Fix ui dockerfile. (#1909)

Signed-off-by: lkk <33276950+lkk12014402@users.noreply.github.com>
(cherry picked from commit ff66600ab4)

.github/workflows/_example-workflow.yml

@@ -76,6 +76,7 @@ jobs:
       example: ${{ inputs.example }}
       hardware: ${{ inputs.node }}
       use_model_cache: ${{ inputs.use_model_cache }}
+      opea_branch: ${{ inputs.opea_branch }}
     secrets: inherit
 
 

.github/workflows/_run-docker-compose.yml

@@ -32,6 +32,10 @@ on:
         required: false
         type: boolean
         default: false
+      opea_branch:
+        default: "main"
+        required: false
+        type: string
 jobs:
   get-test-case:
     runs-on: ubuntu-latest
@@ -169,6 +173,7 @@ jobs:
           FINANCIAL_DATASETS_API_KEY: ${{ secrets.FINANCIAL_DATASETS_API_KEY }}
           IMAGE_REPO: ${{ inputs.registry }}
           IMAGE_TAG: ${{ inputs.tag }}
+          opea_branch: ${{ inputs.opea_branch }}
           example: ${{ inputs.example }}
           hardware: ${{ inputs.hardware }}
           test_case: ${{ matrix.test_case }}

.github/workflows/scripts/codeScan/hadolint.sh

@@ -7,7 +7,7 @@ source /GenAIExamples/.github/workflows/scripts/change_color
 log_dir=/GenAIExamples/.github/workflows/scripts/codeScan
 ERROR_WARN=false
 
-find . -type f \( -name "Dockerfile*" \) -print -exec hadolint --ignore DL3006 --ignore DL3007 --ignore DL3008 --ignore DL3013 {} \; > ${log_dir}/hadolint.log
+find . -type f \( -name "Dockerfile*" \) -print -exec hadolint --ignore DL3006 --ignore DL3007 --ignore DL3008 --ignore DL3013 --ignore DL3018 --ignore DL3016 {} \; > ${log_dir}/hadolint.log
 
 if [[ $(grep -c "error" ${log_dir}/hadolint.log) != 0 ]]; then
     $BOLD_RED && echo "Error!! Please Click on the artifact button to download and check error details." && $RESET

AgentQnA/ui/docker/Dockerfile

@@ -1,49 +1,203 @@
-# Copyright (C) 2024 Intel Corporation
+# Copyright (C) 2025 Intel Corporation
 # SPDX-License-Identifier: Apache-2.0
 
-#FROM python:3.11-slim
-FROM node:22.9.0
+# syntax=docker/dockerfile:1
+# Initialize device type args
+# use build args in the docker build command with --build-arg="BUILDARG=true"
+ARG USE_CUDA=false
+ARG USE_OLLAMA=false
+# Tested with cu117 for CUDA 11 and cu121 for CUDA 12 (default)
+ARG USE_CUDA_VER=cu121
+# any sentence transformer model; models to use can be found at https://huggingface.co/models?library=sentence-transformers
+# Leaderboard: https://huggingface.co/spaces/mteb/leaderboard
+# for better performance and multilangauge support use "intfloat/multilingual-e5-large" (~2.5GB) or "intfloat/multilingual-e5-base" (~1.5GB)
+# IMPORTANT: If you change the embedding model (sentence-transformers/all-MiniLM-L6-v2) and vice versa, you aren't able to use RAG Chat with your previous documents loaded in the WebUI! You need to re-embed them.
+ARG USE_EMBEDDING_MODEL=sentence-transformers/all-MiniLM-L6-v2
+ARG USE_RERANKING_MODEL=""
 
-ENV LANG=C.UTF-8
-ARG ARCH=cpu
+# Tiktoken encoding name; models to use can be found at https://huggingface.co/models?library=tiktoken
+ARG USE_TIKTOKEN_ENCODING_NAME="cl100k_base"
 
-RUN apt-get update -y && apt-get install -y --no-install-recommends --fix-missing \
-    build-essential \
-    libgl1-mesa-glx \
-    libjemalloc-dev \
-    git \
-    python3-venv
+ARG BUILD_HASH=dev-build
+# Override at your own risk - non-root configurations are untested
+ARG UID=0
+ARG GID=0
 
+######## WebUI frontend ########
+FROM --platform=$BUILDPLATFORM node:22-alpine3.20 AS build
+ARG BUILD_HASH
+
+WORKDIR /app
+
+COPY open_webui_patches /app/patches
+ARG WEBUI_VERSION=v0.5.20
+RUN apk add --no-cache git
+
+# Clone code and use patch
+RUN git config --global user.name "opea" && \
+    git config --global user.email "" && \
+    git clone https://github.com/open-webui/open-webui.git
+
+WORKDIR /app/open-webui
+
+RUN git checkout ${WEBUI_VERSION} && git am /app/patches/*.patch
+
+WORKDIR /app
+
+RUN mv open-webui/* . && rm -fr open-webui && ls -lrth /app/backend/
+
+RUN npm install onnxruntime-node --onnxruntime-node-install-cuda=skip
+RUN apk update && \
+    apk add --no-cache wget && \
+    wget https://github.com/microsoft/onnxruntime/releases/download/v1.20.1/onnxruntime-linux-x64-gpu-1.20.1.tgz
+
+ENV APP_BUILD_HASH=${BUILD_HASH}
+RUN npm run build
+
+######## WebUI backend ########
+FROM python:3.11-slim-bookworm AS base
+
+# Use args
+ARG USE_CUDA
+ARG USE_OLLAMA
+ARG USE_CUDA_VER
+ARG USE_EMBEDDING_MODEL
+ARG USE_RERANKING_MODEL
+ARG UID
+ARG GID
+
+## Basis ##
+ENV ENV=prod \
+    PORT=8080 \
+    # pass build args to the build
+    USE_OLLAMA_DOCKER=${USE_OLLAMA} \
+    USE_CUDA_DOCKER=${USE_CUDA} \
+    USE_CUDA_DOCKER_VER=${USE_CUDA_VER} \
+    USE_EMBEDDING_MODEL_DOCKER=${USE_EMBEDDING_MODEL} \
+    USE_RERANKING_MODEL_DOCKER=${USE_RERANKING_MODEL}
+
+## Basis URL Config ##
+ENV OLLAMA_BASE_URL="/ollama" \
+    OPENAI_API_BASE_URL=""
+
+## API Key and Security Config ##
+ENV OPENAI_API_KEY="" \
+    WEBUI_SECRET_KEY="" \
+    SCARF_NO_ANALYTICS=true \
+    DO_NOT_TRACK=true \
+    ANONYMIZED_TELEMETRY=false
+
+#### Other models #########################################################
+## whisper TTS model settings ##
+ENV WHISPER_MODEL="base" \
+    WHISPER_MODEL_DIR="/app/backend/data/cache/whisper/models"
+
+## RAG Embedding model settings ##
+ENV RAG_EMBEDDING_MODEL="$USE_EMBEDDING_MODEL_DOCKER" \
+    RAG_RERANKING_MODEL="$USE_RERANKING_MODEL_DOCKER" \
+    SENTENCE_TRANSFORMERS_HOME="/app/backend/data/cache/embedding/models"
+
+## Tiktoken model settings ##
+ENV TIKTOKEN_ENCODING_NAME="cl100k_base" \
+    TIKTOKEN_CACHE_DIR="/app/backend/data/cache/tiktoken"
+
+## Hugging Face download cache ##
+ENV HF_HOME="/app/backend/data/cache/embedding/models"
+
+## Torch Extensions ##
+# ENV TORCH_EXTENSIONS_DIR="/.cache/torch_extensions"
+
+#### Other models ##########################################################
+
+COPY --from=build /app/backend /app/backend
+
+WORKDIR /app/backend
 
-WORKDIR /root/
 
 ENV HOME=/root
-ENV VIRTUAL_ENV=$HOME/.env/open-webui
+# Create user and group if not root
+RUN if [ $UID -ne 0 ]; then \
+    if [ $GID -ne 0 ]; then \
+    addgroup --gid $GID app; \
+    fi; \
+    adduser --uid $UID --gid $GID --home $HOME --disabled-password --no-create-home app; \
+    fi
 
-COPY open_webui_patches /root/patches
+RUN mkdir -p $HOME/.cache/chroma
+RUN printf 00000000-0000-0000-0000-000000000000 > $HOME/.cache/chroma/telemetry_user_id
 
-RUN git clone https://github.com/open-webui/open-webui.git && \
-    git config --global user.name "opea" && git config --global user.email "" && \
-    mkdir -p $HOME/.env && python3 -m venv $VIRTUAL_ENV && \
-    $VIRTUAL_ENV/bin/python -m pip install --no-cache-dir --upgrade pip && \
-    $VIRTUAL_ENV/bin/python -m pip install --no-cache-dir build
+# Make sure the user has access to the app and root directory
+RUN chown -R $UID:$GID /app $HOME
 
-WORKDIR /root/open-webui
+SHELL ["/bin/bash", "-o", "pipefail", "-c"]
 
-ENV PATH="$VIRTUAL_ENV/bin:$PATH"
+RUN if [ "$USE_OLLAMA" = "true" ]; then \
+    apt-get update && \
+    # Install pandoc and netcat
+    apt-get install -y --no-install-recommends git build-essential pandoc netcat-openbsd curl && \
+    apt-get install -y --no-install-recommends gcc python3-dev && \
+    # for RAG OCR
+    apt-get install -y --no-install-recommends ffmpeg libsm6 libxext6 && \
+    # install helper tools
+    apt-get install -y --no-install-recommends curl jq && \
+    # install ollama
+    curl -fsSL https://ollama.com/install.sh | sh && \
+    # cleanup
+    rm -rf /var/lib/apt/lists/*; \
+    else \
+    apt-get update && \
+    # Install pandoc, netcat and gcc
+    apt-get install -y --no-install-recommends git build-essential pandoc gcc netcat-openbsd curl jq && \
+    apt-get install -y --no-install-recommends gcc python3-dev && \
+    # for RAG OCR
+    apt-get install -y --no-install-recommends ffmpeg libsm6 libxext6 && \
+    # cleanup
+    rm -rf /var/lib/apt/lists/*; \
+    fi
 
-RUN git checkout v0.5.20 && \
-    git am ../patches/*.patch && \
-    python -m build && \
-    pip install --no-cache-dir dist/open_webui-0.5.20-py3-none-any.whl    
+# install python dependencies
+# COPY --chown=$UID:$GID ./backend/requirements.txt ./requirements.txt
+# RUN cp /app/backend/requirements.txt ./requirements.txt
 
-ENV LANG=en_US.UTF-8
-
-WORKDIR /root/
-
-RUN rm -fr /root/open-webui && rm -fr /root/patches
-
-# CMD ["/bin/bash"]
-ENTRYPOINT ["open-webui", "serve"]
+RUN pip3 install --no-cache-dir uv && \
+    if [ "$USE_CUDA" = "true" ]; then \
+    # If you use CUDA the whisper and embedding model will be downloaded on first use
+    pip3 install torch torchvision torchaudio --index-url https://download.pytorch.org/whl/$USE_CUDA_DOCKER_VER --no-cache-dir && \
+    uv pip install --system -r requirements.txt --no-cache-dir && \
+    python -c "import os; from sentence_transformers import SentenceTransformer; SentenceTransformer(os.environ['RAG_EMBEDDING_MODEL'], device='cpu')" && \
+    python -c "import os; from faster_whisper import WhisperModel; WhisperModel(os.environ['WHISPER_MODEL'], device='cpu', compute_type='int8', download_root=os.environ['WHISPER_MODEL_DIR'])"; \
+    python -c "import os; import tiktoken; tiktoken.get_encoding(os.environ['TIKTOKEN_ENCODING_NAME'])"; \
+    else \
+    pip3 install torch torchvision torchaudio --index-url https://download.pytorch.org/whl/cpu --no-cache-dir && \
+    uv pip install --system -r requirements.txt --no-cache-dir && \
+    python -c "import os; from sentence_transformers import SentenceTransformer; SentenceTransformer(os.environ['RAG_EMBEDDING_MODEL'], device='cpu')" && \
+    python -c "import os; from faster_whisper import WhisperModel; WhisperModel(os.environ['WHISPER_MODEL'], device='cpu', compute_type='int8', download_root=os.environ['WHISPER_MODEL_DIR'])"; \
+    python -c "import os; import tiktoken; tiktoken.get_encoding(os.environ['TIKTOKEN_ENCODING_NAME'])"; \
+    fi; \
+    chown -R $UID:$GID /app/backend/data/
 
 
+
+# copy embedding weight from build
+# RUN mkdir -p /root/.cache/chroma/onnx_models/all-MiniLM-L6-v2
+# COPY --from=build /app/onnx /root/.cache/chroma/onnx_models/all-MiniLM-L6-v2/onnx
+
+# copy built frontend files
+COPY --chown=$UID:$GID --from=build /app/build /app/build
+COPY --chown=$UID:$GID --from=build /app/CHANGELOG.md /app/CHANGELOG.md
+COPY --chown=$UID:$GID --from=build /app/package.json /app/package.json
+
+# copy backend files
+# COPY --chown=$UID:$GID ./backend .
+
+EXPOSE 8080
+
+HEALTHCHECK CMD curl --silent --fail http://localhost:${PORT:-8080}/health | jq -ne 'input.status == true' || exit 1
+
+USER $UID:$GID
+
+ARG BUILD_HASH
+ENV WEBUI_BUILD_VERSION=${BUILD_HASH}
+ENV DOCKER=true
+
+CMD [ "bash", "start.sh"]

AudioQnA/Dockerfile

@@ -3,7 +3,6 @@
 
 ARG IMAGE_REPO=opea
 ARG BASE_TAG=latest
-FROM opea/comps-base:$BASE_TAG
 FROM $IMAGE_REPO/comps-base:$BASE_TAG
 
 COPY ./audioqna.py $HOME/audioqna.py

AudioQnA/Dockerfile.multilang

@@ -3,7 +3,6 @@
 
 ARG IMAGE_REPO=opea
 ARG BASE_TAG=latest
-FROM opea/comps-base:$BASE_TAG
 FROM $IMAGE_REPO/comps-base:$BASE_TAG
 
 COPY ./audioqna_multilang.py $HOME/audioqna_multilang.py

AudioQnA/docker_compose/amd/gpu/rocm/README.md

@@ -1,120 +1,59 @@
-# Build Mega Service of AudioQnA on AMD ROCm GPU
+# Deploying 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.
+This document outlines the single node deployment process for a AudioQnA application utilizing the [GenAIComps](https://github.com/opea-project/GenAIComps.git) microservices on server with AMD ROCm processing accelerators. The steps include pulling Docker images, container deployment via Docker Compose, and service execution using microservices `llm`.
 
-## Build Docker Images
+Note: The default LLM is `Intel/neural-chat-7b-v3-3`. Before deploying the application, please make sure either you've requested and been granted the access to it on [Huggingface](https://huggingface.co/meta-llama/Meta-Llama-3-8B-Instruct) or you've downloaded the model locally from [ModelScope](https://www.modelscope.cn/models).
 
-### 1. Build Docker Image
+## Table of Contents
 
-- #### Create application install directory and go to it:
+1. [AudioQnA Quick Start Deployment](#audioqna-quick-start-deployment)
+2. [AudioQnA Docker Compose Files](#audioqna-docker-compose-files)
+3. [Validate Microservices](#validate-microservices)
+4. [Conclusion](#conclusion)
 
-  ```bash
-  mkdir ~/audioqna-install && cd audioqna-install
-  ```
+## AudioQnA Quick Start Deployment
 
-- #### Clone the repository GenAIExamples (the default repository branch "main" is used here):
+This section describes how to quickly deploy and test the AudioQnA service manually on an AMD ROCm platform. The basic steps are:
 
-  ```bash
-  git clone https://github.com/opea-project/GenAIExamples.git
-  ```
+1. [Access the Code](#access-the-code)
+2. [Configure the Deployment Environment](#configure-the-deployment-environment)
+3. [Deploy the Services Using Docker Compose](#deploy-the-services-using-docker-compose)
+4. [Check the Deployment Status](#check-the-deployment-status)
+5. [Validate the Pipeline](#validate-the-pipeline)
+6. [Cleanup the Deployment](#cleanup-the-deployment)
 
-  If you need to use a specific branch/tag of the GenAIExamples repository, then (v1.3 replace with its own value):
+### Access the Code
 
-  ```bash
-  git clone https://github.com/opea-project/GenAIExamples.git && cd GenAIExamples && git checkout v1.3
-  ```
-
-  We remind you that when using a specific version of the code, you need to use the README from this version:
-
-- #### Go to build directory:
-
-  ```bash
-  cd ~/audioqna-install/GenAIExamples/AudioQnA/docker_image_build
-  ```
-
-- Cleaning up the GenAIComps repository if it was previously cloned in this directory.
-  This is necessary if the build was performed earlier and the GenAIComps folder exists and is not empty:
-
-  ```bash
-  echo Y | rm -R GenAIComps
-  ```
-
-- #### Clone the repository GenAIComps (the default repository branch "main" is used here):
+Clone the GenAIExample repository and access the AudioQnA AMD ROCm platform Docker Compose files and supporting scripts:
 
 ```bash
-git clone https://github.com/opea-project/GenAIComps.git
-cd GenAIComps
+git clone https://github.com/opea-project/GenAIExamples.git
+cd GenAIExamples/AudioQnA
 ```
 
-We remind you that when using a specific version of the code, you need to use the README from this version.
+Then checkout a released version, such as v1.3:
 
-- #### Setting the list of images for the build (from the build file.yaml)
+```bash
+git checkout v1.3
+```
 
-  If you want to deploy a vLLM-based or TGI-based application, then the set of services is installed as follows:
+### Configure the Deployment Environment
 
-  #### vLLM-based application
+#### Docker Compose GPU Configuration
 
-  ```bash
-  service_list="vllm-rocm whisper speecht5 audioqna audioqna-ui"
-  ```
+Consult the section on [AudioQnA Service configuration](#audioqna-configuration) for information on how service specific configuration parameters affect deployments.
 
-  #### TGI-based application
-
-  ```bash
-  service_list="whisper speecht5 audioqna audioqna-ui"
-  ```
-
-- #### Optional. Pull TGI Docker Image (Do this if you want to use TGI)
-
-  ```bash
-  docker pull ghcr.io/huggingface/text-generation-inference:2.3.1-rocm
-  ```
-
-- #### Build Docker Images
-
-  ```bash
-  docker compose -f build.yaml build ${service_list} --no-cache
-  ```
-
-  After the build, we check the list of images with the command:
-
-  ```bash
-  docker image ls
-  ```
-
-  The list of images should include:
-
-  ##### vLLM-based application:
-
-  - opea/vllm-rocm:latest
-    - opea/whisper:latest
-    - opea/speecht5:latest
-    - opea/audioqna:latest
-
-  ##### TGI-based application:
-
-  - ghcr.io/huggingface/text-generation-inference:2.3.1-rocm
-    - opea/whisper:latest
-    - opea/speecht5:latest
-    - opea/audioqna:latest
-
----
-
-## Deploy the AudioQnA Application
-
-### Docker Compose Configuration for AMD GPUs
-
-To enable GPU support for AMD GPUs, the following configuration is added to the Docker Compose file:
-
-- compose_vllm.yaml - for vLLM-based application
-- compose.yaml - for TGI-based
+To enable GPU support for AMD GPUs, the following configuration is added to the Docker Compose files (`compose.yaml`, `compose_vllm.yaml`) for the LLM serving container:
 
 ```yaml
+# Example for vLLM service in compose_vllm.yaml
+# Note: Modern docker compose might use deploy.resources syntax instead.
+# Check your docker version and compose file.
 shm_size: 1g
 devices:
   - /dev/kfd:/dev/kfd
   - /dev/dri/:/dev/dri/
+# - /dev/dri/render128:/dev/dri/render128
 cap_add:
   - SYS_PTRACE
 group_add:
@@ -123,131 +62,161 @@ security_opt:
   - seccomp:unconfined
 ```
 
-This configuration forwards all available GPUs to the container. To use a specific GPU, specify its `cardN` and `renderN` device IDs. For example:
+#### Environment Variables (`set_env*.sh`)
 
-```yaml
-shm_size: 1g
-devices:
-  - /dev/kfd:/dev/kfd
-  - /dev/dri/card0:/dev/dri/card0
-  - /dev/dri/render128:/dev/dri/render128
-cap_add:
-  - SYS_PTRACE
-group_add:
-  - video
-security_opt:
-  - seccomp:unconfined
-```
+These scripts (`set_env_vllm.sh` for vLLM, `set_env.sh` for TGI) configure crucial parameters passed to the containers.
 
-**How to Identify GPU Device IDs:**
-Use AMD GPU driver utilities to determine the correct `cardN` and `renderN` IDs for your GPU.
+To set up environment variables for deploying AudioQnA services, set up some parameters specific to the deployment environment and source the `set_env.sh` script in this directory:
 
-### Set deploy environment variables
-
-#### Setting variables in the operating system environment:
-
-##### Set variable HUGGINGFACEHUB_API_TOKEN:
+For TGI inference usage:
 
 ```bash
-### Replace the string 'your_huggingfacehub_token' with your HuggingFacehub repository access token.
-export HUGGINGFACEHUB_API_TOKEN='your_huggingfacehub_token'
+export host_ip="External_Public_IP"           # ip address of the node
+export HUGGINGFACEHUB_API_TOKEN="Your_HuggingFace_API_Token"
+export http_proxy="Your_HTTP_Proxy"           # http proxy if any
+export https_proxy="Your_HTTPs_Proxy"         # https proxy if any
+export no_proxy=localhost,127.0.0.1,$host_ip,whisper-service,speecht5-service,vllm-service,tgi-service,audioqna-xeon-backend-server,audioqna-xeon-ui-server  # additional no proxies if needed
+export NGINX_PORT=${your_nginx_port}          # your usable port for nginx, 80 for example
+source ./set_env.sh
 ```
 
-#### Set variables value in set_env\*\*\*\*.sh file:
-
-Go to Docker Compose directory:
+For vLLM inference usage
 
 ```bash
-cd ~/audioqna-install/GenAIExamples/AudioQnA/docker_compose/amd/gpu/rocm
+export host_ip="External_Public_IP"           # ip address of the node
+export HUGGINGFACEHUB_API_TOKEN="Your_HuggingFace_API_Token"
+export http_proxy="Your_HTTP_Proxy"           # http proxy if any
+export https_proxy="Your_HTTPs_Proxy"         # https proxy if any
+export no_proxy=localhost,127.0.0.1,$host_ip,whisper-service,speecht5-service,vllm-service,tgi-service,audioqna-xeon-backend-server,audioqna-xeon-ui-server  # additional no proxies if needed
+export NGINX_PORT=${your_nginx_port}          # your usable port for nginx, 80 for example
+source ./set_env_vllm.sh
 ```
 
-The example uses the Nano text editor. You can use any convenient text editor:
+### Deploy the Services Using Docker Compose
 
-#### If you use vLLM
-
-```bash
-nano set_env_vllm.sh
-```
-
-#### If you use TGI
-
-```bash
-nano set_env.sh
-```
-
-If you are in a proxy environment, also set the proxy-related environment variables:
-
-```bash
-export http_proxy="Your_HTTP_Proxy"
-export https_proxy="Your_HTTPs_Proxy"
-```
-
-Set the values of the variables:
-
-- **HOST_IP, HOST_IP_EXTERNAL** - These variables are used to configure the name/address of the service in the operating system environment for the application services to interact with each other and with the outside world.
-
-  If your server uses only an internal address and is not accessible from the Internet, then the values for these two variables will be the same and the value will be equal to the server's internal name/address.
-
-  If your server uses only an external, Internet-accessible address, then the values for these two variables will be the same and the value will be equal to the server's external name/address.
-
-  If your server is located on an internal network, has an internal address, but is accessible from the Internet via a proxy/firewall/load balancer, then the HOST_IP variable will have a value equal to the internal name/address of the server, and the EXTERNAL_HOST_IP variable will have a value equal to the external name/address of the proxy/firewall/load balancer behind which the server is located.
-
-  We set these values in the file set_env\*\*\*\*.sh
-
-- **Variables with names like "**\*\*\*\*\*\*\_PORT"\*\* - These variables set the IP port numbers for establishing network connections to the application services.
-  The values shown in the file set_env.sh or set_env_vllm they are the values used for the development and testing of the application, as well as configured for the environment in which the development is performed. These values must be configured in accordance with the rules of network access to your environment's server, and must not overlap with the IP ports of other applications that are already in use.
-
-#### Set variables with script set_env\*\*\*\*.sh
-
-#### If you use vLLM
-
-```bash
-. set_env_vllm.sh
-```
-
-#### If you use TGI
-
-```bash
-. set_env.sh
-```
-
-### Start the services:
-
-#### If you use vLLM
-
-```bash
-docker compose -f compose_vllm.yaml up -d
-```
-
-#### If you use TGI
+To deploy the AudioQnA services, execute the `docker compose up` command with the appropriate arguments. For a default deployment, execute the command below. It uses the 'compose.yaml' file.
+
+for TGI inference deployment
 
 ```bash
+cd docker_compose/amd/gpu/rocm
 docker compose -f compose.yaml up -d
 ```
 
-All containers should be running and should not restart:
+for vLLM inference deployment
 
-##### If you use vLLM:
+```bash
+cd docker_compose/amd/gpu/rocm
+docker compose -f compose_vllm.yaml up -d
+```
 
-- audioqna-vllm-service
-- whisper-service
-- speecht5-service
-- audioqna-backend-server
-- audioqna-ui-server
+> **Note**: developers should build docker image from source when:
+>
+> - Developing off the git main branch (as the container's ports in the repo may be different > from the published docker image).
+> - Unable to download the docker image.
+> - Use a specific version of Docker image.
 
-##### If you use TGI:
+Please refer to the table below to build different microservices from source:
 
-- audioqna-tgi-service
-- whisper-service
-- speecht5-service
-- audioqna-backend-server
-- audioqna-ui-server
+| Microservice | Deployment Guide                                                                                                                  |
+| ------------ | --------------------------------------------------------------------------------------------------------------------------------- |
+| vLLM         | [vLLM build guide](https://github.com/opea-project/GenAIComps/tree/main/comps/third_parties/vllm#build-docker)                    |
+| LLM          | [LLM build guide](https://github.com/opea-project/GenAIComps/tree/main/comps/llms)                                                |
+| WHISPER      | [Whisper build guide](https://github.com/opea-project/GenAIComps/tree/main/comps/asr/src#211-whisper-server-image)                |
+| SPEECHT5     | [SpeechT5 build guide](https://github.com/opea-project/GenAIComps/tree/main/comps/tts/src#211-speecht5-server-image)              |
+| GPT-SOVITS   | [GPT-SOVITS build guide](https://github.com/opea-project/GenAIComps/tree/main/comps/third_parties/gpt-sovits/src#build-the-image) |
+| MegaService  | [MegaService build guide](../../../../README_miscellaneous.md#build-megaservice-docker-image)                                     |
+| UI           | [Basic UI build guide](../../../../README_miscellaneous.md#build-ui-docker-image)                                                 |
 
----
+### Check the Deployment Status
 
-## Validate the Services
+After running docker compose, check if all the containers launched via docker compose have started:
 
-### 1. Validate the vLLM/TGI Service
+#### For TGI inference deployment
+
+```bash
+docker ps -a
+```
+
+For the default deployment, the following 5 containers should have started:
+
+```
+CONTAINER ID   IMAGE                                                      COMMAND                  CREATED          STATUS          PORTS                                         NAMES
+d8007690868d   opea/audioqna:latest                                       "python audioqna.py"     21 seconds ago   Up 19 seconds   0.0.0.0:3008->8888/tcp, [::]:3008->8888/tcp   audioqna-rocm-backend-server
+87ba9a1d56ae   ghcr.io/huggingface/text-generation-inference:2.4.1-rocm   "/tgi-entrypoint.sh …"   21 seconds ago   Up 20 seconds   0.0.0.0:3006->80/tcp, [::]:3006->80/tcp       tgi-service
+59e869acd742   opea/speecht5:latest                                       "python speecht5_ser…"   21 seconds ago   Up 20 seconds   0.0.0.0:7055->7055/tcp, :::7055->7055/tcp     speecht5-service
+0143267a4327   opea/whisper:latest                                        "python whisper_serv…"   21 seconds ago   Up 20 seconds   0.0.0.0:7066->7066/tcp, :::7066->7066/tcp     whisper-service
+```
+
+### For vLLM inference deployment
+
+```bash
+docker ps -a
+```
+
+For the default deployment, the following 5 containers should have started:
+
+```
+CONTAINER ID   IMAGE                     COMMAND                  CREATED          STATUS          PORTS                                           NAMES
+f3e6893a69fa   opea/audioqna-ui:latest   "docker-entrypoint.s…"   37 seconds ago   Up 35 seconds   0.0.0.0:18039->5173/tcp, [::]:18039->5173/tcp   audioqna-ui-server
+f943e5cd21e9   opea/audioqna:latest      "python audioqna.py"     37 seconds ago   Up 35 seconds   0.0.0.0:18038->8888/tcp, [::]:18038->8888/tcp   audioqna-backend-server
+074e8c418f52   opea/speecht5:latest      "python speecht5_ser…"   37 seconds ago   Up 36 seconds   0.0.0.0:7055->7055/tcp, :::7055->7055/tcp       speecht5-service
+77abe498e427   opea/vllm-rocm:latest     "python3 /workspace/…"   37 seconds ago   Up 36 seconds   0.0.0.0:8081->8011/tcp, [::]:8081->8011/tcp     audioqna-vllm-service
+9074a95bb7a6   opea/whisper:latest       "python whisper_serv…"   37 seconds ago   Up 36 seconds   0.0.0.0:7066->7066/tcp, :::7066->7066/tcp       whisper-service
+```
+
+If any issues are encountered during deployment, refer to the [Troubleshooting](../../../../README_miscellaneous.md#troubleshooting) section.
+
+### Validate the Pipeline
+
+Once the AudioQnA services are running, test the pipeline using the following command:
+
+```bash
+# 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.
+wget https://github.com/intel/intel-extension-for-transformers/raw/refs/heads/main/intel_extension_for_transformers/neural_chat/assets/audio/sample_2.wav
+base64_audio=$(base64 -w 0 sample_2.wav)
+
+# if you are using speecht5 as the tts service, voice can be "default" or "male"
+# if you are using gpt-sovits for the tts service, you can set the reference audio following https://github.com/opea-project/GenAIComps/blob/main/comps/third_parties/gpt-sovits/src/README.md
+
+curl http://${host_ip}:3008/v1/audioqna \
+  -X POST \
+  -H "Content-Type: application/json" \
+  -d "{\"audio\": \"${base64_audio}\", \"max_tokens\": 64, \"voice\": \"default\"}" \
+  | sed 's/^"//;s/"$//' | base64 -d > output.wav
+```
+
+**Note** : Access the AudioQnA UI by web browser through this URL: `http://${host_ip}:5173`. Please confirm the `5173` port is opened in the firewall. To validate each microservice used in the pipeline refer to the [Validate Microservices](#validate-microservices) section.
+
+### Cleanup the Deployment
+
+To stop the containers associated with the deployment, execute the following command:
+
+#### If you use vLLM
+
+```bash
+cd ~/audioqna-install/GenAIExamples/AudioQnA/docker_compose/amd/gpu/rocm
+docker compose -f compose_vllm.yaml down
+```
+
+#### If you use TGI
+
+```bash
+cd ~/audioqna-install/GenAIExamples/AudioQnA/docker_compose/amd/gpu/rocm
+docker compose -f compose.yaml down
+```
+
+## AudioQnA Docker Compose Files
+
+In the context of deploying an AudioQnA pipeline on an Intel® Xeon® platform, we can pick and choose different large language model serving frameworks, or single English TTS/multi-language TTS component. The table below outlines the various configurations that are available as part of the application. These configurations can be used as templates and can be extended to different components available in [GenAIComps](https://github.com/opea-project/GenAIComps.git).
+
+| File                                     | Description                                                                               |
+| ---------------------------------------- | ----------------------------------------------------------------------------------------- |
+| [compose_vllm.yaml](./compose_vllm.yaml) | Default compose file using vllm as serving framework and redis as vector database         |
+| [compose.yaml](./compose.yaml)           | The LLM serving framework is TGI. All other configurations remain the same as the default |
+
+### Validate the vLLM/TGI Service
 
 #### If you use vLLM:
 
@@ -313,7 +282,7 @@ Checking the response from the service. The response should be similar to JSON:
 If the service response has a meaningful response in the value of the "generated_text" key,
 then we consider the TGI service to be successfully launched
 
-### 2. Validate MegaServices
+### Validate MegaServices
 
 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
@@ -327,7 +296,7 @@ curl http://${host_ip}:3008/v1/audioqna \
   -H 'Content-Type: application/json' | sed 's/^"//;s/"$//' | base64 -d > output.wav
 ```
 
-### 3. Validate MicroServices
+### Validate MicroServices
 
 ```bash
 # whisper service
@@ -343,18 +312,6 @@ curl http://${host_ip}:7055/v1/tts \
   -H 'Content-Type: application/json'
 ```
 
-### 4. Stop application
+## Conclusion
 
-#### If you use vLLM
-
-```bash
-cd ~/audioqna-install/GenAIExamples/AudioQnA/docker_compose/amd/gpu/rocm
-docker compose -f compose_vllm.yaml down
-```
-
-#### If you use TGI
-
-```bash
-cd ~/audioqna-install/GenAIExamples/AudioQnA/docker_compose/amd/gpu/rocm
-docker compose -f compose.yaml down
-```
+This guide should enable developers to deploy the default configuration or any of the other compose yaml files for different configurations. It also highlights the configurable parameters that can be set before deployment.

AvatarChatbot/docker_compose/amd/gpu/rocm/compose.yaml

@@ -42,7 +42,7 @@ services:
     environment:
       TTS_ENDPOINT: ${TTS_ENDPOINT}
   tgi-service:
-    image: ghcr.io/huggingface/text-generation-inference:2.3.1-rocm
+    image: ghcr.io/huggingface/text-generation-inference:2.4.1-rocm
     container_name: tgi-service
     ports:
       - "${TGI_SERVICE_PORT:-3006}:80"
@@ -66,24 +66,6 @@ services:
       - seccomp:unconfined
     ipc: host
     command: --model-id ${LLM_MODEL_ID} --max-input-length 4096 --max-total-tokens 8192
-  llm:
-    image: ${REGISTRY:-opea}/llm-textgen:${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}
-      LLM_ENDPOINT: ${TGI_LLM_ENDPOINT}
-      HUGGINGFACEHUB_API_TOKEN: ${HUGGINGFACEHUB_API_TOKEN}
-      HF_TOKEN: ${HUGGINGFACEHUB_API_TOKEN}
-      OPENAI_API_KEY: ${OPENAI_API_KEY}
-    restart: unless-stopped
   wav2lip-service:
     image: ${REGISTRY:-opea}/wav2lip:${TAG:-latest}
     container_name: wav2lip-service
@@ -125,7 +107,7 @@ services:
     container_name: avatarchatbot-backend-server
     depends_on:
       - asr
-      - llm
+      - tgi-service
       - tts
       - animation
     ports:

AvatarChatbot/docker_compose/amd/gpu/rocm/set_env.sh

@@ -30,7 +30,7 @@ export ANIMATION_SERVICE_HOST_IP=${host_ip}
 export MEGA_SERVICE_PORT=8888
 export ASR_SERVICE_PORT=3001
 export TTS_SERVICE_PORT=3002
-export LLM_SERVICE_PORT=3007
+export LLM_SERVICE_PORT=3006
 export ANIMATION_SERVICE_PORT=3008
 
 export DEVICE="cpu"

AvatarChatbot/tests/test_compose_on_rocm.sh

@@ -27,7 +27,7 @@ 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="avatarchatbot whisper asr llm-textgen speecht5 tts wav2lip animation"
+    service_list="avatarchatbot whisper asr speecht5 tts wav2lip animation"
     docker compose -f build.yaml build ${service_list} --no-cache > ${LOG_PATH}/docker_image_build.log
 
     docker pull ghcr.io/huggingface/text-generation-inference:2.3.1-rocm
@@ -65,7 +65,7 @@ function start_services() {
     export MEGA_SERVICE_PORT=8888
     export ASR_SERVICE_PORT=3001
     export TTS_SERVICE_PORT=3002
-    export LLM_SERVICE_PORT=3007
+    export LLM_SERVICE_PORT=3006
     export ANIMATION_SERVICE_PORT=3008
 
     export DEVICE="cpu"

ChatQnA/benchmark/performance/kubernetes/intel/gaudi/README.md

@@ -1,192 +0,0 @@
-# ChatQnA Benchmarking
-
-This folder contains a collection of Kubernetes manifest files for deploying the ChatQnA service across scalable nodes. It includes a comprehensive [benchmarking tool](https://github.com/opea-project/GenAIEval/blob/main/evals/benchmark/README.md) that enables throughput analysis to assess inference performance.
-
-By following this guide, you can run benchmarks on your deployment and share the results with the OPEA community.
-
-## Purpose
-
-We aim to run these benchmarks and share them with the OPEA community for three primary reasons:
-
-- To offer insights on inference throughput in real-world scenarios, helping you choose the best service or deployment for your needs.
-- To establish a baseline for validating optimization solutions across different implementations, providing clear guidance on which methods are most effective for your use case.
-- To inspire the community to build upon our benchmarks, allowing us to better quantify new solutions in conjunction with current leading llms, serving frameworks etc.
-
-## Metrics
-
-The benchmark will report the below metrics, including:
-
-- Number of Concurrent Requests
-- End-to-End Latency: P50, P90, P99 (in milliseconds)
-- End-to-End First Token Latency: P50, P90, P99 (in milliseconds)
-- Average Next Token Latency (in milliseconds)
-- Average Token Latency (in milliseconds)
-- Requests Per Second (RPS)
-- Output Tokens Per Second
-- Input Tokens Per Second
-
-Results will be displayed in the terminal and saved as CSV file named `1_stats.csv` for easy export to spreadsheets.
-
-## Table of Contents
-
-- [Deployment](#deployment)
-  - [Prerequisites](#prerequisites)
-  - [Deployment Scenarios](#deployment-scenarios)
-    - [Case 1: Baseline Deployment with Rerank](#case-1-baseline-deployment-with-rerank)
-    - [Case 2: Baseline Deployment without Rerank](#case-2-baseline-deployment-without-rerank)
-    - [Case 3: Tuned Deployment with Rerank](#case-3-tuned-deployment-with-rerank)
-- [Benchmark](#benchmark)
-  - [Test Configurations](#test-configurations)
-  - [Test Steps](#test-steps)
-    - [Upload Retrieval File](#upload-retrieval-file)
-    - [Run Benchmark Test](#run-benchmark-test)
-    - [Data collection](#data-collection)
-- [Teardown](#teardown)
-
-## Deployment
-
-### Prerequisites
-
-- Kubernetes installation: Use [kubespray](https://github.com/opea-project/docs/blob/main/guide/installation/k8s_install/k8s_install_kubespray.md) or other official Kubernetes installation guides: 
-- (Optional) [Kubernetes set up guide on Intel Gaudi product](https://github.com/opea-project/GenAIInfra/blob/main/README.md#setup-kubernetes-cluster) 
-- Helm installation: Follow the [Helm documentation](https://helm.sh/docs/intro/install/#helm) to install Helm.
-- Setup Hugging Face Token
-
-  To access models and APIs from Hugging Face, set your token as environment variable.
-  ```bash
-  export HF_TOKEN="insert-your-huggingface-token-here"
-  ```
-- Prepare Shared Models (Optional but Strongly Recommended)
-
-  Downloading models simultaneously to multiple nodes in your cluster can overload resources such as network bandwidth, memory and storage. To prevent resource exhaustion, it's recommended to preload the models in advance.
-  ```bash
-  pip install -U "huggingface_hub[cli]"
-  sudo mkdir -p /mnt/models
-  sudo chmod 777 /mnt/models
-  huggingface-cli download --cache-dir /mnt/models Intel/neural-chat-7b-v3-3
-  export MODEL_DIR=/mnt/models
-  ```
-  Once the models are downloaded, you can consider the following methods for sharing them across nodes:
-  - Persistent Volume Claim (PVC): This is the recommended approach for production setups. For more details on using PVC, refer to [PVC](https://github.com/opea-project/GenAIInfra/blob/main/helm-charts/README.md#using-persistent-volume).
-  - Local Host Path: For simpler testing, ensure that each node involved in the deployment follows the steps above to locally prepare the models. After preparing the models, use `--set global.modelUseHostPath=${MODELDIR}` in the deployment command.
-
-- Label Nodes
-  ```base
-  python deploy.py --add-label --num-nodes 2
-  ```
-
-### Deployment Scenarios
-
-The example below are based on a two-node setup. You can adjust the number of nodes by using the `--num-nodes` option.
-
-By default, these commands use the `default` namespace. To specify a different namespace, use the `--namespace` flag with deploy, uninstall, and kubernetes command. Additionally, update the `namespace` field in `benchmark.yaml` before running the benchmark test.
-
-For additional configuration options, run `python deploy.py --help`
-
-#### Case 1: Baseline Deployment with Rerank
-
-Deploy Command (with node number, Hugging Face token, model directory specified):
-```bash
-python deploy.py --hf-token $HF_TOKEN --model-dir $MODEL_DIR --num-nodes 2 --with-rerank
-```
-Uninstall Command:
-```bash
-python deploy.py --uninstall
-```
-
-#### Case 2: Baseline Deployment without Rerank
-
-```bash
-python deploy.py --hf-token $HFTOKEN --model-dir $MODELDIR --num-nodes 2
-```
-#### Case 3: Tuned Deployment with Rerank
-
-```bash
-python deploy.py --hf-token $HFTOKEN --model-dir $MODELDIR --num-nodes 2 --with-rerank --tuned
-```
-
-## Benchmark
-
-### Test Configurations
-
-| Key      | Value   |
-| -------- | ------- |
-| Workload | ChatQnA |
-| Tag      | V1.1    |
-
-Models configuration
-| Key | Value |
-| ---------- | ------------------ |
-| Embedding | BAAI/bge-base-en-v1.5 |
-| Reranking | BAAI/bge-reranker-base |
-| Inference | Intel/neural-chat-7b-v3-3 |
-
-Benchmark parameters
-| Key | Value |
-| ---------- | ------------------ |
-| LLM input tokens | 1024 |
-| LLM output tokens | 128 |
-
-Number of test requests for different scheduled node number:
-| Node count | Concurrency | Query number |
-| ----- | -------- | -------- |
-| 1 | 128 | 640 |
-| 2 | 256 | 1280 |
-| 4 | 512 | 2560 |
-
-More detailed configuration can be found in configuration file [benchmark.yaml](./benchmark.yaml).
-
-### Test Steps
-
-Use `kubectl get pods` to confirm that all pods are `READY` before starting the test.
-
-#### Upload Retrieval File
-
-Before testing, upload a specified file to make sure the llm input have the token length of 1k.
-
-Get files:
-
-```bash
-wget https://github.com/opea-project/GenAIEval/tree/main/evals/benchmark/data/upload_file.txt
-```
-
-Retrieve the `ClusterIP` of the `chatqna-data-prep` service.
-
-```bash
-kubectl get svc
-```
-Expected output:
-```log
-chatqna-data-prep         ClusterIP   xx.xx.xx.xx    <none>        6007/TCP            51m
-```
-
-Use the following `cURL` command to upload file:
-
-```bash
-cd GenAIEval/evals/benchmark/data
-curl -X POST "http://${cluster_ip}:6007/v1/dataprep/ingest" \
-     -H "Content-Type: multipart/form-data" \
-     -F "chunk_size=3800" \
-     -F "files=@./upload_file.txt"
-```
-
-#### Run Benchmark Test
-
-Run the benchmark test using:
-```bash
-bash benchmark.sh -n 2
-```
-The `-n` argument specifies the number of test nodes. Required dependencies will be automatically installed when running the benchmark for the first time.
-
-#### Data collection
-
-All the test results will come to the folder `GenAIEval/evals/benchmark/benchmark_output`.
-
-## Teardown
-
-After completing the benchmark, use the following command to clean up the environment:
-
-Remove Node Labels:
-```bash
-python deploy.py --delete-label
-```

ChatQnA/benchmark/performance/kubernetes/intel/gaudi/benchmark.sh

@@ -1,102 +0,0 @@
-#!/bin/bash
-
-# Copyright (C) 2024 Intel Corporation
-# SPDX-License-Identifier: Apache-2.0
-
-deployment_type="k8s"
-node_number=1
-service_port=8888
-query_per_node=640
-
-benchmark_tool_path="$(pwd)/GenAIEval"
-
-usage() {
-    echo "Usage: $0 [-d deployment_type] [-n node_number] [-i service_ip] [-p service_port]"
-    echo "  -d deployment_type    ChatQnA deployment type, select between k8s and docker (default: k8s)"
-    echo "  -n node_number        Test node number, required only for k8s deployment_type, (default: 1)"
-    echo "  -i service_ip         chatqna service ip, required only for docker deployment_type"
-    echo "  -p service_port       chatqna service port, required only for docker deployment_type, (default: 8888)"
-    exit 1
-}
-
-while getopts ":d:n:i:p:" opt; do
-    case ${opt} in
-        d )
-            deployment_type=$OPTARG
-            ;;
-        n )
-            node_number=$OPTARG
-            ;;
-        i )
-            service_ip=$OPTARG
-            ;;
-        p )
-            service_port=$OPTARG
-            ;;
-        \? )
-            echo "Invalid option: -$OPTARG" 1>&2
-            usage
-            ;;
-        : )
-            echo "Invalid option: -$OPTARG requires an argument" 1>&2
-            usage
-            ;;
-    esac
-done
-
-if [[ "$deployment_type" == "docker" && -z "$service_ip" ]]; then
-    echo "Error: service_ip is required for docker deployment_type" 1>&2
-    usage
-fi
-
-if [[ "$deployment_type" == "k8s" && ( -n "$service_ip" || -n "$service_port" ) ]]; then
-    echo "Warning: service_ip and service_port are ignored for k8s deployment_type" 1>&2
-fi
-
-function main() {
-    if [[ ! -d ${benchmark_tool_path} ]]; then
-        echo "Benchmark tool not found, setting up..."
-        setup_env
-    fi
-    run_benchmark
-}
-
-function setup_env() {
-    git clone https://github.com/opea-project/GenAIEval.git
-    pushd ${benchmark_tool_path}
-    python3 -m venv stress_venv
-    source stress_venv/bin/activate
-    pip install -r requirements.txt
-    popd
-}
-
-function run_benchmark() {
-    source ${benchmark_tool_path}/stress_venv/bin/activate
-    export DEPLOYMENT_TYPE=${deployment_type}
-    export SERVICE_IP=${service_ip:-"None"}
-    export SERVICE_PORT=${service_port:-"None"}
-    export LOAD_SHAPE=${load_shape:-"constant"}
-    export CONCURRENT_LEVEL=${concurrent_level:-5}
-    export ARRIVAL_RATE=${arrival_rate:-1.0}
-    if [[ -z $USER_QUERIES ]]; then
-        user_query=$((query_per_node*node_number))
-        export USER_QUERIES="[${user_query}, ${user_query}, ${user_query}, ${user_query}]"
-        echo "USER_QUERIES not configured, setting to: ${USER_QUERIES}."
-    fi
-    export WARMUP=$(echo $USER_QUERIES | sed -e 's/[][]//g' -e 's/,.*//')
-    if [[ -z $WARMUP ]]; then export WARMUP=0; fi
-    if [[ -z $TEST_OUTPUT_DIR ]]; then
-        if [[ $DEPLOYMENT_TYPE == "k8s" ]]; then
-            export TEST_OUTPUT_DIR="${benchmark_tool_path}/evals/benchmark/benchmark_output/node_${node_number}"
-        else
-            export TEST_OUTPUT_DIR="${benchmark_tool_path}/evals/benchmark/benchmark_output/docker"
-        fi
-        echo "TEST_OUTPUT_DIR not configured, setting to: ${TEST_OUTPUT_DIR}."
-    fi
-
-    envsubst < ./benchmark.yaml > ${benchmark_tool_path}/evals/benchmark/benchmark.yaml
-    cd ${benchmark_tool_path}/evals/benchmark
-    python benchmark.py
-}
-
-main

ChatQnA/benchmark/performance/kubernetes/intel/gaudi/benchmark.yaml

@@ -1,68 +0,0 @@
-# Copyright (C) 2024 Intel Corporation
-# SPDX-License-Identifier: Apache-2.0
-
-test_suite_config: # Overall configuration settings for the test suite
-  examples: ["chatqna"]  # The specific test cases being tested, e.g., chatqna, codegen, codetrans, faqgen, audioqna, visualqna
-  deployment_type: ${DEPLOYMENT_TYPE}  # Default is "k8s", can also be "docker"
-  service_ip: ${SERVICE_IP}  # Leave as None for k8s, specify for Docker
-  service_port: ${SERVICE_PORT}  # Leave as None for k8s, specify for Docker
-  warm_ups: ${WARMUP}  # Number of test requests for warm-up
-  run_time: 60m  # The max total run time for the test suite
-  seed:  # The seed for all RNGs
-  user_queries: ${USER_QUERIES}  # Number of test requests at each concurrency level
-  query_timeout: 120  # Number of seconds to wait for a simulated user to complete any executing task before exiting. 120 sec by defeult.
-  random_prompt: false  # Use random prompts if true, fixed prompts if false
-  collect_service_metric: false  # Collect service metrics if true, do not collect service metrics if false
-  data_visualization: false # Generate data visualization if true, do not generate data visualization if false
-  llm_model: "Intel/neural-chat-7b-v3-3"  # The LLM model used for the test
-  test_output_dir: "${TEST_OUTPUT_DIR}"  # The directory to store the test output
-  load_shape:              # Tenant concurrency pattern
-    name: ${LOAD_SHAPE}      # poisson or constant(locust default load shape)
-    params:                  # Loadshape-specific parameters
-      constant:                # Constant load shape specific parameters, activate only if load_shape.name is constant
-        concurrent_level: ${CONCURRENT_LEVEL}      # If user_queries is specified, concurrent_level is target number of requests per user. If not, it is the number of simulated users
-      poisson:                 # Poisson load shape specific parameters, activate only if load_shape.name is poisson
-        arrival_rate: ${ARRIVAL_RATE}        # Request arrival rate
-
-test_cases:
-  chatqna:
-    embedding:
-      run_test: false
-      service_name: "chatqna-embedding-usvc"  # Replace with your service name
-    embedserve:
-      run_test: false
-      service_name: "chatqna-tei"  # Replace with your service name
-    retriever:
-      run_test: false
-      service_name: "chatqna-retriever-usvc"  # Replace with your service name
-      parameters:
-        search_type: "similarity"
-        k: 1
-        fetch_k: 20
-        lambda_mult: 0.5
-        score_threshold: 0.2
-    reranking:
-      run_test: false
-      service_name: "chatqna-reranking-usvc"  # Replace with your service name
-      parameters:
-        top_n: 1
-    rerankserve:
-      run_test: false
-      service_name: "chatqna-teirerank"  # Replace with your service name
-    llm:
-      run_test: false
-      service_name: "chatqna-llm-uservice"  # Replace with your service name
-      parameters:
-        max_tokens: 128
-        temperature: 0.01
-        top_k: 10
-        top_p: 0.95
-        repetition_penalty: 1.03
-        stream: true
-    llmserve:
-      run_test: false
-      service_name: "chatqna-tgi"  # Replace with your service name
-    e2e:
-      run_test: true
-      service_name: "chatqna"  # Replace with your service name
-      k: 1

ChatQnA/benchmark/performance/kubernetes/intel/gaudi/deploy.py

@@ -1,278 +0,0 @@
-# Copyright (C) 2024 Intel Corporation
-# SPDX-License-Identifier: Apache-2.0
-
-import argparse
-import glob
-import json
-import os
-import shutil
-import subprocess
-import sys
-
-from generate_helm_values import generate_helm_values
-
-
-def run_kubectl_command(command):
-    """Run a kubectl command and return the output."""
-    try:
-        result = subprocess.run(command, check=True, stdout=subprocess.PIPE, stderr=subprocess.PIPE, text=True)
-        return result.stdout
-    except subprocess.CalledProcessError as e:
-        print(f"Error running command: {command}\n{e.stderr}")
-        exit(1)
-
-
-def get_all_nodes():
-    """Get the list of all nodes in the Kubernetes cluster."""
-    command = ["kubectl", "get", "nodes", "-o", "json"]
-    output = run_kubectl_command(command)
-    nodes = json.loads(output)
-    return [node["metadata"]["name"] for node in nodes["items"]]
-
-
-def add_label_to_node(node_name, label):
-    """Add a label to the specified node."""
-    command = ["kubectl", "label", "node", node_name, label, "--overwrite"]
-    print(f"Labeling node {node_name} with {label}...")
-    run_kubectl_command(command)
-    print(f"Label {label} added to node {node_name} successfully.")
-
-
-def add_labels_to_nodes(node_count=None, label=None, node_names=None):
-    """Add a label to the specified number of nodes or to specified nodes."""
-
-    if node_names:
-        # Add label to the specified nodes
-        for node_name in node_names:
-            add_label_to_node(node_name, label)
-    else:
-        # Fetch the node list and label the specified number of nodes
-        all_nodes = get_all_nodes()
-        if node_count is None or node_count > len(all_nodes):
-            print(f"Error: Node count exceeds the number of available nodes ({len(all_nodes)} available).")
-            sys.exit(1)
-
-        selected_nodes = all_nodes[:node_count]
-        for node_name in selected_nodes:
-            add_label_to_node(node_name, label)
-
-
-def clear_labels_from_nodes(label, node_names=None):
-    """Clear the specified label from specific nodes if provided, otherwise from all nodes."""
-    label_key = label.split("=")[0]  # Extract key from 'key=value' format
-
-    # If specific nodes are provided, use them; otherwise, get all nodes
-    nodes_to_clear = node_names if node_names else get_all_nodes()
-
-    for node_name in nodes_to_clear:
-        # Check if the node has the label by inspecting its metadata
-        command = ["kubectl", "get", "node", node_name, "-o", "json"]
-        node_info = run_kubectl_command(command)
-        node_metadata = json.loads(node_info)
-
-        # Check if the label exists on this node
-        labels = node_metadata["metadata"].get("labels", {})
-        if label_key in labels:
-            # Remove the label from the node
-            command = ["kubectl", "label", "node", node_name, f"{label_key}-"]
-            print(f"Removing label {label_key} from node {node_name}...")
-            run_kubectl_command(command)
-            print(f"Label {label_key} removed from node {node_name} successfully.")
-        else:
-            print(f"Label {label_key} not found on node {node_name}, skipping.")
-
-
-def install_helm_release(release_name, chart_name, namespace, values_file, device_type):
-    """Deploy a Helm release with a specified name and chart.
-
-    Parameters:
-    - release_name: The name of the Helm release.
-    - chart_name: The Helm chart name or path, e.g., "opea/chatqna".
-    - namespace: The Kubernetes namespace for deployment.
-    - values_file: The user values file for deployment.
-    - device_type: The device type (e.g., "gaudi") for specific configurations (optional).
-    """
-
-    # Check if the namespace exists; if not, create it
-    try:
-        # Check if the namespace exists
-        command = ["kubectl", "get", "namespace", namespace]
-        subprocess.run(command, check=True, stdout=subprocess.DEVNULL, stderr=subprocess.DEVNULL)
-    except subprocess.CalledProcessError:
-        # Namespace does not exist, create it
-        print(f"Namespace '{namespace}' does not exist. Creating it...")
-        command = ["kubectl", "create", "namespace", namespace]
-        subprocess.run(command, check=True)
-        print(f"Namespace '{namespace}' created successfully.")
-
-    # Handle gaudi-specific values file if device_type is "gaudi"
-    hw_values_file = None
-    untar_dir = None
-    if device_type == "gaudi":
-        print("Device type is gaudi. Pulling Helm chart to get gaudi-values.yaml...")
-
-        # Combine chart_name with fixed prefix
-        chart_pull_url = f"oci://ghcr.io/opea-project/charts/{chart_name}"
-
-        # Pull and untar the chart
-        subprocess.run(["helm", "pull", chart_pull_url, "--untar"], check=True)
-
-        # Find the untarred directory
-        untar_dirs = glob.glob(f"{chart_name}*")
-        if untar_dirs:
-            untar_dir = untar_dirs[0]
-            hw_values_file = os.path.join(untar_dir, "gaudi-values.yaml")
-            print("gaudi-values.yaml pulled and ready for use.")
-        else:
-            print(f"Error: Could not find untarred directory for {chart_name}")
-            return
-
-    # Prepare the Helm install command
-    command = ["helm", "install", release_name, chart_name, "--namespace", namespace]
-
-    # Append additional values file for gaudi if it exists
-    if hw_values_file:
-        command.extend(["-f", hw_values_file])
-
-    # Append the main values file
-    command.extend(["-f", values_file])
-
-    # Execute the Helm install command
-    try:
-        print(f"Running command: {' '.join(command)}")  # Print full command for debugging
-        subprocess.run(command, check=True)
-        print("Deployment initiated successfully.")
-    except subprocess.CalledProcessError as e:
-        print(f"Error occurred while deploying Helm release: {e}")
-
-    # Cleanup: Remove the untarred directory
-    if untar_dir and os.path.isdir(untar_dir):
-        print(f"Removing temporary directory: {untar_dir}")
-        shutil.rmtree(untar_dir)
-        print("Temporary directory removed successfully.")
-
-
-def uninstall_helm_release(release_name, namespace=None):
-    """Uninstall a Helm release and clean up resources, optionally delete the namespace if not 'default'."""
-    # Default to 'default' namespace if none is specified
-    if not namespace:
-        namespace = "default"
-
-    try:
-        # Uninstall the Helm release
-        command = ["helm", "uninstall", release_name, "--namespace", namespace]
-        print(f"Uninstalling Helm release {release_name} in namespace {namespace}...")
-        run_kubectl_command(command)
-        print(f"Helm release {release_name} uninstalled successfully.")
-
-        # If the namespace is specified and not 'default', delete it
-        if namespace != "default":
-            print(f"Deleting namespace {namespace}...")
-            delete_namespace_command = ["kubectl", "delete", "namespace", namespace]
-            run_kubectl_command(delete_namespace_command)
-            print(f"Namespace {namespace} deleted successfully.")
-        else:
-            print("Namespace is 'default', skipping deletion.")
-
-    except subprocess.CalledProcessError as e:
-        print(f"Error occurred while uninstalling Helm release or deleting namespace: {e}")
-
-
-def main():
-    parser = argparse.ArgumentParser(description="Manage Helm Deployment.")
-    parser.add_argument(
-        "--release-name",
-        type=str,
-        default="chatqna",
-        help="The Helm release name created during deployment (default: chatqna).",
-    )
-    parser.add_argument(
-        "--chart-name",
-        type=str,
-        default="chatqna",
-        help="The chart name to deploy, composed of repo name and chart name (default: chatqna).",
-    )
-    parser.add_argument("--namespace", default="default", help="Kubernetes namespace (default: default).")
-    parser.add_argument("--hf-token", help="Hugging Face API token.")
-    parser.add_argument(
-        "--model-dir", help="Model directory, mounted as volumes for service access to pre-downloaded models"
-    )
-    parser.add_argument("--user-values", help="Path to a user-specified values.yaml file.")
-    parser.add_argument(
-        "--create-values-only", action="store_true", help="Only create the values.yaml file without deploying."
-    )
-    parser.add_argument("--uninstall", action="store_true", help="Uninstall the Helm release.")
-    parser.add_argument("--num-nodes", type=int, default=1, help="Number of nodes to use (default: 1).")
-    parser.add_argument("--node-names", nargs="*", help="Optional specific node names to label.")
-    parser.add_argument("--add-label", action="store_true", help="Add label to specified nodes if this flag is set.")
-    parser.add_argument(
-        "--delete-label", action="store_true", help="Delete label from specified nodes if this flag is set."
-    )
-    parser.add_argument(
-        "--label", default="node-type=opea-benchmark", help="Label to add/delete (default: node-type=opea-benchmark)."
-    )
-    parser.add_argument("--with-rerank", action="store_true", help="Include rerank service in the deployment.")
-    parser.add_argument(
-        "--tuned",
-        action="store_true",
-        help="Modify resources for services and change extraCmdArgs when creating values.yaml.",
-    )
-    parser.add_argument(
-        "--device-type",
-        type=str,
-        choices=["cpu", "gaudi"],
-        default="gaudi",
-        help="Specify the device type for deployment (choices: 'cpu', 'gaudi'; default: gaudi).",
-    )
-
-    args = parser.parse_args()
-
-    # Adjust num-nodes based on node-names if specified
-    if args.node_names:
-        num_node_names = len(args.node_names)
-        if args.num_nodes != 1 and args.num_nodes != num_node_names:
-            parser.error("--num-nodes must match the number of --node-names if both are specified.")
-        else:
-            args.num_nodes = num_node_names
-
-    # Node labeling management
-    if args.add_label:
-        add_labels_to_nodes(args.num_nodes, args.label, args.node_names)
-        return
-    elif args.delete_label:
-        clear_labels_from_nodes(args.label, args.node_names)
-        return
-
-    # Uninstall Helm release if specified
-    if args.uninstall:
-        uninstall_helm_release(args.release_name, args.namespace)
-        return
-
-    # Prepare values.yaml if not uninstalling
-    if args.user_values:
-        values_file_path = args.user_values
-    else:
-        if not args.hf_token:
-            parser.error("--hf-token are required")
-        node_selector = {args.label.split("=")[0]: args.label.split("=")[1]}
-        values_file_path = generate_helm_values(
-            with_rerank=args.with_rerank,
-            num_nodes=args.num_nodes,
-            hf_token=args.hf_token,
-            model_dir=args.model_dir,
-            node_selector=node_selector,
-            tune=args.tuned,
-        )
-
-    # Read back the generated YAML file for verification
-    with open(values_file_path, "r") as file:
-        print("Generated YAML contents:")
-        print(file.read())
-
-    # Deploy unless --create-values-only is specified
-    if not args.create_values_only:
-        install_helm_release(args.release_name, args.chart_name, args.namespace, values_file_path, args.device_type)
-
-
-if __name__ == "__main__":
-    main()

ChatQnA/benchmark/performance/kubernetes/intel/gaudi/generate_helm_values.py

@@ -1,164 +0,0 @@
-# Copyright (C) 2024 Intel Corporation
-# SPDX-License-Identifier: Apache-2.0
-
-import os
-
-import yaml
-
-
-def generate_helm_values(with_rerank, num_nodes, hf_token, model_dir, node_selector=None, tune=False):
-    """Create a values.yaml file based on the provided configuration."""
-
-    # Log the received parameters
-    print("Received parameters:")
-    print(f"with_rerank: {with_rerank}")
-    print(f"num_nodes: {num_nodes}")
-    print(f"node_selector: {node_selector}")  # Log the node_selector
-    print(f"tune: {tune}")
-
-    if node_selector is None:
-        node_selector = {}
-
-    # Construct the base values dictionary
-    values = {
-        "tei": {"nodeSelector": {key: value for key, value in node_selector.items()}},
-        "tgi": {"nodeSelector": {key: value for key, value in node_selector.items()}},
-        "data-prep": {"nodeSelector": {key: value for key, value in node_selector.items()}},
-        "redis-vector-db": {"nodeSelector": {key: value for key, value in node_selector.items()}},
-        "retriever-usvc": {"nodeSelector": {key: value for key, value in node_selector.items()}},
-        "chatqna-ui": {"nodeSelector": {key: value for key, value in node_selector.items()}},
-        "global": {
-            "HUGGINGFACEHUB_API_TOKEN": hf_token,  # Use passed token
-            "modelUseHostPath": model_dir,  # Use passed model directory
-        },
-        "nodeSelector": {key: value for key, value in node_selector.items()},
-    }
-
-    if with_rerank:
-        values["teirerank"] = {"nodeSelector": {key: value for key, value in node_selector.items()}}
-    else:
-        values["image"] = {"repository": "opea/chatqna-without-rerank"}
-        values["teirerank"] = {"enabled": False}
-
-    default_replicas = [
-        {"name": "chatqna", "replicaCount": 2},
-        {"name": "tei", "replicaCount": 1},
-        {"name": "teirerank", "replicaCount": 1} if with_rerank else None,
-        {"name": "tgi", "replicaCount": 7 if with_rerank else 8},
-        {"name": "data-prep", "replicaCount": 1},
-        {"name": "redis-vector-db", "replicaCount": 1},
-        {"name": "retriever-usvc", "replicaCount": 2},
-    ]
-
-    if num_nodes > 1:
-        # Scale replicas based on number of nodes
-        replicas = [
-            {"name": "chatqna", "replicaCount": 1 * num_nodes},
-            {"name": "tei", "replicaCount": 1 * num_nodes},
-            {"name": "teirerank", "replicaCount": 1} if with_rerank else None,
-            {"name": "tgi", "replicaCount": (8 * num_nodes - 1) if with_rerank else 8 * num_nodes},
-            {"name": "data-prep", "replicaCount": 1},
-            {"name": "redis-vector-db", "replicaCount": 1},
-            {"name": "retriever-usvc", "replicaCount": 1 * num_nodes},
-        ]
-    else:
-        replicas = default_replicas
-
-    # Remove None values for rerank disabled
-    replicas = [r for r in replicas if r]
-
-    # Update values.yaml with replicas
-    for replica in replicas:
-        service_name = replica["name"]
-        if service_name == "chatqna":
-            values["replicaCount"] = replica["replicaCount"]
-            print(replica["replicaCount"])
-        elif service_name in values:
-            values[service_name]["replicaCount"] = replica["replicaCount"]
-
-    # Prepare resource configurations based on tuning
-    resources = []
-    if tune:
-        resources = [
-            {
-                "name": "chatqna",
-                "resources": {
-                    "limits": {"cpu": "16", "memory": "8000Mi"},
-                    "requests": {"cpu": "16", "memory": "8000Mi"},
-                },
-            },
-            {
-                "name": "tei",
-                "resources": {
-                    "limits": {"cpu": "80", "memory": "20000Mi"},
-                    "requests": {"cpu": "80", "memory": "20000Mi"},
-                },
-            },
-            {"name": "teirerank", "resources": {"limits": {"habana.ai/gaudi": 1}}} if with_rerank else None,
-            {"name": "tgi", "resources": {"limits": {"habana.ai/gaudi": 1}}},
-            {"name": "retriever-usvc", "resources": {"requests": {"cpu": "8", "memory": "8000Mi"}}},
-        ]
-
-        # Filter out any None values directly as part of initialization
-        resources = [r for r in resources if r is not None]
-
-        # Add resources for each service if tuning
-        for resource in resources:
-            service_name = resource["name"]
-            if service_name == "chatqna":
-                values["resources"] = resource["resources"]
-            elif service_name in values:
-                values[service_name]["resources"] = resource["resources"]
-
-        # Add extraCmdArgs for tgi service with default values
-        if "tgi" in values:
-            values["tgi"]["extraCmdArgs"] = [
-                "--max-input-length",
-                "1280",
-                "--max-total-tokens",
-                "2048",
-                "--max-batch-total-tokens",
-                "65536",
-                "--max-batch-prefill-tokens",
-                "4096",
-            ]
-
-    yaml_string = yaml.dump(values, default_flow_style=False)
-
-    # Determine the mode based on the 'tune' parameter
-    mode = "tuned" if tune else "oob"
-
-    # Determine the filename based on 'with_rerank' and 'num_nodes'
-    if with_rerank:
-        filename = f"{mode}-{num_nodes}-gaudi-with-rerank-values.yaml"
-    else:
-        filename = f"{mode}-{num_nodes}-gaudi-without-rerank-values.yaml"
-
-    # Write the YAML data to the file
-    with open(filename, "w") as file:
-        file.write(yaml_string)
-
-    # Get the current working directory and construct the file path
-    current_dir = os.getcwd()
-    filepath = os.path.join(current_dir, filename)
-
-    print(f"YAML file {filepath} has been generated.")
-    return filepath  # Optionally return the file path
-
-
-# Main execution for standalone use of create_values_yaml
-if __name__ == "__main__":
-    # Example values for standalone execution
-    with_rerank = True
-    num_nodes = 2
-    hftoken = "xxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx"
-    modeldir = "/mnt/model"
-    node_selector = {"node-type": "opea-benchmark"}
-    tune = True
-
-    filename = generate_helm_values(with_rerank, num_nodes, hftoken, modeldir, node_selector, tune)
-
-    # Read back the generated YAML file for verification
-    with open(filename, "r") as file:
-        print("Generated YAML contents:")
-        print(file.read())

ChatQnA/benchmark_chatqna.yaml

@@ -3,7 +3,7 @@
 
 deploy:
   device: gaudi
-  version: 1.2.0
+  version: 1.3.0
   modelUseHostPath: /mnt/models
   HUGGINGFACEHUB_API_TOKEN: "" # mandatory
   node: [1, 2, 4, 8]

ChatQnA/docker_compose/amd/gpu/rocm/README.md

@@ -1,163 +1,90 @@
-# Build and Deploy ChatQnA Application on AMD GPU (ROCm)
+# Deploying ChatQnA on AMD ROCm GPU
 
-## Build Docker Images
+This document outlines the single node deployment process for a ChatQnA application utilizing the [GenAIComps](https://github.com/opea-project/GenAIComps.git) microservices on Intel Xeon server and AMD GPU. The steps include pulling Docker images, container deployment via Docker Compose, and service execution using microservices `llm`.
 
-### 1. Build Docker Image
+Note: The default LLM is `meta-llama/Meta-Llama-3-8B-Instruct`. Before deploying the application, please make sure either you've requested and been granted the access to it on [Huggingface](https://huggingface.co/meta-llama/Meta-Llama-3-8B-Instruct) or you've downloaded the model locally from [ModelScope](https://www.modelscope.cn/models).
 
-- #### Create application install directory and go to it:
+## Table of Contents
 
-  ```bash
-  mkdir ~/chatqna-install && cd chatqna-install
-  ```
+1. [ChatQnA Quick Start Deployment](#chatqna-quick-start-deployment)
+2. [ChatQnA Docker Compose Files](#chatqna-docker-compose-files)
+3. [Validate Microservices](#validate-microservices)
+4. [Conclusion](#conclusion)
 
-- #### Clone the repository GenAIExamples (the default repository branch "main" is used here):
+## ChatQnA Quick Start Deployment
 
-  ```bash
-  git clone https://github.com/opea-project/GenAIExamples.git
-  ```
+This section describes how to quickly deploy and test the ChatQnA service manually on an AMD ROCm GPU. The basic steps are:
 
-  If you need to use a specific branch/tag of the GenAIExamples repository, then (v1.3 replace with its own value):
+1. [Access the Code](#access-the-code)
+2. [Configure the Deployment Environment](#configure-the-deployment-environment)
+3. [Deploy the Services Using Docker Compose](#deploy-the-services-using-docker-compose)
+4. [Check the Deployment Status](#check-the-deployment-status)
+5. [Validate the Pipeline](#validate-the-pipeline)
+6. [Cleanup the Deployment](#cleanup-the-deployment)
 
-  ```bash
-  git clone https://github.com/opea-project/GenAIExamples.git && cd GenAIExamples && git checkout v1.3
-  ```
+### Access the Code
 
-  We remind you that when using a specific version of the code, you need to use the README from this version:
+Clone the GenAIExample repository and access the ChatQnA AMD ROCm GPU platform Docker Compose files and supporting scripts:
 
-- #### Go to build directory:
+```bash
+git clone https://github.com/opea-project/GenAIExamples.git
+cd GenAIExamples/ChatQnA
+```
 
-  ```bash
-  cd ~/chatqna-install/GenAIExamples/ChatQnA/docker_image_build
-  ```
+Then checkout a released version, such as v1.3:
 
-- Cleaning up the GenAIComps repository if it was previously cloned in this directory.
-  This is necessary if the build was performed earlier and the GenAIComps folder exists and is not empty:
+```bash
+git checkout v1.3
+```
 
-  ```bash
-  echo Y | rm -R GenAIComps
-  ```
+### Configure the Deployment Environment
 
-- #### Clone the repository GenAIComps (the default repository branch "main" is used here):
+To set up environment variables for deploying ChatQnA services, set up some parameters specific to the deployment environment and source the `set_env_*.sh` script in this directory:
 
-  ```bash
-  git clone https://github.com/opea-project/GenAIComps.git
-  ```
+- if used vLLM - set_env_vllm.sh
+- if used vLLM with FaqGen - set_env_faqgen_vllm.sh
+- if used TGI - set_env.sh
+- if used TGI with FaqGen - set_env_faqgen.sh
 
-  If you use a specific tag of the GenAIExamples repository,
-  then you should also use the corresponding tag for GenAIComps. (v1.3 replace with its own value):
+Set the values of the variables:
 
-  ```bash
-  git clone https://github.com/opea-project/GenAIComps.git && cd GenAIComps && git checkout v1.3
-  ```
+- **HOST_IP, HOST_IP_EXTERNAL** - These variables are used to configure the name/address of the service in the operating system environment for the application services to interact with each other and with the outside world.
 
-  We remind you that when using a specific version of the code, you need to use the README from this version.
+  If your server uses only an internal address and is not accessible from the Internet, then the values for these two variables will be the same and the value will be equal to the server's internal name/address.
 
-- #### Setting the list of images for the build (from the build file.yaml)
+  If your server uses only an external, Internet-accessible address, then the values for these two variables will be the same and the value will be equal to the server's external name/address.
 
-  If you want to deploy a vLLM-based or TGI-based application, then the set of services is installed as follows:
+  If your server is located on an internal network, has an internal address, but is accessible from the Internet via a proxy/firewall/load balancer, then the HOST_IP variable will have a value equal to the internal name/address of the server, and the EXTERNAL_HOST_IP variable will have a value equal to the external name/address of the proxy/firewall/load balancer behind which the server is located.
 
-  #### vLLM-based application
+  We set these values in the file set_env\*\*\*\*.sh
 
-  ```bash
-  service_list="dataprep retriever vllm-rocm chatqna chatqna-ui nginx"
-  ```
+- **Variables with names like "**\*\*\*\*\*\*\_PORT"\*\* - These variables set the IP port numbers for establishing network connections to the application services.
+  The values shown in the file set_env.sh or set_env_vllm.sh they are the values used for the development and testing of the application, as well as configured for the environment in which the development is performed. These values must be configured in accordance with the rules of network access to your environment's server, and must not overlap with the IP ports of other applications that are already in use.
 
-  #### vLLM-based application with FaqGen
+Setting variables in the operating system environment:
 
-  ```bash
-  service_list="dataprep retriever vllm-rocm llm-faqgen chatqna chatqna-ui nginx"
-  ```
+```bash
+export HUGGINGFACEHUB_API_TOKEN="Your_HuggingFace_API_Token"
+source ./set_env_*.sh # replace the script name with the appropriate one
+```
 
-  #### TGI-based application
+Consult the section on [ChatQnA Service configuration](#chatqna-configuration) for information on how service specific configuration parameters affect deployments.
 
-  ```bash
-  service_list="dataprep retriever chatqna chatqna-ui nginx"
-  ```
+### Deploy the Services Using Docker Compose
 
-  #### TGI-based application with FaqGen
+To deploy the ChatQnA services, execute the `docker compose up` command with the appropriate arguments. For a default deployment with TGI, execute the command below. It uses the 'compose.yaml' file.
 
-  ```bash
-  service_list="dataprep retriever llm-faqgen chatqna chatqna-ui nginx"
-  ```
-
-- #### Pull Docker Images
-
-  ```bash
-  docker pull redis/redis-stack:7.2.0-v9
-  docker pull ghcr.io/huggingface/text-embeddings-inference:cpu-1.5
-  ```
-
-- #### Optional. Pull TGI Docker Image (Do this if you want to use TGI)
-
-  ```bash
-  docker pull ghcr.io/huggingface/text-generation-inference:2.3.1-rocm
-  ```
-
-- #### Build Docker Images
-
-  ```bash
-  docker compose -f build.yaml build ${service_list} --no-cache
-  ```
-
-  After the build, we check the list of images with the command:
-
-  ```bash
-  docker image ls
-  ```
-
-  The list of images should include:
-
-  ##### vLLM-based application:
-
-  - redis/redis-stack:7.2.0-v9
-  - opea/dataprep:latest
-  - ghcr.io/huggingface/text-embeddings-inference:cpu-1.5
-  - opea/retriever:latest
-  - opea/vllm-rocm:latest
-  - opea/chatqna:latest
-  - opea/chatqna-ui:latest
-  - opea/nginx:latest
-
-  ##### vLLM-based application with FaqGen:
-
-  - redis/redis-stack:7.2.0-v9
-  - opea/dataprep:latest
-  - ghcr.io/huggingface/text-embeddings-inference:cpu-1.5
-  - opea/retriever:latest
-  - opea/vllm-rocm:latest
-  - opea/llm-faqgen:latest
-  - opea/chatqna:latest
-  - opea/chatqna-ui:latest
-  - opea/nginx:latest
-
-  ##### TGI-based application:
-
-  - redis/redis-stack:7.2.0-v9
-  - opea/dataprep:latest
-  - ghcr.io/huggingface/text-embeddings-inference:cpu-1.5
-  - opea/retriever:latest
-  - ghcr.io/huggingface/text-generation-inference:2.3.1-rocm
-  - opea/chatqna:latest
-  - opea/chatqna-ui:latest
-  - opea/nginx:latest
-
-  ##### TGI-based application with FaqGen:
-
-  - redis/redis-stack:7.2.0-v9
-  - opea/dataprep:latest
-  - ghcr.io/huggingface/text-embeddings-inference:cpu-1.5
-  - opea/retriever:latest
-  - ghcr.io/huggingface/text-generation-inference:2.3.1-rocm
-  - opea/llm-faqgen:latest
-  - opea/chatqna:latest
-  - opea/chatqna-ui:latest
-  - opea/nginx:latest
-
----
-
-## Deploy the ChatQnA Application
-
-### Docker Compose Configuration for AMD GPUs
+```bash
+cd docker_compose/amd/gpu/rocm
+# if used TGI
+docker compose -f compose.yaml up -d
+# if used TGI with FaqGen
+# docker compose -f compose_faqgen.yaml up -d
+# if used vLLM
+# docker compose -f compose_vllm.yaml up -d
+# if used vLLM with FaqGen
+# docker compose -f compose_faqgen_vllm.yaml up -d
+```
 
 To enable GPU support for AMD GPUs, the following configuration is added to the Docker Compose file:
 
@@ -198,332 +125,103 @@ security_opt:
 **How to Identify GPU Device IDs:**
 Use AMD GPU driver utilities to determine the correct `cardN` and `renderN` IDs for your GPU.
 
-### Set deploy environment variables
+> **Note**: developers should build docker image from source when:
+>
+> - Developing off the git main branch (as the container's ports in the repo may be different > from the published docker image).
+> - Unable to download the docker image.
+> - Use a specific version of Docker image.
 
-#### Setting variables in the operating system environment:
+Please refer to the table below to build different microservices from source:
 
-##### Set variable HUGGINGFACEHUB_API_TOKEN:
+| Microservice    | Deployment Guide                                                                                                   |
+| --------------- | ------------------------------------------------------------------------------------------------------------------ |
+| vLLM            | [vLLM build guide](https://github.com/opea-project/GenAIComps/tree/main/comps/third_parties/vllm#build-docker)     |
+| TGI             | [TGI project](https://github.com/huggingface/text-generation-inference.git)                                        |
+| LLM             | [LLM build guide](https://github.com/opea-project/GenAIComps/tree/main/comps/llms)                                 |
+| Redis Vector DB | [Redis](https://github.com/redis/redis.git)                                                                        |
+| Dataprep        | [Dataprep build guide](https://github.com/opea-project/GenAIComps/tree/main/comps/dataprep/src/README_redis.md)    |
+| TEI Embedding   | [TEI guide](https://github.com/huggingface/text-embeddings-inference.git)                                          |
+| Retriever       | [Retriever build guide](https://github.com/opea-project/GenAIComps/tree/main/comps/retrievers/src/README_redis.md) |
+| TEI Reranking   | [TEI guide](https://github.com/huggingface/text-embeddings-inference.git)                                          |
+| MegaService     | [MegaService guide](../../../../README.md)                                                                         |
+| UI              | [UI guide](../../../../ui/react/README.md)                                                                         |
+| Nginx           | [Nginx guide](https://github.com/opea-project/GenAIComps/tree/main/comps/third_parties/nginx)                      |
+
+### Check the Deployment Status
+
+After running docker compose, check if all the containers launched via docker compose have started:
 
 ```bash
-### Replace the string 'your_huggingfacehub_token' with your HuggingFacehub repository access token.
-export HUGGINGFACEHUB_API_TOKEN='your_huggingfacehub_token'
+docker ps -a
 ```
 
-#### Set variables value in set_env\*\*\*\*.sh file:
+For the default deployment with TGI, the following 9 containers should have started:
 
-Go to Docker Compose directory:
-
-```bash
-cd ~/chatqna-install/GenAIExamples/ChatQnA/docker_compose/amd/gpu/rocm
+```
+CONTAINER ID   IMAGE                                                   COMMAND                  CREATED          STATUS                    PORTS                                                                                      NAMES
+eaf24161aca8   opea/nginx:latest                                       "/docker-entrypoint.…"   37 seconds ago   Up 5 seconds              0.0.0.0:18104->80/tcp, [::]:18104->80/tcp                                                  chatqna-nginx-server
+2fce48a4c0f4   opea/chatqna-ui:latest                                  "docker-entrypoint.s…"   37 seconds ago   Up 5 seconds              0.0.0.0:18101->5173/tcp, [::]:18101->5173/tcp                                              chatqna-ui-server
+613c384979f4   opea/chatqna:latest                                     "bash entrypoint.sh"     37 seconds ago   Up 5 seconds              0.0.0.0:18102->8888/tcp, [::]:18102->8888/tcp                                              chatqna-backend-server
+05512bd29fee   opea/dataprep:latest                                    "sh -c 'python $( [ …"   37 seconds ago   Up 36 seconds (healthy)   0.0.0.0:18103->5000/tcp, [::]:18103->5000/tcp                                              chatqna-dataprep-service
+49844d339d1d   opea/retriever:latest                                   "python opea_retriev…"   37 seconds ago   Up 36 seconds             0.0.0.0:7000->7000/tcp, [::]:7000->7000/tcp                                                chatqna-retriever
+75b698fe7de0   ghcr.io/huggingface/text-embeddings-inference:cpu-1.5   "text-embeddings-rou…"   37 seconds ago   Up 36 seconds             0.0.0.0:18808->80/tcp, [::]:18808->80/tcp                                                  chatqna-tei-reranking-service
+342f01bfdbb2   ghcr.io/huggingface/text-generation-inference:2.3.1-rocm"python3 /workspace/…"   37 seconds ago   Up 36 seconds             0.0.0.0:18008->8011/tcp, [::]:18008->8011/tcp                                              chatqna-tgi-service
+6081eb1c119d   redis/redis-stack:7.2.0-v9                              "/entrypoint.sh"         37 seconds ago   Up 36 seconds             0.0.0.0:6379->6379/tcp, [::]:6379->6379/tcp, 0.0.0.0:8001->8001/tcp, [::]:8001->8001/tcp   chatqna-redis-vector-db
+eded17420782   ghcr.io/huggingface/text-embeddings-inference:cpu-1.5   "text-embeddings-rou…"   37 seconds ago   Up 36 seconds             0.0.0.0:18090->80/tcp, [::]:18090->80/tcp                                                  chatqna-tei-embedding-service
 ```
 
-The example uses the Nano text editor. You can use any convenient text editor:
+if used TGI with FaqGen:
 
-#### If you use vLLM based application
-
-```bash
-nano set_env_vllm.sh
+```
+CONTAINER ID   IMAGE                                                   COMMAND                  CREATED          STATUS                    PORTS                                                                                      NAMES
+eaf24161aca8   opea/nginx:latest                                       "/docker-entrypoint.…"   37 seconds ago   Up 5 seconds              0.0.0.0:18104->80/tcp, [::]:18104->80/tcp                                                  chatqna-nginx-server
+2fce48a4c0f4   opea/chatqna-ui:latest                                  "docker-entrypoint.s…"   37 seconds ago   Up 5 seconds              0.0.0.0:18101->5173/tcp, [::]:18101->5173/tcp                                              chatqna-ui-server
+613c384979f4   opea/chatqna:latest                                     "bash entrypoint.sh"     37 seconds ago   Up 5 seconds              0.0.0.0:18102->8888/tcp, [::]:18102->8888/tcp                                              chatqna-backend-server
+e0ef1ea67640   opea/llm-faqgen:latest                                  "bash entrypoint.sh"     37 seconds ago   Up 36 seconds             0.0.0.0:18011->9000/tcp, [::]:18011->9000/tcp                                              chatqna-llm-faqgen
+05512bd29fee   opea/dataprep:latest                                    "sh -c 'python $( [ …"   37 seconds ago   Up 36 seconds (healthy)   0.0.0.0:18103->5000/tcp, [::]:18103->5000/tcp                                              chatqna-dataprep-service
+49844d339d1d   opea/retriever:latest                                   "python opea_retriev…"   37 seconds ago   Up 36 seconds             0.0.0.0:7000->7000/tcp, [::]:7000->7000/tcp                                                chatqna-retriever
+75b698fe7de0   ghcr.io/huggingface/text-embeddings-inference:cpu-1.5   "text-embeddings-rou…"   37 seconds ago   Up 36 seconds             0.0.0.0:18808->80/tcp, [::]:18808->80/tcp                                                  chatqna-tei-reranking-service
+342f01bfdbb2   ghcr.io/huggingface/text-generation-inference:2.3.1-rocm"python3 /workspace/…"   37 seconds ago   Up 36 seconds             0.0.0.0:18008->8011/tcp, [::]:18008->8011/tcp                                              chatqna-tgi-service
+6081eb1c119d   redis/redis-stack:7.2.0-v9                              "/entrypoint.sh"         37 seconds ago   Up 36 seconds             0.0.0.0:6379->6379/tcp, [::]:6379->6379/tcp, 0.0.0.0:8001->8001/tcp, [::]:8001->8001/tcp   chatqna-redis-vector-db
+eded17420782   ghcr.io/huggingface/text-embeddings-inference:cpu-1.5   "text-embeddings-rou…"   37 seconds ago   Up 36 seconds             0.0.0.0:18090->80/tcp, [::]:18090->80/tcp                                                  chatqna-tei-embedding-service
 ```
 
-#### If you use vLLM based application with FaqGen
+if used vLLM:
 
-```bash
-nano set_env_vllm_faqgen.sh
+```
+CONTAINER ID   IMAGE                                                   COMMAND                  CREATED          STATUS                    PORTS                                                                                      NAMES
+eaf24161aca8   opea/nginx:latest                                       "/docker-entrypoint.…"   37 seconds ago   Up 5 seconds              0.0.0.0:18104->80/tcp, [::]:18104->80/tcp                                                  chatqna-nginx-server
+2fce48a4c0f4   opea/chatqna-ui:latest                                  "docker-entrypoint.s…"   37 seconds ago   Up 5 seconds              0.0.0.0:18101->5173/tcp, [::]:18101->5173/tcp                                              chatqna-ui-server
+613c384979f4   opea/chatqna:latest                                     "bash entrypoint.sh"     37 seconds ago   Up 5 seconds              0.0.0.0:18102->8888/tcp, [::]:18102->8888/tcp                                              chatqna-backend-server
+05512bd29fee   opea/dataprep:latest                                    "sh -c 'python $( [ …"   37 seconds ago   Up 36 seconds (healthy)   0.0.0.0:18103->5000/tcp, [::]:18103->5000/tcp                                              chatqna-dataprep-service
+49844d339d1d   opea/retriever:latest                                   "python opea_retriev…"   37 seconds ago   Up 36 seconds             0.0.0.0:7000->7000/tcp, [::]:7000->7000/tcp                                                chatqna-retriever
+75b698fe7de0   ghcr.io/huggingface/text-embeddings-inference:cpu-1.5   "text-embeddings-rou…"   37 seconds ago   Up 36 seconds             0.0.0.0:18808->80/tcp, [::]:18808->80/tcp                                                  chatqna-tei-reranking-service
+342f01bfdbb2   opea/vllm-rocm:latest                                   "python3 /workspace/…"   37 seconds ago   Up 36 seconds             0.0.0.0:18008->8011/tcp, [::]:18008->8011/tcp                                              chatqna-vllm-service
+6081eb1c119d   redis/redis-stack:7.2.0-v9                              "/entrypoint.sh"         37 seconds ago   Up 36 seconds             0.0.0.0:6379->6379/tcp, [::]:6379->6379/tcp, 0.0.0.0:8001->8001/tcp, [::]:8001->8001/tcp   chatqna-redis-vector-db
+eded17420782   ghcr.io/huggingface/text-embeddings-inference:cpu-1.5   "text-embeddings-rou…"   37 seconds ago   Up 36 seconds             0.0.0.0:18090->80/tcp, [::]:18090->80/tcp                                                  chatqna-tei-embedding-service
 ```
 
-#### If you use TGI based application
+if used vLLM with FaqGen:
 
-```bash
-nano set_env.sh
+```
+CONTAINER ID   IMAGE                                                   COMMAND                  CREATED          STATUS                    PORTS                                                                                      NAMES
+eaf24161aca8   opea/nginx:latest                                       "/docker-entrypoint.…"   37 seconds ago   Up 5 seconds              0.0.0.0:18104->80/tcp, [::]:18104->80/tcp                                                  chatqna-nginx-server
+2fce48a4c0f4   opea/chatqna-ui:latest                                  "docker-entrypoint.s…"   37 seconds ago   Up 5 seconds              0.0.0.0:18101->5173/tcp, [::]:18101->5173/tcp                                              chatqna-ui-server
+613c384979f4   opea/chatqna:latest                                     "bash entrypoint.sh"     37 seconds ago   Up 5 seconds              0.0.0.0:18102->8888/tcp, [::]:18102->8888/tcp                                              chatqna-backend-server
+e0ef1ea67640   opea/llm-faqgen:latest                                  "bash entrypoint.sh"     37 seconds ago   Up 36 seconds             0.0.0.0:18011->9000/tcp, [::]:18011->9000/tcp                                              chatqna-llm-faqgen
+05512bd29fee   opea/dataprep:latest                                    "sh -c 'python $( [ …"   37 seconds ago   Up 36 seconds (healthy)   0.0.0.0:18103->5000/tcp, [::]:18103->5000/tcp                                              chatqna-dataprep-service
+49844d339d1d   opea/retriever:latest                                   "python opea_retriev…"   37 seconds ago   Up 36 seconds             0.0.0.0:7000->7000/tcp, [::]:7000->7000/tcp                                                chatqna-retriever
+75b698fe7de0   ghcr.io/huggingface/text-embeddings-inference:cpu-1.5   "text-embeddings-rou…"   37 seconds ago   Up 36 seconds             0.0.0.0:18808->80/tcp, [::]:18808->80/tcp                                                  chatqna-tei-reranking-service
+342f01bfdbb2   opea/vllm-rocm:latest                                   "python3 /workspace/…"   37 seconds ago   Up 36 seconds             0.0.0.0:18008->8011/tcp, [::]:18008->8011/tcp                                              chatqna-vllm-service
+6081eb1c119d   redis/redis-stack:7.2.0-v9                              "/entrypoint.sh"         37 seconds ago   Up 36 seconds             0.0.0.0:6379->6379/tcp, [::]:6379->6379/tcp, 0.0.0.0:8001->8001/tcp, [::]:8001->8001/tcp   chatqna-redis-vector-db
+eded17420782   ghcr.io/huggingface/text-embeddings-inference:cpu-1.5   "text-embeddings-rou…"   37 seconds ago   Up 36 seconds             0.0.0.0:18090->80/tcp, [::]:18090->80/tcp                                                  chatqna-tei-embedding-service
 ```
 
-#### If you use TGI based application with FaqGen
+If any issues are encountered during deployment, refer to the [Troubleshooting](../../../../README_miscellaneous.md#troubleshooting) section.
 
-```bash
-nano set_env_faqgen.sh
-```
+### Validate the Pipeline
 
-If you are in a proxy environment, also set the proxy-related environment variables:
-
-```bash
-export http_proxy="Your_HTTP_Proxy"
-export https_proxy="Your_HTTPs_Proxy"
-```
-
-Set the values of the variables:
-
-- **HOST_IP, HOST_IP_EXTERNAL** - These variables are used to configure the name/address of the service in the operating system environment for the application services to interact with each other and with the outside world.
-
-  If your server uses only an internal address and is not accessible from the Internet, then the values for these two variables will be the same and the value will be equal to the server's internal name/address.
-
-  If your server uses only an external, Internet-accessible address, then the values for these two variables will be the same and the value will be equal to the server's external name/address.
-
-  If your server is located on an internal network, has an internal address, but is accessible from the Internet via a proxy/firewall/load balancer, then the HOST_IP variable will have a value equal to the internal name/address of the server, and the EXTERNAL_HOST_IP variable will have a value equal to the external name/address of the proxy/firewall/load balancer behind which the server is located.
-
-  We set these values in the file set_env\*\*\*\*.sh
-
-- **Variables with names like "**\*\*\*\*\*\*\_PORT"\*\* - These variables set the IP port numbers for establishing network connections to the application services.
-  The values shown in the file set_env.sh or set_env_vllm they are the values used for the development and testing of the application, as well as configured for the environment in which the development is performed. These values must be configured in accordance with the rules of network access to your environment's server, and must not overlap with the IP ports of other applications that are already in use.
-
-#### Set variables with script set_env\*\*\*\*.sh
-
-#### If you use vLLM based application
-
-```bash
-. set_env_vllm.sh
-```
-
-#### If you use vLLM based application with FaqGen
-
-```bash
-. set_env_faqgen_vllm.sh
-```
-
-#### If you use TGI based application
-
-```bash
-. set_env.sh
-```
-
-#### If you use TGI based application with FaqGen
-
-```bash
-. set_env_faqgen.sh
-```
-
-### Start the services:
-
-#### If you use vLLM based application
-
-```bash
-docker compose -f compose_vllm.yaml up -d
-```
-
-#### If you use vLLM based application with FaqGen
-
-```bash
-docker compose -f compose_faqgen_vllm.yaml up -d
-```
-
-#### If you use TGI based application
-
-```bash
-docker compose -f compose.yaml up -d
-```
-
-#### If you use TGI based application with FaqGen
-
-```bash
-docker compose -f compose_faqgen.yaml up -d
-```
-
-All containers should be running and should not restart:
-
-##### If you use vLLM based application:
-
-- chatqna-redis-vector-db
-- chatqna-dataprep-service
-- chatqna-tei-embedding-service
-- chatqna-retriever
-- chatqna-tei-reranking-service
-- chatqna-vllm-service
-- chatqna-backend-server
-- chatqna-ui-server
-- chatqna-nginx-server
-
-##### If you use vLLM based application with FaqGen:
-
-- chatqna-redis-vector-db
-- chatqna-dataprep-service
-- chatqna-tei-embedding-service
-- chatqna-retriever
-- chatqna-tei-reranking-service
-- chatqna-vllm-service
-- chatqna-llm-faqgen
-- chatqna-backend-server
-- chatqna-ui-server
-- chatqna-nginx-server
-
-##### If you use TGI based application:
-
-- chatqna-redis-vector-db
-- chatqna-dataprep-service
-- chatqna-tei-embedding-service
-- chatqna-retriever
-- chatqna-tei-reranking-service
-- chatqna-tgi-service
-- chatqna-backend-server
-- chatqna-ui-server
-- chaqna-nginx-server
-
-##### If you use TGI based application with FaqGen:
-
-- chatqna-redis-vector-db
-- chatqna-dataprep-service
-- chatqna-tei-embedding-service
-- chatqna-retriever
-- chatqna-tei-reranking-service
-- chatqna-tgi-service
-- chatqna-llm-faqgen
-- chatqna-backend-server
-- chatqna-ui-server
-- chaqna-nginx-server
-
----
-
-## Validate the Services
-
-### 1. Validate TEI Embedding Service
-
-```bash
-curl http://${HOST_IP}:${CHATQNA_TEI_EMBEDDING_PORT}/embed \
-    -X POST \
-    -d '{"inputs":"What is Deep Learning?"}' \
-    -H 'Content-Type: application/json'
-```
-
-Checking the response from the service. The response should be similar to text:
-
-```textmate
-[[0.00037115702,-0.06356819,0.0024758505,..................,0.022725677,0.016026087,-0.02125421,-0.02984927,-0.0049473033]]
-```
-
-If the service response has a meaningful response in the value,
-then we consider the TEI Embedding Service to be successfully launched
-
-### 2. Validate Retriever Microservice
-
-```bash
-export your_embedding=$(python3 -c "import random; embedding = [random.uniform(-1, 1) for _ in range(768)]; print(embedding)")
-curl http://${HOST_IP}:${CHATQNA_REDIS_RETRIEVER_PORT}/v1/retrieval \
-  -X POST \
-  -d "{\"text\":\"test\",\"embedding\":${your_embedding}}" \
-  -H 'Content-Type: application/json'
-```
-
-Checking the response from the service. The response should be similar to JSON:
-
-```json
-{ "id": "e191846168aed1f80b2ea12df80844d2", "retrieved_docs": [], "initial_query": "test", "top_n": 1, "metadata": [] }
-```
-
-If the response corresponds to the form of the provided JSON, then we consider the
-Retriever Microservice verification successful.
-
-### 3. Validate TEI Reranking Service
-
-```bash
-curl http://${HOST_IP}:${CHATQNA_TEI_RERANKING_PORT}/rerank \
-    -X POST \
-    -d '{"query":"What is Deep Learning?", "texts": ["Deep Learning is not...", "Deep learning is..."]}' \
-    -H 'Content-Type: application/json'
-```
-
-Checking the response from the service. The response should be similar to JSON:
-
-```json
-[
-  { "index": 1, "score": 0.94238955 },
-  { "index": 0, "score": 0.120219156 }
-]
-```
-
-If the response corresponds to the form of the provided JSON, then we consider the TEI Reranking Service
-verification successful.
-
-### 4. Validate the vLLM/TGI Service
-
-#### If you use vLLM:
-
-```bash
-DATA='{"model": "meta-llama/Meta-Llama-3-8B-Instruct", '\
-'"messages": [{"role": "user", "content": "What is a Deep Learning?"}], "max_tokens": 64}'
-
-curl http://${HOST_IP}:${CHATQNA_VLLM_SERVICE_PORT}/v1/chat/completions \
-  -X POST \
-  -d "$DATA" \
-  -H 'Content-Type: application/json'
-```
-
-Checking the response from the service. The response should be similar to JSON:
-
-```json
-{
-  "id": "chatcmpl-91003647d1c7469a89e399958f390f67",
-  "object": "chat.completion",
-  "created": 1742877228,
-  "model": "meta-llama/Meta-Llama-3-8B-Instruct",
-  "choices": [
-    {
-      "index": 0,
-      "message": {
-        "role": "assistant",
-        "content": "Deep Learning ( DL) is a subfield of Machine Learning (ML) that focuses on the design of algorithms and architectures inspired by the structure and function of the human brain. These algorithms are designed to analyze and interpret data that is presented in the form of patterns or signals, and they often mimic the way the human brain",
-        "tool_calls": []
-      },
-      "logprobs": null,
-      "finish_reason": "length",
-      "stop_reason": null
-    }
-  ],
-  "usage": { "prompt_tokens": 16, "total_tokens": 80, "completion_tokens": 64, "prompt_tokens_details": null },
-  "prompt_logprobs": null
-}
-```
-
-If the service response has a meaningful response in the value of the "choices.message.content" key,
-then we consider the vLLM service to be successfully launched
-
-#### If you use TGI:
-
-```bash
-DATA='{"inputs":"What is a Deep Learning?",'\
-'"parameters":{"max_new_tokens":64,"do_sample": true}}'
-
-curl http://${HOST_IP}:${CHATQNA_TGI_SERVICE_PORT}/generate \
-  -X POST \
-  -d "$DATA" \
-  -H 'Content-Type: application/json'
-```
-
-Checking the response from the service. The response should be similar to JSON:
-
-```json
-{
-  "generated_text": " What is its application in Computer Vision?\nWhat is a Deep Learning?\nDeep learning is a subfield of machine learning that involves the use of artificial neural networks to model high-level abstractions in data. It involves the use of deep neural networks, which are composed of multiple layers, to learn complex patterns in data. The"
-}
-```
-
-If the service response has a meaningful response in the value of the "generated_text" key,
-then we consider the TGI service to be successfully launched
-
-### 5. Validate the LLM Service (if your used application with FaqGen)
-
-```bash
-DATA='{"messages":"Text Embeddings Inference (TEI) is a toolkit for deploying and serving open source '\
-'text embeddings and sequence classification models. TEI enables high-performance extraction for the most '\
-'popular models, including FlagEmbedding, Ember, GTE and E5.","max_tokens": 128}'
-
-curl http://${HOST_IP}:${CHATQNA_LLM_FAQGEN_PORT}/v1/faqgen \
-  -X POST \
-  -d "$DATA" \
-  -H 'Content-Type: application/json'
-```
-
-Checking the response from the service. The response should be similar to JSON:
-
-```json
-{
-  "id": "58f0632f5f03af31471b895b0d0d397b",
-  "text": " Q: What is Text Embeddings Inference (TEI)?\n         A: TEI is a toolkit for deploying and serving open source text embeddings and sequence classification models.\n\n         Q: What models does TEI support?\n         A: TEI enables high-performance extraction for the most popular models, including FlagEmbedding, Ember, GTE and E5.\n\n         Q: What is the purpose of TEI?\n         A: The purpose of TEI is to enable high-performance extraction for text embeddings and sequence classification models.\n\n         Q: What are the benefits of using TEI?\n         A: The benefits of using TEI include high",
-  "prompt": "Text Embeddings Inference (TEI) is a toolkit for deploying and serving open source text embeddings and sequence classification models. TEI enables high-performance extraction for the most popular models, including FlagEmbedding, Ember, GTE and E5."
-}
-```
-
-If the service response has a meaningful response in the value of the "text" key,
-then we consider the LLM service to be successfully launched
-
-### 6. Validate the MegaService
+Once the ChatQnA services are running, test the pipeline using the following command:
 
 ```bash
 curl http://${HOST_IP}:${CHATQNA_BACKEND_SERVICE_PORT}/v1/chatqna \
@@ -531,91 +229,105 @@ curl http://${HOST_IP}:${CHATQNA_BACKEND_SERVICE_PORT}/v1/chatqna \
   -d '{"messages": "What is the revenue of Nike in 2023?"}'
 ```
 
-Checking the response from the service. The response should be similar to text:
+**Note** : Access the ChatQnA UI by web browser through this URL: `http://${HOST_IP_EXTERNAL}:${CHATQNA_NGINX_PORT}`
 
-```textmate
-data: b' What'
-data: b' is'
-data: b' the'
-data: b' revenue'
-data: b' of'
-data: b' Nike'
-data: b' in'
-data: b' '
-data: b'202'
-data: b'3'
-data: b'?\n'
-data: b'        '
-data: b' Answer'
-data: b':'
-data: b' According'
-data: b' to'
-data: b' the'
-data: b' search'
-data: b' results'
-data: b','
-data: b' the'
-data: b' revenue'
-data: b' of'
-data: b''
+### Cleanup the Deployment
 
-data: [DONE]
-
-```
-
-If the output lines in the "data" keys contain words (tokens) containing meaning, then the service
-is considered launched successfully.
-
-### 7. Validate the Frontend (UI)
-
-To access the UI, use the URL - http://${EXTERNAL_HOST_IP}:${CHATQNA_NGINX_PORT}
-A page should open when you click through to this address:
-
-![UI start page](../../../../assets/img/ui-starting-page.png)
-
-If a page of this type has opened, then we believe that the service is running and responding,
-and we can proceed to functional UI testing.
-
-Let's enter the task for the service in the "Enter prompt here" field.
-For example, "What is a Deep Learning?" and press Enter.
-After that, a page with the result of the task should open:
-
-#### If used application without FaqGen
-
-![UI result page](../../../../assets/img/ui-result-page.png)
-
-#### If used application with FaqGen
-
-![UI result page](../../../../assets/img/ui-result-page-faqgen.png)
-
-If the result shown on the page is correct, then we consider the verification of the UI service to be successful.
-
-### 5. Stop application
-
-#### If you use vLLM
+To stop the containers associated with the deployment, execute the following command:
 
 ```bash
-cd ~/chatqna-install/GenAIExamples/ChatQnA/docker_compose/amd/gpu/rocm
-docker compose -f compose_vllm.yaml down
-```
-
-#### If you use vLLM with FaqGen
-
-```bash
-cd ~/chatqna-install/GenAIExamples/ChatQnA/docker_compose/amd/gpu/rocm
-docker compose -f compose_faqgen_vllm.yaml down
-```
-
-#### If you use TGI
-
-```bash
-cd ~/chatqna-install/GenAIExamples/ChatQnA/docker_compose/amd/gpu/rocm
+# if used TGI
 docker compose -f compose.yaml down
+# if used TGI with FaqGen
+# docker compose -f compose_faqgen.yaml down
+# if used vLLM
+# docker compose -f compose_vllm.yaml down
+# if used vLLM with FaqGen
+# docker compose -f compose_faqgen_vllm.yaml down
+
+
 ```
 
-#### If you use TGI with FaqGen
+## ChatQnA Docker Compose Files
 
-```bash
-cd ~/chatqna-install/GenAIExamples/ChatQnA/docker_compose/amd/gpu/rocm
-docker compose -f compose_faqgen.yaml down
-```
+In the context of deploying an ChatQnA pipeline on an Intel® Xeon® platform, we can pick and choose different large language model serving frameworks, or single English TTS/multi-language TTS component. The table below outlines the various configurations that are available as part of the application. These configurations can be used as templates and can be extended to different components available in [GenAIComps](https://github.com/opea-project/GenAIComps.git).
+
+| File                                                   | Description                                                                                                              |
+| ------------------------------------------------------ | ------------------------------------------------------------------------------------------------------------------------ |
+| [compose.yaml](./compose.yaml)                         | The LLM serving framework is TGI. Default compose file using TGI as serving framework and redis as vector database       |
+| [compose_faqgen.yaml](./compose_faqgen.yaml)           | The LLM serving framework is TGI with FaqGen. All other configurations remain the same as the default                    |
+| [compose_vllm.yaml](./compose_vllm.yaml)               | The LLM serving framework is vLLM. Compose file using vllm as serving framework and redis as vector database             |
+| [compose_faqgen_vllm.yaml](./compose_faqgen_vllm.yaml) | The LLM serving framework is vLLM with FaqGen. Compose file using vllm as serving framework and redis as vector database |
+
+## Validate MicroServices
+
+1. TEI Embedding Service
+
+   ```bash
+   curl http://${HOST_IP}:${CHATQNA_TEI_EMBEDDING_PORT}/embed \
+   -X POST \
+   -d '{"inputs":"What is Deep Learning?"}' \
+   -H 'Content-Type: application/json'
+   ```
+
+2. Retriever Microservice
+
+   ```bash
+   export your_embedding=$(python3 -c "import random; embedding = [random.uniform(-1, 1) for _ in range(768)]; print(embedding)")
+   curl http://${HOST_IP}:${CHATQNA_REDIS_RETRIEVER_PORT}/v1/retrieval \
+     -X POST \
+     -d "{\"text\":\"test\",\"embedding\":${your_embedding}}" \
+     -H 'Content-Type: application/json'
+   ```
+
+3. TEI Reranking Service
+
+   ```bash
+   curl http://${HOST_IP}:${CHATQNA_TEI_RERANKING_PORT}/rerank \
+   -X POST \
+   -d '{"query":"What is Deep Learning?", "texts": ["Deep Learning is not...", "Deep learning is..."]}' \
+   -H 'Content-Type: application/json'
+   ```
+
+4. vLLM/TGI Service
+
+   If you use vLLM:
+
+   ```bash
+   DATA='{"model": "meta-llama/Meta-Llama-3-8B-Instruct", '\
+   '"messages": [{"role": "user", "content": "What is a Deep Learning?"}], "max_tokens": 64}'
+
+   curl http://${HOST_IP}:${CHATQNA_VLLM_SERVICE_PORT}/v1/chat/completions \
+     -X POST \
+     -d "$DATA" \
+     -H 'Content-Type: application/json'
+   ```
+
+   If you use TGI:
+
+   ```bash
+   DATA='{"inputs":"What is a Deep Learning?",'\
+   '"parameters":{"max_new_tokens":64,"do_sample": true}}'
+
+   curl http://${HOST_IP}:${CHATQNA_TGI_SERVICE_PORT}/generate \
+   -X POST \
+   -d "$DATA" \
+   -H 'Content-Type: application/json'
+   ```
+
+5. LLM Service (if your used application with FaqGen)
+
+   ```bash
+   DATA='{"messages":"Text Embeddings Inference (TEI) is a toolkit for deploying and serving open source '\
+   'text embeddings and sequence classification models. TEI enables high-performance extraction for the most '\
+   'popular models, including FlagEmbedding, Ember, GTE and E5.","max_tokens": 128}'
+
+   curl http://${HOST_IP}:${CHATQNA_LLM_FAQGEN_PORT}/v1/faqgen \
+     -X POST \
+     -d "$DATA" \
+     -H 'Content-Type: application/json'
+   ```
+
+## Conclusion
+
+This guide should enable developers to deploy the default configuration or any of the other compose yaml files for different configurations. It also highlights the configurable parameters that can be set before deployment.

ChatQnA/docker_compose/amd/gpu/rocm/compose.yaml

@@ -165,7 +165,7 @@ services:
 
   chatqna-nginx-server:
     image: ${REGISTRY:-opea}/nginx:${TAG:-latest}
-    container_name: chaqna-nginx-server
+    container_name: chatqna-nginx-server
     depends_on:
       - chatqna-backend-server
       - chatqna-ui-server

ChatQnA/docker_compose/amd/gpu/rocm/compose_faqgen.yaml

@@ -187,7 +187,7 @@ services:
 
   chatqna-nginx-server:
     image: ${REGISTRY:-opea}/nginx:${TAG:-latest}
-    container_name: chaqna-nginx-server
+    container_name: chatqna-nginx-server
     depends_on:
       - chatqna-backend-server
       - chatqna-ui-server

ChatQnA/docker_compose/amd/gpu/rocm/compose_faqgen_vllm.yaml

@@ -192,7 +192,7 @@ services:
 
   chatqna-nginx-server:
     image: ${REGISTRY:-opea}/nginx:${TAG:-latest}
-    container_name: chaqna-nginx-server
+    container_name: chatqna-nginx-server
     depends_on:
       - chatqna-backend-server
       - chatqna-ui-server

ChatQnA/docker_compose/intel/cpu/aipc/compose.yaml

@@ -32,7 +32,7 @@ services:
       retries: 50
     restart: unless-stopped
   tei-embedding-service:
-    image: ghcr.io/huggingface/text-embeddings-inference:cpu-1.6
+    image: ghcr.io/huggingface/text-embeddings-inference:cpu-1.5
     container_name: tei-embedding-server
     ports:
       - "6006:80"
@@ -65,7 +65,7 @@ services:
       RETRIEVER_COMPONENT_NAME: "OPEA_RETRIEVER_REDIS"
     restart: unless-stopped
   tei-reranking-service:
-    image: ghcr.io/huggingface/text-embeddings-inference:cpu-1.6
+    image: ghcr.io/huggingface/text-embeddings-inference:cpu-1.5
     container_name: tei-reranking-server
     ports:
       - "8808:80"

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

@@ -39,7 +39,7 @@ services:
       retries: 50
     restart: unless-stopped
   tei-embedding-service:
-    image: ghcr.io/huggingface/text-embeddings-inference:cpu-1.6
+    image: ghcr.io/huggingface/text-embeddings-inference:cpu-1.5
     container_name: tei-embedding-server
     ports:
       - "6006:80"
@@ -72,7 +72,7 @@ services:
       RETRIEVER_COMPONENT_NAME: "OPEA_RETRIEVER_REDIS"
     restart: unless-stopped
   tei-reranking-service:
-    image: ghcr.io/huggingface/text-embeddings-inference:cpu-1.6
+    image: ghcr.io/huggingface/text-embeddings-inference:cpu-1.5
     container_name: tei-reranking-server
     ports:
       - "8808:80"

ChatQnA/docker_compose/intel/cpu/xeon/compose_faqgen.yaml

@@ -32,7 +32,7 @@ services:
       retries: 50
     restart: unless-stopped
   tei-embedding-service:
-    image: ghcr.io/huggingface/text-embeddings-inference:cpu-1.6
+    image: ghcr.io/huggingface/text-embeddings-inference:cpu-1.5
     container_name: tei-embedding-server
     ports:
       - "6006:80"
@@ -65,7 +65,7 @@ services:
       RETRIEVER_COMPONENT_NAME: "OPEA_RETRIEVER_REDIS"
     restart: unless-stopped
   tei-reranking-service:
-    image: ghcr.io/huggingface/text-embeddings-inference:cpu-1.6
+    image: ghcr.io/huggingface/text-embeddings-inference:cpu-1.5
     container_name: tei-reranking-server
     ports:
       - "8808:80"

ChatQnA/docker_compose/intel/cpu/xeon/compose_faqgen_tgi.yaml

@@ -32,7 +32,7 @@ services:
       retries: 50
     restart: unless-stopped
   tei-embedding-service:
-    image: ghcr.io/huggingface/text-embeddings-inference:cpu-1.6
+    image: ghcr.io/huggingface/text-embeddings-inference:cpu-1.5
     container_name: tei-embedding-server
     ports:
       - "6006:80"
@@ -65,7 +65,7 @@ services:
       RETRIEVER_COMPONENT_NAME: "OPEA_RETRIEVER_REDIS"
     restart: unless-stopped
   tei-reranking-service:
-    image: ghcr.io/huggingface/text-embeddings-inference:cpu-1.6
+    image: ghcr.io/huggingface/text-embeddings-inference:cpu-1.5
     container_name: tei-reranking-server
     ports:
       - "8808:80"

ChatQnA/docker_compose/intel/cpu/xeon/compose_milvus.yaml

@@ -113,7 +113,7 @@ services:
     restart: unless-stopped
 
   tei-embedding-service:
-    image: ghcr.io/huggingface/text-embeddings-inference:cpu-1.6
+    image: ghcr.io/huggingface/text-embeddings-inference:cpu-1.5
     container_name: tei-embedding-server
     ports:
       - "6006:80"
@@ -127,7 +127,7 @@ services:
     command: --model-id ${EMBEDDING_MODEL_ID} --auto-truncate
 
   tei-reranking-service:
-    image: ghcr.io/huggingface/text-embeddings-inference:cpu-1.6
+    image: ghcr.io/huggingface/text-embeddings-inference:cpu-1.5
     container_name: tei-reranking-server
     ports:
       - "8808:80"

ChatQnA/docker_compose/intel/cpu/xeon/compose_pinecone.yaml

@@ -29,7 +29,7 @@ services:
       retries: 50
     restart: unless-stopped
   tei-embedding-service:
-    image: ghcr.io/huggingface/text-embeddings-inference:cpu-1.6
+    image: ghcr.io/huggingface/text-embeddings-inference:cpu-1.5
     container_name: tei-embedding-server
     ports:
       - "6006:80"
@@ -60,7 +60,7 @@ services:
       RETRIEVER_COMPONENT_NAME: "OPEA_RETRIEVER_PINECONE"
     restart: unless-stopped
   tei-reranking-service:
-    image: ghcr.io/huggingface/text-embeddings-inference:cpu-1.6
+    image: ghcr.io/huggingface/text-embeddings-inference:cpu-1.5
     container_name: tei-reranking-server
     ports:
       - "8808:80"

ChatQnA/docker_compose/intel/cpu/xeon/compose_remote.yaml

@@ -33,7 +33,7 @@ services:
       TEI_ENDPOINT: http://tei-embedding-service:80
       HUGGINGFACEHUB_API_TOKEN: ${HUGGINGFACEHUB_API_TOKEN}
   tei-embedding-service:
-    image: ghcr.io/huggingface/text-embeddings-inference:cpu-1.6
+    image: ghcr.io/huggingface/text-embeddings-inference:cpu-1.5
     container_name: tei-embedding-server
     ports:
       - "6006:80"
@@ -66,7 +66,7 @@ services:
       RETRIEVER_COMPONENT_NAME: "OPEA_RETRIEVER_REDIS"
     restart: unless-stopped
   tei-reranking-service:
-    image: ghcr.io/huggingface/text-embeddings-inference:cpu-1.6
+    image: ghcr.io/huggingface/text-embeddings-inference:cpu-1.5
     container_name: tei-reranking-server
     ports:
       - "8808:80"

ChatQnA/docker_compose/intel/cpu/xeon/compose_tgi.yaml

@@ -32,7 +32,7 @@ services:
       retries: 50
     restart: unless-stopped
   tei-embedding-service:
-    image: ghcr.io/huggingface/text-embeddings-inference:cpu-1.6
+    image: ghcr.io/huggingface/text-embeddings-inference:cpu-1.5
     container_name: tei-embedding-server
     ports:
       - "6006:80"
@@ -65,7 +65,7 @@ services:
       RETRIEVER_COMPONENT_NAME: "OPEA_RETRIEVER_REDIS"
     restart: unless-stopped
   tei-reranking-service:
-    image: ghcr.io/huggingface/text-embeddings-inference:cpu-1.6
+    image: ghcr.io/huggingface/text-embeddings-inference:cpu-1.5
     container_name: tei-reranking-server
     ports:
       - "8808:80"

ChatQnA/docker_compose/intel/cpu/xeon/compose_without_rerank.yaml

@@ -32,7 +32,7 @@ services:
       retries: 50
     restart: unless-stopped
   tei-embedding-service:
-    image: ghcr.io/huggingface/text-embeddings-inference:cpu-1.6
+    image: ghcr.io/huggingface/text-embeddings-inference:cpu-1.5
     container_name: tei-embedding-server
     ports:
       - "6006:80"

ChatQnA/docker_compose/intel/hpu/gaudi/README.md

@@ -95,7 +95,7 @@ d560c232b120   opea/retriever:latest
 a1d7ca2d3787   ghcr.io/huggingface/tei-gaudi:1.5.0                                                             "text-embeddings-rou…"   2 minutes ago   Up 2 minutes                0.0.0.0:8808->80/tcp, [::]:8808->80/tcp                                                tei-reranking-gaudi-server
 9a9f3fd4fd4c   opea/vllm-gaudi:latest                                                                          "python3 -m vllm.ent…"   2 minutes ago   Exited (1) 2 minutes ago                                                                                           vllm-gaudi-server
 1ab9bbdf5182   redis/redis-stack:7.2.0-v9                                                                      "/entrypoint.sh"         2 minutes ago   Up 2 minutes                0.0.0.0:6379->6379/tcp, :::6379->6379/tcp, 0.0.0.0:8001->8001/tcp, :::8001->8001/tcp   redis-vector-db
-9ee0789d819e   ghcr.io/huggingface/text-embeddings-inference:cpu-1.6                                           "text-embeddings-rou…"   2 minutes ago   Up 2 minutes                0.0.0.0:8090->80/tcp, [::]:8090->80/tcp                                                tei-embedding-gaudi-server
+9ee0789d819e   ghcr.io/huggingface/text-embeddings-inference:cpu-1.5                                           "text-embeddings-rou…"   2 minutes ago   Up 2 minutes                0.0.0.0:8090->80/tcp, [::]:8090->80/tcp                                                tei-embedding-gaudi-server
 ```
 
 ### Test the Pipeline
@@ -148,7 +148,7 @@ The default deployment utilizes Gaudi devices primarily for the `vllm-service`,
 | ---------------------------- | ----------------------------------------------------- | ------------ |
 | redis-vector-db              | redis/redis-stack:7.2.0-v9                            | No           |
 | dataprep-redis-service       | opea/dataprep:latest                                  | No           |
-| tei-embedding-service        | ghcr.io/huggingface/text-embeddings-inference:cpu-1.6 | No           |
+| tei-embedding-service        | ghcr.io/huggingface/text-embeddings-inference:cpu-1.5 | No           |
 | retriever                    | opea/retriever:latest                                 | No           |
 | tei-reranking-service        | ghcr.io/huggingface/tei-gaudi:1.5.0                   | 1 card       |
 | vllm-service                 | opea/vllm-gaudi:latest                                | Configurable |
@@ -164,7 +164,7 @@ The TGI (Text Generation Inference) deployment and the default deployment differ
 | ---------------------------- | ----------------------------------------------------- | -------------- |
 | redis-vector-db              | redis/redis-stack:7.2.0-v9                            | No             |
 | dataprep-redis-service       | opea/dataprep:latest                                  | No             |
-| tei-embedding-service        | ghcr.io/huggingface/text-embeddings-inference:cpu-1.6 | No             |
+| tei-embedding-service        | ghcr.io/huggingface/text-embeddings-inference:cpu-1.5 | No             |
 | retriever                    | opea/retriever:latest                                 | No             |
 | tei-reranking-service        | ghcr.io/huggingface/tei-gaudi:1.5.0                   | 1 card         |
 | **tgi-service**              | ghcr.io/huggingface/tgi-gaudi:2.3.1                   | Configurable   |
@@ -184,7 +184,7 @@ The TGI (Text Generation Inference) deployment and the default deployment differ
 | ---------------------------- | ----------------------------------------------------- | ------------ |
 | redis-vector-db              | redis/redis-stack:7.2.0-v9                            | No           |
 | dataprep-redis-service       | opea/dataprep:latest                                  | No           |
-| tei-embedding-service        | ghcr.io/huggingface/text-embeddings-inference:cpu-1.6 | No           |
+| tei-embedding-service        | ghcr.io/huggingface/text-embeddings-inference:cpu-1.5 | No           |
 | retriever                    | opea/retriever:latest                                 | No           |
 | tei-reranking-service        | ghcr.io/huggingface/tei-gaudi:1.5.0                   | 1 card       |
 | vllm-service                 | opea/vllm-gaudi:latest                                | Configurable |
@@ -203,7 +203,7 @@ The _compose_without_rerank.yaml_ Docker Compose file is distinct from the defau
 | ---------------------------- | ----------------------------------------------------- | -------------- |
 | redis-vector-db              | redis/redis-stack:7.2.0-v9                            | No             |
 | dataprep-redis-service       | opea/dataprep:latest                                  | No             |
-| tei-embedding-service        | ghcr.io/huggingface/text-embeddings-inference:cpu-1.6 | No             |
+| tei-embedding-service        | ghcr.io/huggingface/text-embeddings-inference:cpu-1.5 | No             |
 | retriever                    | opea/retriever:latest                                 | No             |
 | vllm-service                 | opea/vllm-gaudi:latest                                | Configurable   |
 | chatqna-gaudi-backend-server | opea/chatqna:latest                                   | No             |
@@ -222,7 +222,7 @@ The _compose_guardrails.yaml_ Docker Compose file introduces enhancements over t
 | dataprep-redis-service       | opea/dataprep:latest                                  | No             | No       |
 | _vllm-guardrails-service_    | opea/vllm-gaudi:latest                                | 1 card         | Yes      |
 | _guardrails_                 | opea/guardrails:latest                                | No             | No       |
-| tei-embedding-service        | ghcr.io/huggingface/text-embeddings-inference:cpu-1.6 | No             | No       |
+| tei-embedding-service        | ghcr.io/huggingface/text-embeddings-inference:cpu-1.5 | No             | No       |
 | retriever                    | opea/retriever:latest                                 | No             | No       |
 | tei-reranking-service        | ghcr.io/huggingface/tei-gaudi:1.5.0                   | 1 card         | No       |
 | vllm-service                 | opea/vllm-gaudi:latest                                | Configurable   | Yes      |
@@ -258,7 +258,7 @@ The table provides a comprehensive overview of the ChatQnA services utilized acr
 | ---------------------------- | ----------------------------------------------------- | -------- | -------------------------------------------------------------------------------------------------- |
 | redis-vector-db              | redis/redis-stack:7.2.0-v9                            | No       | Acts as a Redis database for storing and managing data.                                            |
 | dataprep-redis-service       | opea/dataprep:latest                                  | No       | Prepares data and interacts with the Redis database.                                               |
-| tei-embedding-service        | ghcr.io/huggingface/text-embeddings-inference:cpu-1.6 | No       | Provides text embedding services, often using Hugging Face models.                                 |
+| tei-embedding-service        | ghcr.io/huggingface/text-embeddings-inference:cpu-1.5 | No       | Provides text embedding services, often using Hugging Face models.                                 |
 | retriever                    | opea/retriever:latest                                 | No       | Retrieves data from the Redis database and interacts with embedding services.                      |
 | tei-reranking-service        | ghcr.io/huggingface/tei-gaudi:1.5.0                   | Yes      | Reranks text embeddings, typically using Gaudi hardware for enhanced performance.                  |
 | vllm-service                 | opea/vllm-gaudi:latest                                | No       | Handles large language model (LLM) tasks, utilizing Gaudi hardware.                                |
@@ -284,7 +284,7 @@ ChatQnA now supports running the latest DeepSeek models, including [deepseek-ai/
 
 ### tei-embedding-service & tei-reranking-service
 
-The `ghcr.io/huggingface/text-embeddings-inference:cpu-1.6` image supporting `tei-embedding-service` and `tei-reranking-service` depends on the `EMBEDDING_MODEL_ID` or `RERANK_MODEL_ID` environment variables respectively to specify the embedding model and reranking model used for converting text into vector representations and rankings. This choice impacts the quality and relevance of the embeddings rerankings for various applications. Unlike the `vllm-service`, the `tei-embedding-service` and `tei-reranking-service` each typically acquires only one Gaudi device and does not use the `NUM_CARDS` parameter; embedding and reranking tasks generally do not require extensive parallel processing and one Gaudi per service is appropriate. The list of [supported embedding and reranking models](https://github.com/huggingface/tei-gaudi?tab=readme-ov-file#supported-models) can be found at the [huggingface/tei-gaudi](https://github.com/huggingface/tei-gaudi?tab=readme-ov-file#supported-models) website.
+The `ghcr.io/huggingface/text-embeddings-inference:cpu-1.5` image supporting `tei-embedding-service` and `tei-reranking-service` depends on the `EMBEDDING_MODEL_ID` or `RERANK_MODEL_ID` environment variables respectively to specify the embedding model and reranking model used for converting text into vector representations and rankings. This choice impacts the quality and relevance of the embeddings rerankings for various applications. Unlike the `vllm-service`, the `tei-embedding-service` and `tei-reranking-service` each typically acquires only one Gaudi device and does not use the `NUM_CARDS` parameter; embedding and reranking tasks generally do not require extensive parallel processing and one Gaudi per service is appropriate. The list of [supported embedding and reranking models](https://github.com/huggingface/tei-gaudi?tab=readme-ov-file#supported-models) can be found at the [huggingface/tei-gaudi](https://github.com/huggingface/tei-gaudi?tab=readme-ov-file#supported-models) website.
 
 ### tgi-guardrails-service
 

ChatQnA/docker_compose/intel/hpu/gaudi/compose.yaml

@@ -39,7 +39,7 @@ services:
       retries: 50
     restart: unless-stopped
   tei-embedding-service:
-    image: ghcr.io/huggingface/text-embeddings-inference:cpu-1.6
+    image: ghcr.io/huggingface/text-embeddings-inference:cpu-1.5
     container_name: tei-embedding-gaudi-server
     ports:
       - "8090:80"

ChatQnA/docker_compose/intel/hpu/gaudi/compose_faqgen.yaml

@@ -33,7 +33,7 @@ services:
       retries: 50
     restart: unless-stopped
   tei-embedding-service:
-    image: ghcr.io/huggingface/text-embeddings-inference:cpu-1.6
+    image: ghcr.io/huggingface/text-embeddings-inference:cpu-1.5
     container_name: tei-embedding-gaudi-server
     ports:
       - "8090:80"

ChatQnA/docker_compose/intel/hpu/gaudi/compose_faqgen_tgi.yaml

@@ -33,7 +33,7 @@ services:
       retries: 50
     restart: unless-stopped
   tei-embedding-service:
-    image: ghcr.io/huggingface/text-embeddings-inference:cpu-1.6
+    image: ghcr.io/huggingface/text-embeddings-inference:cpu-1.5
     container_name: tei-embedding-gaudi-server
     ports:
       - "8090:80"

ChatQnA/docker_compose/intel/hpu/gaudi/compose_guardrails.yaml

@@ -76,7 +76,7 @@ services:
       HUGGINGFACEHUB_API_TOKEN: ${HUGGINGFACEHUB_API_TOKEN}
     restart: unless-stopped
   tei-embedding-service:
-    image: ghcr.io/huggingface/text-embeddings-inference:cpu-1.6
+    image: ghcr.io/huggingface/text-embeddings-inference:cpu-1.5
     container_name: tei-embedding-gaudi-server
     ports:
       - "8090:80"

ChatQnA/docker_compose/intel/hpu/gaudi/compose_tgi.yaml

@@ -32,7 +32,7 @@ services:
       retries: 50
     restart: unless-stopped
   tei-embedding-service:
-    image: ghcr.io/huggingface/text-embeddings-inference:cpu-1.6
+    image: ghcr.io/huggingface/text-embeddings-inference:cpu-1.5
     container_name: tei-embedding-gaudi-server
     ports:
       - "8090:80"

ChatQnA/docker_compose/intel/hpu/gaudi/compose_without_rerank.yaml

@@ -32,7 +32,7 @@ services:
       retries: 50
     restart: unless-stopped
   tei-embedding-service:
-    image: ghcr.io/huggingface/text-embeddings-inference:cpu-1.6
+    image: ghcr.io/huggingface/text-embeddings-inference:cpu-1.5
     container_name: tei-embedding-gaudi-server
     ports:
       - "8090:80"

ChatQnA/docker_compose/intel/hpu/gaudi/how_to_validate_service.md

@@ -51,7 +51,7 @@ f810f3b4d329   opea/embedding:latest                               "python embed
 174bd43fa6b5   ghcr.io/huggingface/tei-gaudi:1.5.0                    "text-embeddings-rou…"   2 minutes ago   Up 2 minutes                    0.0.0.0:8090->80/tcp, :::8090->80/tcp                                                  tei-embedding-gaudi-server
 05c40b636239   ghcr.io/huggingface/tgi-gaudi:2.3.1                     "text-generation-lau…"   2 minutes ago   Exited (1) About a minute ago                                                                                          tgi-gaudi-server
 74084469aa33   redis/redis-stack:7.2.0-v9                              "/entrypoint.sh"         2 minutes ago   Up 2 minutes                    0.0.0.0:6379->6379/tcp, :::6379->6379/tcp, 0.0.0.0:8001->8001/tcp, :::8001->8001/tcp   redis-vector-db
-88399dbc9e43   ghcr.io/huggingface/text-embeddings-inference:cpu-1.6   "text-embeddings-rou…"   2 minutes ago   Up 2 minutes                    0.0.0.0:8808->80/tcp, :::8808->80/tcp                                                  tei-reranking-gaudi-server
+88399dbc9e43   ghcr.io/huggingface/text-embeddings-inference:cpu-1.5   "text-embeddings-rou…"   2 minutes ago   Up 2 minutes                    0.0.0.0:8808->80/tcp, :::8808->80/tcp                                                  tei-reranking-gaudi-server
 ```
 
 In this case, `ghcr.io/huggingface/tgi-gaudi:2.3.1` Existed.

ChatQnA/tests/test_compose_faqgen_on_gaudi.sh

@@ -31,8 +31,6 @@ function build_docker_images() {
     service_list="chatqna chatqna-ui dataprep retriever llm-faqgen vllm-gaudi nginx"
     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-1.6
-    docker pull ghcr.io/huggingface/tei-gaudi:1.5.0
     docker images && sleep 1s
 }
 

ChatQnA/tests/test_compose_faqgen_on_rocm.sh

@@ -69,9 +69,6 @@ function build_docker_images() {
     service_list="chatqna chatqna-ui dataprep retriever llm-faqgen nginx"
     docker compose -f build.yaml build ${service_list} --no-cache > "${LOG_PATH}"/docker_image_build.log
 
-    docker pull ghcr.io/huggingface/text-generation-inference:2.3.1-rocm
-    docker pull ghcr.io/huggingface/text-embeddings-inference:cpu-1.6
-
     docker images && sleep 1s
 }
 

ChatQnA/tests/test_compose_faqgen_on_xeon.sh

@@ -32,7 +32,6 @@ function build_docker_images() {
     service_list="chatqna chatqna-ui dataprep retriever llm-faqgen vllm nginx"
     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-1.6
     docker images && sleep 1s
 }
 

ChatQnA/tests/test_compose_faqgen_tgi_on_gaudi.sh

@@ -28,9 +28,6 @@ function build_docker_images() {
     service_list="chatqna chatqna-ui dataprep retriever llm-faqgen nginx"
     docker compose -f build.yaml build ${service_list} --no-cache > ${LOG_PATH}/docker_image_build.log
 
-    docker pull ghcr.io/huggingface/tgi-gaudi:2.0.6
-    docker pull ghcr.io/huggingface/text-embeddings-inference:cpu-1.6
-    docker pull ghcr.io/huggingface/tei-gaudi:1.5.0
     docker images && sleep 1s
 }
 

ChatQnA/tests/test_compose_faqgen_tgi_on_xeon.sh

@@ -32,8 +32,6 @@ function build_docker_images() {
     service_list="chatqna chatqna-ui dataprep retriever llm-faqgen nginx"
     docker compose -f build.yaml build ${service_list} --no-cache > ${LOG_PATH}/docker_image_build.log
 
-    docker pull ghcr.io/huggingface/text-generation-inference:2.4.0-intel-cpu
-    docker pull ghcr.io/huggingface/text-embeddings-inference:cpu-1.6
     docker images && sleep 1s
 }
 

ChatQnA/tests/test_compose_guardrails_on_gaudi.sh

@@ -31,9 +31,6 @@ function build_docker_images() {
     service_list="chatqna chatqna-ui dataprep retriever vllm-gaudi guardrails nginx"
     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-1.6
-    docker pull ghcr.io/huggingface/tei-gaudi:1.5.0
-
     docker images && sleep 1s
 }
 

ChatQnA/tests/test_compose_milvus_on_xeon.sh

@@ -35,13 +35,10 @@ function build_docker_images() {
     service_list="chatqna chatqna-ui dataprep retriever vllm nginx"
     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-1.6
-
     docker images && sleep 1s
 }
 function start_services() {
     cd $WORKPATH/docker_compose/intel/cpu/xeon/
-    export no_proxy=${no_proxy},${ip_address}
     export EMBEDDING_MODEL_ID="BAAI/bge-base-en-v1.5"
     export RERANK_MODEL_ID="BAAI/bge-reranker-base"
     export LLM_MODEL_ID="meta-llama/Meta-Llama-3-8B-Instruct"

ChatQnA/tests/test_compose_on_gaudi.sh

@@ -31,8 +31,6 @@ function build_docker_images() {
     service_list="chatqna chatqna-ui dataprep retriever vllm-gaudi nginx"
     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-1.6
-    docker pull ghcr.io/huggingface/tei-gaudi:1.5.0
     docker images && sleep 1s
 }
 

ChatQnA/tests/test_compose_on_rocm.sh

@@ -67,9 +67,6 @@ function build_docker_images() {
     service_list="chatqna chatqna-ui dataprep retriever nginx"
     docker compose -f build.yaml build ${service_list} --no-cache > "${LOG_PATH}"/docker_image_build.log
 
-    docker pull ghcr.io/huggingface/text-generation-inference:2.3.1-rocm
-    docker pull ghcr.io/huggingface/text-embeddings-inference:cpu-1.6
-
     docker images && sleep 1s
 }
 

ChatQnA/tests/test_compose_on_xeon.sh

@@ -34,8 +34,6 @@ function build_docker_images() {
     service_list="chatqna chatqna-ui dataprep retriever vllm nginx"
     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-1.6
-
     docker images && sleep 1s
 }
 

ChatQnA/tests/test_compose_pinecone_on_xeon.sh

@@ -35,8 +35,6 @@ function build_docker_images() {
     service_list="chatqna chatqna-ui dataprep retriever vllm nginx"
     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-1.6
-
     docker images && sleep 1s
 }
 

ChatQnA/tests/test_compose_tgi_on_gaudi.sh

@@ -27,10 +27,6 @@ function build_docker_images() {
     service_list="chatqna chatqna-ui dataprep retriever nginx"
     docker compose -f build.yaml build ${service_list} --no-cache > ${LOG_PATH}/docker_image_build.log
 
-    docker pull ghcr.io/huggingface/tgi-gaudi:2.3.1
-    docker pull ghcr.io/huggingface/text-embeddings-inference:cpu-1.6
-    docker pull ghcr.io/huggingface/tei-gaudi:1.5.0
-
     docker images && sleep 1s
 }
 

ChatQnA/tests/test_compose_tgi_on_xeon.sh

@@ -27,9 +27,6 @@ function build_docker_images() {
     service_list="chatqna chatqna-ui dataprep retriever nginx"
     docker compose -f build.yaml build ${service_list} --no-cache > ${LOG_PATH}/docker_image_build.log
 
-    docker pull ghcr.io/huggingface/text-generation-inference:2.4.0-intel-cpu
-    docker pull ghcr.io/huggingface/text-embeddings-inference:cpu-1.6
-
     docker images && sleep 1s
 }
 

ChatQnA/tests/test_compose_without_rerank_on_gaudi.sh

@@ -31,9 +31,6 @@ function build_docker_images() {
     service_list="chatqna chatqna-ui dataprep retriever vllm-gaudi nginx"
     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-1.6
-    docker pull ghcr.io/huggingface/tei-gaudi:1.5.0
-
     docker images && sleep 1s
 }
 

ChatQnA/tests/test_compose_without_rerank_on_xeon.sh

@@ -35,8 +35,6 @@ function build_docker_images() {
     service_list="chatqna chatqna-ui dataprep retriever vllm nginx"
     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-1.6
-
     docker images && sleep 1s
 }
 

CodeGen/docker_compose/amd/gpu/rocm/README.md

@@ -2,78 +2,69 @@
 
 This README provides instructions for deploying the CodeGen application using Docker Compose on a system equipped with AMD GPUs supporting ROCm, detailing the steps to configure, run, and validate the services. This guide defaults to using the **vLLM** backend for LLM serving.
 
+If the service response has a meaningful response in the value of the "choices.text" key,
+then we consider the vLLM service to be successfully launched
+
 ## Table of Contents
 
-- [Steps to Run with Docker Compose (Default vLLM)](#steps-to-run-with-docker-compose-default-vllm)
-- [Service Overview](#service-overview)
+- [Overview](#overview)
+- [Prerequisites](#prerequisites)
+- [Quick Start](#quick-start)
 - [Available Deployment Options](#available-deployment-options)
-  - [compose_vllm.yaml (vLLM - Default)](#compose_vllyaml-vllm---default)
-  - [compose.yaml (TGI)](#composeyaml-tgi)
-- [Configuration Parameters and Usage](#configuration-parameters-and-usage)
-  - [Docker Compose GPU Configuration](#docker-compose-gpu-configuration)
-  - [Environment Variables (`set_env*.sh`)](#environment-variables-set_envsh)
-- [Building Docker Images Locally (Optional)](#building-docker-images-locally-optional)
-  - [1. Setup Build Environment](#1-setup-build-environment)
-  - [2. Clone Repositories](#2-clone-repositories)
-  - [3. Select Services and Build](#3-select-services-and-build)
-- [Validate Service Health](#validate-service-health)
-  - [1. Validate the vLLM/TGI Service](#1-validate-the-vllmtgi-service)
-  - [2. Validate the LLM Service](#2-validate-the-llm-service)
-  - [3. Validate the MegaService (Backend)](#3-validate-the-megaservice-backend)
-  - [4. Validate the Frontend (UI)](#4-validate-the-frontend-ui)
-- [How to Open the UI](#how-to-open-the-ui)
+  - [Default: vLLM-based Deployment (`--profile codegen-xeon-vllm`)](#default-vllm-based-deployment---profile-codegen-xeon-vllm)
+  - [TGI-based Deployment (`--profile codegen-xeon-tgi`)](#tgi-based-deployment---profile-codegen-xeon-tgi)
+- [Configuration Parameters](#configuration-parameters)
+  - [Environment Variables](#environment-variables)
+  - [Compose Profiles](#compose-profiles)
+- [Building Custom Images (Optional)](#building-custom-images-optional)
+- [Validate Services](#validate-services)
+  - [Check Container Status](#check-container-status)
+  - [Run Validation Script/Commands](#run-validation-scriptcommands)
+- [Accessing the User Interface (UI)](#accessing-the-user-interface-ui)
+  - [Gradio UI (Default)](#gradio-ui-default)
+  - [Svelte UI (Optional)](#svelte-ui-optional)
+  - [React UI (Optional)](#react-ui-optional)
+  - [VS Code Extension (Optional)](#vs-code-extension-optional)
 - [Troubleshooting](#troubleshooting)
 - [Stopping the Application](#stopping-the-application)
 - [Next Steps](#next-steps)
 
-## Steps to Run with Docker Compose (Default vLLM)
+## Overview
 
-_This section assumes you are using pre-built images and targets the default vLLM deployment._
+This guide focuses on running the pre-configured CodeGen service using Docker Compose on AMD ROCm processing acelarating platform. It leverages containers optimized for Intel architecture for the CodeGen gateway, LLM serving (vLLM or TGI), and UI.
 
-1.  **Set Deploy Environment Variables:**
+## CodeGen Quick Start Deployment
 
-    - Go to the Docker Compose directory:
-      ```bash
-      # Adjust path if your GenAIExamples clone is located elsewhere
-      cd GenAIExamples/CodeGen/docker_compose/amd/gpu/rocm
-      ```
-    - Setting variables in the operating system environment:
-      - Set variable `HUGGINGFACEHUB_API_TOKEN`:
-        ```bash
-        ### Replace the string 'your_huggingfacehub_token' with your HuggingFacehub repository access token.
-        export HUGGINGFACEHUB_API_TOKEN='your_huggingfacehub_token'
-        ```
-    - Edit the environment script for the **vLLM** deployment (`set_env_vllm.sh`):
-      ```bash
-      nano set_env_vllm.sh
-      ```
-      - Configure `HOST_IP`, `EXTERNAL_HOST_IP`, `*_PORT` variables, and proxies (`http_proxy`, `https_proxy`, `no_proxy`) as described in the Configuration section below.
-    - Source the environment variables:
-      ```bash
-      . set_env_vllm.sh
-      ```
+This section describes how to quickly deploy and test the CodeGen service manually on an AMD GPU (ROCm) platform. The basic steps are:
 
-2.  **Start the Services (vLLM):**
+1. [Prerequisites](#prerequisites)
+2. [Generate a HuggingFace Access Token](#generate-a-huggingface-access-token)
+3. [Configure the Deployment Environment](#configure-the-deployment-environment)
+4. [Deploy the Services Using Docker Compose](#deploy-the-services-using-docker-compose)
+5. [Check the Deployment Status](#check-the-deployment-status)
+6. [Test the Pipeline](#test-the-pipeline)
+7. [Cleanup the Deployment](#cleanup-the-deployment)
 
-    ```bash
-    docker compose -f compose_vllm.yaml up -d
-    ```
+## Prerequisites
 
-3.  **Verify:** Proceed to the [Validate Service Health](#validate-service-health) section after allowing time for services to start.
+- Docker and Docker Compose installed.
+- x86 Intel or AMD CPU.
+- 4x AMD Instinct MI300X Accelerators.
+- Git installed (for cloning repository).
+- Hugging Face Hub API Token (for downloading models).
+- Access to the internet (or a private model cache).
+- Clone the `GenAIExamples` repository:
 
-## Service Overview
+```bash
+  git clone https://github.com/opea-project/GenAIExamples.git
+  cd GenAIExamples/CodeGen/docker_compose/amd/gpu/rocm/
+```
 
-When using the default `compose_vllm.yaml` (vLLM-based), the following services are deployed:
+Checkout a released version, such as v1.3:
 
-| Service Name           | Default Port (Host)                            | Internal Port | Purpose                     |
-| :--------------------- | :--------------------------------------------- | :------------ | :-------------------------- |
-| codegen-vllm-service   | `${CODEGEN_VLLM_SERVICE_PORT}` (e.g., 8028)    | 8000          | LLM Serving (vLLM on ROCm)  |
-| codegen-llm-server     | `${CODEGEN_LLM_SERVICE_PORT}` (e.g., 9000)     | 80            | LLM Microservice Wrapper    |
-| codegen-backend-server | `${CODEGEN_BACKEND_SERVICE_PORT}` (e.g., 7778) | 80            | CodeGen MegaService/Gateway |
-| codegen-ui-server      | `${CODEGEN_UI_SERVICE_PORT}` (e.g., 5173)      | 80            | Frontend User Interface     |
-
-_(Note: Ports are configurable via `set_env_vllm.sh`. Check the script for actual defaults used.)_
-_(Note: The TGI deployment (`compose.yaml`) uses `codegen-tgi-service` instead of `codegen-vllm-service`)_
+```bash
+git checkout v1.3
+```
 
 ## Available Deployment Options
 
@@ -91,6 +82,69 @@ This directory provides different Docker Compose files:
 
 ## Configuration Parameters and Usage
 
+### Environment Variables (`set_env*.sh`)
+
+These scripts (`set_env_vllm.sh` for vLLM, `set_env.sh` for TGI) configure crucial parameters passed to the containers.
+
+This example covers the single-node on-premises deployment of the CodeGen example using OPEA components. There are various ways to enable CodeGen, but this example will focus on four options available for deploying the CodeGen pipeline to AMD ROCm AI Accelerators. This example begins with a Quick Start section and then documents how to modify deployments, leverage new models and configure the number of allocated devices.
+
+This example includes the following sections:
+
+- [CodeGen Quick Start Deployment](#CodeGen-quick-start-deployment): Demonstrates how to quickly deploy a CodeGen application/pipeline on AMD GPU (ROCm) platform.
+- [CodeGen Docker Compose Files](#CodeGen-docker-compose-files): Describes some example deployments and their docker compose files.
+- [CodeGen Service Configuration](#CodeGen-service-configuration): Describes the services and possible configuration changes.
+
+**Note** This example requires access to a properly installed AMD ROCm platform with a functional Docker service configured
+
+## Generate a HuggingFace Access Token
+
+Some HuggingFace resources, such as some models, are only accessible if you have an access token. If you do not already have a HuggingFace access token, you can create one by first creating an account by following the steps provided at [HuggingFace](https://huggingface.co/) and then generating a [user access token](https://huggingface.co/docs/transformers.js/en/guides/private#step-1-generating-a-user-access-token).
+
+## Configure the Deployment Environment
+
+### Environment Variables
+
+Key parameters are configured via environment variables set before running `docker compose up`.
+
+| Environment Variable                    | Description                                                                                                         | Default (Set Externally)                                                                         |
+| :-------------------------------------- | :------------------------------------------------------------------------------------------------------------------ | :----------------------------------------------------------------------------------------------- |
+| `HOST_IP`                               | External IP address of the host machine. **Required.**                                                              | `your_external_ip_address`                                                                       |
+| `HUGGINGFACEHUB_API_TOKEN`              | Your Hugging Face Hub token for model access. **Required.**                                                         | `your_huggingface_token`                                                                         |
+| `LLM_MODEL_ID`                          | Hugging Face model ID for the CodeGen LLM (used by TGI/vLLM service). Configured within `compose.yaml` environment. | `Qwen/Qwen2.5-Coder-7B-Instruct`                                                                 |
+| `EMBEDDING_MODEL_ID`                    | Hugging Face model ID for the embedding model (used by TEI service). Configured within `compose.yaml` environment.  | `BAAI/bge-base-en-v1.5`                                                                          |
+| `LLM_ENDPOINT`                          | Internal URL for the LLM serving endpoint (used by `codegen-llm-server`). Configured in `compose.yaml`.             | `http://codegen-tgi-server:80/generate` or `http://codegen-vllm-server:8000/v1/chat/completions` |
+| `TEI_EMBEDDING_ENDPOINT`                | Internal URL for the Embedding service. Configured in `compose.yaml`.                                               | `http://codegen-tei-embedding-server:80/embed`                                                   |
+| `DATAPREP_ENDPOINT`                     | Internal URL for the Data Preparation service. Configured in `compose.yaml`.                                        | `http://codegen-dataprep-server:80/dataprep`                                                     |
+| `BACKEND_SERVICE_ENDPOINT`              | External URL for the CodeGen Gateway (MegaService). Derived from `HOST_IP` and port `7778`.                         | `http://${HOST_IP}:7778/v1/codegen`                                                              |
+| `*_PORT` (Internal)                     | Internal container ports (e.g., `80`, `6379`). Defined in `compose.yaml`.                                           | N/A                                                                                              |
+| `http_proxy` / `https_proxy`/`no_proxy` | Network proxy settings (if required).                                                                               | `""`                                                                                             |
+
+To set up environment variables for deploying CodeGen services, source the _setup_env.sh_ script in this directory:
+
+For TGI
+
+```bash
+export host_ip="External_Public_IP"           #ip address of the node
+export HUGGINGFACEHUB_API_TOKEN="Your_Huggingface_API_Token"
+export http_proxy="Your_HTTP_Proxy"           #http proxy if any
+export https_proxy="Your_HTTPs_Proxy"         #https proxy if any
+export no_proxy=localhost,127.0.0.1,$host_ip  #additional no proxies if needed
+export no_proxy=$no_proxy
+source ./set_env.sh
+```
+
+For vLLM
+
+```bash
+export host_ip="External_Public_IP"           #ip address of the node
+export HUGGINGFACEHUB_API_TOKEN="Your_Huggingface_API_Token"
+export http_proxy="Your_HTTP_Proxy"           #http proxy if any
+export https_proxy="Your_HTTPs_Proxy"         #https proxy if any
+export no_proxy=localhost,127.0.0.1,$host_ip  #additional no proxies if needed
+export no_proxy=$no_proxy
+source ./set_env_vllm.sh
+```
+
 ### Docker Compose GPU Configuration
 
 To enable GPU support for AMD GPUs, the following configuration is added to the Docker Compose files (`compose.yaml`, `compose_vllm.yaml`) for the LLM serving container:
@@ -103,7 +157,6 @@ shm_size: 1g
 devices:
   - /dev/kfd:/dev/kfd
   - /dev/dri/:/dev/dri/
-# - /dev/dri/render128:/dev/dri/render128
 cap_add:
   - SYS_PTRACE
 group_add:
@@ -112,302 +165,329 @@ security_opt:
   - seccomp:unconfined
 ```
 
-This configuration forwards all available GPUs to the container. To use a specific GPU, specify its `cardN` and `renderN` device IDs (e.g., `/dev/dri/card0:/dev/dri/card0`, `/dev/dri/render128:/dev/dri/render128`). Use AMD GPU driver utilities to identify device IDs.
+This configuration forwards all available GPUs to the container. To use a specific GPU, specify its `cardN` and `renderN` device IDs (e.g., `/dev/dri/card0:/dev/dri/card0`, `/dev/dri/render128:/dev/dri/render128`). For example:
 
-### Environment Variables (`set_env*.sh`)
+```yaml
+shm_size: 1g
+devices:
+  - /dev/kfd:/dev/kfd
+  - /dev/dri/card0:/dev/dri/card0
+  - /dev/dri/render128:/dev/dri/render128
+cap_add:
+  - SYS_PTRACE
+group_add:
+  - video
+security_opt:
+  - seccomp:unconfined
+```
 
-These scripts (`set_env_vllm.sh` for vLLM, `set_env.sh` for TGI) configure crucial parameters passed to the containers.
+**How to Identify GPU Device IDs:**
+Use AMD GPU driver utilities to determine the correct `cardN` and `renderN` IDs for your GPU.
 
-| Environment Variable           | Description                                                                                              | Example Value (Edit in Script)   |
-| :----------------------------- | :------------------------------------------------------------------------------------------------------- | :------------------------------- |
-| `HUGGINGFACEHUB_API_TOKEN`     | Your Hugging Face Hub token for model access. **Required.**                                              | `your_huggingfacehub_token`      |
-| `HOST_IP`                      | Internal/Primary IP address of the host machine. Used for inter-service communication. **Required.**     | `192.168.1.100`                  |
-| `EXTERNAL_HOST_IP`             | External IP/hostname used to access the UI from outside. Same as `HOST_IP` if no proxy/LB. **Required.** | `192.168.1.100`                  |
-| `CODEGEN_LLM_MODEL_ID`         | Hugging Face model ID for the CodeGen LLM.                                                               | `Qwen/Qwen2.5-Coder-7B-Instruct` |
-| `CODEGEN_VLLM_SERVICE_PORT`    | Host port mapping for the vLLM serving endpoint (in `set_env_vllm.sh`).                                  | `8028`                           |
-| `CODEGEN_TGI_SERVICE_PORT`     | Host port mapping for the TGI serving endpoint (in `set_env.sh`).                                        | `8028`                           |
-| `CODEGEN_LLM_SERVICE_PORT`     | Host port mapping for the LLM Microservice wrapper.                                                      | `9000`                           |
-| `CODEGEN_BACKEND_SERVICE_PORT` | Host port mapping for the CodeGen MegaService/Gateway.                                                   | `7778`                           |
-| `CODEGEN_UI_SERVICE_PORT`      | Host port mapping for the UI service.                                                                    | `5173`                           |
-| `http_proxy`                   | Network HTTP Proxy URL (if required).                                                                    | `Your_HTTP_Proxy`                |
-| `https_proxy`                  | Network HTTPS Proxy URL (if required).                                                                   | `Your_HTTPs_Proxy`               |
-| `no_proxy`                     | Comma-separated list of hosts to bypass proxy. Should include `localhost,127.0.0.1,$HOST_IP`.            | `localhost,127.0.0.1`            |
+### Deploy the Services Using Docker Compose
 
-**How to Use:** Edit the relevant `set_env*.sh` file (`set_env_vllm.sh` for the default) with your values, then source it (`. ./set_env*.sh`) before running `docker compose`.
+Please refer to the table below to build different microservices from source:
 
-## Building Docker Images Locally (Optional)
+When using the default `compose_vllm.yaml` (vLLM-based), the following services are deployed:
 
-Follow these steps if you need to build the Docker images from source instead of using pre-built ones.
+| Service Name           | Default Port (Host)                            | Internal Port | Purpose                     |
+| :--------------------- | :--------------------------------------------- | :------------ | :-------------------------- |
+| codegen-vllm-service   | `${CODEGEN_VLLM_SERVICE_PORT}` (e.g., 8028)    | 8000          | LLM Serving (vLLM on ROCm)  |
+| codegen-llm-server     | `${CODEGEN_LLM_SERVICE_PORT}` (e.g., 9000)     | 80            | LLM Microservice Wrapper    |
+| codegen-backend-server | `${CODEGEN_BACKEND_SERVICE_PORT}` (e.g., 7778) | 80            | CodeGen MegaService/Gateway |
+| codegen-ui-server      | `${CODEGEN_UI_SERVICE_PORT}` (e.g., 5173)      | 80            | Frontend User Interface     |
 
-### 1. Setup Build Environment
+To deploy the CodeGen services, execute the `docker compose up` command with the appropriate arguments. For a vLLM deployment, execute:
 
-- #### Create application install directory and go to it:
+```bash
+docker compose -f compose_vllm.sh up -d
+```
 
-  ```bash
-  mkdir ~/codegen-install && cd codegen-install
-  ```
+The CodeGen docker images should automatically be downloaded from the `OPEA registry` and deployed on the AMD GPU (ROCM) Platform:
 
-### 2. Clone Repositories
+```bash
+[+] Running 5/5_default              Created                                                              0.3s
+ ✔ Network rocm_default              Created                                                              0.3s
+ ✔ Container codegen-vllm-service    Healthy                                                              100.9s
+ ✔ Container codegen-llm-server      Started                                                              101.2s
+ ✔ Container codegen-backend-server  Started                                                              101.5s
+ ✔ Container codegen-ui-server       Started                                                              101.9s
+```
 
-- #### Clone the repository GenAIExamples (the default repository branch "main" is used here):
+# To deploy the CodeGen services, execute the `docker compose up` command with the appropriate arguments. For a TGI deployment, execute:
 
-  ```bash
-  git clone https://github.com/opea-project/GenAIExamples.git
-  ```
+```
+docker compose  up -d
+```
 
-  If you need to use a specific branch/tag of the GenAIExamples repository, then (v1.3 replace with its own value):
+The CodeGen docker images should automatically be downloaded from the `OPEA registry` and deployed on the AMD GPU (ROCM) Platform:
 
-  ```bash
-  git clone https://github.com/opea-project/GenAIExamples.git && cd GenAIExamples && git checkout v1.3
-  ```
+```bash
+[+] Running 5/5_default              Created                                                                0.4s
+ ✔ Network rocm_default              Created                                                                0.4s
+ ✔ Container codegen-tgi-service     Healthy                                                                102.6s
+ ✔ Container codegen-llm-server      Started                                                                100.2s
+ ✔ Container codegen-backend-server  Started                                                                103.7s
+ ✔ Container codegen-ui-server       Started                                                                102.9s
+```
 
-  We remind you that when using a specific version of the code, you need to use the README from this version.
+## Building Custom Images (Optional)
 
-- #### Go to build directory:
+If you need to modify the microservices:
 
-  ```bash
-  cd ~/codegen-install/GenAIExamples/CodeGen/docker_image_build
-  ```
+1.  Clone the [OPEA GenAIComps](https://github.com/opea-project/GenAIComps) repository.
+2.  Follow build instructions in the respective component directories (e.g., `comps/llms/text-generation`, `comps/codegen`, `comps/ui/gradio`, etc.). Use the provided Dockerfiles (e.g., `CodeGen/Dockerfile`, `CodeGen/ui/docker/Dockerfile.gradio`).
+3.  Tag your custom images appropriately (e.g., `my-custom-codegen:latest`).
+4.  Update the `image:` fields in the `compose.yaml` file to use your custom image tags.
 
-- Cleaning up the GenAIComps repository if it was previously cloned in this directory.
-  This is necessary if the build was performed earlier and the GenAIComps folder exists and is not empty:
+_Refer to the main [CodeGen README](../../../../README.md) for links to relevant GenAIComps components._
 
-  ```bash
-  echo Y | rm -R GenAIComps
-  ```
+## Validate Services
 
-- #### Clone the repository GenAIComps (the default repository branch "main" is used here):
+### Check the Deployment Status for TGI base deployment
 
-  ```bash
-  git clone https://github.com/opea-project/GenAIComps.git
-  ```
+After running docker compose, check if all the containers launched via docker compose have started:
 
-  If you use a specific tag of the GenAIExamples repository,
-  then you should also use the corresponding tag for GenAIComps. (v1.3 replace with its own value):
+```bash
+docker ps -a
+```
 
-  ```bash
-  git clone https://github.com/opea-project/GenAIComps.git && cd GenAIComps && git checkout v1.3
-  ```
+For the default deployment, the following 10 containers should have started:
 
-  We remind you that when using a specific version of the code, you need to use the README from this version.
+```bash
+CONTAINER ID   IMAGE                                                      COMMAND                  CREATED         STATUS                   PORTS                                           NAMES
+1d08caeae2ed   opea/codegen-ui:latest                                     "docker-entrypoint.s…"   2 minutes ago   Up About a minute        0.0.0.0:18151->5173/tcp, [::]:18151->5173/tcp   codegen-ui-server
+f52adc66c116   opea/codegen:latest                                        "python codegen.py"      2 minutes ago   Up About a minute        0.0.0.0:18150->7778/tcp, [::]:18150->7778/tcp   codegen-backend-server
+4b1cb8f5d4ff   opea/llm-textgen:latest                                    "bash entrypoint.sh"     2 minutes ago   Up About a minute        0.0.0.0:9000->9000/tcp, :::9000->9000/tcp       codegen-llm-server
+3bb4ee0abf15   ghcr.io/huggingface/text-generation-inference:2.4.1-rocm   "/tgi-entrypoint.sh …"   2 minutes ago   Up 2 minutes (healthy)   0.0.0.0:8028->80/tcp, [::]:8028->80/tcp         codegen-tgi-service
+```
 
-### 3. Select Services and Build
+### Check the Deployment Status for vLLM base deployment
 
-- #### Setting the list of images for the build (from the build file.yaml)
+After running docker compose, check if all the containers launched via docker compose have started:
 
-  Select the services corresponding to your desired deployment (vLLM is the default):
+```bash
+docker ps -a
+```
 
-  ##### vLLM-based application (Default)
+For the default deployment, the following 10 containers should have started:
 
-  ```bash
-  service_list="vllm-rocm llm-textgen codegen codegen-ui"
-  ```
+```bash
+CONTAINER ID   IMAGE                     COMMAND                  CREATED          STATUS                    PORTS                                           NAMES
+f100cc326343   opea/codegen-ui:latest    "docker-entrypoint.s…"   16 minutes ago   Up 14 minutes             0.0.0.0:18151->5173/tcp, [::]:18151->5173/tcp   codegen-ui-server
+c59de0b2da5b   opea/codegen:latest       "python codegen.py"      16 minutes ago   Up 14 minutes             0.0.0.0:18150->7778/tcp, [::]:18150->7778/tcp   codegen-backend-server
+dcd83e0e4c0f   opea/llm-textgen:latest   "bash entrypoint.sh"     16 minutes ago   Up 14 minutes             0.0.0.0:9000->9000/tcp, :::9000->9000/tcp       codegen-llm-server
+d091d8f2fab6   opea/vllm-rocm:latest     "python3 /workspace/…"   16 minutes ago   Up 16 minutes (healthy)   0.0.0.0:8028->8011/tcp, [::]:8028->8011/tcp     codegen-vllm-service
+```
 
-  ##### TGI-based application
+### Test the Pipeline
 
-  ```bash
-  service_list="llm-textgen codegen codegen-ui"
-  ```
+### If you use vLLM:
 
-- #### Optional. Pull TGI Docker Image (Do this if you plan to build/use the TGI variant)
+```bash
+DATA='{"model": "Qwen/Qwen2.5-Coder-7B-Instruct", '\
+'"messages": [{"role": "user", "content": "Implement a high-level API for a TODO list application. '\
+'The API takes as input an operation request and updates the TODO list in place. '\
+'If the request is invalid, raise an exception."}], "max_tokens": 256}'
 
-  ```bash
-  docker pull ghcr.io/huggingface/text-generation-inference:2.3.1-rocm
-  ```
+curl http://${HOST_IP}:${CODEGEN_VLLM_SERVICE_PORT}/v1/chat/completions \
+  -X POST \
+  -d "$DATA" \
+  -H 'Content-Type: application/json'
+```
 
-- #### Build Docker Images
+Checking the response from the service. The response should be similar to JSON:
 
-  _Ensure you are in the `~/codegen-install/GenAIExamples/CodeGen/docker_image_build` directory._
+````json
+{
+  "id": "chatcmpl-142f34ef35b64a8db3deedd170fed951",
+  "object": "chat.completion",
+  "created": 1742270316,
+  "model": "Qwen/Qwen2.5-Coder-7B-Instruct",
+  "choices": [
+    {
+      "index": 0,
+      "message": {
+        "role": "assistant",
+        "content": "```python\nfrom typing import Optional, List, Dict, Union\nfrom pydantic import BaseModel, validator\n\nclass OperationRequest(BaseModel):\n    # Assuming OperationRequest is already defined as per the given text\n    pass\n\nclass UpdateOperation(OperationRequest):\n    new_items: List[str]\n\n    def apply_and_maybe_raise(self, updatable_item: \"Updatable todo list\") -> None:\n        # Assuming updatable_item is an instance of Updatable todo list\n        self.validate()\n        updatable_item.add_items(self.new_items)\n\nclass Updatable:\n    # Abstract class for items that can be updated\n    pass\n\nclass TodoList(Updatable):\n    # Class that represents a todo list\n    items: List[str]\n\n    def add_items(self, new_items: List[str]) -> None:\n        self.items.extend(new_items)\n\ndef handle_request(operation_request: OperationRequest) -> None:\n    # Function to handle an operation request\n    if isinstance(operation_request, UpdateOperation):\n        operation_request.apply_and_maybe_raise(get_todo_list_for_update())\n    else:\n        raise ValueError(\"Invalid operation request\")\n\ndef get_todo_list_for_update() -> TodoList:\n    # Function to get the todo list for update\n    # Assuming this function returns the",
+        "tool_calls": []
+      },
+      "logprobs": null,
+      "finish_reason": "length",
+      "stop_reason": null
+    }
+  ],
+  "usage": { "prompt_tokens": 66, "total_tokens": 322, "completion_tokens": 256, "prompt_tokens_details": null },
+  "prompt_logprobs": null
+}
+````
 
-  ```bash
-  docker compose -f build.yaml build ${service_list} --no-cache
-  ```
+If the service response has a meaningful response in the value of the "choices.message.content" key,
+then we consider the vLLM service to be successfully launched
 
-  After the build, check the list of images with the command:
+### If you use TGI:
 
-  ```bash
-  docker image ls
-  ```
+```bash
+DATA='{"inputs":"Implement a high-level API for a TODO list application. '\
+'The API takes as input an operation request and updates the TODO list in place. '\
+'If the request is invalid, raise an exception.",'\
+'"parameters":{"max_new_tokens":256,"do_sample": true}}'
 
-  The list of images should include (depending on `service_list`):
+curl http://${HOST_IP}:${CODEGEN_TGI_SERVICE_PORT}/generate \
+  -X POST \
+  -d "$DATA" \
+  -H 'Content-Type: application/json'
+```
 
-  ###### vLLM-based application:
+Checking the response from the service. The response should be similar to JSON:
 
-  - opea/vllm-rocm:latest
-  - opea/llm-textgen:latest
-  - opea/codegen:latest
-  - opea/codegen-ui:latest
+````json
+{
+  "generated_text": " The supported operations are \"add_task\", \"complete_task\", and \"remove_task\". Each operation can be defined with a corresponding function in the API.\n\nAdd your API in the following format:\n\n```\nTODO App API\n\nsupported operations:\n\noperation name           description\n-----------------------  ------------------------------------------------\n<operation_name>         <operation description>\n```\n\nUse type hints for function parameters and return values. Specify a text description of the API's supported operations.\n\nUse the following code snippet as a starting point for your high-level API function:\n\n```\nclass TodoAPI:\n    def __init__(self, tasks: List[str]):\n        self.tasks = tasks  # List of tasks to manage\n\n    def add_task(self, task: str) -> None:\n        self.tasks.append(task)\n\n    def complete_task(self, task: str) -> None:\n        self.tasks = [t for t in self.tasks if t != task]\n\n    def remove_task(self, task: str) -> None:\n        self.tasks = [t for t in self.tasks if t != task]\n\n    def handle_request(self, request: Dict[str, str]) -> None:\n        operation = request.get('operation')\n        if operation == 'add_task':\n            self.add_task(request.get('task'))\n        elif"
+}
+````
 
-  ###### TGI-based application:
-
-  - ghcr.io/huggingface/text-generation-inference:2.3.1-rocm (if pulled)
-  - opea/llm-textgen:latest
-  - opea/codegen:latest
-  - opea/codegen-ui:latest
-
-  _After building, ensure the `image:` tags in the main `compose_vllm.yaml` or `compose.yaml` (in the `amd/gpu/rocm` directory) match these built images (e.g., `opea/vllm-rocm:latest`)._
-
-## Validate Service Health
-
-Run these checks after starting the services to ensure they are operational. Focus on the vLLM checks first as it's the default.
-
-### 1. Validate the vLLM/TGI Service
-
-#### If you use vLLM (Default - using `compose_vllm.yaml` and `set_env_vllm.sh`)
-
-- **How Tested:** Send a POST request with a sample prompt to the vLLM endpoint.
-- **CURL Command:**
-
-  ```bash
-  DATA='{"model": "Qwen/Qwen2.5-Coder-7B-Instruct", '\
-  '"messages": [{"role": "user", "content": "Implement a high-level API for a TODO list application. '\
-  'The API takes as input an operation request and updates the TODO list in place. '\
-  'If the request is invalid, raise an exception."}], "max_tokens": 256}'
-
-  curl http://${HOST_IP}:${CODEGEN_VLLM_SERVICE_PORT}/v1/chat/completions \
-    -X POST \
-    -d "$DATA" \
-    -H 'Content-Type: application/json'
-  ```
-
-- **Sample Output:**
-  ```json
-  {
-    "id": "chatcmpl-142f34ef35b64a8db3deedd170fed951",
-    "object": "chat.completion"
-    // ... (rest of output) ...
-  }
-  ```
-- **Expected Result:** A JSON response with a `choices[0].message.content` field containing meaningful generated code.
-
-#### If you use TGI (using `compose.yaml` and `set_env.sh`)
-
-- **How Tested:** Send a POST request with a sample prompt to the TGI endpoint.
-- **CURL Command:**
-
-  ```bash
-  DATA='{"inputs":"Implement a high-level API for a TODO list application. '\
-  # ... (data payload as before) ...
-  '"parameters":{"max_new_tokens":256,"do_sample": true}}'
-
-  curl http://${HOST_IP}:${CODEGEN_TGI_SERVICE_PORT}/generate \
-    -X POST \
-    -d "$DATA" \
-    -H 'Content-Type: application/json'
-  ```
-
-- **Sample Output:**
-  ```json
-  {
-    "generated_text": " The supported operations are \"add_task\", \"complete_task\", and \"remove_task\". # ... (generated code) ..."
-  }
-  ```
-- **Expected Result:** A JSON response with a `generated_text` field containing meaningful generated code.
+If the service response has a meaningful response in the value of the "generated_text" key,
+then we consider the TGI service to be successfully launched
 
 ### 2. Validate the LLM Service
 
-- **Service Name:** `codegen-llm-server`
-- **How Tested:** Send a POST request to the LLM microservice wrapper endpoint.
-- **CURL Command:**
+```bash
+DATA='{"query":"Implement a high-level API for a TODO list application. '\
+'The API takes as input an operation request and updates the TODO list in place. '\
+'If the request is invalid, raise an exception.",'\
+'"max_tokens":256,"top_k":10,"top_p":0.95,"typical_p":0.95,"temperature":0.01,'\
+'"repetition_penalty":1.03,"stream":false}'
 
-  ```bash
-  DATA='{"query":"Implement a high-level API for a TODO list application. '\
-  # ... (data payload as before) ...
-  '"repetition_penalty":1.03,"stream":false}'
+curl http://${HOST_IP}:${CODEGEN_LLM_SERVICE_PORT}/v1/chat/completions \
+  -X POST \
+  -d "$DATA" \
+  -H 'Content-Type: application/json'
+```
 
-  curl http://${HOST_IP}:${CODEGEN_LLM_SERVICE_PORT}/v1/chat/completions \
-    -X POST \
-    -d "$DATA" \
-    -H 'Content-Type: application/json'
-  ```
+Checking the response from the service. The response should be similar to JSON:
 
-- **Sample Output:** (Structure may vary slightly depending on whether vLLM or TGI is backend)
-  ```json
-  {
-    "id": "cmpl-4e89a590b1af46bfb37ce8f12b2996f8" // Example ID
-    // ... (output structure depends on backend, check original validation) ...
+````json
+{
+  "id": "cmpl-4e89a590b1af46bfb37ce8f12b2996f8",
+  "choices": [
+    {
+      "finish_reason": "length",
+      "index": 0,
+      "logprobs": null,
+      "text": " The API should support the following operations:\n\n1. Add a new task to the TODO list.\n2. Remove a task from the TODO list.\n3. Mark a task as completed.\n4. Retrieve the list of all tasks.\n\nThe API should also support the following features:\n\n1. The ability to filter tasks based on their completion status.\n2. The ability to sort tasks based on their priority.\n3. The ability to search for tasks based on their description.\n\nHere is an example of how the API can be used:\n\n```python\ntodo_list = []\napi = TodoListAPI(todo_list)\n\n# Add tasks\napi.add_task(\"Buy groceries\")\napi.add_task(\"Finish homework\")\n\n# Mark a task as completed\napi.mark_task_completed(\"Buy groceries\")\n\n# Retrieve the list of all tasks\nprint(api.get_all_tasks())\n\n# Filter tasks based on completion status\nprint(api.filter_tasks(completed=True))\n\n# Sort tasks based on priority\napi.sort_tasks(priority=\"high\")\n\n# Search for tasks based on description\nprint(api.search_tasks(description=\"homework\"))\n```\n\nIn this example, the `TodoListAPI` class is used to manage the TODO list. The `add_task` method adds a new task to the list, the `mark_task_completed` method",
+      "stop_reason": null,
+      "prompt_logprobs": null
+    }
+  ],
+  "created": 1742270567,
+  "model": "Qwen/Qwen2.5-Coder-7B-Instruct",
+  "object": "text_completion",
+  "system_fingerprint": null,
+  "usage": {
+    "completion_tokens": 256,
+    "prompt_tokens": 37,
+    "total_tokens": 293,
+    "completion_tokens_details": null,
+    "prompt_tokens_details": null
   }
-  ```
-- **Expected Result:** A JSON response containing meaningful generated code within the `choices` array.
+}
+````
 
-### 3. Validate the MegaService (Backend)
+## Accessing the User Interface (UI)
 
-- **Service Name:** `codegen-backend-server`
-- **How Tested:** Send a POST request to the main CodeGen gateway endpoint.
-- **CURL Command:**
+Multiple UI options can be configured via the `compose.yaml`.
 
-  ```bash
-  DATA='{"messages": "Implement a high-level API for a TODO list application. '\
-  # ... (data payload as before) ...
-  'If the request is invalid, raise an exception."}'
+### Svelte UI (Optional)
 
-  curl http://${HOST_IP}:${CODEGEN_BACKEND_SERVICE_PORT}/v1/codegen \
-    -H "Content-Type: application/json" \
-    -d "$DATA"
-  ```
+1.  Modify `compose.yaml`: Comment out the `codegen-gradio-ui-server` service and uncomment/add the `codegen-xeon-ui-server` (Svelte) service definition, ensuring the port mapping is correct (e.g., `"- 5173:5173"`).
+2.  Restart Docker Compose: `docker compose --profile <profile_name> up -d`
+3.  Access: `http://{HOST_IP}:5173` (or the host port you mapped).
 
-- **Sample Output:**
-  ```textmate
-  data: {"id":"cmpl-...", ...}
-  # ... more data chunks ...
-  data: [DONE]
-  ```
-- **Expected Result:** A stream of server-sent events (SSE) containing JSON data with generated code tokens, ending with `data: [DONE]`.
+![Svelte UI Init](../../../../assets/img/codeGen_ui_init.jpg)
 
-### 4. Validate the Frontend (UI)
+### VS Code Extension (Optional)
 
-- **Service Name:** `codegen-ui-server`
-- **How Tested:** Access the UI URL in a web browser and perform a test query.
-- **Steps:** See [How to Open the UI](#how-to-open-the-ui).
-- **Expected Result:** The UI loads correctly, and submitting a prompt results in generated code displayed on the page.
+Users can interact with the backend service using the `Neural Copilot` VS Code extension.
 
-## How to Open the UI
-
-1.  Determine the UI access URL using the `EXTERNAL_HOST_IP` and `CODEGEN_UI_SERVICE_PORT` variables defined in your sourced `set_env*.sh` file (use `set_env_vllm.sh` for the default vLLM deployment). The default URL format is:
-    `http://${EXTERNAL_HOST_IP}:${CODEGEN_UI_SERVICE_PORT}`
-    (e.g., `http://192.168.1.100:5173`)
-
-2.  Open this URL in your web browser.
-
-3.  You should see the CodeGen starting page:
-    ![UI start page](../../../../assets/img/ui-starting-page.png)
-
-4.  Enter a prompt in the input field (e.g., "Write a Python code that returns the current time and date") and press Enter or click the submit button.
-
-5.  Verify that the generated code appears correctly:
-    ![UI result page](../../../../assets/img/ui-result-page.png)
+1.  **Install:** Find and install `Neural Copilot` from the VS Code Marketplace.
+    ![Install Copilot](../../../../assets/img/codegen_copilot.png)
+2.  **Configure:** Set the "Service URL" in the extension settings to your CodeGen backend endpoint: `http://${HOST_IP}:7778/v1/codegen` (use the correct port if changed).
+    ![Configure Endpoint](../../../../assets/img/codegen_endpoint.png)
+3.  **Usage:**
+    - **Inline Suggestion:** Type a comment describing the code you want (e.g., `# Python function to read a file`) and wait for suggestions.
+      ![Code Suggestion](../../../../assets/img/codegen_suggestion.png)
+    - **Chat:** Use the Neural Copilot panel to chat with the AI assistant about code.
+      ![Chat Dialog](../../../../assets/img/codegen_dialog.png)
 
 ## Troubleshooting
 
-_(No specific troubleshooting steps provided in the original content for this file. Add common issues if known.)_
+- **Model Download Issues:** Check `HUGGINGFACEHUB_API_TOKEN`. Ensure internet connectivity or correct proxy settings. Check logs of `tgi-service`/`vllm-service` and `tei-embedding-server`. Gated models need prior Hugging Face access.
+- **Connection Errors:** Verify `HOST_IP` is correct and accessible. Check `docker ps` for port mappings. Ensure `no_proxy` includes `HOST_IP` if using a proxy. Check logs of the service failing to connect (e.g., `codegen-backend-server` logs if it can't reach `codegen-llm-server`).
+- **"Container name is in use"**: Stop existing containers (`docker compose down`) or change `container_name` in `compose.yaml`.
+- **Resource Issues:** CodeGen models can be memory-intensive. Monitor host RAM usage. Increase Docker resources if needed.
 
-- Check container logs (`docker compose -f <file> logs <service_name>`), especially for `codegen-vllm-service` or `codegen-tgi-service`.
-- Ensure `HUGGINGFACEHUB_API_TOKEN` is correct.
-- Verify ROCm drivers and Docker setup for GPU access.
-- Confirm network connectivity and proxy settings.
-- Ensure `HOST_IP` and `EXTERNAL_HOST_IP` are correctly set and accessible.
-- If building locally, ensure build steps completed without error and image tags match compose file.
+### Cleanup the Deployment
 
-## Stopping the Application
-
-### If you use vLLM (Default)
+To stop the containers associated with the deployment, execute the following command:
 
 ```bash
-# Ensure you are in the correct directory
-# cd GenAIExamples/CodeGen/docker_compose/amd/gpu/rocm
-docker compose -f compose_vllm.yaml down
-```
-
-### If you use TGI
-
-```bash
-# Ensure you are in the correct directory
-# cd GenAIExamples/CodeGen/docker_compose/amd/gpu/rocm
 docker compose -f compose.yaml down
 ```
 
+```bash
+[+] Running 0/1
+[+] Running 1/2degen-ui-server  Stopping                                                                                               0.4s
+[+] Running 2/3degen-ui-server       Removed                                                                                          10.5s
+[+] Running 2/3degen-ui-server       Removed                                                                                          10.5s
+[+] Running 3/4degen-ui-server       Removed                                                                                          10.5s
+[+] Running 5/5degen-ui-server       Removed                                                                                          10.5s
+ ✔ Container codegen-ui-server       Removed                                                                                         10.5s
+ ✔ Container codegen-backend-server  Removed                                                                                         10.4s
+ ✔ Container codegen-llm-server      Removed                                                                                         10.4s
+ ✔ Container codegen-tgi-service     Removed                                                                                          8.0s
+ ✔ Network rocm_default              Removed                                                                                          0.6s
+```
+
+### compose.yaml - TGI Deployment
+
+The TGI (Text Generation Inference) deployment and the default deployment differ primarily in their service configurations and specific focus on handling large language models (LLMs). The TGI deployment includes a unique `codegen-tgi-service`, which utilizes the `ghcr.io/huggingface/text-generation-inference:2.4.1-rocm` image and is specifically configured to run on AMD hardware.
+
+| Service Name           | Image Name                                               | AMD Use |
+| ---------------------- | -------------------------------------------------------- | ------- |
+| codegen-backend-server | opea/codegen:latest                                      | no      |
+| codegen-llm-server     | opea/codegen:latest                                      | no      |
+| codegen-tgi-service    | ghcr.io/huggingface/text-generation-inference:2.4.1-rocm | yes     |
+| codegen-ui-server      | opea/codegen-ui:latest                                   | no      |
+
+### compose_vllm.yaml - vLLM Deployment
+
+The vLLM deployment utilizes AMD devices primarily for the `vllm-service`, which handles large language model (LLM) tasks. This service is configured to maximize the use of AMD's capabilities, potentially allocating multiple devices to enhance parallel processing and throughput.
+
+| Service Name           | Image Name             | AMD Use |
+| ---------------------- | ---------------------- | ------- |
+| codegen-backend-server | opea/codegen:latest    | no      |
+| codegen-llm-server     | opea/codegen:latest    | no      |
+| codegen-vllm-service   | opea/vllm-rocm:latest  | yes     |
+| codegen-ui-server      | opea/codegen-ui:latest | no      |
+
+## CodeGen Service Configuration
+
+The table provides a comprehensive overview of the CodeGen services utilized across various deployments as illustrated in the example Docker Compose files. Each row in the table represents a distinct service, detailing its possible images used to enable it and a concise description of its function within the deployment architecture. These services collectively enable functionalities such as data storage and management, text embedding, retrieval, reranking, and large language model processing.
+
+ex.: (From ChatQna)
+| Service Name | Possible Image Names | Optional | Description
+| redis-vector-db | redis/redis-stack:7.2.0-v9 | No | Acts as a Redis database for storing and managing
+
+## Conclusion
+
+In the configuration of the `vllm-service` and the `tgi-service`, two variables play a primary role in determining the service's performance and functionality. The `LLM_MODEL_ID` parameter specifies the particular large language model (LLM) that the service will utilize, effectively determining the capabilities and characteristics of the language processing tasks it can perform. This model identifier ensures that the service is aligned with the specific requirements of the application, whether it involves text generation, comprehension, or other language-related tasks.
+
+However, developers need to be aware of the models that have been tested with the respective service image supporting the `vllm-service` and `tgi-service`. For example, documentation for the OPEA GenAIComps v1.0 release specify the list of [validated LLM models](https://github.com/opea-project/GenAIComps/blob/v1.0/comps/llms/text-generation/README.md#validated-llm-models) for each AMD ROCm enabled service image. Specific models may have stringent requirements on the number of AMD ROCm devices required to support them.
+
+This guide should enable developer to deploy the default configuration or any of the other compose yaml files for different configurations. It also highlights the configurable parameters that can be set before deployment.
+
 ## Next Steps
 
-- Explore the alternative TGI deployment option if needed.
-- Refer to the main [CodeGen README](../../../../README.md) for architecture details and links to other deployment methods (Kubernetes, Xeon).
 - Consult the [OPEA GenAIComps](https://github.com/opea-project/GenAIComps) repository for details on individual microservices.
+- Refer to the main [CodeGen README](../../../../README.md) for links to benchmarking and Kubernetes deployment options.

CodeTrans/docker_compose/amd/gpu/rocm/README.md

@@ -1,8 +1,10 @@
-# Deploy CodeTrans on AMD GPU (ROCm)
+# Deploying CodeTrans on AMD ROCm GPU
 
-This document outlines the single node deployment process for a CodeTrans application utilizing the [GenAIComps](https://github.com/opea-project/GenAIComps.git) microservices on AMD GPU (ROCm) server. The steps include pulling Docker images, container deployment via Docker Compose, and service execution using microservices `llm`.
+This document outlines the single node deployment process for a CodeTrans application utilizing the [GenAIComps](https://github.com/opea-project/GenAIComps.git) microservices on Intel Xeon server and AMD GPU. The steps include pulling Docker images, container deployment via Docker Compose, and service execution using microservices `llm`.
 
-# Table of Contents
+Note: The default LLM is `Qwen/Qwen2.5-Coder-7B-Instruct`. Before deploying the application, please make sure either you've requested and been granted the access to it on [Huggingface](https://huggingface.co/Qwen/Qwen2.5-Coder-7B-Instruct) or you've downloaded the model locally from [ModelScope](https://www.modelscope.cn/models).
+
+## Table of Contents
 
 1. [CodeTrans Quick Start Deployment](#codetrans-quick-start-deployment)
 2. [CodeTrans Docker Compose Files](#codetrans-docker-compose-files)
@@ -11,7 +13,7 @@ This document outlines the single node deployment process for a CodeTrans applic
 
 ## CodeTrans Quick Start Deployment
 
-This section describes how to quickly deploy and test the CodeTrans service manually on an AMD GPU (ROCm) processor. The basic steps are:
+This section describes how to quickly deploy and test the CodeTrans service manually on an AMD ROCm GPU. The basic steps are:
 
 1. [Access the Code](#access-the-code)
 2. [Configure the Deployment Environment](#configure-the-deployment-environment)
@@ -22,7 +24,7 @@ This section describes how to quickly deploy and test the CodeTrans service manu
 
 ### Access the Code
 
-Clone the GenAIExample repository and access the CodeTrans AMD GPU (ROCm) platform Docker Compose files and supporting scripts:
+Clone the GenAIExample repository and access the CodeTrans AMD ROCm GPU platform Docker Compose files and supporting scripts:
 
 ```bash
 git clone https://github.com/opea-project/GenAIExamples.git
@@ -37,29 +39,84 @@ git checkout v1.2
 
 ### Configure the Deployment Environment
 
-To set up environment variables for deploying CodeTrans services, set up some parameters specific to the deployment environment and source the `set_env.sh` script in this directory:
+To set up environment variables for deploying CodeTrans services, set up some parameters specific to the deployment environment and source the `set_env_*.sh` script in this directory:
+
+- if used vLLM - set_env_vllm.sh
+- if used TGI - set_env.sh
+
+Set the values of the variables:
+
+- **HOST_IP, HOST_IP_EXTERNAL** - These variables are used to configure the name/address of the service in the operating system environment for the application services to interact with each other and with the outside world.
+
+  If your server uses only an internal address and is not accessible from the Internet, then the values for these two variables will be the same and the value will be equal to the server's internal name/address.
+
+  If your server uses only an external, Internet-accessible address, then the values for these two variables will be the same and the value will be equal to the server's external name/address.
+
+  If your server is located on an internal network, has an internal address, but is accessible from the Internet via a proxy/firewall/load balancer, then the HOST_IP variable will have a value equal to the internal name/address of the server, and the EXTERNAL_HOST_IP variable will have a value equal to the external name/address of the proxy/firewall/load balancer behind which the server is located.
+
+  We set these values in the file set_env\*\*\*\*.sh
+
+- **Variables with names like "**\*\*\*\*\*\*\_PORT"\*\* - These variables set the IP port numbers for establishing network connections to the application services.
+  The values shown in the file set_env.sh or set_env_vllm they are the values used for the development and testing of the application, as well as configured for the environment in which the development is performed. These values must be configured in accordance with the rules of network access to your environment's server, and must not overlap with the IP ports of other applications that are already in use.
+
+Setting variables in the operating system environment:
 
 ```bash
-export host_ip="External_Public_IP"           # ip address of the node
 export HUGGINGFACEHUB_API_TOKEN="Your_HuggingFace_API_Token"
-export http_proxy="Your_HTTP_Proxy"           # http proxy if any
-export https_proxy="Your_HTTPs_Proxy"         # https proxy if any
-export no_proxy=localhost,127.0.0.1,$host_ip  # additional no proxies if needed
-export NGINX_PORT=${your_nginx_port}          # your usable port for nginx, 80 for example
-source ./set_env.sh
+source ./set_env_*.sh # replace the script name with the appropriate one
 ```
 
 Consult the section on [CodeTrans Service configuration](#codetrans-configuration) for information on how service specific configuration parameters affect deployments.
 
 ### Deploy the Services Using Docker Compose
 
-To deploy the CodeTrans services, execute the `docker compose up` command with the appropriate arguments. For a default deployment, execute the command below. It uses the 'compose.yaml' file.
+To deploy the CodeTrans services, execute the `docker compose up` command with the appropriate arguments. For a default deployment with TGI, execute the command below. It uses the 'compose.yaml' file.
 
 ```bash
 cd docker_compose/amd/gpu/rocm
+# if used TGI
 docker compose -f compose.yaml up -d
+# if used vLLM
+# docker compose -f compose_vllm.yaml up -d
 ```
 
+To enable GPU support for AMD GPUs, the following configuration is added to the Docker Compose file:
+
+- compose_vllm.yaml - for vLLM-based application
+- compose.yaml - for TGI-based
+
+```yaml
+shm_size: 1g
+devices:
+  - /dev/kfd:/dev/kfd
+  - /dev/dri:/dev/dri
+cap_add:
+  - SYS_PTRACE
+group_add:
+  - video
+security_opt:
+  - seccomp:unconfined
+```
+
+This configuration forwards all available GPUs to the container. To use a specific GPU, specify its `cardN` and `renderN` device IDs. For example:
+
+```yaml
+shm_size: 1g
+devices:
+  - /dev/kfd:/dev/kfd
+  - /dev/dri/card0:/dev/dri/card0
+  - /dev/dri/render128:/dev/dri/render128
+cap_add:
+  - SYS_PTRACE
+group_add:
+  - video
+security_opt:
+  - seccomp:unconfined
+```
+
+**How to Identify GPU Device IDs:**
+Use AMD GPU driver utilities to determine the correct `cardN` and `renderN` IDs for your GPU.
+
 > **Note**: developers should build docker image from source when:
 >
 > - Developing off the git main branch (as the container's ports in the repo may be different > from the published docker image).
@@ -71,9 +128,11 @@ Please refer to the table below to build different microservices from source:
 | Microservice | Deployment Guide                                                                                               |
 | ------------ | -------------------------------------------------------------------------------------------------------------- |
 | vLLM         | [vLLM build guide](https://github.com/opea-project/GenAIComps/tree/main/comps/third_parties/vllm#build-docker) |
+| TGI          | [TGI project](https://github.com/huggingface/text-generation-inference.git)                                    |
 | LLM          | [LLM build guide](https://github.com/opea-project/GenAIComps/tree/main/comps/llms)                             |
-| MegaService  | [MegaService build guide](../../../../README_miscellaneous.md#build-megaservice-docker-image)                  |
-| UI           | [Basic UI build guide](../../../../README_miscellaneous.md#build-ui-docker-image)                              |
+| MegaService  | [MegaService guide](../../../../README.md)                                                                     |
+| UI           | [UI guide](../../../../ui/svelte/README.md)                                                                    |
+| Nginx        | [Nginx guide](https://github.com/opea-project/GenAIComps/tree/main/comps/third_parties/nginx)                  |
 
 ### Check the Deployment Status
 
@@ -83,15 +142,26 @@ After running docker compose, check if all the containers launched via docker co
 docker ps -a
 ```
 
-For the default deployment, the following 5 containers should have started:
+For the default deployment with TGI, the following 9 containers should have started:
 
 ```
-CONTAINER ID   IMAGE                                                   COMMAND                  CREATED        STATUS        PORTS                                                                                  NAMES
-b3e1388fa2ca   opea/nginx:${RELEASE_VERSION}                           "/usr/local/bin/star…"   32 hours ago   Up 2 hours   0.0.0.0:80->80/tcp, :::80->80/tcp                                                      codetrans-nginx-server
-3b5fa9a722da   opea/codetrans-ui:${RELEASE_VERSION}                    "docker-entrypoint.s…"   32 hours ago   Up 2 hours   0.0.0.0:5173->5173/tcp, :::5173->5173/tcp                                              codetrans-ui-server
-d3b37f3d1faa   opea/codetrans:${RELEASE_VERSION}                       "python codetrans.py"    32 hours ago   Up 2 hours   0.0.0.0:7777->7777/tcp, :::7777->7777/tcp                                              codetrans-backend-server
-24cae0db1a70   opea/llm-textgen:${RELEASE_VERSION}                     "bash entrypoint.sh"     32 hours ago   Up 2 hours   0.0.0.0:9000->9000/tcp, :::9000->9000/tcp                                              codetrans-llm-server
-b98fa07a4f5c   opea/vllm:${RELEASE_VERSION}                            "python3 -m vllm.ent…"   32 hours ago   Up 2 hours   0.0.0.0:9009->80/tcp, :::9009->80/tcp                                                  codetrans-tgi-service
+CONTAINER ID   IMAGE                                                   COMMAND                  CREATED          STATUS                    PORTS                                                                                      NAMES
+eaf24161aca8   opea/nginx:latest                                       "/docker-entrypoint.…"   37 seconds ago   Up 5 seconds              0.0.0.0:18104->80/tcp, [::]:18104->80/tcp                                                  chaqna-nginx-server
+2fce48a4c0f4   opea/codetrans-ui:latest                                  "docker-entrypoint.s…"   37 seconds ago   Up 5 seconds              0.0.0.0:18101->5173/tcp, [::]:18101->5173/tcp                                              codetrans-ui-server
+613c384979f4   opea/codetrans:latest                                     "bash entrypoint.sh"     37 seconds ago   Up 5 seconds              0.0.0.0:18102->8888/tcp, [::]:18102->8888/tcp                                              codetrans-backend-server
+e0ef1ea67640   opea/llm-textgen:latest                                  "bash entrypoint.sh"     37 seconds ago   Up 36 seconds             0.0.0.0:18011->9000/tcp, [::]:18011->9000/tcp                                              codetrans-llm-server
+342f01bfdbb2   ghcr.io/huggingface/text-generation-inference:2.3.1-rocm"python3 /workspace/…"   37 seconds ago   Up 36 seconds             0.0.0.0:18008->8011/tcp, [::]:18008->8011/tcp                                              codetrans-tgi-service
+```
+
+if used vLLM:
+
+```
+CONTAINER ID   IMAGE                                                   COMMAND                  CREATED          STATUS                    PORTS                                                                                      NAMES
+eaf24161aca8   opea/nginx:latest                                       "/docker-entrypoint.…"   37 seconds ago   Up 5 seconds              0.0.0.0:18104->80/tcp, [::]:18104->80/tcp                                                  chaqna-nginx-server
+2fce48a4c0f4   opea/codetrans-ui:latest                                  "docker-entrypoint.s…"   37 seconds ago   Up 5 seconds              0.0.0.0:18101->5173/tcp, [::]:18101->5173/tcp                                              codetrans-ui-server
+613c384979f4   opea/codetrans:latest                                     "bash entrypoint.sh"     37 seconds ago   Up 5 seconds              0.0.0.0:18102->8888/tcp, [::]:18102->8888/tcp                                              codetrans-backend-server
+e0ef1ea67640   opea/llm-textgen:latest                                  "bash entrypoint.sh"     37 seconds ago   Up 36 seconds             0.0.0.0:18011->9000/tcp, [::]:18011->9000/tcp                                              codetrans-llm-server
+342f01bfdbb2   opea/vllm-rocm:latest                                   "python3 /workspace/…"   37 seconds ago   Up 36 seconds             0.0.0.0:18008->8011/tcp, [::]:18008->8011/tcp                                              codetrans-vllm-service
 ```
 
 If any issues are encountered during deployment, refer to the [Troubleshooting](../../../../README_miscellaneous.md#troubleshooting) section.
@@ -109,65 +179,68 @@ curl http://${HOST_IP}:${CODETRANS_BACKEND_SERVICE_PORT}/v1/codetrans \
   -d "$DATA"
 ```
 
-**Note** : Access the CodeTrans UI by web browser through this URL: `http://${host_ip}:80`. Please confirm the `80` port is opened in the firewall. To validate each microservie used in the pipeline refer to the [Validate Microservices](#validate-microservices) section.
+**Note** : Access the CodeTrans UI by web browser through this URL: `http://${HOST_IP_EXTERNAL}:${CODETRANS_NGINX_PORT}`
 
 ### Cleanup the Deployment
 
 To stop the containers associated with the deployment, execute the following command:
 
 ```bash
+# if used TGI
 docker compose -f compose.yaml down
+# if used vLLM
+# docker compose -f compose_vllm.yaml down
 ```
 
 ## CodeTrans Docker Compose Files
 
-In the context of deploying a CodeTrans pipeline on an AMD GPU (ROCm) platform, we can pick and choose different large language model serving frameworks. The table below outlines the various configurations that are available as part of the application. These configurations can be used as templates and can be extended to different components available in [GenAIComps](https://github.com/opea-project/GenAIComps.git).
+In the context of deploying an ChatQnA pipeline on an Intel® Xeon® platform, we can pick and choose different large language model serving frameworks, or single English TTS/multi-language TTS component. The table below outlines the various configurations that are available as part of the application. These configurations can be used as templates and can be extended to different components available in [GenAIComps](https://github.com/opea-project/GenAIComps.git).
 
-| File                                     | Description                                                                                |
-| ---------------------------------------- | ------------------------------------------------------------------------------------------ |
-| [compose.yaml](./compose.yaml)           | Default compose file using TGI as serving framework                                        |
-| [compose_vllm.yaml](./compose_vllm.yaml) | The LLM serving framework is vLLM. All other configurations remain the same as the default |
+| File                                     | Description                                                                           |
+| ---------------------------------------- | ------------------------------------------------------------------------------------- |
+| [compose.yaml](./compose.yaml)           | The LLM serving framework is TGI. Default compose file using TGI as serving framework |
+| [compose_vllm.yaml](./compose_vllm.yaml) | The LLM serving framework is vLLM. Compose file using vllm as serving framework       |
 
-## Validate Microservices
+## Validate MicroServices
 
-1. LLM backend Service
+LLM backend Service
 
-   In the first startup, this service will take more time to download, load and warm up the model. After it's finished, the service will be ready.
+In the first startup, this service will take more time to download, load and warm up the model. After it's finished, the service will be ready.
 
-   Try the command below to check whether the LLM serving is ready.
+Try the command below to check whether the LLM serving is ready.
 
-   ```bash
-   # vLLM service
-   docker logs codetrans-vllm-service 2>&1 | grep complete
-   # If the service is ready, you will get the response like below.
-   INFO:     Application startup complete.
-   ```
+```bash
+# vLLM service
+docker logs codetrans-vllm-service 2>&1 | grep complete
+# If the service is ready, you will get the response like below.
+INFO:     Application startup complete.
+```
 
-   ```bash
-   # TGI service
-   docker logs codetrans-tgi-service | grep Connected
-   # If the service is ready, you will get the response like below.
-   2024-09-03T02:47:53.402023Z  INFO text_generation_router::server: router/src/server.rs:2311: Connected
-   ```
+```bash
+# TGI service
+docker logs codetrans-tgi-service | grep Connected
+# If the service is ready, you will get the response like below.
+2024-09-03T02:47:53.402023Z  INFO text_generation_router::server: router/src/server.rs:2311: Connected
+```
 
-   Then try the `cURL` command below to validate services.
+Then try the `cURL` command below to validate services.
 
-   ```bash
-   # either vLLM or TGI service
-   # for vllm service
-   export port=${CODETRANS_VLLM_SERVICE_PORT}
-   # for tgi service
-   export port=${CODETRANS_TGI_SERVICE_PORT}
-   curl http://${HOST_IP}:${port}/v1/chat/completions \
-     -X POST \
-     -d '{"inputs":"    ### System: Please translate the following Golang codes into  Python codes.    ### Original codes:    '\'''\'''\''Golang    \npackage main\n\nimport \"fmt\"\nfunc main() {\n    fmt.Println(\"Hello, World!\");\n    '\'''\'''\''    ### Translated codes:","parameters":{"max_new_tokens":17, "do_sample": true}}' \
-     -H 'Content-Type: application/json'
-   ```
+```bash
+# either vLLM or TGI service
+# for vllm service
+export port=${CODETRANS_VLLM_SERVICE_PORT}
+# for tgi service
+export port=${CODETRANS_TGI_SERVICE_PORT}
+curl http://${HOST_IP}:${port}/v1/chat/completions \
+  -X POST \
+  -d '{"inputs":"    ### System: Please translate the following Golang codes into  Python codes.    ### Original codes:    '\'''\'''\''Golang    \npackage main\n\nimport \"fmt\"\nfunc main() {\n    fmt.Println(\"Hello, World!\");\n    '\'''\'''\''    ### Translated codes:","parameters":{"max_new_tokens":17, "do_sample": true}}' \
+  -H 'Content-Type: application/json'
+```
 
 2. LLM Microservice
 
    ```bash
-   curl http://${HOST_IP}:${CODETRANS_LLM_SERVICE_PORT}/v1/chat/completions\
+   curl http://${HOST_IP}:${CODETRANS_LLM_SERVICE_PORT}/v1/chat/completions \
      -X POST \
      -d '{"query":"    ### System: Please translate the following Golang codes into  Python codes.    ### Original codes:    '\'''\'''\''Golang    \npackage main\n\nimport \"fmt\"\nfunc main() {\n    fmt.Println(\"Hello, World!\");\n    '\'''\'''\''    ### Translated codes:"}' \
      -H 'Content-Type: application/json'

CodeTrans/tests/test_compose_on_gaudi.sh

@@ -43,9 +43,6 @@ function build_docker_images() {
 
 function start_services() {
     cd $WORKPATH/docker_compose/intel/hpu/gaudi
-
-    export http_proxy=${http_proxy}
-    export https_proxy=${http_proxy}
     export LLM_MODEL_ID="mistralai/Mistral-7B-Instruct-v0.3"
     export LLM_ENDPOINT="http://${ip_address}:8008"
     export LLM_COMPONENT_NAME="OpeaTextGenService"

CodeTrans/tests/test_compose_on_rocm.sh

@@ -42,8 +42,6 @@ function build_docker_images() {
 
 function start_services() {
     cd $WORKPATH/docker_compose/amd/gpu/rocm/
-    export http_proxy=${http_proxy}
-    export https_proxy=${http_proxy}
     export CODETRANS_TGI_SERVICE_PORT=8008
     export CODETRANS_LLM_SERVICE_PORT=9000
     export CODETRANS_LLM_MODEL_ID="Qwen/Qwen2.5-Coder-7B-Instruct"

CodeTrans/tests/test_compose_on_xeon.sh

@@ -45,8 +45,6 @@ function build_docker_images() {
 
 function start_services() {
     cd $WORKPATH/docker_compose/intel/cpu/xeon/
-    export http_proxy=${http_proxy}
-    export https_proxy=${http_proxy}
     export LLM_MODEL_ID="mistralai/Mistral-7B-Instruct-v0.3"
     export LLM_ENDPOINT="http://${ip_address}:8008"
     export LLM_COMPONENT_NAME="OpeaTextGenService"

CodeTrans/tests/test_compose_tgi_on_gaudi.sh

@@ -41,8 +41,6 @@ function build_docker_images() {
 
 function start_services() {
     cd $WORKPATH/docker_compose/intel/hpu/gaudi/
-    export http_proxy=${http_proxy}
-    export https_proxy=${http_proxy}
     export LLM_MODEL_ID="mistralai/Mistral-7B-Instruct-v0.3"
     export LLM_ENDPOINT="http://${ip_address}:8008"
     export LLM_COMPONENT_NAME="OpeaTextGenService"

CodeTrans/tests/test_compose_tgi_on_xeon.sh

@@ -41,8 +41,6 @@ function build_docker_images() {
 
 function start_services() {
     cd $WORKPATH/docker_compose/intel/cpu/xeon/
-    export http_proxy=${http_proxy}
-    export https_proxy=${http_proxy}
     export LLM_MODEL_ID="mistralai/Mistral-7B-Instruct-v0.3"
     export LLM_ENDPOINT="http://${ip_address}:8008"
     export LLM_COMPONENT_NAME="OpeaTextGenService"

CodeTrans/tests/test_compose_vllm_on_rocm.sh

@@ -40,8 +40,6 @@ function build_docker_images() {
 
 function start_services() {
     cd $WORKPATH/docker_compose/amd/gpu/rocm/
-    export http_proxy=${http_proxy}
-    export https_proxy=${http_proxy}
     export HOST_IP=${ip_address}
     export CODETRANS_VLLM_SERVICE_PORT=8008
     export CODETRANS_LLM_SERVICE_PORT=9000

DBQnA/README.md

@@ -50,7 +50,7 @@ flowchart LR
 
 ### 💬 SQL Query Generation
 
-The key feature of DBQnA app is that it converts a user's natural language query into an SQL query and automatically executes the generated SQL query on the database to return the relevant results. BAsically ask questions to database, receive corresponding SQL query and real-time query execution output, all without needing any SQL knowledge.
+The key feature of DBQnA app is that it converts a user's natural language query into an SQL query and automatically executes the generated SQL query on the database to return the relevant results. Basically ask questions to database, receive corresponding SQL query and real-time query execution output, all without needing any SQL knowledge.
 
 ---
 

DocSum/benchmark_docsum.yaml

@@ -3,7 +3,7 @@
 
 deploy:
   device: gaudi
-  version: 1.2.0
+  version: 1.3.0
   modelUseHostPath: /mnt/models
   HUGGINGFACEHUB_API_TOKEN: "" # mandatory
   node: [1]
@@ -20,14 +20,10 @@ deploy:
         memory_capacity: "8000Mi"
       replicaCount: [1]
 
-    teirerank:
-      enabled: False
-
     llm:
       engine: vllm  # or tgi
       model_id: "meta-llama/Llama-3.2-3B-Instruct" # mandatory
-      replicaCount:
-        without_teirerank: [1]   # When teirerank.enabled is False
+      replicaCount: [1]
       resources:
         enabled: False
         cards_per_instance: 1
@@ -78,7 +74,7 @@ benchmark:
 
   # workload, all of the test cases will run for benchmark
   bench_target: ["docsumfixed"] # specify the bench_target for benchmark
-  dataset: "/home/sdp/upload.txt"  # specify the absolute path to the dataset file
+  dataset: "/home/sdp/pubmed_10.txt"  # specify the absolute path to the dataset file
   summary_type: "stuff"
   stream: True
 

DocSum/docker_compose/amd/gpu/rocm/README.md

@@ -23,17 +23,17 @@ This section describes how to quickly deploy and test the DocSum service manuall
 
 ### Access the Code
 
-Clone the GenAIExample repository and access the ChatQnA AMD GPU platform Docker Compose files and supporting scripts:
+Clone the GenAIExample repository and access the DocSum AMD GPU platform Docker Compose files and supporting scripts:
 
-```
+```bash
 git clone https://github.com/opea-project/GenAIExamples.git
 cd GenAIExamples/DocSum/docker_compose/amd/gpu/rocm
 ```
 
-Checkout a released version, such as v1.2:
+Checkout a released version, such as v1.3:
 
 ```
-git checkout v1.2
+git checkout v1.3
 ```
 
 ### Generate a HuggingFace Access Token
@@ -42,33 +42,96 @@ Some HuggingFace resources, such as some models, are only accessible if you have
 
 ### Configure the Deployment Environment
 
-To set up environment variables for deploying DocSum services, source the _set_env.sh_ script in this directory:
+To set up environment variables for deploying DocSum services, set up some parameters specific to the deployment environment and source the `set_env_*.sh` script in this directory:
 
-```
-source ./set_env.sh
+- if used vLLM - set_env_vllm.sh
+- if used TGI - set_env.sh
+
+Set the values of the variables:
+
+- **HOST_IP, HOST_IP_EXTERNAL** - These variables are used to configure the name/address of the service in the operating system environment for the application services to interact with each other and with the outside world.
+
+  If your server uses only an internal address and is not accessible from the Internet, then the values for these two variables will be the same and the value will be equal to the server's internal name/address.
+
+  If your server uses only an external, Internet-accessible address, then the values for these two variables will be the same and the value will be equal to the server's external name/address.
+
+  If your server is located on an internal network, has an internal address, but is accessible from the Internet via a proxy/firewall/load balancer, then the HOST_IP variable will have a value equal to the internal name/address of the server, and the EXTERNAL_HOST_IP variable will have a value equal to the external name/address of the proxy/firewall/load balancer behind which the server is located.
+
+  We set these values in the file set_env\*\*\*\*.sh
+
+- **Variables with names like "**\*\*\*\*\*\*\_PORT"\*\* - These variables set the IP port numbers for establishing network connections to the application services.
+  The values shown in the file set_env.sh or set_env_vllm.sh they are the values used for the development and testing of the application, as well as configured for the environment in which the development is performed. These values must be configured in accordance with the rules of network access to your environment's server, and must not overlap with the IP ports of other applications that are already in use.
+
+Setting variables in the operating system environment:
+
+```bash
+export HUGGINGFACEHUB_API_TOKEN="Your_HuggingFace_API_Token"
+source ./set_env_*.sh # replace the script name with the appropriate one
 ```
 
-The _set_env.sh_ script will prompt for required and optional environment variables used to configure the DocSum services. If a value is not entered, the script will use a default value for the same. It will also generate a _.env_ file defining the desired configuration. Consult the section on [DocSum Service configuration](#docsum-service-configuration) for information on how service specific configuration parameters affect deployments.
+Consult the section on [DocSum Service configuration](#docsum-configuration) for information on how service specific configuration parameters affect deployments.
 
 ### Deploy the Services Using Docker Compose
 
-To deploy the DocSum services, execute the `docker compose up` command with the appropriate arguments. For a default deployment, execute:
+To deploy the DocSum services, execute the `docker compose up` command with the appropriate arguments. For a default deployment with TGI, execute the command below. It uses the 'compose.yaml' file.
 
 ```bash
-docker compose up -d
+cd docker_compose/amd/gpu/rocm
+# if used TGI
+docker compose -f compose.yaml up -d
+# if used vLLM
+# docker compose -f compose_vllm.yaml up -d
 ```
 
-**Note**: developers should build docker image from source when:
+To enable GPU support for AMD GPUs, the following configuration is added to the Docker Compose file:
 
-- Developing off the git main branch (as the container's ports in the repo may be different from the published docker image).
-- Unable to download the docker image.
-- Use a specific version of Docker image.
+- compose_vllm.yaml - for vLLM-based application
+- compose.yaml - for TGI-based
+
+```yaml
+shm_size: 1g
+devices:
+  - /dev/kfd:/dev/kfd
+  - /dev/dri:/dev/dri
+cap_add:
+  - SYS_PTRACE
+group_add:
+  - video
+security_opt:
+  - seccomp:unconfined
+```
+
+This configuration forwards all available GPUs to the container. To use a specific GPU, specify its `cardN` and `renderN` device IDs. For example:
+
+```yaml
+shm_size: 1g
+devices:
+  - /dev/kfd:/dev/kfd
+  - /dev/dri/card0:/dev/dri/card0
+  - /dev/dri/render128:/dev/dri/render128
+cap_add:
+  - SYS_PTRACE
+group_add:
+  - video
+security_opt:
+  - seccomp:unconfined
+```
+
+**How to Identify GPU Device IDs:**
+Use AMD GPU driver utilities to determine the correct `cardN` and `renderN` IDs for your GPU.
+
+> **Note**: developers should build docker image from source when:
+>
+> - Developing off the git main branch (as the container's ports in the repo may be different > from the published docker image).
+> - Unable to download the docker image.
+> - Use a specific version of Docker image.
 
 Please refer to the table below to build different microservices from source:
 
 | Microservice | Deployment Guide                                                                                                                      |
 | ------------ | ------------------------------------------------------------------------------------------------------------------------------------- |
 | whisper      | [whisper build guide](https://github.com/opea-project/GenAIComps/tree/main/comps/third_parties/whisper/src)                           |
+| TGI          | [TGI project](https://github.com/huggingface/text-generation-inference.git)                                                           |
 | vLLM         | [vLLM build guide](https://github.com/opea-project/GenAIComps/tree/main/comps/third_parties/vllm#build-docker)                        |
 | llm-docsum   | [LLM-DocSum build guide](https://github.com/opea-project/GenAIComps/tree/main/comps/llms/src/doc-summarization#12-build-docker-image) |
 | MegaService  | [MegaService build guide](../../../../README_miscellaneous.md#build-megaservice-docker-image)                                         |
@@ -84,6 +147,8 @@ docker ps -a
 
 For the default deployment, the following 5 containers should have started:
 
+If used TGI:
+
 ```
 CONTAINER ID   IMAGE                                                         COMMAND                  CREATED         STATUS                   PORTS                                       NAMES
 748f577b3c78   opea/whisper:latest                                           "python whisper_s…"      5 minutes ago   Up About a minute        0.0.0.0:7066->7066/tcp, :::7066->7066/tcp   whisper-service
@@ -93,24 +158,39 @@ fds3dd5b9fd8   opea/docsum:latest                                            "py
 78964d0c1hg5   ghcr.io/huggingface/text-generation-inference:2.4.1-rocm      "/tgi-entrypoint.sh"     5 minutes ago   Up 5 minutes (healthy)   0.0.0.0:8008->80/tcp, [::]:8008->80/tcp     docsum-tgi-service
 ```
 
+If used vLLM:
+
+```
+CONTAINER ID   IMAGE                                                         COMMAND                  CREATED         STATUS                   PORTS                                       NAMES
+748f577b3c78   opea/whisper:latest                                           "python whisper_s…"      5 minutes ago   Up About a minute        0.0.0.0:7066->7066/tcp, :::7066->7066/tcp   whisper-service
+4eq8b7034fd9   opea/docsum-gradio-ui:latest                                  "docker-entrypoint.s…"   5 minutes ago   Up About a minute        0.0.0.0:5173->5173/tcp, :::5173->5173/tcp   docsum-ui-server
+fds3dd5b9fd8   opea/docsum:latest                                            "python docsum.py"       5 minutes ago   Up About a minute        0.0.0.0:8888->8888/tcp, :::8888->8888/tcp   docsum-backend-server
+78fsd6fabfs7   opea/llm-docsum:latest                                        "bash entrypoint.sh"     5 minutes ago   Up About a minute        0.0.0.0:9000->9000/tcp, :::9000->9000/tcp   docsum-llm-server
+78964d0c1hg5   opea/vllm-rocm:latest                                         "python3 /workspace/…"   5 minutes ago   Up 5 minutes (healthy)   0.0.0.0:8008->80/tcp, [::]:8008->80/tcp     docsum-vllm-service
+```
+
 ### Test the Pipeline
 
 Once the DocSum services are running, test the pipeline using the following command:
 
 ```bash
-curl -X POST http://${host_ip}:8888/v1/docsum \
+curl -X POST http://${HOST_IP}:${DOCSUM_BACKEND_SERVER_PORT}/v1/docsum \
         -H "Content-Type: application/json" \
         -d '{"type": "text", "messages": "Text Embeddings Inference (TEI) is a toolkit for deploying and serving open source text embeddings and sequence classification models. TEI enables high-performance extraction for the most popular models, including FlagEmbedding, Ember, GTE and E5."}'
 ```
 
-**Note** The value of _host_ip_ was set using the _set_env.sh_ script and can be found in the _.env_ file.
+**Note** The value of _HOST_IP_ was set using the _set_env.sh_ script and can be found in the _.env_ file.
 
 ### Cleanup the Deployment
 
 To stop the containers associated with the deployment, execute the following command:
 
-```
+```bash
+# if used TGI
 docker compose -f compose.yaml down
+# if used vLLM
+# docker compose -f compose_vllm.yaml down
+
 ```
 
 All the DocSum containers will be stopped and then removed on completion of the "down" command.
@@ -132,7 +212,7 @@ There are also some customized usage.
 
 ```bash
 # form input. Use English mode (default).
-curl http://${host_ip}:8888/v1/docsum \
+curl http://${HOST_IP}:${DOCSUM_BACKEND_SERVER_PORT}/v1/docsum \
       -H "Content-Type: multipart/form-data" \
       -F "type=text" \
       -F "messages=Text Embeddings Inference (TEI) is a toolkit for deploying and serving open source text embeddings and sequence classification models. TEI enables high-performance extraction for the most popular models, including FlagEmbedding, Ember, GTE and E5." \
@@ -141,7 +221,7 @@ curl http://${host_ip}:8888/v1/docsum \
       -F "stream=True"
 
 # Use Chinese mode.
-curl http://${host_ip}:8888/v1/docsum \
+curl http://${HOST_IP}:${DOCSUM_BACKEND_SERVER_PORT}/v1/docsum \
       -H "Content-Type: multipart/form-data" \
       -F "type=text" \
       -F "messages=2024年9月26日，北京——今日，英特尔正式发布英特尔® 至强® 6性能核处理器（代号Granite Rapids），为AI、数据分析、科学计算等计算密集型业务提供卓越性能。" \
@@ -150,7 +230,7 @@ curl http://${host_ip}:8888/v1/docsum \
       -F "stream=True"
 
 # Upload file
-curl http://${host_ip}:8888/v1/docsum \
+curl http://${HOST_IP}:${DOCSUM_BACKEND_SERVER_PORT}/v1/docsum \
    -H "Content-Type: multipart/form-data" \
    -F "type=text" \
    -F "messages=" \
@@ -166,11 +246,11 @@ curl http://${host_ip}:8888/v1/docsum \
 Audio:
 
 ```bash
-curl -X POST http://${host_ip}:8888/v1/docsum \
+curl -X POST http://${HOST_IP}:${DOCSUM_BACKEND_SERVER_PORT}/v1/docsum \
    -H "Content-Type: application/json" \
    -d '{"type": "audio", "messages": "UklGRigAAABXQVZFZm10IBIAAAABAAEARKwAAIhYAQACABAAAABkYXRhAgAAAAEA"}'
 
-curl http://${host_ip}:8888/v1/docsum \
+curl http://${HOST_IP}:${DOCSUM_BACKEND_SERVER_PORT}/v1/docsum \
    -H "Content-Type: multipart/form-data" \
    -F "type=audio" \
    -F "messages=UklGRigAAABXQVZFZm10IBIAAAABAAEARKwAAIhYAQACABAAAABkYXRhAgAAAAEA" \
@@ -182,11 +262,11 @@ curl http://${host_ip}:8888/v1/docsum \
 Video:
 
 ```bash
-curl -X POST http://${host_ip}:8888/v1/docsum \
+curl -X POST http://${HOST_IP}:${DOCSUM_BACKEND_SERVER_PORT}/v1/docsum \
    -H "Content-Type: application/json" \
    -d '{"type": "video", "messages": "convert your video to base64 data type"}'
 
-curl http://${host_ip}:8888/v1/docsum \
+curl http://${HOST_IP}:${DOCSUM_BACKEND_SERVER_PORT}/v1/docsum \
    -H "Content-Type: multipart/form-data" \
    -F "type=video" \
    -F "messages=convert your video to base64 data type" \
@@ -208,7 +288,7 @@ If you want to deal with long context, can set following parameters and select s
 "summary_type" is set to be "auto" by default, in this mode we will check input token length, if it exceed `MAX_INPUT_TOKENS`, `summary_type` will automatically be set to `refine` mode, otherwise will be set to `stuff` mode.
 
 ```bash
-curl http://${host_ip}:8888/v1/docsum \
+curl http://${HOST_IP}:${DOCSUM_BACKEND_SERVER_PORT}/v1/docsum \
    -H "Content-Type: multipart/form-data" \
    -F "type=text" \
    -F "messages=" \
@@ -223,7 +303,7 @@ curl http://${host_ip}:8888/v1/docsum \
 In this mode LLM generate summary based on complete input text. In this case please carefully set `MAX_INPUT_TOKENS` and `MAX_TOTAL_TOKENS` according to your model and device memory, otherwise it may exceed LLM context limit and raise error when meet long context.
 
 ```bash
-curl http://${host_ip}:8888/v1/docsum \
+curl http://${HOST_IP}:${DOCSUM_BACKEND_SERVER_PORT}/v1/docsum \
    -H "Content-Type: multipart/form-data" \
    -F "type=text" \
    -F "messages=" \
@@ -238,7 +318,7 @@ curl http://${host_ip}:8888/v1/docsum \
 Truncate mode will truncate the input text and keep only the first chunk, whose length is equal to `min(MAX_TOTAL_TOKENS - input.max_tokens - 50, MAX_INPUT_TOKENS)`
 
 ```bash
-curl http://${host_ip}:8888/v1/docsum \
+curl http://${HOST_IP}:${DOCSUM_BACKEND_SERVER_PORT}/v1/docsum \
    -H "Content-Type: multipart/form-data" \
    -F "type=text" \
    -F "messages=" \
@@ -255,7 +335,7 @@ Map_reduce mode will split the inputs into multiple chunks, map each document to
 In this mode, default `chunk_size` is set to be `min(MAX_TOTAL_TOKENS - input.max_tokens - 50, MAX_INPUT_TOKENS)`
 
 ```bash
-curl http://${host_ip}:8888/v1/docsum \
+curl http://${HOST_IP}:${DOCSUM_BACKEND_SERVER_PORT}/v1/docsum \
    -H "Content-Type: multipart/form-data" \
    -F "type=text" \
    -F "messages=" \
@@ -272,7 +352,7 @@ Refin mode will split the inputs into multiple chunks, generate summary for the
 In this mode, default `chunk_size` is set to be `min(MAX_TOTAL_TOKENS - 2 * input.max_tokens - 128, MAX_INPUT_TOKENS)`.
 
 ```bash
-curl http://${host_ip}:8888/v1/docsum \
+curl http://${HOST_IP}:${DOCSUM_BACKEND_SERVER_PORT}/v1/docsum \
    -H "Content-Type: multipart/form-data" \
    -F "type=text" \
    -F "messages=" \
@@ -288,7 +368,7 @@ Several UI options are provided. If you need to work with multimedia documents,
 
 ### Gradio UI
 
-To access the UI, use the URL - http://${EXTERNAL_HOST_IP}:${FAGGEN_UI_PORT}
+To access the UI, use the URL - http://${HOST_IP}:${DOCSUM_FRONTEND_PORT}
 A page should open when you click through to this address:
 
 ![UI start page](../../../../assets/img/ui-starting-page.png)

EdgeCraftRAG/Dockerfile

@@ -1,8 +1,9 @@
 # Copyright (C) 2024 Intel Corporation
 # SPDX-License-Identifier: Apache-2.0
 
+ARG IMAGE_REPO=opea
 ARG BASE_TAG=latest
-FROM opea/comps-base:$BASE_TAG
+FROM $IMAGE_REPO/comps-base:$BASE_TAG
 
 COPY ./chatqna.py $HOME/chatqna.py
 

EdgeCraftRAG/Dockerfile.server

@@ -40,7 +40,7 @@ USER user
 
 WORKDIR /home/user/edgecraftrag
 RUN pip install --no-cache-dir --upgrade pip setuptools==70.0.0 && \
-    pip install --no-cache-dir -r requirements.txt
+    pip install --no-cache-dir --extra-index-url https://download.pytorch.org/whl/cpu -r requirements.txt 
 
 WORKDIR /home/user/
 RUN git clone https://github.com/openvinotoolkit/openvino.genai.git genai

EdgeCraftRAG/docker_compose/intel/gpu/arc/compose_vllm.yaml

@@ -63,7 +63,7 @@ services:
       - ecrag
   vllm-openvino-server:
     container_name: vllm-openvino-server
-    image: opea/vllm-arc:latest
+    image: ${REGISTRY:-opea}/vllm-arc:${TAG:-latest}
     ports:
       - ${VLLM_SERVICE_PORT:-8008}:80
     environment:

EdgeCraftRAG/docker_image_build/build.yaml

@@ -2,35 +2,33 @@
 # SPDX-License-Identifier: Apache-2.0
 
 services:
-  edgecraftrag-server:
-    build:
-      context: ../
-      args:
-        http_proxy: ${http_proxy}
-        https_proxy: ${https_proxy}
-      dockerfile: ./Dockerfile.server
-    image: ${REGISTRY:-opea}/edgecraftrag-server:${TAG:-latest}
-  edgecraftrag-ui:
-    build:
-      context: ../
-      args:
-        http_proxy: ${http_proxy}
-        https_proxy: ${https_proxy}
-      dockerfile: ./ui/docker/Dockerfile.ui
-    image: ${REGISTRY:-opea}/edgecraftrag-ui:${TAG:-latest}
-  edgecraftrag-ui-gradio:
-    build:
-      context: ../
-      args:
-        http_proxy: ${http_proxy}
-        https_proxy: ${https_proxy}
-      dockerfile: ./ui/docker/Dockerfile.gradio
-    image: ${REGISTRY:-opea}/edgecraftrag-ui-gradio:${TAG:-latest}
   edgecraftrag:
     build:
       context: ../
       args:
+        IMAGE_REPO: ${REGISTRY}
+        BASE_TAG: ${TAG}
         http_proxy: ${http_proxy}
         https_proxy: ${https_proxy}
       dockerfile: ./Dockerfile
     image: ${REGISTRY:-opea}/edgecraftrag:${TAG:-latest}
+  edgecraftrag-server:
+    build:
+      dockerfile: ./Dockerfile.server
+    extends: edgecraftrag
+    image: ${REGISTRY:-opea}/edgecraftrag-server:${TAG:-latest}
+  edgecraftrag-ui:
+    build:
+      dockerfile: ./ui/docker/Dockerfile.ui
+    extends: edgecraftrag
+    image: ${REGISTRY:-opea}/edgecraftrag-ui:${TAG:-latest}
+  edgecraftrag-ui-gradio:
+    build:
+      dockerfile: ./ui/docker/Dockerfile.gradio
+    extends: edgecraftrag
+    image: ${REGISTRY:-opea}/edgecraftrag-ui-gradio:${TAG:-latest}
+  vllm-arc:
+    build:
+      context: GenAIComps
+      dockerfile: comps/third_parties/vllm/src/Dockerfile.intel_gpu
+    image: ${REGISTRY:-opea}/vllm-arc:${TAG:-latest}

EdgeCraftRAG/tests/test_compose_on_arc.sh

@@ -30,8 +30,16 @@ HF_ENDPOINT=https://hf-mirror.com
 
 
 function build_docker_images() {
+    opea_branch=${opea_branch:-"main"}
     cd $WORKPATH/docker_image_build
+    git clone --depth 1 --branch ${opea_branch} https://github.com/opea-project/GenAIComps.git
+    pushd GenAIComps
+    echo "GenAIComps test commit is $(git rev-parse HEAD)"
+    docker build --no-cache -t ${REGISTRY}/comps-base:${TAG} --build-arg https_proxy=$https_proxy --build-arg http_proxy=$http_proxy -f Dockerfile .
+    popd && sleep 1s
+
     echo "Build all the images with --no-cache, check docker_image_build.log for details..."
+    service_list="edgecraftrag edgecraftrag-server edgecraftrag-ui"
     docker compose -f build.yaml build --no-cache > ${LOG_PATH}/docker_image_build.log
 
     docker images && sleep 1s
@@ -102,16 +110,30 @@ function stop_docker() {
 function main() {
     mkdir -p $LOG_PATH
 
+    echo "::group::stop_docker"
     stop_docker
+    echo "::endgroup::"
+
+    echo "::group::build_docker_images"
     if [[ "$IMAGE_REPO" == "opea" ]]; then build_docker_images; fi
+    echo "::endgroup::"
+
+    echo "::group::start_services"
     start_services
-    echo "EC_RAG service started" && sleep 1s
+    echo "::endgroup::"
 
+    echo "::group::validate_rag"
     validate_rag
-    validate_megaservice
+    echo "::endgroup::"
 
+    echo "::group::validate_megaservice"
+    validate_megaservice
+    echo "::endgroup::"
+
+    echo "::group::stop_docker"
     stop_docker
     echo y | docker system prune
+    echo "::endgroup::"
 
 }
 

EdgeCraftRAG/tests/test_compose_vllm_on_arc.sh

@@ -33,7 +33,14 @@ vLLM_ENDPOINT="http://${HOST_IP}:${VLLM_SERVICE_PORT}"
 
 
 function build_docker_images() {
+    opea_branch=${opea_branch:-"main"}
     cd $WORKPATH/docker_image_build
+    git clone --depth 1 --branch ${opea_branch} https://github.com/opea-project/GenAIComps.git
+    pushd GenAIComps
+    echo "GenAIComps test commit is $(git rev-parse HEAD)"
+    docker build --no-cache -t ${REGISTRY}/comps-base:${TAG} --build-arg https_proxy=$https_proxy --build-arg http_proxy=$http_proxy -f Dockerfile .
+    popd && sleep 1s
+
     echo "Build all the images with --no-cache, check docker_image_build.log for details..."
     docker compose -f build.yaml build --no-cache > ${LOG_PATH}/docker_image_build.log
 
@@ -152,19 +159,30 @@ function stop_docker() {
 function main() {
     mkdir -p "$LOG_PATH"
 
+    echo "::group::stop_docker"
     stop_docker
+    echo "::endgroup::"
+
+    echo "::group::build_docker_images"
     if [[ "$IMAGE_REPO" == "opea" ]]; then build_docker_images; fi
-    start_time=$(date +%s)
+    echo "::endgroup::"
+
+    echo "::group::start_services"
     start_services
-    end_time=$(date +%s)
-    duration=$((end_time-start_time))
-    echo "EC_RAG service start duration is $duration s" && sleep 1s
+    echo "::endgroup::"
 
+    echo "::group::validate_rag"
     validate_rag
-    validate_megaservice
+    echo "::endgroup::"
 
+    echo "::group::validate_megaservice"
+    validate_megaservice
+    echo "::endgroup::"
+
+    echo "::group::stop_docker"
     stop_docker
     echo y | docker system prune
+    echo "::endgroup::"
 
 }
 

FinanceAgent/README.md

@@ -44,6 +44,8 @@ git clone https://github.com/opea-project/GenAIExamples.git
 ### 2.2 Set up env vars
 
 ```bash
+export ip_address="External_Public_IP"
+export no_proxy=${your_no_proxy},${ip_address}
 export HF_CACHE_DIR=/path/to/your/model/cache/
 export HF_TOKEN=<you-hf-token>
 export FINNHUB_API_KEY=<your-finnhub-api-key> # go to https://finnhub.io/ to get your free api key
@@ -100,8 +102,8 @@ bash launch_dataprep.sh
 Validate datat ingest data and retrieval from database:
 
 ```bash
-python $WORKPATH/tests/test_redis_finance.py --port 6007 --test_option ingest
-python $WORKPATH/tests/test_redis_finance.py --port 6007 --test_option get
+python $WORKDIR/GenAIExamples/FinanceAgent/tests/test_redis_finance.py --port 6007 --test_option ingest
+python $WORKDIR/GenAIExamples/FinanceAgent/tests/test_redis_finance.py --port 6007 --test_option get
 ```
 
 ### 3.3 Launch the multi-agent system

MultimodalQnA/docker_compose/intel/cpu/xeon/README.md

@@ -241,7 +241,7 @@ docker compose -f compose.yaml up -d
 export MILVUS_HOST=${host_ip}
 export MILVUS_PORT=19530
 export MILVUS_RETRIEVER_PORT=7000
-export COLLECTION_NAME=mm_rag_milvus
+export COLLECTION_NAME=LangChainCollection
 cd GenAIExamples/MultimodalQnA/docker_compose/intel/cpu/xeon/
 docker compose -f compose_milvus.yaml up -d
 ```
@@ -385,6 +385,8 @@ curl --silent --write-out "HTTPSTATUS:%{http_code}" \
 
 Now, test the microservice with posting a custom caption along with an image and a PDF containing images and text. The image caption can be provided as a text (`.txt`) or as spoken audio (`.wav` or `.mp3`).
 
+> Note: Audio captions for images are currently only supported when using the Redis data prep backend.
+
 ```bash
 curl --silent --write-out "HTTPSTATUS:%{http_code}" \
     ${DATAPREP_INGEST_SERVICE_ENDPOINT} \

MultimodalQnA/docker_compose/intel/cpu/xeon/compose_milvus.yaml

@@ -226,6 +226,8 @@ services:
       - DATAPREP_INGEST_SERVICE_ENDPOINT=${DATAPREP_INGEST_SERVICE_ENDPOINT}
       - DATAPREP_GEN_TRANSCRIPT_SERVICE_ENDPOINT=${DATAPREP_GEN_TRANSCRIPT_SERVICE_ENDPOINT}
       - DATAPREP_GEN_CAPTION_SERVICE_ENDPOINT=${DATAPREP_GEN_CAPTION_SERVICE_ENDPOINT}
+      - DATAPREP_GET_FILE_ENDPOINT=${DATAPREP_GET_FILE_ENDPOINT}
+      - DATAPREP_DELETE_FILE_ENDPOINT=${DATAPREP_DELETE_FILE_ENDPOINT}
       - MEGA_SERVICE_PORT:=${MEGA_SERVICE_PORT}
       - UI_PORT=${UI_PORT}
       - DATAPREP_MMR_PORT=${DATAPREP_MMR_PORT}

README-deploy-benchmark.md

@@ -1,4 +1,4 @@
-# ChatQnA Benchmarking
+# Deploy and Benchmark
 
 ## Purpose
 
@@ -8,6 +8,11 @@ We aim to run these benchmarks and share them with the OPEA community for three
 - To establish a baseline for validating optimization solutions across different implementations, providing clear guidance on which methods are most effective for your use case.
 - To inspire the community to build upon our benchmarks, allowing us to better quantify new solutions in conjunction with current leading LLMs, serving frameworks etc.
 
+### Support Example List
+
+- ChatQnA
+- DocSum
+
 ## Table of Contents
 
 - [Prerequisites](#prerequisites)
@@ -68,6 +73,7 @@ Before running the benchmarks, ensure you have:
    ```bash
    pip install -r requirements.txt
    ```
+   notes: the benchmark need `opea-eval>=1.3`, if v1.3 is not released, please build the `opea-eval` from [source](https://github.com/opea-project/GenAIEval).
 
 ## Data Preparation
 

SearchQnA/docker_compose/amd/gpu/rocm/README.md

@@ -1,28 +1,29 @@
-# Example SearchQnA deployments on AMD GPU (ROCm)
+# Deploying SearchQnA on AMD ROCm Platform
 
-This document outlines the deployment process for a SearchQnA application utilizing the [GenAIComps](https://github.com/opea-project/GenAIComps.git) microservice pipeline on AMD GPU (ROCm).
+This document outlines the single node deployment process for a SearchQnA application utilizing the [GenAIComps](https://github.com/opea-project/GenAIComps.git) microservices on AMD ROCm Platform.
 
-This example includes the following sections:
+## Table of Contents
 
-- [SearchQnA Quick Start Deployment](#searchqna-quick-start-deployment): Demonstrates how to quickly deploy a SearchQnA application/pipeline on AMD GPU platform.
-- [SearchQnA Docker Compose Files](#searchqna-docker-compose-files): Describes some example deployments and their docker compose files.
-- [Launch the UI](#launch-the-ui): Guideline for UI usage
+1. [SearchQnA Quick Start Deployment](#searchqna-quick-start-deployment)
+2. [SearchQnA Docker Compose Files](#searchqna-docker-compose-files)
+3. [Validate Microservices](#validate-microservices)
+4. [Launch the UI](#launch-the-ui): Guideline for UI usage
+5. [Conclusion](#conclusion)
 
 ## SearchQnA Quick Start Deployment
 
-This section describes how to quickly deploy and test the SearchQnA service manually on AMD GPU (ROCm). The basic steps are:
+This section describes how to quickly deploy and test the SearchQnA service manually on an AMD ROCm Platform. The basic steps are:
 
 1. [Access the Code](#access-the-code)
-2. [Generate a HuggingFace Access Token](#generate-a-huggingface-access-token)
-3. [Configure the Deployment Environment](#configure-the-deployment-environment)
-4. [Deploy the Services Using Docker Compose](#deploy-the-services-using-docker-compose)
-5. [Check the Deployment Status](#check-the-deployment-status)
-6. [Test the Pipeline](#test-the-pipeline)
-7. [Cleanup the Deployment](#cleanup-the-deployment)
+2. [Configure the Deployment Environment](#configure-the-deployment-environment)
+3. [Deploy the Services Using Docker Compose](#deploy-the-services-using-docker-compose)
+4. [Check the Deployment Status](#check-the-deployment-status)
+5. [Validate the Pipeline](#validate-the-pipeline)
+6. [Cleanup the Deployment](#cleanup-the-deployment)
 
 ### Access the Code
 
-Clone the GenAIExample repository and access the SearchQnA AMD GPU (ROCm) Docker Compose files and supporting scripts:
+Clone the GenAIExample repository and access the SearchQnA AMD ROCm Platform Docker Compose files and supporting scripts:
 
 ```bash
 git clone https://github.com/opea-project/GenAIExamples.git
@@ -41,34 +42,56 @@ Some HuggingFace resources require an access token. Developers can create one by
 
 ### Configure the Deployment Environment
 
-To set up environment variables for deploying SearchQnA services, source the _setup_env.sh_ script in this directory:
+To set up environment variables for deploying SearchQnA services, set up some parameters specific to the deployment environment and source the `set_env.sh` script in this directory:
 
-```
-//with TGI:
-source ./set_env.sh
-```
+#### For vLLM inference type deployment (default)
 
-```
-//with VLLM:
+```bash
+export host_ip="External_Public_IP"           # ip address of the node
+export GOOGLE_CSE_ID="your cse id"
+export GOOGLE_API_KEY="your google api key"
+export HUGGINGFACEHUB_API_TOKEN="Your_HuggingFace_API_Token"
+export http_proxy="Your_HTTP_Proxy"           # http proxy if any
+export https_proxy="Your_HTTPs_Proxy"         # https proxy if any
+export no_proxy=localhost,127.0.0.1,$host_ip  # additional no proxies if needed
+export NGINX_PORT=${your_nginx_port}          # your usable port for nginx, 80 for example
 source ./set_env_vllm.sh
 ```
 
-The _setup_env.sh_ script will prompt for required and optional environment variables used to configure the SearchQnA services based on TGI. The _setup_env_vllm.sh_ script will prompt for required and optional environment variables used to configure the SearchQnA services based on VLLM. If a value is not entered, the script will use a default value for the same. It will also generate a _.env_ file defining the desired configuration. Consult the section on [SearchQnA Service configuration](#SearchQnA-service-configuration) for information on how service specific configuration parameters affect deployments.
+#### For TGI inference type deployment
+
+```bash
+export host_ip="External_Public_IP"           # ip address of the node
+export GOOGLE_CSE_ID="your cse id"
+export GOOGLE_API_KEY="your google api key"
+export HUGGINGFACEHUB_API_TOKEN="Your_HuggingFace_API_Token"
+export http_proxy="Your_HTTP_Proxy"           # http proxy if any
+export https_proxy="Your_HTTPs_Proxy"         # https proxy if any
+export no_proxy=localhost,127.0.0.1,$host_ip  # additional no proxies if needed
+export NGINX_PORT=${your_nginx_port}          # your usable port for nginx, 80 for example
+source ./set_env.sh
+```
+
+Consult the section on [SearchQnA Service configuration](#SearchQnA-configuration) for information on how service specific configuration parameters affect deployments.
 
 ### Deploy the Services Using Docker Compose
 
 To deploy the SearchQnA services, execute the `docker compose up` command with the appropriate arguments. For a default deployment, execute:
 
-```bash
-//with TGI:
-docker compose -f compose.yaml up -d
-```
+#### For vLLM inference type deployment (default)
 
 ```bash
 //with VLLM:
 docker compose -f compose_vllm.yaml up -d
 ```
 
+#### For TGI inference type deployment
+
+```bash
+//with TGI:
+docker compose -f compose.yaml up -d
+```
+
 **Note**: developers should build docker image from source when:
 
 - Developing off the git main branch (as the container's ports in the repo may be different from the published docker image).
@@ -97,7 +120,40 @@ docker ps -a
 
 For the default deployment, the following containers should have started
 
-### Test the Pipeline
+#### For vLLM inference type deployment (default)
+
+```
+CONTAINER ID   IMAGE                                                   COMMAND                  CREATED              STATUS              PORTS                                           NAMES
+50e5f4a00fcc   opea/searchqna-ui:latest                                "docker-entrypoint.s…"   About a minute ago   Up About a minute   0.0.0.0:18143->5173/tcp, [::]:18143->5173/tcp   search-ui-server
+a8f030d17e40   opea/searchqna:latest                                   "python searchqna.py"    About a minute ago   Up About a minute   0.0.0.0:18142->8888/tcp, [::]:18142->8888/tcp   search-backend-server
+916c5db048a2   opea/llm-textgen:latest                                 "bash entrypoint.sh"     About a minute ago   Up About a minute   0.0.0.0:3007->9000/tcp, [::]:3007->9000/tcp     search-llm-server
+bb46cdaf1794   opea/reranking:latest                                   "python opea_reranki…"   About a minute ago   Up About a minute   0.0.0.0:3005->8000/tcp, [::]:3005->8000/tcp     search-reranking-server
+d89ab0ef3f41   opea/embedding:latest                                   "sh -c 'python $( [ …"   About a minute ago   Up About a minute   0.0.0.0:3002->6000/tcp, [::]:3002->6000/tcp     search-embedding-server
+b248e55dd20f   opea/vllm-rocm:latest                                   "python3 /workspace/…"   About a minute ago   Up About a minute   0.0.0.0:3080->8011/tcp, [::]:3080->8011/tcp     search-vllm-service
+c3800753fac5   opea/web-retriever:latest                               "python opea_web_ret…"   About a minute ago   Up About a minute   0.0.0.0:3003->7077/tcp, [::]:3003->7077/tcp     search-web-retriever-server
+0db8af486bd0   ghcr.io/huggingface/text-embeddings-inference:cpu-1.5   "text-embeddings-rou…"   About a minute ago   Up About a minute   0.0.0.0:3001->80/tcp, [::]:3001->80/tcp         search-tei-embedding-server
+3125915447ef   ghcr.io/huggingface/text-embeddings-inference:cpu-1.5   "text-embeddings-rou…"   About a minute ago   Up About a minute   0.0.0.0:3004->80/tcp, [::]:3004->80/tcp         search-tei-reranking-server
+```
+
+#### For TGI inference type deployment
+
+```
+CONTAINER ID   IMAGE                                                      COMMAND                  CREATED              STATUS              PORTS                                           NAMES
+67cc886949a3   opea/searchqna-ui:latest                                   "docker-entrypoint.s…"   About a minute ago   Up About a minute   0.0.0.0:18143->5173/tcp, [::]:18143->5173/tcp   search-ui-server
+6547aca0d5fd   opea/searchqna:latest                                      "python searchqna.py"    About a minute ago   Up About a minute   0.0.0.0:18142->8888/tcp, [::]:18142->8888/tcp   search-backend-server
+213b5d4d5fa5   opea/embedding:latest                                      "sh -c 'python $( [ …"   About a minute ago   Up About a minute   0.0.0.0:3002->6000/tcp, [::]:3002->6000/tcp     search-embedding-server
+6b90d16100b2   opea/reranking:latest                                      "python opea_reranki…"   About a minute ago   Up About a minute   0.0.0.0:3005->8000/tcp, [::]:3005->8000/tcp     search-reranking-server
+3266fd85207e   opea/llm-textgen:latest                                    "bash entrypoint.sh"     About a minute ago   Up About a minute   0.0.0.0:3007->9000/tcp, [::]:3007->9000/tcp     search-llm-server
+d7322b70c15d   ghcr.io/huggingface/text-generation-inference:2.4.1-rocm   "/tgi-entrypoint.sh …"   About a minute ago   Up About a minute   0.0.0.0:3006->80/tcp, [::]:3006->80/tcp         search-tgi-service
+a703b91b28ed   ghcr.io/huggingface/text-embeddings-inference:cpu-1.6      "text-embeddings-rou…"   About a minute ago   Up About a minute   0.0.0.0:3001->80/tcp, [::]:3001->80/tcp         search-tei-embedding-server
+22098a5eaf59   ghcr.io/huggingface/text-embeddings-inference:cpu-1.6      "text-embeddings-rou…"   About a minute ago   Up About a minute   0.0.0.0:3004->80/tcp, [::]:3004->80/tcp         search-tei-reranking-server
+830fe84c971d   opea/web-retriever:latest                                  "python opea_web_ret…"   About a minute ago   Up About a minute   0.0.0.0:3003->7077/tcp, [::]:3003->7077/tcp     search-web-retriever-server
+
+```
+
+If any issues are encountered during deployment, refer to the [Troubleshooting](../../../../README_miscellaneous.md#troubleshooting) section.
+
+### Validate the Pipeline
 
 Once the SearchQnA services are running, test the pipeline using the following command:
 
@@ -131,31 +187,125 @@ data: [DONE]
 
 A response text similar to the one above indicates that the service verification was successful.
 
+**Note** : Access the SearchQnA UI by web browser through this URL: `http://${host_ip}:80`. Please confirm the `80` port is opened in the firewall. To validate each microservice used in the pipeline refer to the [Validate Microservices](#validate-microservices) section.
+
 ### Cleanup the Deployment
 
 To stop the containers associated with the deployment, execute the following command:
 
-```bash
-//with TGI:
-docker compose -f compose.yaml down
-```
+#### For vLLM inference type deployment (default)
 
 ```bash
 //with VLLM:
 docker compose -f compose_vllm.yaml down
 ```
 
+#### For TGI inference type deployment
+
+```bash
+//with TGI:
+docker compose -f compose.yaml down
+```
+
 All the SearchQnA containers will be stopped and then removed on completion of the "down" command.
 
 ## SearchQnA Docker Compose Files
 
-When deploying the SearchQnA pipeline on AMD GPUs (ROCm), different large language model serving frameworks can be selected. The table below outlines the available configurations included in the application.
+When deploying a SearchQnA pipeline on an AMD GPUs (ROCm), different large language model serving frameworks can be selected. The table below outlines the available configurations included in the application. These configurations can serve as templates and be extended to other components available in [GenAIComps](https://github.com/opea-project/GenAIComps.git).
 
 | File                                     | Description                                                                                |
 | ---------------------------------------- | ------------------------------------------------------------------------------------------ |
 | [compose.yaml](./compose.yaml)           | Default compose file using tgi as serving framework                                        |
 | [compose_vllm.yaml](./compose_vllm.yaml) | The LLM serving framework is vLLM. All other configurations remain the same as the default |
 
+## Validate Microservices
+
+1. Embedding backend Service
+
+   ```bash
+    curl http://${host_ip}:3001/embed \
+        -X POST \
+        -d '{"inputs":"What is Deep Learning?"}' \
+        -H 'Content-Type: application/json'
+   ```
+
+2. Embedding Microservice
+
+   ```bash
+    curl http://${host_ip}:3002/v1/embeddings\
+      -X POST \
+      -d '{"text":"hello"}' \
+      -H 'Content-Type: application/json'
+   ```
+
+3. Web Retriever Microservice
+
+   ```bash
+    export your_embedding=$(python3 -c "import random; embedding = [random.uniform(-1, 1) for _ in range(768)]; print(embedding)")
+    curl http://${host_ip}:3003/v1/web_retrieval \
+      -X POST \
+      -d "{\"text\":\"What is the 2024 holiday schedule?\",\"embedding\":${your_embedding}}" \
+      -H 'Content-Type: application/json'
+   ```
+
+4. Reranking backend Service
+
+```bash
+ # TEI Reranking service
+  curl http://${host_ip}:3004/rerank \
+      -X POST \
+      -d '{"query":"What is Deep Learning?", "texts": ["Deep Learning is not...", "Deep learning is..."]}' \
+      -H 'Content-Type: application/json'
+```
+
+5. Reranking Microservice
+
+```bash
+  curl http://${host_ip}:3005/v1/reranking\
+    -X POST \
+    -d '{"initial_query":"What is Deep Learning?", "retrieved_docs": [{"text":"Deep Learning is not..."}, {"text":"Deep learning is..."}]}' \
+    -H 'Content-Type: application/json'
+```
+
+6. LLM backend Service
+
+```bash
+ # TGI service
+  curl http://${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'
+```
+
+7. LLM Microservice
+
+   ```bash
+    curl http://${host_ip}:3007/v1/chat/completions\
+      -X POST \
+      -d '{"query":"What is Deep Learning?","max_tokens":17,"top_k":10,"top_p":0.95,"typical_p":0.95,"temperature":0.01,"repetition_penalty":1.03,"stream":true}' \
+      -H 'Content-Type: application/json'
+   ```
+
+8. MegaService
+
+   ```bash
+    curl http://${host_ip}:3008/v1/searchqna -H "Content-Type: application/json" -d '{
+        "messages": "What is the latest news? Give me also the source link.",
+        "stream": "true"
+        }'
+   ```
+
+9. Nginx Service
+
+   ```bash
+   curl http://${host_ip}:${NGINX_PORT}/v1/searchqna \
+       -H "Content-Type: application/json" \
+       -d '{
+        "messages": "What is the latest news? Give me also the source link.",
+        "stream": "true"
+        }'
+   ```
+
 ## Launch the UI
 
 Access the UI at http://${EXTERNAL_HOST_IP}:${SEARCH_FRONTEND_SERVICE_PORT}. A page should open when navigating to this address.
@@ -167,3 +317,7 @@ Let's enter the task for the service in the "Enter prompt here" field. For examp
 
 ![UI start page](../../../../assets/img/searchqna-ui-response-example.png)
 A correct result displayed on the page indicates that the UI service has been successfully verified.
+
+## Conclusion
+
+This guide should enable developers to deploy the default configuration or any of the other compose yaml files for different configurations. It also highlights the configurable parameters that can be set before deployment.

deploy.py

@@ -224,6 +224,7 @@ def generate_helm_values(example_type, deploy_config, chart_dir, action_type, no
             "modelUseHostPath": deploy_config.get("modelUseHostPath", ""),
         }
     }
+    os.environ["HF_TOKEN"] = deploy_config.get("HUGGINGFACEHUB_API_TOKEN", "")
 
     # Configure components
     values = configure_node_selectors(values, node_selector or {}, deploy_config)
@@ -338,17 +339,15 @@ def get_hw_values_file(deploy_config, chart_dir):
     version = deploy_config.get("version", "1.1.0")
 
     if os.path.isdir(chart_dir):
-        # Determine which values file to use based on version
-        if version in ["1.0.0", "1.1.0"]:
-            hw_values_file = os.path.join(chart_dir, f"{device_type}-values.yaml")
-        else:
-            hw_values_file = os.path.join(chart_dir, f"{device_type}-{llm_engine}-values.yaml")
-
+        hw_values_file = os.path.join(chart_dir, f"{device_type}-{llm_engine}-values.yaml")
         if not os.path.exists(hw_values_file):
             print(f"Warning: {hw_values_file} not found")
-            hw_values_file = None
-        else:
-            print(f"Device-specific values file found: {hw_values_file}")
+            hw_values_file = os.path.join(chart_dir, f"{device_type}-values.yaml")
+            if not os.path.exists(hw_values_file):
+                print(f"Warning: {hw_values_file} not found")
+                print(f"Error: Can not found a correct values file for {device_type} with {llm_engine}")
+                sys.exit(1)
+        print(f"Device-specific values file found: {hw_values_file}")
     else:
         print(f"Error: Could not find directory for {chart_dir}")
         hw_values_file = None

deploy_and_benchmark.py

@@ -54,7 +54,7 @@ def construct_deploy_config(deploy_config, target_node, batch_param_value=None,
 
     # First determine which llm replicaCount to use based on teirerank.enabled
     services = new_config.get("services", {})
-    teirerank_enabled = services.get("teirerank", {}).get("enabled", True)
+    teirerank_enabled = services.get("teirerank", {}).get("enabled", False)
 
     # Process each service's configuration
     for service_name, service_config in services.items():

docker_images_list.md

@@ -16,7 +16,7 @@ Take ChatQnA for example. ChatQnA is a chatbot application service based on the
 | [opea/chatqna-conversation-ui](https://hub.docker.com/r/opea/chatqna-conversation-ui)                       | [Link](https://github.com/opea-project/GenAIExamples/blob/main/ChatQnA/ui/docker/Dockerfile.react)           | Chatqna React UI. Facilitates interaction with users, enabling chat-based Q&A with conversation history stored in the browser's local storage.                                                                                       | [Link](https://github.com/opea-project/GenAIExamples/blob/main/ChatQnA/ui/react/README.md)           |
 | [opea/chatqna-ui](https://hub.docker.com/r/opea/chatqna-ui)                                                 | [Link](https://github.com/opea-project/GenAIExamples/blob/main/ChatQnA/ui/docker/Dockerfile)                 | Chatqna UI entry. Facilitates interaction with users to answer questions                                                                                                                                                             | [Link](https://github.com/opea-project/GenAIExamples/blob/main/ChatQnA/ui/svelte/README.md)          |
 | [opea/codegen](https://hub.docker.com/r/opea/codegen)                                                       | [Link](https://github.com/opea-project/GenAIExamples/blob/main/CodeGen/Dockerfile)                           | Codegen gateway. Provides automatic creation of source code from high-level representations                                                                                                                                          | [Link](https://github.com/opea-project/GenAIExamples/blob/main/CodeGen/README.md)                    |
-| [opea/codegen-gradio-ui]()                                                                                  | [Link](https://github.com/opea-project/GenAIExamples/blob/main/CodeGen/ui/docker/Dockerfile.gradio)          | Codegen Gradio UI entry. Interact with users to generate source code by providing high-level descriptions or inputs.                                                                                                                 |                                                                                                      |
+| [opea/codegen-gradio-ui](https://hub.docker.com/r/opea/codegen-gradio-ui)                                   | [Link](https://github.com/opea-project/GenAIExamples/blob/main/CodeGen/ui/docker/Dockerfile.gradio)          | Codegen Gradio UI entry. Interact with users to generate source code by providing high-level descriptions or inputs.                                                                                                                 | [Link](https://github.com/opea-project/GenAIExamples/blob/main/CodeGen/ui/gradio/README.md)          |
 | [opea/codegen-react-ui](https://hub.docker.com/r/opea/codegen-react-ui)                                     | [Link](https://github.com/opea-project/GenAIExamples/blob/main/CodeGen/ui/docker/Dockerfile.react)           | Codegen React UI. Interact with users to generate appropriate code based on current user input.                                                                                                                                      | [Link](https://github.com/opea-project/GenAIExamples/blob/main/CodeGen/ui/react/README.md)           |
 | [opea/codegen-ui](https://hub.docker.com/r/opea/codegen-ui)                                                 | [Link](https://github.com/opea-project/GenAIExamples/blob/main/CodeGen/ui/docker/Dockerfile)                 | Codegen UI entry. Facilitates interaction with users, automatically generate code based on user's descriptions                                                                                                                       | [Link](https://github.com/opea-project/GenAIExamples/blob/main/CodeGen/ui/svelte/README.md)          |
 | [opea/codetrans](https://hub.docker.com/r/opea/codetrans)                                                   | [Link](https://github.com/opea-project/GenAIExamples/blob/main/CodeTrans/Dockerfile)                         | Codetrans gateway. Provide services to convert source code written in one programming language to an equivalent version in another programming language.                                                                             | [Link](https://github.com/opea-project/GenAIExamples/blob/main/CodeTrans/README.md)                  |
@@ -29,7 +29,7 @@ Take ChatQnA for example. ChatQnA is a chatbot application service based on the
 | [opea/edgecraftrag](https://hub.docker.com/r/opea/edgecraftrag)                                             | [Link](https://github.com/opea-project/GenAIExamples/blob/main/EdgeCraftRAG/Dockerfile)                      | Edge Craft RAG (EC-RAG) gateway. Provides a customizable, production-ready retrieval-enhanced generation system that is optimized for edge solutions.                                                                                | [Link](https://github.com/opea-project/GenAIExamples/blob/main/EdgeCraftRAG/README.md)               |
 | [opea/edgecraftrag-server](https://hub.docker.com/r/opea/edgecraftrag-server)                               | [Link](https://github.com/opea-project/GenAIExamples/blob/main/EdgeCraftRAG/Dockerfile.server)               | Edge Craft RAG (EC-RAG) server, Provides a customizable, production-ready retrieval-enhanced generation system that is optimized for edge solutions.                                                                                 | [Link](https://github.com/opea-project/GenAIExamples/blob/main/EdgeCraftRAG/README.md)               |
 | [opea/edgecraftrag-ui](https://hub.docker.com/r/opea/edgecraftrag-ui)                                       | [Link](https://github.com/opea-project/GenAIExamples/blob/main/EdgeCraftRAG/ui/docker/Dockerfile.ui)         | Edge Craft RAG (EC-RAG) UI entry. Ensuring high-quality, performant interactions tailored for edge environments.                                                                                                                     |                                                                                                      |
-| [opea/edgecraftrag-ui-gradio]()                                                                             | [Link](https://github.com/opea-project/GenAIExamples/blob/main/EdgeCraftRAG/ui/docker/Dockerfile.gradio)     | Edge Craft RAG (EC-RAG) Gradio UI entry. Interact with users to provide a customizable, production-ready retrieval-enhanced generation system optimized for edge solutions.                                                          |                                                                                                      |
+| [opea/edgecraftrag-ui-gradio](https://hub.docker.com/r/opea/edgecraftrag-ui-gradio)                         | [Link](https://github.com/opea-project/GenAIExamples/blob/main/EdgeCraftRAG/ui/docker/Dockerfile.gradio)     | Edge Craft RAG (EC-RAG) Gradio UI entry. Interact with users to provide a customizable, production-ready retrieval-enhanced generation system optimized for edge solutions.                                                          |                                                                                                      |
 | [opea/graphrag](https://hub.docker.com/r/opea/graphrag)                                                     | [Link](https://github.com/opea-project/GenAIExamples/blob/main/GraphRAG/Dockerfile)                          | GraphRAG gateway, Local and global queries are processed using knowledge graphs extracted from source documents.                                                                                                                     | [Link](https://github.com/opea-project/GenAIExamples/blob/main/GraphRAG/README.md)                   |
 | [opea/graphrag-react-ui](https://hub.docker.com/r/opea/graphrag-react-ui)                                   | [Link](https://github.com/opea-project/GenAIExamples/blob/main/GraphRAG/ui/docker/Dockerfile.react)          | Graphrag React UI entry. Facilitates interaction with users, enabling queries and providing relevant answers using knowledge graphs.                                                                                                 | [Link](https://github.com/opea-project/GenAIExamples/blob/main/GraphRAG/ui/react/README.md)          |
 | [opea/graphrag-ui](https://hub.docker.com/r/opea/graphrag-ui)                                               | [Link](https://github.com/opea-project/GenAIExamples/blob/main/GraphRAG/ui/docker/Dockerfile)                | Graphrag UI entry. Interact with users to facilitate queries and provide relevant answers using knowledge graphs.                                                                                                                    | [Link](https://github.com/opea-project/GenAIExamples/blob/main/GraphRAG/ui/svelte/README.md)         |
@@ -54,7 +54,7 @@ Take ChatQnA for example. ChatQnA is a chatbot application service based on the
 | [opea/animation](https://hub.docker.com/r/opea/animation)                                                           | [Link](https://github.com/opea-project/GenAIComps/blob/main/comps/animation/src/Dockerfile)                           | OPEA Avatar Animation microservice for GenAI applications                                                                                                                                    | [Link](https://github.com/opea-project/GenAIComps/blob/main/comps/animation/src/README.md)                               |
 | [opea/asr](https://hub.docker.com/r/opea/asr)                                                                       | [Link](https://github.com/opea-project/GenAIComps/blob/main/comps/asr/src/Dockerfile)                                 | OPEA Audio-Speech-Recognition microservice for GenAI applications                                                                                                                            | [Link](https://github.com/opea-project/GenAIComps/blob/main/comps/asr/src/README.md)                                     |
 | [opea/chathistory-mongo](https://hub.docker.com/r/opea/chathistory-mongo)                                           | [Link](https://github.com/opea-project/GenAIComps/blob/main/comps/chathistory/src/Dockerfile)                         | OPEA Chat History microservice is based on a MongoDB database and is designed to allow users to store, retrieve and manage chat conversations.                                               | [Link](https://github.com/opea-project/GenAIComps/blob/main/comps/chathistory/src/README.md)                             |
-| [opea/comps-base]()                                                                                                 | [Link](https://github.com/opea-project/GenAIComps/blob/main/Dockerfile)                                               | OPEA Microservice base image.                                                                                                                                                                | [Link](https://github.com/opea-project/GenAIComps/blob/main/README.md)                                                   |
+| [opea/comps-base](https://hub.docker.com/r/opea/comps-base)                                                         | [Link](https://github.com/opea-project/GenAIComps/blob/main/Dockerfile)                                               | OPEA Microservice base image.                                                                                                                                                                | [Link](https://github.com/opea-project/GenAIComps/blob/main/README.md)                                                   |
 | [opea/dataprep](https://hub.docker.com/r/opea/dataprep)                                                             | [Link](https://github.com/opea-project/GenAIComps/blob/main/comps/dataprep/src/Dockerfile)                            | OPEA data preparation microservices for GenAI applications                                                                                                                                   | [Link](https://github.com/opea-project/GenAIComps/blob/main/comps/dataprep/README.md)                                    |
 | [opea/embedding](https://hub.docker.com/r/opea/embedding)                                                           | [Link](https://github.com/opea-project/GenAIComps/blob/main/comps/embeddings/src/Dockerfile)                          | OPEA mosec embedding microservice for GenAI application                                                                                                                                      | [Link](https://github.com/opea-project/GenAIComps/blob/main/comps/embeddings/src/README.md)                              |
 | [opea/embedding-multimodal-bridgetower](https://hub.docker.com/r/opea/embedding-multimodal-bridgetower)             | [Link](https://github.com/opea-project/GenAIComps/blob/main/comps/third_parties/bridgetower/src/Dockerfile)           | OPEA multimodal embedded microservices based on bridgetower for use by GenAI applications                                                                                                    | [Link](https://github.com/opea-project/GenAIComps/blob/main/comps/third_parties/bridgetower/src/README.md)               |
@@ -63,7 +63,7 @@ Take ChatQnA for example. ChatQnA is a chatbot application service based on the
 | [opea/feedbackmanagement-mongo](https://hub.docker.com/r/opea/feedbackmanagement-mongo)                             | [Link](https://github.com/opea-project/GenAIComps/blob/main/comps/feedback_management/src/Dockerfile)                 | OPEA feedback management microservice uses MongoDB database for GenAI applications.                                                                                                          | [Link](https://github.com/opea-project/GenAIComps/blob/main/comps/feedback_management/src/README.md)                     |
 | [opea/finetuning](https://hub.docker.com/r/opea/finetuning)                                                         | [Link](https://github.com/opea-project/GenAIComps/blob/main/comps/finetuning/src/Dockerfile)                          | OPEA Fine-tuning microservice for GenAI application                                                                                                                                          | [Link](https://github.com/opea-project/GenAIComps/blob/main/comps/finetuning/src/README.md)                              |
 | [opea/finetuning-gaudi](https://hub.docker.com/r/opea/finetuning-gaudi)                                             | [Link](https://github.com/opea-project/GenAIComps/blob/main/comps/finetuning/src/Dockerfile.intel_hpu)                | OPEA Fine-tuning microservice for GenAI application use on the Gaudi                                                                                                                         | [Link](https://github.com/opea-project/GenAIComps/blob/main/comps/finetuning/src/README.md)                              |
-| [opea/finetuning-xtune]()                                                                                           | [Link](https://github.com/opea-project/GenAIComps/blob/main/comps/finetuning/src/Dockerfile.xtune)                    | OPEA Fine-tuning microservice base on Xtune for GenAI application use on the Arc A770                                                                                                        | [Link](https://github.com/opea-project/GenAIComps/blob/main/comps/finetuning/src/README.md)                              |
+| [opea/finetuning-xtune](https://hub.docker.com/r/opea/finetuning-xtune)                                             | [Link](https://github.com/opea-project/GenAIComps/blob/main/comps/finetuning/src/Dockerfile.xtune)                    | OPEA Fine-tuning microservice base on Xtune for GenAI application use on the Arc A770                                                                                                        | [Link](https://github.com/opea-project/GenAIComps/blob/main/comps/finetuning/src/README.md)                              |
 | [opea/gpt-sovits](https://hub.docker.com/r/opea/gpt-sovits)                                                         | [Link](https://github.com/opea-project/GenAIComps/blob/main/comps/third_parties/gpt-sovits/src/Dockerfile)            | OPEA GPT-SoVITS service for GenAI application                                                                                                                                                | [Link](https://github.com/opea-project/GenAIComps/blob/main/comps/third_parties/gpt-sovits/src/README.md)                |
 | [opea/guardrails](https://hub.docker.com/r/opea/guardrails)                                                         | [Link](https://github.com/opea-project/GenAIComps/blob/main/comps/guardrails/src/guardrails/Dockerfile)               | OPEA guardrail microservice for GenAI application                                                                                                                                            | [Link](https://github.com/opea-project/GenAIComps/blob/main/comps/guardrails/src/guardrails/README.md)                   |
 | [opea/guardrails-bias-detection](https://hub.docker.com/r/opea/guardrails-bias-detection)                           | [Link](https://github.com/opea-project/GenAIComps/blob/main/comps/guardrails/src/bias_detection/Dockerfile)           | OPEA guardrail microservice to provide bias detection for GenAI application                                                                                                                  | [Link](https://github.com/opea-project/GenAIComps/blob/main/comps/guardrails/src/bias_detection/README.md)               |
@@ -76,19 +76,19 @@ Take ChatQnA for example. ChatQnA is a chatbot application service based on the
 | [opea/image2image-gaudi](https://hub.docker.com/r/opea/image2image-gaudi)                                           | [Link](https://github.com/opea-project/GenAIComps/blob/main/comps/image2image/src/Dockerfile.intel_hpu)               | OPEA Image-to-Image microservice for GenAI application use on the Gaudi.                                                                                                                     | [Link](https://github.com/opea-project/GenAIComps/blob/main/comps/image2image/src/README.md)                             |
 | [opea/image2video](https://hub.docker.com/r/opea/image2video)                                                       | [Link](https://github.com/opea-project/GenAIComps/blob/main/comps/image2video/src/Dockerfile)                         | OPEA image-to-video microservice for GenAI application.                                                                                                                                      | [Link](https://github.com/opea-project/GenAIComps/blob/main/comps/image2video/src/README.md)                             |
 | [opea/image2video-gaudi](https://hub.docker.com/r/opea/image2video-gaudi)                                           | [Link](https://github.com/opea-project/GenAIComps/blob/main/comps/image2video/src/Dockerfile.intel_hpu)               | OPEA image-to-video microservice for GenAI application use on the Gaudi.                                                                                                                     | [Link](https://github.com/opea-project/GenAIComps/blob/main/comps/image2video/src/README.md)                             |
-| [opea/ipex-llm]()                                                                                                   | [Link](https://github.com/opea-project/GenAIComps/blob/main/comps/third_parties/ipex/src/Dockerfile)                  | OPEA is a Large Language Model (LLM) service based on intel-extension-for-pytorch. It provides specialized optimizations, including technical points like paged attention, ROPE fusion, etc. | [Link](https://github.com/opea-project/GenAIComps/blob/main/comps/third_parties/ipex/src/README.md)                      |
+| [opea/ipex-llm](https://hub.docker.com/r/opea/ipex-llm)                                                             | [Link](https://github.com/opea-project/GenAIComps/blob/main/comps/third_parties/ipex/src/Dockerfile)                  | OPEA is a Large Language Model (LLM) service based on intel-extension-for-pytorch. It provides specialized optimizations, including technical points like paged attention, ROPE fusion, etc. | [Link](https://github.com/opea-project/GenAIComps/blob/main/comps/third_parties/ipex/src/README.md)                      |
 | [opea/llm-docsum](https://hub.docker.com/r/opea/llm-docsum)                                                         | [Link](https://github.com/opea-project/GenAIComps/blob/main/comps/llms/src/doc-summarization/Dockerfile)              | OPEA LLM microservice upon docsum docker image for GenAI application                                                                                                                         | [Link](https://github.com/opea-project/GenAIComps/blob/main/comps/llms/src/doc-summarization/README.md)                  |
 | [opea/llm-eval](https://hub.docker.com/r/opea/llm-eval)                                                             | [Link](https://github.com/opea-project/GenAIComps/blob/main/comps/llms/utils/lm-eval/Dockerfile)                      | OPEA LLM microservice upon eval docker image for GenAI application                                                                                                                           | [Link](https://github.com/opea-project/GenAIComps/blob/main/comps/llms/utils/lm-eval/README.md)                          |
 | [opea/llm-faqgen](https://hub.docker.com/r/opea/llm-faqgen)                                                         | [Link](https://github.com/opea-project/GenAIComps/blob/main/comps/llms/src/faq-generation/Dockerfile)                 | OPEA FAQ Generation Microservice is designed to generate frequently asked questions from document input using the HuggingFace Text Generation Inference (TGI) framework.                     | [Link](https://github.com/opea-project/GenAIComps/blob/main/comps/llms/src/faq-generation/README.md)                     |
 | [opea/llm-textgen](https://hub.docker.com/r/opea/llm-textgen)                                                       | [Link](https://github.com/opea-project/GenAIComps/blob/main/comps/llms/src/text-generation/Dockerfile)                | OPEA LLM microservice upon textgen docker image for GenAI application                                                                                                                        | [Link](https://github.com/opea-project/GenAIComps/blob/main/comps/llms/src/text-generation/README.md)                    |
 | [opea/llm-textgen-gaudi](https://hub.docker.com/r/opea/llm-textgen-gaudi)                                           | [Link](https://github.com/opea-project/GenAIComps/blob/main/comps/llms/src/text-generation/Dockerfile.intel_hpu)      | OPEA LLM microservice upon textgen docker image for GenAI application use on the Gaudi2                                                                                                      | [Link](https://github.com/opea-project/GenAIComps/blob/main/comps/llms/src/text-generation/README.md)                    |
-| [opea/llm-textgen-phi4-gaudi]()                                                                                     | [Link](https://github.com/opea-project/GenAIComps/blob/main/comps/llms/src/text-generation/Dockerfile.intel_hpu_phi4) | OPEA LLM microservice upon textgen docker image for GenAI application use on the Gaudi2 with Phi4 optimization.                                                                              | [Link](https://github.com/opea-project/GenAIComps/blob/main/comps/llms/src/text-generation/README_native.md)             |
+| [opea/llm-textgen-phi4-gaudi](https://hub.docker.com/r/opea/llm-textgen-phi4-gaudi)                                 | [Link](https://github.com/opea-project/GenAIComps/blob/main/comps/llms/src/text-generation/Dockerfile.intel_hpu_phi4) | OPEA LLM microservice upon textgen docker image for GenAI application use on the Gaudi2 with Phi4 optimization.                                                                              | [Link](https://github.com/opea-project/GenAIComps/blob/main/comps/llms/src/text-generation/README_native.md)             |
 | [opea/lvm](https://hub.docker.com/r/opea/lvm)                                                                       | [Link](https://github.com/opea-project/GenAIComps/blob/main/comps/lvms/src/Dockerfile)                                | OPEA large visual model (LVM) microservice for GenAI application                                                                                                                             | [Link](https://github.com/opea-project/GenAIComps/blob/main/comps/lvms/src/README.md)                                    |
 | [opea/lvm-llama-vision](https://hub.docker.com/r/opea/lvm-llama-vision)                                             | [Link](https://github.com/opea-project/GenAIComps/blob/main/comps/third_parties/llama-vision/src/Dockerfile)          | OPEA microservice running Llama Vision as a large visualization model (LVM) server for GenAI applications                                                                                    | [Link](https://github.com/opea-project/GenAIComps/blob/main/comps/third_parties/llama-vision/src/README.md)              |
 | [opea/lvm-llama-vision-guard](https://hub.docker.com/r/opea/lvm-llama-vision-guard)                                 | [Link](https://github.com/opea-project/GenAIComps/blob/main/comps/third_parties/llama-vision/src/Dockerfile.guard)    | OPEA microservice running Llama Vision Guard as a large visualization model (LVM) server for GenAI applications                                                                              | [Link](https://github.com/opea-project/GenAIComps/blob/main/comps/third_parties/llama-vision/src/README.md)              |
 | [opea/lvm-llama-vision-tp](https://hub.docker.com/r/opea/lvm-llama-vision-tp)                                       | [Link](https://github.com/opea-project/GenAIComps/blob/main/comps/third_parties/llama-vision/src/Dockerfile.tp)       | OPEA microservice running Llama Vision with DeepSpeed as a large visualization model (LVM) server for GenAI applications                                                                     | [Link](https://github.com/opea-project/GenAIComps/blob/main/comps/third_parties/llama-vision/src/README.md)              |
 | [opea/lvm-llava](https://hub.docker.com/r/opea/lvm-llava)                                                           | [Link](https://github.com/opea-project/GenAIComps/blob/main/comps/third_parties/llava/src/Dockerfile)                 | OPEA microservice running LLaVA as a large visualization model (LVM) server for GenAI applications                                                                                           | [Link](https://github.com/opea-project/GenAIComps/blob/main/comps/third_parties/llava/src/README.md)                     |
-| [opea/lvm-llava-gaudi]()                                                                                            | [Link](https://github.com/opea-project/GenAIComps/blob/main/comps/third_parties/llava/src/Dockerfile.intel_hpu)       | OPEA microservice running LLaVA as a large visualization model (LVM) server for GenAI applications on the Gaudi2                                                                             | [Link](https://github.com/opea-project/GenAIComps/blob/main/comps/third_parties/llava/src/README.md)                     |
+| [opea/lvm-llava-gaudi](https://hub.docker.com/r/opea/lvm-llava-gaudi)                                               | [Link](https://github.com/opea-project/GenAIComps/blob/main/comps/third_parties/llava/src/Dockerfile.intel_hpu)       | OPEA microservice running LLaVA as a large visualization model (LVM) server for GenAI applications on the Gaudi2                                                                             | [Link](https://github.com/opea-project/GenAIComps/blob/main/comps/third_parties/llava/src/README.md)                     |
 | [opea/lvm-predictionguard](https://hub.docker.com/r/opea/lvm-predictionguard)                                       | [Link](https://github.com/opea-project/GenAIComps/blob/main/comps/third_parties/predictionguard/src/Dockerfile)       | OPEA microservice running PredictionGuard as a large visualization model (LVM) server for GenAI applications                                                                                 | [Link](https://github.com/opea-project/GenAIComps/blob/main/comps/third_parties/predictionguard/src/README.md)           |
 | [opea/lvm-video-llama](https://hub.docker.com/r/opea/lvm-video-llama)                                               | [Link](https://github.com/opea-project/GenAIComps/blob/main/comps/third_parties/video-llama/src/Dockerfile)           | OPEA microservice running Video-Llama as a large visualization model (LVM) server for GenAI applications                                                                                     | [Link](https://github.com/opea-project/GenAIComps/blob/main/comps/third_parties/video-llama/src/README.md)               |
 | [opea/nginx](https://hub.docker.com/r/opea/nginx)                                                                   | [Link](https://github.com/opea-project/GenAIComps/blob/main/comps/third_parties/nginx/src/Dockerfile)                 | OPEA nginx microservice for GenAI application                                                                                                                                                | [Link](https://github.com/opea-project/GenAIComps/blob/main/comps/third_parties/nginx/deployment/kubernetes/README.md)   |
@@ -98,20 +98,20 @@ Take ChatQnA for example. ChatQnA is a chatbot application service based on the
 | [opea/retriever](https://hub.docker.com/r/opea/retriever)                                                           | [Link](https://github.com/opea-project/GenAIComps/blob/main/comps/retrievers/src/Dockerfile)                          | OPEA retrieval microservice for GenAI application                                                                                                                                            | [Link](https://github.com/opea-project/GenAIComps/blob/main/comps/retrievers/README.md)                                  |
 | [opea/speecht5](https://hub.docker.com/r/opea/speecht5)                                                             | [Link](https://github.com/opea-project/GenAIComps/blob/main/comps/third_parties/speecht5/src/Dockerfile)              | OPEA SpeechT5 service for GenAI application                                                                                                                                                  | [Link](https://github.com/opea-project/GenAIComps/blob/main/comps/tts/src/README.md)                                     |
 | [opea/speecht5-gaudi](https://hub.docker.com/r/opea/speecht5-gaudi)                                                 | [Link](https://github.com/opea-project/GenAIComps/blob/main/comps/third_parties/speecht5/src/Dockerfile.intel_hpu)    | OPEA SpeechT5 service on the Gaudi2 for GenAI application                                                                                                                                    | [Link](https://github.com/opea-project/GenAIComps/blob/main/comps/tts/src/README.md)                                     |
-| [opea/struct2graph]()                                                                                               | [Link](https://github.com/opea-project/GenAIComps/blob/main/comps/struct2graph/src/Dockerfile)                        | OPEA struct-to-graph service for GenAI application                                                                                                                                           | [Link](https://github.com/opea-project/GenAIComps/blob/main/comps/struct2graph/src/README.md)                            |
+| [opea/struct2graph](https://hub.docker.com/r/opea/struct2graph)                                                     | [Link](https://github.com/opea-project/GenAIComps/blob/main/comps/struct2graph/src/Dockerfile)                        | OPEA struct-to-graph service for GenAI application                                                                                                                                           | [Link](https://github.com/opea-project/GenAIComps/blob/main/comps/struct2graph/src/README.md)                            |
 | [opea/text2cypher-gaudi]()                                                                                          | [Link](https://github.com/opea-project/GenAIComps/blob/main/comps/text2cypher/src/Dockerfile.intel_hpu)               | OPEA Text-to-Cypher microservice for GenAI application use on the Gaudi2.                                                                                                                    | [Link](https://github.com/opea-project/GenAIComps/blob/main/comps/text2cypher/src/README.md)                             |
-| [opea/text2graph]()                                                                                                 | [Link](https://github.com/opea-project/GenAIComps/blob/main/comps/text2graph/src/Dockerfile)                          | OPEA Text-to-Graph microservice for GenAI application                                                                                                                                        | [Link](https://github.com/opea-project/GenAIComps/blob/main/comps/text2graph/src/README.md)                              |
+| [opea/text2graph](https://hub.docker.com/r/opea/text2graph)                                                         | [Link](https://github.com/opea-project/GenAIComps/blob/main/comps/text2graph/src/Dockerfile)                          | OPEA Text-to-Graph microservice for GenAI application                                                                                                                                        | [Link](https://github.com/opea-project/GenAIComps/blob/main/comps/text2graph/src/README.md)                              |
 | [opea/text2image](https://hub.docker.com/r/opea/text2image)                                                         | [Link](https://github.com/opea-project/GenAIComps/blob/main/comps/text2image/src/Dockerfile)                          | OPEA text-to-image microservice for GenAI application                                                                                                                                        | [Link](https://github.com/opea-project/GenAIComps/blob/main/comps/text2image/src/README.md)                              |
 | [opea/text2image-gaudi](https://hub.docker.com/r/opea/text2image-gaudi)                                             | [Link](https://github.com/opea-project/GenAIComps/blob/main/comps/text2image/src/Dockerfile.intel_hpu)                | OPEA text-to-image microservice for GenAI application use on the Gaudi                                                                                                                       | [Link](https://github.com/opea-project/GenAIComps/blob/main/comps/text2image/src/README.md)                              |
 | [opea/text2image-ui](https://hub.docker.com/r/opea/text2image-ui)                                                   | [Link](https://github.com/opea-project/GenAIExamples/blob/main/Text2Image/ui/docker/Dockerfile)                       | OPEA text-to-image microservice UI entry for GenAI application                                                                                                                               | [Link](https://github.com/opea-project/GenAIExamples/blob/main/Text2Image/README.md)                                     |
 | [opea/text2sql](https://hub.docker.com/r/opea/text2sql)                                                             | [Link](https://github.com/opea-project/GenAIComps/blob/main/comps/text2sql/src/Dockerfile)                            | OPEA text to Structured Query Language microservice for GenAI application                                                                                                                    | [Link](https://github.com/opea-project/GenAIComps/blob/main/comps/text2sql/src/README.md)                                |
 | [opea/text2sql-react-ui](https://hub.docker.com/r/opea/text2sql-react-ui)                                           | [Link](https://github.com/opea-project/GenAIExamples/blob/main/DBQnA/ui/docker/Dockerfile.react)                      | OPEA text to Structured Query Language microservice react UI entry for GenAI application                                                                                                     | [Link](https://github.com/opea-project/GenAIExamples/blob/main/DBQnA/README.md)                                          |
 | [opea/tts](https://hub.docker.com/r/opea/tts)                                                                       | [Link](https://github.com/opea-project/GenAIComps/blob/main/comps/tts/src/Dockerfile)                                 | OPEA Text-To-Speech microservice for GenAI application                                                                                                                                       | [Link](https://github.com/opea-project/GenAIComps/blob/main/comps/tts/src/README.md)                                     |
-| [opea/vllm](https://hub.docker.com/r/opea/vllm)                                                                     | [Link](https://github.com/HabanaAI/vllm-fork/blob/habana_main/Dockerfile.cpu)                                         | Deploying and servicing VLLM models based on VLLM projects                                                                                                                                   | [Link](https://github.com/HabanaAI/vllm-fork/blob/habana_main/README.md)                                                 |
+| [opea/vllm](https://hub.docker.com/r/opea/vllm)                                                                     | [Link](https://github.com/vllm-project/vllm/blob/v0.8.3/docker/Dockerfile.cpu)                                        | Deploying and servicing VLLM models based on VLLM projects                                                                                                                                   | [Link](https://github.com/vllm-project/vllm/blob/v0.8.3/README.md)                                                       |
 | [opea/vllm-arc](https://hub.docker.com/r/opea/vllm-arc)                                                             | [Link](https://github.com/opea-project/GenAIComps/blob/main/comps/third_parties/vllm/src/Dockerfile.intel_gpu)        | Deploying and servicing VLLM models on Arc based on VLLM projects                                                                                                                            | [Link](https://github.com/opea-project/GenAIComps/blob/main/comps/third_parties/vllm/README.md)                          |
 | [opea/vllm-gaudi](https://hub.docker.com/r/opea/vllm-gaudi)                                                         | [Link](https://github.com/HabanaAI/vllm-fork/blob/v0.6.6.post1%2BGaudi-1.20.0/Dockerfile.hpu)                         | Deploying and servicing VLLM models on Gaudi2 based on VLLM project                                                                                                                          | [Link](https://github.com/HabanaAI/vllm-fork/blob/habana_main/README.md)                                                 |
 | [opea/vllm-openvino](https://hub.docker.com/r/opea/vllm-openvino)                                                   | [Link](https://github.com/vllm-project/vllm/blob/v0.6.1/Dockerfile.openvino)                                          | VLLM Model for Deploying and Serving Openvino Framework Based on VLLM Project                                                                                                                | [Link](https://github.com/vllm-project/vllm/blob/main/README.md)                                                         |
-| [opea/vllm-rocm]()                                                                                                  | [Link](https://github.com/opea-project/GenAIComps/blob/main/comps/third_parties/vllm/src/Dockerfile.amd_gpu)          | Deploying and servicing VLLM models on AMD Rocm based on VLLM project                                                                                                                        |                                                                                                                          |
+| [opea/vllm-rocm](https://hub.docker.com/r/opea/vllm-rocm)                                                           | [Link](https://github.com/opea-project/GenAIComps/blob/main/comps/third_parties/vllm/src/Dockerfile.amd_gpu)          | Deploying and servicing VLLM models on AMD Rocm based on VLLM project                                                                                                                        |                                                                                                                          |
 | [opea/wav2lip](https://hub.docker.com/r/opea/wav2lip)                                                               | [Link](https://github.com/opea-project/GenAIComps/blob/main/comps/third_parties/wav2lip/src/Dockerfile)               | OPEA Generate lip movements from audio files microservice with Pathway for GenAI application                                                                                                 | [Link](https://github.com/opea-project/GenAIComps/blob/main/comps/third_parties/wav2lip/deployment/kubernetes/README.md) |
 | [opea/wav2lip-gaudi](https://hub.docker.com/r/opea/wav2lip-gaudi)                                                   | [Link](https://github.com/opea-project/GenAIComps/blob/main/comps/third_parties/wav2lip/src/Dockerfile.intel_hpu)     | OPEA Generate lip movements from audio files microservice with Pathway for GenAI application use on the Gaudi2                                                                               | [Link](https://github.com/opea-project/GenAIComps/blob/main/comps/third_parties/wav2lip/deployment/kubernetes/README.md) |
 | [opea/web-retriever](https://hub.docker.com/r/opea/web-retriever)<br>                                               | [Link](https://github.com/opea-project/GenAIComps/blob/main/comps/web_retrievers/src/Dockerfile)                      | OPEA retrieval microservice based on chroma vectordb for GenAI application                                                                                                                   | [Link](https://github.com/opea-project/GenAIComps/blob/main/comps/web_retrievers/src/README.md)                          |

requirements.txt

@@ -1,7 +1,7 @@
 kubernetes
 locust
 numpy
-opea-eval>=1.2
+opea-eval>=1.3
 prometheus_client
 pytest
 pyyaml

version.txt

@@ -0,0 +1,3 @@
+VERSION_MAJOR 1
+VERSION_MINOR 3
+VERSION_PATCH 0