AiAugmenterSettings

Settings for AiAugmenter. 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, Advanced

from nutrient_sdk import AiAugmenterSettings

Construction

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

# SDK-wide default (applies to all documents)
SdkSettings.ai_augmenter_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.ai_augmenter_settings = other_settings is rejected.

Properties

classification_confidence

@property
def classification_confidence(self) -> float

@classification_confidence.setter
def classification_confidence(self, value: float) -> None

Minimum confidence threshold for zone classification (0.0 - 1.0).

Type: float

Default: 0.7f

enable_content_description

@property
def enable_content_description(self) -> bool

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

Enable content description extraction for each zone. When enabled, the VLM will provide descriptions of zone content.

Type: bool

Default: true

enable_language_detection

@property
def enable_language_detection(self) -> bool

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

Indicates whether language detection is enabled for text zones.

Type: bool

Default: true

enable_reading_order

@property
def enable_reading_order(self) -> bool

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

Indicates whether reading order analysis is enabled.

Type: bool

Default: true

enable_relationship_detection

@property
def enable_relationship_detection(self) -> bool

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

Indicates whether relationship detection between zones is enabled.

Type: bool

Default: true

enable_vlm_classification

@property
def enable_vlm_classification(self) -> bool

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

Enable or disable VLM-based classification. When disabled, falls back to heuristic classification.

Type: bool

Default: true

reasoning_effort

@property
def reasoning_effort(self) -> str

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

Reasoning-effort budget for reasoning models: default, none, minimal, low, medium, high, or xhigh (case-insensitive). default — the default — sends nothing, leaving the provider’s own budget in force (medium on the OpenAI GPT-5 family). It is spelled out rather than left empty so the intent is readable in a settings file and in the generated API surface. Lower budgets cut latency and reasoning tokens at some cost in recognition quality; which values a given model accepts is decided by the provider, not by this SDK, so an unrecognized value is ignored rather than rejected.

Type: str

Default: "default"