Andrea Bertelli
Lead maintainer
A Moodle AI provider that integrates Google’s Gemini API with Moodle’s core AI framework for text generation, summarisation, explanation, and image creation. It supports Gemini 3.x models, including gemini-3.6-flash, gemini-3.5-flash, gemini-3.5-flash-lite, gemini-3.1-flash-lite, gemini-3.1-pro-preview, gemini-3-flash-preview, gemini-3.1-flash-lite-image, gemini-3.1-flash-image, and gemini-3-pro-image, using the Interactions API or generateContent endpoints as appropriate. Administrators can configure API keys, default models, custom endpoints, system instructions, and site-wide or per-user rate limits. The provider supports custom model configurations, tracks the model used for each successful request, and provides structured error handling for network, HTTP, and incomplete image responses. Designed with privacy in mind, it avoids storing personal data and uses hashed identifiers derived from the site and user where required, sending only the necessary prompt, model, and generation parameters. Developed for Moodle 4.5+ and Moodle 5.0+ environments, it requires PHP 8.0 or higher and provides a straightforward, governed, and privacy-aware way to use modern generative AI within Moodle.