cognesy/instructor-struct

Structured data extraction in PHP, powered by LLMs - core library

v1.11.0 2025-10-14 18:48 UTC

Requires

• php: ^8.2
• cognesy/instructor-config: ^1.11
• cognesy/instructor-events: ^1.11
• cognesy/instructor-messages: ^1.11
• cognesy/instructor-pipeline: ^1.11
• cognesy/instructor-polyglot: ^1.11
• cognesy/instructor-setup: ^1.11
• cognesy/instructor-templates: ^1.11
• cognesy/instructor-utils: ^1.11
• phpdocumentor/reflection-docblock: ^5.4
• phpstan/phpdoc-parser: ^1.29
• symfony/property-access: ^6.4 || ^7.0
• symfony/property-info: ^6.4 || ^7.0
• symfony/serializer: ^6.4 || ^7.0
• symfony/validator: ^6.4 || ^7.0

Requires (Dev)

• icanhazstring/composer-unused: ^0.9.0
• jetbrains/phpstorm-attributes: ^1.2
• maglnet/composer-require-checker: ^4.16
• mockery/mockery: ^1.6
• pestphp/pest: ^2.34
• phpstan/phpstan: ^1.11
• roave/security-advisories: dev-latest
• vimeo/psalm: ^6.0

Suggests

• cognesy/instructor-schema: For Symfony 7+ schema validation and management
• cognesy/instructor-schema-v6: For Symfony 6 schema validation and management

MIT

• Dariusz Debowczyk

• automation
• inference
• data extraction
• ai
• data processing
• openai
• llm
• anthropic
• ollama
• language models
• genai
• cohere
• structured output
• semantic processing

README

Instructor for PHP is a library that provides a developer friendly way to get structured responses from LLM inference, validate returned data, and automate retries in case of errors when LLM responds with invalid data.