Welcome to Lexoid’s Documentation

Lexoid is an efficient document parsing library that supports both LLM-based and non-LLM-based (static) PDF document parsing.

Contents:

• Installation
  • Installing with pip
  • Environment Setup
  • Optional Dependencies
  • Building from Source
  • Local Development Setup
• API Reference
  • Core Function
  • Examples
  • Return Value Format
• Contributing to Lexoid
  • Getting Started
  • Development Setup
  • Contributing Guidelines
  • Documentation
  • Reporting Issues
• Benchmark Report
  • Overview
  • Running the Benchmarks
  • Benchmark Results

Key Features

• Multiple parsing strategies (LLM-based and static parsing)

• Automatic parsing strategy selection

• Support for multiple LLM providers (OpenAI, Google, Meta/Llama, Together AI)

• Table detection and markdown conversion

• Hyperlink detection and preservation

• Recursive URL parsing

• Multi-format support

• Parallel processing support

• Permissive license

Indices and tables

• Index

• Module Index

• Search Page