Files
docling-core/docs/DoclingDocument.json

2460 lines
56 KiB
JSON

{
"$defs": {
"BoundingBox": {
"description": "BoundingBox.",
"properties": {
"l": {
"title": "L",
"type": "number"
},
"t": {
"title": "T",
"type": "number"
},
"r": {
"title": "R",
"type": "number"
},
"b": {
"title": "B",
"type": "number"
},
"coord_origin": {
"$ref": "#/$defs/CoordOrigin",
"default": "TOPLEFT"
}
},
"required": [
"l",
"t",
"r",
"b"
],
"title": "BoundingBox",
"type": "object"
},
"BoundingRectangle": {
"description": "Model representing a rectangular boundary with four corner points.",
"properties": {
"r_x0": {
"title": "R X0",
"type": "number"
},
"r_y0": {
"title": "R Y0",
"type": "number"
},
"r_x1": {
"title": "R X1",
"type": "number"
},
"r_y1": {
"title": "R Y1",
"type": "number"
},
"r_x2": {
"title": "R X2",
"type": "number"
},
"r_y2": {
"title": "R Y2",
"type": "number"
},
"r_x3": {
"title": "R X3",
"type": "number"
},
"r_y3": {
"title": "R Y3",
"type": "number"
},
"coord_origin": {
"$ref": "#/$defs/CoordOrigin",
"default": "BOTTOMLEFT"
}
},
"required": [
"r_x0",
"r_y0",
"r_x1",
"r_y1",
"r_x2",
"r_y2",
"r_x3",
"r_y3"
],
"title": "BoundingRectangle",
"type": "object"
},
"ChartBar": {
"description": "Represents a bar in a bar chart.\n\nAttributes:\n label (str): The label for the bar.\n values (float): The value associated with the bar.",
"properties": {
"label": {
"title": "Label",
"type": "string"
},
"values": {
"title": "Values",
"type": "number"
}
},
"required": [
"label",
"values"
],
"title": "ChartBar",
"type": "object"
},
"ChartLine": {
"description": "Represents a line in a line chart.\n\nAttributes:\n label (str): The label for the line.\n values (List[Tuple[float, float]]): A list of (x, y) coordinate pairs\n representing the line's data points.",
"properties": {
"label": {
"title": "Label",
"type": "string"
},
"values": {
"items": {
"maxItems": 2,
"minItems": 2,
"prefixItems": [
{
"type": "number"
},
{
"type": "number"
}
],
"type": "array"
},
"title": "Values",
"type": "array"
}
},
"required": [
"label",
"values"
],
"title": "ChartLine",
"type": "object"
},
"ChartPoint": {
"description": "Represents a point in a scatter chart.\n\nAttributes:\n value (Tuple[float, float]): A (x, y) coordinate pair representing a point in a\n chart.",
"properties": {
"value": {
"maxItems": 2,
"minItems": 2,
"prefixItems": [
{
"type": "number"
},
{
"type": "number"
}
],
"title": "Value",
"type": "array"
}
},
"required": [
"value"
],
"title": "ChartPoint",
"type": "object"
},
"ChartSlice": {
"description": "Represents a slice in a pie chart.\n\nAttributes:\n label (str): The label for the slice.\n value (float): The value represented by the slice.",
"properties": {
"label": {
"title": "Label",
"type": "string"
},
"value": {
"title": "Value",
"type": "number"
}
},
"required": [
"label",
"value"
],
"title": "ChartSlice",
"type": "object"
},
"ChartStackedBar": {
"description": "Represents a stacked bar in a stacked bar chart.\n\nAttributes:\n label (List[str]): The labels for the stacked bars. Multiple values are stored\n in cases where the chart is \"double stacked,\" meaning bars are stacked both\n horizontally and vertically.\n values (List[Tuple[str, int]]): A list of values representing different segments\n of the stacked bar along with their label.",
"properties": {
"label": {
"items": {
"type": "string"
},
"title": "Label",
"type": "array"
},
"values": {
"items": {
"maxItems": 2,
"minItems": 2,
"prefixItems": [
{
"type": "string"
},
{
"type": "integer"
}
],
"type": "array"
},
"title": "Values",
"type": "array"
}
},
"required": [
"label",
"values"
],
"title": "ChartStackedBar",
"type": "object"
},
"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"
},
"label": {
"const": "code",
"default": "code",
"title": "Label",
"type": "string"
},
"prov": {
"default": [],
"items": {
"$ref": "#/$defs/ProvenanceItem"
},
"title": "Prov",
"type": "array"
},
"orig": {
"title": "Orig",
"type": "string"
},
"text": {
"title": "Text",
"type": "string"
},
"formatting": {
"anyOf": [
{
"$ref": "#/$defs/Formatting"
},
{
"type": "null"
}
],
"default": null
},
"hyperlink": {
"anyOf": [
{
"format": "uri",
"minLength": 1,
"type": "string"
},
{
"format": "path",
"type": "string"
},
{
"type": "null"
}
],
"default": null,
"title": "Hyperlink"
},
"captions": {
"default": [],
"items": {
"$ref": "#/$defs/RefItem"
},
"title": "Captions",
"type": "array"
},
"references": {
"default": [],
"items": {
"$ref": "#/$defs/RefItem"
},
"title": "References",
"type": "array"
},
"footnotes": {
"default": [],
"items": {
"$ref": "#/$defs/RefItem"
},
"title": "Footnotes",
"type": "array"
},
"image": {
"anyOf": [
{
"$ref": "#/$defs/ImageRef"
},
{
"type": "null"
}
],
"default": null
},
"code_language": {
"$ref": "#/$defs/CodeLanguageLabel",
"default": "unknown"
}
},
"required": [
"self_ref",
"orig",
"text"
],
"title": "CodeItem",
"type": "object"
},
"CodeLanguageLabel": {
"description": "CodeLanguageLabel.",
"enum": [
"Ada",
"Awk",
"Bash",
"bc",
"C",
"C#",
"C++",
"CMake",
"COBOL",
"CSS",
"Ceylon",
"Clojure",
"Crystal",
"Cuda",
"Cython",
"D",
"Dart",
"dc",
"Dockerfile",
"Elixir",
"Erlang",
"FORTRAN",
"Forth",
"Go",
"HTML",
"Haskell",
"Haxe",
"Java",
"JavaScript",
"Julia",
"Kotlin",
"Lisp",
"Lua",
"Matlab",
"MoonScript",
"Nim",
"OCaml",
"ObjectiveC",
"Octave",
"PHP",
"Pascal",
"Perl",
"Prolog",
"Python",
"Racket",
"Ruby",
"Rust",
"SML",
"SQL",
"Scala",
"Scheme",
"Swift",
"TypeScript",
"unknown",
"VisualBasic",
"XML",
"YAML"
],
"title": "CodeLanguageLabel",
"type": "string"
},
"ContentLayer": {
"description": "ContentLayer.",
"enum": [
"body",
"furniture",
"background"
],
"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"
},
"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"
},
"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": "#/$defs/ContentLayer",
"default": "body"
},
"label": {
"const": "form",
"default": "form",
"title": "Label",
"type": "string"
},
"prov": {
"default": [],
"items": {
"$ref": "#/$defs/ProvenanceItem"
},
"title": "Prov",
"type": "array"
},
"captions": {
"default": [],
"items": {
"$ref": "#/$defs/RefItem"
},
"title": "Captions",
"type": "array"
},
"references": {
"default": [],
"items": {
"$ref": "#/$defs/RefItem"
},
"title": "References",
"type": "array"
},
"footnotes": {
"default": [],
"items": {
"$ref": "#/$defs/RefItem"
},
"title": "Footnotes",
"type": "array"
},
"image": {
"anyOf": [
{
"$ref": "#/$defs/ImageRef"
},
{
"type": "null"
}
],
"default": null
},
"graph": {
"$ref": "#/$defs/GraphData"
}
},
"required": [
"self_ref",
"graph"
],
"title": "FormItem",
"type": "object"
},
"Formatting": {
"description": "Formatting.",
"properties": {
"bold": {
"default": false,
"title": "Bold",
"type": "boolean"
},
"italic": {
"default": false,
"title": "Italic",
"type": "boolean"
},
"underline": {
"default": false,
"title": "Underline",
"type": "boolean"
},
"strikethrough": {
"default": false,
"title": "Strikethrough",
"type": "boolean"
},
"script": {
"$ref": "#/$defs/Script",
"default": "baseline"
}
},
"title": "Formatting",
"type": "object"
},
"FormulaItem": {
"additionalProperties": false,
"description": "FormulaItem.",
"properties": {
"self_ref": {
"pattern": "^#(?:/([\\w-]+)(?:/(\\d+))?)?$",
"title": "Self Ref",
"type": "string"
},
"parent": {
"anyOf": [
{
"$ref": "#/$defs/RefItem"
},
{
"type": "null"
}
],
"default": null
},
"children": {
"default": [],
"items": {
"$ref": "#/$defs/RefItem"
},
"title": "Children",
"type": "array"
},
"content_layer": {
"$ref": "#/$defs/ContentLayer",
"default": "body"
},
"label": {
"const": "formula",
"default": "formula",
"title": "Label",
"type": "string"
},
"prov": {
"default": [],
"items": {
"$ref": "#/$defs/ProvenanceItem"
},
"title": "Prov",
"type": "array"
},
"orig": {
"title": "Orig",
"type": "string"
},
"text": {
"title": "Text",
"type": "string"
},
"formatting": {
"anyOf": [
{
"$ref": "#/$defs/Formatting"
},
{
"type": "null"
}
],
"default": null
},
"hyperlink": {
"anyOf": [
{
"format": "uri",
"minLength": 1,
"type": "string"
},
{
"format": "path",
"type": "string"
},
{
"type": "null"
}
],
"default": null,
"title": "Hyperlink"
}
},
"required": [
"self_ref",
"orig",
"text"
],
"title": "FormulaItem",
"type": "object"
},
"GraphCell": {
"description": "GraphCell.",
"properties": {
"label": {
"$ref": "#/$defs/GraphCellLabel"
},
"cell_id": {
"title": "Cell Id",
"type": "integer"
},
"text": {
"title": "Text",
"type": "string"
},
"orig": {
"title": "Orig",
"type": "string"
},
"prov": {
"anyOf": [
{
"$ref": "#/$defs/ProvenanceItem"
},
{
"type": "null"
}
],
"default": null
},
"item_ref": {
"anyOf": [
{
"$ref": "#/$defs/RefItem"
},
{
"type": "null"
}
],
"default": null
}
},
"required": [
"label",
"cell_id",
"text",
"orig"
],
"title": "GraphCell",
"type": "object"
},
"GraphCellLabel": {
"description": "GraphCellLabel.",
"enum": [
"unspecified",
"key",
"value",
"checkbox"
],
"title": "GraphCellLabel",
"type": "string"
},
"GraphData": {
"description": "GraphData.",
"properties": {
"cells": {
"items": {
"$ref": "#/$defs/GraphCell"
},
"title": "Cells",
"type": "array"
},
"links": {
"items": {
"$ref": "#/$defs/GraphLink"
},
"title": "Links",
"type": "array"
}
},
"title": "GraphData",
"type": "object"
},
"GraphLink": {
"description": "GraphLink.",
"properties": {
"label": {
"$ref": "#/$defs/GraphLinkLabel"
},
"source_cell_id": {
"title": "Source Cell Id",
"type": "integer"
},
"target_cell_id": {
"title": "Target Cell Id",
"type": "integer"
}
},
"required": [
"label",
"source_cell_id",
"target_cell_id"
],
"title": "GraphLink",
"type": "object"
},
"GraphLinkLabel": {
"description": "GraphLinkLabel.",
"enum": [
"unspecified",
"to_value",
"to_key",
"to_parent",
"to_child"
],
"title": "GraphLinkLabel",
"type": "string"
},
"GroupItem": {
"additionalProperties": false,
"description": "GroupItem.",
"properties": {
"self_ref": {
"pattern": "^#(?:/([\\w-]+)(?:/(\\d+))?)?$",
"title": "Self Ref",
"type": "string"
},
"parent": {
"anyOf": [
{
"$ref": "#/$defs/RefItem"
},
{
"type": "null"
}
],
"default": null
},
"children": {
"default": [],
"items": {
"$ref": "#/$defs/RefItem"
},
"title": "Children",
"type": "array"
},
"content_layer": {
"$ref": "#/$defs/ContentLayer",
"default": "body"
},
"name": {
"default": "group",
"title": "Name",
"type": "string"
},
"label": {
"$ref": "#/$defs/GroupLabel",
"default": "unspecified"
}
},
"required": [
"self_ref"
],
"title": "GroupItem",
"type": "object"
},
"GroupLabel": {
"description": "GroupLabel.",
"enum": [
"unspecified",
"list",
"ordered_list",
"chapter",
"section",
"sheet",
"slide",
"form_area",
"key_value_area",
"comment_section",
"inline",
"picture_area"
],
"title": "GroupLabel",
"type": "string"
},
"ImageRef": {
"description": "ImageRef.",
"properties": {
"mimetype": {
"title": "Mimetype",
"type": "string"
},
"dpi": {
"title": "Dpi",
"type": "integer"
},
"size": {
"$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"
},
"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": "#/$defs/ContentLayer",
"default": "body"
},
"label": {
"const": "key_value_region",
"default": "key_value_region",
"title": "Label",
"type": "string"
},
"prov": {
"default": [],
"items": {
"$ref": "#/$defs/ProvenanceItem"
},
"title": "Prov",
"type": "array"
},
"captions": {
"default": [],
"items": {
"$ref": "#/$defs/RefItem"
},
"title": "Captions",
"type": "array"
},
"references": {
"default": [],
"items": {
"$ref": "#/$defs/RefItem"
},
"title": "References",
"type": "array"
},
"footnotes": {
"default": [],
"items": {
"$ref": "#/$defs/RefItem"
},
"title": "Footnotes",
"type": "array"
},
"image": {
"anyOf": [
{
"$ref": "#/$defs/ImageRef"
},
{
"type": "null"
}
],
"default": null
},
"graph": {
"$ref": "#/$defs/GraphData"
}
},
"required": [
"self_ref",
"graph"
],
"title": "KeyValueItem",
"type": "object"
},
"ListGroup": {
"additionalProperties": false,
"description": "ListGroup.",
"properties": {
"self_ref": {
"pattern": "^#(?:/([\\w-]+)(?:/(\\d+))?)?$",
"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"
},
"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": "#/$defs/ContentLayer",
"default": "body"
},
"label": {
"const": "list_item",
"default": "list_item",
"title": "Label",
"type": "string"
},
"prov": {
"default": [],
"items": {
"$ref": "#/$defs/ProvenanceItem"
},
"title": "Prov",
"type": "array"
},
"orig": {
"title": "Orig",
"type": "string"
},
"text": {
"title": "Text",
"type": "string"
},
"formatting": {
"anyOf": [
{
"$ref": "#/$defs/Formatting"
},
{
"type": "null"
}
],
"default": null
},
"hyperlink": {
"anyOf": [
{
"format": "uri",
"minLength": 1,
"type": "string"
},
{
"format": "path",
"type": "string"
},
{
"type": "null"
}
],
"default": null,
"title": "Hyperlink"
},
"enumerated": {
"default": false,
"title": "Enumerated",
"type": "boolean"
},
"marker": {
"default": "-",
"title": "Marker",
"type": "string"
}
},
"required": [
"self_ref",
"orig",
"text"
],
"title": "ListItem",
"type": "object"
},
"MiscAnnotation": {
"description": "MiscAnnotation.",
"properties": {
"kind": {
"const": "misc",
"default": "misc",
"title": "Kind",
"type": "string"
},
"content": {
"additionalProperties": true,
"title": "Content",
"type": "object"
}
},
"required": [
"content"
],
"title": "MiscAnnotation",
"type": "object"
},
"PageItem": {
"description": "PageItem.",
"properties": {
"size": {
"$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": "#/$defs/PictureClassificationClass"
},
"title": "Predicted Classes",
"type": "array"
}
},
"required": [
"provenance",
"predicted_classes"
],
"title": "PictureClassificationData",
"type": "object"
},
"PictureItem": {
"additionalProperties": false,
"description": "PictureItem.",
"properties": {
"self_ref": {
"pattern": "^#(?:/([\\w-]+)(?:/(\\d+))?)?$",
"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"
},
"label": {
"default": "picture",
"enum": [
"picture",
"chart"
],
"title": "Label",
"type": "string"
},
"prov": {
"default": [],
"items": {
"$ref": "#/$defs/ProvenanceItem"
},
"title": "Prov",
"type": "array"
},
"captions": {
"default": [],
"items": {
"$ref": "#/$defs/RefItem"
},
"title": "Captions",
"type": "array"
},
"references": {
"default": [],
"items": {
"$ref": "#/$defs/RefItem"
},
"title": "References",
"type": "array"
},
"footnotes": {
"default": [],
"items": {
"$ref": "#/$defs/RefItem"
},
"title": "Footnotes",
"type": "array"
},
"image": {
"anyOf": [
{
"$ref": "#/$defs/ImageRef"
},
{
"type": "null"
}
],
"default": null
},
"annotations": {
"default": [],
"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"
},
"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": "ProvenanceItem.",
"properties": {
"page_no": {
"title": "Page No",
"type": "integer"
},
"bbox": {
"anyOf": [
{
"$ref": "#/$defs/BoundingBox"
},
{
"$ref": "#/$defs/BoundingRectangle"
}
],
"title": "Bbox"
},
"charspan": {
"maxItems": 2,
"minItems": 2,
"prefixItems": [
{
"type": "integer"
},
{
"type": "integer"
}
],
"title": "Charspan",
"type": "array"
}
},
"required": [
"page_no",
"bbox",
"charspan"
],
"title": "ProvenanceItem",
"type": "object"
},
"RefItem": {
"description": "RefItem.",
"properties": {
"$ref": {
"pattern": "^#(?:/([\\w-]+)(?:/(\\d+))?)?$",
"title": "$Ref",
"type": "string"
}
},
"required": [
"$ref"
],
"title": "RefItem",
"type": "object"
},
"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": "#/$defs/ContentLayer",
"default": "body"
},
"label": {
"const": "section_header",
"default": "section_header",
"title": "Label",
"type": "string"
},
"prov": {
"default": [],
"items": {
"$ref": "#/$defs/ProvenanceItem"
},
"title": "Prov",
"type": "array"
},
"orig": {
"title": "Orig",
"type": "string"
},
"text": {
"title": "Text",
"type": "string"
},
"formatting": {
"anyOf": [
{
"$ref": "#/$defs/Formatting"
},
{
"type": "null"
}
],
"default": null
},
"hyperlink": {
"anyOf": [
{
"format": "uri",
"minLength": 1,
"type": "string"
},
{
"format": "path",
"type": "string"
},
{
"type": "null"
}
],
"default": null,
"title": "Hyperlink"
},
"level": {
"default": 1,
"maximum": 100,
"minimum": 1,
"title": "Level",
"type": "integer"
}
},
"required": [
"self_ref",
"orig",
"text"
],
"title": "SectionHeaderItem",
"type": "object"
},
"Size": {
"description": "Size.",
"properties": {
"width": {
"default": 0.0,
"title": "Width",
"type": "number"
},
"height": {
"default": 0.0,
"title": "Height",
"type": "number"
}
},
"title": "Size",
"type": "object"
},
"TableCell": {
"description": "TableCell.",
"properties": {
"bbox": {
"anyOf": [
{
"$ref": "#/$defs/BoundingBox"
},
{
"type": "null"
}
],
"default": null
},
"row_span": {
"default": 1,
"title": "Row Span",
"type": "integer"
},
"col_span": {
"default": 1,
"title": "Col Span",
"type": "integer"
},
"start_row_offset_idx": {
"title": "Start Row Offset Idx",
"type": "integer"
},
"end_row_offset_idx": {
"title": "End Row Offset Idx",
"type": "integer"
},
"start_col_offset_idx": {
"title": "Start Col Offset Idx",
"type": "integer"
},
"end_col_offset_idx": {
"title": "End Col Offset Idx",
"type": "integer"
},
"text": {
"title": "Text",
"type": "string"
},
"column_header": {
"default": false,
"title": "Column Header",
"type": "boolean"
},
"row_header": {
"default": false,
"title": "Row Header",
"type": "boolean"
},
"row_section": {
"default": false,
"title": "Row Section",
"type": "boolean"
}
},
"required": [
"start_row_offset_idx",
"end_row_offset_idx",
"start_col_offset_idx",
"end_col_offset_idx",
"text"
],
"title": "TableCell",
"type": "object"
},
"TableData": {
"description": "BaseTableData.",
"properties": {
"table_cells": {
"default": [],
"items": {
"$ref": "#/$defs/TableCell"
},
"title": "Table Cells",
"type": "array"
},
"num_rows": {
"default": 0,
"title": "Num Rows",
"type": "integer"
},
"num_cols": {
"default": 0,
"title": "Num Cols",
"type": "integer"
}
},
"title": "TableData",
"type": "object"
},
"TableItem": {
"additionalProperties": false,
"description": "TableItem.",
"properties": {
"self_ref": {
"pattern": "^#(?:/([\\w-]+)(?:/(\\d+))?)?$",
"title": "Self Ref",
"type": "string"
},
"parent": {
"anyOf": [
{
"$ref": "#/$defs/RefItem"
},
{
"type": "null"
}
],
"default": null
},
"children": {
"default": [],
"items": {
"$ref": "#/$defs/RefItem"
},
"title": "Children",
"type": "array"
},
"content_layer": {
"$ref": "#/$defs/ContentLayer",
"default": "body"
},
"label": {
"default": "table",
"enum": [
"document_index",
"table"
],
"title": "Label",
"type": "string"
},
"prov": {
"default": [],
"items": {
"$ref": "#/$defs/ProvenanceItem"
},
"title": "Prov",
"type": "array"
},
"captions": {
"default": [],
"items": {
"$ref": "#/$defs/RefItem"
},
"title": "Captions",
"type": "array"
},
"references": {
"default": [],
"items": {
"$ref": "#/$defs/RefItem"
},
"title": "References",
"type": "array"
},
"footnotes": {
"default": [],
"items": {
"$ref": "#/$defs/RefItem"
},
"title": "Footnotes",
"type": "array"
},
"image": {
"anyOf": [
{
"$ref": "#/$defs/ImageRef"
},
{
"type": "null"
}
],
"default": null
},
"data": {
"$ref": "#/$defs/TableData"
},
"annotations": {
"default": [],
"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"
},
"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": "#/$defs/ContentLayer",
"default": "body"
},
"label": {
"enum": [
"caption",
"checkbox_selected",
"checkbox_unselected",
"footnote",
"page_footer",
"page_header",
"paragraph",
"reference",
"text",
"empty_value"
],
"title": "Label",
"type": "string"
},
"prov": {
"default": [],
"items": {
"$ref": "#/$defs/ProvenanceItem"
},
"title": "Prov",
"type": "array"
},
"orig": {
"title": "Orig",
"type": "string"
},
"text": {
"title": "Text",
"type": "string"
},
"formatting": {
"anyOf": [
{
"$ref": "#/$defs/Formatting"
},
{
"type": "null"
}
],
"default": null
},
"hyperlink": {
"anyOf": [
{
"format": "uri",
"minLength": 1,
"type": "string"
},
{
"format": "path",
"type": "string"
},
{
"type": "null"
}
],
"default": null,
"title": "Hyperlink"
}
},
"required": [
"self_ref",
"label",
"orig",
"text"
],
"title": "TextItem",
"type": "object"
},
"TitleItem": {
"additionalProperties": false,
"description": "TitleItem.",
"properties": {
"self_ref": {
"pattern": "^#(?:/([\\w-]+)(?:/(\\d+))?)?$",
"title": "Self Ref",
"type": "string"
},
"parent": {
"anyOf": [
{
"$ref": "#/$defs/RefItem"
},
{
"type": "null"
}
],
"default": null
},
"children": {
"default": [],
"items": {
"$ref": "#/$defs/RefItem"
},
"title": "Children",
"type": "array"
},
"content_layer": {
"$ref": "#/$defs/ContentLayer",
"default": "body"
},
"label": {
"const": "title",
"default": "title",
"title": "Label",
"type": "string"
},
"prov": {
"default": [],
"items": {
"$ref": "#/$defs/ProvenanceItem"
},
"title": "Prov",
"type": "array"
},
"orig": {
"title": "Orig",
"type": "string"
},
"text": {
"title": "Text",
"type": "string"
},
"formatting": {
"anyOf": [
{
"$ref": "#/$defs/Formatting"
},
{
"type": "null"
}
],
"default": null
},
"hyperlink": {
"anyOf": [
{
"format": "uri",
"minLength": 1,
"type": "string"
},
{
"format": "path",
"type": "string"
},
{
"type": "null"
}
],
"default": null,
"title": "Hyperlink"
}
},
"required": [
"self_ref",
"orig",
"text"
],
"title": "TitleItem",
"type": "object"
}
},
"description": "DoclingDocument.",
"properties": {
"schema_name": {
"const": "DoclingDocument",
"default": "DoclingDocument",
"title": "Schema Name",
"type": "string"
},
"version": {
"default": "1.5.0",
"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": "#/$defs/GroupItem",
"default": {
"self_ref": "#/furniture",
"parent": null,
"children": [],
"content_layer": "furniture",
"name": "_root_",
"label": "unspecified"
},
"deprecated": true
},
"body": {
"$ref": "#/$defs/GroupItem",
"default": {
"self_ref": "#/body",
"parent": null,
"children": [],
"content_layer": "body",
"name": "_root_",
"label": "unspecified"
}
},
"groups": {
"default": [],
"items": {
"anyOf": [
{
"$ref": "#/$defs/ListGroup"
},
{
"$ref": "#/$defs/InlineGroup"
},
{
"$ref": "#/$defs/GroupItem"
}
]
},
"title": "Groups",
"type": "array"
},
"texts": {
"default": [],
"items": {
"anyOf": [
{
"$ref": "#/$defs/TitleItem"
},
{
"$ref": "#/$defs/SectionHeaderItem"
},
{
"$ref": "#/$defs/ListItem"
},
{
"$ref": "#/$defs/CodeItem"
},
{
"$ref": "#/$defs/FormulaItem"
},
{
"$ref": "#/$defs/TextItem"
}
]
},
"title": "Texts",
"type": "array"
},
"pictures": {
"default": [],
"items": {
"$ref": "#/$defs/PictureItem"
},
"title": "Pictures",
"type": "array"
},
"tables": {
"default": [],
"items": {
"$ref": "#/$defs/TableItem"
},
"title": "Tables",
"type": "array"
},
"key_value_items": {
"default": [],
"items": {
"$ref": "#/$defs/KeyValueItem"
},
"title": "Key Value Items",
"type": "array"
},
"form_items": {
"default": [],
"items": {
"$ref": "#/$defs/FormItem"
},
"title": "Form Items",
"type": "array"
},
"pages": {
"additionalProperties": {
"$ref": "#/$defs/PageItem"
},
"default": {},
"title": "Pages",
"type": "object"
}
},
"required": [
"name"
],
"title": "DoclingDocument",
"type": "object"
}