ParseSettings

Settings for Parse. Values fall back through three levels: document → SDK → built-in default. Writes target the document only when set on a document’s settings, otherwise the SDK globally when set on SdkSettings.

Tags: Vision

from nutrient_sdk import ParseSettings

Construction

# Per-document override
with Document.open("input.pdf") as doc:
    settings = doc.settings.parse_settings
    settings.some_field = new_value          # mutate fields directly

# SDK-wide default (applies to all documents)
SdkSettings.parse_settings.some_field = new_value

Settings are configured by writing to fields on the returned object. The settings property itself cannot be reassigned — doc.settings.parse_settings = other_settings is rejected.

Properties

emit_figure_placeholders

@property
def emit_figure_placeholders(self) -> bool

@emit_figure_placeholders.setter
def emit_figure_placeholders(self, value: bool) -> None

Controls whether pictures that have no alt text and no extractable words emit a [Figure] placeholder line in the Markdown output. When enabled, such pictures are marked with the placeholder; when disabled, they emit nothing. Pictures with alt text are unaffected and always render as ![alt]().

Type: bool

enable_inline_formatting

@property
def enable_inline_formatting(self) -> bool

@enable_inline_formatting.setter
def enable_inline_formatting(self, value: bool) -> None

Controls whether inline text formatting is preserved in the Markdown output using Markdown or inline HTML markers for bold, italic, underline, highlight, strikethrough, superscript, and subscript text.

Type: bool

enable_semantic_block_formatting

@property
def enable_semantic_block_formatting(self) -> bool

@enable_semantic_block_formatting.setter
def enable_semantic_block_formatting(self, value: bool) -> None

Controls whether footnotes render as a blockquote (>) and whether pictures, charts and barcodes are emitted at all (pictures render as ![alt]() when they carry alt text; refer to emit_figure_placeholders for pictures without one; charts render as their table only). When false, footnotes render as plain paragraphs and pictures, charts and barcodes are dropped entirely. Captions render as plain paragraphs and list items with - regardless.

Type: bool

export_formats

@property
def export_formats(self) -> list

@export_formats.setter
def export_formats(self, value: list) -> None

Several export formats at once. Overrides exportFormat. Supported values: json, markdown. Each format is returned as its own artifact (document.json, document.md). Over HTTP, several artifacts arrive as one TAR archive.

Type: list

extract_words_from_pictures

@property
def extract_words_from_pictures(self) -> bool

@extract_words_from_pictures.setter
def extract_words_from_pictures(self, value: bool) -> None

Controls whether words detected inside picture regions are emitted as plain text in Markdown output. This helps preserve chart labels, axis text, legends, and similar image-contained text when available.

Type: bool

include_diagnostics

@property
def include_diagnostics(self) -> Optional[bool]

@include_diagnostics.setter
def include_diagnostics(self, value: Optional[bool]) -> None

When true, emit diagnostics.json when VLM/model diagnostics were produced.

Type: Optional[bool]

include_headers_and_footers

@property
def include_headers_and_footers(self) -> bool

@include_headers_and_footers.setter
def include_headers_and_footers(self, value: bool) -> None

Controls whether running page headers and footers are included in the Markdown output. When enabled, their content (agency ids, case numbers, page numbers, letterhead) is emitted so it stays available to readers and language models. Set emit_header_footer_markers to also wrap it in comment markers.

Type: bool

include_words

@property
def include_words(self) -> Optional[bool]

@include_words.setter
def include_words(self, value: Optional[bool]) -> None

Include word-level details with bounding boxes

Type: Optional[bool]

inverse_deskew

@property
def inverse_deskew(self) -> bool

@inverse_deskew.setter
def inverse_deskew(self, value: bool) -> None

Indicates whether the inverse deskew transform is enabled. When disabled, bounding boxes remain in deskewed-image coordinates. Applies to the recognition pipelines only. A page-level deskew rotates the page content itself, so there are no detected coordinates to map back.

Type: bool

output_directory

@property
def output_directory(self) -> str

@output_directory.setter
def output_directory(self, value: str) -> None

Directory to write all emitted artifacts to (optional). Each artifact is written under its artifact name, for example document.json.

Type: str

output_file_path

@property
def output_file_path(self) -> str

@output_file_path.setter
def output_file_path(self, value: str) -> None

Path to write the single exported artifact to a file (optional). Fails if the chosen format emits multiple artifacts.

Type: str

pretty_print

@property
def pretty_print(self) -> Optional[bool]

@pretty_print.setter
def pretty_print(self, value: Optional[bool]) -> None

Emit indented JSON

Type: Optional[bool]

use_html_tables

@property
def use_html_tables(self) -> bool

@use_html_tables.setter
def use_html_tables(self, value: bool) -> None

Controls how tables are rendered in the Markdown output. When enabled, tables are emitted as HTML (<table>/<tr>/<td>) preserving row/column spans where available; when disabled, tables render as pipe-style Markdown.

Type: bool