app/core/config.py

from functools import lru_cache
from pathlib import Path
from pydantic import Field, model_validator
from pydantic_settings import BaseSettings, SettingsConfigDict


class Settings(BaseSettings):
    model_config = SettingsConfigDict(env_file=".env", env_file_encoding="utf-8")

    app_name: str = "Fast RAG Chatbot"
    llm_provider: str = Field(default="openai", alias="LLM_PROVIDER")
    groq_api_key: str = Field(default="", alias="GROQ_API_KEY")
    groq_model: str = Field(default="qwen/qwen3-32b", alias="GROQ_MODEL")
    groq_rewrite_model: str = Field(default="llama-3.1-8b-instant", alias="GROQ_REWRITE_MODEL")
    fireworks_api_key: str = Field(default="", alias="FIREWORKS_API_KEY")
    fireworks_model: str = Field(default="accounts/fireworks/models/qwen3-30b-a3b-instruct-2507", alias="FIREWORKS_MODEL")
    fireworks_rewrite_model: str = Field(default="accounts/fireworks/models/qwen3-8b", alias="FIREWORKS_REWRITE_MODEL")
    openai_api_key: str = Field(default="", alias="OPENAI_API_KEY")
    openai_model: str = Field(default="gpt-4o-mini", alias="OPENAI_MODEL")
    openai_rewrite_model: str = Field(default="gpt-4o-mini", alias="OPENAI_REWRITE_MODEL")
    hf_api_key: str = Field(default="", alias="HF_API_KEY")
    hf_model: str = Field(default="meta-llama/Llama-3.1-8B-Instruct", alias="HF_MODEL")
    embedding_model: str = Field(default="BAAI/bge-small-en-v1.5", alias="EMBEDDING_MODEL")
    reranker_model: str = Field(default="cross-encoder/ms-marco-MiniLM-L-6-v2", alias="RERANKER_MODEL")
    docs_dir: Path = Field(default=Path("docs"), alias="DOCS_DIR")
    @model_validator(mode='after')
    def set_persistent_paths(self) -> 'Settings':
        # If we are on Hugging Face (detected by /data volume), 
        # force use of /data for persistence regardless of other settings.
        if Path("/data").exists():
            self.index_dir = Path("/data/index")
            self.sessions_dir = Path("/data/sessions")
        return self
    
    index_dir: Path = Field(default=Path("data/index"), alias="INDEX_DIR")
    sessions_dir: Path = Field(default=Path("data/sessions"), alias="SESSIONS_DIR")
    chunk_size_tokens: int = 350  # Reduced for TPM safety
    chunk_overlap_tokens: int = 80
    top_k: int = Field(default=8, alias="TOP_K")  # Focused retrieval — quality over quantity
    max_context_chunks: int = 5  # Enough for exhaustive lists, focused enough for precision
    request_timeout_s: float = 20.0
    cors_allow_origins: str = Field(default="*", alias="CORS_ALLOW_ORIGINS")
    api_key: str = Field(default="", alias="API_KEY")
    rate_limit_requests: int = Field(default=60, alias="RATE_LIMIT_REQUESTS")
    rate_limit_window_seconds: int = Field(default=60, alias="RATE_LIMIT_WINDOW_SECONDS")

    # SMTP Settings for OTP
    smtp_server: str = Field(default="smtp.gmail.com", alias="SMTP_SERVER")
    smtp_port: int = Field(default=465, alias="SMTP_PORT")
    smtp_user: str = Field(default="", alias="SMTP_USER")
    smtp_pass: str = Field(default="", alias="SMTP_PASS")
    admin_email: str = Field(default="randomjoedown@gmail.com", alias="ADMIN_EMAIL")
    admin_user: str = Field(default="martech_admin", alias="ADMIN_USER")
    admin_pass: str = Field(default="martech_admin_303", alias="ADMIN_PASS")

    # WhatsApp API Settings (Meta Cloud API)
    meta_whatsapp_phone_id: str = Field(default="", alias="META_WHATSAPP_PHONE_ID")
    meta_whatsapp_token: str = Field(default="", alias="META_WHATSAPP_TOKEN")
    meta_whatsapp_admin_number: str = Field(default="", alias="META_WHATSAPP_ADMIN_NUMBER")


@lru_cache
def get_settings() -> Settings:
    return Settings()