Enable AvatarChatbot model cache for docker compose test. (#1604)

Signed-off-by: ZePan110 <ze.pan@intel.com>
Co-authored-by: chen, suyue <suyue.chen@intel.com>

AvatarChatbot/docker_compose/intel/cpu/xeon/compose.yaml

@@ -31,7 +31,7 @@ services:
     ports:
       - "3006:80"
     volumes:
-      - "./data:/data"
+      - "${MODEL_CACHE:-./data}:/data"
     shm_size: 1g
     environment:
       no_proxy: ${no_proxy}

AvatarChatbot/docker_compose/intel/hpu/gaudi/compose.yaml

@@ -43,7 +43,7 @@ services:
     ports:
       - "3006:80"
     volumes:
-      - "./data:/data"
+      - "${MODEL_CACHE:-./data}:/data"
     environment:
       no_proxy: ${no_proxy}
       http_proxy: ${http_proxy}