diff --git a/ChatQnA/chatqna.yaml b/ChatQnA/chatqna.yaml
deleted file mode 100644
index 0344b28317..0000000000
--- a/ChatQnA/chatqna.yaml
+++ /dev/null
@@ -1,72 +0,0 @@
-
-# Copyright (C) 2024 Intel Corporation
-# SPDX-License-Identifier: Apache-2.0
-
-opea_micro_services:
-  redis-vector-db:
-    host: ${REDIS_SERVICE_HOST_IP}
-    ports:
-      - "6379:6379"
-      - "8001:8001"
-    image: redis/redis-stack:7.2.0-v9
-  dataprep-redis-service:
-    host: ${DATAPREP_SERVICE_HOST_IP}
-    ports: ${DATAPREP_SERVICE_PORT}
-    image: opea/dataprep-redis:latest
-    environment:
-      REDIS_URL: ${REDIS_URL}
-      INDEX_NAME: ${INDEX_NAME}
-  tei-embedding-service:
-    host: ${TEI_EMBEDDING_SERVICE_IP}
-    ports: ${TEI_EMBEDDING_SERVICE_PORT}
-    image: ghcr.io/huggingface/tei-gaudi:1.5.0
-    volumes:
-      - "./data:/data"
-    runtime: habana
-    cap_add:
-      - SYS_NICE
-    ipc: host
-    environment:
-      HABANA_VISIBLE_DEVICES: all
-      OMPI_MCA_btl_vader_single_copy_mechanism: none
-    model-id: ${EMBEDDING_MODEL_ID}
-  retrieval:
-    host: ${RETRIEVER_SERVICE_HOST_IP}
-    ports: ${RETRIEVER_SERVICE_PORT}
-    image: opea/retriever-redis:latest
-    endpoint: /v1/retrieval
-  tgi-service:
-    host: ${TGI_SERVICE_IP}
-    ports: ${TGI_SERVICE_PORT}
-    image: ghcr.io/huggingface/tgi-gaudi:2.0.6
-    volumes:
-      - "./data:/data"
-    runtime: habana
-    cap_add:
-      - SYS_NICE
-    ipc: host
-    environment:
-      HUGGING_FACE_HUB_TOKEN: ${HUGGINGFACEHUB_API_TOKEN}
-      HABANA_VISIBLE_DEVICES: all
-      OMPI_MCA_btl_vader_single_copy_mechanism: none
-      ENABLE_HPU_GRAPH: true
-      LIMIT_HPU_GRAPH: true
-      USE_FLASH_ATTENTION: true
-      FLASH_ATTENTION_RECOMPUTE: true
-    model-id: ${LLM_MODEL_ID}
-  ui:
-    host: ${UI_SERVICE_HOST_IP}
-    ports:
-      - "5173:5173"
-    image: opea/chatqna-ui:latest
-    environment:
-      - CHAT_BASE_URL=${BACKEND_SERVICE_ENDPOINT}
-      - UPLOAD_FILE_BASE_URL=${DATAPREP_SERVICE_ENDPOINT}
-
-opea_mega_service:
-  host: ${MEGA_SERVICE_HOST_IP}
-  ports: ${MEGA_SERVICE_PORT}
-  image: opea/chatqna:latest
-  endpoint: /v1/chatqna
-  mega_flow:
-    - embedding >> retrieval >> reranking >> llm
diff --git a/ChatQnA/docker_compose/intel/hpu/gaudi/compose_vllm.yaml b/ChatQnA/docker_compose/intel/hpu/gaudi/compose_vllm.yaml
index 9b4002b5bf..50e2f00591 100644
--- a/ChatQnA/docker_compose/intel/hpu/gaudi/compose_vllm.yaml
+++ b/ChatQnA/docker_compose/intel/hpu/gaudi/compose_vllm.yaml
@@ -97,7 +97,7 @@ services:
     cap_add:
       - SYS_NICE
     ipc: host
-    command: --enforce-eager --model $LLM_MODEL_ID --tensor-parallel-size 1 --host 0.0.0.0 --port 80 --block-size 128 --max-num-seqs 256 --max-seq_len-to-capture 2048
+    command: --model $LLM_MODEL_ID --tensor-parallel-size 1 --host 0.0.0.0 --port 80 --block-size 128 --max-num-seqs 256 --max-seq_len-to-capture 2048
   chatqna-gaudi-backend-server:
     image: ${REGISTRY:-opea}/chatqna:${TAG:-latest}
     container_name: chatqna-gaudi-backend-server
diff --git a/ChatQnA/kubernetes/intel/hpu/gaudi/manifest/chatqna-vllm.yaml b/ChatQnA/kubernetes/intel/hpu/gaudi/manifest/chatqna-vllm.yaml
index 715db8976f..eabff7f865 100644
--- a/ChatQnA/kubernetes/intel/hpu/gaudi/manifest/chatqna-vllm.yaml
+++ b/ChatQnA/kubernetes/intel/hpu/gaudi/manifest/chatqna-vllm.yaml
@@ -1286,7 +1286,6 @@ spec:
               type: RuntimeDefault
           image: "opea/vllm-gaudi:latest"
           args:
-            - "--enforce-eager"
             - "--model"
             - "$(MODEL_ID)"
             - "--tensor-parallel-size"
diff --git a/ChatQnA/tests/test_compose_vllm_on_gaudi.sh b/ChatQnA/tests/test_compose_vllm_on_gaudi.sh
index 3b1efa8547..263a17a0d5 100644
--- a/ChatQnA/tests/test_compose_vllm_on_gaudi.sh
+++ b/ChatQnA/tests/test_compose_vllm_on_gaudi.sh
@@ -39,7 +39,7 @@ function start_services() {
     # Start Docker Containers
     docker compose -f compose_vllm.yaml up -d > ${LOG_PATH}/start_services_with_compose.log
     n=0
-    until [[ "$n" -ge 100 ]]; do
+    until [[ "$n" -ge 160 ]]; do
         echo "n=$n"
         docker logs vllm-gaudi-server > vllm_service_start.log
         if grep -q "Warmup finished" vllm_service_start.log; then
diff --git a/CodeGen/codegen.yaml b/CodeGen/codegen.yaml
deleted file mode 100644
index 8dc864f6f6..0000000000
--- a/CodeGen/codegen.yaml
+++ /dev/null
@@ -1,48 +0,0 @@
-
-# Copyright (C) 2024 Intel Corporation
-# SPDX-License-Identifier: Apache-2.0
-
-opea_micro_services:
-  tgi-service:
-    host: ${TGI_SERVICE_IP}
-    ports: ${TGI_SERVICE_PORT}
-    image: ghcr.io/huggingface/tgi-gaudi:2.0.6
-    volumes:
-      - "./data:/data"
-    runtime: habana
-    cap_add:
-      - SYS_NICE
-    ipc: host
-    environment:
-      HUGGINGFACEHUB_API_TOKEN: ${HUGGINGFACEHUB_API_TOKEN}
-      HABANA_VISIBLE_DEVICES: all
-      OMPI_MCA_btl_vader_single_copy_mechanism: none
-      HUGGING_FACE_HUB_TOKEN: ${HUGGINGFACEHUB_API_TOKEN}
-      ENABLE_HPU_GRAPH: true
-      LIMIT_HPU_GRAPH: true
-      USE_FLASH_ATTENTION: true
-      FLASH_ATTENTION_RECOMPUTE: true
-    model-id: ${LLM_MODEL_ID}
-  llm:
-    host: ${LLM_SERVICE_HOST_IP}
-    ports: ${LLM_SERVICE_PORT}
-    image: opea/llm-tgi:latest
-    endpoint: /v1/chat/completions
-    environment:
-      TGI_LLM_ENDPOINT: ${TGI_LLM_ENDPOINT}
-      HUGGINGFACEHUB_API_TOKEN: ${HUGGINGFACEHUB_API_TOKEN}
-  ui:
-    host: ${UI_SERVICE_HOST_IP}
-    ports:
-      - "5173:5173"
-    image: opea/codegen-ui:latest
-    environment:
-      - CHAT_BASE_URL=${BACKEND_SERVICE_ENDPOINT}
-
-opea_mega_service:
-  host: ${MEGA_SERVICE_HOST_IP}
-  ports: ${MEGA_SERVICE_PORT}
-  endpoint: /v1/codegen
-  image: opea/codegen:latest
-  mega_flow:
-    - llm
diff --git a/CodeTrans/codetrans.yaml b/CodeTrans/codetrans.yaml
deleted file mode 100644
index c362599788..0000000000
--- a/CodeTrans/codetrans.yaml
+++ /dev/null
@@ -1,48 +0,0 @@
-
-# Copyright (C) 2024 Intel Corporation
-# SPDX-License-Identifier: Apache-2.0
-
-opea_micro_services:
-  tgi-service:
-    host: ${TGI_SERVICE_IP}
-    ports: ${TGI_SERVICE_PORT}
-    image: ghcr.io/huggingface/tgi-gaudi:2.0.6
-    volumes:
-      - "./data:/data"
-    runtime: habana
-    cap_add:
-      - SYS_NICE
-    ipc: host
-    environment:
-      HUGGINGFACEHUB_API_TOKEN: ${HUGGINGFACEHUB_API_TOKEN}
-      HABANA_VISIBLE_DEVICES: all
-      OMPI_MCA_btl_vader_single_copy_mechanism: none
-      HUGGING_FACE_HUB_TOKEN: ${HUGGINGFACEHUB_API_TOKEN}
-      ENABLE_HPU_GRAPH: true
-      LIMIT_HPU_GRAPH: true
-      USE_FLASH_ATTENTION: true
-      FLASH_ATTENTION_RECOMPUTE: true
-    model-id: ${LLM_MODEL_ID}
-  llm:
-    host: ${LLM_SERVICE_HOST_IP}
-    ports: ${LLM_SERVICE_PORT}
-    image: opea/llm-tgi:latest
-    endpoint: /v1/chat/completions
-    environment:
-      TGI_LLM_ENDPOINT: ${TGI_LLM_ENDPOINT}
-      HUGGINGFACEHUB_API_TOKEN: ${HUGGINGFACEHUB_API_TOKEN}
-  ui:
-    host: ${UI_SERVICE_HOST_IP}
-    ports:
-      - "5173:5173"
-    image: opea/codetrans-ui:latest
-    environment:
-      - CHAT_BASE_URL=${BACKEND_SERVICE_ENDPOINT}
-
-opea_mega_service:
-  host: ${MEGA_SERVICE_HOST_IP}
-  ports: ${MEGA_SERVICE_PORT}
-  endpoint: /v1/codetrans
-  image: opea/codetrans:latest
-  mega_flow:
-    - llm
diff --git a/DocIndexRetriever/docker_compose/intel/cpu/xeon/README.md b/DocIndexRetriever/docker_compose/intel/cpu/xeon/README.md
index 58354babfa..3ad27345cb 100644
--- a/DocIndexRetriever/docker_compose/intel/cpu/xeon/README.md
+++ b/DocIndexRetriever/docker_compose/intel/cpu/xeon/README.md
@@ -62,6 +62,17 @@ cd GenAIExamples/DocIndexRetriever/intel/cpu/xoen/
 docker compose up -d
 ```
 
+Two types of DocRetriever pipeline are supported now: `DocRetriever with/without Rerank`. And the `DocRetriever without Rerank` pipeline (including Embedding and Retrieval) is offered for customers who expect to handle all retrieved documents by LLM, and require high performance of DocRetriever.
+In that case, start Docker Containers with compose_without_rerank.yaml
+
+```bash
+export host_ip="YOUR IP ADDR"
+export HUGGINGFACEHUB_API_TOKEN=${your_hf_api_token}
+export EMBEDDING_MODEL_ID="BAAI/bge-base-en-v1.5"
+cd GenAIExamples/DocIndexRetriever/intel/cpu/xoen/
+docker compose -f compose_without_rerank.yaml up -d
+```
+
 ## 4. Validation
 
 Add Knowledge Base via HTTP Links:
diff --git a/DocIndexRetriever/docker_compose/intel/cpu/xeon/compose_without_rerank.yaml b/DocIndexRetriever/docker_compose/intel/cpu/xeon/compose_without_rerank.yaml
new file mode 100644
index 0000000000..986fcb41af
--- /dev/null
+++ b/DocIndexRetriever/docker_compose/intel/cpu/xeon/compose_without_rerank.yaml
@@ -0,0 +1,102 @@
+# Copyright (C) 2024 Intel Corporation
+# SPDX-License-Identifier: Apache-2.0
+
+version: "3.8"
+
+services:
+  redis-vector-db:
+    image: redis/redis-stack:7.2.0-v9
+    container_name: redis-vector-db
+    ports:
+      - "6379:6379"
+      - "8001:8001"
+  dataprep-redis-service:
+    image: ${REGISTRY:-opea}/dataprep-redis:${TAG:-latest}
+    container_name: dataprep-redis-server
+    depends_on:
+      - redis-vector-db
+    ports:
+      - "6007:6007"
+      - "6008:6008"
+      - "6009:6009"
+    environment:
+      no_proxy: ${no_proxy}
+      http_proxy: ${http_proxy}
+      https_proxy: ${https_proxy}
+      REDIS_URL: redis://redis-vector-db:6379
+      REDIS_HOST: redis-vector-db
+      INDEX_NAME: ${INDEX_NAME:-rag-redis}
+      TEI_EMBEDDING_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
+    container_name: tei-embedding-server
+    ports:
+      - "6006:80"
+    volumes:
+      - "/home/ligang/models:/data"
+    shm_size: 1g
+    environment:
+      no_proxy: ${no_proxy}
+      http_proxy: ${http_proxy}
+      https_proxy: ${https_proxy}
+      HUGGINGFACEHUB_API_TOKEN: ${HUGGINGFACEHUB_API_TOKEN}
+    command: --model-id ${EMBEDDING_MODEL_ID} --auto-truncate
+  embedding:
+    image: ${REGISTRY:-opea}/embedding-tei:${TAG:-latest}
+    container_name: embedding-tei-server
+    ports:
+      - "6000:6000"
+    ipc: host
+    depends_on:
+      - tei-embedding-service
+    environment:
+      no_proxy: ${no_proxy}
+      http_proxy: ${http_proxy}
+      https_proxy: ${https_proxy}
+      HUGGINGFACEHUB_API_TOKEN: ${HUGGINGFACEHUB_API_TOKEN}
+      TEI_EMBEDDING_ENDPOINT: http://tei-embedding-service:80
+    restart: unless-stopped
+  retriever:
+    image: ${REGISTRY:-opea}/retriever-redis:${TAG:-latest}
+    container_name: retriever-redis-server
+    depends_on:
+      - redis-vector-db
+    ports:
+      - "7000:7000"
+    ipc: host
+    environment:
+      no_proxy: ${no_proxy}
+      http_proxy: ${http_proxy}
+      https_proxy: ${https_proxy}
+      REDIS_URL: redis://redis-vector-db:6379
+      INDEX_NAME: ${INDEX_NAME:-rag-redis}
+      HUGGINGFACEHUB_API_TOKEN: ${HUGGINGFACEHUB_API_TOKEN}
+      TEI_EMBEDDING_ENDPOINT: http://tei-embedding-service:80
+    restart: unless-stopped
+  doc-index-retriever-server:
+    image: ${REGISTRY:-opea}/doc-index-retriever:${TAG:-latest}
+    container_name: doc-index-retriever-server
+    depends_on:
+      - redis-vector-db
+      - tei-embedding-service
+      - embedding
+      - retriever
+    ports:
+      - "8889:8889"
+    environment:
+      no_proxy: ${no_proxy}
+      https_proxy: ${https_proxy}
+      http_proxy: ${http_proxy}
+      MEGA_SERVICE_HOST_IP: ${MEGA_SERVICE_HOST_IP:-0.0.0.0}
+      EMBEDDING_SERVICE_HOST_IP: embedding
+      EMBEDDING_SERVICE_PORT: ${EMBEDDING_SERVER_PORT:-6000}
+      RETRIEVER_SERVICE_HOST_IP: retriever
+      LOGFLAG: ${LOGFLAG}
+    ipc: host
+    restart: always
+    command: --without-rerank
+
+networks:
+  default:
+    driver: bridge
diff --git a/DocIndexRetriever/retrieval_tool.py b/DocIndexRetriever/retrieval_tool.py
index b902b7a20e..9581612a50 100644
--- a/DocIndexRetriever/retrieval_tool.py
+++ b/DocIndexRetriever/retrieval_tool.py
@@ -1,6 +1,7 @@
 # Copyright (C) 2024 Intel Corporation
 # SPDX-License-Identifier: Apache-2.0
 
+import argparse
 import asyncio
 import os
 from typing import Union
@@ -124,8 +125,37 @@ def start(self):
             output_datatype=Union[RerankedDoc, LLMParamsDoc],
         )
 
+    def add_remote_service_without_rerank(self):
+        embedding = MicroService(
+            name="embedding",
+            host=EMBEDDING_SERVICE_HOST_IP,
+            port=EMBEDDING_SERVICE_PORT,
+            endpoint="/v1/embeddings",
+            use_remote_service=True,
+            service_type=ServiceType.EMBEDDING,
+        )
+        retriever = MicroService(
+            name="retriever",
+            host=RETRIEVER_SERVICE_HOST_IP,
+            port=RETRIEVER_SERVICE_PORT,
+            endpoint="/v1/retrieval",
+            use_remote_service=True,
+            service_type=ServiceType.RETRIEVER,
+        )
+
+        self.megaservice.add(embedding).add(retriever)
+        self.megaservice.flow_to(embedding, retriever)
+
 
 if __name__ == "__main__":
+    parser = argparse.ArgumentParser()
+    parser.add_argument("--without-rerank", action="store_true")
+
+    args = parser.parse_args()
+
     chatqna = RetrievalToolService(port=MEGA_SERVICE_PORT)
-    chatqna.add_remote_service()
+    if args.without_rerank:
+        chatqna.add_remote_service_without_rerank()
+    else:
+        chatqna.add_remote_service()
     chatqna.start()
diff --git a/DocIndexRetriever/tests/test_compose_without_rerank_on_xeon.sh b/DocIndexRetriever/tests/test_compose_without_rerank_on_xeon.sh
new file mode 100644
index 0000000000..0298a8a55b
--- /dev/null
+++ b/DocIndexRetriever/tests/test_compose_without_rerank_on_xeon.sh
@@ -0,0 +1,147 @@
+#!/bin/bash
+# Copyright (C) 2024 Intel Corporation
+# SPDX-License-Identifier: Apache-2.0
+
+set -e
+IMAGE_REPO=${IMAGE_REPO:-"opea"}
+IMAGE_TAG=${IMAGE_TAG:-"latest"}
+echo "REGISTRY=IMAGE_REPO=${IMAGE_REPO}"
+echo "TAG=IMAGE_TAG=${IMAGE_TAG}"
+export REGISTRY=${IMAGE_REPO}
+export TAG=${IMAGE_TAG}
+
+WORKPATH=$(dirname "$PWD")
+LOG_PATH="$WORKPATH/tests"
+ip_address=$(hostname -I | awk '{print $1}')
+
+function build_docker_images() {
+    echo "Building Docker Images...."
+    cd $WORKPATH/docker_image_build
+    if [ ! -d "GenAIComps" ] ; then
+        echo "Cloning GenAIComps repository"
+        git clone https://github.com/opea-project/GenAIComps.git && cd GenAIComps && git checkout "${opea_branch:-"main"}" && cd ../
+    fi
+    service_list="dataprep-redis embedding-tei retriever-redis doc-index-retriever"
+    docker compose -f build.yaml build ${service_list} --no-cache > ${LOG_PATH}/docker_image_build.log
+
+    docker pull ghcr.io/huggingface/text-embeddings-inference:cpu-1.5
+    docker pull redis/redis-stack:7.2.0-v9
+    docker images && sleep 1s
+
+    echo "Docker images built!"
+}
+
+function start_services() {
+    echo "Starting Docker Services...."
+    cd $WORKPATH/docker_compose/intel/cpu/xeon
+    export EMBEDDING_MODEL_ID="BAAI/bge-base-en-v1.5"
+    export TEI_EMBEDDING_ENDPOINT="http://${ip_address}:6006"
+    export REDIS_URL="redis://${ip_address}:6379"
+    export INDEX_NAME="rag-redis"
+    export HUGGINGFACEHUB_API_TOKEN=${HUGGINGFACEHUB_API_TOKEN}
+    export MEGA_SERVICE_HOST_IP=${ip_address}
+    export EMBEDDING_SERVICE_HOST_IP=${ip_address}
+    export RETRIEVER_SERVICE_HOST_IP=${ip_address}
+
+    # Start Docker Containers
+    docker compose -f compose_without_rerank.yaml up -d
+    sleep 5m
+    echo "Docker services started!"
+}
+
+function validate() {
+    local CONTENT="$1"
+    local EXPECTED_RESULT="$2"
+    local SERVICE_NAME="$3"
+
+    if echo "$CONTENT" | grep -q "$EXPECTED_RESULT"; then
+        echo "[ $SERVICE_NAME ] Content is as expected: $CONTENT."
+        echo 0
+    else
+        echo "[ $SERVICE_NAME ] Content does not match the expected result: $CONTENT"
+        echo 1
+    fi
+}
+
+function validate_megaservice() {
+    echo "===========Ingest data=================="
+    local CONTENT=$(http_proxy="" curl -X POST "http://${ip_address}:6007/v1/dataprep" \
+     -H "Content-Type: multipart/form-data" \
+     -F 'link_list=["https://opea.dev/"]')
+    local EXIT_CODE=$(validate "$CONTENT" "Data preparation succeeded" "dataprep-redis-service-xeon")
+    echo "$EXIT_CODE"
+    local EXIT_CODE="${EXIT_CODE:0-1}"
+    echo "return value is $EXIT_CODE"
+    if [ "$EXIT_CODE" == "1" ]; then
+        docker logs dataprep-redis-server | tee -a ${LOG_PATH}/dataprep-redis-service-xeon.log
+        return 1
+    fi
+
+    # Curl the Mega Service
+    echo "================Testing retriever service: Text Request ================"
+    cd $WORKPATH/tests
+    local CONTENT=$(http_proxy="" curl http://${ip_address}:8889/v1/retrievaltool -X POST -H "Content-Type: application/json" -d '{
+     "text": "Explain the OPEA project?"
+    }')
+    # local CONTENT=$(python test.py --host_ip ${ip_address} --request_type text)
+    local EXIT_CODE=$(validate "$CONTENT" "OPEA" "doc-index-retriever-service-xeon")
+    echo "$EXIT_CODE"
+    local EXIT_CODE="${EXIT_CODE:0-1}"
+    echo "return value is $EXIT_CODE"
+    if [ "$EXIT_CODE" == "1" ]; then
+        echo "=============Embedding container log=================="
+        docker logs embedding-tei-server | tee -a ${LOG_PATH}/doc-index-retriever-service-xeon.log
+        echo "=============Retriever container log=================="
+        docker logs retriever-redis-server | tee -a ${LOG_PATH}/doc-index-retriever-service-xeon.log
+        echo "=============Doc-index-retriever container log=================="
+        docker logs doc-index-retriever-server | tee -a ${LOG_PATH}/doc-index-retriever-service-xeon.log
+        exit 1
+    fi
+
+    echo "================Testing retriever service: ChatCompletion Request================"
+    cd $WORKPATH/tests
+    local CONTENT=$(python test.py --host_ip ${ip_address} --request_type chat_completion)
+    local EXIT_CODE=$(validate "$CONTENT" "OPEA" "doc-index-retriever-service-xeon")
+    echo "$EXIT_CODE"
+    local EXIT_CODE="${EXIT_CODE:0-1}"
+    echo "return value is $EXIT_CODE"
+    if [ "$EXIT_CODE" == "1" ]; then
+        echo "=============Embedding container log=================="
+        docker logs embedding-tei-server | tee -a ${LOG_PATH}/doc-index-retriever-service-xeon.log
+        echo "=============Retriever container log=================="
+        docker logs retriever-redis-server | tee -a ${LOG_PATH}/doc-index-retriever-service-xeon.log
+        echo "=============Doc-index-retriever container log=================="
+        docker logs doc-index-retriever-server | tee -a ${LOG_PATH}/doc-index-retriever-service-xeon.log
+        exit 1
+    fi
+}
+
+function stop_docker() {
+    cd $WORKPATH/docker_compose/intel/cpu/xeon
+    container_list=$(cat compose.yaml | grep container_name | cut -d':' -f2)
+    for container_name in $container_list; do
+        cid=$(docker ps -aq --filter "name=$container_name")
+        echo "Stopping container $container_name"
+        if [[ ! -z "$cid" ]]; then docker rm $cid -f && sleep 1s; fi
+    done
+}
+
+function main() {
+
+    stop_docker
+    build_docker_images
+    echo "Dump current docker ps"
+    docker ps
+    start_time=$(date +%s)
+    start_services
+    end_time=$(date +%s)
+    duration=$((end_time-start_time))
+    echo "Mega service start duration is $duration s"
+    validate_megaservice
+
+    stop_docker
+    echo y | docker system prune
+
+}
+
+main
diff --git a/DocSum/docker_compose/intel/cpu/xeon/README.md b/DocSum/docker_compose/intel/cpu/xeon/README.md
index 82cbcf841b..212f5693dc 100644
--- a/DocSum/docker_compose/intel/cpu/xeon/README.md
+++ b/DocSum/docker_compose/intel/cpu/xeon/README.md
@@ -67,22 +67,22 @@ docker build -t opea/docsum:latest --build-arg https_proxy=$https_proxy --build-
 
 Several UI options are provided. If you need to work with multimedia documents, .doc, or .pdf files, suggested to use Gradio UI.
 
-#### Svelte UI
+#### Gradio UI
 
-Build the frontend Docker image via below command:
+Build the Gradio UI frontend Docker image using the following command:
 
 ```bash
 cd GenAIExamples/DocSum/ui
-docker build -t opea/docsum-ui:latest --build-arg https_proxy=$https_proxy --build-arg http_proxy=$http_proxy -f docker/Dockerfile .
+docker build -t opea/docsum-gradio-ui:latest --build-arg https_proxy=$https_proxy --build-arg http_proxy=$http_proxy -f docker/Dockerfile.gradio .
 ```
 
-#### Gradio UI
+#### Svelte UI
 
-Build the Gradio UI frontend Docker image using the following command:
+Build the frontend Docker image via below command:
 
 ```bash
 cd GenAIExamples/DocSum/ui
-docker build -t opea/docsum-gradio-ui:latest --build-arg https_proxy=$https_proxy --build-arg http_proxy=$http_proxy -f docker/Dockerfile.gradio .
+docker build -t opea/docsum-ui:latest --build-arg https_proxy=$https_proxy --build-arg http_proxy=$http_proxy -f docker/Dockerfile .
 ```
 
 #### React UI
diff --git a/DocSum/docker_compose/intel/cpu/xeon/compose.yaml b/DocSum/docker_compose/intel/cpu/xeon/compose.yaml
index 72332a9012..170cdc79b8 100644
--- a/DocSum/docker_compose/intel/cpu/xeon/compose.yaml
+++ b/DocSum/docker_compose/intel/cpu/xeon/compose.yaml
@@ -95,8 +95,8 @@ services:
     ipc: host
     restart: always
 
-  docsum-ui:
-    image: ${REGISTRY:-opea}/docsum-ui:${TAG:-latest}
+  docsum-gradio-ui:
+    image: ${REGISTRY:-opea}/docsum-gradio-ui:${TAG:-latest}
     container_name: docsum-xeon-ui-server
     depends_on:
       - docsum-xeon-backend-server
diff --git a/DocSum/docker_compose/intel/hpu/gaudi/README.md b/DocSum/docker_compose/intel/hpu/gaudi/README.md
index 172f24d67a..f9f3d6af58 100644
--- a/DocSum/docker_compose/intel/hpu/gaudi/README.md
+++ b/DocSum/docker_compose/intel/hpu/gaudi/README.md
@@ -51,22 +51,22 @@ docker build -t opea/docsum:latest --build-arg https_proxy=$https_proxy --build-
 
 Several UI options are provided. If you need to work with multimedia documents, .doc, or .pdf files, suggested to use Gradio UI.
 
-#### Svelte UI
+#### Gradio UI
 
-Build the frontend Docker image via below command:
+Build the Gradio UI frontend Docker image using the following command:
 
 ```bash
 cd GenAIExamples/DocSum/ui
-docker build -t opea/docsum-ui:latest --build-arg https_proxy=$https_proxy --build-arg http_proxy=$http_proxy -f docker/Dockerfile .
+docker build -t opea/docsum-gradio-ui:latest --build-arg https_proxy=$https_proxy --build-arg http_proxy=$http_proxy -f docker/Dockerfile.gradio .
 ```
 
-#### Gradio UI
+#### Svelte UI
 
-Build the Gradio UI frontend Docker image using the following command:
+Build the frontend Docker image via below command:
 
 ```bash
 cd GenAIExamples/DocSum/ui
-docker build -t opea/docsum-gradio-ui:latest --build-arg https_proxy=$https_proxy --build-arg http_proxy=$http_proxy -f docker/Dockerfile.gradio .
+docker build -t opea/docsum-ui:latest --build-arg https_proxy=$https_proxy --build-arg http_proxy=$http_proxy -f docker/Dockerfile .
 ```
 
 #### React UI
diff --git a/DocSum/docker_compose/intel/hpu/gaudi/compose.yaml b/DocSum/docker_compose/intel/hpu/gaudi/compose.yaml
index 39bb3d4777..2e8211fdf3 100644
--- a/DocSum/docker_compose/intel/hpu/gaudi/compose.yaml
+++ b/DocSum/docker_compose/intel/hpu/gaudi/compose.yaml
@@ -108,8 +108,8 @@ services:
     ipc: host
     restart: always
 
-  docsum-ui:
-    image: ${REGISTRY:-opea}/docsum-ui:${TAG:-latest}
+  docsum-gradio-ui:
+    image: ${REGISTRY:-opea}/docsum-gradio-ui:${TAG:-latest}
     container_name: docsum-gaudi-ui-server
     depends_on:
       - docsum-gaudi-backend-server
diff --git a/DocSum/tests/test_compose_on_gaudi.sh b/DocSum/tests/test_compose_on_gaudi.sh
index 7b9ff49260..b26bb7eab9 100644
--- a/DocSum/tests/test_compose_on_gaudi.sh
+++ b/DocSum/tests/test_compose_on_gaudi.sh
@@ -46,7 +46,7 @@ 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="docsum docsum-ui whisper dataprep-multimedia2text dataprep-audio2text dataprep-video2audio llm-docsum-tgi"
+    service_list="docsum docsum-gradio-ui whisper dataprep-multimedia2text dataprep-audio2text dataprep-video2audio llm-docsum-tgi"
     docker compose -f build.yaml build ${service_list} --no-cache > ${LOG_PATH}/docker_image_build.log
 
     docker pull ghcr.io/huggingface/tgi-gaudi:2.0.6
diff --git a/DocSum/tests/test_compose_on_xeon.sh b/DocSum/tests/test_compose_on_xeon.sh
index 60da44a7eb..2b32f4438a 100644
--- a/DocSum/tests/test_compose_on_xeon.sh
+++ b/DocSum/tests/test_compose_on_xeon.sh
@@ -45,7 +45,7 @@ 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="docsum docsum-ui whisper dataprep-multimedia2text dataprep-audio2text dataprep-video2audio llm-docsum-tgi"
+    service_list="docsum docsum-gradio-ui whisper dataprep-multimedia2text dataprep-audio2text dataprep-video2audio llm-docsum-tgi"
     docker compose -f build.yaml build ${service_list} --no-cache > ${LOG_PATH}/docker_image_build.log
 
     docker pull ghcr.io/huggingface/text-generation-inference:1.4
diff --git a/FaqGen/faqgen.yaml b/FaqGen/faqgen.yaml
deleted file mode 100644
index 5b924a38eb..0000000000
--- a/FaqGen/faqgen.yaml
+++ /dev/null
@@ -1,47 +0,0 @@
-
-# Copyright (C) 2024 Intel Corporation
-# SPDX-License-Identifier: Apache-2.0
-
-opea_micro_services:
-  tgi-service:
-    host: ${TGI_SERVICE_IP}
-    ports: ${TGI_SERVICE_PORT}
-    image: ghcr.io/huggingface/tgi-gaudi:2.0.6
-    volumes:
-      - "./data:/data"
-    runtime: habana
-    cap_add:
-      - SYS_NICE
-    ipc: host
-    environment:
-      HABANA_VISIBLE_DEVICES: all
-      OMPI_MCA_btl_vader_single_copy_mechanism: none
-      HUGGING_FACE_HUB_TOKEN: ${HUGGINGFACEHUB_API_TOKEN}
-      ENABLE_HPU_GRAPH: true
-      LIMIT_HPU_GRAPH: true
-      USE_FLASH_ATTENTION: true
-      FLASH_ATTENTION_RECOMPUTE: true
-    model-id: ${LLM_MODEL_ID}
-  llm:
-    host: ${LLM_SERVICE_HOST_IP}
-    ports: ${LLM_SERVICE_PORT}
-    image: opea/llm-tgi:latest
-    endpoint: /v1/chat/completions
-    environment:
-      TGI_LLM_ENDPOINT: ${TGI_LLM_ENDPOINT}
-      HUGGINGFACEHUB_API_TOKEN: ${HUGGINGFACEHUB_API_TOKEN}
-  ui:
-    host: ${UI_SERVICE_HOST_IP}
-    ports:
-      - "5173:5173"
-    image: opea/faqgen-ui:latest
-    environment:
-      - CHAT_BASE_URL=${BACKEND_SERVICE_ENDPOINT}
-
-opea_mega_service:
-  host: ${MEGA_SERVICE_HOST_IP}
-  ports: ${MEGA_SERVICE_PORT}
-  image: opea/faqgen:latest
-  endpoint: /v1/faqgen
-  mega_flow:
-    - llm
diff --git a/MultimodalQnA/docker_compose/intel/cpu/xeon/README.md b/MultimodalQnA/docker_compose/intel/cpu/xeon/README.md
index d0a1c7d279..dcd145bbd7 100644
--- a/MultimodalQnA/docker_compose/intel/cpu/xeon/README.md
+++ b/MultimodalQnA/docker_compose/intel/cpu/xeon/README.md
@@ -78,6 +78,9 @@ export https_proxy=${your_http_proxy}
 export EMBEDDER_PORT=6006
 export MMEI_EMBEDDING_ENDPOINT="http://${host_ip}:$EMBEDDER_PORT/v1/encode"
 export MM_EMBEDDING_PORT_MICROSERVICE=6000
+export ASR_ENDPOINT=http://$host_ip:7066
+export ASR_SERVICE_PORT=3001
+export ASR_SERVICE_ENDPOINT="http://${host_ip}:${ASR_SERVICE_PORT}/v1/audio/transcriptions"
 export REDIS_URL="redis://${host_ip}:6379"
 export REDIS_HOST=${host_ip}
 export INDEX_NAME="mm-rag-redis"
@@ -144,7 +147,21 @@ docker build --no-cache -t opea/lvm-llava-svc:latest --build-arg https_proxy=$ht
 docker build --no-cache -t opea/dataprep-multimodal-redis:latest --build-arg https_proxy=$https_proxy --build-arg http_proxy=$http_proxy -f comps/dataprep/multimodal/redis/langchain/Dockerfile .
 ```
 
-### 5. Build MegaService Docker Image
+### 5. Build asr images
+
+Build whisper server image
+
+```bash
+docker build --no-cache -t opea/whisper:latest --build-arg https_proxy=$https_proxy --build-arg http_proxy=$http_proxy -f comps/asr/whisper/dependency/Dockerfile .
+```
+
+Build asr image
+
+```bash
+docker build --no-cache -t opea/asr:latest --build-arg https_proxy=$https_proxy --build-arg http_proxy=$http_proxy -f comps/asr/whisper/Dockerfile .
+```
+
+### 6. Build MegaService Docker Image
 
 To construct the Mega Service, we utilize the [GenAIComps](https://github.com/opea-project/GenAIComps.git) microservice pipeline within the [multimodalqna.py](../../../../multimodalqna.py) Python script. Build MegaService Docker image via below command:
 
@@ -155,7 +172,7 @@ docker build --no-cache -t opea/multimodalqna:latest --build-arg https_proxy=$ht
 cd ../..
 ```
 
-### 6. Build UI Docker Image
+### 7. Build UI Docker Image
 
 Build frontend Docker image via below command:
 
@@ -165,16 +182,19 @@ docker build --no-cache -t opea/multimodalqna-ui:latest --build-arg https_proxy=
 cd ../../../
 ```
 
-Then run the command `docker images`, you will have the following 8 Docker Images:
+Then run the command `docker images`, you will have the following 11 Docker Images:
 
 1. `opea/dataprep-multimodal-redis:latest`
 2. `opea/lvm-llava-svc:latest`
 3. `opea/lvm-llava:latest`
 4. `opea/retriever-multimodal-redis:latest`
-5. `opea/embedding-multimodal:latest`
-6. `opea/embedding-multimodal-bridgetower:latest`
-7. `opea/multimodalqna:latest`
-8. `opea/multimodalqna-ui:latest`
+5. `opea/whisper:latest`
+6. `opea/asr:latest`
+7. `opea/redis-vector-db`
+8. `opea/embedding-multimodal:latest`
+9. `opea/embedding-multimodal-bridgetower:latest`
+10. `opea/multimodalqna:latest`
+11. `opea/multimodalqna-ui:latest`
 
 ## 🚀 Start Microservices
 
@@ -240,7 +260,16 @@ curl http://${host_ip}:7000/v1/multimodal_retrieval \
     -d "{\"text\":\"test\",\"embedding\":${your_embedding}}"
 ```
 
-4. lvm-llava
+4. asr
+
+```bash
+curl ${ASR_SERVICE_ENDPOINT} \
+    -X POST \
+    -H "Content-Type: application/json" \
+    -d '{"byte_str" : "UklGRigAAABXQVZFZm10IBIAAAABAAEARKwAAIhYAQACABAAAABkYXRhAgAAAAEA"}'
+```
+
+5. lvm-llava
 
 ```bash
 curl http://${host_ip}:${LLAVA_SERVER_PORT}/generate \
@@ -249,7 +278,7 @@ curl http://${host_ip}:${LLAVA_SERVER_PORT}/generate \
      -d '{"prompt":"Describe the image please.", "img_b64_str": "iVBORw0KGgoAAAANSUhEUgAAAAoAAAAKCAYAAACNMs+9AAAAFUlEQVR42mP8/5+hnoEIwDiqkL4KAcT9GO0U4BxoAAAAAElFTkSuQmCC"}'
 ```
 
-5. lvm-llava-svc
+6. lvm-llava-svc
 
 ```bash
 curl http://${host_ip}:9399/v1/lvm \
@@ -274,7 +303,7 @@ curl http://${host_ip}:9399/v1/lvm \
     -d '{"retrieved_docs": [], "initial_query": "What is this?", "top_n": 1, "metadata": [], "chat_template":"The caption of the image is: '\''{context}'\''. {question}"}'
 ```
 
-6. dataprep-multimodal-redis
+7. dataprep-multimodal-redis
 
 Download a sample video, image, and audio file and create a caption
 
@@ -348,7 +377,7 @@ curl -X POST \
     ${DATAPREP_DELETE_FILE_ENDPOINT}
 ```
 
-7. MegaService
+8. MegaService
 
 ```bash
 curl http://${host_ip}:8888/v1/multimodalqna \
@@ -357,6 +386,12 @@ curl http://${host_ip}:8888/v1/multimodalqna \
     -d '{"messages": "What is the revenue of Nike in 2023?"}'
 ```
 
+```bash
+curl http://${host_ip}:8888/v1/multimodalqna  \
+    -H "Content-Type: application/json"  \
+    -d '{"messages": [{"role": "user", "content": [{"type": "audio", "audio": "UklGRigAAABXQVZFZm10IBIAAAABAAEARKwAAIhYAQACABAAAABkYXRhAgAAAAEA"}]}]}'
+```
+
 ```bash
 curl http://${host_ip}:8888/v1/multimodalqna \
     -H "Content-Type: application/json" \
diff --git a/MultimodalQnA/docker_compose/intel/cpu/xeon/compose.yaml b/MultimodalQnA/docker_compose/intel/cpu/xeon/compose.yaml
index eece99da85..4f9900db72 100644
--- a/MultimodalQnA/docker_compose/intel/cpu/xeon/compose.yaml
+++ b/MultimodalQnA/docker_compose/intel/cpu/xeon/compose.yaml
@@ -2,6 +2,27 @@
 # SPDX-License-Identifier: Apache-2.0
 
 services:
+  whisper-service:
+    image: ${REGISTRY:-opea}/whisper:${TAG:-latest}
+    container_name: whisper-service
+    ports:
+      - "7066:7066"
+    ipc: host
+    environment:
+      no_proxy: ${no_proxy}
+      http_proxy: ${http_proxy}
+      https_proxy: ${https_proxy}
+    restart: unless-stopped
+  asr:
+    image: ${REGISTRY:-opea}/asr:${TAG:-latest}
+    container_name: asr-service
+    ports:
+      - "${ASR_SERVICE_PORT}:9099"
+    ipc: host
+    environment:
+      ASR_ENDPOINT: ${ASR_ENDPOINT}
+      ASR_SERVICE_PORT: ${ASR_SERVICE_PORT}
+      ASR_SERVICE_ENDPOINT: ${ASR_SERVICE_ENDPOINT}
   redis-vector-db:
     image: redis/redis-stack:7.2.0-v9
     container_name: redis-vector-db
@@ -102,6 +123,7 @@ services:
       - embedding-multimodal
       - retriever-multimodal-redis
       - lvm-llava-svc
+      - asr
     ports:
       - "8888:8888"
     environment:
@@ -113,6 +135,8 @@ services:
       MM_EMBEDDING_PORT_MICROSERVICE: ${MM_EMBEDDING_PORT_MICROSERVICE}
       MM_RETRIEVER_SERVICE_HOST_IP: ${MM_RETRIEVER_SERVICE_HOST_IP}
       LVM_SERVICE_HOST_IP: ${LVM_SERVICE_HOST_IP}
+      ASR_SERVICE_PORT: ${ASR_SERVICE_PORT}
+      ASR_SERVICE_ENDPOINT: ${ASR_SERVICE_ENDPOINT}
     ipc: host
     restart: always
   multimodalqna-ui:
diff --git a/MultimodalQnA/docker_compose/intel/cpu/xeon/set_env.sh b/MultimodalQnA/docker_compose/intel/cpu/xeon/set_env.sh
index c77300a132..b9c9e3d5ea 100755
--- a/MultimodalQnA/docker_compose/intel/cpu/xeon/set_env.sh
+++ b/MultimodalQnA/docker_compose/intel/cpu/xeon/set_env.sh
@@ -12,6 +12,9 @@ export https_proxy=${your_http_proxy}
 export EMBEDDER_PORT=6006
 export MMEI_EMBEDDING_ENDPOINT="http://${host_ip}:$EMBEDDER_PORT/v1/encode"
 export MM_EMBEDDING_PORT_MICROSERVICE=6000
+export ASR_ENDPOINT=http://$host_ip:7066
+export ASR_SERVICE_PORT=3001
+export ASR_SERVICE_ENDPOINT="http://${host_ip}:${ASR_SERVICE_PORT}/v1/audio/transcriptions"
 export REDIS_URL="redis://${host_ip}:6379"
 export REDIS_HOST=${host_ip}
 export INDEX_NAME="mm-rag-redis"
diff --git a/MultimodalQnA/docker_compose/intel/hpu/gaudi/README.md b/MultimodalQnA/docker_compose/intel/hpu/gaudi/README.md
index 9e7db70b79..67e95cb51b 100644
--- a/MultimodalQnA/docker_compose/intel/hpu/gaudi/README.md
+++ b/MultimodalQnA/docker_compose/intel/hpu/gaudi/README.md
@@ -37,6 +37,9 @@ export LVM_MODEL_ID="llava-hf/llava-v1.6-vicuna-13b-hf"
 export WHISPER_MODEL="base"
 export MM_EMBEDDING_SERVICE_HOST_IP=${host_ip}
 export MM_RETRIEVER_SERVICE_HOST_IP=${host_ip}
+export ASR_ENDPOINT=http://$host_ip:7066
+export ASR_SERVICE_PORT=3001
+export ASR_SERVICE_ENDPOINT="http://${host_ip}:${ASR_SERVICE_PORT}/v1/audio/transcriptions"
 export LVM_SERVICE_HOST_IP=${host_ip}
 export MEGA_SERVICE_HOST_IP=${host_ip}
 export BACKEND_SERVICE_ENDPOINT="http://${host_ip}:8888/v1/multimodalqna"
@@ -95,7 +98,21 @@ docker build --no-cache -t opea/lvm-tgi:latest --build-arg https_proxy=$https_pr
 docker build --no-cache -t opea/dataprep-multimodal-redis:latest --build-arg https_proxy=$https_proxy --build-arg http_proxy=$http_proxy -f comps/dataprep/multimodal/redis/langchain/Dockerfile .
 ```
 
-### 5. Build MegaService Docker Image
+### 5. Build asr images
+
+Build whisper server image
+
+```bash
+docker build --no-cache -t opea/whisper:latest --build-arg https_proxy=$https_proxy --build-arg http_proxy=$http_proxy -f comps/asr/whisper/dependency/Dockerfile .
+```
+
+Build asr image
+
+```bash
+docker build --no-cache -t opea/asr:latest --build-arg https_proxy=$https_proxy --build-arg http_proxy=$http_proxy -f comps/asr/whisper/Dockerfile .
+```
+
+### 6. Build MegaService Docker Image
 
 To construct the Mega Service, we utilize the [GenAIComps](https://github.com/opea-project/GenAIComps.git) microservice pipeline within the [multimodalqna.py](../../../../multimodalqna.py) Python script. Build MegaService Docker image via below command:
 
@@ -114,16 +131,19 @@ cd  GenAIExamples/MultimodalQnA/ui/
 docker build --no-cache -t opea/multimodalqna-ui:latest --build-arg https_proxy=$https_proxy --build-arg http_proxy=$http_proxy -f ./docker/Dockerfile .
 ```
 
-Then run the command `docker images`, you will have the following 8 Docker Images:
+Then run the command `docker images`, you will have the following 11 Docker Images:
 
 1. `opea/dataprep-multimodal-redis:latest`
 2. `opea/lvm-tgi:latest`
 3. `ghcr.io/huggingface/tgi-gaudi:2.0.6`
 4. `opea/retriever-multimodal-redis:latest`
-5. `opea/embedding-multimodal:latest`
-6. `opea/embedding-multimodal-bridgetower:latest`
-7. `opea/multimodalqna:latest`
-8. `opea/multimodalqna-ui:latest`
+5. `opea/whisper:latest`
+6. `opea/asr:latest`
+7. `opea/redis-vector-db`
+8. `opea/embedding-multimodal:latest`
+9. `opea/embedding-multimodal-bridgetower:latest`
+10. `opea/multimodalqna:latest`
+11. `opea/multimodalqna-ui:latest`
 
 ## 🚀 Start Microservices
 
@@ -189,7 +209,16 @@ curl http://${host_ip}:7000/v1/multimodal_retrieval \
     -d "{\"text\":\"test\",\"embedding\":${your_embedding}}"
 ```
 
-4. TGI LLaVA Gaudi Server
+4. asr
+
+```bash
+curl ${ASR_SERVICE_ENDPOINT} \
+    -X POST \
+    -H "Content-Type: application/json" \
+    -d '{"byte_str" : "UklGRigAAABXQVZFZm10IBIAAAABAAEARKwAAIhYAQACABAAAABkYXRhAgAAAAEA"}'
+```
+
+5. TGI LLaVA Gaudi Server
 
 ```bash
 curl http://${host_ip}:${LLAVA_SERVER_PORT}/generate \
@@ -198,7 +227,7 @@ curl http://${host_ip}:${LLAVA_SERVER_PORT}/generate \
     -H 'Content-Type: application/json'
 ```
 
-5. lvm-tgi
+6. lvm-tgi
 
 ```bash
 curl http://${host_ip}:9399/v1/lvm \
@@ -223,7 +252,7 @@ curl http://${host_ip}:9399/v1/lvm \
     -d '{"retrieved_docs": [], "initial_query": "What is this?", "top_n": 1, "metadata": [], "chat_template":"The caption of the image is: '\''{context}'\''. {question}"}'
 ```
 
-6. Multimodal Dataprep Microservice
+7. Multimodal Dataprep Microservice
 
 Download a sample video, image, and audio file and create a caption
 
@@ -297,7 +326,7 @@ curl -X POST \
     ${DATAPREP_DELETE_FILE_ENDPOINT}
 ```
 
-7. MegaService
+8. MegaService
 
 ```bash
 curl http://${host_ip}:8888/v1/multimodalqna \
diff --git a/MultimodalQnA/docker_compose/intel/hpu/gaudi/compose.yaml b/MultimodalQnA/docker_compose/intel/hpu/gaudi/compose.yaml
index ddaf2b09d1..87a6821c77 100644
--- a/MultimodalQnA/docker_compose/intel/hpu/gaudi/compose.yaml
+++ b/MultimodalQnA/docker_compose/intel/hpu/gaudi/compose.yaml
@@ -8,6 +8,27 @@ services:
     ports:
       - "6379:6379"
       - "8001:8001"
+  whisper-service:
+    image: ${REGISTRY:-opea}/whisper:${TAG:-latest}
+    container_name: whisper-service
+    ports:
+      - "7066:7066"
+    ipc: host
+    environment:
+      no_proxy: ${no_proxy}
+      http_proxy: ${http_proxy}
+      https_proxy: ${https_proxy}
+    restart: unless-stopped
+  asr:
+    image: ${REGISTRY:-opea}/asr:${TAG:-latest}
+    container_name: asr-service
+    ports:
+      - "${ASR_SERVICE_PORT}:9099"
+    ipc: host
+    environment:
+      ASR_ENDPOINT: ${ASR_ENDPOINT}
+      ASR_SERVICE_PORT: ${ASR_SERVICE_PORT}
+      ASR_SERVICE_ENDPOINT: ${ASR_SERVICE_ENDPOINT}
   dataprep-multimodal-redis:
     image: ${REGISTRY:-opea}/dataprep-multimodal-redis:${TAG:-latest}
     container_name: dataprep-multimodal-redis
@@ -119,6 +140,7 @@ services:
       - embedding-multimodal
       - retriever-multimodal-redis
       - lvm-tgi
+      - asr
     ports:
       - "8888:8888"
     environment:
@@ -130,6 +152,8 @@ services:
       MM_EMBEDDING_PORT_MICROSERVICE: ${MM_EMBEDDING_PORT_MICROSERVICE}
       MM_RETRIEVER_SERVICE_HOST_IP: ${MM_RETRIEVER_SERVICE_HOST_IP}
       LVM_SERVICE_HOST_IP: ${LVM_SERVICE_HOST_IP}
+      ASR_SERVICE_PORT: ${ASR_SERVICE_PORT}
+      ASR_SERVICE_ENDPOINT: ${ASR_SERVICE_ENDPOINT}
     ipc: host
     restart: always
   multimodalqna-ui:
diff --git a/MultimodalQnA/docker_compose/intel/hpu/gaudi/set_env.sh b/MultimodalQnA/docker_compose/intel/hpu/gaudi/set_env.sh
index aac8ebdf86..9ca2d6d9fc 100755
--- a/MultimodalQnA/docker_compose/intel/hpu/gaudi/set_env.sh
+++ b/MultimodalQnA/docker_compose/intel/hpu/gaudi/set_env.sh
@@ -12,6 +12,9 @@ export https_proxy=${your_http_proxy}
 export EMBEDDER_PORT=6006
 export MMEI_EMBEDDING_ENDPOINT="http://${host_ip}:$EMBEDDER_PORT/v1/encode"
 export MM_EMBEDDING_PORT_MICROSERVICE=6000
+export ASR_ENDPOINT=http://$host_ip:7066
+export ASR_SERVICE_PORT=3001
+export ASR_SERVICE_ENDPOINT="http://${host_ip}:${ASR_SERVICE_PORT}/v1/audio/transcriptions"
 export REDIS_URL="redis://${host_ip}:6379"
 export REDIS_HOST=${host_ip}
 export INDEX_NAME="mm-rag-redis"
diff --git a/MultimodalQnA/docker_image_build/build.yaml b/MultimodalQnA/docker_image_build/build.yaml
index 5b19aeffd9..0efa6a37e3 100644
--- a/MultimodalQnA/docker_image_build/build.yaml
+++ b/MultimodalQnA/docker_image_build/build.yaml
@@ -59,3 +59,15 @@ services:
       dockerfile: comps/dataprep/multimodal/redis/langchain/Dockerfile
     extends: multimodalqna
     image: ${REGISTRY:-opea}/dataprep-multimodal-redis:${TAG:-latest}
+  whisper:
+    build:
+      context: GenAIComps
+      dockerfile: comps/asr/whisper/dependency/Dockerfile
+    extends: multimodalqna
+    image: ${REGISTRY:-opea}/whisper:${TAG:-latest}
+  asr:
+    build:
+      context: GenAIComps
+      dockerfile: comps/asr/whisper/Dockerfile
+    extends: multimodalqna
+    image: ${REGISTRY:-opea}/asr:${TAG:-latest}
diff --git a/MultimodalQnA/multimodalqna.py b/MultimodalQnA/multimodalqna.py
index bf9b375749..87565a5b8a 100644
--- a/MultimodalQnA/multimodalqna.py
+++ b/MultimodalQnA/multimodalqna.py
@@ -2,6 +2,7 @@
 # SPDX-License-Identifier: Apache-2.0
 
 import base64
+import json
 import os
 from io import BytesIO
 
@@ -16,7 +17,7 @@
 )
 from comps.cores.proto.docarray import LLMParams
 from fastapi import Request
-from fastapi.responses import StreamingResponse
+from fastapi.responses import JSONResponse, StreamingResponse
 from PIL import Image
 
 MEGA_SERVICE_PORT = int(os.getenv("MEGA_SERVICE_PORT", 8888))
@@ -29,6 +30,9 @@
 
 
 class MultimodalQnAService(Gateway):
+    asr_port = int(os.getenv("ASR_SERVICE_PORT", 3001))
+    asr_endpoint = os.getenv("ASR_SERVICE_ENDPOINT", "http://0.0.0.0:{}/v1/audio/transcriptions".format(asr_port))
+
     def __init__(self, host="0.0.0.0", port=8000):
         self.host = host
         self.port = port
@@ -73,7 +77,10 @@ def add_remote_service(self):
     # this overrides _handle_message method of Gateway
     def _handle_message(self, messages):
         images = []
+        audios = []
+        b64_types = {}
         messages_dicts = []
+        decoded_audio_input = ""
         if isinstance(messages, str):
             prompt = messages
         else:
@@ -87,16 +94,26 @@ def _handle_message(self, messages):
                     system_prompt = message["content"]
                 elif msg_role == "user":
                     if type(message["content"]) == list:
+                        # separate each media type and store accordingly
                         text = ""
                         text_list = [item["text"] for item in message["content"] if item["type"] == "text"]
                         text += "\n".join(text_list)
                         image_list = [
                             item["image_url"]["url"] for item in message["content"] if item["type"] == "image_url"
                         ]
-                        if image_list:
-                            messages_dict[msg_role] = (text, image_list)
-                        else:
+                        audios = [item["audio"] for item in message["content"] if item["type"] == "audio"]
+                        if audios:
+                            # translate audio to text. From this point forward, audio is treated like text
+                            decoded_audio_input = self.convert_audio_to_text(audios)
+                            b64_types["audio"] = decoded_audio_input
+
+                        if text and not audios and not image_list:
                             messages_dict[msg_role] = text
+                        elif audios and not text and not image_list:
+                            messages_dict[msg_role] = decoded_audio_input
+                        else:
+                            messages_dict[msg_role] = (text, decoded_audio_input, image_list)
+
                     else:
                         messages_dict[msg_role] = message["content"]
                     messages_dicts.append(messages_dict)
@@ -108,55 +125,84 @@ def _handle_message(self, messages):
 
             if system_prompt:
                 prompt = system_prompt + "\n"
-            for messages_dict in messages_dicts:
-                for i, (role, message) in enumerate(messages_dict.items()):
+            for i, messages_dict in enumerate(messages_dicts):
+                for role, message in messages_dict.items():
                     if isinstance(message, tuple):
-                        text, image_list = message
+                        text, decoded_audio_input, image_list = message
                         if i == 0:
                             # do not add role for the very first message.
                             # this will be added by llava_server
                             if text:
                                 prompt += text + "\n"
+                            elif decoded_audio_input:
+                                prompt += decoded_audio_input + "\n"
                         else:
                             if text:
                                 prompt += role.upper() + ": " + text + "\n"
+                            elif decoded_audio_input:
+                                prompt += role.upper() + ": " + decoded_audio_input + "\n"
                             else:
                                 prompt += role.upper() + ":"
-                        for img in image_list:
-                            # URL
-                            if img.startswith("http://") or img.startswith("https://"):
-                                response = requests.get(img)
-                                image = Image.open(BytesIO(response.content)).convert("RGBA")
-                                image_bytes = BytesIO()
-                                image.save(image_bytes, format="PNG")
-                                img_b64_str = base64.b64encode(image_bytes.getvalue()).decode()
-                            # Local Path
-                            elif os.path.exists(img):
-                                image = Image.open(img).convert("RGBA")
-                                image_bytes = BytesIO()
-                                image.save(image_bytes, format="PNG")
-                                img_b64_str = base64.b64encode(image_bytes.getvalue()).decode()
-                            # Bytes
-                            else:
-                                img_b64_str = img
 
-                            images.append(img_b64_str)
-                    else:
+                        if image_list:
+                            for img in image_list:
+                                # URL
+                                if img.startswith("http://") or img.startswith("https://"):
+                                    response = requests.get(img)
+                                    image = Image.open(BytesIO(response.content)).convert("RGBA")
+                                    image_bytes = BytesIO()
+                                    image.save(image_bytes, format="PNG")
+                                    img_b64_str = base64.b64encode(image_bytes.getvalue()).decode()
+                                # Local Path
+                                elif os.path.exists(img):
+                                    image = Image.open(img).convert("RGBA")
+                                    image_bytes = BytesIO()
+                                    image.save(image_bytes, format="PNG")
+                                    img_b64_str = base64.b64encode(image_bytes.getvalue()).decode()
+                                # Bytes
+                                else:
+                                    img_b64_str = img
+
+                                images.append(img_b64_str)
+
+                    elif isinstance(message, str):
                         if i == 0:
                             # do not add role for the very first message.
                             # this will be added by llava_server
                             if message:
-                                prompt += role.upper() + ": " + message + "\n"
+                                prompt += message + "\n"
                         else:
                             if message:
                                 prompt += role.upper() + ": " + message + "\n"
                             else:
                                 prompt += role.upper() + ":"
+
         if images:
-            return prompt, images
+            b64_types["image"] = images
+
+        # If the query has multiple media types, return all types
+        if prompt and b64_types:
+            return prompt, b64_types
         else:
             return prompt
 
+    def convert_audio_to_text(self, audio):
+        # translate audio to text by passing in base64 encoded audio to ASR
+        if isinstance(audio, dict):
+            input_dict = {"byte_str": audio["audio"][0]}
+        else:
+            input_dict = {"byte_str": audio[0]}
+
+        response = requests.post(self.asr_endpoint, data=json.dumps(input_dict))
+
+        if response.status_code != 200:
+            return JSONResponse(
+                status_code=503, content={"message": "Unable to convert audio to text. {}".format(response.text)}
+            )
+
+        response = response.json()
+        return response["query"]
+
     async def handle_request(self, request: Request):
         data = await request.json()
         stream_opt = bool(data.get("stream", False))
@@ -165,16 +211,35 @@ async def handle_request(self, request: Request):
             stream_opt = False
         chat_request = ChatCompletionRequest.model_validate(data)
         # Multimodal RAG QnA With Videos has not yet accepts image as input during QnA.
-        prompt_and_image = self._handle_message(chat_request.messages)
-        if isinstance(prompt_and_image, tuple):
-            # print(f"This request include image, thus it is a follow-up query. Using lvm megaservice")
-            prompt, images = prompt_and_image
+        num_messages = len(data["messages"]) if isinstance(data["messages"], list) else 1
+        messages = self._handle_message(chat_request.messages)
+        decoded_audio_input = ""
+
+        if num_messages > 1:
+            # This is a follow up query, go to LVM
             cur_megaservice = self.lvm_megaservice
-            initial_inputs = {"prompt": prompt, "image": images[0]}
+            if isinstance(messages, tuple):
+                prompt, b64_types = messages
+                if "audio" in b64_types:
+                    # for metadata storage purposes
+                    decoded_audio_input = b64_types["audio"]
+                if "image" in b64_types:
+                    initial_inputs = {"prompt": prompt, "image": b64_types["image"][0]}
+                else:
+                    initial_inputs = {"prompt": prompt, "image": ""}
+            else:
+                prompt = messages
+                initial_inputs = {"prompt": prompt, "image": ""}
         else:
-            # print(f"This is the first query, requiring multimodal retrieval. Using multimodal rag megaservice")
-            prompt = prompt_and_image
+            # This is the first query. Ignore image input
             cur_megaservice = self.megaservice
+            if isinstance(messages, tuple):
+                prompt, b64_types = messages
+                if "audio" in b64_types:
+                    # for metadata storage purposes
+                    decoded_audio_input = b64_types["audio"]
+            else:
+                prompt = messages
             initial_inputs = {"text": prompt}
 
         parameters = LLMParams(
@@ -207,18 +272,24 @@ async def handle_request(self, request: Request):
         if "text" in result_dict[last_node].keys():
             response = result_dict[last_node]["text"]
         else:
-            # text in not response message
+            # text is not in response message
             # something wrong, for example due to empty retrieval results
             if "detail" in result_dict[last_node].keys():
                 response = result_dict[last_node]["detail"]
             else:
-                response = "The server fail to generate answer to your query!"
+                response = "The server failed to generate an answer to your query!"
         if "metadata" in result_dict[last_node].keys():
             # from retrieval results
             metadata = result_dict[last_node]["metadata"]
+            if decoded_audio_input:
+                metadata["audio"] = decoded_audio_input
         else:
             # follow-up question, no retrieval
-            metadata = None
+            if decoded_audio_input:
+                metadata = {"audio": decoded_audio_input}
+            else:
+                metadata = None
+
         choices = []
         usage = UsageInfo()
         choices.append(
diff --git a/MultimodalQnA/tests/test_compose_on_gaudi.sh b/MultimodalQnA/tests/test_compose_on_gaudi.sh
index 5ac1228dbf..0c522dd08f 100644
--- a/MultimodalQnA/tests/test_compose_on_gaudi.sh
+++ b/MultimodalQnA/tests/test_compose_on_gaudi.sh
@@ -22,7 +22,7 @@ function build_docker_images() {
     cd $WORKPATH/docker_image_build
     git clone https://github.com/opea-project/GenAIComps.git && cd GenAIComps && git checkout "${opea_branch:-"main"}" && cd ../
     echo "Build all the images with --no-cache, check docker_image_build.log for details..."
-    service_list="multimodalqna multimodalqna-ui embedding-multimodal-bridgetower embedding-multimodal retriever-multimodal-redis lvm-tgi dataprep-multimodal-redis"
+    service_list="multimodalqna multimodalqna-ui embedding-multimodal-bridgetower embedding-multimodal retriever-multimodal-redis lvm-tgi dataprep-multimodal-redis whisper asr"
     docker compose -f build.yaml build ${service_list} --no-cache > ${LOG_PATH}/docker_image_build.log
 
     docker pull ghcr.io/huggingface/tgi-gaudi:2.0.6
@@ -35,6 +35,9 @@ function setup_env() {
     export EMBEDDER_PORT=6006
     export MMEI_EMBEDDING_ENDPOINT="http://${host_ip}:$EMBEDDER_PORT/v1/encode"
     export MM_EMBEDDING_PORT_MICROSERVICE=6000
+    export ASR_ENDPOINT=http://$host_ip:7066
+    export ASR_SERVICE_PORT=3001
+    export ASR_SERVICE_ENDPOINT="http://${host_ip}:${ASR_SERVICE_PORT}/v1/audio/transcriptions"
     export REDIS_URL="redis://${host_ip}:6379"
     export REDIS_HOST=${host_ip}
     export INDEX_NAME="mm-rag-redis"
@@ -239,13 +242,29 @@ function validate_megaservice() {
         "multimodalqna-backend-server" \
         '{"messages": "What is the revenue of Nike in 2023?"}'
 
+    echo "Validate megaservice with first audio query"
+    validate_service \
+        "http://${host_ip}:8888/v1/multimodalqna" \
+        '"time_of_frame_ms":' \
+        "multimodalqna" \
+        "multimodalqna-backend-server" \
+        '{"messages": [{"role": "user", "content": [{"type": "audio", "audio": "UklGRigAAABXQVZFZm10IBIAAAABAAEARKwAAIhYAQACABAAAABkYXRhAgAAAAEA"}]}]}'
+
     echo "Validate megaservice with follow-up query"
     validate_service \
         "http://${host_ip}:8888/v1/multimodalqna" \
         '"content":"' \
         "multimodalqna" \
         "multimodalqna-backend-server" \
-        '{"messages": [{"role": "user", "content": [{"type": "text", "text": "hello, "}, {"type": "image_url", "image_url": {"url": "https://www.ilankelman.org/stopsigns/australia.jpg"}}]}, {"role": "assistant", "content": "opea project! "}, {"role": "user", "content": "chao, "}], "max_tokens": 10}'
+        '{"messages": [{"role": "user", "content": [{"type": "audio", "audio": "UklGRigAAABXQVZFZm10IBIAAAABAAEARKwAAIhYAQACABAAAABkYXRhAgAAAAEA"}, {"type": "image_url", "image_url": {"url": "https://www.ilankelman.org/stopsigns/australia.jpg"}}]}, {"role": "assistant", "content": "opea project! "}, {"role": "user", "content": [{"type": "text", "text": "goodbye"}]}]}'
+
+    echo "Validate megaservice with multiple text queries"
+    validate_service \
+        "http://${host_ip}:8888/v1/multimodalqna" \
+        '"content":"' \
+        "multimodalqna" \
+        "multimodalqna-backend-server" \
+        '{"messages": [{"role": "user", "content": [{"type": "text", "text": "hello, "}]}, {"role": "assistant", "content": "opea project! "}, {"role": "user", "content": [{"type": "text", "text": "goodbye"}]}]}'
 
 }
 
diff --git a/MultimodalQnA/tests/test_compose_on_xeon.sh b/MultimodalQnA/tests/test_compose_on_xeon.sh
index 7d3ab0faee..0475272206 100644
--- a/MultimodalQnA/tests/test_compose_on_xeon.sh
+++ b/MultimodalQnA/tests/test_compose_on_xeon.sh
@@ -21,9 +21,8 @@ export caption_fn="apple.txt"
 function build_docker_images() {
     cd $WORKPATH/docker_image_build
     git clone https://github.com/opea-project/GenAIComps.git && cd GenAIComps && git checkout "${opea_branch:-"main"}" && cd ../
-
     echo "Build all the images with --no-cache, check docker_image_build.log for details..."
-    service_list="multimodalqna multimodalqna-ui embedding-multimodal-bridgetower embedding-multimodal retriever-multimodal-redis lvm-llava lvm-llava-svc dataprep-multimodal-redis"
+    service_list="multimodalqna multimodalqna-ui embedding-multimodal-bridgetower embedding-multimodal retriever-multimodal-redis lvm-llava lvm-llava-svc dataprep-multimodal-redis whisper asr"
     docker compose -f build.yaml build ${service_list} --no-cache > ${LOG_PATH}/docker_image_build.log
 
     docker images && sleep 1m
@@ -34,6 +33,9 @@ function setup_env() {
     export EMBEDDER_PORT=6006
     export MMEI_EMBEDDING_ENDPOINT="http://${host_ip}:$EMBEDDER_PORT/v1/encode"
     export MM_EMBEDDING_PORT_MICROSERVICE=6000
+    export ASR_ENDPOINT=http://$host_ip:7066
+    export ASR_SERVICE_PORT=3001
+    export ASR_SERVICE_ENDPOINT="http://${host_ip}:${ASR_SERVICE_PORT}/v1/audio/transcriptions"
     export REDIS_URL="redis://${host_ip}:6379"
     export REDIS_HOST=${host_ip}
     export INDEX_NAME="mm-rag-redis"
@@ -238,14 +240,29 @@ function validate_megaservice() {
         "multimodalqna-backend-server" \
         '{"messages": "What is the revenue of Nike in 2023?"}'
 
+    echo "Validate megaservice with first audio query"
+    validate_service \
+        "http://${host_ip}:8888/v1/multimodalqna" \
+        '"time_of_frame_ms":' \
+        "multimodalqna" \
+        "multimodalqna-backend-server" \
+        '{"messages": [{"role": "user", "content": [{"type": "audio", "audio": "UklGRigAAABXQVZFZm10IBIAAAABAAEARKwAAIhYAQACABAAAABkYXRhAgAAAAEA"}]}]}'
+
     echo "Validate megaservice with follow-up query"
     validate_service \
         "http://${host_ip}:8888/v1/multimodalqna" \
         '"content":"' \
         "multimodalqna" \
         "multimodalqna-backend-server" \
-        '{"messages": [{"role": "user", "content": [{"type": "text", "text": "hello, "}, {"type": "image_url", "image_url": {"url": "https://www.ilankelman.org/stopsigns/australia.jpg"}}]}, {"role": "assistant", "content": "opea project! "}, {"role": "user", "content": "chao, "}], "max_tokens": 10}'
+        '{"messages": [{"role": "user", "content": [{"type": "audio", "audio": "UklGRigAAABXQVZFZm10IBIAAAABAAEARKwAAIhYAQACABAAAABkYXRhAgAAAAEA"}, {"type": "image_url", "image_url": {"url": "https://www.ilankelman.org/stopsigns/australia.jpg"}}]}, {"role": "assistant", "content": "opea project! "}, {"role": "user", "content": [{"type": "text", "text": "goodbye"}]}]}'
 
+    echo "Validate megaservice with multiple text queries"
+    validate_service \
+        "http://${host_ip}:8888/v1/multimodalqna" \
+        '"content":"' \
+        "multimodalqna" \
+        "multimodalqna-backend-server" \
+        '{"messages": [{"role": "user", "content": [{"type": "text", "text": "hello, "}]}, {"role": "assistant", "content": "opea project! "}, {"role": "user", "content": [{"type": "text", "text": "goodbye"}]}]}'
 }
 
 function validate_delete {
diff --git a/MultimodalQnA/ui/gradio/conversation.py b/MultimodalQnA/ui/gradio/conversation.py
index 3057e9879d..f080d7a154 100644
--- a/MultimodalQnA/ui/gradio/conversation.py
+++ b/MultimodalQnA/ui/gradio/conversation.py
@@ -5,7 +5,7 @@
 from enum import Enum, auto
 from typing import List
 
-from utils import get_b64_frame_from_timestamp
+from utils import convert_audio_to_base64, get_b64_frame_from_timestamp
 
 
 class SeparatorStyle(Enum):
@@ -31,6 +31,7 @@ class Conversation:
     skip_next: bool = False
     split_video: str = None
     image: str = None
+    audio_query_file: str = None
 
     def _template_caption(self):
         out = ""
@@ -41,31 +42,32 @@ def _template_caption(self):
     def get_prompt(self):
         messages = self.messages
         if len(messages) > 1 and messages[1][1] is None:
-            # Need to do RAG. prompt is the query only
-            ret = messages[0][1]
+            # Need to do RAG. If the query is text, prompt is the query only
+            if self.audio_query_file:
+                ret = [{"role": "user", "content": [{"type": "audio", "audio": self.get_b64_audio_query()}]}]
+            else:
+                ret = messages[0][1]
         else:
             # No need to do RAG. Thus, prompt of chatcompletion format
             conv_dict = []
             if self.sep_style == SeparatorStyle.SINGLE:
                 for i, (role, message) in enumerate(messages):
                     if message:
-                        if i != 0:
-                            dic = {"role": role, "content": message}
+                        dic = {"role": role}
+                        if self.audio_query_file:
+                            content = [{"type": "audio", "audio": self.get_b64_audio_query()}]
                         else:
-                            dic = {"role": role}
-                            if self.time_of_frame_ms and self.video_file:
-                                content = [{"type": "text", "text": message}]
-                                if self.base64_frame:
-                                    base64_frame = self.base64_frame
-                                else:
-                                    base64_frame = get_b64_frame_from_timestamp(self.video_file, self.time_of_frame_ms)
-                                    self.base64_frame = base64_frame
-                                if base64_frame is None:
-                                    base64_frame = ""
-                                content.append({"type": "image_url", "image_url": {"url": base64_frame}})
-                            else:
-                                content = message
-                            dic["content"] = content
+                            content = [{"type": "text", "text": message}]
+                        if i == 0 and self.time_of_frame_ms and self.video_file:
+                            base64_frame = (
+                                self.base64_frame
+                                if self.base64_frame
+                                else get_b64_frame_from_timestamp(self.video_file, self.time_of_frame_ms)
+                            )
+                            if base64_frame is None:
+                                base64_frame = ""
+                            content.append({"type": "image_url", "image_url": {"url": base64_frame}})
+                        dic["content"] = content
                         conv_dict.append(dic)
             else:
                 raise ValueError(f"Invalid style: {self.sep_style}")
@@ -83,6 +85,12 @@ def get_b64_image(self):
             b64_img = get_b64_frame_from_timestamp(video_file, time_of_frame_ms)
         return b64_img
 
+    def get_b64_audio_query(self):
+        b64_audio = None
+        if self.audio_query_file:
+            b64_audio = convert_audio_to_base64(self.audio_query_file)
+        return b64_audio
+
     def to_gradio_chatbot(self):
         ret = []
         for i, (role, msg) in enumerate(self.messages[self.offset :]):
@@ -141,6 +149,7 @@ def dict(self):
             "base64_frame": self.base64_frame,
             "split_video": self.split_video,
             "image": self.image,
+            "audio_query_file": self.audio_query_file,
         }
 
 
@@ -157,4 +166,5 @@ def dict(self):
     base64_frame=None,
     split_video=None,
     image=None,
+    audio_query_file=None,
 )
diff --git a/MultimodalQnA/ui/gradio/multimodalqna_ui_gradio.py b/MultimodalQnA/ui/gradio/multimodalqna_ui_gradio.py
index ec6a033ca8..28d3534be5 100644
--- a/MultimodalQnA/ui/gradio/multimodalqna_ui_gradio.py
+++ b/MultimodalQnA/ui/gradio/multimodalqna_ui_gradio.py
@@ -16,6 +16,7 @@
 from utils import build_logger, make_temp_image, moderation_msg, server_error_msg, split_video
 
 logger = build_logger("gradio_web_server", "gradio_web_server.log")
+logflag = os.getenv("LOGFLAG", False)
 
 headers = {"Content-Type": "application/json"}
 
@@ -50,21 +51,28 @@ def clear_history(state, request: gr.Request):
     if state.image and os.path.exists(state.image):
         os.remove(state.image)
     state = multimodalqna_conv.copy()
-    return (state, state.to_gradio_chatbot(), None, None, None) + (disable_btn,) * 1
+    return (state, state.to_gradio_chatbot(), None, None, None, None) + (disable_btn,) * 1
 
 
-def add_text(state, text, request: gr.Request):
+def add_text(state, text, audio, request: gr.Request):
     logger.info(f"add_text. ip: {request.client.host}. len: {len(text)}")
-    if len(text) <= 0:
+    if audio:
+        state.audio_query_file = audio
+        state.append_message(state.roles[0], "--input placeholder--")
+        state.append_message(state.roles[1], None)
+        state.skip_next = False
+        return (state, state.to_gradio_chatbot(), None, None) + (disable_btn,) * 1
+    elif len(text) <= 0:
         state.skip_next = True
-        return (state, state.to_gradio_chatbot(), None) + (no_change_btn,) * 1
+        return (state, state.to_gradio_chatbot(), None, None) + (no_change_btn,) * 1
 
     text = text[:2000]  # Hard cut-off
 
     state.append_message(state.roles[0], text)
     state.append_message(state.roles[1], None)
     state.skip_next = False
-    return (state, state.to_gradio_chatbot(), None) + (disable_btn,) * 1
+
+    return (state, state.to_gradio_chatbot(), None, None) + (disable_btn,) * 1
 
 
 def http_bot(state, request: gr.Request):
@@ -72,6 +80,7 @@ def http_bot(state, request: gr.Request):
     logger.info(f"http_bot. ip: {request.client.host}")
     url = gateway_addr
     is_very_first_query = False
+    is_audio_query = state.audio_query_file is not None
     if state.skip_next:
         # This generate call is skipped due to invalid inputs
         path_to_sub_videos = state.get_path_to_subvideos()
@@ -84,13 +93,13 @@ def http_bot(state, request: gr.Request):
         new_state = multimodalqna_conv.copy()
         new_state.append_message(new_state.roles[0], state.messages[-2][1])
         new_state.append_message(new_state.roles[1], None)
+        new_state.audio_query_file = state.audio_query_file
         state = new_state
 
     # Construct prompt
     prompt = state.get_prompt()
 
     # Make requests
-
     pload = {
         "messages": prompt,
     }
@@ -99,6 +108,7 @@ def http_bot(state, request: gr.Request):
     logger.info(f"==== url request ====\n{gateway_addr}")
 
     state.messages[-1][-1] = "▌"
+
     yield (state, state.to_gradio_chatbot(), state.split_video, state.image) + (disable_btn,) * 1
 
     try:
@@ -108,8 +118,9 @@ def http_bot(state, request: gr.Request):
             json=pload,
             timeout=100,
         )
-        print(response.status_code)
-        print(response.json())
+        logger.info(response.status_code)
+        if logflag:
+            logger.info(response.json())
 
         if response.status_code == 200:
             response = response.json()
@@ -152,6 +163,11 @@ def http_bot(state, request: gr.Request):
         return
 
     state.messages[-1][-1] = message
+
+    if is_audio_query:
+        state.messages[-2][-1] = metadata.get("audio", "--transcribed audio not available--")
+        state.audio_query_file = None
+
     yield (
         state,
         state.to_gradio_chatbot(),
@@ -188,10 +204,11 @@ def ingest_gen_transcript(filepath, filetype, request: gr.Request):
         "files": open(dest, "rb"),
     }
     response = requests.post(dataprep_gen_transcript_addr, headers=headers, files=files)
-    print(response.status_code)
+    logger.info(response.status_code)
     if response.status_code == 200:
         response = response.json()
-        print(response)
+        if logflag:
+            logger.info(response)
         yield (gr.Textbox(visible=True, value=f"The {filetype} ingestion is done. Saving your uploaded {filetype}..."))
         time.sleep(2)
         fn_no_ext = Path(dest).stem
@@ -242,10 +259,11 @@ def ingest_gen_caption(filepath, filetype, request: gr.Request):
         "files": open(dest, "rb"),
     }
     response = requests.post(dataprep_gen_caption_addr, headers=headers, files=files)
-    print(response.status_code)
+    logger.info(response.status_code)
     if response.status_code == 200:
         response = response.json()
-        print(response)
+        if logflag:
+            logger.info(response)
         yield (gr.Textbox(visible=True, value=f"The {filetype} ingestion is done. Saving your uploaded {filetype}..."))
         time.sleep(2)
         fn_no_ext = Path(dest).stem
@@ -299,10 +317,11 @@ def ingest_with_text(filepath, text, request: gr.Request):
         response = requests.post(dataprep_ingest_addr, headers=headers, files=files)
     finally:
         os.remove(text_dest)
-    print(response.status_code)
+    logger.info(response.status_code)
     if response.status_code == 200:
         response = response.json()
-        print(response)
+        if logflag:
+            logger.info(response)
         yield (gr.Textbox(visible=True, value="Image ingestion is done. Saving your uploaded image..."))
         time.sleep(2)
         fn_no_ext = Path(dest).stem
@@ -436,21 +455,26 @@ def select_upload_type(choice, request: gr.Request):
 with gr.Blocks() as qna:
     state = gr.State(multimodalqna_conv.copy())
     with gr.Row():
-        with gr.Column(scale=4):
+        with gr.Column(scale=2):
             video = gr.Video(height=512, width=512, elem_id="video", visible=True, label="Media")
             image = gr.Image(height=512, width=512, elem_id="image", visible=False, label="Media")
-        with gr.Column(scale=7):
+        with gr.Column(scale=9):
             chatbot = gr.Chatbot(elem_id="chatbot", label="MultimodalQnA Chatbot", height=390)
             with gr.Row():
-                with gr.Column(scale=6):
-                    # textbox.render()
-                    textbox = gr.Textbox(
-                        # show_label=False,
-                        # container=False,
-                        label="Query",
-                        info="Enter a text query below",
-                        # submit_btn=False,
-                    )
+                with gr.Column(scale=8):
+                    with gr.Tabs():
+                        with gr.TabItem("Text Query"):
+                            textbox = gr.Textbox(
+                                show_label=False,
+                                container=True,
+                            )
+                        with gr.TabItem("Audio Query"):
+                            audio = gr.Audio(
+                                type="filepath",
+                                sources=["microphone", "upload"],
+                                show_label=False,
+                                container=False,
+                            )
                 with gr.Column(scale=1, min_width=100):
                     with gr.Row():
                         submit_btn = gr.Button(value="Send", variant="primary", interactive=True)
@@ -462,13 +486,13 @@ def select_upload_type(choice, request: gr.Request):
         [
             state,
         ],
-        [state, chatbot, textbox, video, image, clear_btn],
+        [state, chatbot, textbox, audio, video, image, clear_btn],
     )
 
     submit_btn.click(
         add_text,
-        [state, textbox],
-        [state, chatbot, textbox, clear_btn],
+        [state, textbox, audio],
+        [state, chatbot, textbox, audio, clear_btn],
     ).then(
         http_bot,
         [
diff --git a/MultimodalQnA/ui/gradio/utils.py b/MultimodalQnA/ui/gradio/utils.py
index 7a730a7ed4..3d7be10118 100644
--- a/MultimodalQnA/ui/gradio/utils.py
+++ b/MultimodalQnA/ui/gradio/utils.py
@@ -163,7 +163,7 @@ def delete_split_video(video_path):
 
 
 def convert_img_to_base64(image):
-    "Convert image to base64 string"
+    """Convert image to base64 string."""
     _, buffer = cv2.imencode(".png", image)
     encoded_string = base64.b64encode(buffer)
     return encoded_string.decode("utf-8")
@@ -180,3 +180,9 @@ def get_b64_frame_from_timestamp(video_path, timestamp_in_ms, maintain_aspect_ra
         b64_img_str = convert_img_to_base64(frame)
         return b64_img_str
     return None
+
+
+def convert_audio_to_base64(audio_path):
+    """Convert .wav file to base64 string."""
+    encoded_string = base64.b64encode(open(audio_path, "rb").read())
+    return encoded_string.decode("utf-8")
diff --git a/Translation/translation.yaml b/Translation/translation.yaml
deleted file mode 100644
index f3a07da966..0000000000
--- a/Translation/translation.yaml
+++ /dev/null
@@ -1,54 +0,0 @@
-
-# Copyright (C) 2024 Intel Corporation
-# SPDX-License-Identifier: Apache-2.0
-
-opea_micro_services:
-  tgi-service:
-    host: ${TGI_SERVICE_IP}
-    ports: ${TGI_SERVICE_PORT}
-    image: ghcr.io/huggingface/tgi-gaudi:2.0.6
-    volumes:
-      - "./data:/data"
-    runtime: habana
-    cap_add:
-      - SYS_NICE
-    ipc: host
-    environment:
-      no_proxy: ${no_proxy}
-      http_proxy: ${http_proxy}
-      https_proxy: ${https_proxy}
-      HUGGINGFACEHUB_API_TOKEN: ${HUGGINGFACEHUB_API_TOKEN}
-      HABANA_VISIBLE_DEVICES: all
-      OMPI_MCA_btl_vader_single_copy_mechanism: none
-      HUGGING_FACE_HUB_TOKEN: ${HUGGINGFACEHUB_API_TOKEN}
-      ENABLE_HPU_GRAPH: true
-      LIMIT_HPU_GRAPH: true
-      USE_FLASH_ATTENTION: true
-      FLASH_ATTENTION_RECOMPUTE: true
-    model-id: ${LLM_MODEL_ID}
-  llm:
-    host: ${LLM_SERVICE_HOST_IP}
-    ports: ${LLM_SERVICE_PORT}
-    image: opea/llm-tgi:latest
-    endpoint: /v1/chat/completions
-    environment:
-      no_proxy: ${no_proxy}
-      http_proxy: ${http_proxy}
-      https_proxy: ${https_proxy}
-      TGI_LLM_ENDPOINT: ${TGI_LLM_ENDPOINT}
-      HUGGINGFACEHUB_API_TOKEN: ${HUGGINGFACEHUB_API_TOKEN}
-  ui:
-    host: ${UI_SERVICE_HOST_IP}
-    ports:
-      - "5173:5173"
-    image: opea/translation-ui:latest
-    environment:
-      - CHAT_BASE_URL=${BACKEND_SERVICE_ENDPOINT}
-
-opea_mega_service:
-  host: ${MEGA_SERVICE_HOST_IP}
-  ports: ${MEGA_SERVICE_PORT}
-  image: opea/translation:latest
-  endpoint: /v1/translation
-  mega_flow:
-    - llm