Candidate Ranking System

This project is an AI-powered candidate ranking system that allows users to upload candidate data, configure ranking criteria, and receive stack-ranked results using OpenAI's GPT models. The system is built with a Flask backend and a modern HTML/JS frontend.

Features

• Upload candidate data via CSV
• Use sample candidate data for demo/testing
• Configure ranking criteria weights (academic degree, rank score, age)
• Optionally provide a job title and job description for context-aware AI ranking
• AI-powered ranking and justification for each candidate
• Download ranked results as CSV
• Responsive, modern UI

Project Structure

candidate-ranking-system/
│
├── backend/
│   ├── app.py                     # Flask application
│   ├── ranking_engine.py          # LLM ranking implementation
│   ├── prompt_templates.py        # Structured prompts for the LLM
│   ├── document_processor.py      # Resume processing functionality
│   ├── utils.py                   # Helper functions
│   └── requirements.txt           # Dependencies
│
├── frontend/
│   ├── static/
│   │   ├── css/
│   │   │   └── main.css
│   │   └── js/
│   │       └── main.js
│   └── templates/
│       ├── index.html
│       └── results.html
│
├── uploads/                       # Uploaded and processed files
├── results/                       # (Optional) Output results
└── README.md

Setup Instructions

1. Backend Setup

1. Create a virtual environment

   python -m venv .venv
   .venv\Scripts\activate  # On Windows
   source .venv/bin/activate  # On Mac/Linux
   

2. Install dependencies

   pip install -r backend/requirements.txt
   

3. Set your OpenAI API key
   • Create a .env file in the project root with:

     OPENAI_API_KEY=sk-...
     

2. Frontend Setup

No build step is required. The frontend is served by Flask from the frontend/templates and frontend/static folders.

3. Running the App

From the project root, run:

python -m backend.app

Then open http://127.0.0.1:5000 in your browser.

How to Start the Project

1. Clone or download this repository.
2. Set up your Python virtual environment and install dependencies:

   python -m venv .venv
   .venv\Scripts\activate  # On Windows
   # or
   source .venv/bin/activate  # On Mac/Linux
   pip install -r backend/requirements.txt
   

3. Set your OpenAI API key:
   • Create a .env file in the project root with:

     OPENAI_API_KEY=sk-...
     

4. Start the backend server:

   python -m backend.app
   

5. Open your browser and go to: http://127.0.0.1:5000

Usage

1. Upload a CSV with candidate data (columns: candidate_name, age, academic_degree, rank_score), or use the sample data.
2. Configure ranking parameters:
   • Set job position (required)
   • Optionally provide a job description for more context-aware ranking
   • Adjust weights for academic degree, rank score, and age
   • Set degree values if needed
3. Click "Rank Candidates" to get AI-generated rankings and justifications.
4. View and export results on the results page.

Customization

• You can add more criteria or change the prompt in backend/prompt_templates.py.
• The backend is designed to be extensible for more advanced resume parsing or additional AI features.

Requirements

• Python 3.10+
• OpenAI API key

License

MIT License