "FloatingMeta",
"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"
},
"HumanLanguageLabel": {
"description": "Two-letter human language primary subtags using BCP-47 values.",
"enum": [
"aa",
"ab",
"ae",
"af",
"ak",
"am",
"an",
"ar",
"as",
"av",
"ay",
"az",
"ba",
"be",
"bg",
"bh",
"bi",
"bm",
"bn",
"bo",
"br",
"bs",
"ca",
"ce",
"ch",
"co",
"cr",
"cs",
"cu",
"cv",
"cy",
"da",
"de",
"dv",
"dz",
"ee",
"el",
"en",
"eo",
"es",
"et",
"eu",
"fa",
"ff",
"fi",
"fj",
"fo",
"fr",
"fy",
"ga",
"gd",
"gl",
"gn",
"gu",
"gv",
"ha",
"he",
"hi",
"ho",
"hr",
"ht",
"hu",
"hy",
"hz",
"ia",
"id",
"ie",
"ig",
"ii",
"ik",
"io",
"is",
"it",
"iu",
"ja",
"jv",
"ka",
"kg",
"ki",
"kj",
"kk",
"kl",
"km",
"kn",
"ko",
"kr",
"ks",
"ku",
"kv",
"kw",
"ky",
"la",
"lb",
"lg",
"li",
"ln",
"lo",
"lt",
"lu",
"lv",
"mg",
"mh",
"mi",
"mk",
"ml",
"mn",
"mr",
"ms",
"mt",
"my",
"na",
"nb",
"nd",
"ne",
"ng",
"nl",
"nn",
"no",
"nr",
"nv",
"ny",
"oc",
"oj",
"om",
"or",
"os",
"pa",
"pi",
"pl",
"ps",
"pt",
"qu",
"rm",
"rn",
"ro",
"ru",
"rw",
"sa",
"sc",
"sd",
"se",
"sg",
"sh",
"si",
"sk",
"sl",
"sm",
"sn",
"so",
"sq",
"sr",
"ss",
"st",
"su",
"sv",
"sw",
"ta",
"te",
"tg",
"th",
"ti",
"tk",
"tl",
"tn",
"to",
"tr",
"ts",
"tt",
"tw",
"ty",
"ug",
"uk",
"ur",
"uz",
"ve",
"vi",
"vo",
"wa",
"wo",
"xh",
"yi",
"yo",
"za",
"zh",
"zu"
],
"title": "HumanLanguageLabel",
"type": "string"
},
"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"
},
"LanguageMetaField": {
"additionalProperties": true,
"description": "Detected human language.",
"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"
},
"code": {
"$ref": "#/$defs/HumanLanguageLabel"
}
},
"required": [
"code"
],
"title": "LanguageMetaField",
"type": "object"
},
"ProvenanceItem": {
"description": "Provenance information for elements extracted from a textual document.\n\nA `ProvenanceItem` object acts as a lightweight pointer back into the original\ndocument for an extracted element. It applies to documents with an explicity\nor implicit layout, such as PDF, HTML, docx, or pptx.",
"properties": {
"page_no": {
"description": "Page number",
"title": "Page No",
"type": "integer"
},
"bbox": {
"$ref": "#/$defs/BoundingBox",
"description": "Bounding box"
},
"charspan": {
"description": "Character span (0-indexed)",
"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"
},
"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"
},
"TrackSource": {
"description": "Source metadata for a cue extracted from a media track.\n\nA `TrackSource` instance identifies a cue in a media track (audio, video, subtitles, screen-recording captions,\netc.). A *cue* here refers to any discrete segment that was pulled out of the original asset, e.g., a subtitle\nblock, an audio clip, or a timed marker in a screen-recording.",
"properties": {
"kind": {
"const": "track",
"default": "track",
"description": "Identifies this type of source.",
"title": "Kind",
"type": "string"
},
"start_time": {
"description": "Start time offset of the track cue in seconds",
"examples": [
11.0,
6.5,
5370.0
],
"title": "Start Time",
"type": "number"
},
"end_time": {
"description": "End time offset of the track cue in seconds",
"examples": [
12.0,
8.2,
5370.1
],
"title": "End Time",
"type": "number"
},
"identifier": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"default": null,
"description": "An identifier of the cue",
"examples": [
"test",
"123",
"b72d946"
],
"title": "Identifier"
},
"voice": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"default": null,
"description": "The name of the voice in this track (the speaker)",
"examples": [
"John",
"Mary",
"Speaker 1"
],
"title": "Voice"
}
},
"required": [
"start_time",
"end_time"
],
"title": "TrackSource",
"type": "object"
}
},
"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": "#/$defs/ProvenanceItem"
},
"title": "Prov",
"type": "array"
},
"source": {
"default": [],
"description": "The provenance of this document item. Currently, it is only used for media track provenance.",
"items": {
"discriminator": {
"mapping": {
"track": "#/$defs/TrackSource"
},
"propertyName": "kind"
},
"oneOf": [
{
"$ref": "#/$defs/TrackSource"
}
]
},
"title": "Source",
"type": "array"
},
"comments": {
"default": [],
"items": {
"$ref": "#/$defs/FineRef"
},
"title": "Comments",
"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"
}
Fields:
-
self_ref(str) -
parent(Optional[RefItem]) -
children(list[RefItem]) -
content_layer(ContentLayer) -
meta(Optional[FloatingMeta]) -
prov(list[ProvenanceItem]) -
source(list[SourceType]) -
comments(list[FineRef]) -
captions(list[RefItem]) -
references(list[RefItem]) -
footnotes(list[RefItem]) -
image(Optional[ImageRef]) -
label(Literal[KEY_VALUE_REGION]) -
graph(GraphData)
comments: list[FineRef] = []
content_layer: ContentLayer = BODY
graph: GraphData
meta: Optional[FloatingMeta] = None
model_config = ConfigDict(extra='forbid')
self_ref: str
source: list[SourceType]
The provenance of this document item. Currently, it is only used for media track provenance.
export_to_document_tokens(
doc: DoclingDocument,
new_line: str = "",
xsize: int = 500,
ysize: int = 500,
add_location: bool = True,
add_content: bool = True,
)
Export key value item to document tokens format.
:param doc: "DoclingDocument": :param new_line: str (Default value = "") Deprecated :param xsize: int: (Default value = 500) :param ysize: int: (Default value = 500) :param add_location: bool: (Default value = True) :param add_content: bool: (Default value = True)
get_annotations() -> Sequence[BaseAnnotation]
Get the annotations of this DocItem.
get_image(
doc: DoclingDocument, prov_index: int = 0
) -> Optional[Image]
Returns the image corresponding to this FloatingItem.
This function returns the PIL image from self.image if one is available. Otherwise, it uses DocItem.get_image to get an image of this FloatingItem.
In particular, when self.image is None, the function returns None if this FloatingItem has no valid provenance or the doc does not contain a valid image for the required page.
get_location_tokens(
doc: DoclingDocument,
new_line: str = "",
xsize: int = 500,
ysize: int = 500,
self_closing: bool = False,
) -> str
Get the location string for the BaseCell.
Bases: TextItem
SectionItem.
Show JSON schema:
{
"$defs": {
"BaseMeta": {
"additionalProperties": true,
"description": "Base class for metadata.",
"properties": {
"summary": {
"anyOf": [
{
"$ref": "#/$defs/SummaryMetaField"
},
{
"type": "null"
}
],
"default": null
},
"language": {
"anyOf": [
{
"$ref": "#/$defs/LanguageMetaField"
},
{
"type": "null"
}
],
"default": null
},
"entities": {
"anyOf": [
{
"$ref": "#/$defs/EntitiesMetaField"
},
{
"type": "null"
}
],
"default": null
}
},
"title": "BaseMeta",
"type": "object"
},
"BoundingBox": {
"description": "BoundingBox.",
"properties": {
"l": {
"title": "L",
"type": "number"
},
"t": {
"title": "T",
"type": "number"
},
"r": {
"title": "R",
"type": "number"
},
"b": {
"title": "B",
"type": "number"
},
"coord_origin": {
"$ref": "#/$defs/CoordOrigin",
"default": "TOPLEFT"
}
},
"required": [
"l",
"t",
"r",
"b"
],
"title": "BoundingBox",
"type": "object"
},
"ContentLayer": {
"description": "ContentLayer.",
"enum": [
"body",
"furniture",
"background",
"invisible",
"notes"
],
"title": "ContentLayer",
"type": "string"
},
"CoordOrigin": {
"description": "CoordOrigin.",
"enum": [
"TOPLEFT",
"BOTTOMLEFT"
],
"title": "CoordOrigin",
"type": "string"
},
"EntitiesMetaField": {
"additionalProperties": true,
"description": "Container for extracted entity mentions.",
"properties": {
"mentions": {
"items": {
"$ref": "#/$defs/EntityMention"
},
"minItems": 1,
"title": "Mentions",
"type": "array"
}
},
"required": [
"mentions"
],
"title": "EntitiesMetaField",
"type": "object"
},
"EntityMention": {
"additionalProperties": true,
"description": "Entity mention extracted from text.",
"properties": {
"confidence": {
"anyOf": [
{
"maximum": 1,
"minimum": 0,
"type": "number"
},
{
"type": "null"
}
],
"default": null,
"description": "The confidence of the prediction.",
"examples": [
0.9,
0.42
],
"title": "Confidence"
},
"created_by": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"default": null,
"description": "The origin of the prediction.",
"examples": [
"ibm-granite/granite-docling-258M"
],
"title": "Created By"
},
"text": {
"description": "Normalized text of the entity mention.",
"title": "Text",
"type": "string"
},
"orig": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"default": null,
"description": "Exact source text extracted from the original charspan, analogous to TextItem.orig. This may differ from 'text' when the mention has been normalized.",
"title": "Orig"
},
"label": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"default": null,
"description": "Entity type or category.",
"title": "Label"
},
"charspan": {
"anyOf": [
{
"description": "Character span (0-indexed)",
"maxItems": 2,
"minItems": 2,
"prefixItems": [
{
"type": "integer"
},
{
"type": "integer"
}
],
"type": "array"
},
{
"type": "null"
}
],
"default": null,
"description": "Character span (0-indexed) of the entity mention in the source text.",
"title": "Charspan"
}
},
"required": [
"text"
],
"title": "EntityMention",
"type": "object"
},
"FineRef": {
"description": "Fine-granular reference item that can capture span range info.",
"properties": {
"$ref": {
"pattern": "^#(?:/([\\w-]+)(?:/(\\d+))?)?$",
"title": "$Ref",
"type": "string"
},
"range": {
"anyOf": [
{
"maxItems": 2,
"minItems": 2,
"prefixItems": [
{
"type": "integer"
},
{
"type": "integer"
}
],
"type": "array"
},
{
"type": "null"
}
],
"default": null,
"title": "Range"
}
},
"required": [
"$ref"
],
"title": "FineRef",
"type": "object"
},
"Formatting": {
"description": "Formatting.",
"properties": {
"bold": {
"default": false,
"title": "Bold",
"type": "boolean"
},
"italic": {
"default": false,
"title": "Italic",
"type": "boolean"
},
"underline": {
"default": false,
"title": "Underline",
"type": "boolean"
},
"strikethrough": {
"default": false,
"title": "Strikethrough",
"type": "boolean"
},
"script": {
"$ref": "#/$defs/Script",
"default": "baseline"
}
},
"title": "Formatting",
"type": "object"
},
"HumanLanguageLabel": {
"description": "Two-letter human language primary subtags using BCP-47 values.",
"enum": [
"aa",
"ab",
"ae",
"af",
"ak",
"am",
"an",
"ar",
"as",
"av",
"ay",
"az",
"ba",
"be",
"bg",
"bh",
"bi",
"bm",
"bn",
"bo",
"br",
"bs",
"ca",
"ce",
"ch",
"co",
"cr",
"cs",
"cu",
"cv",
"cy",
"da",
"de",
"dv",
"dz",
"ee",
"el",
"en",
"eo",
"es",
"et",
"eu",
"fa",
"ff",
"fi",
"fj",
"fo",
"fr",
"fy",
"ga",
"gd",
"gl",
"gn",
"gu",
"gv",
"ha",
"he",
"hi",
"ho",
"hr",
"ht",
"hu",
"hy",
"hz",
"ia",
"id",
"ie",
"ig",
"ii",
"ik",
"io",
"is",
"it",
"iu",
"ja",
"jv",
"ka",
"kg",
"ki",
"kj",
"kk",
"kl",
"km",
"kn",
"ko",
"kr",
"ks",
"ku",
"kv",
"kw",
"ky",
"la",
"lb",
"lg",
"li",
"ln",
"lo",
"lt",
"lu",
"lv",
"mg",
"mh",
"mi",
"mk",
"ml",
"mn",
"mr",
"ms",
"mt",
"my",
"na",
"nb",
"nd",
"ne",
"ng",
"nl",
"nn",
"no",
"nr",
"nv",
"ny",
"oc",
"oj",
"om",
"or",
"os",
"pa",
"pi",
"pl",
"ps",
"pt",
"qu",
"rm",
"rn",
"ro",
"ru",
"rw",
"sa",
"sc",
"sd",
"se",
"sg",
"sh",
"si",
"sk",
"sl",
"sm",
"sn",
"so",
"sq",
"sr",
"ss",
"st",
"su",
"sv",
"sw",
"ta",
"te",
"tg",
"th",
"ti",
"tk",
"tl",
"tn",
"to",
"tr",
"ts",
"tt",
"tw",
"ty",
"ug",
"uk",
"ur",
"uz",
"ve",
"vi",
"vo",
"wa",
"wo",
"xh",
"yi",
"yo",
"za",
"zh",
"zu"
],
"title": "HumanLanguageLabel",
"type": "string"
},
"LanguageMetaField": {
"additionalProperties": true,
"description": "Detected human language.",
"properties": {
"confidence": {
"anyOf": [
{
"maximum": 1,
"minimum": 0,
"type": "number"
},
{
"type": "null"
}
],
"default": null,
"description": "The confidence of the prediction.",
"examples": [
0.9,
0.42
],
"title": "Confidence"
},
"created_by": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"default": null,
"description": "The origin of the prediction.",
"examples": [
"ibm-granite/granite-docling-258M"
],
"title": "Created By"
},
"code": {
"$ref": "#/$defs/HumanLanguageLabel"
}
},
"required": [
"code"
],
"title": "LanguageMetaField",
"type": "object"
},
"ProvenanceItem": {
"description": "Provenance information for elements extracted from a textual document.\n\nA `ProvenanceItem` object acts as a lightweight pointer back into the original\ndocument for an extracted element. It applies to documents with an explicity\nor implicit layout, such as PDF, HTML, docx, or pptx.",
"properties": {
"page_no": {
"description": "Page number",
"title": "Page No",
"type": "integer"
},
"bbox": {
"$ref": "#/$defs/BoundingBox",
"description": "Bounding box"
},
"charspan": {
"description": "Character span (0-indexed)",
"maxItems": 2,
"minItems": 2,
"prefixItems": [
{
"type": "integer"
},
{
"type": "integer"
}
],
"title": "Charspan",
"type": "array"
}
},
"required": [
"page_no",
"bbox",
"charspan"
],
"title": "ProvenanceItem",
"type": "object"
},
"RefItem": {
"description": "RefItem.",
"properties": {
"$ref": {
"pattern": "^#(?:/([\\w-]+)(?:/(\\d+))?)?$",
"title": "$Ref",
"type": "string"
}
},
"required": [
"$ref"
],
"title": "RefItem",
"type": "object"
},
"Script": {
"description": "Text script position.",
"enum": [
"baseline",
"sub",
"super"
],
"title": "Script",
"type": "string"
},
"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"
},
"TrackSource": {
"description": "Source metadata for a cue extracted from a media track.\n\nA `TrackSource` instance identifies a cue in a media track (audio, video, subtitles, screen-recording captions,\netc.). A *cue* here refers to any discrete segment that was pulled out of the original asset, e.g., a subtitle\nblock, an audio clip, or a timed marker in a screen-recording.",
"properties": {
"kind": {
"const": "track",
"default": "track",
"description": "Identifies this type of source.",
"title": "Kind",
"type": "string"
},
"start_time": {
"description": "Start time offset of the track cue in seconds",
"examples": [
11.0,
6.5,
5370.0
],
"title": "Start Time",
"type": "number"
},
"end_time": {
"description": "End time offset of the track cue in seconds",
"examples": [
12.0,
8.2,
5370.1
],
"title": "End Time",
"type": "number"
},
"identifier": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"default": null,
"description": "An identifier of the cue",
"examples": [
"test",
"123",
"b72d946"
],
"title": "Identifier"
},
"voice": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"default": null,
"description": "The name of the voice in this track (the speaker)",
"examples": [
"John",
"Mary",
"Speaker 1"
],
"title": "Voice"
}
},
"required": [
"start_time",
"end_time"
],
"title": "TrackSource",
"type": "object"
}
},
"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"
},
"source": {
"default": [],
"description": "The provenance of this document item. Currently, it is only used for media track provenance.",
"items": {
"discriminator": {
"mapping": {
"track": "#/$defs/TrackSource"
},
"propertyName": "kind"
},
"oneOf": [
{
"$ref": "#/$defs/TrackSource"
}
]
},
"title": "Source",
"type": "array"
},
"comments": {
"default": [],
"items": {
"$ref": "#/$defs/FineRef"
},
"title": "Comments",
"type": "array"
},
"orig": {
"title": "Orig",
"type": "string"
},
"text": {
"title": "Text",
"type": "string"
},
"formatting": {
"anyOf": [
{
"$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"
}
Fields:
-
self_ref(str) -
parent(Optional[RefItem]) -
children(list[RefItem]) -
content_layer(ContentLayer) -
meta(Optional[BaseMeta]) -
prov(list[ProvenanceItem]) -
source(list[SourceType]) -
comments(list[FineRef]) -
orig(str) -
text(str) -
formatting(Optional[Formatting]) -
hyperlink(Optional[Union[AnyUrl, Path]]) -
label(Literal[SECTION_HEADER]) -
level(LevelNumber)
comments: list[FineRef] = []
content_layer: ContentLayer = BODY
formatting: Optional[Formatting] = None
hyperlink: Optional[Union[AnyUrl, Path]] = None
level: LevelNumber = 1
meta: Optional[BaseMeta] = None
model_config = ConfigDict(extra='forbid')
orig: str
self_ref: str
source: list[SourceType]
The provenance of this document item. Currently, it is only used for media track provenance.
text: str
export_to_doctags(
doc: DoclingDocument,
new_line: str = "",
xsize: int = 500,
ysize: int = 500,
add_location: bool = True,
add_content: bool = True,
)
Export text element to document tokens format.
:param doc: "DoclingDocument": :param new_line: str (Default value = "") Deprecated :param xsize: int: (Default value = 500) :param ysize: int: (Default value = 500) :param add_location: bool: (Default value = True) :param add_content: bool: (Default value = True)
export_to_document_tokens(*args, **kwargs)
Export to DocTags format.
get_annotations() -> Sequence[BaseAnnotation]
Get the annotations of this DocItem.
get_image(
doc: DoclingDocument, prov_index: int = 0
) -> Optional[Image]
Returns the image of this DocItem.
The function returns None if this DocItem has no valid provenance or if a valid image of the page containing this DocItem is not available in doc.
get_location_tokens(
doc: DoclingDocument,
new_line: str = "",
xsize: int = 500,
ysize: int = 500,
self_closing: bool = False,
) -> str
Get the location string for the BaseCell.
Bases: FloatingItem
PictureItem.
Show JSON schema:
{
"$defs": {
"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"
},
"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"
},
"CodeLanguageLabel": {
"description": "CodeLanguageLabel.",
"enum": [
"Ada",
"Awk",
"Bash",
"bc",
"C",
"C#",
"C++",
"CMake",
"COBOL",
"CSS",
"Ceylon",
"Clojure",
"Crystal",
"Cuda",
"Cython",
"D",
"Dart",
"dc",
"Dockerfile",
"DocLang",
"Elixir",
"Erlang",
"FORTRAN",
"Forth",
"Go",
"HTML",
"Haskell",
"Haxe",
"Java",
"JavaScript",
"JSON",
"Julia",
"Kotlin",
"Latex",
"Lisp",
"Lua",
"Matlab",
"MoonScript",
"Nim",
"OCaml",
"ObjectiveC",
"Octave",
"PHP",
"Pascal",
"Perl",
"Prolog",
"Python",
"Racket",
"Ruby",
"Rust",
"SML",
"SQL",
"Scala",
"Scheme",
"Swift",
"Tikz",
"TypeScript",
"unknown",
"VisualBasic",
"XML",
"YAML"
],
"title": "CodeLanguageLabel",
"type": "string"
},
"CodeMetaField": {
"additionalProperties": true,
"description": "Code representation for the respective item.",
"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"
},
"language": {
"anyOf": [
{
"$ref": "#/$defs/CodeLanguageLabel"
},
{
"type": "null"
}
],
"default": null
}
},
"required": [
"text"
],
"title": "CodeMetaField",
"type": "object"
},
"ContentLayer": {
"description": "ContentLayer.",
"enum": [
"body",
"furniture",
"background",
"invisible",
"notes"
],
"title": "ContentLayer",
"type": "string"
},
"CoordOrigin": {
"description": "CoordOrigin.",
"enum": [
"TOPLEFT",
"BOTTOMLEFT"
],
"title": "CoordOrigin",
"type": "string"
},
"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"
},
"EntitiesMetaField": {
"additionalProperties": true,
"description": "Container for extracted entity mentions.",
"properties": {
"mentions": {
"items": {
"$ref": "#/$defs/EntityMention"
},
"minItems": 1,
"title": "Mentions",
"type": "array"
}
},
"required": [
"mentions"
],
"title": "EntitiesMetaField",
"type": "object"
},
"EntityMention": {
"additionalProperties": true,
"description": "Entity mention extracted from text.",
"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": {
"description": "Normalized text of the entity mention.",
"title": "Text",
"type": "string"
},
"orig": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"default": null,
"description": "Exact source text extracted from the original charspan, analogous to TextItem.orig. This may differ from 'text' when the mention has been normalized.",
"title": "Orig"
},
"label": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"default": null,
"description": "Entity type or category.",
"title": "Label"
},
"charspan": {
"anyOf": [
{
"description": "Character span (0-indexed)",
"maxItems": 2,
"minItems": 2,
"prefixItems": [
{
"type": "integer"
},
{
"type": "integer"
}
],
"type": "array"
},
{
"type": "null"
}
],
"default": null,
"description": "Character span (0-indexed) of the entity mention in the source text.",
"title": "Charspan"
}
},
"required": [
"text"
],
"title": "EntityMention",
"type": "object"
},
"FineRef": {
"description": "Fine-granular reference item that can capture span range info.",
"properties": {
"$ref": {
"pattern": "^#(?:/([\\w-]+)(?:/(\\d+))?)?$",
"title": "$Ref",
"type": "string"
},
"range": {
"anyOf": [
{
"maxItems": 2,
"minItems": 2,
"prefixItems": [
{
"type": "integer"
},
{
"type": "integer"
}
],
"type": "array"
},
{
"type": "null"
}
],
"default": null,
"title": "Range"
}
},
"required": [
"$ref"
],
"title": "FineRef",
"type": "object"
},
"HumanLanguageLabel": {
"description": "Two-letter human language primary subtags using BCP-47 values.",
"enum": [
"aa",
"ab",
"ae",
"af",
"ak",
"am",
"an",
"ar",
"as",
"av",
"ay",
"az",
"ba",
"be",
"bg",
"bh",
"bi",
"bm",
"bn",
"bo",
"br",
"bs",
"ca",
"ce",
"ch",
"co",
"cr",
"cs",
"cu",
"cv",
"cy",
"da",
"de",
"dv",
"dz",
"ee",
"el",
"en",
"eo",
"es",
"et",
"eu",
"fa",
"ff",
"fi",
"fj",
"fo",
"fr",
"fy",
"ga",
"gd",
"gl",
"gn",
"gu",
"gv",
"ha",
"he",
"hi",
"ho",
"hr",
"ht",
"hu",
"hy",
"hz",
"ia",
"id",
"ie",
"ig",
"ii",
"ik",
"io",
"is",
"it",
"iu",
"ja",
"jv",
"ka",
"kg",
"ki",
"kj",
"kk",
"kl",
"km",
"kn",
"ko",
"kr",
"ks",
"ku",
"kv",
"kw",
"ky",
"la",
"lb",
"lg",
"li",
"ln",
"lo",
"lt",
"lu",
"lv",
"mg",
"mh",
"mi",
"mk",
"ml",
"mn",
"mr",
"ms",
"mt",
"my",
"na",
"nb",
"nd",
"ne",
"ng",
"nl",
"nn",
"no",
"nr",
"nv",
"ny",
"oc",
"oj",
"om",
"or",
"os",
"pa",
"pi",
"pl",
"ps",
"pt",
"qu",
"rm",
"rn",
"ro",
"ru",
"rw",
"sa",
"sc",
"sd",
"se",
"sg",
"sh",
"si",
"sk",
"sl",
"sm",
"sn",
"so",
"sq",
"sr",
"ss",
"st",
"su",
"sv",
"sw",
"ta",
"te",
"tg",
"th",
"ti",
"tk",
"tl",
"tn",
"to",
"tr",
"ts",
"tt",
"tw",
"ty",
"ug",
"uk",
"ur",
"uz",
"ve",
"vi",
"vo",
"wa",
"wo",
"xh",
"yi",
"yo",
"za",
"zh",
"zu"
],
"title": "HumanLanguageLabel",
"type": "string"
},
"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"
},
"LanguageMetaField": {
"additionalProperties": true,
"description": "Detected human language.",
"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"
},
"code": {
"$ref": "#/$defs/HumanLanguageLabel"
}
},
"required": [
"code"
],
"title": "LanguageMetaField",
"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"
},
"Orientation": {
"description": "Counter-clockwise rotation of a table on the page, in degrees.\n\nFollows the convention used by PIL/Pillow's ``Image.rotate``: positive\nangles rotate the table counter-clockwise. ``ROT_0`` / ``ROT_180`` keep\nrows running horizontally on the page; ``ROT_90`` / ``ROT_270`` turn\nrows into vertical stripes.",
"enum": [
"rot_0",
"rot_90",
"rot_180",
"rot_270"
],
"title": "Orientation",
"type": "string"
},
"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"
},
"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
},
"language": {
"anyOf": [
{
"$ref": "#/$defs/LanguageMetaField"
},
{
"type": "null"
}
],
"default": null
},
"entities": {
"anyOf": [
{
"$ref": "#/$defs/EntitiesMetaField"
},
{
"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
},
"code": {
"anyOf": [
{
"$ref": "#/$defs/CodeMetaField"
},
{
"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"
},
"ProvenanceItem": {
"description": "Provenance information for elements extracted from a textual document.\n\nA `ProvenanceItem` object acts as a lightweight pointer back into the original\ndocument for an extracted element. It applies to documents with an explicity\nor implicit layout, such as PDF, HTML, docx, or pptx.",
"properties": {
"page_no": {
"description": "Page number",
"title": "Page No",
"type": "integer"
},
"bbox": {
"$ref": "#/$defs/BoundingBox",
"description": "Bounding box"
},
"charspan": {
"description": "Character span (0-indexed)",
"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"
},
"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"
},
"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"
},
"orientation": {
"$ref": "#/$defs/Orientation",
"default": "rot_0"
}
},
"title": "TableData",
"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"
},
"TrackSource": {
"description": "Source metadata for a cue extracted from a media track.\n\nA `TrackSource` instance identifies a cue in a media track (audio, video, subtitles, screen-recording captions,\netc.). A *cue* here refers to any discrete segment that was pulled out of the original asset, e.g., a subtitle\nblock, an audio clip, or a timed marker in a screen-recording.",
"properties": {
"kind": {
"const": "track",
"default": "track",
"description": "Identifies this type of source.",
"title": "Kind",
"type": "string"
},
"start_time": {
"description": "Start time offset of the track cue in seconds",
"examples": [
11.0,
6.5,
5370.0
],
"title": "Start Time",
"type": "number"
},
"end_time": {
"description": "End time offset of the track cue in seconds",
"examples": [
12.0,
8.2,
5370.1
],
"title": "End Time",
"type": "number"
},
"identifier": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"default": null,
"description": "An identifier of the cue",
"examples": [
"test",
"123",
"b72d946"
],
"title": "Identifier"
},
"voice": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"default": null,
"description": "The name of the voice in this track (the speaker)",
"examples": [
"John",
"Mary",
"Speaker 1"
],
"title": "Voice"
}
},
"required": [
"start_time",
"end_time"
],
"title": "TrackSource",
"type": "object"
}
},
"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": "#/$defs/ProvenanceItem"
},
"title": "Prov",
"type": "array"
},
"source": {
"default": [],
"description": "The provenance of this document item. Currently, it is only used for media track provenance.",
"items": {
"discriminator": {
"mapping": {
"track": "#/$defs/TrackSource"
},
"propertyName": "kind"
},
"oneOf": [
{
"$ref": "#/$defs/TrackSource"
}
]
},
"title": "Source",
"type": "array"
},
"comments": {
"default": [],
"items": {
"$ref": "#/$defs/FineRef"
},
"title": "Comments",
"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"
}
Fields:
-
self_ref(str) -
parent(Optional[RefItem]) -
children(list[RefItem]) -
content_layer(ContentLayer) -
prov(list[ProvenanceItem]) -
source(list[SourceType]) -
comments(list[FineRef]) -
captions(list[RefItem]) -
references(list[RefItem]) -
footnotes(list[RefItem]) -
image(Optional[ImageRef]) -
label(Literal[PICTURE, CHART]) -
meta(Optional[PictureMeta]) -
annotations(list[PictureDataType])
Validators:
-
_migrate_annotations_to_meta
annotations: list[PictureDataType] = []
comments: list[FineRef] = []
content_layer: ContentLayer = BODY
meta: Optional[PictureMeta] = None
model_config = ConfigDict(extra='forbid')
self_ref: str
source: list[SourceType]
The provenance of this document item. Currently, it is only used for media track provenance.
export_to_doctags(
doc: DoclingDocument,
new_line: str = "",
xsize: int = 500,
ysize: int = 500,
add_location: bool = True,
add_caption: bool = True,
add_content: bool = True,
)
Export picture to document tokens format.
:param doc: "DoclingDocument": :param new_line: str (Default value = "") Deprecated :param xsize: int: (Default value = 500) :param ysize: int: (Default value = 500) :param add_location: bool: (Default value = True) :param add_caption: bool: (Default value = True) :param add_content: bool: (Default value = True) :param # not used at the moment
export_to_document_tokens(*args, **kwargs)
Export to DocTags format.
export_to_html(
doc: DoclingDocument,
add_caption: bool = True,
image_mode: ImageRefMode = PLACEHOLDER,
) -> str
Export picture to HTML format.
export_to_markdown(
doc: DoclingDocument,
add_caption: bool = True,
image_mode: ImageRefMode = EMBEDDED,
image_placeholder: str = "<!-- image -->",
) -> str
Export picture to Markdown format.
get_annotations() -> Sequence[BaseAnnotation]
Get the annotations of this PictureItem.
get_image(
doc: DoclingDocument, prov_index: int = 0
) -> Optional[Image]
Returns the image corresponding to this FloatingItem.
This function returns the PIL image from self.image if one is available. Otherwise, it uses DocItem.get_image to get an image of this FloatingItem.
In particular, when self.image is None, the function returns None if this FloatingItem has no valid provenance or the doc does not contain a valid image for the required page.
get_location_tokens(
doc: DoclingDocument,
new_line: str = "",
xsize: int = 500,
ysize: int = 500,
self_closing: bool = False,
) -> str
Get the location string for the BaseCell.
Bases: BaseModel
ImageRef.
Show JSON schema:
{
"$defs": {
"Size": {
"description": "Size.",
"properties": {
"width": {
"default": 0.0,
"title": "Width",
"type": "number"
},
"height": {
"default": 0.0,
"title": "Height",
"type": "number"
}
},
"title": "Size",
"type": "object"
}
},
"description": "ImageRef.",
"properties": {
"mimetype": {
"title": "Mimetype",
"type": "string"
},
"dpi": {
"title": "Dpi",
"type": "integer"
},
"size": {
"$ref": "#/$defs/Size"
},
"uri": {
"anyOf": [
{
"format": "uri",
"minLength": 1,
"type": "string"
},
{
"format": "path",
"type": "string"
}
],
"title": "Uri"
}
},
"required": [
"mimetype",
"dpi",
"size",
"uri"
],
"title": "ImageRef",
"type": "object"
}
Fields:
Validators:
dpi: int
mimetype: str
pil_image: Optional[Image]
Return the PIL Image.
uri: Union[AnyUrl, Path]
from_pil(image: Image, dpi: int) -> Self
Construct ImageRef from a PIL Image.
validate_mimetype(v)
validate_mimetype.
Bases: BaseModel
PictureClassificationData.
Show JSON schema:
{
"description": "PictureClassificationData.",
"properties": {
"class_name": {
"title": "Class Name",
"type": "string"
},
"confidence": {
"title": "Confidence",
"type": "number"
}
},
"required": [
"class_name",
"confidence"
],
"title": "PictureClassificationClass",
"type": "object"
}
Fields:
-
class_name(str) -
confidence(float)
class_name: str
confidence: float
Bases: BaseAnnotation
PictureClassificationData.
Show JSON schema:
{
"$defs": {
"PictureClassificationClass": {
"description": "PictureClassificationData.",
"properties": {
"class_name": {
"title": "Class Name",
"type": "string"
},
"confidence": {
"title": "Confidence",
"type": "number"
}
},
"required": [
"class_name",
"confidence"
],
"title": "PictureClassificationClass",
"type": "object"
}
},
"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"
}
Fields:
-
kind(Literal['classification']) -
provenance(str) -
predicted_classes(list[PictureClassificationClass])
kind: Literal['classification'] = 'classification'
provenance: str
Bases: BaseModel
RefItem.
Show JSON schema:
{
"description": "RefItem.",
"properties": {
"$ref": {
"pattern": "^#(?:/([\\w-]+)(?:/(\\d+))?)?$",
"title": "$Ref",
"type": "string"
}
},
"required": [
"$ref"
],
"title": "RefItem",
"type": "object"
}
Config:
populate_by_name:True
Fields:
-
cref(str)
cref: str
model_config = ConfigDict(populate_by_name=True)
get_ref()
get_ref.
Bases: BaseModel
BoundingBox.
Show JSON schema:
{
"$defs": {
"CoordOrigin": {
"description": "CoordOrigin.",
"enum": [
"TOPLEFT",
"BOTTOMLEFT"
],
"title": "CoordOrigin",
"type": "string"
}
},
"description": "BoundingBox.",
"properties": {
"l": {
"title": "L",
"type": "number"
},
"t": {
"title": "T",
"type": "number"
},
"r": {
"title": "R",
"type": "number"
},
"b": {
"title": "B",
"type": "number"
},
"coord_origin": {
"$ref": "#/$defs/CoordOrigin",
"default": "TOPLEFT"
}
},
"required": [
"l",
"t",
"r",
"b"
],
"title": "BoundingBox",
"type": "object"
}
Fields:
-
l(float) -
t(float) -
r(float) -
b(float) -
coord_origin(CoordOrigin)
b: float
height
height.
l: float
r: float
t: float
width
width.
area() -> float
area.
as_tuple() -> tuple[float, float, float, float]
as_tuple.
enclosing_bbox(boxes: list[BoundingBox]) -> BoundingBox
Create a bounding box that covers all of the given boxes.
from_tuple(coord: tuple[float, ...], origin: CoordOrigin)
from_tuple.
:param coord: tuple[float: :param ...]: :param origin: CoordOrigin:
get_intersection_bbox(
other: BoundingBox,
) -> Optional[BoundingBox]
Return the intersection bounding box with another bounding box or None when disjoint.
intersection_area_with(other: BoundingBox) -> float
Calculate the intersection area with another bounding box.
intersection_over_self(
other: BoundingBox, eps: float = 1e-06
) -> float
intersection_over_self.
intersection_over_union(
other: BoundingBox, eps: float = 1e-06
) -> float
intersection_over_union.
is_horizontally_connected(
elem_i: BoundingBox, elem_j: BoundingBox
) -> bool
is_horizontally_connected.
is_strictly_above(
other: BoundingBox, eps: float = 0.001
) -> bool
is_strictly_above.
is_strictly_left_of(
other: BoundingBox, eps: float = 0.001
) -> bool
is_strictly_left_of.
overlaps_horizontally(other: BoundingBox) -> bool
Check if two bounding boxes overlap horizontally.
overlaps_vertically(other: BoundingBox) -> bool
Check if two bounding boxes overlap vertically.
overlaps_vertically_with_iou(
other: BoundingBox, iou: float
) -> bool
overlaps_y_with_iou.
resize_by_scale(x_scale: float, y_scale: float)
resize_by_scale.
scaled(scale: float)
scaled.
to_bottom_left_origin(page_height: float) -> BoundingBox
to_bottom_left_origin.
:param page_height:
to_top_left_origin(page_height: float) -> BoundingBox
to_top_left_origin.
:param page_height:
union_area_with(other: BoundingBox) -> float
Calculates the union area with another bounding box.
x_overlap_with(other: BoundingBox) -> float
Calculates the horizontal overlap with another bounding box.
x_union_with(other: BoundingBox) -> float
Calculates the horizontal union dimension with another bounding box.
y_overlap_with(other: BoundingBox) -> float
Calculates the vertical overlap with another bounding box, respecting coordinate origin.
y_union_with(other: BoundingBox) -> float
Calculates the vertical union dimension with another bounding box, respecting coordinate origin.
Bases: str, Enum
CoordOrigin.
Attributes:
-
BOTTOMLEFT– -
TOPLEFT–
BOTTOMLEFT = 'BOTTOMLEFT'
TOPLEFT = 'TOPLEFT'
Bases: str, Enum
ImageRefMode.
Attributes:
-
EMBEDDED– -
PLACEHOLDER– -
REFERENCED–
EMBEDDED = 'embedded'
PLACEHOLDER = 'placeholder'
REFERENCED = 'referenced'
Bases: BaseModel
Size.
Show JSON schema:
{
"description": "Size.",
"properties": {
"width": {
"default": 0.0,
"title": "Width",
"type": "number"
},
"height": {
"default": 0.0,
"title": "Height",
"type": "number"
}
},
"title": "Size",
"type": "object"
}
Fields:
height: float = 0.0
width: float = 0.0
as_tuple()
as_tuple.