An intelligent Application Tracking System (ATS) that uses Google's Gemini AI to analyze resumes against job descriptions, providing comprehensive feedback on compatibility, formatting, and optimization suggestions.

• AI-Powered Analysis - Leverages Google Gemini 1.5 Flash for intelligent resume evaluation
• JD Match Scoring - Calculates percentage match between resume and job description
• Missing Keywords Detection - Identifies important keywords from JD missing in resume
• Profile Summary - AI-generated professional summary of candidate profile

• Grammar Analysis - Detects and highlights grammatical errors
• Word Repetition Detection - Identifies overused words and phrases
• Format Issues - Checks for formatting problems and inconsistencies
• Readability Score - Calculates resume readability using industry-standard metrics

• Multi-Format Support - Accepts both PDF and DOCX resume formats
• Real-time Processing - Background task processing with status polling
• Professional UI - Modern, responsive design with Bootstrap 5
• Analytics Dashboard - Visual insights into analysis history and score distribution
• Caching System - Improved performance for repeated analyses

Backend (FastAPI)

• FastAPI 0.104.1 - Modern, fast web framework
• Uvicorn - ASGI server
• Google Generative AI (Gemini 1.5 Flash)
• PyPDF2 & python-docx for document parsing
• Pydantic for data validation

Frontend (Flask)

• Flask 3.0.0 - Web framework
• Bootstrap 5 - Responsive UI
• Chart.js - Data visualization
• AOS - Scroll animations

AI & Processing

• Google Gemini AI API
• NLTK for text processing
• Textstat for readability metrics

Smart-ATS-Checker/ ├── backend/ # FastAPI Backend │ ├── app/ │ │ ├── __init__.py │ │ └── main.py # API endpoints │ ├── models/ │ │ ├── __init__.py │ │ └── ats_models.py # Pydantic models │ ├── services/ │ │ ├── __init__.py │ │ └── ai_service.py # AI analysis service │ └── utils/ │ ├── __init__.py │ └── document_parser.py # Document parsing ├── frontend/ # Flask Frontend │ ├── app.py # Flask application │ ├── static/ │ │ ├── css/ │ │ │ └── style.css │ │ └── js/ │ │ └── main.js │ └── templates/ │ ├── base.html │ ├── index.html │ ├── results.html │ ├── dashboard.html │ └── about.html ├── Dashboard/ # UI Screenshots │ ├── 1.png │ ├── 2.png │ ├── 3.png │ └── 4.png ├── logs/ # Application logs ├── uploads/ # Temporary file storage ├── .env # Environment variables (not committed) ├── .env.example # Environment template ├── config.py # Configuration management └── requirements.txt # Python dependencies 

• Python 3.8 or higher
• Google Gemini API key (Get it here)
• pip package manager

1. Clone the repository

git clone https://github.com/yourusername/Smart-ATS-Checker.git cd Smart-ATS-Checker

2. Create virtual environment

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

3. Install dependencies

pip install -r requirements.txt

4. Configure environment variables

# Copy the example file cp .env.example .env # Edit .env and add your API key GOOGLE_API_KEY=your_google_api_key_here SECRET_KEY=your_generated_secret_key_here

Generate a secure SECRET_KEY:

python -c "import secrets; print(secrets.token_hex(32))"

Terminal 1 - Backend:

cd backend uvicorn app.main:app --reload --host 0.0.0.0 --port 8000

Terminal 2 - Frontend:

cd frontend python app.py

• Frontend: http://localhost:5000
• Backend API: http://localhost:8000
• API Documentation: http://localhost:8000/api/docs

The Smart ATS uses a comprehensive scoring system:

Total Score = (JD Match × 0.70) + (Other Factors × 0.30) 

JD Match (70%)

• Keyword matching between resume and job description
• Skill alignment
• Experience relevance

Other Factors (30%)

• Grammar quality (10%)
• Format consistency (10%)
• Readability score (10%)

• 90-100%: Excellent - Highly optimized for ATS
• 75-89%: Good - Well-aligned with requirements
• 60-74%: Fair - Needs improvement
• Below 60%: Poor - Significant optimization needed

Analyze a resume against a job description

Request:

• resume_file: File (PDF or DOCX)
• job_description: String

Response:

{ "success": true, "message": "Analysis started", "data": { "analysis_id": "uuid", "status": "processing", "estimated_time": "30-60 seconds" } }

Check analysis status

Response:

{ "analysis_id": "uuid", "status": "completed", "timestamp": "2024-01-01T12:00:00" }

Get complete analysis results

Response:

{ "success": true, "message": "Analysis result retrieved", "data": { "id": "uuid", "percentage_score": 85, "jd_match": 88, "missing_keywords": ["Python", "Docker"], "profile_summary": "Experienced software engineer...", "grammar_mistakes": [...], "word_repetitions": [...], "format_issues": [...], "readability_score": 65, "timestamp": "2024-01-01T12:00:00", "status": "completed" } }

Get analytics data for dashboard

See .env.example for complete configuration options.

Run the setup validation:

python test_setup.py

Run scoring algorithm tests:

python test_scoring.py

1. Upload Resume: Navigate to home page and upload your resume (PDF/DOCX)
2. Paste Job Description: Copy and paste the target job description
3. Analyze: Click "Analyze Resume" to start processing
4. View Results: Wait for analysis to complete (30-60 seconds)
5. Review Feedback: Check score, missing keywords, and improvement suggestions
6. Dashboard: View analytics and historical analysis data

• Environment variable protection for API keys
• CORS configuration for secure API access
• File type validation (PDF/DOCX only)
• File size limits (16MB max)
• Rate limiting on API endpoints
• Secure session management

ModuleNotFoundError

# Ensure virtual environment is activated pip install -r requirements.txt

API Key Error

# Verify .env file exists and contains valid GOOGLE_API_KEY cat .env

Port Already in Use

# Change port in command uvicorn app.main:app --port 8001 # Backend # Or modify frontend/app.py for frontend port

File Upload Fails

• Check file size (max 16MB)
• Verify file format (PDF or DOCX only)
• Ensure file is not corrupted

Contributions are welcome! Please follow these steps:

1. Fork the repository
2. Create a feature branch (git checkout -b feature/AmazingFeature)
3. Commit your changes (git commit -m 'Add some AmazingFeature')
4. Push to the branch (git push origin feature/AmazingFeature)
5. Open a Pull Request

This project is licensed under the MIT License - see the LICENSE file for details.

• Google Gemini AI for powerful language model
• FastAPI for excellent async framework
• Flask for simple and elegant frontend framework
• Bootstrap for responsive UI components
• Chart.js for beautiful data visualizations

For questions or support, please open an issue on GitHub.

Note: This application is for educational and professional development purposes. Always review AI-generated suggestions critically and ensure your resume accurately represents your skills and experience.