https://github.com/ftoucch/weblit
A GPT-4 LLM for Systematic literature review
https://github.com/ftoucch/weblit
Last synced: 7 months ago
JSON representation
A GPT-4 LLM for Systematic literature review
- Host: GitHub
- URL: https://github.com/ftoucch/weblit
- Owner: ftoucch
- License: mit
- Created: 2024-03-25T20:13:41.000Z (over 1 year ago)
- Default Branch: main
- Last Pushed: 2025-02-27T20:35:20.000Z (7 months ago)
- Last Synced: 2025-02-28T05:22:46.481Z (7 months ago)
- Language: TypeScript
- Homepage:
- Size: 2.14 MB
- Stars: 56
- Watchers: 1
- Forks: 4
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
- License: LICENSE
Awesome Lists containing this project
README
# WebLit: Automated Primary Study Selection for Systematic Literature Reviews (SLRs).
## Overview
**WebLit** is an open-source, web-based application designed to fully automate the **primary study selection process** in **Systematic Literature Reviews (SLRs)**. Built with **Angular** for the frontend and **Node.js** for the backend, WebLit leverages the power of **GPT-4** to dynamically retrieve, filter, and analyze research papers across multiple disciplines.
This tool aims to:
- Eliminate manual efforts in SLRs.
- Provide transparent, user-controlled automation.
- Enhance cross-domain applicability.
---
## Key Features
- **Dynamic Paper Retrieval**: Automates the search and retrieval of research papers using customizable search strings.
- **Full Automation**: From data collection to study selection—no manual uploads required.
- **Customizable Criteria**: Flexible inclusion/exclusion parameters tailored to specific research needs.
- **Integrated Chat**: Interact with an LLM trained on your selected studies for deeper insights.
- **SLR History & Traceability**: View, edit, and manage all past SLRs for continuous improvement.
- **Cross-Disciplinary Support**: Tested in medical sciences, engineering, and social sciences.
---
## Performance Highlights
- **Precision Rate**: 73.3% (High accuracy in identifying relevant studies)
- **Retention Rate**: 1.7% (Selective and rigorous screening process)
These metrics emphasize WebLit’s focus on **quality over quantity** in study selection.
---
## Tech Stack
- **Frontend:** [Angular](https://angular.io/)
- **Backend:** [Node.js](https://nodejs.org/)
- **LLM:** GPT-4
---
## Getting Started
### Prerequisites
- **Node.js** (v14 or above)
- **Angular CLI** (v15 or above)
- **npm** (v6 or above)
---
### Installation
1. **Clone the Repository**
```bash
git clone https://github.com/ftoucch/weblit.git
cd weblit
2. **Environment Setup**
Rename .env-example to .env
Add the required environment variables in .env
(Ensure you have API keys or credentials if needed)
3. **Backend Setup**
```bash
npm install && npm run dev
4. **Frontend Setup**
```bash
cd client-v2
npm install
ng serve --open