app/core/app.py

"""FastAPI application factory and core infrastructure."""

import asyncio
import warnings
from contextlib import asynccontextmanager
from typing import AsyncGenerator

from fastapi import FastAPI
from pydantic import Field
from pydantic_settings import BaseSettings

from app.core.logging import logger
from app.core.dependencies import set_inference_service
from app.services.inference import ResNetInferenceService
from app.api.routes import prediction


class Settings(BaseSettings):
    """Application settings. Override via environment variables or .env file."""

    app_name: str = Field(default="ML Inference Service")
    app_version: str = Field(default="0.1.0")
    debug: bool = Field(default=False)
    host: str = Field(default="0.0.0.0")
    port: int = Field(default=8000)

    class Config:
        env_file = ".env"


settings = Settings()


@asynccontextmanager
async def lifespan(app: FastAPI) -> AsyncGenerator[None, None]:
    """Application lifecycle: startup/shutdown."""
    logger.info("Starting ML Inference Service...")

    try:
        with warnings.catch_warnings():
            warnings.filterwarnings("ignore", category=FutureWarning)

            # Replace ResNetInferenceService with your own implementation
            service = ResNetInferenceService(model_name="microsoft/resnet-18")
            await asyncio.to_thread(service.load_model)
            set_inference_service(service)

        logger.info("Startup completed successfully")

    except Exception as e:
        logger.error(f"Startup failed: {e}")
        raise

    yield

    logger.info("Shutting down...")


def create_app() -> FastAPI:
    """Create and configure FastAPI application."""
    app = FastAPI(
        title=settings.app_name,
        description="ML inference service for image classification",
        version=settings.app_version,
        debug=settings.debug,
        lifespan=lifespan
    )

    app.include_router(prediction.router)

    return app