Changelog¶

All notable changes to Kreuzberg will be documented in this file.

The format is based on Keep a Changelog, and this project adheres to Semantic Versioning.

[Unreleased]¶

Added¶

• Documentation site with comprehensive examples and API reference
• Improved configuration for all OCR backends
• Added hooks system for validation and post-processing

Changed¶

• Refactored internal structure for better maintainability
• Updated extraction functions to use config object instead of kwargs
• Improved error messages and reporting

[0.1.0] - 2023-11-15¶

Added¶

• Initial release
• Support for PDF, image, and Office document extraction
• OCR capabilities with Tesseract
• Basic error handling and reporting
• Async and sync APIs