src/config.py

"""HR Report Generator - Configuration Module (HuggingFace Version)."""

from pathlib import Path
from typing import Literal
import os

from pydantic import Field
from pydantic_settings import BaseSettings, SettingsConfigDict


class Settings(BaseSettings):
    """Application settings loaded from environment variables."""

    model_config = SettingsConfigDict(
        env_file=".env",
        env_file_encoding="utf-8",
        extra="ignore",
    )

    # LLM Configuration (loaded from environment or endpoints.txt)
    llm_model: str = Field(default="google/gemma-2-9b-it:free", description="LLM model name")
    llm_temperature: float = Field(default=0.0, ge=0.0, le=1.0, description="LLM temperature")

    # Embedding Configuration
    embedding_model: str = Field(
        default="BAAI/bge-small-en-v1.5",
        description="HuggingFace embedding model",
    )

    # Paths (relative for Docker)
    data_dir: Path = Field(default=Path("./data"))
    documents_dir: Path = Field(default=Path("./data/documents"))
    markdown_dir: Path = Field(default=Path("./data/markdown"))
    embeddings_dir: Path = Field(default=Path("./data/embeddings"))
    outputs_dir: Path = Field(default=Path("./data/outputs"))
    templates_dir: Path = Field(default=Path("./templates"))

    # Vector Store
    faiss_index_path: Path = Field(default=Path("./data/embeddings/faiss_index"))

    # Chunking Configuration
    chunk_size: int = Field(default=512, description="Target chunk size in tokens")
    chunk_overlap: int = Field(default=50, description="Overlap between chunks")

    # Retrieval Configuration
    retrieval_top_k: int = Field(default=5, description="Number of documents to retrieve")
    retrieval_min_score: float = Field(default=0.3, description="Minimum similarity score")

    def ensure_directories(self) -> None:
        """Create all required directories if they don't exist."""
        for path in [
            self.data_dir,
            self.documents_dir,
            self.markdown_dir,
            self.embeddings_dir,
            self.outputs_dir,
            self.templates_dir,
        ]:
            path.mkdir(parents=True, exist_ok=True)


# Global settings instance
settings = Settings()