Skip to content

syedanida/DocInsight-AI

Repository files navigation

DocInsight- AI :Automated Legal Document Analysis Platform

Overview

The Automated Legal Document Analysis Platform is a powerful web application that automates the laborious process of analyzing legal documents. By leveraging cutting-edge technologies such as Next.js, NLP, and machine learning models, our platform extracts relevant information and identifies potential risks from legal documents. It empowers users to understand complex contract clauses, avoid potential losses, and make informed decisions when signing contracts.

Key Features

  • Automated Document Analysis: Our platform streamlines the manual process of analyzing legal documents, saving time and effort.
  • Reading Comprehension Model: We have developed and evaluated a reading comprehension model based on the SQuAD dataset, allowing users to extract information directly from the documents.
  • CUAD Dataset: To address critical clauses commonly asked by people and lawyers, we created a CUAD dataset consisting of 500 contracts in the form of question responses.
  • Paraphrasing Model: We integrate a paraphrasing model based on the T5-base model. This model utilizes datasets from Quora, SQuAD 2.0, and the CNN news dataset, enabling users to better understand contract clauses.
  • Sentiment Analysis: Our platform includes a sentiment analysis model powered by TextBlob, which provides insights into the impact and implications of contract clauses.
  • User-Friendly Interface: We have developed a user-friendly interface using Next.js, ensuring a seamless and intuitive user experience.
  • Flask Server Integration: The web interface connects seamlessly to the machine learning side through a Flask server, enabling efficient data processing and analysis.
  • Docker Containerization: To simplify deployment, we have containerized our application using Docker. Users can run the application effortlessly by executing Docker Compose.

Technology Stack

The DocInsight-AI Platform is built on the following technologies:

  • Next.js
  • NLP
  • SQuAD Dataset
  • CUAD Dataset
  • T5-base Model
  • Flask
  • TextBlob
  • Docker

Steps to run

  • Getting Started

To get started with DocInsight-AI, follow these steps:

  1. ⁠Clone the repository from GitHub.

  2. Navigate to the web directory and create a .env file that contains your google OAuth API keys.

  3. Install the necessary dependencies using ⁠ npm install⁠.

  4. Start the development server using ⁠ npm run dev.

  5. ⁠Navigate to the flask directory.

  6. ⁠Install the flask dependencies using ⁠ pip install flask⁠.

  7. Start flask server using ⁠ flask run.

  8. Access the web application through your browser.

  • Alternatively, if you prefer to use Docker:
  1. Install Docker on your system.

  2. ⁠Navigate to the project directory.

  3. ⁠Execute ⁠ docker-compose up ⁠ to start the application.

  4. ⁠Access the web application through your browser.

Acknowledgments

We would like to acknowledge the following open-source projects and datasets that have contributed to the development of our platform:

About

No description, website, or topics provided.

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Contributors 2

  •  
  •