OPTIMIZED CONTRACT LAWYER RAG

Overview

This repository contains the implementation of a Retrieval Augmented Generation (RAG) system for Contract Q&A. In this project I aim to build, evaluate, and improve a RAG system capable of answering questions related to legal contracts autonomously. The system leverages Langchain, a leading LLM application framework, for development and evaluation. Fastapi for backend and React on the frontend.

Objectives

Build a RAG system for Contract Q&A using Langchain.
Evaluate the performance of the RAG system using predefined metrics and benchmarks.
Implement enhancements to optimize the Contract Q&A process.
Interpret and report the findings, including incremental improvements achieved.

Tasks

The project is structured into several tasks, including:

Literature Review and Trend Analysis
Understanding RAG Performance Metrics
Efficiency and Scalability Optimization
Personalization and Contextualization
Bias Reduction
Planning and Design of Q&A Pipeline
Development of Retrieval and Generation Components
Integration and Testing
Building a RAG Evaluation Pipeline
Optimization Ideas for Contract Q&A
Implementation of Enhancements
Interpretation & Reporting

Dependencies

Python 3.x
Langchain framework
TensorFlow or PyTorch
langchain
RAGAS
TruLens
Cohere API
FastAPI

How to setup

Setup Instructions

Clone the Repository:

git clone git@github.com:biniyam69/AI-Contract-Lawyer.git

Create a New Virtual Environment:
```
python -m venv <env_name>
```
Replace <env_name> with your desired environment name.
Activate the Virtual Environment:
- For Windows:
```
.\<env_name>\Scripts\activate
```
- For macOS/Linux:
```
source <env_name>/bin/activate
```
Install Requirements:
```
pip install -r requirements.txt
```
Start the FastAPI Backend:
```
cd backend
uvicorn app:api
```
Install Node Dependencies and Start the Frontend:
```
cd frontend
npm install
npm run dev
```
Access the Application:
- Open your browser and go to http://localhost:3000/chat to access the chat interface.

Screenshots

Contributors

Biniyam Ajaw

License

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

Feel free to customize this README template according to your project specifics and requirements. Ensure it provides clear instructions for setup, dependencies, and usage, as well as an overview of the project objectives and structure.

biniyam69 / AI-Contract-Lawyer