Refactor lvm related examples (#1333)

VisualQnA/docker_compose/intel/cpu/xeon/README.md

@@ -41,7 +41,7 @@ First of all, you need to build Docker Images locally and install the python pac
 ```bash
 git clone https://github.com/opea-project/GenAIComps.git
 cd GenAIComps
-docker build --no-cache -t opea/lvm-tgi:latest --build-arg https_proxy=$https_proxy --build-arg http_proxy=$http_proxy -f comps/lvms/tgi-llava/Dockerfile .
+docker build --no-cache -t opea/lvm:latest --build-arg https_proxy=$https_proxy --build-arg http_proxy=$http_proxy -f comps/lvms/src/Dockerfile .
 docker build --no-cache -t opea/nginx:latest --build-arg https_proxy=$https_proxy --build-arg http_proxy=$http_proxy -f comps/third_parties/nginx/src/Dockerfile .
 ```
 
@@ -73,7 +73,7 @@ docker pull ghcr.io/huggingface/text-generation-inference:2.4.0-intel-cpu
 Then run the command `docker images`, you will have the following 5 Docker Images:
 
 1. `ghcr.io/huggingface/text-generation-inference:2.4.0-intel-cpu`
-2. `opea/lvm-tgi:latest`
+2. `opea/lvm:latest`
 3. `opea/visualqna:latest`
 4. `opea/visualqna-ui:latest`
 5. `opea/nginx`

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

@@ -23,9 +23,9 @@ services:
       timeout: 10s
       retries: 60
     command: --model-id ${LVM_MODEL_ID} --max-input-length 4096 --max-total-tokens 8192 --cuda-graphs 0
-  lvm-tgi:
-    image: ${REGISTRY:-opea}/lvm-tgi:${TAG:-latest}
-    container_name: lvm-tgi-xeon-server
+  lvm:
+    image: ${REGISTRY:-opea}/lvm:${TAG:-latest}
+    container_name: lvm-xeon-server
     depends_on:
       llava-tgi-service:
         condition: service_healthy
@@ -37,6 +37,7 @@ services:
       http_proxy: ${http_proxy}
       https_proxy: ${https_proxy}
       LVM_ENDPOINT: ${LVM_ENDPOINT}
+      LVM_COMPONENT_NAME: "OPEA_TGI_LLAVA_LVM"
       HF_HUB_DISABLE_PROGRESS_BARS: 1
       HF_HUB_ENABLE_HF_TRANSFER: 0
     restart: unless-stopped
@@ -45,7 +46,7 @@ services:
     container_name: visualqna-xeon-backend-server
     depends_on:
       - llava-tgi-service
-      - lvm-tgi
+      - lvm
     ports:
       - "8888:8888"
     environment:

VisualQnA/docker_compose/intel/hpu/gaudi/README.md

@@ -11,7 +11,7 @@ First of all, you need to build Docker Images locally. This step can be ignored
 ```bash
 git clone https://github.com/opea-project/GenAIComps.git
 cd GenAIComps
-docker build --no-cache -t opea/lvm-tgi:latest --build-arg https_proxy=$https_proxy --build-arg http_proxy=$http_proxy -f comps/lvms/tgi-llava/Dockerfile .
+docker build --no-cache -t opea/lvm:latest --build-arg https_proxy=$https_proxy --build-arg http_proxy=$http_proxy -f comps/lvms/src/Dockerfile .
 docker build --no-cache -t opea/nginx:latest --build-arg https_proxy=$https_proxy --build-arg http_proxy=$http_proxy -f comps/third_parties/nginx/src/Dockerfile .
 ```
 
@@ -44,7 +44,7 @@ docker build --no-cache -t opea/visualqna-ui:latest --build-arg https_proxy=$htt
 Then run the command `docker images`, you will have the following 5 Docker Images:
 
 1. `ghcr.io/huggingface/tgi-gaudi:2.0.6`
-2. `opea/lvm-tgi:latest`
+2. `opea/lvm:latest`
 3. `opea/visualqna:latest`
 4. `opea/visualqna-ui:latest`
 5. `opea/nginx`

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

@@ -27,9 +27,9 @@ services:
       - SYS_NICE
     ipc: host
     command: --model-id ${LVM_MODEL_ID} --max-input-length 4096 --max-total-tokens 8192
-  lvm-tgi:
-    image: ${REGISTRY:-opea}/lvm-tgi:${TAG:-latest}
-    container_name: lvm-tgi-gaudi-server
+  lvm:
+    image: ${REGISTRY:-opea}/lvm:${TAG:-latest}
+    container_name: lvm-gaudi-server
     depends_on:
       - llava-tgi-service
     ports:
@@ -40,6 +40,7 @@ services:
       http_proxy: ${http_proxy}
       https_proxy: ${https_proxy}
       LVM_ENDPOINT: ${LVM_ENDPOINT}
+      LVM_COMPONENT_NAME: "OPEA_TGI_LLAVA_LVM"
       HF_HUB_DISABLE_PROGRESS_BARS: 1
       HF_HUB_ENABLE_HF_TRANSFER: 0
     restart: unless-stopped
@@ -48,7 +49,7 @@ services:
     container_name: visualqna-gaudi-backend-server
     depends_on:
       - llava-tgi-service
-      - lvm-tgi
+      - lvm
     ports:
       - "8888:8888"
     environment: