Class TextExtractionElement

Namespace: LMKit.Extraction

Assembly: LM-Kit.NET.dll

Represents an element used in text extraction processes, encapsulating metadata such as name, type, description, and optional nested elements for complex data structures.

public sealed class TextExtractionElement

Inheritance: object

TextExtractionElement

Inherited Members: object.Equals(object)

object.Equals(object, object)

object.GetHashCode()

object.GetType()

object.ReferenceEquals(object, object)

object.ToString()

Examples

Example: Simple flat schema

using LMKit.Extraction;
using LMKit.Data;
using System;

// A flat schema with primitive types
var invoiceNo = new TextExtractionElement("InvoiceNumber", ElementType.String, "Human-readable invoice ID", isRequired: true);
var issueDate = new TextExtractionElement("IssueDate", ElementType.Date, "Date the invoice was issued");
var total = new TextExtractionElement("Total", ElementType.Double, "Total amount including tax");
var isPaid = new TextExtractionElement("IsPaid", ElementType.Bool, "Whether payment has been received");

Example: Nested object structure

using LMKit.Extraction;
using LMKit.Data;
using System;

// A nested object for vendor information
var vendor = new TextExtractionElement(
    "Vendor",
    new[]
    {
        new TextExtractionElement("Name", ElementType.String, "Company name"),
        new TextExtractionElement("Country", ElementType.String, "Country of origin"),
        new TextExtractionElement("TaxId", ElementType.String, "Tax identification number")
    },
    isArray: false,
    description: "Supplier information");

Example: Array of objects

using LMKit.Extraction;
using LMKit.Data;
using System;

// An array of line items
var lineItems = new TextExtractionElement(
    "LineItems",
    new[]
    {
        new TextExtractionElement("Sku", ElementType.String, "Product SKU"),
        new TextExtractionElement("Description", ElementType.String, "Item description"),
        new TextExtractionElement("Quantity", ElementType.Integer, "Number of units"),
        new TextExtractionElement("UnitPrice", ElementType.Double, "Price per unit")
    },
    isArray: true,
    description: "List of items on the invoice");

Example: Using enum values

using LMKit.Extraction;
using LMKit.Data;
using System;
using System.Collections.Generic;

// Element with constrained allowed values
var priority = new TextExtractionElement("Priority", ElementType.String, "Task priority level");
priority.Format.AllowedValues = new List<string> { "Low", "Medium", "High", "Critical" };

var status = new TextExtractionElement("Status", ElementType.String, "Current status");
status.Format.AllowedValues = new List<string> { "Pending", "InProgress", "Completed", "Cancelled" };

Remarks

The TextExtractionElement class is designed to model elements within a text extraction schema. It supports simple data types as well as complex types with nested elements, enabling the representation of hierarchical data models.

Supported Element Types

String - Text values
Integer - Whole numbers
Double - Floating-point numbers
Bool - True/false values
Date - Date values
Date - Date and time values
StringArray - Arrays of strings
IntegerArray - Arrays of integers
DoubleArray - Arrays of decimals
Object - Nested object with child elements
ObjectArray - Array of nested objects

Key Properties

Name - Unique identifier for the element
Type - Data type of the element
Description - Helps the LLM understand what to extract
IsRequired - Whether the element must be present
Format with AllowedValues - Constrain values to a specific set
Format - Formatting options (case, length, etc.)
InnerElements - Child elements for nested objects

Constructors

TextExtractionElement(string, ElementType, string, bool): Initializes a new instance of the TextExtractionElement class representing a simple data element.

TextExtractionElement(string, IEnumerable<TextExtractionElement>, bool, string, bool): Initializes a new instance of the TextExtractionElement class representing a complex object or an array with nested elements.

Properties

Description: Gets the descriptive text associated with the extraction element.

DetectedEntityKind: Gets the semantic entity kind that was automatically detected from the element name and type (for example, EmailAddress, Iban, or PhoneNumber).

ElementType: Gets the data type of the extraction element.

Format: Gets the format settings applied to this extraction element.

InnerElements: Gets a read-only list of nested TextExtractionElement instances if this element contains inner elements.

IsArray: Gets a value indicating whether this element represents an array.

IsArrayOfObject: Gets a value indicating whether this element represents an array of objects.

IsObject: Gets a value indicating whether this element represents a complex object with nested elements.

IsRequired: Gets or sets a value indicating whether this element must be present in the extracted output.

Name: Gets the original name of the extraction element.

Table of Contents

Class TextExtractionElement

Examples

Remarks

Constructors

Properties