feat: add paddleocr-service directory to coolify branch

The docker-compose.coolify.yml references paddleocr-service/Dockerfile
but the directory only existed on main. Coolify clones the coolify branch
and needs the source files to build the container.

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

paddleocr-service/main.py

@@ -0,0 +1,115 @@
+"""PaddleOCR Remote Service — PP-OCRv5 Latin auf x86_64."""
+
+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("Import done. Loading PaddleOCR model...")
+        # Try multiple init strategies for different PaddleOCR versions
+        inits = [
+            # PaddleOCR 3.x (no show_log)
+            dict(lang="en", ocr_version="PP-OCRv5", use_angle_cls=True),
+            # PaddleOCR 3.x with show_log
+            dict(lang="en", ocr_version="PP-OCRv5", use_angle_cls=True, show_log=False),
+            # PaddleOCR 2.8+ (latin)
+            dict(lang="latin", use_angle_cls=True, show_log=False),
+            # PaddleOCR 2.8+ (en, no version)
+            dict(lang="en", use_angle_cls=True, show_log=False),
+        ]
+        for i, kwargs in enumerate(inits):
+            try:
+                _engine = PaddleOCR(**kwargs)
+                logger.info(f"PaddleOCR init succeeded with strategy {i}: {kwargs}")
+                break
+            except Exception as e:
+                logger.info(f"PaddleOCR init strategy {i} failed: {e}")
+        else:
+            raise RuntimeError("All PaddleOCR init strategies failed")
+        _ready = True
+        logger.info("PaddleOCR model loaded successfully — ready to serve")
+    except Exception as e:
+        logger.error(f"Failed to load PaddleOCR model: {e}")
+
+
+@app.on_event("startup")
+def startup_load_model():
+    """Start model loading in background so health check passes immediately."""
+    global _loading
+    _loading = True
+    thread = threading.Thread(target=_load_model, daemon=True)
+    thread.start()
+    logger.info("Model loading started in background thread")
+
+
+@app.get("/health")
+def health():
+    if _ready:
+        return {"status": "ok", "model": "PP-OCRv5-latin"}
+    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)
+
+    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.strip(),
+                "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],
+    }