Evalio is a cutting-edge AI-powered technical interview platform that streamlines the hiring process for companies. It conducts automated technical interviews, provides real-time candidate assessment, and generates comprehensive reports to help HR teams make informed hiring decisions.
- Dynamic Question Generation: AI adapts questions based on job requirements and candidate responses
- Real-time Speech Recognition: Natural conversation with advanced speech analysis using Web Speech API
- Voice Synthesis: AI interviewer with natural speech capabilities
- LLaMA 3.2 Integration: Powered by Ollama for intelligent conversation flow
- Performance Metrics: Evaluates accuracy, communication, technical depth, and cultural fit
- Bias Reduction: Standardized evaluation criteria to minimize unconscious bias
- Detailed Reports: Comprehensive candidate assessments with hiring recommendations
- PDF Report Generation: Downloadable detailed assessment reports
- Automated Proctoring: Real-time monitoring with face detection and malpractice detection
- Secure Access: Token-based authentication with session management
- Image Analysis: OpenCV-based face detection for interview integrity
- Candidate Pipeline: Upload and manage candidates via Excel files
- Interview Scheduling: Automated scheduling with email notifications
- Dashboard Analytics: Monitor all interviews and candidate progress through Templates/dashboard.html
- Feedback System: Post-interview feedback collection via Templates/feedback.html
- Backend: Django (Python 3.x)
- Frontend: HTML5, CSS3, JavaScript, TailwindCSS
- Database: SQLite
- AI/ML: Ollama (LLaMA 3.2) / Gemini API
- Speech Processing: Web Speech API (webkitSpeechRecognition)
- Computer Vision: OpenCV for proctoring
- File Processing: PyMuPDF for PDF handling
- Authentication: Django Authentication System
Evalio/
├── Authentication/ # User authentication module
│ ├── models.py
│ ├── views.py
│ └── urls.py
├── Hr/ # HR management functionality
│ ├── models.py
│ ├── views.py
│ └── urls.py
├── Myapp/ # Core application logic
│ ├── models.py # Database models
│ ├── views.py # Application views
│ ├── utils.py # AI utilities and evaluation functions
│ └── urls.py # URL routing
├── Templates/ # HTML templates
│ ├── homepage.html # Landing page
│ ├── dashboard.html # HR dashboard
│ ├── interview.html # Interview interface
│ ├── feedback.html # Post-interview feedback
│ ├── ResultReport.html # Assessment reports
│ ├── login.html # Authentication pages
│ └── updatedSignup.html
├── Evalio/ # Django project settings
│ ├── settings.py
│ ├── urls.py
│ └── wsgi.py
├── db.sqlite3 # Database file
├── manage.py # Django management script
├── requirements.txt # Python dependencies
└── README.md
- Python 3.8+
- pip (Python package manager)
- Git
- Ollama (for local AI model hosting)
-
Clone the repository
git clone https://github.com/yourusername/evalio.git cd evalio -
Create virtual environment
python -m venv venv source venv/bin/activate # On Windows: venv\Scripts\activate
-
Install dependencies
pip install -r requirements.txt
-
Set up Ollama and LLaMA 3.2
# Install Ollama curl -fsSL https://ollama.ai/install.sh | sh # Pull LLaMA 3.2 model ollama pull llama3.2
-
Set up database
python manage.py makemigrations python manage.py migrate
-
Create superuser (optional)
python manage.py createsuperuser
-
Run the development server
python manage.py runserver
-
Access the application
- Open your browser and navigate to
http://127.0.0.1:8000/
- Open your browser and navigate to
- Sign Up/Login: Create an HR account using Templates/updatedSignup.html
- Dashboard Access: Use Templates/dashboard.html to manage interviews
- Upload Candidates: Import candidate information via Excel files
- Schedule Interviews: System automatically schedules and sends email invitations
- Monitor Progress: Track interview completion and review analytics
- Generate Reports: Download detailed PDF reports via Templates/ResultReport.html
- Receive Invitation: Get email invitation with unique interview link
- Join Interview: Access Templates/interview.html to start the AI interview
- Complete Assessment: Answer questions naturally through voice interaction
- Automated Proctoring: System monitors interview integrity using computer vision
- Provide Feedback: Submit post-interview feedback via Templates/feedback.html
The evaluation system is configured in Myapp/utils.py:
- Configure Ollama endpoint for LLaMA 3.2
- Customize evaluation criteria and scoring metrics
- Set required skills and nice-to-have skills for technical evaluation
Automated proctoring features include:
- Face detection using OpenCV
- Malpractice detection through image analysis
- Real-time monitoring during interviews
The AI evaluation system assesses candidates across multiple dimensions:
- Accuracy: Relevance of answers to questions asked
- Communication: Clarity and elaboration in responses
- Technical Depth: Presence of domain-specific terminology
- Cultural/Role Fit: Alignment with job requirements
Each metric is calculated using sophisticated algorithms detailed in the info.txt documentation.
- Dynamic Questioning: AI adapts questions based on candidate responses
- Speech Recognition: Real-time transcription and analysis
- Voice Synthesis: Natural AI interviewer voice
- Session Management: Token-based secure interview sessions
- Performance Metrics: Comprehensive candidate evaluation
- PDF Generation: Professional interview reports
- Dashboard Insights: Real-time analytics for HR teams
- Feedback Collection: Post-interview candidate feedback
- Proctoring System: Computer vision-based monitoring
- Secure Authentication: Django-based user management
- Session Tokens: Secure interview access control
- Fork the repository
- Create a feature branch (
git checkout -b feature/AmazingFeature) - Commit your changes (
git commit -m 'Add some AmazingFeature') - Push to the branch (
git push origin feature/AmazingFeature) - Open a Pull Request
This project is licensed under the MIT License - see the LICENSE file for details.
Developed by:
- Akash Kumar Gupta (10800221055)
- Samarjit Banerjee (10800221056)
- Pritam Sarbajna (10800222135)
- Md Athar Ansari (10800222137)
Under the guidance of:
- Dr. Sheuli Chakraborty, Assistant Professor, HOD Dept of CSBS
- Information Technology, Asansol Engineering College
- Asansol Engineering College for providing the platform for this project
- Ollama for local AI model hosting capabilities
- Django Community for the robust web framework
- TailwindCSS for responsive design
- OpenCV for computer vision capabilities
For support and questions:
- Email: banerjeesamarjit9@gmail.com
- Issues: GitHub Issues
- Documentation: See info.txt for detailed project information
Made with ❤️ by the Evalio Team
© 2025 Evalio Inc. All rights reserved.
Asansol Engineering College | Information Technology Department