#!/usr/bin/env python3
"""Minimal local web app for v802: upload a quiz image, get the answer.
python serve_v802.py --bundle ../artifacts/models/v802/classifier.joblib \
--model ../../models/dinov3-vitl16-pretrain-lvd1689m [--port 8802]
Binds to 127.0.0.1 only. Uses the standard library server; one prediction at a time.
"""
from __future__ import annotations
import argparse
import io
import json
import threading
import time
from http.server import BaseHTTPRequestHandler, ThreadingHTTPServer
from pathlib import Path
import torch
from PIL import Image
from predict_v802 import V802Predictor
MAX_BYTES = 20 * 1024 * 1024
PAGE = """
v802 Pony Quiz Solver
v802 Pony Quiz Solver
퀴즈 이미지를 클릭해 선택하거나, 끌어다 놓거나, 붙여넣기(Ctrl+V) 하세요. 한 장에 10–20초 걸립니다.
이미지 선택
"""
def make_handler(predictor: V802Predictor, lock: threading.Lock):
class Handler(BaseHTTPRequestHandler):
def _send(self, status: int, body: bytes, content_type: str) -> None:
self.send_response(status)
self.send_header("Content-Type", content_type)
self.send_header("Content-Length", str(len(body)))
self.end_headers()
self.wfile.write(body)
def _json(self, status: int, payload: dict) -> None:
self._send(status, json.dumps(payload, ensure_ascii=False).encode(), "application/json; charset=utf-8")
def do_GET(self) -> None:
if self.path in ("/", "/index.html"):
self._send(200, PAGE.encode(), "text/html; charset=utf-8")
else:
self._json(404, {"error": "not found"})
def do_POST(self) -> None:
if self.path.rstrip("/").split("/")[-1] != "predict":
return self._json(404, {"error": "not found"})
length = int(self.headers.get("Content-Length") or 0)
if not 0 < length <= MAX_BYTES:
return self._json(413, {"error": f"image must be 1 byte to {MAX_BYTES // 2**20} MiB"})
try:
image = Image.open(io.BytesIO(self.rfile.read(length)))
image.load()
except Exception:
return self._json(400, {"error": "could not read the image"})
started = time.time()
with lock:
result = predictor.predict([image])[0]
self._json(200, {**result, "seconds": time.time() - started})
return Handler
def main() -> None:
parser = argparse.ArgumentParser(description=__doc__, formatter_class=argparse.RawDescriptionHelpFormatter)
parser.add_argument("--bundle", type=Path, required=True)
parser.add_argument("--model", type=Path, required=True)
parser.add_argument("--port", type=int, default=8802)
parser.add_argument("--threads", type=int, default=4)
parser.add_argument("--fp32", action="store_true")
args = parser.parse_args()
torch.set_num_threads(args.threads)
predictor = V802Predictor(args.bundle, args.model, bf16=not args.fp32)
server = ThreadingHTTPServer(("127.0.0.1", args.port), make_handler(predictor, threading.Lock()))
print(f"v802 app on http://127.0.0.1:{args.port}", flush=True)
server.serve_forever()
if __name__ == "__main__":
main()