[ChatQnA] Fix the service connection issue on GPU and modify the emb backend (#1059)

Signed-off-by: Wang, Kai Lawrence <kai.lawrence.wang@intel.com>

Author: wangkl2

ChatQnA/docker_compose/nvidia/gpu/README.md

@@ -97,7 +97,7 @@ To construct the Mega Service, we utilize the [GenAIComps](https://github.com/op
 git clone https://github.com/opea-project/GenAIExamples.git
 cd GenAIExamples/ChatQnA
 docker build --no-cache -t opea/chatqna:latest --build-arg https_proxy=$https_proxy --build-arg http_proxy=$http_proxy -f Dockerfile .
-cd ../../..
+cd ../..
 ```
 
 ### 5. Build UI Docker Image
@@ -107,7 +107,7 @@ Construct the frontend Docker image using the command below:
 ```bash
 cd GenAIExamples/ChatQnA/ui
 docker build --no-cache -t opea/chatqna-ui:latest --build-arg https_proxy=$https_proxy --build-arg http_proxy=$http_proxy -f ./docker/Dockerfile .
-cd ../../../..
+cd ../../../
 ```
 
 ### 6. Build React UI Docker Image (Optional)
@@ -117,7 +117,7 @@ Construct the frontend Docker image using the command below:
 ```bash
 cd GenAIExamples/ChatQnA/ui
 docker build --no-cache -t opea/chatqna-react-ui:latest --build-arg https_proxy=$https_proxy --build-arg http_proxy=$http_proxy -f ./docker/Dockerfile.react .
-cd ../../../..
+cd ../../..
 ```
 
 ### 7. Build Nginx Docker Image

ChatQnA/docker_compose/nvidia/gpu/compose.yaml

@@ -20,10 +20,10 @@ services:
       no_proxy: ${no_proxy}
       http_proxy: ${http_proxy}
       https_proxy: ${https_proxy}
-      REDIS_URL: ${REDIS_URL}
-      REDIS_HOST: ${REDIS_HOST}
+      REDIS_URL: redis://redis-vector-db:6379
+      REDIS_HOST: redis-vector-db
       INDEX_NAME: ${INDEX_NAME}
-      TEI_ENDPOINT: ${TEI_EMBEDDING_ENDPOINT}
+      TEI_ENDPOINT: http://tei-embedding-service:80
       HUGGINGFACEHUB_API_TOKEN: ${HUGGINGFACEHUB_API_TOKEN}
   tei-embedding-service:
     image: ghcr.io/huggingface/text-embeddings-inference:cpu-1.5
@@ -39,13 +39,6 @@ services:
       http_proxy: ${http_proxy}
       https_proxy: ${https_proxy}
     command: --model-id ${EMBEDDING_MODEL_ID} --auto-truncate
-    deploy:
-      resources:
-        reservations:
-          devices:
-            - driver: nvidia
-              count: 1
-              capabilities: [gpu]
   retriever:
     image: ${REGISTRY:-opea}/retriever-redis:${TAG:-latest}
     container_name: retriever-redis-server
@@ -58,12 +51,13 @@ services:
       no_proxy: ${no_proxy}
       http_proxy: ${http_proxy}
       https_proxy: ${https_proxy}
-      REDIS_URL: ${REDIS_URL}
+      REDIS_URL: redis://redis-vector-db:6379
+      REDIS_HOST: redis-vector-db
       INDEX_NAME: ${INDEX_NAME}
       TEI_EMBEDDING_ENDPOINT: ${TEI_EMBEDDING_ENDPOINT}
     restart: unless-stopped
   tei-reranking-service:
-    image: ghcr.io/huggingface/text-embeddings-inference:cpu-1.5
+    image: ghcr.io/huggingface/text-embeddings-inference:1.5
     container_name: tei-reranking-server
     ports:
       - "8808:80"
@@ -123,11 +117,14 @@ services:
       - no_proxy=${no_proxy}
       - https_proxy=${https_proxy}
       - http_proxy=${http_proxy}
-      - MEGA_SERVICE_HOST_IP=${MEGA_SERVICE_HOST_IP}
-      - EMBEDDING_SERVICE_HOST_IP=${EMBEDDING_SERVICE_HOST_IP}
-      - RETRIEVER_SERVICE_HOST_IP=${RETRIEVER_SERVICE_HOST_IP}
-      - RERANK_SERVICE_HOST_IP=${RERANK_SERVICE_HOST_IP}
-      - LLM_SERVICE_HOST_IP=${LLM_SERVICE_HOST_IP}
+      - MEGA_SERVICE_HOST_IP=chaqna-backend-server
+      - EMBEDDING_SERVER_HOST_IP=tei-embedding-service
+      - EMBEDDING_SERVER_PORT=${EMBEDDING_SERVER_PORT:-80}
+      - RETRIEVER_SERVICE_HOST_IP=retriever
+      - RERANK_SERVER_HOST_IP=tei-reranking-service
+      - RERANK_SERVER_PORT=${RERANK_SERVER_PORT:-80}
+      - LLM_SERVER_HOST_IP=tgi-service
+      - LLM_SERVER_PORT=${LLM_SERVER_PORT:-80}
     ipc: host
     restart: always
   chaqna-ui-server: