From 2824cc07151f198e0c6686d87d95fc1bf23da604 Mon Sep 17 00:00:00 2001
From: artem-astafev <a.astafev@datamonsters.com>
Date: Fri, 15 Nov 2024 14:46:23 +0700
Subject: [PATCH 01/10] Add example for AudioQnA deploy in AMD ROCm

Signed-off-by: artem-astafev <a.astafev@datamonsters.com>
---
 .../docker_compose/amd/gpu/rocm/README.md     | 155 ++++++++++++++++++
 .../docker_compose/amd/gpu/rocm/compose.yaml  | 110 +++++++++++++
 .../docker_compose/amd/gpu/rocm/set_env.sh    |  26 +++
 AudioQnA/tests/test_compose_on_rocm.sh        | 102 ++++++++++++
 4 files changed, 393 insertions(+)
 create mode 100644 AudioQnA/docker_compose/amd/gpu/rocm/README.md
 create mode 100644 AudioQnA/docker_compose/amd/gpu/rocm/compose.yaml
 create mode 100644 AudioQnA/docker_compose/amd/gpu/rocm/set_env.sh
 create mode 100644 AudioQnA/tests/test_compose_on_rocm.sh

diff --git a/AudioQnA/docker_compose/amd/gpu/rocm/README.md b/AudioQnA/docker_compose/amd/gpu/rocm/README.md
new file mode 100644
index 000000000..aaf2f0c7a
--- /dev/null
+++ b/AudioQnA/docker_compose/amd/gpu/rocm/README.md
@@ -0,0 +1,155 @@
+# Build Mega Service of AudioQnA on AMD ROCm GPU
+
+This document outlines the deployment process for a AudioQnA application utilizing the [GenAIComps](https://github.com/opea-project/GenAIComps.git) microservice
+pipeline on server on AMD ROCm GPU platform.
+
+Quick Start Deployment Steps:
+
+1) Set up the environment variables.
+2) Run Docker Compose.
+3) Consume the ChatQnA Service.
+
+## 1) 🚀 Set the environment variables
+
+Before starting the services with `docker compose`, you have to recheck the following environment variables.
+
+```bash
+export host_ip=<your External Public IP>    # export host_ip=$(hostname -I | awk '{print $1}')
+export HUGGINGFACEHUB_API_TOKEN=<your HF token>
+
+export TGI_LLM_ENDPOINT=http://$host_ip:3006
+export LLM_MODEL_ID=Intel/neural-chat-7b-v3-3
+
+export ASR_ENDPOINT=http://$host_ip:7066
+export TTS_ENDPOINT=http://$host_ip:7055
+
+export MEGA_SERVICE_HOST_IP=${host_ip}
+export ASR_SERVICE_HOST_IP=${host_ip}
+export TTS_SERVICE_HOST_IP=${host_ip}
+export LLM_SERVICE_HOST_IP=${host_ip}
+
+export ASR_SERVICE_PORT=3001
+export TTS_SERVICE_PORT=3002
+export LLM_SERVICE_PORT=3007
+```
+
+## 2) 🚀 Start the MegaService
+
+```bash
+cd GenAIExamples/AudioQnA/docker_compose/amd/gpu/rocm/
+docker compose up -d
+```
+
+In following cases, you could build docker image from source by yourself.
+
+- Failed to download the docker image.
+- If you want to use a specific version of Docker image.
+
+Please refer to 'Build Docker Images' in below.
+
+## 3) 🚀 Consume the AudioQnA Service
+
+Test the AudioQnA megaservice by recording a .wav file, encoding the file into the base64 format, and then sending the
+base64 string to the megaservice endpoint. The megaservice will return a spoken response as a base64 string. To listen
+to the response, decode the base64 string and save it as a .wav file.
+
+```bash
+curl http://${host_ip}:3008/v1/audioqna \
+  -X POST \
+  -d '{"audio": "UklGRigAAABXQVZFZm10IBIAAAABAAEARKwAAIhYAQACABAAAABkYXRhAgAAAAEA", "max_tokens":64}' \
+  -H 'Content-Type: application/json' | sed 's/^"//;s/"$//' | base64 -d > output.wav
+```
+
+## 🚀 Build Docker images
+
+### 1. Source Code install GenAIComps
+
+```bash
+git clone https://github.com/opea-project/GenAIComps.git
+cd GenAIComps
+```
+
+### 2. Build ASR Image
+
+```bash
+docker build -t opea/whisper:latest --build-arg https_proxy=$https_proxy --build-arg http_proxy=$http_proxy -f comps/asr/whisper/dependency/Dockerfile .
+
+
+docker build -t opea/asr:latest --build-arg https_proxy=$https_proxy --build-arg http_proxy=$http_proxy -f comps/asr/whisper/Dockerfile .
+```
+
+### 3. Build LLM Image
+
+```bash
+docker build --no-cache -t opea/llm-tgi:latest --build-arg https_proxy=$https_proxy --build-arg http_proxy=$http_proxy -f comps/llms/text-generation/tgi/Dockerfile .
+```
+
+### 4. Build TTS Image
+
+```bash
+docker build -t opea/speecht5:latest --build-arg https_proxy=$https_proxy --build-arg http_proxy=$http_proxy -f comps/tts/speecht5/dependency/Dockerfile .
+
+docker build -t opea/tts:latest --build-arg https_proxy=$https_proxy --build-arg http_proxy=$http_proxy -f comps/tts/speecht5/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 `audioqna.py` Python script. Build the MegaService Docker image using the command below:
+
+```bash
+git clone https://github.com/opea-project/GenAIExamples.git
+cd GenAIExamples/AudioQnA/
+docker build --no-cache -t opea/audioqna:latest --build-arg https_proxy=$https_proxy --build-arg http_proxy=$http_proxy -f Dockerfile .
+```
+
+Then run the command `docker images`, you will have following images ready:
+
+1. `opea/whisper:latest`
+2. `opea/asr:latest`
+3. `opea/llm-tgi:latest`
+4. `opea/speecht5:latest`
+5. `opea/tts:latest`
+6. `opea/audioqna:latest`
+
+
+
+## 🚀 Test MicroServices
+
+```bash
+# whisper service
+curl http://${host_ip}:7066/v1/asr \
+  -X POST \
+  -d '{"audio": "UklGRigAAABXQVZFZm10IBIAAAABAAEARKwAAIhYAQACABAAAABkYXRhAgAAAAEA"}' \
+  -H 'Content-Type: application/json'
+
+# asr microservice
+curl http://${host_ip}:3001/v1/audio/transcriptions \
+  -X POST \
+  -d '{"byte_str": "UklGRigAAABXQVZFZm10IBIAAAABAAEARKwAAIhYAQACABAAAABkYXRhAgAAAAEA"}' \
+  -H 'Content-Type: application/json'
+
+# tgi service
+curl http://${host_ip}:3006/generate \
+  -X POST \
+  -d '{"inputs":"What is Deep Learning?","parameters":{"max_new_tokens":17, "do_sample": true}}' \
+  -H 'Content-Type: application/json'
+
+# llm microservice
+curl http://${host_ip}:3007/v1/chat/completions\
+  -X POST \
+  -d '{"query":"What is Deep Learning?","max_tokens":17,"top_k":10,"top_p":0.95,"typical_p":0.95,"temperature":0.01,"repetition_penalty":1.03,"streaming":false}' \
+  -H 'Content-Type: application/json'
+
+# speecht5 service
+curl http://${host_ip}:7055/v1/tts \
+  -X POST \
+  -d '{"text": "Who are you?"}' \
+  -H 'Content-Type: application/json'
+
+# tts microservice
+curl http://${host_ip}:3002/v1/audio/speech \
+  -X POST \
+  -d '{"text": "Who are you?"}' \
+  -H 'Content-Type: application/json'
+
+```
diff --git a/AudioQnA/docker_compose/amd/gpu/rocm/compose.yaml b/AudioQnA/docker_compose/amd/gpu/rocm/compose.yaml
new file mode 100644
index 000000000..3588056b5
--- /dev/null
+++ b/AudioQnA/docker_compose/amd/gpu/rocm/compose.yaml
@@ -0,0 +1,110 @@
+# Copyright (C) 2024 Advanced Micro Devices, Inc.
+# 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:
+      - "3001:9099"
+    ipc: host
+    environment:
+      ASR_ENDPOINT: ${ASR_ENDPOINT}
+  speecht5-service:
+    image: ${REGISTRY:-opea}/speecht5:${TAG:-latest}
+    container_name: speecht5-service
+    ports:
+      - "7055:7055"
+    ipc: host
+    environment:
+      no_proxy: ${no_proxy}
+      http_proxy: ${http_proxy}
+      https_proxy: ${https_proxy}
+    restart: unless-stopped
+  tts:
+    image: ${REGISTRY:-opea}/tts:${TAG:-latest}
+    container_name: tts-service
+    ports:
+      - "3002:9088"
+    ipc: host
+    environment:
+      TTS_ENDPOINT: ${TTS_ENDPOINT}
+tgi-service:
+    image: ghcr.io/huggingface/text-generation-inference:2.3.1-rocm
+    container_name: tgi-service
+    ports:
+      - "3006:80"
+    volumes:
+      - "./data:/data"
+    shm_size: 1g
+    devices:
+      - /dev/kfd:/dev/kfd
+      - /dev/dri/card1:/dev/dri/card1
+      - /dev/dri/renderD136:/dev/dri/renderD136
+    environment:
+      no_proxy: ${no_proxy}
+      http_proxy: ${http_proxy}
+      https_proxy: ${https_proxy}
+      HF_TOKEN: ${HUGGINGFACEHUB_API_TOKEN}
+      HF_HUB_DISABLE_PROGRESS_BARS: 1
+      HF_HUB_ENABLE_HF_TRANSFER: 0
+    command: --model-id ${LLM_MODEL_ID}
+    cap_add:
+      - SYS_PTRACE
+    group_add:
+      - video
+    security_opt:
+      - seccomp:unconfined
+    ipc: host
+  llm:
+    image: ${REGISTRY:-opea}/llm-tgi:${TAG:-latest}
+    container_name: llm-tgi-server
+    depends_on:
+      - tgi-service
+    ports:
+      - "3007:9000"
+    ipc: host
+    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}
+    restart: unless-stopped
+audioqna-backend-server:
+    image: ${REGISTRY:-opea}/audioqna:${TAG:-latest}
+    container_name: audioqna-xeon-backend-server
+    depends_on:
+      - asr
+      - llm
+      - tts
+    ports:
+      - "3008:8888"
+    environment:
+      - no_proxy=${no_proxy}
+      - https_proxy=${https_proxy}
+      - http_proxy=${http_proxy}
+      - MEGA_SERVICE_HOST_IP=${MEGA_SERVICE_HOST_IP}
+      - ASR_SERVICE_HOST_IP=${ASR_SERVICE_HOST_IP}
+      - ASR_SERVICE_PORT=${ASR_SERVICE_PORT}
+      - LLM_SERVICE_HOST_IP=${LLM_SERVICE_HOST_IP}
+      - LLM_SERVICE_PORT=${LLM_SERVICE_PORT}
+      - TTS_SERVICE_HOST_IP=${TTS_SERVICE_HOST_IP}
+      - TTS_SERVICE_PORT=${TTS_SERVICE_PORT}
+    ipc: host
+    restart: always
+
+networks:
+  default:
+    driver: bridge
diff --git a/AudioQnA/docker_compose/amd/gpu/rocm/set_env.sh b/AudioQnA/docker_compose/amd/gpu/rocm/set_env.sh
new file mode 100644
index 000000000..8765b702b
--- /dev/null
+++ b/AudioQnA/docker_compose/amd/gpu/rocm/set_env.sh
@@ -0,0 +1,26 @@
+#!/usr/bin/env bash                                                                                                           set_env.sh
+
+# Copyright (C) 2024 Advanced Micro Devices, Inc.
+# SPDX-License-Identifier: Apache-2.0
+
+
+# export host_ip=<your External Public IP>    # export host_ip=$(hostname -I | awk '{print $1}')
+
+export host_ip="192.165.1.21"
+export HUGGINGFACEHUB_API_TOKEN=${YOUR_HUGGINGFACEHUB_API_TOKEN}
+# <token>
+
+export TGI_LLM_ENDPOINT=http://$host_ip:3006
+export LLM_MODEL_ID=Intel/neural-chat-7b-v3-3
+
+export ASR_ENDPOINT=http://$host_ip:7066
+export TTS_ENDPOINT=http://$host_ip:7055
+
+export MEGA_SERVICE_HOST_IP=${host_ip}
+export ASR_SERVICE_HOST_IP=${host_ip}
+export TTS_SERVICE_HOST_IP=${host_ip}
+export LLM_SERVICE_HOST_IP=${host_ip}
+
+export ASR_SERVICE_PORT=3001
+export TTS_SERVICE_PORT=3002
+export LLM_SERVICE_PORT=3007
diff --git a/AudioQnA/tests/test_compose_on_rocm.sh b/AudioQnA/tests/test_compose_on_rocm.sh
new file mode 100644
index 000000000..953f8df70
--- /dev/null
+++ b/AudioQnA/tests/test_compose_on_rocm.sh
@@ -0,0 +1,102 @@
+#!/bin/bash
+# Copyright (C) 2024 Advanced Micro Devices, Inc.
+# SPDX-License-Identifier: Apache-2.0
+
+set -e
+IMAGE_REPO=${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 $1}')
+export PATH="/home/huggingface/miniconda3/bin:$PATH"
+
+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="audioqna whisper asr llm-tgi speecht5 tts"
+    docker compose -f build.yaml build ${service_list} --no-cache > ${LOG_PATH}/docker_image_build.log
+    echo "docker pull ghcr.io/huggingface/text-generation-inference:2.3.1-rocm"
+    docker pull ghcr.io/huggingface/text-generation-inference:2.3.1-rocm
+    docker images && sleep 1s
+}
+
+function start_services() {
+    cd $WORKPATH/docker_compose/amd/gpu/rocm/
+    export HUGGINGFACEHUB_API_TOKEN=${HUGGINGFACEHUB_API_TOKEN}
+    export TGI_LLM_ENDPOINT=http://$ip_address:3006
+    export LLM_MODEL_ID=Intel/neural-chat-7b-v3-3
+
+    export ASR_ENDPOINT=http://$ip_address:7066
+    export TTS_ENDPOINT=http://$ip_address:7055
+
+    export MEGA_SERVICE_HOST_IP=${ip_address}
+    export ASR_SERVICE_HOST_IP=${ip_address}
+    export TTS_SERVICE_HOST_IP=${ip_address}
+    export LLM_SERVICE_HOST_IP=${ip_address}
+
+    export ASR_SERVICE_PORT=3001
+    export TTS_SERVICE_PORT=3002
+    export LLM_SERVICE_PORT=3007
+
+    # sed -i "s/backend_address/$ip_address/g" $WORKPATH/ui/svelte/.env
+
+    # Start Docker Containers
+    docker compose up -d > ${LOG_PATH}/start_services_with_compose.log
+    n=0
+    until [[ "$n" -ge 100 ]]; do
+       docker logs tgi-service > $LOG_PATH/tgi_service_start.log
+       if grep -q Connected $LOG_PATH/tgi_service_start.log; then
+           break
+       fi
+       sleep 5s
+       n=$((n+1))
+    done
+}
+function validate_megaservice() {
+    result=$(http_proxy="" curl http://${ip_address}:3008/v1/audioqna -XPOST -d '{"audio": "UklGRigAAABXQVZFZm10IBIAAAABAAEARKwAAIhYAQACABAAAABkYXRhAgAAAAEA", "max_tokens":64}' -H 'Content-Type: application/json')
+    echo $result
+    if [[ $result == *"AAA"* ]]; then
+        echo "Result correct."
+    else
+        docker logs whisper-service > $LOG_PATH/whisper-service.log
+        docker logs asr-service > $LOG_PATH/asr-service.log
+        docker logs speecht5-service > $LOG_PATH/tts-service.log
+        docker logs tts-service > $LOG_PATH/tts-service.log
+        docker logs tgi-service > $LOG_PATH/tgi-service.log
+        docker logs llm-tgi-server > $LOG_PATH/llm-tgi-server.log
+        docker logs audioqna-xeon-backend-server > $LOG_PATH/audioqna-xeon-backend-server.log
+
+        echo "Result wrong."
+        exit 1
+    fi
+
+}
+
+function stop_docker() {
+    cd $WORKPATH/docker_compose/amd/gpu/rocm/
+    docker compose stop && docker compose rm -f
+}
+
+function main() {
+
+    stop_docker
+    if [[ "$IMAGE_REPO" == "opea" ]]; then build_docker_images; fi
+    start_services
+
+    validate_megaservice
+    # validate_frontend
+
+    stop_docker
+    echo y | docker system prune
+
+}
+
+main
+

From 87b2c40695a928b0209b357d1431fcd485ec33e4 Mon Sep 17 00:00:00 2001
From: "pre-commit-ci[bot]"
 <66853113+pre-commit-ci[bot]@users.noreply.github.com>
Date: Fri, 15 Nov 2024 08:14:05 +0000
Subject: [PATCH 02/10] [pre-commit.ci] auto fixes from pre-commit.com hooks

for more information, see https://pre-commit.ci
---
 AudioQnA/docker_compose/amd/gpu/rocm/README.md | 8 +++-----
 AudioQnA/tests/test_compose_on_rocm.sh         | 1 -
 2 files changed, 3 insertions(+), 6 deletions(-)

diff --git a/AudioQnA/docker_compose/amd/gpu/rocm/README.md b/AudioQnA/docker_compose/amd/gpu/rocm/README.md
index aaf2f0c7a..044c934f5 100644
--- a/AudioQnA/docker_compose/amd/gpu/rocm/README.md
+++ b/AudioQnA/docker_compose/amd/gpu/rocm/README.md
@@ -5,9 +5,9 @@ pipeline on server on AMD ROCm GPU platform.
 
 Quick Start Deployment Steps:
 
-1) Set up the environment variables.
-2) Run Docker Compose.
-3) Consume the ChatQnA Service.
+1. Set up the environment variables.
+2. Run Docker Compose.
+3. Consume the ChatQnA Service.
 
 ## 1) 🚀 Set the environment variables
 
@@ -111,8 +111,6 @@ Then run the command `docker images`, you will have following images ready:
 5. `opea/tts:latest`
 6. `opea/audioqna:latest`
 
-
-
 ## 🚀 Test MicroServices
 
 ```bash
diff --git a/AudioQnA/tests/test_compose_on_rocm.sh b/AudioQnA/tests/test_compose_on_rocm.sh
index 953f8df70..eeeb58b5e 100644
--- a/AudioQnA/tests/test_compose_on_rocm.sh
+++ b/AudioQnA/tests/test_compose_on_rocm.sh
@@ -99,4 +99,3 @@ function main() {
 }
 
 main
-

From 8a98c4fbe2395a71e07cb2a56d79e04e4069b521 Mon Sep 17 00:00:00 2001
From: Artem Astafev <a.astafev@datamonsters.com>
Date: Tue, 19 Nov 2024 12:17:10 +0700
Subject: [PATCH 03/10] Update README.md

Signed-off-by: Artem Astafev <a.astafev@datamonsters.com>
---
 .../docker_compose/amd/gpu/rocm/README.md     | 125 ++++++++++--------
 1 file changed, 70 insertions(+), 55 deletions(-)

diff --git a/AudioQnA/docker_compose/amd/gpu/rocm/README.md b/AudioQnA/docker_compose/amd/gpu/rocm/README.md
index 044c934f5..542fae692 100644
--- a/AudioQnA/docker_compose/amd/gpu/rocm/README.md
+++ b/AudioQnA/docker_compose/amd/gpu/rocm/README.md
@@ -3,11 +3,58 @@
 This document outlines the deployment process for a AudioQnA application utilizing the [GenAIComps](https://github.com/opea-project/GenAIComps.git) microservice
 pipeline on server on AMD ROCm GPU platform.
 
-Quick Start Deployment Steps:
+## 🚀 Build Docker images
+
+### 1. Source Code install GenAIComps
+
+```bash
+git clone https://github.com/opea-project/GenAIComps.git
+cd GenAIComps
+```
+
+### 2. Build ASR Image
+
+```bash
+docker build -t opea/whisper:latest --build-arg https_proxy=$https_proxy --build-arg http_proxy=$http_proxy -f comps/asr/whisper/dependency/Dockerfile .
+
+
+docker build -t opea/asr:latest --build-arg https_proxy=$https_proxy --build-arg http_proxy=$http_proxy -f comps/asr/whisper/Dockerfile .
+```
+
+### 3. Build LLM Image
+
+```bash
+docker build --no-cache -t opea/llm-tgi:latest --build-arg https_proxy=$https_proxy --build-arg http_proxy=$http_proxy -f comps/llms/text-generation/tgi/Dockerfile .
+```
+Note:
+For compose for ROCm example AMD optimized image hosted in huggingface repo will be used for TGI service: ghcr.io/huggingface/text-generation-inference:2.3.1-rocm (https://github.com/huggingface/text-generation-inference)
+
+### 4. Build TTS Image
+
+```bash
+docker build -t opea/speecht5:latest --build-arg https_proxy=$https_proxy --build-arg http_proxy=$http_proxy -f comps/tts/speecht5/dependency/Dockerfile .
+
+docker build -t opea/tts:latest --build-arg https_proxy=$https_proxy --build-arg http_proxy=$http_proxy -f comps/tts/speecht5/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 `audioqna.py` Python script. Build the MegaService Docker image using the command below:
 
-1. Set up the environment variables.
-2. Run Docker Compose.
-3. Consume the ChatQnA Service.
+```bash
+git clone https://github.com/opea-project/GenAIExamples.git
+cd GenAIExamples/AudioQnA/
+docker build --no-cache -t opea/audioqna:latest --build-arg https_proxy=$https_proxy --build-arg http_proxy=$http_proxy -f Dockerfile .
+```
+
+Then run the command `docker images`, you will have following images ready:
+
+1. `opea/whisper:latest`
+2. `opea/asr:latest`
+3. `opea/llm-tgi:latest`
+4. `opea/speecht5:latest`
+5. `opea/tts:latest`
+6. `opea/audioqna:latest`
 
 ## 1) 🚀 Set the environment variables
 
@@ -32,6 +79,25 @@ export ASR_SERVICE_PORT=3001
 export TTS_SERVICE_PORT=3002
 export LLM_SERVICE_PORT=3007
 ```
+or use set_env.sh file to setup environment variables. 
+
+Note: Please replace with host_ip with your external IP address, do not use localhost.
+
+Note: In order to limit access to a subset of GPUs, please pass each device individually using one or more -device /dev/dri/rendered, where is the card index, starting from 128. (https://rocm.docs.amd.com/projects/install-on-linux/en/latest/how-to/docker.html#docker-restrict-gpus)
+
+Example for set isolation for 1 GPU
+
+      - /dev/dri/card0:/dev/dri/card0
+      - /dev/dri/renderD128:/dev/dri/renderD128
+Example for set isolation for 2 GPUs
+
+      - /dev/dri/card0:/dev/dri/card0
+      - /dev/dri/renderD128:/dev/dri/renderD128
+      - /dev/dri/card0:/dev/dri/card0
+      - /dev/dri/renderD129:/dev/dri/renderD129
+Please find more information about accessing and restricting AMD GPUs in the link (https://rocm.docs.amd.com/projects/install-on-linux/en/latest/how-to/docker.html#docker-restrict-gpus)
+
+
 
 ## 2) 🚀 Start the MegaService
 
@@ -60,57 +126,6 @@ curl http://${host_ip}:3008/v1/audioqna \
   -H 'Content-Type: application/json' | sed 's/^"//;s/"$//' | base64 -d > output.wav
 ```
 
-## 🚀 Build Docker images
-
-### 1. Source Code install GenAIComps
-
-```bash
-git clone https://github.com/opea-project/GenAIComps.git
-cd GenAIComps
-```
-
-### 2. Build ASR Image
-
-```bash
-docker build -t opea/whisper:latest --build-arg https_proxy=$https_proxy --build-arg http_proxy=$http_proxy -f comps/asr/whisper/dependency/Dockerfile .
-
-
-docker build -t opea/asr:latest --build-arg https_proxy=$https_proxy --build-arg http_proxy=$http_proxy -f comps/asr/whisper/Dockerfile .
-```
-
-### 3. Build LLM Image
-
-```bash
-docker build --no-cache -t opea/llm-tgi:latest --build-arg https_proxy=$https_proxy --build-arg http_proxy=$http_proxy -f comps/llms/text-generation/tgi/Dockerfile .
-```
-
-### 4. Build TTS Image
-
-```bash
-docker build -t opea/speecht5:latest --build-arg https_proxy=$https_proxy --build-arg http_proxy=$http_proxy -f comps/tts/speecht5/dependency/Dockerfile .
-
-docker build -t opea/tts:latest --build-arg https_proxy=$https_proxy --build-arg http_proxy=$http_proxy -f comps/tts/speecht5/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 `audioqna.py` Python script. Build the MegaService Docker image using the command below:
-
-```bash
-git clone https://github.com/opea-project/GenAIExamples.git
-cd GenAIExamples/AudioQnA/
-docker build --no-cache -t opea/audioqna:latest --build-arg https_proxy=$https_proxy --build-arg http_proxy=$http_proxy -f Dockerfile .
-```
-
-Then run the command `docker images`, you will have following images ready:
-
-1. `opea/whisper:latest`
-2. `opea/asr:latest`
-3. `opea/llm-tgi:latest`
-4. `opea/speecht5:latest`
-5. `opea/tts:latest`
-6. `opea/audioqna:latest`
-
 ## 🚀 Test MicroServices
 
 ```bash

From 02df9cd0d338d2733ad175e8fcf8871706e99f41 Mon Sep 17 00:00:00 2001
From: "pre-commit-ci[bot]"
 <66853113+pre-commit-ci[bot]@users.noreply.github.com>
Date: Tue, 19 Nov 2024 05:17:35 +0000
Subject: [PATCH 04/10] [pre-commit.ci] auto fixes from pre-commit.com hooks

for more information, see https://pre-commit.ci
---
 AudioQnA/docker_compose/amd/gpu/rocm/README.md | 8 +++++---
 1 file changed, 5 insertions(+), 3 deletions(-)

diff --git a/AudioQnA/docker_compose/amd/gpu/rocm/README.md b/AudioQnA/docker_compose/amd/gpu/rocm/README.md
index 542fae692..870922db8 100644
--- a/AudioQnA/docker_compose/amd/gpu/rocm/README.md
+++ b/AudioQnA/docker_compose/amd/gpu/rocm/README.md
@@ -26,6 +26,7 @@ docker build -t opea/asr:latest --build-arg https_proxy=$https_proxy --build-arg
 ```bash
 docker build --no-cache -t opea/llm-tgi:latest --build-arg https_proxy=$https_proxy --build-arg http_proxy=$http_proxy -f comps/llms/text-generation/tgi/Dockerfile .
 ```
+
 Note:
 For compose for ROCm example AMD optimized image hosted in huggingface repo will be used for TGI service: ghcr.io/huggingface/text-generation-inference:2.3.1-rocm (https://github.com/huggingface/text-generation-inference)
 
@@ -79,7 +80,8 @@ export ASR_SERVICE_PORT=3001
 export TTS_SERVICE_PORT=3002
 export LLM_SERVICE_PORT=3007
 ```
-or use set_env.sh file to setup environment variables. 
+
+or use set_env.sh file to setup environment variables.
 
 Note: Please replace with host_ip with your external IP address, do not use localhost.
 
@@ -89,15 +91,15 @@ Example for set isolation for 1 GPU
 
       - /dev/dri/card0:/dev/dri/card0
       - /dev/dri/renderD128:/dev/dri/renderD128
+
 Example for set isolation for 2 GPUs
 
       - /dev/dri/card0:/dev/dri/card0
       - /dev/dri/renderD128:/dev/dri/renderD128
       - /dev/dri/card0:/dev/dri/card0
       - /dev/dri/renderD129:/dev/dri/renderD129
-Please find more information about accessing and restricting AMD GPUs in the link (https://rocm.docs.amd.com/projects/install-on-linux/en/latest/how-to/docker.html#docker-restrict-gpus)
-
 
+Please find more information about accessing and restricting AMD GPUs in the link (https://rocm.docs.amd.com/projects/install-on-linux/en/latest/how-to/docker.html#docker-restrict-gpus)
 
 ## 2) 🚀 Start the MegaService
 

From fbbc349c4cde262c28699b79c98a8c0a801af9dd Mon Sep 17 00:00:00 2001
From: Artem Astafev <a.astafev@datamonsters.com>
Date: Tue, 19 Nov 2024 12:19:51 +0700
Subject: [PATCH 05/10] Update test_compose_on_rocm.sh

Signed-off-by: Artem Astafev <a.astafev@datamonsters.com>
---
 AudioQnA/tests/test_compose_on_rocm.sh | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/AudioQnA/tests/test_compose_on_rocm.sh b/AudioQnA/tests/test_compose_on_rocm.sh
index eeeb58b5e..6c80337e9 100644
--- a/AudioQnA/tests/test_compose_on_rocm.sh
+++ b/AudioQnA/tests/test_compose_on_rocm.sh
@@ -2,7 +2,7 @@
 # Copyright (C) 2024 Advanced Micro Devices, Inc.
 # SPDX-License-Identifier: Apache-2.0
 
-set -e
+set -ex
 IMAGE_REPO=${IMAGE_REPO:-"opea"}
 IMAGE_TAG=${IMAGE_TAG:-"latest"}
 echo "REGISTRY=IMAGE_REPO=${IMAGE_REPO}"

From b5b52c56c5f12ffb902f7e1f5b622098687b08c2 Mon Sep 17 00:00:00 2001
From: Artem Astafev <a.astafev@datamonsters.com>
Date: Tue, 19 Nov 2024 12:33:39 +0700
Subject: [PATCH 06/10] Update test_compose_on_rocm.sh

Signed-off-by: Artem Astafev <a.astafev@datamonsters.com>
---
 AudioQnA/tests/test_compose_on_rocm.sh | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/AudioQnA/tests/test_compose_on_rocm.sh b/AudioQnA/tests/test_compose_on_rocm.sh
index 6c80337e9..22385112e 100644
--- a/AudioQnA/tests/test_compose_on_rocm.sh
+++ b/AudioQnA/tests/test_compose_on_rocm.sh
@@ -48,7 +48,7 @@ function start_services() {
     # sed -i "s/backend_address/$ip_address/g" $WORKPATH/ui/svelte/.env
 
     # Start Docker Containers
-    docker compose up -d > ${LOG_PATH}/start_services_with_compose.log
+    docker compose -f compose.yaml up -d > ${LOG_PATH}/start_services_with_compose.log
     n=0
     until [[ "$n" -ge 100 ]]; do
        docker logs tgi-service > $LOG_PATH/tgi_service_start.log
@@ -81,7 +81,7 @@ function validate_megaservice() {
 
 function stop_docker() {
     cd $WORKPATH/docker_compose/amd/gpu/rocm/
-    docker compose stop && docker compose rm -f
+    docker compose -f compose.yaml stop && docker compose -f compose.yaml rm -f
 }
 
 function main() {

From c6ad7e47012eb5b01fa6bafd8ac6c22a65306173 Mon Sep 17 00:00:00 2001
From: Artem Astafev <a.astafev@datamonsters.com>
Date: Tue, 19 Nov 2024 12:39:30 +0700
Subject: [PATCH 07/10] Update compose.yaml

Signed-off-by: Artem Astafev <a.astafev@datamonsters.com>
---
 AudioQnA/docker_compose/amd/gpu/rocm/compose.yaml | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/AudioQnA/docker_compose/amd/gpu/rocm/compose.yaml b/AudioQnA/docker_compose/amd/gpu/rocm/compose.yaml
index 3588056b5..651fd5464 100644
--- a/AudioQnA/docker_compose/amd/gpu/rocm/compose.yaml
+++ b/AudioQnA/docker_compose/amd/gpu/rocm/compose.yaml
@@ -40,13 +40,13 @@ services:
     ipc: host
     environment:
       TTS_ENDPOINT: ${TTS_ENDPOINT}
-tgi-service:
+  tgi-service:
     image: ghcr.io/huggingface/text-generation-inference:2.3.1-rocm
     container_name: tgi-service
     ports:
       - "3006:80"
     volumes:
-      - "./data:/data"
+     - "./data:/data"
     shm_size: 1g
     devices:
       - /dev/kfd:/dev/kfd
@@ -82,7 +82,7 @@ tgi-service:
       TGI_LLM_ENDPOINT: ${TGI_LLM_ENDPOINT}
       HUGGINGFACEHUB_API_TOKEN: ${HUGGINGFACEHUB_API_TOKEN}
     restart: unless-stopped
-audioqna-backend-server:
+  audioqna-backend-server:
     image: ${REGISTRY:-opea}/audioqna:${TAG:-latest}
     container_name: audioqna-xeon-backend-server
     depends_on:

From ad4a995f2ba1a9fd6f7eb9c8562fd2103b0a799c Mon Sep 17 00:00:00 2001
From: Artem Astafev <a.astafev@datamonsters.com>
Date: Tue, 19 Nov 2024 12:54:17 +0700
Subject: [PATCH 08/10] Update test_compose_on_rocm.sh

Signed-off-by: Artem Astafev <a.astafev@datamonsters.com>
---
 AudioQnA/tests/test_compose_on_rocm.sh | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/AudioQnA/tests/test_compose_on_rocm.sh b/AudioQnA/tests/test_compose_on_rocm.sh
index 22385112e..6c80337e9 100644
--- a/AudioQnA/tests/test_compose_on_rocm.sh
+++ b/AudioQnA/tests/test_compose_on_rocm.sh
@@ -48,7 +48,7 @@ function start_services() {
     # sed -i "s/backend_address/$ip_address/g" $WORKPATH/ui/svelte/.env
 
     # Start Docker Containers
-    docker compose -f compose.yaml up -d > ${LOG_PATH}/start_services_with_compose.log
+    docker compose up -d > ${LOG_PATH}/start_services_with_compose.log
     n=0
     until [[ "$n" -ge 100 ]]; do
        docker logs tgi-service > $LOG_PATH/tgi_service_start.log
@@ -81,7 +81,7 @@ function validate_megaservice() {
 
 function stop_docker() {
     cd $WORKPATH/docker_compose/amd/gpu/rocm/
-    docker compose -f compose.yaml stop && docker compose -f compose.yaml rm -f
+    docker compose stop && docker compose rm -f
 }
 
 function main() {

From f9207ac03beed69e86c24b93841729e6389dc65f Mon Sep 17 00:00:00 2001
From: Artem Astafev <a.astafev@datamonsters.com>
Date: Tue, 19 Nov 2024 13:21:43 +0700
Subject: [PATCH 09/10] Update test_compose_on_rocm.sh

Signed-off-by: Artem Astafev <a.astafev@datamonsters.com>
---
 AudioQnA/tests/test_compose_on_rocm.sh | 29 +++++++++++++++++++++++++-
 1 file changed, 28 insertions(+), 1 deletion(-)

diff --git a/AudioQnA/tests/test_compose_on_rocm.sh b/AudioQnA/tests/test_compose_on_rocm.sh
index 6c80337e9..86a148472 100644
--- a/AudioQnA/tests/test_compose_on_rocm.sh
+++ b/AudioQnA/tests/test_compose_on_rocm.sh
@@ -13,7 +13,7 @@ export TAG=${IMAGE_TAG}
 WORKPATH=$(dirname "$PWD")
 LOG_PATH="$WORKPATH/tests"
 ip_address=$(hostname -I | awk '{print $1}')
-export PATH="/home/huggingface/miniconda3/bin:$PATH"
+export PATH="~/miniconda3/bin:$PATH"
 
 function build_docker_images() {
     cd $WORKPATH/docker_image_build
@@ -79,6 +79,32 @@ function validate_megaservice() {
 
 }
 
+#function validate_frontend() {
+# Frontend tests are currently disabled
+#    cd $WORKPATH/ui/svelte
+#    local conda_env_name="OPEA_e2e"
+#    export PATH=${HOME}/miniforge3/bin/:$PATH
+##    conda remove -n ${conda_env_name} --all -y
+##    conda create -n ${conda_env_name} python=3.12 -y
+#    source activate ${conda_env_name}
+#
+#    sed -i "s/localhost/$ip_address/g" playwright.config.ts
+#
+##    conda install -c conda-forge nodejs -y
+#    npm install && npm ci && npx playwright install --with-deps
+#    node -v && npm -v && pip list
+#
+#    exit_status=0
+#    npx playwright test || exit_status=$?
+#
+#    if [ $exit_status -ne 0 ]; then
+#        echo "[TEST INFO]: ---------frontend test failed---------"
+#        exit $exit_status
+#    else
+#        echo "[TEST INFO]: ---------frontend test passed---------"
+#    fi
+#}
+
 function stop_docker() {
     cd $WORKPATH/docker_compose/amd/gpu/rocm/
     docker compose stop && docker compose rm -f
@@ -91,6 +117,7 @@ function main() {
     start_services
 
     validate_megaservice
+    # Frontend tests are currently disabled
     # validate_frontend
 
     stop_docker

From d4496918a1dcfa325c9f5786df4feccffae5f75c Mon Sep 17 00:00:00 2001
From: Artem Astafev <a.astafev@datamonsters.com>
Date: Wed, 20 Nov 2024 13:11:20 +0700
Subject: [PATCH 10/10] Update README.md

Signed-off-by: Artem Astafev <a.astafev@datamonsters.com>
---
 AudioQnA/docker_compose/amd/gpu/rocm/README.md | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/AudioQnA/docker_compose/amd/gpu/rocm/README.md b/AudioQnA/docker_compose/amd/gpu/rocm/README.md
index 870922db8..3ae8cc8a3 100644
--- a/AudioQnA/docker_compose/amd/gpu/rocm/README.md
+++ b/AudioQnA/docker_compose/amd/gpu/rocm/README.md
@@ -57,7 +57,7 @@ Then run the command `docker images`, you will have following images ready:
 5. `opea/tts:latest`
 6. `opea/audioqna:latest`
 
-## 1) 🚀 Set the environment variables
+## 🚀 Set the environment variables
 
 Before starting the services with `docker compose`, you have to recheck the following environment variables.
 
@@ -101,7 +101,7 @@ Example for set isolation for 2 GPUs
 
 Please find more information about accessing and restricting AMD GPUs in the link (https://rocm.docs.amd.com/projects/install-on-linux/en/latest/how-to/docker.html#docker-restrict-gpus)
 
-## 2) 🚀 Start the MegaService
+## 🚀 Start the MegaService
 
 ```bash
 cd GenAIExamples/AudioQnA/docker_compose/amd/gpu/rocm/
@@ -115,7 +115,7 @@ In following cases, you could build docker image from source by yourself.
 
 Please refer to 'Build Docker Images' in below.
 
-## 3) 🚀 Consume the AudioQnA Service
+## 🚀 Consume the AudioQnA Service
 
 Test the AudioQnA megaservice by recording a .wav file, encoding the file into the base64 format, and then sending the
 base64 string to the megaservice endpoint. The megaservice will return a spoken response as a base64 string. To listen