# lextract v0.1.3 - Table of Contents

> LLM-powered text extraction library for Elixir. Based on Google's LangExtract

## Pages

- [Changelog](changelog.md)
- [Introduction](readme.md)
- [License](license.md)

## Modules

- [LeXtract](LeXtract.md): # LeXtract
- [LeXtract.Alignment](LeXtract.Alignment.md): Aligns extracted entities back to their positions in source text.
- [LeXtract.AlignmentStatus](LeXtract.AlignmentStatus.md): Represents the quality/status of text alignment.
- [LeXtract.AnnotatedDocument](LeXtract.AnnotatedDocument.md): Represents a document with extracted entities and relationships.
- [LeXtract.Annotator](LeXtract.Annotator.md): Annotates documents with extractions using LLMs.
- [LeXtract.CharInterval](LeXtract.CharInterval.md): Represents a character position interval in text.
- [LeXtract.Chunking](LeXtract.Chunking.md): Integrates semantic text chunking with tokenization for document processing.
- [LeXtract.Config](LeXtract.Config.md): Configuration for extraction operations using NimbleOptions for validation.
- [LeXtract.Document](LeXtract.Document.md): Represents an input document for information extraction.
- [LeXtract.Error](LeXtract.Error.md): Main error aggregator for LeXtract using Splode.
- [LeXtract.ExampleData](LeXtract.ExampleData.md): Represents a training example for extraction with input text and expected output.
- [LeXtract.Extraction](LeXtract.Extraction.md): Represents a single extracted entity with alignment information.
- [LeXtract.FormatHandler](LeXtract.FormatHandler.md): Handles detection and parsing of different text formats (JSON, YAML).
- [LeXtract.FormatType](LeXtract.FormatType.md): Enumeration of supported format types for parsing LLM outputs.
- [LeXtract.LLM](LeXtract.LLM.md): Behaviour for pluggable LLM adapters.
- [LeXtract.LLM.ReqLLM](LeXtract.LLM.ReqLLM.md): Default `LeXtract.LLM` adapter, backed by the `req_llm` library.
- [LeXtract.Prompting](LeXtract.Prompting.md): Prompt generation for LLM extraction.
- [LeXtract.Resolver](LeXtract.Resolver.md): Parses LLM output into Extraction structs.
- [LeXtract.Schema](LeXtract.Schema.md): Generate and manage NimbleOptions schemas from extraction examples.
- [LeXtract.Schema.Analyzer](LeXtract.Schema.Analyzer.md): Analyzes example extractions to infer schema information.
- [LeXtract.TextChunk](LeXtract.TextChunk.md): Represents a chunk of text from a document, used for processing long documents.
- [LeXtract.TokenInterval](LeXtract.TokenInterval.md): Represents a token position interval.
- [LeXtract.Tokenizer](LeXtract.Tokenizer.md): Tokenization wrapper using Hugging Face Tokenizers library.

- Exceptions
  - [LeXtract.Error.External](LeXtract.Error.External.md): Error class for external service and resource failures.
  - [LeXtract.Error.External.Annotation](LeXtract.Error.External.Annotation.md): Error for LLM annotation/inference failures.
  - [LeXtract.Error.External.TemplateRead](LeXtract.Error.External.TemplateRead.md): Error for template file I/O failures.
  - [LeXtract.Error.External.TokenizerLoad](LeXtract.Error.External.TokenizerLoad.md): Error for tokenizer loading failures.
  - [LeXtract.Error.Invalid](LeXtract.Error.Invalid.md): Error class for validation and format errors.
  - [LeXtract.Error.Invalid.Config](LeXtract.Error.Invalid.Config.md): Error for configuration validation failures.
  - [LeXtract.Error.Invalid.Format](LeXtract.Error.Invalid.Format.md): Error for unknown or invalid format types.
  - [LeXtract.Error.Invalid.Template](LeXtract.Error.Invalid.Template.md): Error for invalid template structure or content.
  - [LeXtract.Error.Processing](LeXtract.Error.Processing.md): Error class for processing pipeline failures.
  - [LeXtract.Error.Processing.Alignment](LeXtract.Error.Processing.Alignment.md): Error for text alignment failures.
  - [LeXtract.Error.Processing.Chunking](LeXtract.Error.Processing.Chunking.md): Error for text chunking failures.
  - [LeXtract.Error.Processing.Parsing](LeXtract.Error.Processing.Parsing.md): Error for JSON/YAML parsing failures.
  - [LeXtract.Error.Processing.Resolution](LeXtract.Error.Processing.Resolution.md): Error for extraction resolution failures.
  - [LeXtract.Error.Processing.Tokenization](LeXtract.Error.Processing.Tokenization.md): Error for tokenization failures.
  - [LeXtract.Error.Unknown](LeXtract.Error.Unknown.md): Error class for unexpected errors.
  - [LeXtract.Error.Unknown.Unknown](LeXtract.Error.Unknown.Unknown.md): Catch-all error for truly unexpected failures.