An intelligent loan compliance system that leverages AI and Elasticsearch to analyze loan documents, assess risk, and ensure regulatory compliance in real-time.

• Google Gemini Integration: Advanced NLP for document understanding and risk assessment
• Semantic Search: Find similar loans and clauses using vector embeddings
• Automated Risk Scoring: ML-driven risk calculation at document and clause level
• Compliance Monitoring: Real-time detection of regulatory violations

• Portfolio Health Score: Visual gauge showing overall portfolio status
• Risk Distribution: Interactive charts showing risk breakdown
• Regional Analysis: Geographic risk patterns and trends
• Trend Tracking: Historical risk score evolution over time
• Active Alerts: Real-time compliance violation notifications

• Full-Text Search: Fast document retrieval using Elasticsearch
• Semantic Search: Context-aware search using embeddings
• Clause-Level Analysis: Granular risk assessment for each clause
• Highlighted Results: Visual emphasis on risk factors

• PDF Ingestion: Automated extraction from loan documents
• Clause Chunking: Intelligent document segmentation
• Risk Factor Detection: Identify problematic clauses
• Metadata Extraction: Borrower info, amounts, rates, dates

┌─────────────────┐
│   Next.js UI    │  ← React Dashboard with Charts
└────────┬────────┘
         │
         ↓
┌─────────────────┐
│  FastAPI Backend│  ← Python REST API
└────────┬────────┘
         │
    ┌────┴────┬──────────┬──────────┐
    ↓         ↓          ↓          ↓
┌────────┐ ┌──────┐ ┌────────┐ ┌────────┐
│Elastic │ │Gemini│ │PyPDF2  │ │Pydantic│
│Search  │ │ AI   │ │Parser  │ │Models  │
└────────┘ └──────┘ └────────┘ └────────┘

• Python 3.8+
• Node.js 18+
• Elasticsearch Cloud account (or local instance)
• Google Gemini API key

git clone https://github.com/UnknownGod2011/Edge-Ledger.git
cd Edge-Ledger

cd loan-compliance-engine

# Create virtual environment
python -m venv venv

# Activate virtual environment
# Windows:
venv\Scripts\activate
# Linux/Mac:
source venv/bin/activate

# Install dependencies
pip install -r requirements.txt

# Configure environment variables
cp .env.example .env
# Edit .env with your credentials:
# - ELASTIC_CLOUD_ID
# - ELASTIC_API_KEY
# - GEMINI_API_KEY

# Start the backend server
python app/main.py

Backend will run on: http://localhost:8000

cd loan-compliance-engine/frontend

# Install dependencies
npm install

# Start development server
npm run dev

Frontend will run on: http://localhost:3000

1. Navigate to http://localhost:3000
2. Use the sidebar to drag & drop PDF loan documents
3. Watch real-time processing logs
4. View results in the dashboard

• Dashboard: Portfolio overview with health metrics
• Loans: Browse all processed loan documents
• Search: Semantic search across all documents
• Compliance: View regulatory violations
• Analytics: Deep dive into risk patterns
• Reports: Detailed loan-by-loan analysis
• Activity: System logs and workflow tracking

Create .env file in loan-compliance-engine/:

# Elasticsearch Configuration
ELASTIC_CLOUD_ID=your_cloud_id_here
ELASTIC_API_KEY=your_api_key_here

# Google Gemini API
GEMINI_API_KEY=your_gemini_api_key_here

# Optional: Custom Settings
ELASTIC_INDEX_NAME=loan_documents
EMBEDDING_MODEL=models/text-embedding-004
EMBEDDING_DIMENSIONS=768

1. Create a free account at Elastic Cloud
2. Create a deployment
3. Get your Cloud ID and API Key
4. Add to .env file

1. Visit Google AI Studio
2. Create an API key
3. Add to .env file

• FastAPI: Modern Python web framework
• Elasticsearch: Search and analytics engine
• Google Gemini: AI language model
• PyPDF2: PDF text extraction
• Pydantic: Data validation
• Uvicorn: ASGI server

• Next.js 16: React framework with App Router
• TypeScript: Type-safe JavaScript
• Tailwind CSS: Utility-first styling
• Recharts: Data visualization
• React Hooks: State management

• POST /upload - Upload loan documents
• GET /search - Search loans with filters
• GET /loans/{loan_id} - Get loan details

• GET /dashboard/summary - Portfolio metrics
• GET /analytics/risk-distribution - Risk breakdown
• GET /analytics/region - Regional analysis
• GET /analytics/trend - Historical trends

• POST /semantic_search - AI-powered search
• GET /workflow_logs - System activity logs

# Backend tests
cd loan-compliance-engine
python -m pytest tests/

# Frontend tests
cd loan-compliance-engine/frontend
npm test

Edge-Ledger/
├── loan-compliance-engine/          # Backend
│   ├── app/
│   │   ├── main.py                  # FastAPI application
│   │   ├── ingestion.py             # Document processing
│   │   ├── risk_engine.py           # Risk calculation
│   │   ├── semantic_search.py       # Vector search
│   │   ├── gemini_client.py         # AI integration
│   │   └── elastic_client.py        # Elasticsearch client
│   ├── sample_loans/                # Demo PDF files
│   ├── requirements.txt             # Python dependencies
│   └── .env.example                 # Environment template
│
├── loan-compliance-engine/frontend/ # Frontend
│   ├── app/                         # Next.js pages
│   │   ├── page.tsx                 # Dashboard
│   │   ├── loans/                   # Loan listing & details
│   │   ├── search/                  # Semantic search
│   │   ├── compliance/              # Violations
│   │   ├── analytics/               # Analytics
│   │   └── reports/                 # Detailed reports
│   ├── components/                  # React components
│   │   ├── Dashboard/               # Charts & metrics
│   │   ├── Layout/                  # Sidebar, TopNav
│   │   ├── LoanDetail/              # Loan view components
│   │   └── SemanticSearch/          # Search UI
│   ├── layouts/                     # Page layouts
│   └── package.json                 # Node dependencies
│
├── README.md                        # This file
├── LICENSE                          # MIT License
└── .gitignore                       # Git ignore rules

Contributions are welcome! Please feel free to submit a Pull Request.

1. Fork the repository
2. Create your feature branch (git checkout -b feature/AmazingFeature)
3. Commit your changes (git commit -m 'Add some AmazingFeature')
4. Push to the branch (git push origin feature/AmazingFeature)
5. Open a Pull Request

This project is licensed under the MIT License - see the LICENSE file for details.

• Elastic for the powerful search and analytics platform
• Google for Gemini AI capabilities
• Vercel for Next.js framework
• FastAPI for the excellent Python web framework

Project Link: https://github.com/UnknownGod2011/Edge-Ledger

• Elasticsearch Documentation
• Google Gemini API
• FastAPI Documentation
• Next.js Documentation

Built with ❤️ for better loan compliance