Confidence

Confidence expresses how certain the API is about a piece of extracted information. The model wraps the probability value together with qualitative categories and the extraction source, allowing you to calibrate post-processing logic. High confidence results can be consumed automatically, while lower scores might trigger human review or cross-checks against ERP data. The object also records contextual hints, such as whether the value was derived from text, symbols, or geometric analysis. By exposing these details, the API enables transparent decision-making and traceability, which are essential when automating workflows that historically required manual validation. Treat the Confidence class as a signal for prioritizing work queues, designing escalation rules, or measuring how changes in drawing templates affect parsing accuracy over time.

53
54
55
56
57
58
59
60
61
62

class Confidence(BaseModel):
    """
    Represents a confidence score for a feature or measurement.
    """

    score: Decimal = Field(
        ...,
        description="The confidence score of the feature, indicating the confidence the symstem has in the reading.",
        examples=[Decimal("0.75")],
    )