HouseOfTec/ai-compliance

An AI-powered solution designed to simplify compliance and tax-related issues for South African banking customers. Many people don’t know which tax bracket they fall into or how to handle SARS-related challenges. This project leverages AI and automation to provide instant guidance, personalized compliance checks, and efficient resolution paths. # 🇿🇦 AI Banking Compliance Assistant An AI-powered solution designed to simplify compliance and tax-related issues for South African banking customers. ## Features - 📊 **Tax Bracket Detection** – Automatically calculate which SARS tax bracket you fall into - 🧠 **AI Compliance Advisor** – Get step-by-step guidance on handling compliance or SARS-related issues - ⚡ **Automated Document Checks** – Upload payslips or tax certificates for instant compliance validation - 🔔 **Smart Alerts** – Get reminders for deadlines, tax return filing, or outstanding issues - 🔒 **Secure & Private** – User data encrypted and never shared ## Tech Stack - **Backend:** Python (FastAPI) - **AI Layer:** OpenAI GPT - **Database:** PostgreSQL (with SQLite fallback) - **Cache & Queue:** Redis + Celery - **Containerization:** Docker + Docker Compose ## Setup Instructions 1. Clone the repository 2. Copy `.env.example` to `.env` and configure your settings 3. Run `docker-compose up` to start all services 4. Access the API at `localhost` 5. Check API documentation at `localhost` ## API Endpoints - `POST /api/tax/calculate` - Calculate tax based on annual income - `GET /api/tax/bracket/{index}` - Get information about a tax bracket - `POST /api/compliance/advice` - Get AI-powered compliance advice - `GET /api/compliance/sars/deadlines` - Get important SARS deadlines - `POST /api/documents/upload` - Upload and analyze documents - `GET /api/alerts` - Get user alerts ## Development To run without Docker: 1. Create a virtual environment: `python -m venv venv` 2. Activate it: `source venv/bin/activate` (Linux/Mac) or `venv\Scripts\activate` (Windows) 3. Install dependencies: `pip install -r requirements.txt` 4. Run the server: `uvicorn app.main:app --reload`