This project offers a Perplexity-style AI-powered search engine, leveraging Google's Gemini 2.0 Flash model and real-time web grounding. It's designed for users seeking concise, cited answers to queries, with a focus on a clean UI and fast response times.

How It Works

The engine integrates Google Search for real-time information retrieval and uses the Gemini 2.0 Flash API to process queries and generate answers. It provides source citations and supports follow-up questions within a chat session, mimicking the user experience of established AI search platforms.

Quick Start & Requirements

• Install dependencies: npm install
• Prerequisites: Node.js (v18+), npm/yarn, Google API key with Gemini API access.
• Setup: Create a .env file with GOOGLE_API_KEY=your_api_key_here.
• Run: npm run dev
• Demo: http://localhost:3000

Highlighted Details

• Gemini 2.0 Flash model integration.
• Real-time web search and source citations.
• Perplexity-inspired UI with React, Vite, and Tailwind CSS.
• Backend powered by Express.js.

Maintenance & Community

The project is maintained by @ammaarreshi. Community links or roadmaps are not specified in the README.

Licensing & Compatibility

MIT License. Permissive for commercial use and integration into closed-source projects.

Limitations & Caveats

Requires a Google API key, which may incur costs. The project appears to be a personal clone and may not have the robustness or feature set of established commercial products.