feat(ocr): Surya OCR 마이크로서비스 추가

GPU 가속 OCR (Surya, Apache 2.0) 별도 컨테이너로 추가.
스캔 PDF/이미지 파일의 텍스트 추출 지원.

- services/ocr: Dockerfile + server.py + requirements.txt
- /health (liveness) + /ready (readiness, CUDA+모델 상태)
- /ocr: 페이지 단위 스트리밍 처리 (메모리 피크 억제)
- docker-compose: ocr-service + GPU reservation + ocr_models 볼륨

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

docker-compose.yml

@@ -32,6 +32,28 @@ services:
       retries: 3
     restart: unless-stopped
 
+  ocr-service:
+    build: ./services/ocr
+    expose:
+      - "3200"
+    volumes:
+      - ${NAS_NFS_PATH:-/mnt/nas/Document_Server}:/documents:ro
+      - ocr_models:/root/.cache
+    deploy:
+      resources:
+        reservations:
+          devices:
+            - driver: nvidia
+              count: 1
+              capabilities: [gpu]
+    healthcheck:
+      test: ["CMD", "python", "-c", "import urllib.request; urllib.request.urlopen('http://localhost:3200/health')"]
+      interval: 30s
+      timeout: 10s
+      retries: 3
+      start_period: 180s
+    restart: unless-stopped
+
   ollama:
     image: ollama/ollama
     volumes:
@@ -102,6 +124,7 @@ services:
     environment:
       - DATABASE_URL=postgresql+asyncpg://pkm:${POSTGRES_PASSWORD}@postgres:5432/pkm
       - KORDOC_ENDPOINT=http://kordoc-service:3100
+      - OCR_ENDPOINT=http://ocr-service:3200
     restart: unless-stopped
 
   frontend:
@@ -129,3 +152,4 @@ volumes:
   caddy_data:
   ollama_data:
   reranker_cache:
+  ocr_models: