Gemini-Router

GeminiRouter is a sophisticated implementation of the Model Context Protocol (MCP) that integrates with Google's Gemini Flash 1.5 API. It showcases how modular AI services can work together through a centralized router to provide intelligent, context-aware responses. The system is designed to handle various types of queries by routing them to specialized microservices, each performing distinct functions such as chat, web search, weather information, deep reasoning, and retrieval-augmented generation (RAG). The router intelligently dispatches requests based on the query's intent, ensuring efficient and accurate responses. The architecture supports modularity, scalability, and real-time data integration, making it a robust solution for complex AI-driven applications.

Features

• {'name': 'Modular AI Services', 'description': 'Each function (chat, search, RAG, think) operates independently as a microservice.'}
• {'name': 'Centralized Context Router', 'description': 'Manages request dispatching, context management, and service coordination.'}
• {'name': 'Gemini Flash 1.5', 'description': 'Utilizes a high-performance model for reasoning, generation, and information retrieval.'}
• {'name': 'OpenWeather Integration', 'description': 'Incorporates real-time weather data into the search context.'}
• {'name': 'Dockerized Backend', 'description': 'Facilitates easy deployment of services in isolation or as a single stack using Docker.'}

Usage with Different Platforms

Clone the Repository

bash
git clone https://github.com/AditHash/gemini-mcp-router.git
cd gemini-mcp-router

Start the Backend

bash
cd backend
docker-compose up --build

Start the Frontend

bash
npm install
npm run dev