FinSight AI 📊

An AI-powered financial document analyzer built with RAG pipeline.

Tech Stack

• Frontend: React + Vite
• Backend: FastAPI (Python)
• AI: Groq LLaMA 3.3 70B
• Vector DB: ChromaDB
• Embeddings: HuggingFace sentence-transformers
• Database: SQLite

Features

• Upload single or multiple PDFs
• Ask questions about documents using RAG
• Download Word report of Q&A session
• Multi-document support with sidebar
• Chat history persistence

Setup

Backend

cd backend
python -m venv venv
venv\Scripts\activate
pip install -r requirements.txt
uvicorn main:app --reload

Frontend

cd frontend
npm install
npm run dev

Environment Variables

Create backend/.env:

GROQ_API_KEY=your_key_here
CHROMA_DB_PATH=./vector_store
UPLOAD_DIR=./uploads
REPORTS_DIR=./reports