src/config.py

import os
from dataclasses import dataclass
from pathlib import Path
from dotenv import load_dotenv

# Load environment variables
load_dotenv()

@dataclass
class Settings:
    # Paths
    BASE_DIR: Path = Path(__file__).resolve().parent.parent
    DATA_DIR: Path = BASE_DIR / "data"
    DB_PATH: Path = DATA_DIR / "satellites.db"
    OUTPUT_FILE: Path = DATA_DIR / "satellites_detailed.json"
    CHROMA_PATH: Path = DATA_DIR / "chroma_db"
    
    # Vector DB
    COLLECTION_NAME: str = "satellites"
    
    # Models
    EMBEDDING_MODEL: str = "BAAI/bge-small-en-v1.5"
    LLM_MODEL: str = "llama-3.3-70b-versatile"
    
    # API Keys
    GROQ_API_KEY: str = os.getenv("GROQ_API_KEY", "")
    
    # Scraping
    MAX_WORKERS: int = 10
    REQUEST_TIMEOUT: int = 10

settings = Settings()