MoneyDump is a next-generation financial management tool that eliminates the friction of manual expense tracking using Natural Language Processing (NLP) and provides expert financial coaching through a Dual-RAG (Retrieval-Augmented Generation) engine.
- Node.js (v18 or higher)
- Python (v3.10 or higher)
- An OpenAI API Key (or Gemini/Claude if configured)
Navigate to the API directory:
cd budget-tracker-apiCreate and activate a virtual environment:
python -m venv venv
# Windows:
.\venv\Scripts\activate
# Mac/Linux:
source venv/bin/activateInstall dependencies:
pip install fastapi uvicorn sqlalchemy chromadb langchain-text-splitters python-dotenv openaiConfigure Environment Variables:
Create a .env file in the budget-tracker-api folder (or edit the existing one):
OPENAI_API_KEY=your_key_here
DATABASE_URL=sqlite:///./budget.db
KNOWLEDGE_BASE_PATH=../knowledge_base
VECTOR_DB_PATH=../vector_db
SECRET_KEY=your_secret_keyInitialize & Seed the Database: There are two ways to seed the database:
- Fast Seed (API directory):
python seed.py - Full Demo Data (Root directory):
python populate_db.py(Indexes 3 months of history and generates reports).
Index the Knowledge Base (for Wealth Wisdom):
python -m app.rag_managerStart the Backend Server:
uvicorn app.main:app --reloadThe API will be available at http://localhost:8000.
Open a new terminal and navigate to the frontend directory:
cd BudgetTrackerInstall dependencies:
npm installStart the Development Server:
npm run devThe application will be available at http://localhost:5173.
- MoneyDump Interface: Log expenses, income, and goals by simply typing or speaking in natural language.
- Wealth Wisdom (Expert RAG): A dedicated chat interface powered by 5 world-renowned financial bestsellers.
- AI Auditor: Get professional-grade audits of your spending with historical tracking and a 0-100 financial health score.
- Multi-Theme UI: Choose from premium themes like Cyberpunk, Synthwave, and Emerald (powered by DaisyUI).
- Local-First Security: API keys are stored in your browser, and financial data is handled securely via FastAPI.
- Frontend: React, Vite, Tailwind CSS, DaisyUI, Lucide React.
- Backend: Python, FastAPI, SQLAlchemy, ChromaDB (Vector Store).
- AI: OpenAI/Gemini/Ollama, LangChain (for RAG orchestration).
For deeper insights into the project, refer to: