chore: update Docker and compose files for PaddleOCR engine (refs #119)

- Replace libtesseract-dev with libgomp1 (OpenMP for PaddlePaddle)
- Pre-download PP-OCRv4 models during Docker build
- Add OCR engine env vars to all compose files (base, staging, prod)
- Add optional Google Vision secret mount (commented, enable on demand)
- Create google-vision-key.json.example placeholder

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

docker-compose.prod.yml

@@ -38,13 +38,17 @@ services:
       STRIPE_ENTERPRISE_MONTHLY_PRICE_ID: prod_Toj8xGEui9jl6j
       STRIPE_ENTERPRISE_YEARLY_PRICE_ID: prod_Toj9A7A773xrdn
 
-  # OCR - Production log level
+  # OCR - Production log level + engine config
   mvp-ocr:
     environment:
       LOG_LEVEL: error
       REDIS_HOST: mvp-redis
       REDIS_PORT: 6379
       REDIS_DB: 1
+      OCR_PRIMARY_ENGINE: paddleocr
+      OCR_FALLBACK_ENGINE: ${OCR_FALLBACK_ENGINE:-none}
+      OCR_FALLBACK_THRESHOLD: ${OCR_FALLBACK_THRESHOLD:-0.6}
+      GOOGLE_VISION_KEY_PATH: /run/secrets/google-vision-key.json
 
   # PostgreSQL - Remove dev ports, production log level
   mvp-postgres:

docker-compose.staging.yml

@@ -63,6 +63,15 @@ services:
   mvp-ocr:
     image: ${OCR_IMAGE:-git.motovaultpro.com/egullickson/ocr:latest}
     container_name: mvp-ocr-staging
+    environment:
+      LOG_LEVEL: debug
+      REDIS_HOST: mvp-redis
+      REDIS_PORT: 6379
+      REDIS_DB: 1
+      OCR_PRIMARY_ENGINE: paddleocr
+      OCR_FALLBACK_ENGINE: ${OCR_FALLBACK_ENGINE:-none}
+      OCR_FALLBACK_THRESHOLD: ${OCR_FALLBACK_THRESHOLD:-0.6}
+      GOOGLE_VISION_KEY_PATH: /run/secrets/google-vision-key.json
 
   # ========================================
   # PostgreSQL (Staging - Separate Database)

docker-compose.yml

@@ -193,8 +193,16 @@ services:
       REDIS_HOST: mvp-redis
       REDIS_PORT: 6379
       REDIS_DB: 1
+      # OCR engine configuration (PaddleOCR primary, cloud fallback optional)
+      OCR_PRIMARY_ENGINE: paddleocr
+      OCR_FALLBACK_ENGINE: ${OCR_FALLBACK_ENGINE:-none}
+      OCR_FALLBACK_THRESHOLD: ${OCR_FALLBACK_THRESHOLD:-0.6}
+      GOOGLE_VISION_KEY_PATH: /run/secrets/google-vision-key.json
     volumes:
       - /tmp/vin-debug:/tmp/vin-debug
+      # Optional: Uncomment to enable Google Vision cloud fallback.
+      # Requires: secrets/app/google-vision-key.json and OCR_FALLBACK_ENGINE=google_vision
+      # - ./secrets/app/google-vision-key.json:/run/secrets/google-vision-key.json:ro
     networks:
       - backend
       - database

ocr/Dockerfile

@@ -1,5 +1,9 @@
 # Production Dockerfile for MotoVaultPro OCR Service
 # Uses mirrored base images from Gitea Package Registry
+#
+# Primary engine: PaddleOCR PP-OCRv4 (models baked into image)
+# Backward compat: Tesseract 5.x (optional, via TesseractEngine)
+# Cloud fallback: Google Vision (optional, requires API key at runtime)
 
 # Build argument for registry (defaults to Gitea mirrors, falls back to Docker Hub)
 ARG REGISTRY_MIRRORS=git.motovaultpro.com/egullickson/mirrors
@@ -7,10 +11,16 @@ ARG REGISTRY_MIRRORS=git.motovaultpro.com/egullickson/mirrors
 FROM ${REGISTRY_MIRRORS}/python:3.13-slim
 
 # System dependencies
+# - tesseract-ocr/eng: Backward-compatible OCR engine (used by TesseractEngine)
+# - libgomp1: OpenMP runtime required by PaddlePaddle
+# - libheif1/libheif-dev: HEIF image support (iPhone photos)
+# - libglib2.0-0: GLib shared library (OpenCV dependency)
+# - libmagic1: File type detection
+# - curl: Health check endpoint
 RUN apt-get update && apt-get install -y --no-install-recommends \
     tesseract-ocr \
     tesseract-ocr-eng \
-    libtesseract-dev \
+    libgomp1 \
     libheif1 \
     libheif-dev \
     libglib2.0-0 \
@@ -23,6 +33,12 @@ WORKDIR /app
 COPY requirements.txt .
 RUN pip install --no-cache-dir -r requirements.txt
 
+# Pre-download PaddleOCR PP-OCRv4 models during build (not at runtime).
+# Models are baked into the image so container starts are fast and
+# no network access is needed at runtime for model download.
+RUN python -c "from paddleocr import PaddleOCR; PaddleOCR(use_angle_cls=True, lang='en', use_gpu=False, show_log=False)" \
+    && echo "PaddleOCR PP-OCRv4 models downloaded and verified"
+
 COPY . .
 
 EXPOSE 8000

secrets/app/google-vision-key.json.example

@@ -0,0 +1,18 @@
+{
+  "_comment": "Google Vision API service account key for OCR cloud fallback",
+  "_instructions": [
+    "1. Create a Google Cloud service account with Vision API access",
+    "2. Download the JSON key file",
+    "3. Save it as secrets/app/google-vision-key.json (gitignored)",
+    "4. Uncomment the volume mount in docker-compose.yml",
+    "5. Set OCR_FALLBACK_ENGINE=google_vision"
+  ],
+  "type": "service_account",
+  "project_id": "your-project-id",
+  "private_key_id": "",
+  "private_key": "",
+  "client_email": "your-sa@your-project-id.iam.gserviceaccount.com",
+  "client_id": "",
+  "auth_uri": "https://accounts.google.com/o/oauth2/auth",
+  "token_uri": "https://oauth2.googleapis.com/token"
+}