🏦 Financial Temporal RAG System

A sophisticated Retrieval-Augmented Generation (RAG) system designed for financial document analysis with temporal intelligence and memory capabilities.

✨ Features

• 📄 Multi-Document Processing - Extract and analyze content from financial PDF reports
• ⏰ Temporal Intelligence - Understand time-based queries and track financial trends over periods
• 🧠 Memory-Augmented Conversations - Session management with context awareness
• 🔍 Cross-Document Analysis - Compare insights across multiple financial documents
• 📊 Causal Reasoning - Identify relationships and causality in financial data
• 🎯 Semantic Search - Advanced vector-based document retrieval

🛠️ Tech Stack

Backend

• Python 3.8+ - Core application logic
• FastAPI - RESTful API framework
• Google Gemini 2.0 Flash - Large Language Model
• ChromaDB - Vector database for embeddings
• Sentence Transformers - Text embeddings (all-MiniLM-L6-v2)
• PyMuPDF - PDF processing and extraction
• LangChain - Document processing and text splitting

Frontend

• React - Component-based UI framework
• Vue.js - Progressive frontend framework
• Bootstrap - Responsive design system

AI/ML Libraries

• Pytesseract - OCR for image text extraction
• Pandas - Data manipulation and analysis
• NumPy - Numerical computations

User Interface Preview

Modern, intuitive interface for seamless financial document analysis

🚀 Quick Start

Prerequisites

• Python 3.8 or higher
• Google Gemini API key
• Node.js (for frontend)

Installation

1. Clone the repository

   git clone https://github.com/your-username/financial-temporal-rag.git
   cd financial-temporal-rag

2. Set up Python environment

   pip install -r requirements.txt

3. Configure environment variables

   cp .env.example .env
   # Edit .env and add your GEMINI_API_KEY

4. Add financial documents

   # Place your PDF files in the data/ directory
   mkdir data
   # Copy your financial PDFs to data/

5. Run the system

   # Backend
   python main.py
   
   # FastAPI server (in separate terminal)
   uvicorn app:app --reload
   
   # Frontend (in separate terminal)
   cd frontend
   npm install
   npm start

🔧 Configuration

Key configurations in src/core/config.py:

• Embedding Model: all-MiniLM-L6-v2
• LLM Model: gemini-2.0-flash
• Chunk Size: 1000 tokens with 200 overlap
• Session TTL: 24 hours
• Max Sessions: 10

🤝 Contributing

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

📝 License

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

🙏 Acknowledgments

• Google Gemini for providing powerful LLM capabilities
• ChromaDB for efficient vector storage
• LangChain community for document processing tools

---

⭐ Star this repo if you find it helpful! | 📧 Issues & Feedback welcome