Extractor Laravel Package

What's New

Model Support

• Complete GPT-5 family: GPT_5_4, GPT_5_4_PRO, GPT_5_3, GPT_5_2, GPT_5_2_PRO, GPT_5_1, GPT_5, GPT_5_PRO, GPT_5_MINI, GPT_5_NANO
• GPT-4.1 family: GPT_4_1, GPT_4_1_MINI, GPT_4_1_NANO
• O-series reasoning models: O4_MINI, O3, O3_MINI, O3_PRO, O1, O1_PRO
• Automatic parameter handling for GPT-5 and O-series models — max_completion_tokens used instead of max_tokens, temperature omitted automatically
• Renamed: GPT_4O, GPT_4O_MINI (cleaner naming, old aliases deprecated)

Features

• Configurable default model via EXTRACTOR_MODEL env var (defaults to gpt-4o-mini)
• System prompt support — configure globally or per-extractor
• ImageContent detail parameter for OpenAI vision API (low, high, auto)
• JSON response_format sent with all requests for reliable structured output
• Laravel 13 compatibility
• Widened openai-php/laravel constraint to support v0.10.2 through v0.19+

Breaking Changes

• Default model changed from gpt-3.5-turbo-1106 to gpt-4o-mini
• $model, $maxTokens, $temperature parameters are now nullable with config fallback chains
• Removed legacy OpenAI Completions API support — chat-only
• Removed deprecated model constants (TEXT_DAVINCI_*, GPT_3_*, GPT_4_VISION, etc.)
• Removed isCompletionModel(), isJsonModeCompatibleModel(), isHybridModel(), isOhOne() methods
• PHP 8.3+ required

See UPGRADING.md for a full migration guide.

Integration Tested

All model families verified against the live OpenAI API:

What's Changed

Added

• Added declare(strict_types=1) to all source files for improved type safety
• Added comprehensive test suite with 127+ tests covering Engine, ExtractorManager, Extractors, and Text loaders
• Added Laravel 10/11/12 integration test script (test-laravel-install.sh)
• Added file size validation in Word loader (50MB limit)
• Added proper error messages for vision model input validation
• Added justfile for simplified development commands
• Added CONTRIBUTING.md with contributor guidelines
• Added pint.json for consistent code formatting configuration
• Added support for custom OpenAI API endpoints (Ollama, Together.ai, Groq, Azure)

Changed

• Improved JSON decode error handling with json_last_error_msg() for better debugging
• Fixed Factory::fromMime() rescue fallbacks to use lazy evaluation (closures)
• Fixed loose equality operators (==) to strict equality (===) in ImageContent
• Improved temp file cleanup with try-finally blocks in Word loader
• Updated temp file prefixes from legacy names to extractor_*
• Fixed Extractor::prompt() to explicitly call ->render() on View objects
• Reorganized test structure into Unit/Feature/Integration directories
• Updated CLAUDE.md with comprehensive architecture documentation

Fixed

• Fixed placeholder exception message in Engine.php for vision model errors
• Fixed eager evaluation bug in Factory::fromMime() fallback handling

Full Changelog: https://github.com/HelgeSverre/extractor/compare/v0.3.0...v0.4.0

v0.3.0 - Enhanced Word Document Extraction

Features & Improvements

• Improved Word document extraction reliability with better fallback handling
• Added support for Google Docs exported Word files
• Better error handling and resource cleanup in Word document processing

Testing

• Added new test case for Google Docs compatibility
• All existing tests pass with improved implementation

Technical Details

• Enhanced Word.php loader implementation
• Improved error handling with proper exception catching
• Better resource cleanup after document processing

Full Changelog: https://github.com/HelgeSverre/extractor/compare/v0.2.2...v0.3.0

What's Changed

• Laravel 12.x Compatibility by @laravel-shift in https://github.com/HelgeSverre/extractor/pull/11

New Contributors

• @laravel-shift made their first contribution in https://github.com/HelgeSverre/extractor/pull/11

Full Changelog: https://github.com/HelgeSverre/extractor/compare/v0.2.1...v0.2.2

Full Changelog: https://github.com/HelgeSverre/extractor/compare/v0.2.0...v0.2.1

Fix booboo

• Fixed ability to use gpt-4o for vision tasks, deprecated the vision preview model that no longer works, updated docs to reference new model. Thanks to [@blorange2](https://github.com/blorange2) for providing a fix

Full Changelog: https://github.com/HelgeSverre/extractor/compare/v0.1.3...v0.2.0

Updated dependancies and changed stuff in the readme.

Full Changelog: https://github.com/HelgeSverre/extractor/compare/v0.1.2...v0.1.3

What's Changed

• Add support for GPT-4o file handling by @andreascreten in https://github.com/HelgeSverre/extractor/pull/9

New Contributors

• @andreascreten made their first contribution in https://github.com/HelgeSverre/extractor/pull/9

Full Changelog: https://github.com/HelgeSverre/extractor/compare/v0.1.1...v0.1.2

Changes

• Bumped smalot/pdfparser from v2.9.0 to ^2.10

Full Changelog: https://github.com/HelgeSverre/extractor/compare/v0.1.0...v0.1.1

Add support for Laravel 11

What's Changed

• Fixed broken tests
• Removed prinsfrank/standards from dependancies, it was not used.
• Bumped the following dependancies:

Full Changelog: https://github.com/HelgeSverre/extractor/compare/v0.0.10...v0.0.11

What's Changed

• Add hook to enable deletion of files after processing with Textract by @HelgeSverre in https://github.com/HelgeSverre/extractor/pull/5
• Added Mockery as dev dependency

Full Changelog: https://github.com/HelgeSverre/extractor/compare/v0.0.9...v0.0.10

Changes

• fixes #3 - Corrected a mistake related to the default value of textract_version and textract_secret in config/extractor.php.

Full Changelog: https://github.com/HelgeSverre/extractor/compare/v0.0.8...v0.0.9

Changes

• added method fromMime($mime, $content in HelgeSverre\Extractor\Text\Factory::class

Full Changelog: https://github.com/HelgeSverre/extractor/compare/v0.0.7...v0.0.8

Changes

• Bump symfony/dom-crawler to ^7.0.0
• Added support for GPT-4-Vision vision api by @HelgeSverre in https://github.com/HelgeSverre/extractor/pull/2

Full Changelog: https://github.com/HelgeSverre/extractor/compare/v0.0.6...v0.0.7

Changes

• Updated the installation instructions for openai.

Full Changelog: https://github.com/HelgeSverre/extractor/compare/v0.0.5...v0.0.6

Changes

• Set gpt-3.5-turbo-1106 as the default model.

Full Changelog: https://github.com/HelgeSverre/extractor/compare/v0.0.4...v0.0.5

Changes

• Removed unused configuration option from config/extractor.php
• Improved readme.

Full Changelog: https://github.com/HelgeSverre/extractor/compare/v0.0.3...v0.0.4

Changes:

• Fixed broken composer.json config that causes the autoloader and Extractor facade to not be loaded correctly, gotta be careful with that "rename" refactor feature in PhpStorm apparently...

Full Changelog: https://github.com/HelgeSverre/extractor/compare/v0.0.2...v0.0.3

Changes

• Added missing $outputKey in builtin prompt
• Removed unused blade file
• Removed duplicate text in readme and fixed mistake in example

Full Changelog: https://github.com/HelgeSverre/extractor/compare/v0.0.1...v0.0.2

Pre-release.