feat(deploy): Phase 1.3 reranker (TEI bge-reranker-v2-m3) 서비스 추가

docker-compose.yml에 reranker 서비스 추가:
- image: ghcr.io/huggingface/text-embeddings-inference:1.5
- MODEL_ID=BAAI/bge-reranker-v2-m3
- MAX_BATCH_TOKENS=8192, MAX_CONCURRENT_REQUESTS=4
- GPU 1개 할당 (RTX 4070 Ti Super, CUDA 13.0)
- expose 80만 (host 노출 X, internal network 전용)
- reranker_cache volume으로 모델 영속화
- fastapi가 depends_on 안 함 → 단독 시작 가능, reranker 없어도 fastapi 동작
  (rerank_service가 RRF fallback)

다음 단계:
- GPU에서 docker pull로 호환성 확인
- docker compose up -d reranker → warmup
- config.yaml의 rerank.endpoint를 http://reranker:80/rerank로 갱신 (GPU 직접)
- fastapi rebuild + 평가셋 측정 (rerank=true)

docker-compose.yml

@@ -45,6 +45,28 @@ services:
       - "127.0.0.1:11434:11434"
     restart: unless-stopped
 
+  # Phase 1.3: bge-reranker-v2-m3 (TEI) — internal only, fastapi에서 reranker:80으로 호출
+  # fastapi가 depends_on 안 함 → 단독 시작 가능, 없어도 fastapi 동작 (rerank=false fallback)
+  reranker:
+    image: ghcr.io/huggingface/text-embeddings-inference:1.5
+    container_name: hyungi_document_server-reranker-1
+    expose:
+      - "80"
+    environment:
+      - MODEL_ID=BAAI/bge-reranker-v2-m3
+      - MAX_BATCH_TOKENS=8192
+      - MAX_CONCURRENT_REQUESTS=4
+    volumes:
+      - reranker_cache:/data
+    deploy:
+      resources:
+        reservations:
+          devices:
+            - driver: nvidia
+              count: 1
+              capabilities: [gpu]
+    restart: unless-stopped
+
   ai-gateway:
     build: ./gpu-server/services/ai-gateway
     ports:
@@ -103,3 +125,4 @@ volumes:
   pgdata:
   caddy_data:
   ollama_data:
+  reranker_cache: