Skip to content

Upload multiple resumés, parse + embed, answer queries with snippet evidence, and match against job descriptions.

Notifications You must be signed in to change notification settings

sonal1201/MatchCv

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

14 Commits
 
 
 
 
 
 

Repository files navigation

MatchCV 🚀

AI-Powered Resume Matching & Candidate Ranking Platform

MatchCV is an AI-driven recruitment platform that helps recruiters upload resumes, extract candidate data, and rank the best candidates using semantic search instead of traditional keyword matching.


✨ Features

  • 📄 Resume Upload – Upload resumes in PDF or DOCX format
  • 🔍 Automatic Parsing – Extract email, phone number, skills, and experience
  • 🤖 AI Resume Summaries – Generate concise candidate summaries using AI
  • 🧠 Semantic Search – Find candidates based on meaning, not just keywords
  • 📊 Candidate Ranking – Rank resumes using embeddings, cosine similarity, and keyword scoring
  • 🧑‍💼 Recruiter Dashboard – View, filter, and manage candidates in one place

🛠️ Tech Stack

Frontend

  • React.js
  • TypeScript
  • Tailwind CSS

Backend

  • Node.js
  • Express.js
  • MongoDB

AI

  • Google Gemini API
  • AI Embeddings
  • Cosine Similarity

🏗️ System Architecture

  1. Recruiter uploads resumes (PDF/DOCX)
  2. Backend extracts raw text and structured data
  3. AI generates resume summaries and embeddings
  4. Job requirements are embedded
  5. Candidates are ranked using cosine similarity + keyword scoring
  6. Results are displayed in a recruiter-friendly dashboard

🚀 Getting Started

Prerequisites

  • Node.js 18+
  • MongoDB (local or Atlas)
  • Google Gemini API key

1️⃣ Clone the Repository

git clone https://github.com/your-username/matchcv.git
cd matchcv

2️⃣ Backend Setup

cd backend
npm install
cp .env.example .env
npm run dev

Backend runs on: http://localhost:5000


3️⃣ Frontend Setup

cd frontend
npm install
cp .env.example .env
npm run dev

Frontend runs on: http://localhost:5173


🔐 Environment Variables

Backend (.env)

MONGODB_URI=your_mongodb_connection_string
GEMINI_API_KEY=your_google_gemini_api_key
JWT_SECRET=your_jwt_secret
PORT=5000

Frontend (.env)

VITE_API_URL=http://localhost:5000/api

📊 Ranking Logic

  • AI Embeddings are generated for resumes and job descriptions
  • Cosine Similarity measures semantic relevance
  • Keyword Scoring boosts important skills and terms
  • Final score determines candidate ranking

🧪 Development Scripts

Backend

npm run dev

Frontend

npm run dev
npm run build
npm run preview

📈 Future Improvements

  • Job description upload & matching
  • Recruiter team collaboration
  • Feedback-based ranking improvements
  • Exportable shortlists
  • Enterprise-scale hiring workflows

📄 License

MIT License


👤 Author

Built by Sonal Singh An AI-powered full-stack project focused on modern hiring workflows

About

Upload multiple resumés, parse + embed, answer queries with snippet evidence, and match against job descriptions.

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

 
 
 

Contributors