Clause Buddy Understand complex legal documents in plain English using the power of Google Gemini. This full-stack application provides a user-friendly interface to upload documents, ask specific questions, and automatically scan for risky clauses.

Core Features Document Upload: Securely upload your legal documents in various formats (.pdf, .docx, .txt). The backend processes and prepares them for analysis.

Question Answering (RAG): Ask specific questions about your document (e.g., "What are the termination conditions?") and receive concise, easy-to-understand answers generated by a Retrieval-Augmented Generation pipeline.

Risk Analysis: Automatically scan your document to identify and explain important legal clauses such as Termination, Limitation of Liability, and Indemnification, complete with severity ratings (High, Medium, Low).

Tech Stack This project is a monorepo containing a separate frontend and backend.

Area: Technology

Frontend : React (with Vite), Tailwind CSS

Backend : Python, FastAPI

LLM, embedding : Google Gemini 1.5 Flash, LangChain

Database :ChromaDB (Vector Store)

Deployment : Frontend on Vercel, Backend on Render

Getting Started Prerequisites Python 3.9+ Node.js v18+ A Google Gemini API Key.

1. Backend Setup

Navigate to the backend directory

cd src/backend

Install Python dependencies

pip install -r requirements.txt

Create a .env file and add your API key :

"GOOGLE_API_KEY='YOUR_GOOGLE_API_KEY_HERE'"

Run the FastAPI server

uvicorn main:app --reload

The backend will be running at http://localhost:8000.

2. Frontend Setup

Navigate to the client directory from the root

cd src/client

Install Node.js dependencies

npm install

Create a .env.local file for the backend URL

"LLM_API_URL"="http://localhost:8000"

Run the development server

npm run dev

The frontend will be running at http://localhost:5173.