Skip to content

Repository files navigation

Document Compliance Validation System

AI-powered autonomous compliance reviews for proper financial documentation.

This system uses Generative AI (Llama 3.1 & LLaVA) to automatically validate marketing documents against complex regulatory rules (SFDR, ESG, Cross-border registration).

Demo

Demo: SFDR Compliance Validator

Product walkthrough of the Document Compliance Validation System.

📚 Documentation

Enter the Documentation Hub

🚀 Quick Start

1. Prerequisites

  • Python 3.12+
  • Node.js 18+ (for UI)
  • Tesseract OCR (for image extraction)

2. Setup

# Clone and Install
git clone <repo>
cd "Advanced Ai Project"
python -m venv .venv
source .venv/bin/activate  # or .\.venv\Scripts\Activate on Windows
pip install -r requirements.txt

# Configure Env
cp .env.example .env
# Edit .env with your API Keys

3. Run

Windows:

start_web_interface.bat

Linux/Mac:

./start_web_interface.sh

📁 Project Structure

Advanced Ai Project/
├── api.py                    # Flask API entry point
├── backend/                  # Core Python Application
│   ├── extractors/           # Extraction & Validation Logic
│   │   ├── core/            # Document, chart, feature extractors
│   │   ├── pipeline/        # Pipeline orchestrator
│   │   ├── validators/      # Compliance validators (15+ validators)
│   │   ├── agents/          # Data consistency agent
│   │   ├── parsers/         # Filename & registration parsers
│   │   └── rules/           # Compliance rules engine
│   ├── server/               # Flask API Server
│   │   ├── routes/v1/       # REST API endpoints
│   │   ├── services/        # Business logic services
│   │   └── config.py        # API configuration
│   ├── utils/                # Utilities (metrics, caching, reporting)
│   └── evaluation/          # Evaluation metrics
├── frontend/                 # Next.js Dashboard (React 19, Tailwind CSS)
├── server/                   # Flask application (legacy, use api.py)
├── docs/                     # Complete Documentation
│   ├── index.md             # Documentation hub
│   ├── architecture.md     # System architecture
│   ├── guide_usage.md       # User guide
│   ├── guide_development.md # Development guide
│   ├── features.md           # Validation rules & features
│   └── api_reference.md     # Complete API documentation
├── tests/                    # Comprehensive Test Suite
│   ├── README.md            # Test documentation
│   ├── test_pipeline_*.py    # Pipeline tests
│   ├── test_data_consistency*.py  # Validation tests
│   ├── test_esg_*.py        # ESG compliance tests
│   ├── test_api*.py         # API endpoint tests
│   └── run_all_tests.py     # Test runner
├── examples/                 # Example scripts
├── scripts/                  # Utility scripts
├── dataset/                  # Test datasets & reference data
└── outputs/                  # Generated outputs (gitignored)

License

Proprietary - Internal use only.

About

AI-powered compliance validation system for financial documents. Analyzes PPTX/PDF/DOCX files for ESG/SFDR compliance, data consistency, chart accuracy, and disclaimer verification. Features automated corrections, comprehensive reporting, and REST API. Built with Python and Next.js dashboard.

Topics

Resources

Stars

1 star

Watchers

0 watching

Forks

Releases

Packages

Contributors

Languages