arjvand / ai-provider-for-nvidia
Forgeia AI Provider for NVIDIA for the PHP AI Client SDK. Works as both a Composer package and a WordPress plugin.
Requires
- php: >=7.4
Requires (Dev)
Suggests
- wordpress/php-ai-client: Required. The core PHP AI Client SDK that this provider extends.
Provides
None
Conflicts
None
Replaces
None
This package is auto-updated.
Last update: 2026-11-08 11:16:30 UTC
README
Forgeia AI Provider for NVIDIA for the PHP AI Client SDK. Works as both a Composer package and a WordPress plugin.
Requirements
- PHP 7.4 or higher
- When using with WordPress, requires WordPress 6.9 or higher with the wordpress/php-ai-client plugin installed, or WordPress 7.0 or higher, which bundles the AI Client SDK
- Embedding generation requires AI Client 1.4 or higher. WordPress 7.0 and 7.1 bundle AI Client 1.3.1, which does not include embedding support.
Installation
As a Composer Package
composer require forgeia/forgeia-ai-provider-for-nvidia
As a WordPress Plugin
- Download the plugin files
- Upload to
/wp-content/plugins/forgeia-ai-provider-for-nvidia/ - Ensure the PHP AI Client plugin is installed and activated
- Activate the plugin through the WordPress admin
Usage
With WordPress
The provider automatically registers itself with the PHP AI Client on the init hook. Simply ensure both plugins are active and configure your API key:
// Set your NVIDIA API key (or use the NVIDIA_API_KEY environment variable) putenv('NVIDIA_API_KEY=your-api-key'); // Use the provider $result = AiClient::prompt('Hello, world!') ->usingProvider('nvidia') ->generateTextResult();
As a Standalone Package
use WordPress\AiClient\AiClient; use Forgeia\NvidiaAiProvider\Provider\NvidiaProvider; // Register the provider $registry = AiClient::defaultRegistry(); $registry->registerProvider(NvidiaProvider::class); // Set your API key putenv('NVIDIA_API_KEY=your-api-key'); // Generate text $result = AiClient::prompt('Explain quantum computing') ->usingProvider('nvidia') ->generateTextResult(); echo $result->toText();
Supported Models
Available models are dynamically discovered from the NVIDIA NIM API and classified by capability using explicit allowlists. This includes text generation models (NVIDIA Nemotron 3 and 3.5, Meta Llama, Google Gemma 3 and 4, Mistral Large 4, Moonshot Kimi K2.6, Muse Glimmer, Step 5, GLM 5.3, and others), vision / multimodal models that accept images (including Gemma 3 and 4, Kimi K2.6, Muse Glimmer, Step 5, Mistral Large 4, GLM 5.3, NVIDIA NeVA, and NVIDIA VILA), image generation (DiffusionGemma), and embedding models (Nemotron 3.5 Embed, NVCLIP, NV-EmbedQA, Arctic Embed). Embedding generation requires AI Client 1.4+ and is unavailable on WordPress 7.0/7.1, which bundle AI Client 1.3.1. See the NVIDIA Build for the full list of available models.
Configuration
The provider uses the NVIDIA_API_KEY environment variable for authentication. You can set this in your environment or via PHP:
putenv('NVIDIA_API_KEY=your-api-key');
License
GPL-2.0-or-later
