Transform your interview preparation with cutting-edge AI technology, real-time feedback, and comprehensive performance analytics.
🎯 Features • 🚀 Quick Start • 📖 Documentation • 🤝 Contributing
|
|
| 🔐 Authentication | 📄 Resume Processing | 🎤 AI Interviews | 📊 Analytics |
|---|---|---|---|
| JWT-based security | PDF & text parsing | Voice/text responses | Performance tracking |
| User management | Skills extraction | Real-time feedback | Progress visualization |
| Session handling | Experience analysis | Follow-up questions | Detailed reports |
graph TB
A[🌐 Frontend Interface] --> B[🚀 Flask Backend]
B --> C[🧠 AI Engine]
B --> D[🗄️ Database Layer]
B --> E[🎤 Voice Processor]
B --> F[📄 PDF Parser]
C --> G[🤖 Google Gemini]
C --> H[📊 Similarity Engine]
E --> I[🗣️ Whisper STT]
D --> J[👤 Users]
D --> K[📋 Resumes]
D --> L[🎯 Interviews]
style A fill:#e1f5fe
style B fill:#f3e5f5
style C fill:#e8f5e8
style D fill:#fff3e0
- 🐍 Python 3.8 or higher
- 🔑 Google Gemini API Key
- 💾 50MB free disk space
# 1️⃣ Clone the repository
git clone https://github.com/hari7261/AI-INTERVIEW-CRM.git
cd AI-INTERVIEW-CRM
# 2️⃣ Create virtual environment
python -m venv venv
source venv/bin/activate # On Windows: venv\Scripts\activate
# 3️⃣ Install dependencies
pip install -r requirements.txt
# 4️⃣ Set up environment variables
cp .env.example .env
# Edit .env with your API keys
# 5️⃣ Initialize database
python -c "from models.db import init_db; from app import create_app; init_db(create_app())"
# 6️⃣ Start the application
python app.pyOpen your browser and navigate to: http://localhost:5000 🎉
Click to expand Authentication details
- JWT Token-based Authentication: Secure session management
- Password Hashing: Using Werkzeug's security utilities
- Email Validation: Proper email format checking
- Session Expiry: Automatic token expiration
POST /api/auth/register- User registrationPOST /api/auth/login- User authenticationGET /api/auth/profile- Get user profilePOST /api/auth/logout- Secure logout
// Register new user
const registerUser = async (userData) => {
const response = await fetch('/api/auth/register', {
method: 'POST',
headers: { 'Content-Type': 'application/json' },
body: JSON.stringify(userData)
});
return response.json();
};Click to expand Resume Processing details
- PDF Text Extraction: Using PyPDF2 for accurate text parsing
- Skills Identification: AI-powered skill detection
- Experience Parsing: Automatic work history extraction
- Education Analysis: Academic background processing
- 📄 PDF files (primary)
- 📝 Plain text input
- 🔄 Multiple resume versions
- Text Extraction → Raw text from PDF/input
- Content Analysis → Google Gemini processes content
- Structured Parsing → JSON format with categorized data
- Validation → Ensures data quality and completeness
{
"name": "John Doe",
"email": "[email protected]",
"skills": ["Python", "React", "SQL"],
"experience": [
{
"company": "Tech Corp",
"position": "Software Engineer",
"duration": "2020-2023"
}
],
"education": [...],
"projects": [...]
}Click to expand AI Engine details
- Resume-Based Questions: Tailored to candidate's background
- Category Distribution: Technical, behavioral, situational
- Difficulty Scaling: Adaptive question complexity
- Follow-up Intelligence: Context-aware follow-up questions
evaluation_criteria = {
"technical_accuracy": "Technical knowledge demonstration",
"communication_clarity": "Clear and articulate responses",
"problem_solving": "Analytical thinking and approach",
"experience_relevance": "Real-world application examples"
}- AI Analysis (60%): Google Gemini evaluates content quality
- Similarity Matching (40%): TF-IDF compares with ideal answers
- Final Score: Weighted combination with detailed breakdown
- Lightweight Processing: TF-IDF instead of heavy transformers
- Caching Strategy: Reduces API calls for similar questions
- Error Handling: Graceful fallbacks for AI service issues
- Response Time: Average 2-3 seconds per evaluation
Click to expand Voice Processing details
- Audio Capture: Browser MediaRecorder API
- Format Support: WAV, MP3, M4A, OGG
- Whisper Integration: OpenAI's state-of-the-art STT
- Quality Enhancement: Noise reduction and normalization
class VoiceProcessor:
def __init__(self):
self.whisper_model = whisper.load_model("base")
def speech_to_text(self, audio_path):
# Advanced audio processing
result = self.whisper_model.transcribe(audio_path)
return result["text"]// Voice recording functionality
const recordVoice = async () => {
const stream = await navigator.mediaDevices.getUserMedia({ audio: true });
const recorder = new MediaRecorder(stream);
// Recording logic...
};- Microphone Permissions: Graceful permission handling
- Audio Quality: Automatic quality detection
- Fallback Options: Text input when voice fails
- Browser Compatibility: Cross-browser support
Click to expand Analytics details
- Overall Score: Comprehensive performance rating
- Skill Breakdown: Individual skill assessments
- Progress Tracking: Improvement over time
- Comparative Analysis: Benchmarking against standards
def generate_comprehensive_report(self, data):
pdf = FPDF()
pdf.add_page()
# Header with branding
self._add_header(pdf, data)
# Performance summary with charts
self._add_performance_summary(pdf, data)
# Detailed question analysis
self._add_question_breakdown(pdf, data)
# Recommendations and next steps
self._add_recommendations(pdf, data)
return pdf.output(dest='S').encode('latin-1')- Executive Summary: High-level performance overview
- Skills Analysis: Detailed breakdown by competency
- Question-by-Question: Individual answer evaluations
- Improvement Roadmap: Personalized recommendations
- Progress Visualization: Charts and graphs
Click to expand Database details
CREATE TABLE users (
id INTEGER PRIMARY KEY,
email VARCHAR(120) UNIQUE NOT NULL,
full_name VARCHAR(100),
password_hash VARCHAR(255),
created_at DATETIME DEFAULT CURRENT_TIMESTAMP
);CREATE TABLE resumes (
id INTEGER PRIMARY KEY,
user_id INTEGER FOREIGN KEY,
text_content TEXT,
file_path VARCHAR(255),
parsed_data JSON,
created_at DATETIME DEFAULT CURRENT_TIMESTAMP
);CREATE TABLE interviews (
id INTEGER PRIMARY KEY,
user_id INTEGER FOREIGN KEY,
start_time DATETIME,
end_time DATETIME,
transcript TEXT,
evaluation JSON,
report_path VARCHAR(255),
created_at DATETIME DEFAULT CURRENT_TIMESTAMP
);- SQLAlchemy Integration: Object-relational mapping
- Relationship Management: Foreign key constraints
- JSON Field Support: Flexible data storage
- Migration Support: Database version control
journey
title AI Interview CRM User Journey
section Getting Started
Sign Up : 5: User
Login : 5: User
Upload Resume : 4: User
section Interview Preparation
Generate Questions: 5: AI
Review Profile : 4: User
Start Interview : 5: User
section Interview Process
Answer Questions : 4: User
Get Real-time Feedback: 5: AI
Complete Interview: 4: User
section Results & Improvement
View Report : 5: User
Download PDF : 4: User
Track Progress : 5: User
- Hero Section: Compelling value proposition
- Feature Highlights: Key platform benefits
- Call-to-Action: Quick registration process
- Social Proof: Success stories and testimonials
- Performance Overview: Quick stats and metrics
- Recent Activity: Latest interviews and scores
- Progress Tracking: Visual improvement charts
- Quick Actions: Start new interview, view reports
- Question Display: Clear, readable question presentation
- Response Options: Voice recording or text input
- Progress Indicator: Current question position
- Real-time Feedback: Instant scoring and suggestions
- Executive Summary: High-level performance overview
- Detailed Analysis: Question-by-question breakdown
- Visual Charts: Performance graphs and comparisons
- Action Items: Personalized improvement recommendations
# Run all tests
python test_platform.py
# Run specific test categories
python -m pytest tests/ -k "authentication"
python -m pytest tests/ -k "interview_flow"
python -m pytest tests/ -k "ai_engine"- ✅ Authentication: Registration, login, JWT validation
- ✅ Resume Processing: PDF parsing, AI analysis
- ✅ Interview Flow: Question generation, answer evaluation
- ✅ Voice Processing: STT, audio handling
- ✅ Report Generation: PDF creation, analytics
- ✅ Database Operations: CRUD operations, relationships
- ✅ API Endpoints: All REST endpoints
- ✅ Error Handling: Edge cases, failure scenarios
- CSS Variables: Easy theme customization
- Responsive Design: Mobile-first approach
- Animation Library: Smooth transitions and effects
- Component System: Reusable UI components
- Modern ES6+: Clean, maintainable code
- API Integration: Fetch-based HTTP client
- Voice Recording: MediaRecorder API integration
- Real-time Updates: WebSocket support ready
# 🤖 AI Configuration
GOOGLE_API_KEY=your_gemini_api_key_here
AI_MODEL=gemini-1.5-flash
# 🗄️ Database Configuration
DATABASE_URL=sqlite:///interview.db
SQLALCHEMY_TRACK_MODIFICATIONS=False
# 🔐 Security Configuration
SECRET_KEY=your_super_secret_key_here
JWT_SECRET_KEY=your_jwt_secret_key_here
JWT_EXPIRATION_HOURS=24
# 📁 File Upload Configuration
UPLOAD_FOLDER=static/uploads
MAX_CONTENT_LENGTH=16777216 # 16MB
# 🎤 Voice Processing Configuration
WHISPER_MODEL=base
SUPPORTED_AUDIO_FORMATS=wav,mp3,m4a,ogg
# 📊 Analytics Configuration
ENABLE_ANALYTICS=True
REPORT_GENERATION=TrueFROM python:3.9-slim
WORKDIR /app
COPY requirements.txt .
RUN pip install -r requirements.txt
COPY . .
EXPOSE 5000
CMD ["gunicorn", "--bind", "0.0.0.0:5000", "app:app"]- 🔧 Heroku: One-click deployment
- ☁️ AWS: EC2, ECS, or Lambda
- 🌐 Google Cloud: App Engine or Cloud Run
- 💙 Azure: App Service or Container Instances
- Development: SQLite (included)
- Production: PostgreSQL, MySQL, or MongoDB
- Cloud: AWS RDS, Google Cloud SQL, Azure Database
- HTTPS: SSL/TLS encryption
- Environment Variables: Secure secret management
- Rate Limiting: API endpoint protection
- Input Validation: XSS and injection prevention
- CORS Configuration: Cross-origin request handling
- Lightweight AI: TF-IDF instead of heavy transformers (90% size reduction)
- Efficient Caching: Redis integration ready
- Database Indexing: Optimized queries
- CDN Integration: Static asset delivery
- Lazy Loading: On-demand resource loading
- Performance Metrics: Response time tracking
- Error Monitoring: Automated error reporting
- Usage Analytics: User behavior insights
- Health Checks: System status monitoring
-
🍴 Fork the Repository
git clone https://github.com/hari7261/AI-INTERVIEW-CRM.git
-
🌿 Create Feature Branch
git checkout -b feature/amazing-feature
-
💡 Make Your Changes
- Follow code style guidelines
- Add tests for new features
- Update documentation
-
✅ Test Your Changes
python test_platform.py
-
📤 Submit Pull Request
- Clear description of changes
- Reference related issues
- Include screenshots if UI changes
- Code Style: PEP 8 for Python, ESLint for JavaScript
- Documentation: Docstrings for all functions
- Testing: Minimum 80% code coverage
- Version Control: Semantic versioning (semver)
Use GitHub Issues with the following template:
- Bug Description: Clear, concise description
- Steps to Reproduce: Detailed reproduction steps
- Expected Behavior: What should happen
- Screenshots: Visual evidence if applicable
- Environment: OS, Python version, browser
This project is licensed under the MIT License - see the LICENSE file for details.
- ✅ Commercial Use: Use in commercial projects
- ✅ Modification: Modify and adapt the code
- ✅ Distribution: Share with others
- ✅ Private Use: Use for personal projects
- ❌ Liability: No warranty or liability
- ❌ Patent Grant: No patent rights granted
- Google Gemini: For powerful AI capabilities
- OpenAI Whisper: For excellent speech-to-text
- Flask Community: For the amazing web framework
- Open Source Contributors: For inspiration and tools
🚀 Passionate about building innovative solutions that make a difference
|
"Having gone through countless interviews myself and seeing friends struggle with interview preparation, I realized there was a gap in accessible, AI-powered practice platforms. This project combines my passion for AI with my desire to help fellow developers and job seekers succeed in their careers."
- 🤖 Democratize AI: Make advanced AI interview practice accessible to everyone
- 📈 Skill Enhancement: Help candidates identify and improve their weak areas
- 🌍 Global Impact: Support job seekers worldwide in achieving their career goals
- 🔄 Continuous Learning: Provide personalized feedback for ongoing improvement
| 🎯 User-Centric | 🔧 Clean Code | 🚀 Performance | 🌟 Innovation |
|---|---|---|---|
| Always put user needs first | Write maintainable, readable code | Optimize for speed and efficiency | Embrace cutting-edge technology |
| Gather feedback continuously | Follow best practices | Test performance rigorously | Experiment with new ideas |
| Design intuitive interfaces | Document thoroughly | Scale intelligently | Stay ahead of trends |
🎯 Helping developers and job seekers worldwide achieve their career dreams!
I'm always excited to connect with fellow developers, discuss new ideas, or help with any questions you might have about the project!
🤝 Let's build something amazing together!
🚀 Get Started Now • ⭐ Star on GitHub • 🐛 Report Issues
Made with ❤️ by Hari, for developers worldwide
🎉 Thank you for choosing AI Interview CRM! Together, let's help candidates ace their interviews and build their dream careers! 🚀