Beschreibung
Unleash the power of large language models in your Unreal Engine projects with HttpGemini, the most straightforward way to integrate Google's cutting-edge Gemini API. Power up your games and applications with conversational AI, dynamic content generation, and intelligent systems, all without writing a single line of C++.
HttpGemini is built from the ground up for simplicity and performance, allowing you to send prompts to the Gemini API and receive responses at runtime, directly within your Blueprint graphs.
Key Features:100% Blueprint Ready: No C++ knowledge needed. The entire functionality is exposed through a single, powerful, and easy-to-use asynchronous Blueprint node.
Runtime Communication: Send requests and receive AI-generated responses live in your packaged projects. Perfect for creating dynamic NPCs, procedural storytelling, and much more.
Easy Configuration: Get started in minutes. Simply add your Google AI API Key and select your desired model directly in the Project Settings.
Asynchronous by Design: All API calls are non-blocking, ensuring your game's performance remains smooth and responsive without any freezes or frame drops.
Robust Error Handling: Receive clear, actionable feedback directly in your Blueprints for connection issues, invalid API keys, or other potential problems.
Lightweight & Self-Contained: No external dependencies are required. The plugin uses Unreal Engine's native HTTP and JSON modules for maximum stability and compatibility across platforms.
Install & Enable: Add the plugin to your project and enable it in the Plugins window.
Configure Settings: Navigate to Project Settings > Plugins > HttpGemini Settings and paste your API key.
Use in Blueprint: Call the Send Chat Message (Gemini) node and handle the response using its dedicated OnResponseReceived event. It's that simple!
Supported Engine Versions: 5.5, 5.6
Supported Platforms: Windows (64-bit), Android
Dependencies: None! Uses built-in engine modules.
For a complete guide and examples, please visit the Official Online Documentation.
For support, feature requests, or any questions, please contact us at [email protected].