From 7cdb53051ff4c544cb55fa59a7aa00b54a4e63e0 Mon Sep 17 00:00:00 2001
From: Benjamin Admin <benjaminadmin@MacBookPro.fritz.box>
Date: Thu, 12 Mar 2026 10:20:41 +0100
Subject: [PATCH] feat: PaddleOCR Service (PP-OCRv5 Latin auf x86_64)

Microservice fuer PaddleOCR auf Hetzner. FastAPI mit /ocr und /health
Endpoints, API-Key Auth, 4GB Memory Limit, Modell-Cache Volume.

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
---
 docker-compose.coolify.yml         | 31 ++++++++++++-
 paddleocr-service/Dockerfile       | 16 +++++++
 paddleocr-service/main.py          | 71 ++++++++++++++++++++++++++++++
 paddleocr-service/requirements.txt |  7 +++
 4 files changed, 124 insertions(+), 1 deletion(-)
 create mode 100644 paddleocr-service/Dockerfile
 create mode 100644 paddleocr-service/main.py
 create mode 100644 paddleocr-service/requirements.txt

diff --git a/docker-compose.coolify.yml b/docker-compose.coolify.yml
index 32cc969..9c9afc7 100644
--- a/docker-compose.coolify.yml
+++ b/docker-compose.coolify.yml
@@ -15,6 +15,7 @@ networks:
 volumes:
   valkey_data:
   embedding_models:
+  paddleocr_models:
 
 services:
 
@@ -141,6 +142,34 @@ services:
     networks:
       - breakpilot-network
 
+  # =========================================================
+  # OCR SERVICE (PaddleOCR PP-OCRv5 Latin)
+  # =========================================================
+  paddleocr-service:
+    build:
+      context: ./paddleocr-service
+      dockerfile: Dockerfile
+    container_name: bp-core-paddleocr
+    expose:
+      - "8095"
+    environment:
+      PADDLEOCR_API_KEY: ${PADDLEOCR_API_KEY:-}
+    volumes:
+      - paddleocr_models:/root/.paddleocr
+    deploy:
+      resources:
+        limits:
+          memory: 4G
+    healthcheck:
+      test: ["CMD", "curl", "-f", "http://127.0.0.1:8095/health"]
+      interval: 30s
+      timeout: 10s
+      start_period: 120s
+      retries: 3
+    restart: unless-stopped
+    networks:
+      - breakpilot-network
+
   # =========================================================
   # HEALTH AGGREGATOR
   # =========================================================
@@ -153,7 +182,7 @@ services:
       - "8099"
     environment:
       PORT: 8099
-      CHECK_SERVICES: "valkey:6379,consent-service:8081,rag-service:8097,embedding-service:8087"
+      CHECK_SERVICES: "valkey:6379,consent-service:8081,rag-service:8097,embedding-service:8087,paddleocr-service:8095"
     healthcheck:
       test: ["CMD", "curl", "-f", "http://127.0.0.1:8099/health"]
       interval: 30s
diff --git a/paddleocr-service/Dockerfile b/paddleocr-service/Dockerfile
new file mode 100644
index 0000000..e10f22c
--- /dev/null
+++ b/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"]
diff --git a/paddleocr-service/main.py b/paddleocr-service/main.py
new file mode 100644
index 0000000..1195c5e
--- /dev/null
+++ b/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],
+    }
diff --git a/paddleocr-service/requirements.txt b/paddleocr-service/requirements.txt
new file mode 100644
index 0000000..47f8951
--- /dev/null
+++ b/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