Information Buster is a state-of-the-art AI Assistant designed for high-performance information retrieval and interactive chat. Powered by Google Gemini 2.0 Flash, it provides lightning-fast responses with a premium, multi-threaded user interface built for the modern web.
- ποΈ Powered by Gemini 2.0 Flash: Leverages the latest high-speed, high-context model from Google.
- π¬ Interactive Chat UI: A slick, professional interface built with
assistant-uifor a seamless user experience. - π Multi-Thread Support: Organize multiple conversations easily with a dedicated thread sidebar.
- β‘ Real-time Streaming: Instant feedback with ultra-low latency text streaming.
- π Premium Dark Mode: Beautifully crafted minimalist design that is easy on the eyes.
- π± Responsive Design: Fully optimized for mobile, tablet, and desktop viewports.
- Frontend: Next.js 15 (App Router), React 19, TypeScript
- AI Framework: Vercel AI SDK (@ai-sdk/google)
- UI Components:
@assistant-ui/react, Radix UI, Tailwind CSS 4 - Icons: Lucide React
- Node.js 18.x or later
- A Google AI (Gemini) API Key
-
Clone the repository:
git clone https://github.com/vivekyadav-3/information-buster.git cd information-buster/my-app -
Install dependencies:
npm install
-
Set up Environment Variables: Create a
.env.localfile in themy-appdirectory:GOOGLE_GENERATIVE_AI_API_KEY=your_gemini_api_key_here
-
Run the Development Server:
npm run dev
Visit http://localhost:3000 to interact with Information Buster!
my-app/
βββ app/ # Next.js App Router (Pages & API)
β βββ api/chat/ # AI Streaming Route
β βββ assistant.tsx # Main AI Component logic
βββ components/ # UI Components (Thread, Message, Tooltip)
βββ lib/ # Utility functions
βββ tailwind.config.ts # Design System configuration
Distributed under the MIT License. See LICENSE for more information.
Built with β€οΈ by Vivek Yadav