Skip to content

Docling Document

This is an automatic generated API reference of the DoclingDocument type.

doc

Package for models defined by the Document type.

Classes:

DoclingDocument

Bases: BaseModel

DoclingDocument.

Methods:

Attributes:

body 

body: GroupItem = GroupItem(name='_root_', self_ref='#/body')

form_items 

form_items: List[FormItem] = []

furniture 

furniture: Annotated[GroupItem, Field(deprecated=True)] = GroupItem(name='_root_', self_ref='#/furniture', content_layer=FURNITURE)

groups 

groups: List[Union[ListGroup, InlineGroup, GroupItem]] = []

key_value_items 

key_value_items: List[KeyValueItem] = []

name 

name: str

origin 

origin: Optional[DocumentOrigin] = None

pages 

pages: Dict[int, PageItem] = {}

pictures 

pictures: List[PictureItem] = []

schema_name 

schema_name: Literal['DoclingDocument'] = 'DoclingDocument'

tables 

tables: List[TableItem] = []

texts 

texts: List[Union[TitleItem, SectionHeaderItem, ListItem, CodeItem, FormulaItem, TextItem]] = []

version 

version: Annotated[str, StringConstraints(pattern=VERSION_PATTERN, strict=True)] = CURRENT_VERSION

add_code 

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.

Parameters:

  • text (str) –

    str:

  • code_language (Optional[CodeLanguageLabel], default: None ) –

    Optional[str]: (Default value = None)

  • orig (Optional[str], default: None ) –

    Optional[str]: (Default value = None)

  • caption (Optional[Union[TextItem, RefItem]], default: None ) –

    Optional[Union[TextItem:

  • RefItem]] –

    (Default value = None)

  • prov (Optional[ProvenanceItem], default: None ) –

    Optional[ProvenanceItem]: (Default value = None)

  • parent (Optional[NodeItem], default: None ) –

    Optional[NodeItem]: (Default value = None)

add_document 

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.

Parameters:

  • doc (DoclingDocument) –

    DoclingDocument: The document whose content will be added

  • parent (Optional[NodeItem], default: None ) –

    Optional[NodeItem]: The parent NodeItem under which new items are added (Default value = None)

Returns:

  • None –

    None

add_form 

add_form(graph: GraphData, prov: Optional[ProvenanceItem] = None, parent: Optional[NodeItem] = None)

add_form.

Parameters:

  • graph (GraphData) –

    GraphData:

  • prov (Optional[ProvenanceItem], default: None ) –

    Optional[ProvenanceItem]: (Default value = None)

  • parent (Optional[NodeItem], default: None ) –

    Optional[NodeItem]: (Default value = None)

add_formula 

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.

Parameters:

  • text (str) –

    str:

  • orig (Optional[str], default: None ) –

    Optional[str]: (Default value = None)

  • level –

    LevelNumber: (Default value = 1)

  • prov (Optional[ProvenanceItem], default: None ) –

    Optional[ProvenanceItem]: (Default value = None)

  • parent (Optional[NodeItem], default: None ) –

    Optional[NodeItem]: (Default value = None)

add_group 

add_group(label: Optional[GroupLabel] = None, name: Optional[str] = None, parent: Optional[NodeItem] = None, content_layer: Optional[ContentLayer] = None) -> GroupItem

add_group.

Parameters:

  • label (Optional[GroupLabel], default: None ) –

    Optional[GroupLabel]: (Default value = None)

  • name (Optional[str], default: None ) –

    Optional[str]: (Default value = None)

  • parent (Optional[NodeItem], default: None ) –

    Optional[NodeItem]: (Default value = None)

add_heading 

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.

Parameters:

  • label –

    DocItemLabel:

  • text (str) –

    str:

  • orig (Optional[str], default: None ) –

    Optional[str]: (Default value = None)

  • level (LevelNumber, default: 1 ) –

    LevelNumber: (Default value = 1)

  • prov (Optional[ProvenanceItem], default: None ) –

    Optional[ProvenanceItem]: (Default value = None)

  • parent (Optional[NodeItem], default: None ) –

    Optional[NodeItem]: (Default value = None)

add_inline_group 

add_inline_group(name: Optional[str] = None, parent: Optional[NodeItem] = None, content_layer: Optional[ContentLayer] = None) -> InlineGroup

add_inline_group.

add_key_values 

add_key_values(graph: GraphData, prov: Optional[ProvenanceItem] = None, parent: Optional[NodeItem] = None)

add_key_values.

Parameters:

  • graph (GraphData) –

    GraphData:

  • prov (Optional[ProvenanceItem], default: None ) –

    Optional[ProvenanceItem]: (Default value = None)

  • parent (Optional[NodeItem], default: None ) –

    Optional[NodeItem]: (Default value = None)

add_list_group 

add_list_group(name: Optional[str] = None, parent: Optional[NodeItem] = None, content_layer: Optional[ContentLayer] = None) -> ListGroup

add_list_group.

add_list_item 

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.

Parameters:

  • label –

    str:

  • text (str) –

    str:

  • orig (Optional[str], default: None ) –

    Optional[str]: (Default value = None)

  • prov (Optional[ProvenanceItem], default: None ) –

    Optional[ProvenanceItem]: (Default value = None)

  • parent (Optional[NodeItem], default: None ) –

    Optional[NodeItem]: (Default value = None)

add_node_items 

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.

Parameters:

  • node_items (List[NodeItem]) –

    list[NodeItem]: The NodeItems to be added

  • doc (DoclingDocument) –

    DoclingDocument: The document to which the NodeItems and their children belong

  • parent (Optional[NodeItem], default: None ) –

    Optional[NodeItem]: The parent NodeItem under which new items are added (Default value = None)

Returns:

  • None –

    None

add_ordered_list 

add_ordered_list(name: Optional[str] = None, parent: Optional[NodeItem] = None, content_layer: Optional[ContentLayer] = None) -> GroupItem

add_ordered_list.

add_page 

add_page(page_no: int, size: Size, image: Optional[ImageRef] = None) -> PageItem

add_page.

Parameters:

  • page_no (int) –

    int:

  • size (Size) –

    Size:

add_picture 

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.

Parameters:

  • data –

    Optional[List[PictureData]]: (Default value = None)

  • caption (Optional[Union[TextItem, RefItem]], default: None ) –

    Optional[Union[TextItem:

  • RefItem]] –

    (Default value = None)

  • prov (Optional[ProvenanceItem], default: None ) –

    Optional[ProvenanceItem]: (Default value = None)

  • parent (Optional[NodeItem], default: None ) –

    Optional[NodeItem]: (Default value = None)

add_table 

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.

Parameters:

  • data (TableData) –

    TableData:

  • caption (Optional[Union[TextItem, RefItem]], default: None ) –

    Optional[Union[TextItem, RefItem]]: (Default value = None)

  • prov (Optional[ProvenanceItem], default: None ) –

    Optional[ProvenanceItem]: (Default value = None)

  • parent (Optional[NodeItem], default: None ) –

    Optional[NodeItem]: (Default value = None)

  • label (DocItemLabel, default: TABLE ) –

    DocItemLabel: (Default value = DocItemLabel.TABLE)

add_text 

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)

add_text.

Parameters:

  • label (DocItemLabel) –

    str:

  • text (str) –

    str:

  • orig (Optional[str], default: None ) –

    Optional[str]: (Default value = None)

  • prov (Optional[ProvenanceItem], default: None ) –

    Optional[ProvenanceItem]: (Default value = None)

  • parent (Optional[NodeItem], default: None ) –

    Optional[NodeItem]: (Default value = None)

add_title 

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.

Parameters:

  • text (str) –

    str:

  • orig (Optional[str], default: None ) –

    Optional[str]: (Default value = None)

  • level –

    LevelNumber: (Default value = 1)

  • prov (Optional[ProvenanceItem], default: None ) –

    Optional[ProvenanceItem]: (Default value = None)

  • parent (Optional[NodeItem], default: None ) –

    Optional[NodeItem]: (Default value = None)

add_unordered_list 

add_unordered_list(name: Optional[str] = None, parent: Optional[NodeItem] = None, content_layer: Optional[ContentLayer] = None) -> GroupItem

add_unordered_list.

append_child_item 

append_child_item(*, child: NodeItem, parent: Optional[NodeItem] = None) -> None

Adds an item.

check_version_is_compatible 

check_version_is_compatible(v: str) -> str

Check if this document version is compatible with SDK schema version.

delete_items 

delete_items(*, node_items: List[NodeItem]) -> None

Deletes an item, given its instance or ref, and any children it has.

delete_items_range 

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.

Parameters:

  • start (NodeItem) –

    NodeItem: The starting NodeItem of the range

  • end (NodeItem) –

    NodeItem: The ending NodeItem of the range

  • start_inclusive (bool, default: True ) –

    bool: (Default value = True): If True, the start NodeItem will also be deleted

  • end_inclusive (bool, default: True ) –

    bool: (Default value = True): If True, the end NodeItem will also be deleted

Returns:

  • None –

    None

export_to_dict 

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_doctags 

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.

Parameters:

  • delim (str, default: '' ) –

    str: (Default value = "") Deprecated

  • from_element (int, default: 0 ) –

    int: (Default value = 0)

  • to_element (int, default: maxsize ) –

    Optional[int]: (Default value = None)

  • labels (Optional[set[DocItemLabel]], default: None ) –

    set[DocItemLabel]

  • xsize (int, default: 500 ) –

    int: (Default value = 500)

  • ysize (int, default: 500 ) –

    int: (Default value = 500)

  • add_location (bool, default: True ) –

    bool: (Default value = True)

  • add_content (bool, default: True ) –

    bool: (Default value = True)

  • add_page_index (bool, default: True ) –

    bool: (Default value = True)

  • add_table_cell_text (bool, default: True ) –

    bool: (Default value = True)

  • minified (bool, default: False ) –

    bool: (Default value = False)

  • pages (Optional[set[int]], default: None ) –

    set[int]: (Default value = None)

Returns:

  • str –

    The content of the document formatted as a DocTags string.

export_to_document_tokens 

export_to_document_tokens(*args, **kwargs)

Export to DocTags format.

export_to_element_tree 

export_to_element_tree() -> str

Export_to_element_tree.

export_to_html 

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 

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_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) -> 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.

Parameters:

  • delim (str, default: '\n\n' ) –

    Deprecated.

  • from_element (int, default: 0 ) –

    Body slicing start index (inclusive). (Default value = 0).

  • to_element (int, default: maxsize ) –

    Body slicing stop index (exclusive). (Default value = maxint).

  • labels (Optional[set[DocItemLabel]], default: None ) –

    The set of document labels to include in the export. None falls back to the system-defined default.

  • strict_text (bool, default: False ) –

    Deprecated.

  • escape_underscores (bool, default: True ) –

    bool: Whether to escape underscores in the text content of the document. (Default value = True).

  • image_placeholder (str, default: '<!-- image -->' ) –

    The placeholder to include to position images in the markdown. (Default value = "\<!-- image -->").

  • image_mode (ImageRefMode, default: PLACEHOLDER ) –

    The mode to use for including images in the markdown. (Default value = ImageRefMode.PLACEHOLDER).

  • indent (int, default: 4 ) –

    The indent in spaces of the nested lists. (Default value = 4).

  • included_content_layers (Optional[set[ContentLayer]], default: None ) –

    The set of layels to include in the export. None falls back to the system-defined default.

  • page_break_placeholder (Optional[str], default: None ) –

    The placeholder to include for marking page breaks. None means no page break placeholder will be used.

  • include_annotations (bool, default: True ) –

    bool: Whether to include annotations in the export. (Default value = True).

  • mark_annotations (bool, default: False ) –

    bool: Whether to mark annotations in the export; only relevant if include_annotations is True. (Default value = False).

Returns:

  • str –

    The exported Markdown representation.

export_to_text 

export_to_text(delim: str = '\n\n', from_element: int = 0, to_element: int = 1000000, labels: Optional[set[DocItemLabel]] = None) -> str

export_to_text.

extract_items_range 

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.

Parameters:

  • start (NodeItem) –

    NodeItem: The starting NodeItem of the range (must be a direct child of the document body)

  • end (NodeItem) –

    NodeItem: The ending NodeItem of the range (must be a direct child of the document body)

  • start_inclusive (bool, default: True ) –

    bool: (Default value = True): If True, the start NodeItem will also be extracted

  • end_inclusive (bool, default: True ) –

    bool: (Default value = True): If True, the end NodeItem will also be extracted

  • delete (bool, default: False ) –

    bool: (Default value = False): If True, extracted items are deleted in the original document

Returns:

  • DoclingDocument –

    DoclingDocument: A new document containing the extracted NodeItems and their children

get_visualization 

get_visualization(show_label: bool = True, show_branch_numbering: bool = False) -> dict[Optional[int], Image]

Get visualization of the document as images by page.

insert_code 

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.

Parameters:

  • sibling (NodeItem) –

    NodeItem:

  • text (str) –

    str:

  • code_language (Optional[CodeLanguageLabel], default: None ) –

    Optional[str]: (Default value = None)

  • orig (Optional[str], default: None ) –

    Optional[str]: (Default value = None)

  • caption (Optional[Union[TextItem, RefItem]], default: None ) –

    Optional[Union[TextItem, RefItem]]: (Default value = None)

  • prov (Optional[ProvenanceItem], default: None ) –

    Optional[ProvenanceItem]: (Default value = None)

  • content_layer (Optional[ContentLayer], default: None ) –

    Optional[ContentLayer]: (Default value = None)

  • formatting (Optional[Formatting], default: None ) –

    Optional[Formatting]: (Default value = None)

  • hyperlink (Optional[Union[AnyUrl, Path]], default: None ) –

    Optional[Union[AnyUrl, Path]]: (Default value = None)

  • after (bool, default: True ) –

    bool: (Default value = True)

Returns:

  • CodeItem –

    CodeItem: The newly created CodeItem item.

insert_document 

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.

Parameters:

  • doc (DoclingDocument) –

    DoclingDocument: The document whose content will be inserted

  • sibling (NodeItem) –

    NodeItem: The NodeItem after/before which the new items will be inserted

  • after (bool, default: True ) –

    bool: If True, insert after the sibling; if False, insert before (Default value = True)

Returns:

  • None –

    None

insert_form 

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.

Parameters:

  • sibling (NodeItem) –

    NodeItem:

  • graph (GraphData) –

    GraphData:

  • prov (Optional[ProvenanceItem], default: None ) –

    Optional[ProvenanceItem]: (Default value = None)

  • after (bool, default: True ) –

    bool: (Default value = True)

Returns:

  • FormItem –

    FormItem: The newly created FormItem item.

insert_formula 

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.

Parameters:

  • sibling (NodeItem) –

    NodeItem:

  • text (str) –

    str:

  • orig (Optional[str], default: None ) –

    Optional[str]: (Default value = None)

  • prov (Optional[ProvenanceItem], default: None ) –

    Optional[ProvenanceItem]: (Default value = None)

  • content_layer (Optional[ContentLayer], default: None ) –

    Optional[ContentLayer]: (Default value = None)

  • formatting (Optional[Formatting], default: None ) –

    Optional[Formatting]: (Default value = None)

  • hyperlink (Optional[Union[AnyUrl, Path]], default: None ) –

    Optional[Union[AnyUrl, Path]]: (Default value = None)

  • after (bool, default: True ) –

    bool: (Default value = True)

Returns:

  • FormulaItem –

    FormulaItem: The newly created FormulaItem item.

insert_group 

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.

Parameters:

  • sibling (NodeItem) –

    NodeItem:

  • label (Optional[GroupLabel], default: None ) –

    Optional[GroupLabel]: (Default value = None)

  • name (Optional[str], default: None ) –

    Optional[str]: (Default value = None)

  • content_layer (Optional[ContentLayer], default: None ) –

    Optional[ContentLayer]: (Default value = None)

  • after (bool, default: True ) –

    bool: (Default value = True)

Returns:

  • GroupItem –

    GroupItem: The newly created GroupItem.

insert_heading 

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.

Parameters:

  • sibling (NodeItem) –

    NodeItem:

  • text (str) –

    str:

  • orig (Optional[str], default: None ) –

    Optional[str]: (Default value = None)

  • level (LevelNumber, default: 1 ) –

    LevelNumber: (Default value = 1)

  • prov (Optional[ProvenanceItem], default: None ) –

    Optional[ProvenanceItem]: (Default value = None)

  • content_layer (Optional[ContentLayer], default: None ) –

    Optional[ContentLayer]: (Default value = None)

  • formatting (Optional[Formatting], default: None ) –

    Optional[Formatting]: (Default value = None)

  • hyperlink (Optional[Union[AnyUrl, Path]], default: None ) –

    Optional[Union[AnyUrl, Path]]: (Default value = None)

  • after (bool, default: True ) –

    bool: (Default value = True)

Returns:

insert_inline_group 

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.

Parameters:

  • sibling (NodeItem) –

    NodeItem:

  • name (Optional[str], default: None ) –

    Optional[str]: (Default value = None)

  • content_layer (Optional[ContentLayer], default: None ) –

    Optional[ContentLayer]: (Default value = None)

  • after (bool, default: True ) –

    bool: (Default value = True)

Returns:

  • InlineGroup –

    InlineGroup: The newly created InlineGroup item.

insert_item_after_sibling 

insert_item_after_sibling(*, new_item: NodeItem, sibling: NodeItem) -> None

Inserts an item, given its node_item instance, after other as a sibling.

insert_item_before_sibling 

insert_item_before_sibling(*, new_item: NodeItem, sibling: NodeItem) -> None

Inserts an item, given its node_item instance, before other as a sibling.

insert_key_values 

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.

Parameters:

  • sibling (NodeItem) –

    NodeItem:

  • graph (GraphData) –

    GraphData:

  • prov (Optional[ProvenanceItem], default: None ) –

    Optional[ProvenanceItem]: (Default value = None)

  • after (bool, default: True ) –

    bool: (Default value = True)

Returns:

  • KeyValueItem –

    KeyValueItem: The newly created KeyValueItem item.

insert_list_group 

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.

Parameters:

  • sibling (NodeItem) –

    NodeItem:

  • name (Optional[str], default: None ) –

    Optional[str]: (Default value = None)

  • content_layer (Optional[ContentLayer], default: None ) –

    Optional[ContentLayer]: (Default value = None)

  • after (bool, default: True ) –

    bool: (Default value = True)

Returns:

  • ListGroup –

    ListGroup: The newly created ListGroup item.

insert_list_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.

Parameters:

  • sibling (NodeItem) –

    NodeItem:

  • text (str) –

    str:

  • enumerated (bool, default: False ) –

    bool: (Default value = False)

  • marker (Optional[str], default: None ) –

    Optional[str]: (Default value = None)

  • orig (Optional[str], default: None ) –

    Optional[str]: (Default value = None)

  • prov (Optional[ProvenanceItem], default: None ) –

    Optional[ProvenanceItem]: (Default value = None)

  • content_layer (Optional[ContentLayer], default: None ) –

    Optional[ContentLayer]: (Default value = None)

  • formatting (Optional[Formatting], default: None ) –

    Optional[Formatting]: (Default value = None)

  • hyperlink (Optional[Union[AnyUrl, Path]], default: None ) –

    Optional[Union[AnyUrl, Path]]: (Default value = None)

  • after (bool, default: True ) –

    bool: (Default value = True)

Returns:

  • ListItem –

    ListItem: The newly created ListItem item.

insert_node_items 

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.

Parameters:

  • sibling (NodeItem) –

    NodeItem: The NodeItem after/before which the new items will be inserted

  • node_items (List[NodeItem]) –

    list[NodeItem]: The NodeItems to be inserted

  • doc (DoclingDocument) –

    DoclingDocument: The document to which the NodeItems and their children belong

  • after (bool, default: True ) –

    bool: If True, insert after the sibling; if False, insert before (Default value = True)

Returns:

  • None –

    None

insert_picture 

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.

Parameters:

  • sibling (NodeItem) –

    NodeItem:

  • annotations (Optional[List[PictureDataType]], default: None ) –

    Optional[List[PictureDataType]]: (Default value = None)

  • image (Optional[ImageRef], default: None ) –

    Optional[ImageRef]: (Default value = None)

  • caption (Optional[Union[TextItem, RefItem]], default: None ) –

    Optional[Union[TextItem, RefItem]]: (Default value = None)

  • prov (Optional[ProvenanceItem], default: None ) –

    Optional[ProvenanceItem]: (Default value = None)

  • content_layer (Optional[ContentLayer], default: None ) –

    Optional[ContentLayer]: (Default value = None)

  • after (bool, default: True ) –

    bool: (Default value = True)

Returns:

  • PictureItem –

    PictureItem: The newly created PictureItem item.

insert_table 

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.

Parameters:

  • sibling (NodeItem) –

    NodeItem:

  • data (TableData) –

    TableData:

  • caption (Optional[Union[TextItem, RefItem]], default: None ) –

    Optional[Union[TextItem, RefItem]]: (Default value = None)

  • prov (Optional[ProvenanceItem], default: None ) –

    Optional[ProvenanceItem]: (Default value = None)

  • label (DocItemLabel, default: TABLE ) –

    DocItemLabel: (Default value = DocItemLabel.TABLE)

  • content_layer (Optional[ContentLayer], default: None ) –

    Optional[ContentLayer]: (Default value = None)

  • annotations (Optional[list[TableAnnotationType]], default: None ) –

    Optional[List[TableAnnotationType]]: (Default value = None)

  • after (bool, default: True ) –

    bool: (Default value = True)

Returns:

  • TableItem –

    TableItem: The newly created TableItem item.

insert_text 

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.

Parameters:

  • sibling (NodeItem) –

    NodeItem:

  • label (DocItemLabel) –

    DocItemLabel:

  • text (str) –

    str:

  • orig (Optional[str], default: None ) –

    Optional[str]: (Default value = None)

  • prov (Optional[ProvenanceItem], default: None ) –

    Optional[ProvenanceItem]: (Default value = None)

  • content_layer (Optional[ContentLayer], default: None ) –

    Optional[ContentLayer]: (Default value = None)

  • formatting (Optional[Formatting], default: None ) –

    Optional[Formatting]: (Default value = None)

  • hyperlink (Optional[Union[AnyUrl, Path]], default: None ) –

    Optional[Union[AnyUrl, Path]]: (Default value = None)

  • after (bool, default: True ) –

    bool: (Default value = True)

Returns:

  • TextItem –

    TextItem: The newly created TextItem item.

insert_title 

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.

Parameters:

  • sibling (NodeItem) –

    NodeItem:

  • text (str) –

    str:

  • orig (Optional[str], default: None ) –

    Optional[str]: (Default value = None)

  • prov (Optional[ProvenanceItem], default: None ) –

    Optional[ProvenanceItem]: (Default value = None)

  • content_layer (Optional[ContentLayer], default: None ) –

    Optional[ContentLayer]: (Default value = None)

  • formatting (Optional[Formatting], default: None ) –

    Optional[Formatting]: (Default value = None)

  • hyperlink (Optional[Union[AnyUrl, Path]], default: None ) –

    Optional[Union[AnyUrl, Path]]: (Default value = None)

  • after (bool, default: True ) –

    bool: (Default value = True)

Returns:

  • TitleItem –

    TitleItem: The newly created TitleItem item.

iterate_items 

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 

load_from_doctags(doctag_document: DocTagsDocument, document_name: str = 'Document') -> DoclingDocument

Load Docling document from lists of DocTags and Images.

load_from_json 

load_from_json(filename: Union[str, Path]) -> DoclingDocument

load_from_json.

Parameters:

  • filename (Union[str, Path]) –

    The filename to load a saved DoclingDocument from a .json.

Returns:

  • DoclingDocument –

    The loaded DoclingDocument.

load_from_yaml 

load_from_yaml(filename: Union[str, Path]) -> DoclingDocument

load_from_yaml.

Args: filename: The filename to load a YAML-serialized DoclingDocument from.

Returns: DoclingDocument: the loaded DoclingDocument

num_pages 

num_pages()

num_pages.

print_element_tree 

print_element_tree()

Print_element_tree.

replace_item 

replace_item(*, new_item: NodeItem, old_item: NodeItem) -> None

Replace item with new item.

save_as_doctags 

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 

save_as_document_tokens(*args, **kwargs)

Save the document content to a DocumentToken format.

save_as_html 

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 

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 

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, 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)

Save to markdown.

save_as_yaml 

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 

transform_to_content_layer(data: dict) -> dict

transform_to_content_layer.

validate_document 

validate_document(d: DoclingDocument)

validate_document.

validate_misplaced_list_items 

validate_misplaced_list_items()

validate_misplaced_list_items.

validate_tree 

validate_tree(root) -> bool

validate_tree.

DocumentOrigin

Bases: BaseModel

FileSource.

Methods:

Attributes:

binary_hash 

binary_hash: Uint64

filename 

filename: str

mimetype 

mimetype: str

uri 

uri: Optional[AnyUrl] = None

parse_hex_string 

parse_hex_string(value)

parse_hex_string.

validate_mimetype 

validate_mimetype(v)

validate_mimetype.

DocItem

Bases: NodeItem

DocItem.

Methods:

Attributes:

children 

children: List[RefItem] = []

content_layer 

content_layer: ContentLayer = BODY

label 

label: DocItemLabel

model_config 

model_config = ConfigDict(extra='forbid')

parent 

parent: Optional[RefItem] = None

prov 

prov: List[ProvenanceItem] = []

self_ref 

self_ref: str = Field(pattern=_JSON_POINTER_REGEX)

get_annotations 

get_annotations() -> Sequence[BaseAnnotation]

Get the annotations of this DocItem.

get_image 

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 

get_location_tokens(doc: DoclingDocument, new_line: str = '', xsize: int = 500, ysize: int = 500) -> str

Get the location string for the BaseCell.

get_ref 

get_ref() -> RefItem

get_ref.

DocItemLabel

Bases: str, Enum

DocItemLabel.

Methods:

  • get_color –

    Return the RGB color associated with a given label.

Attributes:

CAPTION 

CAPTION = 'caption'

CHART 

CHART = 'chart'

CHECKBOX_SELECTED 

CHECKBOX_SELECTED = 'checkbox_selected'

CHECKBOX_UNSELECTED 

CHECKBOX_UNSELECTED = 'checkbox_unselected'

CODE 

CODE = 'code'

DOCUMENT_INDEX 

DOCUMENT_INDEX = 'document_index'

EMPTY_VALUE 

EMPTY_VALUE = 'empty_value'

FOOTNOTE 

FOOTNOTE = 'footnote'

FORM 

FORM = 'form'

FORMULA 

FORMULA = 'formula'

GRADING_SCALE 

GRADING_SCALE = 'grading_scale'

HANDWRITTEN_TEXT 

HANDWRITTEN_TEXT = 'handwritten_text'

KEY_VALUE_REGION 

KEY_VALUE_REGION = 'key_value_region'

LIST_ITEM 

LIST_ITEM = 'list_item'

PAGE_FOOTER = 'page_footer'

PAGE_HEADER 

PAGE_HEADER = 'page_header'

PARAGRAPH 

PARAGRAPH = 'paragraph'

PICTURE 

PICTURE = 'picture'

REFERENCE 

REFERENCE = 'reference'

SECTION_HEADER 

SECTION_HEADER = 'section_header'

TABLE 

TABLE = 'table'

TEXT 

TEXT = 'text'

TITLE 

TITLE = 'title'

get_color 

get_color(label: DocItemLabel) -> Tuple[int, int, int]

Return the RGB color associated with a given label.

ProvenanceItem

Bases: BaseModel

ProvenanceItem.

Attributes:

bbox 

bbox: BoundingBox

charspan 

charspan: Tuple[int, int]

page_no 

page_no: int

GroupItem

Bases: NodeItem

GroupItem.

Methods:

Attributes:

children 

children: List[RefItem] = []

content_layer 

content_layer: ContentLayer = BODY

label 

label: GroupLabel = UNSPECIFIED

model_config 

model_config = ConfigDict(extra='forbid')

name 

name: str = 'group'

parent 

parent: Optional[RefItem] = None

self_ref 

self_ref: str = Field(pattern=_JSON_POINTER_REGEX)

get_ref 

get_ref() -> RefItem

get_ref.

GroupLabel

Bases: str, Enum

GroupLabel.

Attributes:

CHAPTER 

CHAPTER = 'chapter'

COMMENT_SECTION 

COMMENT_SECTION = 'comment_section'

FORM_AREA 

FORM_AREA = 'form_area'

INLINE 

INLINE = 'inline'

KEY_VALUE_AREA 

KEY_VALUE_AREA = 'key_value_area'

LIST 

LIST = 'list'

ORDERED_LIST 

ORDERED_LIST = 'ordered_list'

PICTURE_AREA 

PICTURE_AREA = 'picture_area'

SECTION 

SECTION = 'section'

SHEET 

SHEET = 'sheet'

SLIDE 

SLIDE = 'slide'

UNSPECIFIED 

UNSPECIFIED = 'unspecified'

NodeItem

Bases: BaseModel

NodeItem.

Methods:

Attributes:

children 

children: List[RefItem] = []

content_layer 

content_layer: ContentLayer = BODY

model_config 

model_config = ConfigDict(extra='forbid')

parent 

parent: Optional[RefItem] = None

self_ref 

self_ref: str = Field(pattern=_JSON_POINTER_REGEX)

get_ref 

get_ref() -> RefItem

get_ref.

PageItem

Bases: BaseModel

PageItem.

Attributes:

image 

image: Optional[ImageRef] = None

page_no 

page_no: int

size 

size: Size

FloatingItem

Bases: DocItem

FloatingItem.

Methods:

Attributes:

captions 

captions: List[RefItem] = []

children 

children: List[RefItem] = []

content_layer 

content_layer: ContentLayer = BODY

footnotes 

footnotes: List[RefItem] = []

image 

image: Optional[ImageRef] = None

label 

label: DocItemLabel

model_config 

model_config = ConfigDict(extra='forbid')

parent 

parent: Optional[RefItem] = None

prov 

prov: List[ProvenanceItem] = []

references 

references: List[RefItem] = []

self_ref 

self_ref: str = Field(pattern=_JSON_POINTER_REGEX)

caption_text 

caption_text(doc: DoclingDocument) -> str

Computes the caption as a single text.

get_annotations 

get_annotations() -> Sequence[BaseAnnotation]

Get the annotations of this DocItem.

get_image 

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 

get_location_tokens(doc: DoclingDocument, new_line: str = '', xsize: int = 500, ysize: int = 500) -> str

Get the location string for the BaseCell.

get_ref 

get_ref() -> RefItem

get_ref.

TextItem

Bases: DocItem

TextItem.

Methods:

Attributes:

children 

children: List[RefItem] = []

content_layer 

content_layer: ContentLayer = BODY

formatting 

formatting: Optional[Formatting] = None

hyperlink: Optional[Union[AnyUrl, Path]] = Field(union_mode='left_to_right', default=None)

label 

label: Literal[CAPTION, CHECKBOX_SELECTED, CHECKBOX_UNSELECTED, FOOTNOTE, PAGE_FOOTER, PAGE_HEADER, PARAGRAPH, REFERENCE, TEXT, EMPTY_VALUE]

model_config 

model_config = ConfigDict(extra='forbid')

orig 

orig: str

parent 

parent: Optional[RefItem] = None

prov 

prov: List[ProvenanceItem] = []

self_ref 

self_ref: str = Field(pattern=_JSON_POINTER_REGEX)

text 

text: str

export_to_doctags 

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.

Parameters:

  • doc (DoclingDocument) –

    "DoclingDocument":

  • new_line (str, default: '' ) –

    str (Default value = "") Deprecated

  • xsize (int, default: 500 ) –

    int: (Default value = 500)

  • ysize (int, default: 500 ) –

    int: (Default value = 500)

  • add_location (bool, default: True ) –

    bool: (Default value = True)

  • add_content (bool, default: True ) –

    bool: (Default value = True)

export_to_document_tokens 

export_to_document_tokens(*args, **kwargs)

Export to DocTags format.

get_annotations 

get_annotations() -> Sequence[BaseAnnotation]

Get the annotations of this DocItem.

get_image 

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 

get_location_tokens(doc: DoclingDocument, new_line: str = '', xsize: int = 500, ysize: int = 500) -> str

Get the location string for the BaseCell.

get_ref 

get_ref() -> RefItem

get_ref.

TableItem

Bases: FloatingItem

TableItem.

Methods:

Attributes:

annotations 

annotations: List[TableAnnotationType] = []

captions 

captions: List[RefItem] = []

children 

children: List[RefItem] = []

content_layer 

content_layer: ContentLayer = BODY

data 

data: TableData

footnotes 

footnotes: List[RefItem] = []

image 

image: Optional[ImageRef] = None

label 

label: Literal[DOCUMENT_INDEX, TABLE] = TABLE

model_config 

model_config = ConfigDict(extra='forbid')

parent 

parent: Optional[RefItem] = None

prov 

prov: List[ProvenanceItem] = []

references 

references: List[RefItem] = []

self_ref 

self_ref: str = Field(pattern=_JSON_POINTER_REGEX)

add_annotation 

add_annotation(annotation: TableAnnotationType) -> None

Add an annotation to the table.

caption_text 

caption_text(doc: DoclingDocument) -> str

Computes the caption as a single text.

export_to_dataframe 

export_to_dataframe() -> DataFrame

Export the table as a Pandas DataFrame.

export_to_doctags 

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.

Parameters:

  • doc (DoclingDocument) –

    "DoclingDocument":

  • new_line (str, default: '' ) –

    str (Default value = "") Deprecated

  • xsize (int, default: 500 ) –

    int: (Default value = 500)

  • ysize (int, default: 500 ) –

    int: (Default value = 500)

  • add_location (bool, default: True ) –

    bool: (Default value = True)

  • add_cell_location (bool, default: True ) –

    bool: (Default value = True)

  • add_cell_text (bool, default: True ) –

    bool: (Default value = True)

  • add_caption (bool, default: True ) –

    bool: (Default value = True)

export_to_document_tokens 

export_to_document_tokens(*args, **kwargs)

Export to DocTags format.

export_to_html 

export_to_html(doc: Optional[DoclingDocument] = None, add_caption: bool = True) -> str

Export the table as html.

export_to_markdown 

export_to_markdown(doc: Optional[DoclingDocument] = None) -> str

Export the table as markdown.

export_to_otsl 

export_to_otsl(doc: DoclingDocument, add_cell_location: bool = True, add_cell_text: bool = True, xsize: int = 500, ysize: int = 500) -> str

Export the table as OTSL.

get_annotations 

get_annotations() -> Sequence[BaseAnnotation]

Get the annotations of this TableItem.

get_image 

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 

get_location_tokens(doc: DoclingDocument, new_line: str = '', xsize: int = 500, ysize: int = 500) -> str

Get the location string for the BaseCell.

get_ref 

get_ref() -> RefItem

get_ref.

TableCell

Bases: BaseModel

TableCell.

Methods:

Attributes:

bbox 

bbox: Optional[BoundingBox] = None

col_span 

col_span: int = 1

column_header 

column_header: bool = False

end_col_offset_idx 

end_col_offset_idx: int

end_row_offset_idx 

end_row_offset_idx: int

row_header 

row_header: bool = False

row_section 

row_section: bool = False

row_span 

row_span: int = 1

start_col_offset_idx 

start_col_offset_idx: int

start_row_offset_idx 

start_row_offset_idx: int

text 

text: str

from_dict_format 

from_dict_format(data: Any) -> Any

from_dict_format.

TableData

Bases: BaseModel

BaseTableData.

Methods:

  • add_row –

    Add a new row to the table from a list of strings.

  • add_rows –

    Add multiple new rows to the table from a list of lists of strings.

  • get_column_bounding_boxes –

    Get the minimal bounding box for each column in the table.

  • get_row_bounding_boxes –

    Get the minimal bounding box for each row in the table.

  • insert_row –

    Insert a new row from a list of strings before/after a specific index in the table.

  • insert_rows –

    Insert multiple new rows from a list of lists of strings before/after a specific index in the table.

  • pop_row –

    Remove and return the last row from the table.

  • remove_row –

    Remove a row from the table by its index.

  • remove_rows –

    Remove rows from the table by their indices.

Attributes:

grid 

grid: List[List[TableCell]]

grid.

num_cols 

num_cols: int = 0

num_rows 

num_rows: int = 0

table_cells 

table_cells: List[TableCell] = []

add_row 

add_row(row: List[str]) -> None

Add a new row to the table from a list of strings.

Parameters:

  • row (List[str]) –

    List[str]: A list of strings representing the content of the new row.

Returns:

  • None –

    None

add_rows 

add_rows(rows: List[List[str]]) -> None

Add multiple new rows to the table from a list of lists of strings.

Parameters:

  • rows (List[List[str]]) –

    List[List[str]]: A list of lists, where each inner list represents the content of a new row.

Returns:

  • None –

    None

get_column_bounding_boxes 

get_column_bounding_boxes() -> dict[int, BoundingBox]

Get the minimal bounding box for each column in the table.

Returns: List[Optional[BoundingBox]]: A list where each element is the minimal bounding box that encompasses all cells in that column, or None if no cells in the column have bounding boxes.

get_row_bounding_boxes 

get_row_bounding_boxes() -> dict[int, BoundingBox]

Get the minimal bounding box for each row in the table.

Returns: List[Optional[BoundingBox]]: A list where each element is the minimal bounding box that encompasses all cells in that row, or None if no cells in the row have bounding boxes.

insert_row 

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.

Parameters:

  • row_index (int) –

    int: The index at which to insert the new row. (Starting from 0)

  • row (List[str]) –

    List[str]: A list of strings representing the content of the new row.

  • after (bool, default: False ) –

    bool: If True, insert the row after the specified index, otherwise before it. (Default is False)

Returns:

  • None –

    None

insert_rows 

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.

Parameters:

  • row_index (int) –

    int: The index at which to insert the new rows. (Starting from 0)

  • rows (List[List[str]]) –

    List[List[str]]: A list of lists, where each inner list represents the content of a new row.

  • after (bool, default: False ) –

    bool: If True, insert the rows after the specified index, otherwise before it. (Default is False)

Returns:

  • None –

    None

pop_row 

pop_row() -> List[TableCell]

Remove and return the last row from the table.

Returns:

  • List[TableCell] –

    List[TableCell]: A list of TableCell objects representing the popped row.

remove_row 

remove_row(row_index: int) -> List[TableCell]

Remove a row from the table by its index.

Parameters:

  • row_index (int) –

    int: The index of the row to remove. (Starting from 0)

Returns:

  • List[TableCell] –

    List[TableCell]: A list of TableCell objects representing the removed row.

remove_rows 

remove_rows(indices: List[int]) -> List[List[TableCell]]

Remove rows from the table by their indices.

Parameters:

  • indices (List[int]) –

    List[int]: A list of indices of the rows to remove. (Starting from 0)

Returns:

  • List[List[TableCell]] –

    List[List[TableCell]]: A list representation of the removed rows as lists of TableCell objects.

TableCellLabel

Bases: str, Enum

TableCellLabel.

Methods:

  • get_color –

    Return the RGB color associated with a given label.

Attributes:

BODY 

BODY = 'body'

COLUMN_HEADER 

COLUMN_HEADER = 'col_header'

ROW_HEADER 

ROW_HEADER = 'row_header'

ROW_SECTION 

ROW_SECTION = 'row_section'

get_color 

get_color(label: TableCellLabel) -> Tuple[int, int, int]

Return the RGB color associated with a given label.

KeyValueItem

Bases: FloatingItem

KeyValueItem.

Methods:

Attributes:

captions 

captions: List[RefItem] = []

children 

children: List[RefItem] = []

content_layer 

content_layer: ContentLayer = BODY

footnotes 

footnotes: List[RefItem] = []

graph 

graph: GraphData

image 

image: Optional[ImageRef] = None

label 

label: Literal[KEY_VALUE_REGION] = KEY_VALUE_REGION

model_config 

model_config = ConfigDict(extra='forbid')

parent 

parent: Optional[RefItem] = None

prov 

prov: List[ProvenanceItem] = []

references 

references: List[RefItem] = []

self_ref 

self_ref: str = Field(pattern=_JSON_POINTER_REGEX)

caption_text 

caption_text(doc: DoclingDocument) -> str

Computes the caption as a single text.

export_to_document_tokens 

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.

Parameters:

  • doc (DoclingDocument) –

    "DoclingDocument":

  • new_line (str, default: '' ) –

    str (Default value = "") Deprecated

  • xsize (int, default: 500 ) –

    int: (Default value = 500)

  • ysize (int, default: 500 ) –

    int: (Default value = 500)

  • add_location (bool, default: True ) –

    bool: (Default value = True)

  • add_content (bool, default: True ) –

    bool: (Default value = True)

get_annotations 

get_annotations() -> Sequence[BaseAnnotation]

Get the annotations of this DocItem.

get_image 

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 

get_location_tokens(doc: DoclingDocument, new_line: str = '', xsize: int = 500, ysize: int = 500) -> str

Get the location string for the BaseCell.

get_ref 

get_ref() -> RefItem

get_ref.

SectionHeaderItem

Bases: TextItem

SectionItem.

Methods:

Attributes:

children 

children: List[RefItem] = []

content_layer 

content_layer: ContentLayer = BODY

formatting 

formatting: Optional[Formatting] = None

hyperlink: Optional[Union[AnyUrl, Path]] = Field(union_mode='left_to_right', default=None)

label 

label: Literal[SECTION_HEADER] = SECTION_HEADER

level 

level: LevelNumber = 1

model_config 

model_config = ConfigDict(extra='forbid')

orig 

orig: str

parent 

parent: Optional[RefItem] = None

prov 

prov: List[ProvenanceItem] = []

self_ref 

self_ref: str = Field(pattern=_JSON_POINTER_REGEX)

text 

text: str

export_to_doctags 

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.

Parameters:

  • doc (DoclingDocument) –

    "DoclingDocument":

  • new_line (str, default: '' ) –

    str (Default value = "") Deprecated

  • xsize (int, default: 500 ) –

    int: (Default value = 500)

  • ysize (int, default: 500 ) –

    int: (Default value = 500)

  • add_location (bool, default: True ) –

    bool: (Default value = True)

  • add_content (bool, default: True ) –

    bool: (Default value = True)

export_to_document_tokens 

export_to_document_tokens(*args, **kwargs)

Export to DocTags format.

get_annotations 

get_annotations() -> Sequence[BaseAnnotation]

Get the annotations of this DocItem.

get_image 

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 

get_location_tokens(doc: DoclingDocument, new_line: str = '', xsize: int = 500, ysize: int = 500) -> str

Get the location string for the BaseCell.

get_ref 

get_ref() -> RefItem

get_ref.

PictureItem

Bases: FloatingItem

PictureItem.

Methods:

Attributes:

annotations 

annotations: List[PictureDataType] = []

captions 

captions: List[RefItem] = []

children 

children: List[RefItem] = []

content_layer 

content_layer: ContentLayer = BODY

footnotes 

footnotes: List[RefItem] = []

image 

image: Optional[ImageRef] = None

label 

label: Literal[PICTURE, CHART] = PICTURE

model_config 

model_config = ConfigDict(extra='forbid')

parent 

parent: Optional[RefItem] = None

prov 

prov: List[ProvenanceItem] = []

references 

references: List[RefItem] = []

self_ref 

self_ref: str = Field(pattern=_JSON_POINTER_REGEX)

caption_text 

caption_text(doc: DoclingDocument) -> str

Computes the caption as a single text.

export_to_doctags 

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.

Parameters:

  • doc (DoclingDocument) –

    "DoclingDocument":

  • new_line (str, default: '' ) –

    str (Default value = "") Deprecated

  • xsize (int, default: 500 ) –

    int: (Default value = 500)

  • ysize (int, default: 500 ) –

    int: (Default value = 500)

  • add_location (bool, default: True ) –

    bool: (Default value = True)

  • add_caption (bool, default: True ) –

    bool: (Default value = True)

  • add_content (bool, default: True ) –

    bool: (Default value = True)

export_to_document_tokens 

export_to_document_tokens(*args, **kwargs)

Export to DocTags format.

export_to_html 

export_to_html(doc: DoclingDocument, add_caption: bool = True, image_mode: ImageRefMode = PLACEHOLDER) -> str

Export picture to HTML format.

export_to_markdown 

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 

get_annotations() -> Sequence[BaseAnnotation]

Get the annotations of this PictureItem.

get_image 

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 

get_location_tokens(doc: DoclingDocument, new_line: str = '', xsize: int = 500, ysize: int = 500) -> str

Get the location string for the BaseCell.

get_ref 

get_ref() -> RefItem

get_ref.

ImageRef

Bases: BaseModel

ImageRef.

Methods:

Attributes:

dpi 

dpi: int

mimetype 

mimetype: str

pil_image 

pil_image: Optional[Image]

Return the PIL Image.

size 

size: Size

uri 

uri: Union[AnyUrl, Path] = Field(union_mode='left_to_right')

from_pil 

from_pil(image: Image, dpi: int) -> Self

Construct ImageRef from a PIL Image.

validate_mimetype 

validate_mimetype(v)

validate_mimetype.

PictureClassificationClass

Bases: BaseModel

PictureClassificationData.

Attributes:

class_name 

class_name: str

confidence 

confidence: float

PictureClassificationData

Bases: BaseAnnotation

PictureClassificationData.

Attributes:

kind 

kind: Literal['classification'] = 'classification'

predicted_classes 

predicted_classes: List[PictureClassificationClass]

provenance 

provenance: str

RefItem

Bases: BaseModel

RefItem.

Methods:

Attributes:

cref 

cref: str = Field(alias='$ref', pattern=_JSON_POINTER_REGEX)

model_config 

model_config = ConfigDict(populate_by_name=True)

get_ref 

get_ref()

get_ref.

resolve 

resolve(doc: DoclingDocument)

Resolve the path in the document.

BoundingBox

Bases: BaseModel

BoundingBox.

Methods:

Attributes:

b 

b: float

coord_origin 

coord_origin: CoordOrigin = TOPLEFT

height 

height

height.

l 

l: float

r 

r: float

t 

t: float

width 

width

width.

area 

area() -> float

area.

as_tuple 

as_tuple() -> Tuple[float, float, float, float]

as_tuple.

enclosing_bbox 

enclosing_bbox(boxes: List[BoundingBox]) -> BoundingBox

Create a bounding box that covers all of the given boxes.

expand_by_scale 

expand_by_scale(x_scale: float, y_scale: float) -> BoundingBox

expand_to_size.

from_tuple 

from_tuple(coord: Tuple[float, ...], origin: CoordOrigin)

from_tuple.

Parameters:

  • coord (Tuple[float, ...]) –

    Tuple[float:

  • ...] –
  • origin (CoordOrigin) –

    CoordOrigin:

intersection_area_with 

intersection_area_with(other: BoundingBox) -> float

Calculate the intersection area with another bounding box.

intersection_over_self 

intersection_over_self(other: BoundingBox, eps: float = 1e-06) -> float

intersection_over_self.

intersection_over_union 

intersection_over_union(other: BoundingBox, eps: float = 1e-06) -> float

intersection_over_union.

is_above 

is_above(other: BoundingBox) -> bool

is_above.

is_horizontally_connected 

is_horizontally_connected(elem_i: BoundingBox, elem_j: BoundingBox) -> bool

is_horizontally_connected.

is_left_of 

is_left_of(other: BoundingBox) -> bool

is_left_of.

is_strictly_above 

is_strictly_above(other: BoundingBox, eps: float = 0.001) -> bool

is_strictly_above.

is_strictly_left_of 

is_strictly_left_of(other: BoundingBox, eps: float = 0.001) -> bool

is_strictly_left_of.

normalized 

normalized(page_size: Size)

normalized.

overlaps 

overlaps(other: BoundingBox) -> bool

overlaps.

overlaps_horizontally 

overlaps_horizontally(other: BoundingBox) -> bool

Check if two bounding boxes overlap horizontally.

overlaps_vertically 

overlaps_vertically(other: BoundingBox) -> bool

Check if two bounding boxes overlap vertically.

overlaps_vertically_with_iou 

overlaps_vertically_with_iou(other: BoundingBox, iou: float) -> bool

overlaps_y_with_iou.

resize_by_scale 

resize_by_scale(x_scale: float, y_scale: float)

resize_by_scale.

scale_to_size 

scale_to_size(old_size: Size, new_size: Size)

scale_to_size.

scaled 

scaled(scale: float)

scaled.

to_bottom_left_origin 

to_bottom_left_origin(page_height: float) -> BoundingBox

to_bottom_left_origin.

Parameters:

  • page_height (float) –

to_top_left_origin 

to_top_left_origin(page_height: float) -> BoundingBox

to_top_left_origin.

Parameters:

  • page_height (float) –

union_area_with 

union_area_with(other: BoundingBox) -> float

Calculates the union area with another bounding box.

x_overlap_with 

x_overlap_with(other: BoundingBox) -> float

Calculates the horizontal overlap with another bounding box.

x_union_with 

x_union_with(other: BoundingBox) -> float

Calculates the horizontal union dimension with another bounding box.

y_overlap_with 

y_overlap_with(other: BoundingBox) -> float

Calculates the vertical overlap with another bounding box, respecting coordinate origin.

y_union_with 

y_union_with(other: BoundingBox) -> float

Calculates the vertical union dimension with another bounding box, respecting coordinate origin.

CoordOrigin

Bases: str, Enum

CoordOrigin.

Attributes:

BOTTOMLEFT 

BOTTOMLEFT = 'BOTTOMLEFT'

TOPLEFT 

TOPLEFT = 'TOPLEFT'

ImageRefMode

Bases: str, Enum

ImageRefMode.

Attributes:

EMBEDDED 

EMBEDDED = 'embedded'

PLACEHOLDER 

PLACEHOLDER = 'placeholder'

REFERENCED 

REFERENCED = 'referenced'

Size

Bases: BaseModel

Size.

Methods:

Attributes:

height 

height: float = 0.0

width 

width: float = 0.0

as_tuple 

as_tuple()

as_tuple.