Skip to content

anish2105/oneAPI-GenAI-Hackathon-2023

 
 

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

36 Commits
 
 
 
 

Repository files navigation

Team Name - 404Found

Problem Statement - AI-Enhanced Legal Practice Platform

Team Leader Email - [email protected]

An Overview of the Prototype:

image

Our creative idea is to create a smart legal chatbot that is integrated into an easy-to-use platform. This would give lawyers instant access to legal information and remove the need for laborious manual research in books or regulations. With the use of sophisticated Large Language Models (LLMs), this chatbot provides legal practitioners with a rapid and effective means to get immediate responses to their questions. The chatbot's comprehension of intricate legal jargon will allow attorneys to ask queries in plain English and get accurate, situation-appropriate answers. It will make use of machine learning algorithms to enhance its accuracy over time and stay current with changes and revisions to the law.

Tech Stack:

  • Python
  • Langchain
  • Intel® oneAPI Data Analytics Library
  • Intel® Optimization for PyTorch
  • Large Language Models
  • Intel developer cloud
  • Streamlit
  • ngrok

Step-by-Step Code Execution Instructions:

Clone the project

  git clone https://github.com/anish2105/oneAPI-GenAI-Hackathon-2023.git

Create a virtual envirnoment

  1. Use the cd command to navigate to the directory where you want to create the virtual environment. For example:
  cd path/to/your/project
  1. Use the following command to create a virtual environment named venv:
  python -m venv venv
  1. To activate the virtual environment, navigate to the Scripts directory inside the venv folder and run the activate script. Use the following command:
  venv\Scripts\activate

Install dependencies

  pip install -r requirements.txt

Start the server

  streamlit run chat.py

  1. To deactivate the virtual environment, Use the following command:
  deactivate

Future Scope:

  • Further improvements to the user interface are required.
  • A variety of open-source embeddings are available for use.
  • We are currently utilizing a dataset that only includes information about women and children, but we plan to eventually add the entire constitution.

About

No description, website, or topics provided.

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages

  • Python 100.0%