Cortex: AI-Powered Financial Intelligence

Analyze. Synthesize. Strategize.
A professional-grade RAG platform fueled by Gemini 2.5 Flash and LangGraph.
Transforming static financial documents and portfolios into interactive, actionable insights.

⚡ Key Features

• 🤖 Agentic Reasoning Loop: Powered by LangGraph, allowing the AI to "think" through complex financial queries rather than just retrieving text.
• 🧠 Enterprise RAG Pipeline: Orchestrated by LangChain for precise document chunking, citation, and hallucination reduction.
• 🔍 Deep Semantic Search: Utilizes Supabase pgvector to find hidden connections in large PDF reports.
• 📊 Live Analytics Dashboard: A responsive React interface for real-time data visualization and chat.
• 🛡️ Secure Infrastructure: Full authentication via Supabase Auth and Row Level Security (RLS).

🛠️ Tech Stack

React

TypeScript

Tailwind

Python

FastAPI

Supabase

Gemini

LangChain

LangGraph

📸 Interface Preview

Intelligent Analytics Dashboard

Context-Aware AI Chat

Data Ingestion & Controls

Drag & Drop Upload

User Preferences

🚀 Getting Started

1. Backend Setup

cd backend
python -m venv venv
source venv/bin/activate  # Windows: venv\Scripts\activate
pip install -r requirements.txt

2. Frontend Setup

cd ../frontend
npm install

3. Environment Variables

Create .env files in both backend and frontend directories following the .env.example templates.

4. Run the Application

# Terminal 1 (Backend)
cd backend && python -m uvicorn main:app --reload
Terminal 2 (Frontend)

cd frontend && npm run dev

---

Built with ❤️ by Kalash Pratap Gaur

GitHub • Repository