Class PiiExtraction
- Namespace
- LMKit.TextAnalysis
- Assembly
- LM-Kit.NET.dll
A class for performing PII extraction on input content using a Language Model (LM). This class identifies and extracts all occurrences of specified PII entity types (built‐in or custom) from the provided content, returning each entity verbatim along with its type and optional positional information.
public sealed class PiiExtraction- Inheritance
-
PiiExtraction
- Inherited Members
Remarks
Use this class to extract PII such as persons, organization identifiers, locations, dates, etc., by leveraging an underlying LMKit LM model. You can customize which PII types to extract by setting the PiiEntityDefinitions property.
Constructors
- PiiExtraction(LM)
Initializes a new instance of PiiExtraction with default entity definitions (all built‐in PiiExtraction.PiiEntityType values except Custom).
- PiiExtraction(LM, List<PiiEntityDefinition>)
Initializes a new instance of PiiExtraction with a custom list of entity definitions.
Properties
- Confidence
Gets the confidence score of the last extraction operation.
- Guidance
Gets or sets semantic guidance for the extraction process.
- MaxContextLength
Gets or sets the maximum context length (in tokens) used during PII extraction.
- OcrEngine
Gets or sets the OCR engine used to perform optical character recognition on image attachments during PII extraction.
- PiiEntityDefinitions
Gets or sets the list of entity types (built‐in and/or custom) that this extractor will capture. Must contain at least one PiiExtraction.PiiEntityDefinition; otherwise, an ArgumentNullException is thrown.
- PreferredInferenceModality
Gets or sets the preferred modality for inference. This determines whether text, image, or both modalities are used when processing input. Defaults to Multimodal.
Methods
- Extract(Attachment, CancellationToken)
Synchronously recognizes PII in the given image attachment.
- Extract(string, CancellationToken)
Synchronously recognizes PII in the given
content.
- ExtractAsync(Attachment, CancellationToken)
Asynchronously recognizes PII in the given image attachment.
- ExtractAsync(string, CancellationToken)
Asynchronously recognizes PII in the given
content.