config.py

"""
Configuration file for AI Resume Screener
Modify these settings to customize the application behavior
"""

# Model Configuration
MODELS = {
    "embedding_model": "BAAI/bge-large-en-v1.5",
    "cross_encoder": "cross-encoder/ms-marco-MiniLM-L6-v2", 
    "llm_model": "Qwen/Qwen2-1.5B",  # Using smaller model for compatibility
}

# Pipeline Configuration
PIPELINE_CONFIG = {
    "faiss_recall_top_k": 50,
    "cross_encoder_top_k": 20,
    "max_text_length": 8000,
    "embedding_dimension": 1024,
}

# Scoring Weights (must sum to 1.0)
SCORING_WEIGHTS = {
    "cross_encoder": 0.5,
    "bm25": 0.3,
    "intent": 0.2,
}

# Intent Analysis Configuration
INTENT_CONFIG = {
    "max_prompt_length": 1024,
    "max_new_tokens": 10,
    "temperature": 0.1,
    "intent_scores": {
        "yes": 0.9,
        "maybe": 0.5,
        "no": 0.1,
    }
}

# File Processing Configuration
FILE_CONFIG = {
    "supported_formats": ["pdf", "docx", "txt", "csv"],
    "max_file_size_mb": 10,
    "max_files_per_upload": 50,
}

# UI Configuration
UI_CONFIG = {
    "page_title": "🤖 AI Resume Screener",
    "page_icon": "🤖",
    "layout": "wide",
    "sidebar_state": "expanded",
    "max_display_resumes": 100,
}

# Performance Configuration
PERFORMANCE_CONFIG = {
    "use_gpu": True,
    "quantization": True,
    "batch_size": 32,
    "cache_models": True,
}

# Skills Database
TECHNICAL_SKILLS = [
    # Programming Languages
    'python', 'java', 'javascript', 'typescript', 'c++', 'c#', 'go', 'rust', 
    'scala', 'r', 'matlab', 'php', 'ruby', 'swift', 'kotlin', 'dart',
    
    # Web Technologies
    'html', 'css', 'react', 'angular', 'vue', 'node.js', 'express', 'django', 
    'flask', 'fastapi', 'spring', 'laravel', 'bootstrap', 'tailwind',
    
    # Databases
    'sql', 'mongodb', 'postgresql', 'mysql', 'redis', 'elasticsearch', 
    'cassandra', 'dynamodb', 'sqlite', 'oracle',
    
    # Cloud & DevOps
    'aws', 'azure', 'gcp', 'docker', 'kubernetes', 'terraform', 'ansible',
    'jenkins', 'gitlab', 'github', 'ci/cd', 'devops', 'microservices',
    
    # Data Science & ML
    'machine learning', 'deep learning', 'tensorflow', 'pytorch', 'keras',
    'scikit-learn', 'pandas', 'numpy', 'matplotlib', 'plotly', 'seaborn',
    'jupyter', 'spark', 'hadoop', 'kafka', 'airflow',
    
    # Analytics & BI
    'tableau', 'powerbi', 'excel', 'google analytics', 'mixpanel', 'amplitude',
    'looker', 'qlik', 'sas', 'spss', 'stata',
    
    # Operating Systems & Tools
    'linux', 'ubuntu', 'centos', 'windows', 'macos', 'bash', 'powershell',
    'git', 'vim', 'vscode', 'intellij', 'eclipse',
    
    # Methodologies
    'agile', 'scrum', 'kanban', 'lean', 'waterfall', 'tdd', 'bdd',
    
    # Networking & Security
    'tcp/ip', 'http', 'https', 'ssl', 'oauth', 'jwt', 'api', 'rest', 'graphql',
    'nginx', 'apache', 'load balancing', 'vpn', 'firewall',
]

# Job Categories for Enhanced Matching
JOB_CATEGORIES = {
    "software_engineer": [
        "programming", "coding", "development", "software", "engineer", "developer"
    ],
    "data_scientist": [
        "data", "analytics", "machine learning", "statistics", "modeling", "scientist"
    ],
    "devops_engineer": [
        "devops", "infrastructure", "deployment", "automation", "cloud", "operations"
    ],
    "product_manager": [
        "product", "manager", "strategy", "roadmap", "requirements", "stakeholder"
    ],
    "designer": [
        "design", "ui", "ux", "user experience", "interface", "visual", "creative"
    ],
    "marketing": [
        "marketing", "campaign", "brand", "social media", "content", "seo", "sem"
    ],
    "sales": [
        "sales", "business development", "account", "revenue", "client", "customer"
    ]
}

# Default Job Description Template
DEFAULT_JOB_DESCRIPTION = """
Software Engineer - Full Stack Development

We are looking for a talented Software Engineer to join our growing team. 

Requirements:
- 3+ years of experience in software development
- Proficiency in Python, JavaScript, and SQL
- Experience with React and Node.js
- Knowledge of cloud platforms (AWS, Azure, or GCP)
- Familiarity with Docker and CI/CD pipelines
- Strong problem-solving and communication skills

Responsibilities:
- Develop and maintain web applications
- Collaborate with cross-functional teams
- Write clean, maintainable code
- Participate in code reviews
- Contribute to technical architecture decisions

Nice to have:
- Experience with machine learning
- Knowledge of microservices architecture
- DevOps experience
- Open source contributions
"""

# Error Messages
ERROR_MESSAGES = {
    "models_not_loaded": "❌ AI models are still loading. Please wait...",
    "no_job_description": "❌ Please enter a job description",
    "no_resumes": "❌ Please load some resumes first",
    "file_processing_error": "❌ Error processing file: {filename}",
    "model_loading_error": "❌ Error loading model: {model_name}",
    "pipeline_error": "❌ Error in pipeline stage: {stage}",
}

# Success Messages
SUCCESS_MESSAGES = {
    "models_loaded": "✅ All AI models loaded successfully!",
    "files_processed": "✅ Processed {count} resume files",
    "pipeline_complete": "✅ Resume screening pipeline completed!",
    "results_exported": "✅ Results exported successfully",
}

# Validation Rules
VALIDATION_RULES = {
    "min_job_description_length": 50,
    "max_job_description_length": 10000,
    "min_resume_length": 20,
    "max_resume_length": 20000,
    "min_resumes_for_ranking": 1,
    "max_resumes_for_ranking": 1000,
}