src/config.py

"""Project-level configuration values."""

from dataclasses import dataclass
import os

from dotenv import load_dotenv

load_dotenv()


@dataclass(frozen=True)
class Settings:
    """Central settings object for model and runtime controls."""

    model_name: str = os.getenv("MODEL_NAME", "Qwen/Qwen2.5-Coder-1.5B-Instruct")
    fallback_model_name: str = os.getenv("FALLBACK_MODEL_NAME", "Qwen/Qwen2.5-Coder-0.5B-Instruct")
    final_fallback_model_name: str = os.getenv("FINAL_FALLBACK_MODEL_NAME", "sshleifer/tiny-gpt2")
    embedding_model: str = os.getenv("EMBEDDING_MODEL", "sentence-transformers/all-MiniLM-L6-v2")
    max_new_tokens: int = int(os.getenv("MAX_NEW_TOKENS", "256"))
    temperature: float = float(os.getenv("TEMPERATURE", "0.2"))
    top_p: float = float(os.getenv("TOP_P", "0.95"))
    use_rag: bool = os.getenv("USE_RAG", "true").lower() == "true"
    force_mock_mode: bool = os.getenv("FORCE_MOCK_MODE", "false").lower() == "true"
    api_key: str = os.getenv("API_KEY", "")
    rate_limit_per_minute: int = int(os.getenv("RATE_LIMIT_PER_MINUTE", "30"))


settings = Settings()