Archive Insight

Advanced Semantic Analysis & Academic Integrity Platform

Archive Insight (formerly PlagioSense) is an enterprise-grade academic project explorer designed to redefine how research originality is verified. Moving beyond simple keyword matching, it leverages a sophisticated Semantic Analysis Engine to detect idea-level duplication, assess project novelty, and provide actionable intelligence for researchers and evaluators.

Built with a "Mastery through Curiosity" philosophy, the platform combines a high-fidelity Editorial Design System with powerful analytics to create a transparent, explainable, and visually stunning audit experience.

• Semantic Layer Analysis: Analyzes abstracts and project descriptions using advanced NLP techniques (Cosine Similarity, Vector Embeddings) to understand intent not just keywords.
• Context-Aware Chatbot: An integrated AI assistant that provides real-time feedback on document structure, citation quality, and originality probability.

• Editorial Design System: A clean, heuristic-driven UI inspired by top-tier academic journals, featuring crisp typography (Geist/Inter) and a minimalist 1px border aesthetic.
• Interactive Visualizations:
  • Particle Canvas Hero: A dynamic, physics-based entry point that responds to user interaction.
  • Bento Grid Explorer: A responsive, high-performance project directory with "Quick View" hover states and smooth Framer Motion transitions.

• Originality Scoring: Real-time calculation of a "Uniqueness Score" based on comparison with a global archive of 1.2M+ projects.
• Tech Stack Recommendations: AI-driven suggestions for modernizing project architectures to foster genuine innovation.

This project is built on a modern, type-safe stack designed for performance and scalability.

Follow these steps to set up the development environment locally.

• Node.js (v18 or higher recommended)
• npm (v9 or higher) or Bun (optional)

1. Clone the Repository

   git clone https://github.com/Sandeep010-hub/archive-insight.git
   cd archive-insight

2. Install Dependencies

   npm install
   # or if you use bun
   bun install

3. Start Development Server

   npm run dev

   The application will be available at http://localhost:5173.

   npm run build

The "Quick Check" feature relies on a Python backend.

1. Navigate to Project Root

   cd archive-insight

2. Create and Activate Virtual Environment

   python -m venv .venv
   # Windows
   .venv\Scripts\activate
   # Mac/Linux
   source .venv/bin/activate

3. Install Python Dependencies

   pip install -r backend/requirements.txt

4. Start the Backend Server

   python -m uvicorn backend.main:app --reload

   The API will be available at http://localhost:8000.

5. Environment Variables Copy .env.example to .env and fill in your Supabase credentials:

   cp .env.example .env

The codebase follows a scalable Feature-Based architecture:

src/
├── components/
│   ├── ui/           # Reusable atomic components (shadcn/ui)
│   ├── landing/      # Specific landing page sections (Hero, Chatbot)
│   ├── scanner/      # Core scanning engine components
│   └── explorer/     # Project discovery and filtering tools
├── pages/            # Page-level route components (Home, Scanner, About)
├── hooks/            # Custom React hooks for logic reuse
├── lib/              # Utility functions and cn helpers
└── assets/           # Static assets and global styles

This project is developed for the Computer Science & Engineering Department Academic Year 2025–26. All rights reserved.