Skip to content
/ flagr Public

An AI-powered legal advisor that uses a multi-agent system with RAG-enhanced LLM councils to analyze employment contracts against Indian Labour Law

Notifications You must be signed in to change notification settings

shub15/flagr

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

43 Commits
 
 
 
 
 
 
 
 
 
 

Repository files navigation

Overrule Legal Advisor

Introduction

Overrule is a parallel multi-agent system for intelligent contract review, designed to help legal professionals and individuals analyze contracts with speed and precision.

Key Features:

  • Multi-Agent Review: Utilizes a "council" of AI agents (running on OpenAI, Google Gemini, and Grok) to provide diverse perspectives.
  • RAG Integration: Leverages Pinecone vector database with legal document embeddings (e.g., Indian Labour Law) for context-aware analysis.
  • Smart Interface: A modern, React-based frontend for uploading contracts, viewing agent insights, and managing reviews.
  • Dynamic Analysis: Automated text extraction and risk scoring.

How to Run

Prerequisites

  • Node.js (v16+ recommended)
  • Python (v3.10+)
  • PostgreSQL or SQLite (for local dev)
  • API Keys: You will need API keys for OpenAI, Google Gemini, Grok (xAI), and Pinecone.

Backend Setup

  1. Navigate to the backend directory:

    cd backend
  2. Create a virtual environment (optional but recommended):

    python -m venv venv
    source venv/bin/activate  # On Windows: venv\Scripts\activate
  3. Install dependencies:

    pip install -r requirements.txt
  4. Set up environment variables:

    • Copy .env.example to .env:
      cp .env.example .env
    • Open .env and add your API keys.
  5. Initialize the database (if required):

    python -m app.database.session
  6. Start the backend server:

    uvicorn app.main:app --reload

    The backend API will be available at http://localhost:8000.

Frontend Setup

  1. Open a new terminal and navigate to the frontend directory:

    cd frontend
  2. Install dependencies:

    npm install
  3. Start the development server:

    npm run dev

    The application will be running at http://localhost:3000.

Presentation and Demo

License

MIT

About

An AI-powered legal advisor that uses a multi-agent system with RAG-enhanced LLM councils to analyze employment contracts against Indian Labour Law

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Contributors 2

  •  
  •