Expand description
Core data types for the annotation pipeline.
This module defines the fundamental data structures used throughout the langextract library, including documents, extractions, and configuration types.
Structs§
- Annotated
Document - Annotated document with extractions
- Char
Interval - Represents a character interval in text
- Document
- Document class for input text
- Example
Data - Example data for training/prompting
- Extraction
- Represents an extraction extracted from text
- Token
Interval - Token interval information (placeholder for future tokenizer integration)
Enums§
- Alignment
Status - Status indicating how well an extraction aligns with the source text
- Format
Type - Enumeration of supported output formats