Insight is a sleek, modern LLM interface where users can select AI models tailored to their needs, with premium models unlocked via a secure payment system. Built for practice and future scalability.
- Model Selection: Choose from a variety of AI models to suit your needs, with a dropdown selector.
- Paywall for Premium Models: Access advanced models (e.g., Gemini 2.0) with a premium subscription, featuring a lock icon and "Buy Premium" section.
- Secure Payment System: Integrated with Payment Gateway for seamless payments to unlock premium features.
- Responsive Design: Works beautifully on desktop and mobile with Tailwind CSS.
- Chat Interface: Clean and intuitive chat UI to interact with your chosen AI model.
- Frontend: Next.js (App Router), React, TypeScript, Tailwind CSS
- Backend: Next.js API routes, Supabase (for model storage)
- Payment Gateway: PhonePe (sandbox environment)
- Libraries: Axios, Heroicons
Head to https://insight-beta-flax.vercel.app/ to Interact with AI models, select premium ones, and upgrade via the payment page—all in one seamless experience.
The main chat interface where users interact with their chosen AI model.
A sleek payment page to upgrade to premium, featuring the Insight logo and a dynamic form.
- Node.js (v18 or higher)
- Supabase account (for model storage)
- PhonePe sandbox credentials (for payment testing)
- Clone the repository:
git clone https://github.com/anshvert/insight.git cd insight - Install dependencies:
pnpm install
- Set up environment variables in .env.local:
NEXT_PUBLIC_OPEN_ROUTER_API_KEY= AUTH_SECRET= GOOGLE_CLIENT_ID= GOOGLE_CLIENT_SECRET= GITHUB_CLIENT_ID= GITHUB_CLIENT_SECRET= SUPABASE_URL= NEXT_PUBLIC_SUPABASE_KEY=
- Run the development server:
next dev
- Open http://localhost:3000 in your browser to start using Insight.
Insight is just getting started! Here’s what’s on the horizon:
- More AI Models: Expand the model library with cutting-edge LLMs and enhance the chat experience with richer interactions.
- Analytics Dashboard: Add usage analytics for users to track their interactions and model performance.
Got ideas? Let me know in the issues section!
- This project is licensed under the MIT License - see the LICENSE file for details.