update compose.yaml

Signed-off-by: Mustafa <[email protected]>

Author: MSCetin37

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

@@ -2,13 +2,16 @@
 # SPDX-License-Identifier: Apache-2.0
 
 services:
+
   tgi-service:
     image: ghcr.io/huggingface/text-generation-inference:2.4.0-intel-cpu
-    container_name: tgi-service
+    container_name: tgi-server
+    # profiles:
+    #   - codegen-xeon-tgi
     ports:
       - "8028:80"
     volumes:
-      - "./data:/data"
+      - "${MODEL_CACHE:-./data}:/data"
     shm_size: 1g
     environment:
       no_proxy: ${no_proxy}
@@ -22,46 +25,82 @@ services:
       timeout: 10s
       retries: 100
     command: --model-id ${LLM_MODEL_ID} --cuda-graphs 0
+
+  vllm-service:
+    image: ${REGISTRY:-opea}/vllm:${TAG:-latest}
+    container_name: vllm-server
+    profiles:
+      - codegen-xeon-vllm
+    ports:
+      - "8028:80"
+    volumes:
+      - "${MODEL_CACHE:-./data}:/root/.cache/huggingface/hub"
+    shm_size: 1g
+    environment:
+      no_proxy: ${no_proxy}
+      http_proxy: ${http_proxy}
+      https_proxy: ${https_proxy}
+      HF_TOKEN: ${HUGGINGFACEHUB_API_TOKEN}
+      host_ip: ${host_ip}
+    healthcheck:
+      test: ["CMD-SHELL", "curl -f http://$host_ip:8028/health || exit 1"]
+      interval: 10s
+      timeout: 10s
+      retries: 100
+    command: --model ${LLM_MODEL_ID} --host 0.0.0.0 --port 80
 
-  llm:
+  llm-base:
     image: ${REGISTRY:-opea}/llm-textgen:${TAG:-latest}
     container_name: llm-textgen-server
-    depends_on:
-      tgi-service:
-        condition: service_healthy
-    ports:
-      - "9000:9000"
-    ipc: host
     environment:
       no_proxy: ${no_proxy}
       http_proxy: ${http_proxy}
       https_proxy: ${https_proxy}
-      LLM_ENDPOINT: ${TGI_LLM_ENDPOINT}
+      LLM_ENDPOINT: ${LLM_ENDPOINT}
       LLM_MODEL_ID: ${LLM_MODEL_ID}
       HUGGINGFACEHUB_API_TOKEN: ${HUGGINGFACEHUB_API_TOKEN}
     restart: unless-stopped
-  
+
+  llm-tgi-service:
+    extends: llm-base
+    container_name: llm-codegen-tgi-server
+    # profiles:
+    #   - codegen-xeon-tgi
+    ports:
+      - "9000:9000"
+    ipc: host
+    depends_on:
+      tgi-service:
+        condition: service_healthy
+  llm-vllm-service:
+    extends: llm-base
+    container_name: llm-codegen-vllm-server
+    profiles:
+      - codegen-xeon-vllm
+    ports:
+      - "9000:9000"
+    ipc: host
+    depends_on:
+      vllm-service:
+        condition: service_healthy
 
   codegen-xeon-backend-server:
     image: ${REGISTRY:-opea}/codegen:${TAG:-latest}
     container_name: codegen-xeon-backend-server
     depends_on:
-      - llm
+      - llm-base
     ports:
       - "7778:7778"
     environment:
       - no_proxy=${no_proxy}
       - https_proxy=${https_proxy}
       - http_proxy=${http_proxy}
-      - MEGA_SERVICE_HOST_IP=${host_ip} #${MEGA_SERVICE_HOST_IP}
-      - LLM_SERVICE_HOST_IP=${host_ip} #${LLM_SERVICE_HOST_IP}
-      # - RETRIEVAL_SERVICE_HOST_IP=${REDIS_RETRIEVER_PORT}
-      - RETRIEVAL_SERVICE_HOST_IP=${host_ip} #${RETRIEVAL_SERVICE_HOST_IP}
+      - MEGA_SERVICE_HOST_IP=${MEGA_SERVICE_HOST_IP}
+      - LLM_SERVICE_HOST_IP=${LLM_SERVICE_HOST_IP}
+      - RETRIEVAL_SERVICE_HOST_IP=${RETRIEVAL_SERVICE_HOST_IP}
       - REDIS_RETRIEVER_PORT=${REDIS_RETRIEVER_PORT}
-      # - MM_EMBEDDING_SERVICE_HOST_IP=${MM_EMBEDDING_PORT_MICROSERVICE}
-      - TEI_EMBEDDING_HOST_IP=${host_ip} #${TEI_EMBEDDING_HOST_IP}
+      - TEI_EMBEDDING_HOST_IP=${TEI_EMBEDDING_HOST_IP}
       - EMBEDDER_PORT=${EMBEDDER_PORT}
-
     ipc: host
     restart: always
   codegen-xeon-ui-server:
@@ -85,7 +124,7 @@ services:
     ports:
       - "${REDIS_DB_PORT}:${REDIS_DB_PORT}"
       - "${REDIS_INSIGHTS_PORT}:${REDIS_INSIGHTS_PORT}"
-  
+
   dataprep-redis-server:
     image: ${REGISTRY:-opea}/dataprep:${TAG:-latest}
     container_name: dataprep-redis-server
@@ -165,6 +204,8 @@ services:
       RETRIEVER_COMPONENT_NAME: ${RETRIEVER_COMPONENT_NAME:-OPEA_RETRIEVER_REDIS}
     restart: unless-stopped
 
+
+
 networks:
   default:
-    driver: bridge
+    driver: bridge