41ff7671cd
Some checks failed
CI / go-lint (push) Has been skipped
CI / python-lint (push) Has been skipped
CI / nodejs-lint (push) Has been skipped
CI / test-go-school (push) Successful in 29s
CI / test-go-edu-search (push) Successful in 28s
CI / test-python-klausur (push) Failing after 2m5s
CI / test-python-agent-core (push) Successful in 16s
CI / test-nodejs-website (push) Successful in 18s
PaddleOCR 3.4.0 removed 'latin' language support. Use 'en' with explicit ocr_version='PP-OCRv5' instead, with fallback for older API. Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
81 lines
2.0 KiB
Python
81 lines
2.0 KiB
Python
"""PaddleOCR Remote Service — PP-OCRv5 Latin auf x86_64."""
|
|
|
|
import io
|
|
import os
|
|
|
|
import numpy as np
|
|
from fastapi import FastAPI, File, Header, HTTPException, UploadFile
|
|
from PIL import Image
|
|
|
|
app = FastAPI(title="PaddleOCR Service")
|
|
|
|
_engine = None
|
|
API_KEY = os.environ.get("PADDLEOCR_API_KEY", "")
|
|
|
|
|
|
def get_engine():
|
|
global _engine
|
|
if _engine is None:
|
|
from paddleocr import PaddleOCR
|
|
|
|
# PaddleOCR >= 3.x: use ocr_version param; fallback for older API
|
|
try:
|
|
_engine = PaddleOCR(
|
|
lang="en",
|
|
ocr_version="PP-OCRv5",
|
|
use_angle_cls=True,
|
|
show_log=False,
|
|
)
|
|
except (ValueError, TypeError):
|
|
_engine = PaddleOCR(
|
|
lang="latin",
|
|
use_angle_cls=True,
|
|
show_log=False,
|
|
)
|
|
return _engine
|
|
|
|
|
|
@app.get("/health")
|
|
def health():
|
|
return {"status": "ok", "model": "PP-OCRv5-latin"}
|
|
|
|
|
|
@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")
|
|
|
|
img_bytes = await file.read()
|
|
img = Image.open(io.BytesIO(img_bytes)).convert("RGB")
|
|
img_np = np.array(img)
|
|
|
|
engine = get_engine()
|
|
result = engine.ocr(img_np)
|
|
|
|
words = []
|
|
for line in result[0] or []:
|
|
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": text,
|
|
"left": int(x_min),
|
|
"top": int(y_min),
|
|
"width": int(x_max - x_min),
|
|
"height": int(y_max - y_min),
|
|
"conf": round(conf * 100, 1),
|
|
}
|
|
)
|
|
|
|
return {
|
|
"words": words,
|
|
"image_width": img_np.shape[1],
|
|
"image_height": img_np.shape[0],
|
|
}
|