cortexphp/model-info

A unified way to get AI model info from various providers

0.1.0 2025-05-14 07:52 UTC

Requires

• php: ^8.3
• psr-discovery/cache-implementations: ^1.2
• psr-discovery/container-implementations: ^1.2
• psr-discovery/discovery: >1.1.2
• psr-discovery/http-client-implementations: ^1.4
• psr-discovery/http-factory-implementations: ^1.2

Requires (Dev)

• guzzlehttp/guzzle: ^7.9
• pestphp/pest: ^3.0
• pestphp/pest-plugin-type-coverage: ^3.2
• phpstan/phpstan: ^2.0
• phpstan/phpstan-strict-rules: ^2.0
• rector/rector: ^2.0
• symplify/easy-coding-standard: ^12.5

MIT

• Sean Tymon

• ai
• cortex
• llm
• model-info

README

Features

• Get model information from various AI providers (Ollama, LiteLLM)
• PSR-16 Simple Cache support for caching model information
• Retrieve available models for supported providers
• Get detailed model information for specific models
• Extensible provider system

Requirements

• PHP 8.3+

Installation

composer require cortexphp/model-info

Usage

use Cortex\ModelInfo\ModelInfoFactory;
use Cortex\ModelInfo\Enums\ModelProvider;

// Create a new factory instance
$factory = new ModelInfoFactory();

// Get all available models for a provider
$models = $factory->getModels(ModelProvider::Ollama);

// Get information about a specific model
$modelInfo = $factory->getModelInfo(ModelProvider::Ollama, 'llama3.1');

use Psr\SimpleCache\CacheInterface;

// Using with custom cache implementation
$factory = new ModelInfoFactory(
    cache: $yourPsr16CacheImplementation
);

// Force fetch (bypass cache) with exception handling
try {
    $models = $factory->getModelsOrFail(ModelProvider::LiteLLM);
    $modelInfo = $factory->getModelInfoOrFail(ModelProvider::LiteLLM, 'gpt-4');
} catch (ModelInfoException $e) {
    // Handle exception
}

// Clear the cache
$factory->flushCache();

Credits

• Sean Tymon
• All Contributors

License

The MIT License (MIT). Please see License File for more information.