diff --git a/ChatQnA/docker_compose/intel/cpu/xeon/README.md b/ChatQnA/docker_compose/intel/cpu/xeon/README.md
index 5eca0d284..d3540bcb8 100644
--- a/ChatQnA/docker_compose/intel/cpu/xeon/README.md
+++ b/ChatQnA/docker_compose/intel/cpu/xeon/README.md
@@ -216,7 +216,14 @@ cd GenAIExamples/ChatQnA/ui
 docker build --no-cache -t opea/chatqna-conversation-ui:latest --build-arg https_proxy=$https_proxy --build-arg http_proxy=$http_proxy -f ./docker/Dockerfile.react .
 ```
 
-Then run the command `docker images`, you will have the following 7 Docker Images:
+### 9. Build Nginx Docker Image
+
+```bash
+cd GenAIComps
+docker build -t opea/nginx:latest --build-arg https_proxy=$https_proxy --build-arg http_proxy=$http_proxy -f comps/nginx/Dockerfile .
+```
+
+Then run the command `docker images`, you will have the following 8 Docker Images:
 
 1. `opea/dataprep-redis:latest`
 2. `opea/embedding-tei:latest`
@@ -225,6 +232,7 @@ Then run the command `docker images`, you will have the following 7 Docker Image
 5. `opea/llm-tgi:latest` or `opea/llm-vllm:latest`
 6. `opea/chatqna:latest` or `opea/chatqna-without-rerank:latest`
 7. `opea/chatqna-ui:latest`
+8. `opea/nginx:latest`
 
 ## 🚀 Start Microservices
 
@@ -267,57 +275,30 @@ For users in China who are unable to download models directly from Huggingface,
 
 ### Setup Environment Variables
 
-Since the `compose.yaml` will consume some environment variables, you need to setup them in advance as below.
-
-**Export the value of the public IP address of your Xeon server to the `host_ip` environment variable**
-
-> Change the External_Public_IP below with the actual IPV4 value
-
-```
-export host_ip="External_Public_IP"
-```
-
-**Export the value of your Huggingface API token to the `your_hf_api_token` environment variable**
-
-> Change the Your_Huggingface_API_Token below with tyour actual Huggingface API Token value
+1. Set the required environment variables:
 
-```
-export your_hf_api_token="Your_Huggingface_API_Token"
-```
+   ```bash
+   # Example: host_ip="192.168.1.1"
+   export host_ip="External_Public_IP"
+   # Example: no_proxy="localhost, 127.0.0.1, 192.168.1.1"
+   export no_proxy="Your_No_Proxy"
+   export HUGGINGFACEHUB_API_TOKEN="Your_Huggingface_API_Token"
+   # Example: NGINX_PORT=80
+   export NGINX_PORT=${your_nginx_port}
+   ```
 
-**Append the value of the public IP address to the no_proxy list**
+2. If you are in a proxy environment, also set the proxy-related environment variables:
 
-```bash
-export your_no_proxy=${your_no_proxy},"External_Public_IP"
-```
+   ```bash
+   export http_proxy="Your_HTTP_Proxy"
+   export https_proxy="Your_HTTPs_Proxy"
+   ```
 
-```bash
-export no_proxy=${your_no_proxy}
-export http_proxy=${your_http_proxy}
-export https_proxy=${your_http_proxy}
-export EMBEDDING_MODEL_ID="BAAI/bge-base-en-v1.5"
-export RERANK_MODEL_ID="BAAI/bge-reranker-base"
-export LLM_MODEL_ID="Intel/neural-chat-7b-v3-3"
-export TEI_EMBEDDING_ENDPOINT="http://${host_ip}:6006"
-export TEI_RERANKING_ENDPOINT="http://${host_ip}:8808"
-export TGI_LLM_ENDPOINT="http://${host_ip}:9009"
-export vLLM_LLM_ENDPOINT="http://${host_ip}:9009"
-export LLM_SERVICE_PORT=9000
-export REDIS_URL="redis://${host_ip}:6379"
-export INDEX_NAME="rag-redis"
-export HUGGINGFACEHUB_API_TOKEN=${your_hf_api_token}
-export MEGA_SERVICE_HOST_IP=${host_ip}
-export EMBEDDING_SERVICE_HOST_IP=${host_ip}
-export RETRIEVER_SERVICE_HOST_IP=${host_ip}
-export RERANK_SERVICE_HOST_IP=${host_ip}
-export LLM_SERVICE_HOST_IP=${host_ip}
-export BACKEND_SERVICE_ENDPOINT="http://${host_ip}:8888/v1/chatqna"
-export DATAPREP_SERVICE_ENDPOINT="http://${host_ip}:6007/v1/dataprep"
-export DATAPREP_GET_FILE_ENDPOINT="http://${host_ip}:6007/v1/dataprep/get_file"
-export DATAPREP_DELETE_FILE_ENDPOINT="http://${host_ip}:6007/v1/dataprep/delete_file"
-```
+3. Set up other environment variables:
 
-Note: Please replace with `host_ip` with you external IP address, do not use localhost.
+   ```bash
+   source ./set_env.sh
+   ```
 
 ### Start all the services Docker Containers
 
@@ -449,7 +430,7 @@ docker compose -f compose_vllm.yaml up -d
 
    ```bash
    # vLLM Service
-   curl http://${your_ip}:9000/v1/chat/completions \
+   curl http://${host_ip}:9000/v1/chat/completions \
     -X POST \
     -d '{"query":"What is Deep Learning?","max_tokens":17,"top_p":1,"temperature":0.7,"frequency_penalty":0,"presence_penalty":0, "streaming":false}' \
     -H 'Content-Type: application/json'
@@ -465,88 +446,98 @@ docker compose -f compose_vllm.yaml up -d
           }'
    ```
 
-9. Dataprep Microservice（Optional）
+9. Nginx Service
+
+   ```bash
+   curl http://${host_ip}:${NGINX_PORT}/v1/chatqna \
+       -H "Content-Type: application/json" \
+       -d '{"messages": "What is the revenue of Nike in 2023?"}'
+   ```
 
-   If you want to update the default knowledge base, you can use the following commands:
+10. Dataprep Microservice（Optional）
 
-   Update Knowledge Base via Local File [nke-10k-2023.pdf](https://github.com/opea-project/GenAIComps/blob/main/comps/retrievers/redis/data/nke-10k-2023.pdf). Or
-   click [here](https://raw.githubusercontent.com/opea-project/GenAIComps/main/comps/retrievers/redis/data/nke-10k-2023.pdf) to download the file via any web browser.
-   Or run this command to get the file on a terminal.
+If you want to update the default knowledge base, you can use the following commands:
 
-   ```bash
-   wget https://raw.githubusercontent.com/opea-project/GenAIComps/main/comps/retrievers/redis/data/nke-10k-2023.pdf
+Update Knowledge Base via Local File [nke-10k-2023.pdf](https://github.com/opea-project/GenAIComps/blob/main/comps/retrievers/redis/data/nke-10k-2023.pdf). Or
+click [here](https://raw.githubusercontent.com/opea-project/GenAIComps/main/comps/retrievers/redis/data/nke-10k-2023.pdf) to download the file via any web browser.
+Or run this command to get the file on a terminal.
 
-   ```
+```bash
+wget https://raw.githubusercontent.com/opea-project/GenAIComps/main/comps/retrievers/redis/data/nke-10k-2023.pdf
 
-   Upload:
+```
 
-   ```bash
-   curl -X POST "http://${host_ip}:6007/v1/dataprep" \
-        -H "Content-Type: multipart/form-data" \
-        -F "files=@./nke-10k-2023.pdf"
-   ```
+Upload:
 
-   This command updates a knowledge base by uploading a local file for processing. Update the file path according to your environment.
+```bash
+curl -X POST "http://${host_ip}:6007/v1/dataprep" \
+     -H "Content-Type: multipart/form-data" \
+     -F "files=@./nke-10k-2023.pdf"
+```
 
-   Add Knowledge Base via HTTP Links:
+This command updates a knowledge base by uploading a local file for processing. Update the file path according to your environment.
 
-   ```bash
-   curl -X POST "http://${host_ip}:6007/v1/dataprep" \
-        -H "Content-Type: multipart/form-data" \
-        -F 'link_list=["https://opea.dev"]'
-   ```
+Add Knowledge Base via HTTP Links:
 
-   This command updates a knowledge base by submitting a list of HTTP links for processing.
+```bash
+curl -X POST "http://${host_ip}:6007/v1/dataprep" \
+     -H "Content-Type: multipart/form-data" \
+     -F 'link_list=["https://opea.dev"]'
+```
 
-   Also, you are able to get the file list that you uploaded:
+This command updates a knowledge base by submitting a list of HTTP links for processing.
 
-   ```bash
-   curl -X POST "http://${host_ip}:6007/v1/dataprep/get_file" \
-        -H "Content-Type: application/json"
-   ```
+Also, you are able to get the file list that you uploaded:
 
-   Then you will get the response JSON like this. Notice that the returned `name`/`id` of the uploaded link is `https://xxx.txt`.
-
-   ```json
-   [
-     {
-       "name": "nke-10k-2023.pdf",
-       "id": "nke-10k-2023.pdf",
-       "type": "File",
-       "parent": ""
-     },
-     {
-       "name": "https://opea.dev.txt",
-       "id": "https://opea.dev.txt",
-       "type": "File",
-       "parent": ""
-     }
-   ]
-   ```
+```bash
+curl -X POST "http://${host_ip}:6007/v1/dataprep/get_file" \
+     -H "Content-Type: application/json"
+```
+
+Then you will get the response JSON like this. Notice that the returned `name`/`id` of the uploaded link is `https://xxx.txt`.
+
+```json
+[
+  {
+    "name": "nke-10k-2023.pdf",
+    "id": "nke-10k-2023.pdf",
+    "type": "File",
+    "parent": ""
+  },
+  {
+    "name": "https://opea.dev.txt",
+    "id": "https://opea.dev.txt",
+    "type": "File",
+    "parent": ""
+  }
+]
+```
 
-   To delete the file/link you uploaded:
+To delete the file/link you uploaded:
 
-   The `file_path` here should be the `id` get from `/v1/dataprep/get_file` API.
+The `file_path` here should be the `id` get from `/v1/dataprep/get_file` API.
 
-   ```bash
-   # delete link
-   curl -X POST "http://${host_ip}:6007/v1/dataprep/delete_file" \
-        -d '{"file_path": "https://opea.dev.txt"}' \
-        -H "Content-Type: application/json"
-
-   # delete file
-   curl -X POST "http://${host_ip}:6007/v1/dataprep/delete_file" \
-        -d '{"file_path": "nke-10k-2023.pdf"}' \
-        -H "Content-Type: application/json"
-
-   # delete all uploaded files and links
-   curl -X POST "http://${host_ip}:6007/v1/dataprep/delete_file" \
-        -d '{"file_path": "all"}' \
-        -H "Content-Type: application/json"
-   ```
+```bash
+# delete link
+curl -X POST "http://${host_ip}:6007/v1/dataprep/delete_file" \
+     -d '{"file_path": "https://opea.dev.txt"}' \
+     -H "Content-Type: application/json"
+
+# delete file
+curl -X POST "http://${host_ip}:6007/v1/dataprep/delete_file" \
+     -d '{"file_path": "nke-10k-2023.pdf"}' \
+     -H "Content-Type: application/json"
+
+# delete all uploaded files and links
+curl -X POST "http://${host_ip}:6007/v1/dataprep/delete_file" \
+     -d '{"file_path": "all"}' \
+     -H "Content-Type: application/json"
+```
 
 ## 🚀 Launch the UI
 
+### Launch with origin port
+
 To access the frontend, open the following URL in your browser: http://{host_ip}:5173. By default, the UI runs on port 5173 internally. If you prefer to use a different host port to access the frontend, you can modify the port mapping in the `compose.yaml` file as shown below:
 
 ```yaml
@@ -557,6 +548,10 @@ To access the frontend, open the following URL in your browser: http://{host_ip}
       - "80:5173"
 ```
 
+### Launch with Nginx
+
+If you want to launch the UI using Nginx, open this URL: `http://${host_ip}:${NGINX_PORT}` in your browser to access the frontend.
+
 ## 🚀 Launch the Conversational UI (Optional)
 
 To access the Conversational UI (react based) frontend, modify the UI service in the `compose.yaml` file. Replace `chaqna-xeon-ui-server` service with the `chatqna-xeon-conversation-ui-server` service as per the config below:
diff --git a/ChatQnA/docker_compose/intel/cpu/xeon/compose.yaml b/ChatQnA/docker_compose/intel/cpu/xeon/compose.yaml
index ef64a3098..6f253093d 100644
--- a/ChatQnA/docker_compose/intel/cpu/xeon/compose.yaml
+++ b/ChatQnA/docker_compose/intel/cpu/xeon/compose.yaml
@@ -178,6 +178,25 @@ services:
       - DELETE_FILE=${DATAPREP_DELETE_FILE_ENDPOINT}
     ipc: host
     restart: always
+  chaqna-xeon-nginx-server:
+    image: ${REGISTRY:-opea}/nginx:${TAG:-latest}
+    container_name: chaqna-xeon-nginx-server
+    depends_on:
+      - chaqna-xeon-backend-server
+      - chaqna-xeon-ui-server
+    ports:
+      - "${NGINX_PORT:-80}:80"
+    environment:
+      - no_proxy=${no_proxy}
+      - https_proxy=${https_proxy}
+      - http_proxy=${http_proxy}
+      - FRONTEND_SERVICE_IP=${FRONTEND_SERVICE_IP}
+      - FRONTEND_SERVICE_PORT=${FRONTEND_SERVICE_PORT}
+      - BACKEND_SERVICE_NAME=${BACKEND_SERVICE_NAME}
+      - BACKEND_SERVICE_IP=${BACKEND_SERVICE_IP}
+      - BACKEND_SERVICE_PORT=${BACKEND_SERVICE_PORT}
+    ipc: host
+    restart: always
 
 networks:
   default:
diff --git a/ChatQnA/docker_compose/intel/cpu/xeon/set_env.sh b/ChatQnA/docker_compose/intel/cpu/xeon/set_env.sh
index d2cfd86d3..3373eb9fd 100644
--- a/ChatQnA/docker_compose/intel/cpu/xeon/set_env.sh
+++ b/ChatQnA/docker_compose/intel/cpu/xeon/set_env.sh
@@ -22,3 +22,8 @@ export BACKEND_SERVICE_ENDPOINT="http://${host_ip}:8888/v1/chatqna"
 export DATAPREP_SERVICE_ENDPOINT="http://${host_ip}:6007/v1/dataprep"
 export DATAPREP_GET_FILE_ENDPOINT="http://${host_ip}:6007/v1/dataprep/get_file"
 export DATAPREP_DELETE_FILE_ENDPOINT="http://${host_ip}:6007/v1/dataprep/delete_file"
+export FRONTEND_SERVICE_IP=${host_ip}
+export FRONTEND_SERVICE_PORT=5173
+export BACKEND_SERVICE_NAME=chatqna
+export BACKEND_SERVICE_IP=${host_ip}
+export BACKEND_SERVICE_PORT=8888
diff --git a/ChatQnA/docker_compose/intel/hpu/gaudi/README.md b/ChatQnA/docker_compose/intel/hpu/gaudi/README.md
index ec8e3ad09..fab6f1046 100644
--- a/ChatQnA/docker_compose/intel/hpu/gaudi/README.md
+++ b/ChatQnA/docker_compose/intel/hpu/gaudi/README.md
@@ -192,7 +192,14 @@ cd GenAIExamples/ChatQnA/ui
 docker build --no-cache -t opea/chatqna-conversation-ui:latest --build-arg https_proxy=$https_proxy --build-arg http_proxy=$http_proxy -f ./docker/Dockerfile.react .
 ```
 
-Then run the command `docker images`, you will have the following 7 Docker Images:
+### 10. Build Nginx Docker Image
+
+```bash
+cd GenAIComps
+docker build -t opea/nginx:latest --build-arg https_proxy=$https_proxy --build-arg http_proxy=$http_proxy -f comps/nginx/Dockerfile .
+```
+
+Then run the command `docker images`, you will have the following 8 Docker Images:
 
 - `opea/embedding-tei:latest`
 - `opea/retriever-redis:latest`
@@ -201,6 +208,7 @@ Then run the command `docker images`, you will have the following 7 Docker Image
 - `opea/dataprep-redis:latest`
 - `opea/chatqna:latest` or `opea/chatqna-guardrails:latest` or `opea/chatqna-without-rerank:latest`
 - `opea/chatqna-ui:latest`
+- `opea/nginx:latest`
 
 If Conversation React UI is built, you will find one more image:
 
@@ -251,51 +259,30 @@ For users in China who are unable to download models directly from Huggingface,
 
 ### Setup Environment Variables
 
-Since the `compose.yaml` will consume some environment variables, you need to setup them in advance as below.
+1. Set the required environment variables:
 
-```bash
-export no_proxy=${your_no_proxy}
-export http_proxy=${your_http_proxy}
-export https_proxy=${your_http_proxy}
-export EMBEDDING_MODEL_ID="BAAI/bge-base-en-v1.5"
-export RERANK_MODEL_ID="BAAI/bge-reranker-base"
-export LLM_MODEL_ID="Intel/neural-chat-7b-v3-3"
-export LLM_MODEL_ID_NAME="neural-chat-7b-v3-3"
-export TEI_EMBEDDING_ENDPOINT="http://${host_ip}:8090"
-export TEI_RERANKING_ENDPOINT="http://${host_ip}:8808"
-export TGI_LLM_ENDPOINT="http://${host_ip}:8005"
-export vLLM_LLM_ENDPOINT="http://${host_ip}:8007"
-export vLLM_RAY_LLM_ENDPOINT="http://${host_ip}:8006"
-export LLM_SERVICE_PORT=9000
-export REDIS_URL="redis://${host_ip}:6379"
-export INDEX_NAME="rag-redis"
-export HUGGINGFACEHUB_API_TOKEN=${your_hf_api_token}
-export MEGA_SERVICE_HOST_IP=${host_ip}
-export EMBEDDING_SERVICE_HOST_IP=${host_ip}
-export RETRIEVER_SERVICE_HOST_IP=${host_ip}
-export RERANK_SERVICE_HOST_IP=${host_ip}
-export LLM_SERVICE_HOST_IP=${host_ip}
-export BACKEND_SERVICE_ENDPOINT="http://${host_ip}:8888/v1/chatqna"
-export DATAPREP_SERVICE_ENDPOINT="http://${host_ip}:6007/v1/dataprep"
-export DATAPREP_GET_FILE_ENDPOINT="http://${host_ip}:6007/v1/dataprep/get_file"
-export DATAPREP_DELETE_FILE_ENDPOINT="http://${host_ip}:6007/v1/dataprep/delete_file"
-
-export llm_service_devices=all
-export tei_embedding_devices=all
-```
+   ```bash
+   # Example: host_ip="192.168.1.1"
+   export host_ip="External_Public_IP"
+   # Example: no_proxy="localhost, 127.0.0.1, 192.168.1.1"
+   export no_proxy="Your_No_Proxy"
+   export HUGGINGFACEHUB_API_TOKEN="Your_Huggingface_API_Token"
+   # Example: NGINX_PORT=80
+   export NGINX_PORT=${your_nginx_port}
+   ```
 
-To specify the device ids, "llm_service_devices" and "tei_embedding_devices"` can be set as "0,1,2,3" alike. More info in [gaudi docs](https://docs.habana.ai/en/latest/Orchestration/Multiple_Tenants_on_HPU/Multiple_Dockers_each_with_Single_Workload.html).
+2. If you are in a proxy environment, also set the proxy-related environment variables:
 
-If guardrails microservice is enabled in the pipeline, the below environment variables are necessary to be set.
+   ```bash
+   export http_proxy="Your_HTTP_Proxy"
+   export https_proxy="Your_HTTPs_Proxy"
+   ```
 
-```bash
-export GURADRAILS_MODEL_ID="meta-llama/Meta-Llama-Guard-2-8B"
-export SAFETY_GUARD_MODEL_ID="meta-llama/Meta-Llama-Guard-2-8B"
-export SAFETY_GUARD_ENDPOINT="http://${host_ip}:8088"
-export GUARDRAIL_SERVICE_HOST_IP=${host_ip}
-```
+3. Set up other environment variables:
 
-Note: Please replace `host_ip` with your external IP address, do **NOT** use localhost.
+   ```bash
+   source ./set_env.sh
+   ```
 
 ### Start all the services Docker Containers
 
@@ -463,7 +450,7 @@ For validation details, please refer to [how-to-validate_service](./how_to_valid
 
    ```bash
    # vLLM-on-Ray Service
-   curl http://${your_ip}:9000/v1/chat/completions \
+   curl http://${host_ip}:9000/v1/chat/completions \
      -X POST \
      -d '{"query":"What is Deep Learning?","max_tokens":17,"presence_penalty":1.03","streaming":false}' \
      -H 'Content-Type: application/json'
@@ -479,74 +466,82 @@ For validation details, please refer to [how-to-validate_service](./how_to_valid
          }'
    ```
 
-9. Dataprep Microservice（Optional）
-
-   If you want to update the default knowledge base, you can use the following commands:
-
-   Update Knowledge Base via Local File Upload:
+9. Nginx Service
 
    ```bash
-   curl -X POST "http://${host_ip}:6007/v1/dataprep" \
-        -H "Content-Type: multipart/form-data" \
-        -F "files=@./nke-10k-2023.pdf"
+   curl http://${host_ip}:${NGINX_PORT}/v1/chatqna \
+       -H "Content-Type: application/json" \
+       -d '{"messages": "What is the revenue of Nike in 2023?"}'
    ```
 
-   This command updates a knowledge base by uploading a local file for processing. Update the file path according to your environment.
+10. Dataprep Microservice（Optional）
 
-   Add Knowledge Base via HTTP Links:
+If you want to update the default knowledge base, you can use the following commands:
 
-   ```bash
-   curl -X POST "http://${host_ip}:6007/v1/dataprep" \
-        -H "Content-Type: multipart/form-data" \
-        -F 'link_list=["https://opea.dev"]'
-   ```
+Update Knowledge Base via Local File Upload:
 
-   This command updates a knowledge base by submitting a list of HTTP links for processing.
+```bash
+curl -X POST "http://${host_ip}:6007/v1/dataprep" \
+     -H "Content-Type: multipart/form-data" \
+     -F "files=@./nke-10k-2023.pdf"
+```
 
-   Also, you are able to get the file/link list that you uploaded:
+This command updates a knowledge base by uploading a local file for processing. Update the file path according to your environment.
 
-   ```bash
-   curl -X POST "http://${host_ip}:6007/v1/dataprep/get_file" \
-        -H "Content-Type: application/json"
-   ```
+Add Knowledge Base via HTTP Links:
 
-   Then you will get the response JSON like this. Notice that the returned `name`/`id` of the uploaded link is `https://xxx.txt`.
-
-   ```json
-   [
-     {
-       "name": "nke-10k-2023.pdf",
-       "id": "nke-10k-2023.pdf",
-       "type": "File",
-       "parent": ""
-     },
-     {
-       "name": "https://opea.dev.txt",
-       "id": "https://opea.dev.txt",
-       "type": "File",
-       "parent": ""
-     }
-   ]
-   ```
+```bash
+curl -X POST "http://${host_ip}:6007/v1/dataprep" \
+     -H "Content-Type: multipart/form-data" \
+     -F 'link_list=["https://opea.dev"]'
+```
 
-   To delete the file/link you uploaded:
+This command updates a knowledge base by submitting a list of HTTP links for processing.
 
-   ```bash
-   # delete link
-   curl -X POST "http://${host_ip}:6007/v1/dataprep/delete_file" \
-        -d '{"file_path": "https://opea.dev.txt"}' \
-        -H "Content-Type: application/json"
-
-   # delete file
-   curl -X POST "http://${host_ip}:6007/v1/dataprep/delete_file" \
-        -d '{"file_path": "nke-10k-2023.pdf"}' \
-        -H "Content-Type: application/json"
-
-   # delete all uploaded files and links
-   curl -X POST "http://${host_ip}:6007/v1/dataprep/delete_file" \
-        -d '{"file_path": "all"}' \
-        -H "Content-Type: application/json"
-   ```
+Also, you are able to get the file/link list that you uploaded:
+
+```bash
+curl -X POST "http://${host_ip}:6007/v1/dataprep/get_file" \
+     -H "Content-Type: application/json"
+```
+
+Then you will get the response JSON like this. Notice that the returned `name`/`id` of the uploaded link is `https://xxx.txt`.
+
+```json
+[
+  {
+    "name": "nke-10k-2023.pdf",
+    "id": "nke-10k-2023.pdf",
+    "type": "File",
+    "parent": ""
+  },
+  {
+    "name": "https://opea.dev.txt",
+    "id": "https://opea.dev.txt",
+    "type": "File",
+    "parent": ""
+  }
+]
+```
+
+To delete the file/link you uploaded:
+
+```bash
+# delete link
+curl -X POST "http://${host_ip}:6007/v1/dataprep/delete_file" \
+     -d '{"file_path": "https://opea.dev.txt"}' \
+     -H "Content-Type: application/json"
+
+# delete file
+curl -X POST "http://${host_ip}:6007/v1/dataprep/delete_file" \
+     -d '{"file_path": "nke-10k-2023.pdf"}' \
+     -H "Content-Type: application/json"
+
+# delete all uploaded files and links
+curl -X POST "http://${host_ip}:6007/v1/dataprep/delete_file" \
+     -d '{"file_path": "all"}' \
+     -H "Content-Type: application/json"
+```
 
 10. Guardrails (Optional)
 
@@ -559,6 +554,8 @@ curl http://${host_ip}:9090/v1/guardrails\
 
 ## 🚀 Launch the UI
 
+### Launch with origin port
+
 To access the frontend, open the following URL in your browser: http://{host_ip}:5173. By default, the UI runs on port 5173 internally. If you prefer to use a different host port to access the frontend, you can modify the port mapping in the `compose.yaml` file as shown below:
 
 ```yaml
@@ -569,11 +566,9 @@ To access the frontend, open the following URL in your browser: http://{host_ip}
       - "80:5173"
 ```
 
-![project-screenshot](../../../../assets/img/chat_ui_init.png)
+### Launch with Nginx
 
-Here is an example of running ChatQnA:
-
-![project-screenshot](../../../../assets/img/chat_ui_response.png)
+If you want to launch the UI using Nginx, open this URL: `http://${host_ip}:${NGINX_PORT}` in your browser to access the frontend.
 
 ## 🚀 Launch the Conversational UI (Optional)
 
@@ -604,6 +599,12 @@ Once the services are up, open the following URL in your browser: http://{host_i
       - "80:80"
 ```
 
+![project-screenshot](../../../../assets/img/chat_ui_init.png)
+
+Here is an example of running ChatQnA:
+
+![project-screenshot](../../../../assets/img/chat_ui_response.png)
+
 Here is an example of running ChatQnA with Conversational UI (React):
 
 ![project-screenshot](../../../../assets/img/conversation_ui_response.png)
diff --git a/ChatQnA/docker_compose/intel/hpu/gaudi/compose.yaml b/ChatQnA/docker_compose/intel/hpu/gaudi/compose.yaml
index 6689efc6f..e5aa98713 100644
--- a/ChatQnA/docker_compose/intel/hpu/gaudi/compose.yaml
+++ b/ChatQnA/docker_compose/intel/hpu/gaudi/compose.yaml
@@ -187,6 +187,25 @@ services:
       - DELETE_FILE=${DATAPREP_DELETE_FILE_ENDPOINT}
     ipc: host
     restart: always
+  chaqna-gaudi-nginx-server:
+    image: ${REGISTRY:-opea}/nginx:${TAG:-latest}
+    container_name: chaqna-gaudi-nginx-server
+    depends_on:
+      - chaqna-gaudi-backend-server
+      - chaqna-gaudi-ui-server
+    ports:
+      - "${NGINX_PORT:-80}:80"
+    environment:
+      - no_proxy=${no_proxy}
+      - https_proxy=${https_proxy}
+      - http_proxy=${http_proxy}
+      - FRONTEND_SERVICE_IP=${FRONTEND_SERVICE_IP}
+      - FRONTEND_SERVICE_PORT=${FRONTEND_SERVICE_PORT}
+      - BACKEND_SERVICE_NAME=${BACKEND_SERVICE_NAME}
+      - BACKEND_SERVICE_IP=${BACKEND_SERVICE_IP}
+      - BACKEND_SERVICE_PORT=${BACKEND_SERVICE_PORT}
+    ipc: host
+    restart: always
 
 networks:
   default:
diff --git a/ChatQnA/docker_compose/intel/hpu/gaudi/set_env.sh b/ChatQnA/docker_compose/intel/hpu/gaudi/set_env.sh
index 968f49492..d3b805953 100644
--- a/ChatQnA/docker_compose/intel/hpu/gaudi/set_env.sh
+++ b/ChatQnA/docker_compose/intel/hpu/gaudi/set_env.sh
@@ -21,3 +21,8 @@ export BACKEND_SERVICE_ENDPOINT="http://${host_ip}:8888/v1/chatqna"
 export DATAPREP_SERVICE_ENDPOINT="http://${host_ip}:6007/v1/dataprep"
 export DATAPREP_GET_FILE_ENDPOINT="http://${host_ip}:6007/v1/dataprep/get_file"
 export DATAPREP_DELETE_FILE_ENDPOINT="http://${host_ip}:6007/v1/dataprep/delete_file"
+export FRONTEND_SERVICE_IP=${host_ip}
+export FRONTEND_SERVICE_PORT=5173
+export BACKEND_SERVICE_NAME=chatqna
+export BACKEND_SERVICE_IP=${host_ip}
+export BACKEND_SERVICE_PORT=8888
diff --git a/ChatQnA/docker_compose/nvidia/gpu/README.md b/ChatQnA/docker_compose/nvidia/gpu/README.md
index 7e3966a7f..dd21def27 100644
--- a/ChatQnA/docker_compose/nvidia/gpu/README.md
+++ b/ChatQnA/docker_compose/nvidia/gpu/README.md
@@ -134,7 +134,14 @@ docker build --no-cache -t opea/chatqna-react-ui:latest --build-arg https_proxy=
 cd ../../../..
 ```
 
-Then run the command `docker images`, you will have the following 7 Docker Images:
+### 10. Build Nginx Docker Image
+
+```bash
+cd GenAIComps
+docker build -t opea/nginx:latest --build-arg https_proxy=$https_proxy --build-arg http_proxy=$http_proxy -f comps/nginx/Dockerfile .
+```
+
+Then run the command `docker images`, you will have the following 8 Docker Images:
 
 1. `opea/embedding-tei:latest`
 2. `opea/retriever-redis:latest`
@@ -142,8 +149,8 @@ Then run the command `docker images`, you will have the following 7 Docker Image
 4. `opea/llm-tgi:latest`
 5. `opea/dataprep-redis:latest`
 6. `opea/chatqna:latest`
-7. `opea/chatqna-ui:latest`
-8. `opea/chatqna-react-ui:latest`
+7. `opea/chatqna-ui:latest` or `opea/chatqna-react-ui:latest`
+8. `opea/nginx:latest`
 
 ## 🚀 Start MicroServices and MegaService
 
@@ -161,33 +168,30 @@ Change the `xxx_MODEL_ID` below for your needs.
 
 ### Setup Environment Variables
 
-Since the `compose.yaml` will consume some environment variables, you need to setup them in advance as below.
+1. Set the required environment variables:
 
-```bash
-export no_proxy=${your_no_proxy}
-export http_proxy=${your_http_proxy}
-export https_proxy=${your_http_proxy}
-export EMBEDDING_MODEL_ID="BAAI/bge-base-en-v1.5"
-export RERANK_MODEL_ID="BAAI/bge-reranker-base"
-export LLM_MODEL_ID="Intel/neural-chat-7b-v3-3"
-export TEI_EMBEDDING_ENDPOINT="http://${host_ip}:8090"
-export TEI_RERANKING_ENDPOINT="http://${host_ip}:8808"
-export TGI_LLM_ENDPOINT="http://${host_ip}:8008"
-export REDIS_URL="redis://${host_ip}:6379"
-export INDEX_NAME="rag-redis"
-export HUGGINGFACEHUB_API_TOKEN=${your_hf_api_token}
-export MEGA_SERVICE_HOST_IP=${host_ip}
-export EMBEDDING_SERVICE_HOST_IP=${host_ip}
-export RETRIEVER_SERVICE_HOST_IP=${host_ip}
-export RERANK_SERVICE_HOST_IP=${host_ip}
-export LLM_SERVICE_HOST_IP=${host_ip}
-export BACKEND_SERVICE_ENDPOINT="http://${host_ip}:8888/v1/chatqna"
-export DATAPREP_SERVICE_ENDPOINT="http://${host_ip}:6007/v1/dataprep"
-export DATAPREP_GET_FILE_ENDPOINT="http://${host_ip}:6007/v1/dataprep/get_file"
-export DATAPREP_DELETE_FILE_ENDPOINT="http://${host_ip}:6007/v1/dataprep/delete_file"
-```
+   ```bash
+   # Example: host_ip="192.168.1.1"
+   export host_ip="External_Public_IP"
+   # Example: no_proxy="localhost, 127.0.0.1, 192.168.1.1"
+   export no_proxy="Your_No_Proxy"
+   export HUGGINGFACEHUB_API_TOKEN="Your_Huggingface_API_Token"
+   # Example: NGINX_PORT=80
+   export NGINX_PORT=${your_nginx_port}
+   ```
+
+2. If you are in a proxy environment, also set the proxy-related environment variables:
 
-Note: Please replace with `host_ip` with you external IP address, do **NOT** use localhost.
+   ```bash
+   export http_proxy="Your_HTTP_Proxy"
+   export https_proxy="Your_HTTPs_Proxy"
+   ```
+
+3. Set up other environment variables:
+
+   ```bash
+   source ./set_env.sh
+   ```
 
 ### Start all the services Docker Containers
 
@@ -292,58 +296,68 @@ docker compose up -d
         }'
    ```
 
-9. Dataprep Microservice（Optional）
-
-   If you want to update the default knowledge base, you can use the following commands:
-
-   Update Knowledge Base via Local File Upload:
+9. Nginx Service
 
    ```bash
-   curl -X POST "http://${host_ip}:6007/v1/dataprep" \
-        -H "Content-Type: multipart/form-data" \
-        -F "files=@./nke-10k-2023.pdf"
+   curl http://${host_ip}:${NGINX_PORT}/v1/chatqna \
+       -H "Content-Type: application/json" \
+       -d '{"messages": "What is the revenue of Nike in 2023?"}'
    ```
 
-   This command updates a knowledge base by uploading a local file for processing. Update the file path according to your environment.
+10. Dataprep Microservice（Optional）
 
-   Add Knowledge Base via HTTP Links:
+If you want to update the default knowledge base, you can use the following commands:
 
-   ```bash
-   curl -X POST "http://${host_ip}:6007/v1/dataprep" \
-        -H "Content-Type: multipart/form-data" \
-        -F 'link_list=["https://opea.dev"]'
-   ```
+Update Knowledge Base via Local File Upload:
 
-   This command updates a knowledge base by submitting a list of HTTP links for processing.
+```bash
+curl -X POST "http://${host_ip}:6007/v1/dataprep" \
+     -H "Content-Type: multipart/form-data" \
+     -F "files=@./nke-10k-2023.pdf"
+```
 
-   Also, you are able to get the file list that you uploaded:
+This command updates a knowledge base by uploading a local file for processing. Update the file path according to your environment.
 
-   ```bash
-   curl -X POST "http://${host_ip}:6007/v1/dataprep/get_file" \
-        -H "Content-Type: application/json"
-   ```
+Add Knowledge Base via HTTP Links:
 
-   To delete the file/link you uploaded:
+```bash
+curl -X POST "http://${host_ip}:6007/v1/dataprep" \
+     -H "Content-Type: multipart/form-data" \
+     -F 'link_list=["https://opea.dev"]'
+```
 
-   ```bash
-   # delete link
-   curl -X POST "http://${host_ip}:6007/v1/dataprep/delete_file" \
-        -d '{"file_path": "https://opea.dev"}' \
-        -H "Content-Type: application/json"
-
-   # delete file
-   curl -X POST "http://${host_ip}:6007/v1/dataprep/delete_file" \
-        -d '{"file_path": "nke-10k-2023.pdf"}' \
-        -H "Content-Type: application/json"
-
-   # delete all uploaded files and links
-   curl -X POST "http://${host_ip}:6007/v1/dataprep/delete_file" \
-        -d '{"file_path": "all"}' \
-        -H "Content-Type: application/json"
-   ```
+This command updates a knowledge base by submitting a list of HTTP links for processing.
+
+Also, you are able to get the file list that you uploaded:
+
+```bash
+curl -X POST "http://${host_ip}:6007/v1/dataprep/get_file" \
+     -H "Content-Type: application/json"
+```
+
+To delete the file/link you uploaded:
+
+```bash
+# delete link
+curl -X POST "http://${host_ip}:6007/v1/dataprep/delete_file" \
+     -d '{"file_path": "https://opea.dev"}' \
+     -H "Content-Type: application/json"
+
+# delete file
+curl -X POST "http://${host_ip}:6007/v1/dataprep/delete_file" \
+     -d '{"file_path": "nke-10k-2023.pdf"}' \
+     -H "Content-Type: application/json"
+
+# delete all uploaded files and links
+curl -X POST "http://${host_ip}:6007/v1/dataprep/delete_file" \
+     -d '{"file_path": "all"}' \
+     -H "Content-Type: application/json"
+```
 
 ## 🚀 Launch the UI
 
+### Launch with origin port
+
 To access the frontend, open the following URL in your browser: http://{host_ip}:5173. By default, the UI runs on port 5173 internally. If you prefer to use a different host port to access the frontend, you can modify the port mapping in the `compose.yaml` file as shown below:
 
 ```yaml
@@ -354,6 +368,10 @@ To access the frontend, open the following URL in your browser: http://{host_ip}
       - "80:5173"
 ```
 
+### Launch with Nginx
+
+If you want to launch the UI using Nginx, open this URL: `http://${host_ip}:${NGINX_PORT}` in your browser to access the frontend.
+
 ## 🚀 Launch the Conversational UI (Optional)
 
 To access the Conversational UI (react based) frontend, modify the UI service in the `compose.yaml` file. Replace `chaqna-ui-server` service with the `chatqna-react-ui-server` service as per the config below:
@@ -384,3 +402,11 @@ Once the services are up, open the following URL in your browser: http://{host_i
 ```
 
 ![project-screenshot](../../../assets/img/chat_ui_init.png)
+
+Here is an example of running ChatQnA:
+
+![project-screenshot](../../../assets/img/chat_ui_response.png)
+
+Here is an example of running ChatQnA with Conversational UI (React):
+
+![project-screenshot](../../../assets/img/conversation_ui_response.png)
diff --git a/ChatQnA/docker_compose/nvidia/gpu/compose.yaml b/ChatQnA/docker_compose/nvidia/gpu/compose.yaml
index 5e50214d1..218e11bec 100644
--- a/ChatQnA/docker_compose/nvidia/gpu/compose.yaml
+++ b/ChatQnA/docker_compose/nvidia/gpu/compose.yaml
@@ -197,6 +197,25 @@ services:
       - DELETE_FILE=${DATAPREP_DELETE_FILE_ENDPOINT}
     ipc: host
     restart: always
+  chaqna-nginx-server:
+    image: ${REGISTRY:-opea}/nginx:${TAG:-latest}
+    container_name: chaqna-nginx-server
+    depends_on:
+      - chaqna-backend-server
+      - chaqna-ui-server
+    ports:
+      - "${NGINX_PORT:-80}:80"
+    environment:
+      - no_proxy=${no_proxy}
+      - https_proxy=${https_proxy}
+      - http_proxy=${http_proxy}
+      - FRONTEND_SERVICE_IP=${FRONTEND_SERVICE_IP}
+      - FRONTEND_SERVICE_PORT=${FRONTEND_SERVICE_PORT}
+      - BACKEND_SERVICE_NAME=${BACKEND_SERVICE_NAME}
+      - BACKEND_SERVICE_IP=${BACKEND_SERVICE_IP}
+      - BACKEND_SERVICE_PORT=${BACKEND_SERVICE_PORT}
+    ipc: host
+    restart: always
 
 networks:
   default:
diff --git a/ChatQnA/docker_compose/nvidia/gpu/set_env.sh b/ChatQnA/docker_compose/nvidia/gpu/set_env.sh
index 3b3d43336..49a7ad7d8 100644
--- a/ChatQnA/docker_compose/nvidia/gpu/set_env.sh
+++ b/ChatQnA/docker_compose/nvidia/gpu/set_env.sh
@@ -21,3 +21,8 @@ export BACKEND_SERVICE_ENDPOINT="http://${host_ip}:8888/v1/chatqna"
 export DATAPREP_SERVICE_ENDPOINT="http://${host_ip}:6007/v1/dataprep"
 export DATAPREP_GET_FILE_ENDPOINT="http://${host_ip}:6007/v1/dataprep/get_file"
 export DATAPREP_DELETE_FILE_ENDPOINT="http://${host_ip}:6007/v1/dataprep/delete_file"
+export FRONTEND_SERVICE_IP=${host_ip}
+export FRONTEND_SERVICE_PORT=5173
+export BACKEND_SERVICE_NAME=chatqna
+export BACKEND_SERVICE_IP=${host_ip}
+export BACKEND_SERVICE_PORT=8888
diff --git a/ChatQnA/docker_image_build/build.yaml b/ChatQnA/docker_image_build/build.yaml
index 4dd1d3b74..906f6fcf7 100644
--- a/ChatQnA/docker_image_build/build.yaml
+++ b/ChatQnA/docker_image_build/build.yaml
@@ -137,3 +137,9 @@ services:
       dockerfile: Dockerfile.cpu
     extends: chatqna
     image: ${REGISTRY:-opea}/vllm:${TAG:-latest}
+  nginx:
+    build:
+      context: GenAIComps
+      dockerfile: comps/nginx/Dockerfile
+    extends: chatqna
+    image: ${REGISTRY:-opea}/nginx:${TAG:-latest}
diff --git a/ChatQnA/tests/test_compose_on_gaudi.sh b/ChatQnA/tests/test_compose_on_gaudi.sh
index d40f7ad1d..e98a76311 100644
--- a/ChatQnA/tests/test_compose_on_gaudi.sh
+++ b/ChatQnA/tests/test_compose_on_gaudi.sh
@@ -20,7 +20,7 @@ function build_docker_images() {
     git clone https://github.com/huggingface/tei-gaudi
 
     echo "Build all the images with --no-cache, check docker_image_build.log for details..."
-    service_list="chatqna chatqna-ui dataprep-redis embedding-tei retriever-redis reranking-tei llm-tgi tei-gaudi"
+    service_list="chatqna chatqna-ui dataprep-redis embedding-tei retriever-redis reranking-tei llm-tgi tei-gaudi nginx"
     docker compose -f build.yaml build ${service_list} --no-cache > ${LOG_PATH}/docker_image_build.log
 
     docker pull ghcr.io/huggingface/tgi-gaudi:2.0.1
@@ -52,6 +52,12 @@ function start_services() {
     export DATAPREP_DELETE_FILE_ENDPOINT="http://${ip_address}:6009/v1/dataprep/delete_file"
     export llm_service_devices=all
     export tei_embedding_devices=all
+    export FRONTEND_SERVICE_IP=${host_ip}
+    export FRONTEND_SERVICE_PORT=5173
+    export BACKEND_SERVICE_NAME=chatqna
+    export BACKEND_SERVICE_IP=${host_ip}
+    export BACKEND_SERVICE_PORT=8888
+    export NGINX_PORT=80
 
     sed -i "s/backend_address/$ip_address/g" $WORKPATH/ui/svelte/.env
 
diff --git a/ChatQnA/tests/test_compose_on_xeon.sh b/ChatQnA/tests/test_compose_on_xeon.sh
index feba1039f..b7275cf8e 100644
--- a/ChatQnA/tests/test_compose_on_xeon.sh
+++ b/ChatQnA/tests/test_compose_on_xeon.sh
@@ -19,7 +19,7 @@ function build_docker_images() {
     git clone https://github.com/opea-project/GenAIComps.git && cd GenAIComps && git checkout "${opea_branch:-"main"}" && cd ../
 
     echo "Build all the images with --no-cache, check docker_image_build.log for details..."
-    service_list="chatqna chatqna-ui chatqna-conversation-ui dataprep-redis embedding-tei retriever-redis reranking-tei llm-tgi"
+    service_list="chatqna chatqna-ui chatqna-conversation-ui dataprep-redis embedding-tei retriever-redis reranking-tei llm-tgi nginx"
     docker compose -f build.yaml build ${service_list} --no-cache > ${LOG_PATH}/docker_image_build.log
 
     docker pull ghcr.io/huggingface/tgi-gaudi:2.0.1
@@ -50,6 +50,12 @@ function start_services() {
     export DATAPREP_SERVICE_ENDPOINT="http://${ip_address}:6007/v1/dataprep"
     export DATAPREP_GET_FILE_ENDPOINT="http://${ip_address}:6007/v1/dataprep/get_file"
     export DATAPREP_DELETE_FILE_ENDPOINT="http://${ip_address}:6007/v1/dataprep/delete_file"
+    export FRONTEND_SERVICE_IP=${host_ip}
+    export FRONTEND_SERVICE_PORT=5173
+    export BACKEND_SERVICE_NAME=chatqna
+    export BACKEND_SERVICE_IP=${host_ip}
+    export BACKEND_SERVICE_PORT=8888
+    export NGINX_PORT=80
 
     sed -i "s/backend_address/$ip_address/g" $WORKPATH/ui/svelte/.env