import dns.resolver import logging import yaml import os from datetime import datetime from enum import Enum from pathlib import Path from fastapi import Request from typing import Dict, Optional class TaskStatus(str, Enum): PROCESSING = "processing" FAILED = "failed" COMPLETED = "completed" class FilterType(str, Enum): RAW = "raw" FIT = "fit" BM25 = "bm25" LLM = "llm" def load_config() -> Dict: """Load and return application configuration with environment variable overrides.""" config_path = Path(__file__).parent / "config.yml" with open(config_path, "r") as config_file: config = yaml.safe_load(config_file) # Override LLM provider from environment if set llm_provider = os.environ.get("LLM_PROVIDER") if llm_provider: config["llm"]["provider"] = llm_provider logging.info(f"LLM provider overridden from environment: {llm_provider}") # Also support direct API key from environment if the provider-specific key isn't set llm_api_key = os.environ.get("LLM_API_KEY") if llm_api_key and "api_key" not in config["llm"]: config["llm"]["api_key"] = llm_api_key logging.info("LLM API key loaded from LLM_API_KEY environment variable") return config def setup_logging(config: Dict) -> None: """Configure application logging.""" logging.basicConfig( level=config["logging"]["level"], format=config["logging"]["format"] ) def get_base_url(request: Request) -> str: """Get base URL including scheme and host.""" return f"{request.url.scheme}://{request.url.netloc}" def is_task_id(value: str) -> bool: """Check if the value matches task ID pattern.""" return value.startswith("llm_") and "_" in value def datetime_handler(obj: any) -> Optional[str]: """Handle datetime serialization for JSON.""" if hasattr(obj, 'isoformat'): return obj.isoformat() raise TypeError(f"Object of type {type(obj)} is not JSON serializable") def should_cleanup_task(created_at: str, ttl_seconds: int = 3600) -> bool: """Check if task should be cleaned up based on creation time.""" created = datetime.fromisoformat(created_at) return (datetime.now() - created).total_seconds() > ttl_seconds def decode_redis_hash(hash_data: Dict[bytes, bytes]) -> Dict[str, str]: """Decode Redis hash data from bytes to strings.""" return {k.decode('utf-8'): v.decode('utf-8') for k, v in hash_data.items()} def get_llm_api_key(config: Dict, provider: Optional[str] = None) -> Optional[str]: """Get the appropriate API key based on the LLM provider. Args: config: The application configuration dictionary provider: Optional provider override (e.g., "openai/gpt-4") Returns: The API key if directly configured, otherwise None to let litellm handle it """ # Check if direct API key is configured (for backward compatibility) if "api_key" in config["llm"]: return config["llm"]["api_key"] # Return None - litellm will automatically find the right environment variable return None def validate_llm_provider(config: Dict, provider: Optional[str] = None) -> tuple[bool, str]: """Validate that the LLM provider has an associated API key. Args: config: The application configuration dictionary provider: Optional provider override (e.g., "openai/gpt-4") Returns: Tuple of (is_valid, error_message) """ # If a direct API key is configured, validation passes if "api_key" in config["llm"]: return True, "" # Otherwise, trust that litellm will find the appropriate environment variable # We can't easily validate this without reimplementing litellm's logic return True, "" def get_llm_temperature(config: Dict, provider: Optional[str] = None) -> Optional[float]: """Get temperature setting based on the LLM provider. Priority order: 1. Provider-specific environment variable (e.g., OPENAI_TEMPERATURE) 2. Global LLM_TEMPERATURE environment variable 3. None (to use litellm/provider defaults) Args: config: The application configuration dictionary provider: Optional provider override (e.g., "openai/gpt-4") Returns: The temperature setting if configured, otherwise None """ # Check provider-specific temperature first if provider: provider_name = provider.split('/')[0].upper() provider_temp = os.environ.get(f"{provider_name}_TEMPERATURE") if provider_temp: try: return float(provider_temp) except ValueError: logging.warning(f"Invalid temperature value for {provider_name}: {provider_temp}") # Check global LLM_TEMPERATURE global_temp = os.environ.get("LLM_TEMPERATURE") if global_temp: try: return float(global_temp) except ValueError: logging.warning(f"Invalid global temperature value: {global_temp}") # Return None to use litellm/provider defaults return None def get_llm_base_url(config: Dict, provider: Optional[str] = None) -> Optional[str]: """Get base URL setting based on the LLM provider. Priority order: 1. Provider-specific environment variable (e.g., OPENAI_BASE_URL) 2. Global LLM_BASE_URL environment variable 3. None (to use default endpoints) Args: config: The application configuration dictionary provider: Optional provider override (e.g., "openai/gpt-4") Returns: The base URL if configured, otherwise None """ # Check provider-specific base URL first if provider: provider_name = provider.split('/')[0].upper() provider_url = os.environ.get(f"{provider_name}_BASE_URL") if provider_url: return provider_url # Check global LLM_BASE_URL return os.environ.get("LLM_BASE_URL") def verify_email_domain(email: str) -> bool: try: domain = email.split('@')[1] # Try to resolve MX records for the domain. records = dns.resolver.resolve(domain, 'MX') return True if records else False except Exception as e: return False