96f94475f6
All checks were successful
CI / go-lint (push) Has been skipped
CI / test-go-consent (push) Successful in 33s
CI / test-python-voice (push) Successful in 31s
CI / test-bqas (push) Successful in 34s
CI / python-lint (push) Has been skipped
CI / nodejs-lint (push) Has been skipped
CI / Deploy (push) Successful in 2s
PaddlePaddle 3.x + PP-OCRv5 requires >6GB RAM and has oneDNN compatibility issues on CPU. PaddleOCR 2.x with PP-OCRv4 works reliably with ~2-3GB RAM and has no MKLDNN issues. - Pin paddlepaddle<3.0.0 and paddleocr<3.0.0 - Simplify main.py — single init strategy, direct 2.x result format - Re-enable warmup (fits in memory with 2.x) Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
111 lines
3.1 KiB
Python
111 lines
3.1 KiB
Python
"""PaddleOCR Remote Service — PP-OCRv4 on x86_64 (CPU)."""
|
|
|
|
import io
|
|
import logging
|
|
import os
|
|
import threading
|
|
|
|
import numpy as np
|
|
from fastapi import FastAPI, File, Header, HTTPException, UploadFile
|
|
from PIL import Image
|
|
|
|
logging.basicConfig(level=logging.INFO)
|
|
logger = logging.getLogger(__name__)
|
|
|
|
app = FastAPI(title="PaddleOCR Service")
|
|
|
|
_engine = None
|
|
_ready = False
|
|
_loading = False
|
|
API_KEY = os.environ.get("PADDLEOCR_API_KEY", "")
|
|
|
|
|
|
def _load_model():
|
|
"""Load PaddleOCR model in background thread."""
|
|
global _engine, _ready
|
|
try:
|
|
logger.info("Importing paddleocr...")
|
|
from paddleocr import PaddleOCR
|
|
|
|
logger.info("Loading PaddleOCR model (PP-OCRv4, lang=en)...")
|
|
_engine = PaddleOCR(
|
|
lang="en",
|
|
use_angle_cls=True,
|
|
show_log=False,
|
|
enable_mkldnn=False,
|
|
use_gpu=False,
|
|
)
|
|
logger.info("PaddleOCR model loaded — running warmup...")
|
|
# Warmup with tiny image to trigger any lazy init
|
|
dummy = np.ones((30, 100, 3), dtype=np.uint8) * 255
|
|
_engine.ocr(dummy)
|
|
_ready = True
|
|
logger.info("PaddleOCR ready to serve")
|
|
except Exception as e:
|
|
logger.error(f"Failed to load PaddleOCR: {e}", exc_info=True)
|
|
|
|
|
|
@app.on_event("startup")
|
|
def startup_load_model():
|
|
"""Start model loading in background so health check passes immediately."""
|
|
global _loading
|
|
_loading = True
|
|
threading.Thread(target=_load_model, daemon=True).start()
|
|
logger.info("Model loading started in background thread")
|
|
|
|
|
|
@app.get("/health")
|
|
def health():
|
|
if _ready:
|
|
return {"status": "ok", "model": "PP-OCRv4"}
|
|
if _loading:
|
|
return {"status": "loading"}
|
|
return {"status": "error"}
|
|
|
|
|
|
@app.post("/ocr")
|
|
async def ocr(
|
|
file: UploadFile = File(...),
|
|
x_api_key: str = Header(default=""),
|
|
):
|
|
if API_KEY and x_api_key != API_KEY:
|
|
raise HTTPException(status_code=401, detail="Invalid API key")
|
|
|
|
if not _ready:
|
|
raise HTTPException(status_code=503, detail="Model still loading")
|
|
|
|
img_bytes = await file.read()
|
|
img = Image.open(io.BytesIO(img_bytes)).convert("RGB")
|
|
img_np = np.array(img)
|
|
|
|
try:
|
|
result = _engine.ocr(img_np)
|
|
except Exception as e:
|
|
logger.error(f"OCR failed: {e}", exc_info=True)
|
|
raise HTTPException(status_code=500, detail=f"OCR failed: {e}")
|
|
|
|
if not result or not result[0]:
|
|
return {"words": [], "image_width": img_np.shape[1], "image_height": img_np.shape[0]}
|
|
|
|
words = []
|
|
for line in result[0]:
|
|
box, (text, conf) = line[0], line[1]
|
|
x_min = min(p[0] for p in box)
|
|
y_min = min(p[1] for p in box)
|
|
x_max = max(p[0] for p in box)
|
|
y_max = max(p[1] for p in box)
|
|
words.append({
|
|
"text": str(text).strip(),
|
|
"left": int(x_min),
|
|
"top": int(y_min),
|
|
"width": int(x_max - x_min),
|
|
"height": int(y_max - y_min),
|
|
"conf": round(float(conf) * 100, 1),
|
|
})
|
|
|
|
return {
|
|
"words": words,
|
|
"image_width": img_np.shape[1],
|
|
"image_height": img_np.shape[0],
|
|
}
|