DetectiveInferno is an innovative detective story game that combines advanced AI techniques with interactive storytelling. Powered by generative AI and Retrieval-Augmented Generation (RAG), it offers players a unique and immersive detective experience.
- Dynamic Story Generation: Each game session produces a unique detective story with rich characters and intriguing plots.
- Interactive Gameplay: Players can interrogate suspects, investigate crime scenes, and use hints to solve mysteries.
- Advanced AI Integration: Utilizes GPT-3.5 for story creation and character interactions.
- Memory-Augmented Generation: Employs a dictionary-based memory system with RAG to ensure narrative coherence and consistency.
- Prompt Engineering: Implements techniques like "chain-of-thought" and "least-to-most" for improved narrative logic.
Watch our demo video to see DetectiveInferno in action:
- Frontend: React.js, TypeScript, Vite
- Backend: Flask
- AI Integration: OpenAI GPT-3.5
- RAG Architecture: Langchain, ChromaDB
This project was bootstrapped with Vite.
Before you begin, ensure you have met the following requirements:
- You have installed Node.js version 20.5 or later. You can check your Node.js version by running node -v in your terminal.
- You have a recent version of npm installed. You can check your npm version by running npm -v in your terminal.
To install the Frontend Service, follow these steps:
- Navigate to the frontend directory in your terminal.
- Run
npm installto install the project dependencies.
To start the Frontend Service in development mode, follow these steps:
- Navigate to the frontend directory in your terminal.
- Run
npm run dev. - The application will start and should be available at http://localhost:5173 (or another port if 5173 is not available).
For more details on the research behind DetectiveInferno, check out our paper: DetectiveInferno: When RAG Meets Generative AI Detective Story Game