https://github.com/suniksha12/jobsforce.ai_21bce10497assignment
https://github.com/suniksha12/jobsforce.ai_21bce10497assignment
Last synced: 3 months ago
JSON representation
- Host: GitHub
- URL: https://github.com/suniksha12/jobsforce.ai_21bce10497assignment
- Owner: Suniksha12
- Created: 2025-01-21T14:02:54.000Z (5 months ago)
- Default Branch: main
- Last Pushed: 2025-01-21T15:44:17.000Z (5 months ago)
- Last Synced: 2025-01-21T16:32:50.086Z (5 months ago)
- Language: JavaScript
- Homepage: https://jobsforce-ai-21-bce-10497-assignment.vercel.app
- Size: 8.45 MB
- Stars: 0
- Watchers: 1
- Forks: 0
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
Awesome Lists containing this project
README
# Jobsforce.ai_21BCE10497Assignment
# PDF Data Extractor
This project automatically extracts personal information from PDF documents and populates a web form. It uses React for the frontend, Node.js for the backend, and leverages AI models for accurate data extraction.
## Features
- PDF file upload and processing
- Automatic extraction of personal information (Name, Phone, Address)
- Real-time form population with extracted data
- Simple and intuitive user interface
## Prerequisites
- Node.js v16 or higher
- Python 3.8 or higher (for PDF processing)
- npm or yarn package manager
## Installation
### Backend Setup
```bash
cd backend
npm install
pip install -r requirements.txt
npm start
```
### Frontend Setup
```bash
cd frontend
npm install
npm start
```
## Technology Stack
- Frontend: React, Axios, TailwindCSS
- Backend: Node.js, Express
- PDF Processing: pdfplumber
- AI/ML: spaCy for NER (Named Entity Recognition)
## Usage
1. Start both frontend and backend servers
2. Navigate to http://localhost:3000
3. Upload a PDF file containing personal information
4. Watch as the form automatically populates with extracted data
## API Endpoints
- POST /api/extract - Accepts PDF file and returns extracted information
## Environment Variables
Create a .env file in the backend directory:
```
PORT=5000
NODE_ENV=development
```