config.py

import os
from pathlib import Path
from typing import Dict, Any, Optional
import streamlit as st

class Config:
    """
    Centralized configuration management for BLUESCARF AI HR Assistant.
    Provides environment-aware settings with sensible defaults and validation.
    """
    
    def __init__(self):
        """Initialize configuration with environment-specific optimizations."""
        self._load_environment_config()
        self._validate_configuration()
    
    def _load_environment_config(self):
        """Load configuration from environment variables with intelligent defaults."""
        
        # === Core Application Settings ===
        self.APP_NAME = "BLUESCARF AI HR Assistant"
        self.APP_VERSION = "1.0.0"
        self.COMPANY_NAME = "BLUESCARF ARTIFICIAL INTELLIGENCE"
        
        # === Document Processing Configuration ===
        # Optimal chunk size for semantic coherence (384-512 tokens typical)
        self.CHUNK_SIZE = int(os.getenv('CHUNK_SIZE', 1000))
        
        # Overlap for context continuity (10-20% of chunk size)
        self.CHUNK_OVERLAP = int(os.getenv('CHUNK_OVERLAP', 200))
        
        # Minimum viable chunk size to filter noise
        self.MIN_CHUNK_SIZE = int(os.getenv('MIN_CHUNK_SIZE', 100))
        
        # Maximum file size (50MB default for enterprise documents)
        self.MAX_FILE_SIZE = int(os.getenv('MAX_FILE_SIZE', 50 * 1024 * 1024))
        
        # === Vector Store Configuration ===
        # Persistent storage path with environment fallback
        default_db_path = Path("vector_db")
        self.VECTOR_DB_PATH = Path(os.getenv('VECTOR_DB_PATH', default_db_path))
        
        # Maximum context chunks for retrieval (balance between context and noise)
        self.MAX_CONTEXT_CHUNKS = int(os.getenv('MAX_CONTEXT_CHUNKS', 5))
        
        # Similarity search parameters
        self.SIMILARITY_THRESHOLD = float(os.getenv('SIMILARITY_THRESHOLD', 0.5))
        self.MAX_SEARCH_RESULTS = int(os.getenv('MAX_SEARCH_RESULTS', 10))
        
        # === API Configuration ===
        # Gemini model selection (optimized for reasoning and context)
        self.GEMINI_MODEL = os.getenv('GEMINI_MODEL', 'gemini-pro')
        
        # Response generation parameters
        self.MAX_RESPONSE_TOKENS = int(os.getenv('MAX_RESPONSE_TOKENS', 1024))
        self.TEMPERATURE = float(os.getenv('TEMPERATURE', 0.3))  # Conservative for factual responses
        
        # API rate limiting and retry configuration
        self.API_RETRY_ATTEMPTS = int(os.getenv('API_RETRY_ATTEMPTS', 3))
        self.API_TIMEOUT_SECONDS = int(os.getenv('API_TIMEOUT_SECONDS', 30))
        
        # === Security Configuration ===
        # Session and authentication settings
        self.SESSION_TIMEOUT_HOURS = int(os.getenv('SESSION_TIMEOUT_HOURS', 8))
        self.ADMIN_SESSION_TIMEOUT_HOURS = int(os.getenv('ADMIN_SESSION_TIMEOUT_HOURS', 2))
        
        # === Logging and Monitoring ===
        # Application logging configuration
        self.LOG_LEVEL = os.getenv('LOG_LEVEL', 'INFO')
        self.LOG_FILE_PATH = Path(os.getenv('LOG_FILE_PATH', 'logs/hr_assistant.log'))
        self.ENABLE_INTERACTION_LOGGING = os.getenv('ENABLE_INTERACTION_LOGGING', 'true').lower() == 'true'
        
        # === Performance Optimization ===
        # Embedding model caching and batch processing
        self.EMBEDDING_BATCH_SIZE = int(os.getenv('EMBEDDING_BATCH_SIZE', 32))
        self.ENABLE_MODEL_CACHING = os.getenv('ENABLE_MODEL_CACHING', 'true').lower() == 'true'
        
        # Streamlit performance settings
        self.STREAMLIT_THEME = os.getenv('STREAMLIT_THEME', 'light')
        self.ENABLE_CACHING = os.getenv('ENABLE_CACHING', 'true').lower() == 'true'
        
        # === Deployment Configuration ===
        # Environment detection for deployment-specific optimizations
        self.ENVIRONMENT = os.getenv('ENVIRONMENT', 'development')
        self.IS_PRODUCTION = self.ENVIRONMENT.lower() == 'production'
        self.IS_HUGGINGFACE = os.getenv('SPACE_ID') is not None
        
        # Resource limits for cloud deployment
        if self.IS_HUGGINGFACE:
            self._apply_huggingface_optimizations()
    
    def _apply_huggingface_optimizations(self):
        """Apply Hugging Face Spaces specific optimizations."""
        # Reduce memory footprint for cloud deployment
        self.CHUNK_SIZE = min(self.CHUNK_SIZE, 800)
        self.MAX_CONTEXT_CHUNKS = min(self.MAX_CONTEXT_CHUNKS, 4)
        self.EMBEDDING_BATCH_SIZE = min(self.EMBEDDING_BATCH_SIZE, 16)
        self.MAX_FILE_SIZE = min(self.MAX_FILE_SIZE, 25 * 1024 * 1024)  # 25MB limit
        
        # Optimize for limited computational resources
        self.ENABLE_MODEL_CACHING = True
        self.API_TIMEOUT_SECONDS = 60  # More lenient timeout for cloud
    
    def _validate_configuration(self):
        """Validate configuration parameters and ensure system compatibility."""
        validation_errors = []
        
        # Validate numeric ranges
        if self.CHUNK_SIZE < 100 or self.CHUNK_SIZE > 2000:
            validation_errors.append("CHUNK_SIZE must be between 100 and 2000")
        
        if self.CHUNK_OVERLAP >= self.CHUNK_SIZE:
            validation_errors.append("CHUNK_OVERLAP must be less than CHUNK_SIZE")
        
        if self.SIMILARITY_THRESHOLD < 0 or self.SIMILARITY_THRESHOLD > 1:
            validation_errors.append("SIMILARITY_THRESHOLD must be between 0 and 1")
        
        if self.TEMPERATURE < 0 or self.TEMPERATURE > 1:
            validation_errors.append("TEMPERATURE must be between 0 and 1")
        
        # Validate paths and create directories
        try:
            self.VECTOR_DB_PATH.mkdir(parents=True, exist_ok=True)
            self.LOG_FILE_PATH.parent.mkdir(parents=True, exist_ok=True)
        except Exception as e:
            validation_errors.append(f"Cannot create required directories: {str(e)}")
        
        # Report validation errors
        if validation_errors:
            error_message = "Configuration validation failed:\n" + "\n".join(validation_errors)
            if 'streamlit' in globals():
                st.error(error_message)
            else:
                print(f"ERROR: {error_message}")
            raise ValueError(error_message)
    
    def get_hr_context_prompt(self) -> str:
        """
        Generate context-aware system prompt for HR assistant interactions.
        
        Returns:
            Optimized system prompt for Gemini API
        """
        return f"""
        You are an intelligent HR Assistant for {self.COMPANY_NAME}.
        
        CORE IDENTITY:
        - Professional, helpful, and knowledgeable about company policies
        - Exclusively focused on HR-related matters using provided company documents
        - Maintain confidentiality and provide accurate, policy-based guidance
        
        RESPONSE GUIDELINES:
        1. SCOPE: Only answer questions related to company HR policies, procedures, and benefits
        2. SOURCE: Base responses exclusively on provided company documents
        3. CLARITY: Provide clear, actionable guidance with specific policy references
        4. BOUNDARIES: Politely redirect non-HR questions to appropriate resources
        5. ACCURACY: If information isn't in the documents, state this clearly
        6. TONE: Professional yet approachable, maintaining company values
        
        STRUCTURED RESPONSE FORMAT:
        - Direct answer to the question
        - Relevant policy/document references
        - Next steps or additional resources if applicable
        - Contact information for complex cases requiring human intervention
        
        Remember: You represent {self.COMPANY_NAME} and should reflect our commitment to supporting employees through clear, accurate HR guidance.
        """
    
    def get_similarity_search_config(self) -> Dict[str, Any]:
        """
        Get optimized configuration for vector similarity search.
        
        Returns:
            Dictionary with search parameters
        """
        return {
            'k': self.MAX_CONTEXT_CHUNKS,
            'similarity_threshold': self.SIMILARITY_THRESHOLD,
            'max_results': self.MAX_SEARCH_RESULTS,
            'include_metadata': True,
            'score_threshold': 0.3,  # Minimum relevance score
            'diversity_penalty': 0.1  # Encourage diverse results
        }
    
    def get_gemini_config(self) -> Dict[str, Any]:
        """
        Get optimized configuration for Gemini API calls.
        
        Returns:
            Dictionary with API parameters
        """
        return {
            'model': self.GEMINI_MODEL,
            'temperature': self.TEMPERATURE,
            'max_output_tokens': self.MAX_RESPONSE_TOKENS,
            'top_p': 0.8,  # Nucleus sampling for balanced creativity
            'top_k': 40,   # Limit token consideration for consistency
            'stop_sequences': ["Human:", "Assistant:", "---"],
        }
    
    def get_document_processing_config(self) -> Dict[str, Any]:
        """
        Get optimized configuration for document processing pipeline.
        
        Returns:
            Dictionary with processing parameters
        """
        return {
            'chunk_size': self.CHUNK_SIZE,
            'chunk_overlap': self.CHUNK_OVERLAP,
            'min_chunk_size': self.MIN_CHUNK_SIZE,
            'max_file_size': self.MAX_FILE_SIZE,
            'embedding_batch_size': self.EMBEDDING_BATCH_SIZE,
            'enable_caching': self.ENABLE_MODEL_CACHING,
            'supported_formats': ['pdf'],
            'content_filters': {
                'min_word_count': 10,
                'max_word_count': 2000,
                'remove_headers_footers': True,
                'normalize_whitespace': True
            }
        }
    
    def get_streamlit_config(self) -> Dict[str, str]:
        """
        Get Streamlit-specific configuration for optimal UI performance.
        
        Returns:
            Dictionary with Streamlit settings
        """
        return {
            'page_title': self.APP_NAME,
            'page_icon': '🔷',
            'layout': 'wide',
            'initial_sidebar_state': 'collapsed',
            'menu_items': {
                'Get Help': f'mailto:support@{self.COMPANY_NAME.lower().replace(" ", "")}.com',
                'Report a bug': None,
                'About': f'{self.APP_NAME} v{self.APP_VERSION} - Powered by Google Gemini AI'
            }
        }
    
    def get_logging_config(self) -> Dict[str, Any]:
        """
        Get comprehensive logging configuration for monitoring and debugging.
        
        Returns:
            Dictionary with logging parameters
        """
        return {
            'level': self.LOG_LEVEL,
            'file_path': str(self.LOG_FILE_PATH),
            'enable_interaction_logging': self.ENABLE_INTERACTION_LOGGING,
            'log_format': '%(asctime)s - %(name)s - %(levelname)s - %(message)s',
            'max_file_size': 10 * 1024 * 1024,  # 10MB
            'backup_count': 5,
            'console_output': not self.IS_PRODUCTION
        }
    
    def get_security_config(self) -> Dict[str, Any]:
        """
        Get security configuration for admin access and session management.
        
        Returns:
            Dictionary with security parameters
        """
        return {
            'session_timeout_hours': self.SESSION_TIMEOUT_HOURS,
            'admin_session_timeout_hours': self.ADMIN_SESSION_TIMEOUT_HOURS,
            'password_min_length': 8,
            'password_complexity_required': self.IS_PRODUCTION,
            'enable_rate_limiting': self.IS_PRODUCTION,
            'max_failed_attempts': 3,
            'lockout_duration_minutes': 15
        }
    
    def create_environment_file(self, file_path: Optional[str] = None) -> str:
        """
        Generate .env file template with all configuration options.
        
        Args:
            file_path: Optional path for .env file
            
        Returns:
            Path to created .env file
        """
        if not file_path:
            file_path = '.env'
        
        env_content = f"""# {self.APP_NAME} Configuration
# Generated automatically - modify as needed for your deployment

# === Application Settings ===
APP_NAME="{self.APP_NAME}"
APP_VERSION="{self.APP_VERSION}"
COMPANY_NAME="{self.COMPANY_NAME}"
ENVIRONMENT=production

# === Document Processing ===
CHUNK_SIZE={self.CHUNK_SIZE}
CHUNK_OVERLAP={self.CHUNK_OVERLAP}
MIN_CHUNK_SIZE={self.MIN_CHUNK_SIZE}
MAX_FILE_SIZE={self.MAX_FILE_SIZE}

# === Vector Database ===
VECTOR_DB_PATH=./vector_db
MAX_CONTEXT_CHUNKS={self.MAX_CONTEXT_CHUNKS}
SIMILARITY_THRESHOLD={self.SIMILARITY_THRESHOLD}

# === API Configuration ===
GEMINI_MODEL={self.GEMINI_MODEL}
TEMPERATURE={self.TEMPERATURE}
MAX_RESPONSE_TOKENS={self.MAX_RESPONSE_TOKENS}

# === Security ===
SESSION_TIMEOUT_HOURS={self.SESSION_TIMEOUT_HOURS}
ADMIN_SESSION_TIMEOUT_HOURS={self.ADMIN_SESSION_TIMEOUT_HOURS}

# === Logging ===
LOG_LEVEL={self.LOG_LEVEL}
LOG_FILE_PATH=./logs/hr_assistant.log
ENABLE_INTERACTION_LOGGING=true

# === Performance ===
EMBEDDING_BATCH_SIZE={self.EMBEDDING_BATCH_SIZE}
ENABLE_MODEL_CACHING=true
ENABLE_CACHING=true
"""
        
        try:
            with open(file_path, 'w') as f:
                f.write(env_content)
            return file_path
        except Exception as e:
            if 'streamlit' in globals():
                st.error(f"Failed to create .env file: {str(e)}")
            return ""
    
    def __str__(self) -> str:
        """String representation for debugging and logging."""
        return f"{self.APP_NAME} Config (Environment: {self.ENVIRONMENT})"
    
    def __repr__(self) -> str:
        """Developer-friendly representation."""
        return f"Config(app='{self.APP_NAME}', env='{self.ENVIRONMENT}', version='{self.APP_VERSION}')"