feat: PaddleOCR Remote-Engine (PP-OCRv5 Latin auf Hetzner x86_64)

PaddleOCR als neue engine=paddle Option in der OCR-Pipeline.
Microservice auf Hetzner (paddleocr-service/), async HTTP-Client
(paddleocr_remote.py), Frontend-Dropdown, automatisch words_first.

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

paddleocr-service/Dockerfile

@@ -0,0 +1,16 @@
+FROM python:3.11-slim
+WORKDIR /app
+
+RUN apt-get update && apt-get install -y --no-install-recommends \
+    libgl1-mesa-glx libglib2.0-0 curl \
+    && rm -rf /var/lib/apt/lists/*
+
+COPY requirements.txt .
+RUN pip install --no-cache-dir -r requirements.txt
+
+COPY . .
+
+EXPOSE 8095
+HEALTHCHECK --interval=30s --timeout=10s --start-period=120s --retries=3 \
+    CMD curl -f http://127.0.0.1:8095/health || exit 1
+CMD ["uvicorn", "main:app", "--host", "0.0.0.0", "--port", "8095"]

paddleocr-service/main.py

@@ -0,0 +1,71 @@
+"""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
+
+        _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],
+    }

paddleocr-service/requirements.txt

@@ -0,0 +1,7 @@
+paddlepaddle>=3.0.0
+paddleocr>=2.9.0
+fastapi>=0.110.0
+uvicorn>=0.25.0
+python-multipart>=0.0.6
+Pillow>=10.0.0
+numpy>=1.24.0