Provide unified scalable deployment and benchmarking support for exam… (#1315)

Signed-off-by: Cathy Zhang <cathy.zhang@intel.com>
Signed-off-by: letonghan <letong.han@intel.com>
Co-authored-by: letonghan <letong.han@intel.com>
Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com>
(cherry picked from commit ed163087ba)

.github/workflows/_example-workflow.yml

@@ -79,6 +79,7 @@ jobs:
           fi
           if [[ $(grep -c "vllm-gaudi:" ${docker_compose_path}) != 0 ]]; then
               git clone --depth 1 --branch v0.6.4.post2+Gaudi-1.19.0 https://github.com/HabanaAI/vllm-fork.git
+              sed -i 's/triton/triton==3.1.0/g' vllm-fork/requirements-hpu.txt
           fi
           git clone --depth 1 --branch ${{ inputs.opea_branch }} https://github.com/opea-project/GenAIComps.git
           cd GenAIComps && git rev-parse HEAD && cd ../

.github/workflows/_helm-e2e.yml

@@ -97,7 +97,6 @@ jobs:
 
   helm-test:
     needs: [get-test-case]
-    if: ${{ fromJSON(needs.get-test-case.outputs.value_files).length != 0 }}
     strategy:
       matrix:
         value_file: ${{ fromJSON(needs.get-test-case.outputs.value_files) }}

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

@@ -91,7 +91,6 @@ jobs:
 
   compose-test:
     needs: [get-test-case]
-    if: ${{ needs.get-test-case.outputs.test_cases != '' }}
     strategy:
       matrix:
         test_case: ${{ fromJSON(needs.get-test-case.outputs.test_cases) }}
@@ -127,7 +126,6 @@ jobs:
         shell: bash
         env:
           HUGGINGFACEHUB_API_TOKEN: ${{ secrets.HUGGINGFACEHUB_API_TOKEN }}
-          HF_TOKEN: ${{ secrets.HUGGINGFACEHUB_API_TOKEN }}
           GOOGLE_CSE_ID: ${{ secrets.GOOGLE_CSE_ID }}
           GOOGLE_API_KEY: ${{ secrets.GOOGLE_API_KEY }}
           PINECONE_KEY: ${{ secrets.PINECONE_KEY }}

.github/workflows/manual-docker-publish.yml

@@ -41,11 +41,9 @@ jobs:
 
   publish:
     needs: [get-image-list]
-    if: ${{ needs.get-image-list.outputs.matrix != '' }}
     strategy:
       matrix:
         image: ${{ fromJSON(needs.get-image-list.outputs.matrix) }}
-      fail-fast: false
     runs-on: "docker-build-${{ inputs.node }}"
     steps:
       - uses: docker/login-action@v3.2.0

.github/workflows/manual-docker-scan.yml

@@ -47,7 +47,6 @@ jobs:
   scan-docker:
     needs: get-image-list
     runs-on: "docker-build-${{ inputs.node }}"
-    if: ${{ fromJSON(needs.get-image-list.outputs.matrix).length != 0 }}
     strategy:
       matrix:
         image: ${{ fromJson(needs.get-image-list.outputs.matrix) }}

.github/workflows/manual-example-workflow.yml

@@ -76,7 +76,7 @@ jobs:
 
   build-deploy-gmc:
     needs: [get-test-matrix]
-    if: ${{ fromJSON(inputs.deploy_gmc) }} && ${{ fromJSON(needs.get-test-matrix.outputs.nodes).length != 0 }}
+    if: ${{ fromJSON(inputs.deploy_gmc) }}
     strategy:
       matrix:
         node: ${{ fromJson(needs.get-test-matrix.outputs.nodes) }}
@@ -90,7 +90,7 @@ jobs:
 
   run-examples:
     needs: [get-test-matrix, build-deploy-gmc]
-    if: always() && ${{ fromJSON(needs.get-test-matrix.outputs.examples).length != 0 }}
+    if: always()
     strategy:
       matrix:
         example: ${{ fromJson(needs.get-test-matrix.outputs.examples) }}

.github/workflows/manual-freeze-tag.yml

@@ -25,9 +25,9 @@ jobs:
 
       - name: Set up Git
         run: |
-          git config --global user.name "CICD-at-OPEA"
-          git config --global user.email "CICD@opea.dev"
-          git remote set-url origin https://CICD-at-OPEA:"${{ secrets.ACTION_TOKEN }}"@github.com/opea-project/GenAIExamples.git
+          git config --global user.name "NeuralChatBot"
+          git config --global user.email "grp_neural_chat_bot@intel.com"
+          git remote set-url origin https://NeuralChatBot:"${{ secrets.ACTION_TOKEN }}"@github.com/opea-project/GenAIExamples.git
 
       - name: Run script
         run: |

.github/workflows/manual-image-build.yml

@@ -51,7 +51,6 @@ jobs:
 
   image-build:
     needs: get-test-matrix
-    if: ${{ needs.get-test-matrix.outputs.nodes != '' }}
     strategy:
       matrix:
         node: ${{ fromJson(needs.get-test-matrix.outputs.nodes) }}

.github/workflows/manual-reset-local-registry.yml

@@ -33,7 +33,6 @@ jobs:
 
   clean-up:
     needs: get-build-matrix
-    if: ${{ fromJSON(needs.get-build-matrix.outputs.nodes).length != 0 }}
     strategy:
       matrix:
         node: ${{ fromJson(needs.get-build-matrix.outputs.nodes) }}
@@ -48,7 +47,6 @@ jobs:
 
   build:
     needs: [get-build-matrix, clean-up]
-    if: ${{ fromJSON(needs.get-build-matrix.outputs.nodes).length != 0 }}
     strategy:
       matrix:
         example: ${{ fromJson(needs.get-build-matrix.outputs.examples) }}

.github/workflows/nightly-docker-build-publish.yml

@@ -34,7 +34,6 @@ jobs:
 
   build-and-test:
     needs: get-build-matrix
-    if: ${{ needs.get-build-matrix.outputs.examples_json != '' }}
     strategy:
       matrix:
         example: ${{ fromJSON(needs.get-build-matrix.outputs.examples_json) }}
@@ -54,11 +53,9 @@ jobs:
 
   publish:
     needs: [get-build-matrix, get-image-list, build-and-test]
-    if: ${{ needs.get-image-list.outputs.matrix != '' }}
     strategy:
       matrix:
         image: ${{ fromJSON(needs.get-image-list.outputs.matrix) }}
-      fail-fast: false
     runs-on: "docker-build-gaudi"
     steps:
       - uses: docker/login-action@v3.2.0

.github/workflows/pr-chart-e2e.yml

@@ -65,7 +65,7 @@ jobs:
 
   helm-chart-test:
     needs: [job1]
-    if: always() && ${{ fromJSON(needs.job1.outputs.run_matrix).length != 0 }}
+    if: always() && ${{ needs.job1.outputs.run_matrix.example.length > 0 }}
     uses: ./.github/workflows/_helm-e2e.yml
     strategy:
       matrix: ${{ fromJSON(needs.job1.outputs.run_matrix) }}

.github/workflows/pr-docker-compose-e2e.yml

@@ -32,10 +32,10 @@ jobs:
 
   example-test:
     needs: [get-test-matrix]
-    if: ${{ needs.get-test-matrix.outputs.run_matrix != '' }}
     strategy:
       matrix: ${{ fromJSON(needs.get-test-matrix.outputs.run_matrix) }}
       fail-fast: false
+    if: ${{ !github.event.pull_request.draft }}
     uses: ./.github/workflows/_run-docker-compose.yml
     with:
       registry: "opea"

.github/workflows/push-image-build.yml

@@ -24,7 +24,6 @@ jobs:
 
   image-build:
     needs: job1
-    if: ${{ fromJSON(needs.job1.outputs.run_matrix).length != 0 }}
     strategy:
       matrix: ${{ fromJSON(needs.job1.outputs.run_matrix) }}
       fail-fast: false

.github/workflows/weekly-update-images.yml

@@ -16,8 +16,8 @@ jobs:
   freeze-images:
     runs-on: ubuntu-latest
     env:
-      USER_NAME: "CICD-at-OPEA"
-      USER_EMAIL: "CICD@opea.dev"
+      USER_NAME: "NeuralChatBot"
+      USER_EMAIL: "grp_neural_chat_bot@intel.com"
       BRANCH_NAME: "update_images_tag"
     steps:
       - name: Checkout repository

AgentQnA/tests/step1_build_images.sh

@@ -43,6 +43,7 @@ function build_vllm_docker_image() {
     fi
     cd ./vllm-fork
     git checkout v0.6.4.post2+Gaudi-1.19.0
+    sed -i 's/triton/triton==3.1.0/g' requirements-hpu.txt
     docker build --no-cache -f Dockerfile.hpu -t opea/vllm-gaudi:ci --shm-size=128g . --build-arg https_proxy=$https_proxy --build-arg http_proxy=$http_proxy
     if [ $? -ne 0 ]; then
         echo "opea/vllm-gaudi:ci failed"

AgentQnA/ui/svelte/README.md

@@ -18,7 +18,7 @@ Here're some of the project's features:
 2. cd command to the current folder.
 
    ```
-   cd AgentQnA/ui/svelte
+   cd AgentQnA/ui
    ```
 
 3. Modify the required .env variables.
@@ -41,7 +41,7 @@ Here're some of the project's features:
   npm run dev
   ```
 
-- The application will be available at `http://localhost:5173`.
+- The application will be available at `http://localhost:3000`.
 
 5. **For Docker Setup:**
 
@@ -54,7 +54,7 @@ Here're some of the project's features:
 - Run the Docker container:
 
   ```
-  docker run -d -p 5173:5173 --name agent-ui opea:agent-ui
+  docker run -d -p 3000:3000 --name agent-ui opea:agent-ui
   ```
 
-- The application will be available at `http://localhost:5173`.
+- The application will be available at `http://localhost:3000`.

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

@@ -1,209 +0,0 @@
-# Build Mega Service of AvatarChatbot on AMD GPU
-
-This document outlines the deployment process for a AvatarChatbot application utilizing the [GenAIComps](https://github.com/opea-project/GenAIComps.git) microservice pipeline on Intel Xeon server.
-
-## 🚀 Build Docker images
-
-### 1. Source Code install GenAIComps
-
-```bash
-git clone https://github.com/opea-project/GenAIComps.git
-cd GenAIComps
-```
-
-### 2. Build ASR Image
-
-```bash
-docker build -t opea/whisper:latest --build-arg https_proxy=$https_proxy --build-arg http_proxy=$http_proxy -f comps/asr/src/integrations/dependency/whisper/Dockerfile .
-
-
-docker build -t opea/asr:latest --build-arg https_proxy=$https_proxy --build-arg http_proxy=$http_proxy -f comps/asr/src/Dockerfile .
-```
-
-### 3. Build LLM Image
-
-```bash
-docker build --no-cache -t opea/llm-textgen:latest --build-arg https_proxy=$https_proxy --build-arg http_proxy=$http_proxy -f comps/llms/src/text-generation/Dockerfile .
-```
-
-### 4. Build TTS Image
-
-```bash
-docker build -t opea/speecht5:latest --build-arg https_proxy=$https_proxy --build-arg http_proxy=$http_proxy -f comps/tts/src/integrations/dependency/speecht5/Dockerfile .
-
-docker build -t opea/tts:latest --build-arg https_proxy=$https_proxy --build-arg http_proxy=$http_proxy -f comps/tts/src/Dockerfile .
-```
-
-### 5. Build Animation Image
-
-```bash
-docker build -t opea/wav2lip:latest --build-arg https_proxy=$https_proxy --build-arg http_proxy=$http_proxy -f comps/third_parties/wav2lip/src/Dockerfile .
-
-docker build -t opea/animation:latest --build-arg https_proxy=$https_proxy --build-arg http_proxy=$http_proxy -f comps/animation/src/Dockerfile .
-```
-
-### 6. Build MegaService Docker Image
-
-To construct the Mega Service, we utilize the [GenAIComps](https://github.com/opea-project/GenAIComps.git) microservice pipeline within the `audioqna.py` Python script. Build the MegaService Docker image using the command below:
-
-```bash
-git clone https://github.com/opea-project/GenAIExamples.git
-cd GenAIExamples/AvatarChatbot/
-docker build --no-cache -t opea/avatarchatbot:latest --build-arg https_proxy=$https_proxy --build-arg http_proxy=$http_proxy -f Dockerfile .
-```
-
-Then run the command `docker images`, you will have following images ready:
-
-1. `opea/whisper:latest`
-2. `opea/asr:latest`
-3. `opea/llm-tgi:latest`
-4. `opea/speecht5:latest`
-5. `opea/tts:latest`
-6. `opea/wav2lip:latest`
-7. `opea/animation:latest`
-8. `opea/avatarchatbot:latest`
-
-## 🚀 Set the environment variables
-
-Before starting the services with `docker compose`, you have to recheck the following environment variables.
-
-```bash
-export HUGGINGFACEHUB_API_TOKEN=${HUGGINGFACEHUB_API_TOKEN}
-export host_ip=$(hostname -I | awk '{print $1}')
-
-export TGI_SERVICE_PORT=3006
-export TGI_LLM_ENDPOINT=http://${host_ip}:${TGI_SERVICE_PORT}
-export LLM_MODEL_ID="Intel/neural-chat-7b-v3-3"
-
-export ASR_ENDPOINT=http://${host_ip}:7066
-export TTS_ENDPOINT=http://${host_ip}:7055
-export WAV2LIP_ENDPOINT=http://${host_ip}:7860
-
-export MEGA_SERVICE_HOST_IP=${host_ip}
-export ASR_SERVICE_HOST_IP=${host_ip}
-export TTS_SERVICE_HOST_IP=${host_ip}
-export LLM_SERVICE_HOST_IP=${host_ip}
-export ANIMATION_SERVICE_HOST_IP=${host_ip}
-
-export MEGA_SERVICE_PORT=8888
-export ASR_SERVICE_PORT=3001
-export TTS_SERVICE_PORT=3002
-export LLM_SERVICE_PORT=3007
-export ANIMATION_SERVICE_PORT=3008
-
-export DEVICE="cpu"
-export WAV2LIP_PORT=7860
-export INFERENCE_MODE='wav2lip+gfpgan'
-export CHECKPOINT_PATH='/usr/local/lib/python3.11/site-packages/Wav2Lip/checkpoints/wav2lip_gan.pth'
-export FACE="assets/img/avatar5.png"
-# export AUDIO='assets/audio/eg3_ref.wav' # audio file path is optional, will use base64str in the post request as input if is 'None'
-export AUDIO='None'
-export FACESIZE=96
-export OUTFILE="/outputs/result.mp4"
-export GFPGAN_MODEL_VERSION=1.4 # latest version, can roll back to v1.3 if needed
-export UPSCALE_FACTOR=1
-export FPS=10
-```
-
-Warning!!! - The Wav2lip service works in this solution using only the CPU. To use AMD GPUs and achieve operational performance, the Wav2lip image needs to be modified to adapt to AMD hardware and the ROCm framework.
-
-## 🚀 Start the MegaService
-
-```bash
-cd GenAIExamples/AvatarChatbot/docker_compose/intel/cpu/xeon/
-docker compose -f compose.yaml up -d
-```
-
-## 🚀 Test MicroServices
-
-```bash
-# whisper service
-curl http://${host_ip}:7066/v1/asr \
-  -X POST \
-  -d '{"audio": "UklGRigAAABXQVZFZm10IBIAAAABAAEARKwAAIhYAQACABAAAABkYXRhAgAAAAEA"}' \
-  -H 'Content-Type: application/json'
-
-# asr microservice
-curl http://${host_ip}:3001/v1/audio/transcriptions \
-  -X POST \
-  -d '{"byte_str": "UklGRigAAABXQVZFZm10IBIAAAABAAEARKwAAIhYAQACABAAAABkYXRhAgAAAAEA"}' \
-  -H 'Content-Type: application/json'
-
-# tgi service
-curl http://${host_ip}:3006/generate \
-  -X POST \
-  -d '{"inputs":"What is Deep Learning?","parameters":{"max_new_tokens":17, "do_sample": true}}' \
-  -H 'Content-Type: application/json'
-
-# llm microservice
-curl http://${host_ip}:3007/v1/chat/completions\
-  -X POST \
-  -d '{"query":"What is Deep Learning?","max_tokens":17,"top_k":10,"top_p":0.95,"typical_p":0.95,"temperature":0.01,"repetition_penalty":1.03,"streaming":false}' \
-  -H 'Content-Type: application/json'
-
-# speecht5 service
-curl http://${host_ip}:7055/v1/tts \
-  -X POST \
-  -d '{"text": "Who are you?"}' \
-  -H 'Content-Type: application/json'
-
-# tts microservice
-curl http://${host_ip}:3002/v1/audio/speech \
-  -X POST \
-  -d '{"text": "Who are you?"}' \
-  -H 'Content-Type: application/json'
-
-# wav2lip service
-cd ../../../..
-curl http://${host_ip}:7860/v1/wav2lip \
-  -X POST \
-  -d @assets/audio/sample_minecraft.json \
-  -H 'Content-Type: application/json'
-
-# animation microservice
-curl http://${host_ip}:3008/v1/animation \
-  -X POST \
-  -d @assets/audio/sample_question.json \
-  -H "Content-Type: application/json"
-
-```
-
-## 🚀 Test MegaService
-
-```bash
-curl http://${host_ip}:3009/v1/avatarchatbot \
-  -X POST \
-  -d @assets/audio/sample_whoareyou.json \
-  -H 'Content-Type: application/json'
-```
-
-If the megaservice is running properly, you should see the following output:
-
-```bash
-"/outputs/result.mp4"
-```
-
-The output file will be saved in the current working directory, as `${PWD}` is mapped to `/outputs` inside the wav2lip-service Docker container.
-
-## Gradio UI
-
-```bash
-cd $WORKPATH/GenAIExamples/AvatarChatbot
-python3 ui/gradio/app_gradio_demo_avatarchatbot.py
-```
-
-The UI can be viewed at http://${host_ip}:7861  
-<img src="../../../../assets/img/UI.png" alt="UI Example" width="60%">  
-In the current version v1.0, you need to set the avatar figure image/video and the DL model choice in the environment variables before starting AvatarChatbot backend service and running the UI. Please just customize the audio question in the UI.  
-\*\* We will enable change of avatar figure between runs in v2.0
-
-## Troubleshooting
-
-```bash
-cd GenAIExamples/AvatarChatbot/tests
-export IMAGE_REPO="opea"
-export IMAGE_TAG="latest"
-export HUGGINGFACEHUB_API_TOKEN=<your_hf_token>
-
-test_avatarchatbot_on_xeon.sh
-```

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

@@ -1,158 +0,0 @@
-
-# Copyright (C) 2024 Intel Corporation
-# SPDX-License-Identifier: Apache-2.0
-
-services:
-  whisper-service:
-    image: ${REGISTRY:-opea}/whisper:${TAG:-latest}
-    container_name: whisper-service
-    ports:
-      - "7066:7066"
-    ipc: host
-    environment:
-      no_proxy: ${no_proxy}
-      http_proxy: ${http_proxy}
-      https_proxy: ${https_proxy}
-    restart: unless-stopped
-  asr:
-    image: ${REGISTRY:-opea}/asr:${TAG:-latest}
-    container_name: asr-service
-    ports:
-      - "3001:9099"
-    ipc: host
-    environment:
-      ASR_ENDPOINT: ${ASR_ENDPOINT}
-  speecht5-service:
-    image: ${REGISTRY:-opea}/speecht5:${TAG:-latest}
-    container_name: speecht5-service
-    ports:
-      - "7055:7055"
-    ipc: host
-    environment:
-      no_proxy: ${no_proxy}
-      http_proxy: ${http_proxy}
-      https_proxy: ${https_proxy}
-    restart: unless-stopped
-  tts:
-    image: ${REGISTRY:-opea}/tts:${TAG:-latest}
-    container_name: tts-service
-    ports:
-      - "3002:9088"
-    ipc: host
-    environment:
-      TTS_ENDPOINT: ${TTS_ENDPOINT}
-  tgi-service:
-    image: ghcr.io/huggingface/text-generation-inference:2.3.1-rocm
-    container_name: tgi-service
-    ports:
-      - "${TGI_SERVICE_PORT:-3006}:80"
-    volumes:
-      - "./data:/data"
-    environment:
-      no_proxy: ${no_proxy}
-      http_proxy: ${http_proxy}
-      https_proxy: ${https_proxy}
-      HUGGING_FACE_HUB_TOKEN: ${HUGGINGFACEHUB_API_TOKEN}
-      HUGGINGFACEHUB_API_TOKEN: ${HUGGINGFACEHUB_API_TOKEN}
-    shm_size: 1g
-    devices:
-      - /dev/kfd:/dev/kfd
-      - /dev/dri/:/dev/dri/
-    cap_add:
-      - SYS_PTRACE
-    group_add:
-      - video
-    security_opt:
-      - 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
-    ports:
-      - "7860:7860"
-    ipc: host
-    volumes:
-      - ${PWD}:/outputs
-    environment:
-      no_proxy: ${no_proxy}
-      http_proxy: ${http_proxy}
-      https_proxy: ${https_proxy}
-      DEVICE: ${DEVICE}
-      INFERENCE_MODE: ${INFERENCE_MODE}
-      CHECKPOINT_PATH: ${CHECKPOINT_PATH}
-      FACE: ${FACE}
-      AUDIO: ${AUDIO}
-      FACESIZE: ${FACESIZE}
-      OUTFILE: ${OUTFILE}
-      GFPGAN_MODEL_VERSION: ${GFPGAN_MODEL_VERSION}
-      UPSCALE_FACTOR: ${UPSCALE_FACTOR}
-      FPS: ${FPS}
-      WAV2LIP_PORT: ${WAV2LIP_PORT}
-    restart: unless-stopped
-  animation:
-    image: ${REGISTRY:-opea}/animation:${TAG:-latest}
-    container_name: animation-server
-    ports:
-      - "3008:9066"
-    ipc: host
-    environment:
-      no_proxy: ${no_proxy}
-      http_proxy: ${http_proxy}
-      https_proxy: ${https_proxy}
-      WAV2LIP_ENDPOINT: ${WAV2LIP_ENDPOINT}
-    restart: unless-stopped
-  avatarchatbot-backend-server:
-    image: ${REGISTRY:-opea}/avatarchatbot:${TAG:-latest}
-    container_name: avatarchatbot-backend-server
-    depends_on:
-      - asr
-      - llm
-      - tts
-      - animation
-    ports:
-      - "3009:8888"
-    environment:
-      no_proxy: ${no_proxy}
-      https_proxy: ${https_proxy}
-      http_proxy: ${http_proxy}
-      MEGA_SERVICE_HOST_IP: ${MEGA_SERVICE_HOST_IP}
-      MEGA_SERVICE_PORT: ${MEGA_SERVICE_PORT}
-      ASR_SERVICE_HOST_IP: ${ASR_SERVICE_HOST_IP}
-      ASR_SERVICE_PORT: ${ASR_SERVICE_PORT}
-      LLM_SERVICE_HOST_IP: ${LLM_SERVICE_HOST_IP}
-      LLM_SERVICE_PORT: ${LLM_SERVICE_PORT}
-      LLM_SERVER_HOST_IP: ${LLM_SERVICE_HOST_IP}
-      LLM_SERVER_PORT: ${LLM_SERVICE_PORT}
-      TTS_SERVICE_HOST_IP: ${TTS_SERVICE_HOST_IP}
-      TTS_SERVICE_PORT: ${TTS_SERVICE_PORT}
-      ANIMATION_SERVICE_HOST_IP: ${ANIMATION_SERVICE_HOST_IP}
-      ANIMATION_SERVICE_PORT: ${ANIMATION_SERVICE_PORT}
-      WHISPER_SERVER_HOST_IP: ${WHISPER_SERVER_HOST_IP}
-      WHISPER_SERVER_PORT: ${WHISPER_SERVER_PORT}
-      SPEECHT5_SERVER_HOST_IP: ${SPEECHT5_SERVER_HOST_IP}
-      SPEECHT5_SERVER_PORT: ${SPEECHT5_SERVER_PORT}
-    ipc: host
-    restart: always
-
-networks:
-  default:
-    driver: bridge

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

@@ -1,47 +0,0 @@
-#!/usr/bin/env bash
-
-# Copyright (C) 2024 Intel Corporation
-# SPDX-License-Identifier: Apache-2.0
-
-export HUGGINGFACEHUB_API_TOKEN=${HUGGINGFACEHUB_API_TOKEN}
-export OPENAI_API_KEY=${OPENAI_API_KEY}
-export host_ip=$(hostname -I | awk '{print $1}')
-
-export TGI_SERVICE_PORT=3006
-export TGI_LLM_ENDPOINT=http://${host_ip}:${TGI_SERVICE_PORT}
-export LLM_MODEL_ID="Intel/neural-chat-7b-v3-3"
-
-export ASR_ENDPOINT=http://${host_ip}:7066
-export TTS_ENDPOINT=http://${host_ip}:7055
-export WAV2LIP_ENDPOINT=http://${host_ip}:7860
-
-export WHISPER_SERVER_HOST_IP=${host_ip}
-export WHISPER_SERVER_PORT=7066
-
-export SPEECHT5_SERVER_HOST_IP=${host_ip}
-export SPEECHT5_SERVER_PORT=7055
-
-export MEGA_SERVICE_HOST_IP=${host_ip}
-export ASR_SERVICE_HOST_IP=${host_ip}
-export TTS_SERVICE_HOST_IP=${host_ip}
-export LLM_SERVICE_HOST_IP=${host_ip}
-export 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 ANIMATION_SERVICE_PORT=3008
-
-export DEVICE="cpu"
-export WAV2LIP_PORT=7860
-export INFERENCE_MODE='wav2lip+gfpgan'
-export CHECKPOINT_PATH='/usr/local/lib/python3.11/site-packages/Wav2Lip/checkpoints/wav2lip_gan.pth'
-export FACE="/home/user/comps/animation/src/assets/img/avatar5.png"
-# export AUDIO='assets/audio/eg3_ref.wav' # audio file path is optional, will use base64str in the post request as input if is 'None'
-export AUDIO='None'
-export FACESIZE=96
-export OUTFILE="/outputs/result.mp4"
-export GFPGAN_MODEL_VERSION=1.4 # latest version, can roll back to v1.3 if needed
-export UPSCALE_FACTOR=1
-export FPS=10

AvatarChatbot/tests/test_compose_on_rocm.sh

@@ -1,170 +0,0 @@
-#!/bin/bash
-# Copyright (C) 2024 Intel Corporation
-# SPDX-License-Identifier: Apache-2.0
-
-set -e
-IMAGE_REPO=${IMAGE_REPO:-"opea"}
-IMAGE_TAG=${IMAGE_TAG:-"latest"}
-echo "REGISTRY=IMAGE_REPO=${IMAGE_REPO}"
-echo "TAG=IMAGE_TAG=${IMAGE_TAG}"
-export REGISTRY=${IMAGE_REPO}
-export TAG=${IMAGE_TAG}
-
-WORKPATH=$(dirname "$PWD")
-LOG_PATH="$WORKPATH/tests"
-if ls $LOG_PATH/*.log 1> /dev/null 2>&1; then
-    rm $LOG_PATH/*.log
-    echo "Log files removed."
-else
-    echo "No log files to remove."
-fi
-ip_address=$(hostname -I | awk '{print $1}')
-
-
-function build_docker_images() {
-    cd $WORKPATH/docker_image_build
-    git clone https://github.com/opea-project/GenAIComps.git && cd GenAIComps && git checkout "${opea_branch:-"main"}" && cd ../
-
-    echo "Build all the images with --no-cache, check docker_image_build.log for details..."
-    service_list="avatarchatbot whisper asr llm-textgen 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
-
-    docker images && sleep 3s
-}
-
-
-function start_services() {
-    cd $WORKPATH/docker_compose/amd/gpu/rocm
-
-    export HUGGINGFACEHUB_API_TOKEN=$HUGGINGFACEHUB_API_TOKEN
-    export OPENAI_API_KEY=$OPENAI_API_KEY
-    export host_ip=${ip_address}
-
-    export TGI_SERVICE_PORT=3006
-    export TGI_LLM_ENDPOINT=http://${host_ip}:${TGI_SERVICE_PORT}
-    export LLM_MODEL_ID="Intel/neural-chat-7b-v3-3"
-
-    export ASR_ENDPOINT=http://${host_ip}:7066
-    export TTS_ENDPOINT=http://${host_ip}:7055
-    export WAV2LIP_ENDPOINT=http://${host_ip}:7860
-
-    export MEGA_SERVICE_HOST_IP=${host_ip}
-    export ASR_SERVICE_HOST_IP=${host_ip}
-    export TTS_SERVICE_HOST_IP=${host_ip}
-    export LLM_SERVICE_HOST_IP=${host_ip}
-    export ANIMATION_SERVICE_HOST_IP=${host_ip}
-    export WHISPER_SERVER_HOST_IP=${host_ip}
-    export WHISPER_SERVER_PORT=7066
-
-    export SPEECHT5_SERVER_HOST_IP=${host_ip}
-    export SPEECHT5_SERVER_PORT=7055
-
-    export MEGA_SERVICE_PORT=8888
-    export ASR_SERVICE_PORT=3001
-    export TTS_SERVICE_PORT=3002
-    export LLM_SERVICE_PORT=3007
-    export ANIMATION_SERVICE_PORT=3008
-
-    export DEVICE="cpu"
-    export WAV2LIP_PORT=7860
-    export INFERENCE_MODE='wav2lip+gfpgan'
-    export CHECKPOINT_PATH='/usr/local/lib/python3.11/site-packages/Wav2Lip/checkpoints/wav2lip_gan.pth'
-    export FACE="/home/user/comps/animation/src/assets/img/avatar5.png"
-    # export AUDIO='assets/audio/eg3_ref.wav' # audio file path is optional, will use base64str in the post request as input if is 'None'
-    export AUDIO='None'
-    export FACESIZE=96
-    export OUTFILE="./outputs/result.mp4"
-    export GFPGAN_MODEL_VERSION=1.4 # latest version, can roll back to v1.3 if needed
-    export UPSCALE_FACTOR=1
-    export FPS=5
-
-    # Start Docker Containers
-    docker compose up -d --force-recreate
-
-    echo "Check tgi-service status"
-
-    n=0
-    until [[ "$n" -ge 100 ]]; do
-       docker logs tgi-service > $LOG_PATH/tgi_service_start.log
-       if grep -q Connected $LOG_PATH/tgi_service_start.log; then
-           break
-       fi
-       sleep 5s
-       n=$((n+1))
-    done
-    echo "tgi-service are up and running"
-    sleep 5s
-
-    echo "Check wav2lip-service status"
-
-    n=0
-    until [[ "$n" -ge 100 ]]; do
-       docker logs wav2lip-service >& $LOG_PATH/wav2lip-service_start.log
-       if grep -q "Application startup complete" $LOG_PATH/wav2lip-service_start.log; then
-           break
-       fi
-       sleep 5s
-       n=$((n+1))
-    done
-    echo "wav2lip-service are up and running"
-    sleep 5s
-}
-
-
-function validate_megaservice() {
-    cd $WORKPATH
-    ls
-    result=$(http_proxy="" curl http://${ip_address}:3009/v1/avatarchatbot -X POST -d @assets/audio/sample_whoareyou.json -H 'Content-Type: application/json')
-    echo "result is === $result"
-    if [[ $result == *"mp4"* ]]; then
-        echo "Result correct."
-    else
-        docker logs whisper-service > $LOG_PATH/whisper-service.log
-        docker logs asr-service > $LOG_PATH/asr-service.log
-        docker logs speecht5-service > $LOG_PATH/speecht5-service.log
-        docker logs tts-service > $LOG_PATH/tts-service.log
-        docker logs tgi-service > $LOG_PATH/tgi-service.log
-        docker logs llm-tgi-server > $LOG_PATH/llm-tgi-server.log
-        docker logs wav2lip-service > $LOG_PATH/wav2lip-service.log
-        docker logs animation-server > $LOG_PATH/animation-server.log
-
-        echo "Result wrong."
-        exit 1
-    fi
-
-}
-
-
-#function validate_frontend() {
-
-#}
-
-
-function stop_docker() {
-    cd $WORKPATH/docker_compose/amd/gpu/rocm
-    docker compose down && docker compose rm -f
-}
-
-
-function main() {
-
-    echo $OPENAI_API_KEY
-    echo $OPENAI_KEY
-
-    stop_docker
-    if [[ "$IMAGE_REPO" == "opea" ]]; then build_docker_images; fi
-    start_services
-    # validate_microservices
-    sleep 30
-    validate_megaservice
-    # validate_frontend
-    stop_docker
-
-    echo y | docker system prune
-
-}
-
-
-main

ChatQnA/README.md

@@ -91,14 +91,6 @@ cd GenAIExamples/ChatQnA/docker_compose/intel/cpu/xeon/
 docker compose up -d
 ```
 
-To enable Open Telemetry Tracing, compose.telemetry.yaml file need to be merged along with default compose.yaml file.  
-CPU example with Open Telemetry feature:
-
-```bash
-cd GenAIExamples/ChatQnA/docker_compose/intel/cpu/xeon/
-docker compose -f compose.yaml -f compose.telemetry.yaml up -d
-```
-
 It will automatically download the docker image on `docker hub`:
 
 ```bash
@@ -240,13 +232,6 @@ cd GenAIExamples/ChatQnA/docker_compose/intel/hpu/gaudi/
 docker compose up -d
 ```
 
-To enable Open Telemetry Tracing, compose.telemetry.yaml file need to be merged along with default compose.yaml file.
-
-```bash
-cd GenAIExamples/ChatQnA/docker_compose/intel/hpu/gaudi/
-docker compose -f compose.yaml -f compose.telemetry.yaml up -d
-```
-
 Refer to the [Gaudi Guide](./docker_compose/intel/hpu/gaudi/README.md) to build docker images from source.
 
 ### Deploy ChatQnA on Xeon
@@ -258,13 +243,6 @@ cd GenAIExamples/ChatQnA/docker_compose/intel/cpu/xeon/
 docker compose up -d
 ```
 
-To enable Open Telemetry Tracing, compose.telemetry.yaml file need to be merged along with default compose.yaml file.
-
-```bash
-cd GenAIExamples/ChatQnA/docker_compose/intel/cpu/xeon/
-docker compose -f compose.yaml -f compose.telemetry.yaml up -d
-```
-
 Refer to the [Xeon Guide](./docker_compose/intel/cpu/xeon/README.md) for more instructions on building docker images from source.
 
 ### Deploy ChatQnA on NVIDIA GPU
@@ -368,7 +346,7 @@ OPEA microservice deployment can easily be monitored through Grafana dashboards
 
 ## Tracing Services with OpenTelemetry Tracing and Jaeger
 
-> NOTE: This feature is disabled by default. Please check the Deploy ChatQnA sessions for how to enable this feature with compose.telemetry.yaml file.
+> NOTE: limited support. Only LLM inference serving with TGI on Gaudi is enabled for this feature.
 
 OPEA microservice and TGI/TEI serving can easily be traced through Jaeger dashboards in conjunction with OpenTelemetry Tracing feature. Follow the [README](https://github.com/opea-project/GenAIComps/tree/main/comps/cores/telemetry#tracing) to trace additional functions if needed.
 
@@ -379,17 +357,8 @@ Users could also get the external IP via below command.
 ip route get 8.8.8.8 | grep -oP 'src \K[^ ]+'
 ```
 
-Access the Jaeger dashboard UI at http://{EXTERNAL_IP}:16686
-
 For TGI serving on Gaudi, users could see different services like opea, TEI and TGI.
 ![Screenshot from 2024-12-27 11-58-18](https://github.com/user-attachments/assets/6126fa70-e830-4780-bd3f-83cb6eff064e)
 
 Here is a screenshot for one tracing of TGI serving request.
 ![Screenshot from 2024-12-27 11-26-25](https://github.com/user-attachments/assets/3a7c51c6-f422-41eb-8e82-c3df52cd48b8)
-
-There are also OPEA related tracings. Users could understand the time breakdown of each service request by looking into each opea:schedule operation.
-![image](https://github.com/user-attachments/assets/6137068b-b374-4ff8-b345-993343c0c25f)
-
-There could be async function such as `llm/MicroService_asyn_generate` and user needs to check the trace of the async function in another operation like
-opea:llm_generate_stream.
-![image](https://github.com/user-attachments/assets/a973d283-198f-4ce2-a7eb-58515b77503e)

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

@@ -34,36 +34,16 @@ To set up environment variables for deploying ChatQnA services, follow these ste
    ```
 
 3. Set up other environment variables:
-
    ```bash
    source ./set_env.sh
    ```
 
-4. Change Model for LLM serving
-
-   By default, Meta-Llama-3-8B-Instruct is used for LLM serving, the default model can be changed to other validated LLM models.  
-   Please pick a [validated llm models](https://github.com/opea-project/GenAIComps/tree/main/comps/llms/src/text-generation#validated-llm-models) from the table.  
-   To change the default model defined in set_env.sh, overwrite it by exporting LLM_MODEL_ID to the new model or by modifying set_env.sh, and then repeat step 3.  
-   For example, change to Llama-2-7b-chat-hf using the following command.
-
-   ```bash
-   export LLM_MODEL_ID="meta-llama/Llama-2-7b-chat-hf"
-   ```
-
 ## Quick Start: 2.Run Docker Compose
 
 ```bash
 docker compose up -d
 ```
 
-To enable Open Telemetry Tracing, compose.telemetry.yaml file need to be merged along with default compose.yaml file.  
-CPU example with Open Telemetry feature:
-
-```bash
-cd GenAIExamples/ChatQnA/docker_compose/intel/cpu/xeon/
-docker compose -f compose.yaml -f compose.telemetry.yaml up -d
-```
-
 It will automatically download the docker image on `docker hub`:
 
 ```bash
@@ -283,16 +263,12 @@ If use vLLM as the LLM serving backend.
 docker compose -f compose.yaml up -d
 # Start ChatQnA without Rerank Pipeline
 docker compose -f compose_without_rerank.yaml up -d
-# Start ChatQnA with Rerank Pipeline and Open Telemetry Tracing
-docker compose -f compose.yaml -f compose.telemetry.yaml up -d
 ```
 
 If use TGI as the LLM serving backend.
 
 ```bash
 docker compose -f compose_tgi.yaml up -d
-# Start ChatQnA with Open Telemetry Tracing
-docker compose -f compose_tgi.yaml -f compose_tgi.telemetry.yaml up -d
 ```
 
 ### Validate Microservices

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

@@ -1,27 +0,0 @@
-# Copyright (C) 2024 Intel Corporation
-# SPDX-License-Identifier: Apache-2.0
-
-services:
-  tei-embedding-service:
-    command: --model-id ${EMBEDDING_MODEL_ID} --auto-truncate --otlp-endpoint $OTEL_EXPORTER_OTLP_TRACES_ENDPOINT
-  tei-reranking-service:
-    command: --model-id ${RERANK_MODEL_ID} --auto-truncate --otlp-endpoint $OTEL_EXPORTER_OTLP_TRACES_ENDPOINT
-  jaeger:
-    image: jaegertracing/all-in-one:latest
-    container_name: jaeger
-    ports:
-      - "16686:16686"
-      - "4317:4317"
-      - "4318:4318"
-      - "9411:9411"
-    ipc: host
-    environment:
-      no_proxy: ${no_proxy}
-      http_proxy: ${http_proxy}
-      https_proxy: ${https_proxy}
-      COLLECTOR_ZIPKIN_HOST_PORT: 9411
-    restart: unless-stopped
-  chatqna-xeon-backend-server:
-    environment:
-      - ENABLE_OPEA_TELEMETRY=true
-      - TELEMETRY_ENDPOINT=${TELEMETRY_ENDPOINT}

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

@@ -1,29 +0,0 @@
-# Copyright (C) 2024 Intel Corporation
-# SPDX-License-Identifier: Apache-2.0
-
-services:
-  tei-embedding-service:
-    command: --model-id ${EMBEDDING_MODEL_ID} --auto-truncate --otlp-endpoint $OTEL_EXPORTER_OTLP_TRACES_ENDPOINT
-  tei-reranking-service:
-    command: --model-id ${RERANK_MODEL_ID} --auto-truncate --otlp-endpoint $OTEL_EXPORTER_OTLP_TRACES_ENDPOINT
-  tgi-service:
-    command: --model-id ${LLM_MODEL_ID} --cuda-graphs 0 --otlp-endpoint $OTEL_EXPORTER_OTLP_TRACES_ENDPOINT
-  jaeger:
-    image: jaegertracing/all-in-one:latest
-    container_name: jaeger
-    ports:
-      - "16686:16686"
-      - "4317:4317"
-      - "4318:4318"
-      - "9411:9411"
-    ipc: host
-    environment:
-      no_proxy: ${no_proxy}
-      http_proxy: ${http_proxy}
-      https_proxy: ${https_proxy}
-      COLLECTOR_ZIPKIN_HOST_PORT: 9411
-    restart: unless-stopped
-  chatqna-xeon-backend-server:
-    environment:
-      - ENABLE_OPEA_TELEMETRY=true
-      - TELEMETRY_ENDPOINT=${TELEMETRY_ENDPOINT}

ChatQnA/docker_compose/intel/cpu/xeon/set_env.sh

@@ -14,7 +14,3 @@ export INDEX_NAME="rag-redis"
 # Set it as a non-null string, such as true, if you want to enable logging facility,
 # otherwise, keep it as "" to disable it.
 export LOGFLAG=""
-# Set OpenTelemetry Tracing Endpoint
-export JAEGER_IP=$(ip route get 8.8.8.8 | grep -oP 'src \K[^ ]+')
-export OTEL_EXPORTER_OTLP_TRACES_ENDPOINT=grpc://$JAEGER_IP:4317
-export TELEMETRY_ENDPOINT=http://$JAEGER_IP:4318/v1/traces

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

@@ -10,7 +10,7 @@ Quick Start:
 2. Run Docker Compose.
 3. Consume the ChatQnA Service.
 
-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). We now support running the latest DeepSeek models, including [deepseek-ai/DeepSeek-R1-Distill-Llama-70B](https://huggingface.co/deepseek-ai/DeepSeek-R1-Distill-Llama-70B) and [deepseek-ai/DeepSeek-R1-Distill-Qwen-32B](https://huggingface.co/deepseek-ai/DeepSeek-R1-Distill-Qwen-32B) on Gaudi accelerators. To run `deepseek-ai/DeepSeek-R1-Distill-Llama-70B`, update the `LLM_MODEL_ID` and configure `NUM_CARDS` to 8 in the [set_env.sh](./set_env.sh) script. To run `deepseek-ai/DeepSeek-R1-Distill-Qwen-32B`, update the `LLM_MODEL_ID` and configure `NUM_CARDS` to 4 in the [set_env.sh](./set_env.sh) script.
+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).
 
 ## Quick Start: 1.Setup Environment Variable
 
@@ -39,37 +39,12 @@ To set up environment variables for deploying ChatQnA services, follow these ste
    source ./set_env.sh
    ```
 
-4. Change Model for LLM serving
-
-   By default, Meta-Llama-3-8B-Instruct is used for LLM serving, the default model can be changed to other validated LLM models.  
-   Please pick a [validated llm models](https://github.com/opea-project/GenAIComps/tree/main/comps/llms/src/text-generation#validated-llm-models) from the table.  
-   To change the default model defined in set_env.sh, overwrite it by exporting LLM_MODEL_ID to the new model or by modifying set_env.sh, and then repeat step 3.  
-   For example, change to DeepSeek-R1-Distill-Qwen-32B using the following command.
-
-   ```bash
-   export LLM_MODEL_ID="deepseek-ai/DeepSeek-R1-Distill-Qwen-32B"
-   ```
-
-   Please also check [required gaudi cards for different models](https://github.com/opea-project/GenAIComps/tree/main/comps/llms/src/text-generation#system-requirements-for-llm-models) for new models.  
-   It might be necessary to increase the number of Gaudi cards for the model by exporting NUM_CARDS to the new model or by modifying set_env.sh, and then repeating step 3. For example, increase the number of Gaudi cards for DeepSeek-R1-
-   Distill-Qwen-32B using the following command:
-
-   ```bash
-   export NUM_CARDS=4
-   ```
-
 ## Quick Start: 2.Run Docker Compose
 
 ```bash
 docker compose up -d
 ```
 
-To enable Open Telemetry Tracing, compose.telemetry.yaml file need to be merged along with default compose.yaml file.
-
-```bash
-docker compose -f compose.yaml -f compose.telemetry.yaml up -d
-```
-
 It will automatically download the docker image on `docker hub`:
 
 ```bash
@@ -284,16 +259,12 @@ If use vLLM as the LLM serving backend.
 docker compose -f compose.yaml up -d
 # Start ChatQnA without Rerank Pipeline
 docker compose -f compose_without_rerank.yaml up -d
-# Start ChatQnA with Rerank Pipeline and Open Telemetry Tracing
-docker compose -f compose.yaml -f compose.telemetry.yaml up -d
 ```
 
 If use TGI as the LLM serving backend.
 
 ```bash
 docker compose -f compose_tgi.yaml up -d
-# Start ChatQnA with Open Telemetry Tracing
-docker compose -f compose_tgi.yaml -f compose_tgi.telemetry.yaml up -d
 ```
 
 If you want to enable guardrails microservice in the pipeline, please follow the below command instead:

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

@@ -1,27 +0,0 @@
-# Copyright (C) 2024 Intel Corporation
-# SPDX-License-Identifier: Apache-2.0
-
-services:
-  tei-embedding-service:
-    command: --model-id ${EMBEDDING_MODEL_ID} --auto-truncate --otlp-endpoint $OTEL_EXPORTER_OTLP_TRACES_ENDPOINT
-  tei-reranking-service:
-    command: --model-id ${RERANK_MODEL_ID} --auto-truncate --otlp-endpoint $OTEL_EXPORTER_OTLP_TRACES_ENDPOINT
-  jaeger:
-    image: jaegertracing/all-in-one:latest
-    container_name: jaeger
-    ports:
-      - "16686:16686"
-      - "4317:4317"
-      - "4318:4318"
-      - "9411:9411"
-    ipc: host
-    environment:
-      no_proxy: ${no_proxy}
-      http_proxy: ${http_proxy}
-      https_proxy: ${https_proxy}
-      COLLECTOR_ZIPKIN_HOST_PORT: 9411
-    restart: unless-stopped
-  chatqna-gaudi-backend-server:
-    environment:
-      - ENABLE_OPEA_TELEMETRY=true
-      - TELEMETRY_ENDPOINT=${TELEMETRY_ENDPOINT}

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

@@ -92,7 +92,6 @@ services:
       HABANA_VISIBLE_DEVICES: all
       OMPI_MCA_btl_vader_single_copy_mechanism: none
       LLM_MODEL_ID: ${LLM_MODEL_ID}
-      NUM_CARDS: ${NUM_CARDS}
       VLLM_TORCH_PROFILER_DIR: "/mnt"
     healthcheck:
       test: ["CMD-SHELL", "curl -f http://$host_ip:8007/health || exit 1"]
@@ -103,7 +102,7 @@ services:
     cap_add:
       - SYS_NICE
     ipc: host
-    command: --model ${LLM_MODEL_ID} --tensor-parallel-size ${NUM_CARDS} --host 0.0.0.0 --port 80 --block-size 128 --max-num-seqs 256 --max-seq_len-to-capture 2048
+    command: --model $LLM_MODEL_ID --tensor-parallel-size 1 --host 0.0.0.0 --port 80 --block-size 128 --max-num-seqs 256 --max-seq_len-to-capture 2048
   chatqna-gaudi-backend-server:
     image: ${REGISTRY:-opea}/chatqna:${TAG:-latest}
     container_name: chatqna-gaudi-backend-server

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

@@ -133,13 +133,12 @@ services:
       HABANA_VISIBLE_DEVICES: all
       OMPI_MCA_btl_vader_single_copy_mechanism: none
       LLM_MODEL_ID: ${LLM_MODEL_ID}
-      NUM_CARDS: ${NUM_CARDS}
       VLLM_TORCH_PROFILER_DIR: "/mnt"
     runtime: habana
     cap_add:
       - SYS_NICE
     ipc: host
-    command: --model ${LLM_MODEL_ID} --tensor-parallel-size ${NUM_CARDS} --host 0.0.0.0 --port 80 --block-size 128 --max-num-seqs 256 --max-seq_len-to-capture 2048
+    command: --model $LLM_MODEL_ID --tensor-parallel-size 1 --host 0.0.0.0 --port 80 --block-size 128 --max-num-seqs 256 --max-seq_len-to-capture 2048
   chatqna-gaudi-backend-server:
     image: ${REGISTRY:-opea}/chatqna-guardrails:${TAG:-latest}
     container_name: chatqna-gaudi-guardrails-server

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

@@ -1,29 +0,0 @@
-# Copyright (C) 2024 Intel Corporation
-# SPDX-License-Identifier: Apache-2.0
-
-services:
-  tei-embedding-service:
-    command: --model-id ${EMBEDDING_MODEL_ID} --auto-truncate --otlp-endpoint $OTEL_EXPORTER_OTLP_TRACES_ENDPOINT
-  tei-reranking-service:
-    command: --model-id ${RERANK_MODEL_ID} --auto-truncate --otlp-endpoint $OTEL_EXPORTER_OTLP_TRACES_ENDPOINT
-  tgi-service:
-    command: --model-id ${LLM_MODEL_ID} --max-input-length 2048 --max-total-tokens 4096 --otlp-endpoint $OTEL_EXPORTER_OTLP_TRACES_ENDPOINT
-  jaeger:
-    image: jaegertracing/all-in-one:latest
-    container_name: jaeger
-    ports:
-      - "16686:16686"
-      - "4317:4317"
-      - "4318:4318"
-      - "9411:9411"
-    ipc: host
-    environment:
-      no_proxy: ${no_proxy}
-      http_proxy: ${http_proxy}
-      https_proxy: ${https_proxy}
-      COLLECTOR_ZIPKIN_HOST_PORT: 9411
-    restart: unless-stopped
-  chatqna-gaudi-backend-server:
-    environment:
-      - ENABLE_OPEA_TELEMETRY=true
-      - TELEMETRY_ENDPOINT=${TELEMETRY_ENDPOINT}

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

@@ -25,6 +25,7 @@ services:
       INDEX_NAME: ${INDEX_NAME}
       TEI_ENDPOINT: http://tei-embedding-service:80
       HUGGINGFACEHUB_API_TOKEN: ${HUGGINGFACEHUB_API_TOKEN}
+      TELEMETRY_ENDPOINT: ${TELEMETRY_ENDPOINT}
   tei-embedding-service:
     image: ghcr.io/huggingface/text-embeddings-inference:cpu-1.5
     container_name: tei-embedding-gaudi-server
@@ -37,7 +38,7 @@ services:
       no_proxy: ${no_proxy}
       http_proxy: ${http_proxy}
       https_proxy: ${https_proxy}
-    command: --model-id ${EMBEDDING_MODEL_ID} --auto-truncate
+    command: --model-id ${EMBEDDING_MODEL_ID} --auto-truncate --otlp-endpoint $OTEL_EXPORTER_OTLP_TRACES_ENDPOINT
   retriever:
     image: ${REGISTRY:-opea}/retriever:${TAG:-latest}
     container_name: retriever-redis-server
@@ -55,6 +56,7 @@ services:
       INDEX_NAME: ${INDEX_NAME}
       TEI_EMBEDDING_ENDPOINT: http://tei-embedding-service:80
       HUGGINGFACEHUB_API_TOKEN: ${HUGGINGFACEHUB_API_TOKEN}
+      TELEMETRY_ENDPOINT: ${TELEMETRY_ENDPOINT}
       LOGFLAG: ${LOGFLAG}
       RETRIEVER_COMPONENT_NAME: "OPEA_RETRIEVER_REDIS"
     restart: unless-stopped
@@ -78,7 +80,7 @@ services:
       HABANA_VISIBLE_DEVICES: all
       OMPI_MCA_btl_vader_single_copy_mechanism: none
       MAX_WARMUP_SEQUENCE_LENGTH: 512
-    command: --model-id ${RERANK_MODEL_ID} --auto-truncate
+    command: --model-id ${RERANK_MODEL_ID} --auto-truncate --otlp-endpoint $OTEL_EXPORTER_OTLP_TRACES_ENDPOINT
   tgi-service:
     image: ghcr.io/huggingface/tgi-gaudi:2.0.6
     container_name: tgi-gaudi-server
@@ -99,12 +101,26 @@ services:
       LIMIT_HPU_GRAPH: true
       USE_FLASH_ATTENTION: true
       FLASH_ATTENTION_RECOMPUTE: true
-      NUM_CARDS: ${NUM_CARDS}
     runtime: habana
     cap_add:
       - SYS_NICE
     ipc: host
-    command: --model-id ${LLM_MODEL_ID} --num-shard ${NUM_CARDS} --max-input-length 2048 --max-total-tokens 4096
+    command: --model-id ${LLM_MODEL_ID} --max-input-length 2048 --max-total-tokens 4096 --otlp-endpoint $OTEL_EXPORTER_OTLP_TRACES_ENDPOINT
+  jaeger:
+    image: jaegertracing/all-in-one:latest
+    container_name: jaeger
+    ports:
+      - "16686:16686"
+      - "4317:4317"
+      - "4318:4318"
+      - "9411:9411"
+    ipc: host
+    environment:
+      no_proxy: ${no_proxy}
+      http_proxy: ${http_proxy}
+      https_proxy: ${https_proxy}
+      COLLECTOR_ZIPKIN_HOST_PORT: 9411
+    restart: unless-stopped
   chatqna-gaudi-backend-server:
     image: ${REGISTRY:-opea}/chatqna:${TAG:-latest}
     container_name: chatqna-gaudi-backend-server
@@ -130,6 +146,7 @@ services:
       - LLM_SERVER_PORT=${LLM_SERVER_PORT:-80}
       - LLM_MODEL=${LLM_MODEL_ID}
       - LOGFLAG=${LOGFLAG}
+      - TELEMETRY_ENDPOINT=${TELEMETRY_ENDPOINT}
     ipc: host
     restart: always
   chatqna-gaudi-ui-server:

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

@@ -73,13 +73,12 @@ services:
       HABANA_VISIBLE_DEVICES: all
       OMPI_MCA_btl_vader_single_copy_mechanism: none
       LLM_MODEL_ID: ${LLM_MODEL_ID}
-      NUM_CARDS: ${NUM_CARDS}
       VLLM_TORCH_PROFILER_DIR: "/mnt"
     runtime: habana
     cap_add:
       - SYS_NICE
     ipc: host
-    command: --model ${LLM_MODEL_ID} --tensor-parallel-size ${NUM_CARDS} --host 0.0.0.0 --port 80 --block-size 128 --max-num-seqs 256 --max-seq_len-to-capture 2048
+    command: --model $LLM_MODEL_ID --tensor-parallel-size 1 --host 0.0.0.0 --port 80 --block-size 128 --max-num-seqs 256 --max-seq_len-to-capture 2048
   chatqna-gaudi-backend-server:
     image: ${REGISTRY:-opea}/chatqna-without-rerank:${TAG:-latest}
     container_name: chatqna-gaudi-backend-server

ChatQnA/docker_compose/intel/hpu/gaudi/set_env.sh

@@ -11,7 +11,6 @@ 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"
 export INDEX_NAME="rag-redis"
-export NUM_CARDS=1
 # Set it as a non-null string, such as true, if you want to enable logging facility,
 # otherwise, keep it as "" to disable it.
 export LOGFLAG=""

ChatQnA/tests/test_compose_guardrails_on_gaudi.sh

@@ -29,6 +29,7 @@ function build_docker_images() {
     cd $WORKPATH/docker_image_build
     git clone --depth 1 --branch ${opea_branch} https://github.com/opea-project/GenAIComps.git
     git clone --depth 1 --branch v0.6.4.post2+Gaudi-1.19.0 https://github.com/HabanaAI/vllm-fork.git
+    sed -i 's/triton/triton==3.1.0/g' vllm-fork/requirements-hpu.txt
 
     echo "Build all the images with --no-cache, check docker_image_build.log for details..."
     service_list="chatqna-guardrails chatqna-ui dataprep retriever vllm-gaudi guardrails nginx"
@@ -46,7 +47,6 @@ function start_services() {
     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"
-    export NUM_CARDS=1
     export INDEX_NAME="rag-redis"
     export HUGGINGFACEHUB_API_TOKEN=${HUGGINGFACEHUB_API_TOKEN}
     export GURADRAILS_MODEL_ID="meta-llama/Meta-Llama-Guard-2-8B"

ChatQnA/tests/test_compose_on_gaudi.sh

@@ -29,6 +29,7 @@ function build_docker_images() {
     cd $WORKPATH/docker_image_build
     git clone --depth 1 --branch ${opea_branch} https://github.com/opea-project/GenAIComps.git
     git clone --depth 1 --branch v0.6.4.post2+Gaudi-1.19.0 https://github.com/HabanaAI/vllm-fork.git
+    sed -i 's/triton/triton==3.1.0/g' vllm-fork/requirements-hpu.txt
 
     echo "Build all the images with --no-cache, check docker_image_build.log for details..."
     service_list="chatqna chatqna-ui dataprep retriever vllm-gaudi nginx"
@@ -44,16 +45,12 @@ function start_services() {
     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"
-    export NUM_CARDS=1
     export INDEX_NAME="rag-redis"
     export HUGGINGFACEHUB_API_TOKEN=${HUGGINGFACEHUB_API_TOKEN}
     export host_ip=${ip_address}
-    export JAEGER_IP=$(ip route get 8.8.8.8 | grep -oP 'src \K[^ ]+')
-    export OTEL_EXPORTER_OTLP_TRACES_ENDPOINT=grpc://$JAEGER_IP:4317
-    export TELEMETRY_ENDPOINT=http://$JAEGER_IP:4318/v1/traces
 
     # Start Docker Containers
-    docker compose -f compose.yaml -f compose.telemetry.yaml up -d > ${LOG_PATH}/start_services_with_compose.log
+    docker compose -f compose.yaml up -d > ${LOG_PATH}/start_services_with_compose.log
     n=0
     until [[ "$n" -ge 160 ]]; do
         echo "n=$n"
@@ -174,7 +171,7 @@ function validate_frontend() {
 
 function stop_docker() {
     cd $WORKPATH/docker_compose/intel/hpu/gaudi
-    docker compose -f compose.yaml -f compose.telemetry.yaml down
+    docker compose -f compose.yaml down
 }
 
 function main() {

ChatQnA/tests/test_compose_on_xeon.sh

@@ -49,12 +49,9 @@ function start_services() {
     export INDEX_NAME="rag-redis"
     export HUGGINGFACEHUB_API_TOKEN=${HUGGINGFACEHUB_API_TOKEN}
     export host_ip=${ip_address}
-    export JAEGER_IP=$(ip route get 8.8.8.8 | grep -oP 'src \K[^ ]+')
-    export OTEL_EXPORTER_OTLP_TRACES_ENDPOINT=grpc://$JAEGER_IP:4317
-    export TELEMETRY_ENDPOINT=http://$JAEGER_IP:4318/v1/traces
 
     # Start Docker Containers
-    docker compose -f compose.yaml -f compose.telemetry.yaml up -d > ${LOG_PATH}/start_services_with_compose.log
+    docker compose -f compose.yaml up -d > ${LOG_PATH}/start_services_with_compose.log
     n=0
     until [[ "$n" -ge 100 ]]; do
         docker logs vllm-service > ${LOG_PATH}/vllm_service_start.log 2>&1
@@ -175,7 +172,7 @@ function validate_frontend() {
 
 function stop_docker() {
     cd $WORKPATH/docker_compose/intel/cpu/xeon
-    docker compose -f compose.yaml -f compose.telemetry.yaml down
+    docker compose -f compose.yaml down
 }
 
 function main() {

ChatQnA/tests/test_compose_tgi_on_gaudi.sh

@@ -46,7 +46,6 @@ function start_services() {
     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"
-    export NUM_CARDS=1
     export INDEX_NAME="rag-redis"
     export HUGGINGFACEHUB_API_TOKEN=${HUGGINGFACEHUB_API_TOKEN}
     export JAEGER_IP=$(ip route get 8.8.8.8 | grep -oP 'src \K[^ ]+')
@@ -54,7 +53,7 @@ function start_services() {
     export TELEMETRY_ENDPOINT=http://$JAEGER_IP:4318/v1/traces
 
     # Start Docker Containers
-    docker compose -f compose_tgi.yaml -f compose_tgi.telemetry.yaml up -d > ${LOG_PATH}/start_services_with_compose.log
+    docker compose -f compose_tgi.yaml up -d > ${LOG_PATH}/start_services_with_compose.log
 
     n=0
     until [[ "$n" -ge 500 ]]; do
@@ -218,7 +217,7 @@ function validate_frontend() {
 
 function stop_docker() {
     cd $WORKPATH/docker_compose/intel/hpu/gaudi
-    docker compose -f compose_tgi.yaml -f compose_tgi.telemetry.yaml down
+    docker compose -f compose_tgi.yaml down
 }
 
 function main() {

ChatQnA/tests/test_compose_tgi_on_xeon.sh

@@ -48,12 +48,9 @@ function start_services() {
     export LLM_MODEL_ID="meta-llama/Meta-Llama-3-8B-Instruct"
     export INDEX_NAME="rag-redis"
     export HUGGINGFACEHUB_API_TOKEN=${HUGGINGFACEHUB_API_TOKEN}
-    export JAEGER_IP=$(ip route get 8.8.8.8 | grep -oP 'src \K[^ ]+')
-    export OTEL_EXPORTER_OTLP_TRACES_ENDPOINT=grpc://$JAEGER_IP:4317
-    export TELEMETRY_ENDPOINT=http://$JAEGER_IP:4318/v1/traces
 
     # Start Docker Containers
-    docker compose -f compose_tgi.yaml -f compose_tgi.telemetry.yaml up -d > ${LOG_PATH}/start_services_with_compose.log
+    docker compose -f compose_tgi.yaml up -d > ${LOG_PATH}/start_services_with_compose.log
 
     n=0
     until [[ "$n" -ge 100 ]]; do
@@ -219,7 +216,7 @@ function validate_frontend() {
 
 function stop_docker() {
     cd $WORKPATH/docker_compose/intel/cpu/xeon
-    docker compose -f compose_tgi.yaml -f compose_tgi.telemetry.yaml down
+    docker compose -f compose_tgi.yaml down
 }
 
 function main() {

ChatQnA/tests/test_compose_without_rerank_on_gaudi.sh

@@ -29,6 +29,7 @@ function build_docker_images() {
     cd $WORKPATH/docker_image_build
     git clone --depth 1 --branch ${opea_branch} https://github.com/opea-project/GenAIComps.git
     git clone --depth 1 --branch v0.6.4.post2+Gaudi-1.19.0 https://github.com/HabanaAI/vllm-fork.git
+    sed -i 's/triton/triton==3.1.0/g' vllm-fork/requirements-hpu.txt
 
     echo "Build all the images with --no-cache, check docker_image_build.log for details..."
     service_list="chatqna-without-rerank chatqna-ui dataprep retriever vllm-gaudi nginx"
@@ -44,7 +45,6 @@ function start_services() {
     cd $WORKPATH/docker_compose/intel/hpu/gaudi
     export EMBEDDING_MODEL_ID="BAAI/bge-base-en-v1.5"
     export LLM_MODEL_ID="meta-llama/Meta-Llama-3-8B-Instruct"
-    export NUM_CARDS=1
     export INDEX_NAME="rag-redis"
     export HUGGINGFACEHUB_API_TOKEN=${HUGGINGFACEHUB_API_TOKEN}
 

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

@@ -1,126 +0,0 @@
-# Deploy on AMD GPU
-
-This document outlines the deployment process for DBQnA application which helps generating a SQL query and its output given a NLP question, utilizing the [GenAIComps](https://github.com/opea-project/GenAIComps.git) microservice pipeline on an AMD GPU. The steps include Docker image creation, container deployment via Docker Compose, and service execution to integrate microservices. We will publish the Docker images to Docker Hub soon, which will simplify the deployment process for this service.
-
-## 🚀 Build Docker Images
-
-First of all, you need to build Docker Images locally. This step can be ignored once the Docker images are published to Docker hub.
-
-### 1.1 Build Text to SQL service Image
-
-```bash
-git clone https://github.com/opea-project/GenAIComps.git
-cd GenAIComps
-docker build --no-cache -t opea/texttosql:latest -f comps/text2sql/src/Dockerfile .
-```
-
-### 1.2 Build react UI Docker Image
-
-Build the frontend Docker image based on react framework via below command:
-
-```bash
-cd GenAIExamples/DBQnA/ui
-docker build --no-cache -t opea/dbqna-react-ui:latest --build-arg texttosql_url=$textToSql_host:$textToSql_port/v1 -f docker/Dockerfile.react .
-```
-
-Attention! Replace $textToSql_host and $textToSql_port with your own value.
-
-Then run the command `docker images`, you will have the following Docker Images:
-
-1. `opea/texttosql:latest`
-2. `opea/dbqna-react-ui:latest`
-
-## 🚀 Start Microservices
-
-### Required Models
-
-We set default model as "mistralai/Mistral-7B-Instruct-v0.3", change "LLM_MODEL_ID" in following Environment Variables setting if you want to use other models.
-
-If use gated models, you also need to provide [huggingface token](https://huggingface.co/docs/hub/security-tokens) to "HUGGINGFACEHUB_API_TOKEN" environment variable.
-
-### 2.1 Setup Environment Variables
-
-Since the `compose.yaml` will consume some environment variables, you need to setup them in advance as below.
-
-```bash
-export host_ip="host_ip_address_or_dns_name"
-export DBQNA_HUGGINGFACEHUB_API_TOKEN=""
-export DBQNA_TGI_SERVICE_PORT=8008
-export DBQNA_TGI_LLM_ENDPOINT="http://${host_ip}:${DBQNA_TGI_SERVICE_PORT}"
-export DBQNA_LLM_MODEL_ID="mistralai/Mistral-7B-Instruct-v0.3"
-export MODEL_ID="mistralai/Mistral-7B-Instruct-v0.3"
-export POSTGRES_USER="postgres"
-export POSTGRES_PASSWORD="testpwd"
-export POSTGRES_DB="chinook"
-export DBQNA_TEXT_TO_SQL_PORT=18142
-export DBQNA_UI_PORT=18143
-```
-
-Note: Please replace with `host_ip_address_or_dns_name` with your external IP address or DNS name, do not use localhost.
-
-### 2.2 Start Microservice Docker Containers
-
-There are 2 options to start the microservice
-
-#### 2.2.1 Start the microservice using docker compose
-
-```bash
-cd GenAIExamples/DBQnA/docker_compose/amd/gpu/rocm
-docker compose up -d
-```
-
-## 🚀 Validate Microservices
-
-### 3.1 TGI Service
-
-```bash
-curl http://${host_ip}:$DBQNA_TGI_SERVICE_PORT/generate \
-    -X POST \
-    -d '{"inputs":"What is Deep Learning?","parameters":{"max_new_tokens":17, "do_sample": true}}' \
-    -H 'Content-Type: application/json'
-```
-
-### 3.2 Postgres Microservice
-
-Once Text-to-SQL microservice is started, user can use below command
-
-#### 3.2.1 Test the Database connection
-
-```bash
-curl --location http://${host_ip}:${DBQNA_TEXT_TO_SQL_PORT}/v1/postgres/health \
-    --header 'Content-Type: application/json' \
-    --data '{"user": "'${POSTGRES_USER}'","password": "'${POSTGRES_PASSWORD}'","host": "'${host_ip}'", "port": "5442", "database": "'${POSTGRES_DB}'"}'
-```
-
-#### 3.2.2 Invoke the microservice.
-
-```bash
-curl http://${host_ip}:${DBQNA_TEXT_TO_SQL_PORT}/v1/texttosql \
-    -X POST \
-    -d '{"input_text": "Find the total number of Albums.","conn_str": {"user": "'${POSTGRES_USER}'","password": "'${POSTGRES_PASSWORD}'","host": "'${host_ip}'", "port": "5442", "database": "'${POSTGRES_DB}'"}}' \
-    -H 'Content-Type: application/json'
-```
-
-### 3.3 Frontend validation
-
-We test the API in frontend validation to check if API returns HTTP_STATUS: 200 and validates if API response returns SQL query and output
-
-The test is present in App.test.tsx under react root folder ui/react/
-
-Command to run the test
-
-```bash
-npm run test
-```
-
-## 🚀 Launch the React UI
-
-Open this URL `http://${host_ip}:${DBQNA_UI_PORT}` in your browser to access the frontend.
-
-![project-screenshot](../../../../assets/img/dbQnA_ui_init.png)
-
-Test DB Connection
-![project-screenshot](../../../../assets/img/dbQnA_ui_successful_db_connection.png)
-
-Create SQL query and output for given NLP question
-![project-screenshot](../../../../assets/img/dbQnA_ui_succesful_sql_output_generation.png)

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

@@ -1,75 +0,0 @@
-# Copyright (C) 2024 Intel Corporation
-# SPDX-License-Identifier: Apache-2.0
-
-# SPDX-License-Identifier: Apache-2.0
-
-version: "3.8"
-
-services:
-  dbqna-tgi-service:
-    image: ghcr.io/huggingface/text-generation-inference:2.3.1-rocm
-    container_name: dbqna-tgi-service
-    ports:
-      - "${DBQNA_TGI_SERVICE_PORT:-8008}:80"
-    volumes:
-      - "./data:/data"
-    environment:
-      no_proxy: ${no_proxy}
-      http_proxy: ${http_proxy}
-      https_proxy: ${https_proxy}
-      TGI_SERVICE_PORT: ${DBQNA_TGI_SERVICE_PORT}
-      MODEL_ID: ${DBQNA_LLM_MODEL_ID}
-      HUGGING_FACE_HUB_TOKEN: ${DBQNA_HUGGINGFACEHUB_API_TOKEN}
-      HUGGINGFACEHUB_API_TOKEN: ${DBQNA_HUGGINGFACEHUB_API_TOKEN}
-    shm_size: 1g
-    devices:
-      - /dev/kfd:/dev/kfd
-      - /dev/dri/:/dev/dri/
-    cap_add:
-      - SYS_PTRACE
-    group_add:
-      - video
-    security_opt:
-      - seccomp:unconfined
-    ipc: host
-    command: --model-id ${MODEL_ID} --max-input-length 2048 --max-total-tokens 4096
-
-  postgres:
-    image: postgres:latest
-    container_name: postgres-container
-    restart: always
-    environment:
-      POSTGRES_USER: ${POSTGRES_USER}
-      POSTGRES_PASSWORD: ${POSTGRES_PASSWORD}
-      POSTGRES_DB: ${POSTGRES_DB}
-    ports:
-      - '5442:5432'
-    volumes:
-      - ./chinook.sql:/docker-entrypoint-initdb.d/chinook.sql
-
-  text2sql:
-    image: opea/text2sql:latest
-    container_name: text2sql
-    ports:
-      - "${DBQNA_TEXT_TO_SQL_PORT:-9090}:8080"
-    environment:
-      TGI_LLM_ENDPOINT: ${DBQNA_TGI_LLM_ENDPOINT}
-
-  text2sql-react-ui:
-    image: opea/text2sql-react-ui:latest
-    container_name: text2sql-react-ui
-    depends_on:
-      - text2sql
-    ports:
-      - "${DBQNA_UI_PORT:-5174}:80"
-    environment:
-      no_proxy: ${no_proxy}
-      https_proxy: ${https_proxy}
-      http_proxy: ${http_proxy}
-      texttosql_port: ${texttosql_port}
-    ipc: host
-    restart: always
-
-networks:
-  default:
-    driver: bridge

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

@@ -1,16 +0,0 @@
-#!/usr/bin/env bash
-
-# Copyright (C) 2024 Intel Corporation
-# SPDX-License-Identifier: Apache-2.0
-
-export host_ip=""
-export DBQNA_HUGGINGFACEHUB_API_TOKEN=""
-export DBQNA_TGI_SERVICE_PORT=8008
-export DBQNA_TGI_LLM_ENDPOINT="http://${host_ip}:${DBQNA_TGI_SERVICE_PORT}"
-export DBQNA_LLM_MODEL_ID="mistralai/Mistral-7B-Instruct-v0.3"
-export MODEL_ID=${DBQNA_LLM_MODEL_ID}
-export POSTGRES_USER="postgres"
-export POSTGRES_PASSWORD="testpwd"
-export POSTGRES_DB="chinook"
-export DBQNA_TEXT_TO_SQL_PORT=9090
-export DBQNA_UI_PORT=5174

DBQnA/docker_image_build/build.yaml

@@ -19,5 +19,4 @@ services:
         http_proxy: ${http_proxy}
         https_proxy: ${https_proxy}
         no_proxy: ${no_proxy}
-        texttosql_url: ${build_texttosql_url}
     image: ${REGISTRY:-opea}/text2sql-react-ui:${TAG:-latest}

DBQnA/tests/test_compose_on_rocm.sh

@@ -1,120 +0,0 @@
-#!/bin/bash
-# Copyright (C) 2024 Intel Corporation
-# SPDX-License-Identifier: Apache-2.0
-
-set -xe
-
-WORKPATH=$(dirname "$PWD")
-LOG_PATH="$WORKPATH/tests"
-ip_address=$(hostname -I | awk '{print $1}')
-tgi_port=8008
-tgi_volume=$WORKPATH/data
-
-export host_ip=${ip_address}
-export DBQNA_HUGGINGFACEHUB_API_TOKEN=${HUGGINGFACEHUB_API_TOKEN}
-export DBQNA_TGI_SERVICE_PORT=8008
-export DBQNA_TGI_LLM_ENDPOINT="http://${host_ip}:${DBQNA_TGI_SERVICE_PORT}"
-export DBQNA_LLM_MODEL_ID="mistralai/Mistral-7B-Instruct-v0.3"
-export MODEL_ID=${DBQNA_LLM_MODEL_ID}
-export POSTGRES_USER="postgres"
-export POSTGRES_PASSWORD="testpwd"
-export POSTGRES_DB="chinook"
-export DBQNA_TEXT_TO_SQL_PORT=9090
-export DBQNA_UI_PORT=5174
-export build_texttosql_url="${ip_address}:${DBQNA_TEXT_TO_SQL_PORT}/v1"
-
-function build_docker_images() {
-    cd "$WORKPATH"/docker_image_build
-    git clone https://github.com/opea-project/GenAIComps.git && cd GenAIComps && git checkout "${opea_branch:-"main"}" && cd ../
-
-    echo "Build all the images with --no-cache, check docker_image_build.log for details..."
-    service_list="text2sql text2sql-react-ui"
-
-    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 images && sleep 1s
-}
-
-function start_service() {
-    cd "$WORKPATH"/docker_compose/amd/gpu/rocm
-    # Start Docker Containers
-    docker compose up -d > "${LOG_PATH}"/start_services_with_compose.log
-    n=0
-    until [[ "$n" -ge 100 ]]; do
-        docker logs dbqna-tgi-service > "${LOG_PATH}"/tgi_service_start.log
-        if grep -q Connected "${LOG_PATH}"/tgi_service_start.log; then
-            break
-        fi
-        sleep 5s
-        n=$((n+1))
-    done
-}
-
-function validate_microservice() {
-    result=$(http_proxy="" curl --connect-timeout 5 --max-time 120000 http://${ip_address}:${DBQNA_TEXT_TO_SQL_PORT}/v1/text2sql \
-        -X POST \
-        -d '{"input_text": "Find the total number of Albums.","conn_str": {"user": "'${POSTGRES_USER}'","password": "'${POSTGRES_PASSWORD}'","host": "'${ip_address}'", "port": "5442", "database": "'${POSTGRES_DB}'" }}' \
-        -H 'Content-Type: application/json')
-
-    if [[ $result == *"output"* ]]; then
-        echo $result
-        echo "Result correct."
-    else
-        echo "Result wrong. Received was $result"
-        docker logs text2sql > ${LOG_PATH}/text2sql.log
-        docker logs dbqna-tgi-service > ${LOG_PATH}/tgi.log
-        exit 1
-    fi
-
-}
-
-function validate_frontend() {
-    echo "[ TEST INFO ]: --------- frontend test started ---------"
-    cd $WORKPATH/ui/react
-    local conda_env_name="OPEA_e2e"
-    export PATH=${HOME}/miniconda3/bin/:$PATH
-    if conda info --envs | grep -q "$conda_env_name"; then
-        echo "$conda_env_name exist!"
-    else
-        conda create -n ${conda_env_name} python=3.12 -y
-    fi
-
-    source activate ${conda_env_name}
-    echo "[ TEST INFO ]: --------- conda env activated ---------"
-
-    conda install -c conda-forge nodejs=22.6.0 -y
-    npm install && npm ci
-    node -v && npm -v && pip list
-
-    exit_status=0
-    npm run test || exit_status=$?
-
-    if [ $exit_status -ne 0 ]; then
-        echo "[TEST INFO]: ---------frontend test failed---------"
-        exit $exit_status
-    else
-        echo "[TEST INFO]: ---------frontend test passed---------"
-    fi
-}
-
-function stop_docker() {
-    cd $WORKPATH/docker_compose/amd/gpu/rocm/
-    docker compose stop && docker compose rm -f
-}
-
-function main() {
-
-    stop_docker
-
-    build_docker_images
-    start_service
-    sleep 10s
-    validate_microservice
-    validate_frontend
-
-    stop_docker
-    echo y | docker system prune
-
-}
-
-main

DBQnA/ui/docker/Dockerfile.react

@@ -3,13 +3,8 @@
 
 # Stage 1: Build the React application using Node.js
 # Use Node 20.11.1 as the base image for the build step
-
 FROM node:20.11.1 AS vite-app
 
-ARG texttosql_url
-
-ENV TEXT_TO_SQL_URL=$texttosql_url
-
 WORKDIR /usr/app/react
 
 COPY react /usr/app/react
@@ -21,10 +16,6 @@ RUN ["npm", "run", "build"]
 
 FROM nginx:alpine
 
-ARG texttosql_url
-
-ENV TEXT_TO_SQL_URL=$texttosql_url
-
 EXPOSE 80
 
 COPY --from=vite-app /usr/app/react/dist /usr/share/nginx/html

DBQnA/ui/react/.env

@@ -1 +1 @@
-VITE_TEXT_TO_SQL_URL=${TEXT_TO_SQL_URL}
+VITE_TEXT_TO_SQL_URL=http://${HOSTNAME}:9090/v1

DBQnA/ui/react/src/App.test.tsx

@@ -26,7 +26,7 @@ test('testing api with dynamic host', async () => {
   const formData = {
     user: 'postgres',
     database: 'chinook',
-    host: host,
+    host: host,  // Dynamic IP
     password: 'testpwd',
     port: '5442',
   };

DBQnA/ui/react/vite.config.ts

@@ -24,7 +24,7 @@ export default defineConfig({
   },
   define: {
     // Dynamically set the hostname for the VITE_TEXT_TO_SQL_URL
-    "import.meta.env.VITE_TEXT_TO_SQL_URL": JSON.stringify(`http://${process.env.TEXT_TO_SQL_URL}`),
+    "import.meta.env.VITE_TEXT_TO_SQL_URL": JSON.stringify(`http://${os.hostname()}:9090/v1`),
     "import.meta.env": process.env,
   },
 });

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

@@ -8,7 +8,7 @@ services:
     ports:
       - ${LLM_ENDPOINT_PORT:-8008}:80
     volumes:
-      - "${DATA_PATH:-./data}:/data"
+      - "${DATA_PATH:-data}:/data"
     environment:
       no_proxy: ${no_proxy}
       http_proxy: ${http_proxy}

DocSum/ui/gradio/docsum_ui_gradio.py

@@ -296,8 +296,8 @@ class DocSumUI:
                     audio_ui.render()
                 with gr.TabItem("Upload Video"):
                     video_ui.render()
-                # with gr.TabItem("Enter URL"):
-                #     url_ui.render()
+                with gr.TabItem("Enter URL"):
+                    url_ui.render()
 
         return self.demo
 
@@ -313,8 +313,6 @@ app = gr.mount_gradio_app(app, demo, path="/")
 if __name__ == "__main__":
     import argparse
 
-    import nltk
-
     parser = argparse.ArgumentParser()
     parser.add_argument("--host", type=str, default="0.0.0.0")
     parser.add_argument("--port", type=int, default=5173)
@@ -322,8 +320,4 @@ if __name__ == "__main__":
     args = parser.parse_args()
     logger.info(">>> Starting server at %s:%d", args.host, args.port)
 
-    # Needed for UnstructuredURLLoader when reading content from a URL
-    nltk.download("punkt_tab")
-    nltk.download("averaged_perceptron_tagger_eng")
-
     uvicorn.run(app, host=args.host, port=args.port)

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

@@ -8,7 +8,7 @@ services:
     ports:
       - ${LLM_ENDPOINT_PORT:-8008}:80
     volumes:
-      - "${DATA_PATH:-./data}:/data"
+      - "${DATA_PATH:-data}:/data"
     environment:
       no_proxy: ${no_proxy}
       http_proxy: ${http_proxy}

FaqGen/ui/svelte/src/lib/shared/Network.ts

@@ -52,7 +52,6 @@ export async function fetchTextStream(query: string | Blob, params: string, file
     }
     const reader = postResponse.body.getReader();
     const decoder = new TextDecoder("utf-8");
-
     let done, value;
 
     let buffer = ""; // Initialize a buffer
@@ -62,7 +61,6 @@ export async function fetchTextStream(query: string | Blob, params: string, file
 
       // Decode chunk and append to buffer
       const chunk = decoder.decode(value, { stream: true });
-
       buffer += chunk;
 
       // Use regex to clean and extract data
@@ -74,21 +72,6 @@ export async function fetchTextStream(query: string | Blob, params: string, file
         })
         .filter((line) => line); // Remove empty lines
 
-      const validJsonChunks = cleanedChunks.filter((item) => {
-        if (item === "[DONE]") {
-          return true;
-        }
-        try {
-          JSON.parse(item);
-          return true;
-        } catch (e) {
-          return false;
-        }
-      });
-
-      cleanedChunks.length = 0;
-      cleanedChunks.push(...validJsonChunks);
-
       for (const cleanedChunk of cleanedChunks) {
         // Further clean to ensure all unnecessary parts are removed
         yield cleanedChunk.replace(/^b'|['"]$/g, ""); // Again clean 'b' and other single or double quotes

FaqGen/ui/svelte/src/routes/+page.svelte

@@ -36,7 +36,6 @@
     urlSuffix: string,
     params: string
   ) => {
-    messages = "";
     // Fetch the stream
     const eventStream = await fetchTextStream(
       query,

README.md

@@ -50,7 +50,7 @@ Deployment are based on released docker images by default, check [docker image l
 | CodeTrans         | [Xeon Instructions](CodeTrans/docker_compose/intel/cpu/xeon/README.md)         | [Gaudi Instructions](CodeTrans/docker_compose/intel/hpu/gaudi/README.md)     | [ROCm Instructions](CodeTrans/docker_compose/amd/gpu/rocm/README.md)     | [CodeTrans with Helm Charts](CodeTrans/kubernetes/helm/README.md)   | [CodeTrans with GMC](CodeTrans/kubernetes/gmc/README.md)     |
 | DocSum            | [Xeon Instructions](DocSum/docker_compose/intel/cpu/xeon/README.md)            | [Gaudi Instructions](DocSum/docker_compose/intel/hpu/gaudi/README.md)        | [ROCm Instructions](DocSum/docker_compose/amd/gpu/rocm/README.md)        | [DocSum with Helm Charts](DocSum/kubernetes/helm/README.md)         | [DocSum with GMC](DocSum/kubernetes/gmc/README.md)           |
 | SearchQnA         | [Xeon Instructions](SearchQnA/docker_compose/intel/cpu/xeon/README.md)         | [Gaudi Instructions](SearchQnA/docker_compose/intel/hpu/gaudi/README.md)     | Not Supported                                                            | [SearchQnA with Helm Charts](SearchQnA/kubernetes/helm/README.md)   | [SearchQnA with GMC](SearchQnA/kubernetes/gmc/README.md)     |
-| FaqGen            | [Xeon Instructions](FaqGen/docker_compose/intel/cpu/xeon/README.md)            | [Gaudi Instructions](FaqGen/docker_compose/intel/hpu/gaudi/README.md)        | [ROCm Instructions](FaqGen/docker_compose/amd/gpu/rocm/README.md)        | [FaqGen with Helm Charts](FaqGen/kubernetes/helm/README.md)         | Not supported                                                |
+| FaqGen            | [Xeon Instructions](FaqGen/docker_compose/intel/cpu/xeon/README.md)            | [Gaudi Instructions](FaqGen/docker_compose/intel/hpu/gaudi/README.md)        | [ROCm Instructions](FaqGen/docker_compose/amd/gpu/rocm/README.md)        | [FaqGen with Helm Charts](FaqGen/kubernetes/helm/README.md)         | [FaqGen with GMC](FaqGen/kubernetes/gmc/README.md)           |
 | Translation       | [Xeon Instructions](Translation/docker_compose/intel/cpu/xeon/README.md)       | [Gaudi Instructions](Translation/docker_compose/intel/hpu/gaudi/README.md)   | [ROCm Instructions](Translation/docker_compose/amd/gpu/rocm/README.md)   | Not Supported                                                       | [Translation with GMC](Translation/kubernetes/gmc/README.md) |
 | AudioQnA          | [Xeon Instructions](AudioQnA/docker_compose/intel/cpu/xeon/README.md)          | [Gaudi Instructions](AudioQnA/docker_compose/intel/hpu/gaudi/README.md)      | [ROCm Instructions](AudioQnA/docker_compose/amd/gpu/rocm/README.md)      | [AudioQnA with Helm Charts](AudioQnA/kubernetes/helm/README.md)     | [AudioQnA with GMC](AudioQnA/kubernetes/gmc/README.md)       |
 | VisualQnA         | [Xeon Instructions](VisualQnA/docker_compose/intel/cpu/xeon/README.md)         | [Gaudi Instructions](VisualQnA/docker_compose/intel/hpu/gaudi/README.md)     | [ROCm Instructions](VisualQnA/docker_compose/amd/gpu/rocm/README.md)     | [VisualQnA with Helm Charts](VisualQnA/kubernetes/helm/README.md)   | [VisualQnA with GMC](VisualQnA/kubernetes/gmc/README.md)     |

RerankFinetuning/docker_image_build/build.yaml

@@ -11,12 +11,3 @@ services:
       context: GenAIComps
       dockerfile: comps/finetuning/src/Dockerfile
     image: ${REGISTRY:-opea}/finetuning:${TAG:-latest}
-  finetuning-gaudi:
-    build:
-      args:
-        http_proxy: ${http_proxy}
-        https_proxy: ${https_proxy}
-        no_proxy: ${no_proxy}
-      context: GenAIComps
-      dockerfile: comps/finetuning/src/Dockerfile.intel_hpu
-    image: ${REGISTRY:-opea}/finetuning-gaudi:${TAG:-latest}

RerankFinetuning/tests/test_compose_on_gaudi.sh

@@ -1,131 +0,0 @@
-# Copyright (C) 2024 Intel Corporation
-# SPDX-License-Identifier: Apache-2.0
-
-set -x
-IMAGE_REPO=${IMAGE_REPO:-"opea"}
-IMAGE_TAG=${IMAGE_TAG:-"latest"}
-echo "REGISTRY=IMAGE_REPO=${IMAGE_REPO}"
-echo "TAG=IMAGE_TAG=${IMAGE_TAG}"
-export REGISTRY=${IMAGE_REPO}
-export TAG=${IMAGE_TAG}
-
-WORKPATH=$(dirname "$PWD")
-LOG_PATH="$WORKPATH/tests"
-ip_address=$(hostname -I | awk '{print $1}')
-finetuning_service_port=8015
-ray_port=8265
-service_name=finetuning-gaudi
-
-function build_docker_images() {
-    cd $WORKPATH/docker_image_build
-    if [ ! -d "GenAIComps" ] ; then
-        git clone --depth 1 --branch ${opea_branch:-"main"} https://github.com/opea-project/GenAIComps.git
-    fi
-    docker compose -f build.yaml build ${service_name} --no-cache > ${LOG_PATH}/docker_image_build.log
-}
-
-function start_service() {
-    export no_proxy="localhost,127.0.0.1,"${ip_address}
-    docker run -d --name="finetuning-server" -p $finetuning_service_port:$finetuning_service_port -p $ray_port:$ray_port --runtime=habana -e HABANA_VISIBLE_DEVICES=all -e OMPI_MCA_btl_vader_single_copy_mechanism=none --cap-add=sys_nice --ipc=host -e http_proxy=$http_proxy -e https_proxy=$https_proxy -e no_proxy=$no_proxy ${IMAGE_REPO}/finetuning-gaudi:${IMAGE_TAG}
-    sleep 1m
-}
-
-function validate_microservice() {
-    cd $LOG_PATH
-    export no_proxy="localhost,127.0.0.1,"${ip_address}
-
-    # test /v1/dataprep upload file
-    URL="http://${ip_address}:$finetuning_service_port/v1/files"
-    cat <<EOF > test_data.json
-{"query": "Five women walk along a beach wearing flip-flops.", "pos": ["Some women with flip-flops on, are walking along the beach"], "neg": ["The 4 women are sitting on the beach.", "There was a reform in 1996.", "She's not going to court to clear her record.", "The man is talking about hawaii.", "A woman is standing outside.", "The battle was over. ", "A group of people plays volleyball."]}
-{"query": "A woman standing on a high cliff on one leg looking over a river.", "pos": ["A woman is standing on a cliff."], "neg": ["A woman sits on a chair.", "George Bush told the Republicans there was no way he would let them even consider this foolish idea, against his top advisors advice.", "The family was falling apart.", "no one showed up to the meeting", "A boy is sitting outside playing in the sand.", "Ended as soon as I received the wire.", "A child is reading in her bedroom."]}
-{"query": "Two woman are playing instruments; one a clarinet, the other a violin.", "pos": ["Some people are playing a tune."], "neg": ["Two women are playing a guitar and drums.", "A man is skiing down a mountain.", "The fatal dose was not taken when the murderer thought it would be.", "Person on bike", "The girl is standing, leaning against the archway.", "A group of women watch soap operas.", "No matter how old people get they never forget. "]}
-{"query": "A girl with a blue tank top sitting watching three dogs.", "pos": ["A girl is wearing blue."], "neg": ["A girl is with three cats.", "The people are watching a funeral procession.", "The child is wearing black.", "Financing is an issue for us in public schools.", "Kids at a pool.", "It is calming to be assaulted.", "I face a serious problem at eighteen years old. "]}
-{"query": "A yellow dog running along a forest path.", "pos": ["a dog is running"], "neg": ["a cat is running", "Steele did not keep her original story.", "The rule discourages people to pay their child support.", "A man in a vest sits in a car.", "Person in black clothing, with white bandanna and sunglasses waits at a bus stop.", "Neither the Globe or Mail had comments on the current state of Canada's road system. ", "The Spring Creek facility is old and outdated."]}
-{"query": "It sets out essential activities in each phase along with critical factors related to those activities.", "pos": ["Critical factors for essential activities are set out."], "neg": ["It lays out critical activities but makes no provision for critical factors related to those activities.", "People are assembled in protest.", "The state would prefer for you to do that.", "A girl sits beside a boy.", "Two males are performing.", "Nobody is jumping", "Conrad was being plotted against, to be hit on the head."]}
-EOF
-    HTTP_RESPONSE=$(curl --silent --write-out "HTTPSTATUS:%{http_code}" -X POST -F 'file=@./test_data.json' -F purpose="fine-tune" -H 'Content-Type: multipart/form-data' "$URL")
-    HTTP_STATUS=$(echo $HTTP_RESPONSE | tr -d '\n' | sed -e 's/.*HTTPSTATUS://')
-    RESPONSE_BODY=$(echo $HTTP_RESPONSE | sed -e 's/HTTPSTATUS\:.*//g')
-    SERVICE_NAME="finetuning-server - upload - file"
-
-    # Parse the JSON response
-    purpose=$(echo "$RESPONSE_BODY" | jq -r '.purpose')
-    filename=$(echo "$RESPONSE_BODY" | jq -r '.filename')
-
-    # Define expected values
-    expected_purpose="fine-tune"
-    expected_filename="test_data.json"
-
-    if [ "$HTTP_STATUS" -ne "200" ]; then
-        echo "[ $SERVICE_NAME ] HTTP status is not 200. Received status was $HTTP_STATUS"
-        docker logs finetuning-server >> ${LOG_PATH}/finetuning-server_upload_file.log
-        exit 1
-    else
-        echo "[ $SERVICE_NAME ] HTTP status is 200. Checking content..."
-    fi
-    # Check if the parsed values match the expected values
-    if [[ "$purpose" != "$expected_purpose" || "$filename" != "$expected_filename" ]]; then
-        echo "[ $SERVICE_NAME ] Content does not match the expected result: $RESPONSE_BODY"
-        docker logs finetuning-server >> ${LOG_PATH}/finetuning-server_upload_file.log
-        exit 1
-    else
-        echo "[ $SERVICE_NAME ] Content is as expected."
-    fi
-
-    # test /v1/fine_tuning/jobs
-    URL="http://${ip_address}:$finetuning_service_port/v1/fine_tuning/jobs"
-    HTTP_RESPONSE=$(curl --silent --write-out "HTTPSTATUS:%{http_code}" -X POST -H 'Content-Type: application/json' -d '{"training_file": "test_data.json","model": "BAAI/bge-reranker-base","General":{"task":"rerank","lora_config":null}}' "$URL")
-    HTTP_STATUS=$(echo $HTTP_RESPONSE | tr -d '\n' | sed -e 's/.*HTTPSTATUS://')
-    RESPONSE_BODY=$(echo $HTTP_RESPONSE | sed -e 's/HTTPSTATUS\:.*//g')
-    SERVICE_NAME="finetuning-server - create finetuning job"
-
-    if [ "$HTTP_STATUS" -ne "200" ]; then
-        echo "[ $SERVICE_NAME ] HTTP status is not 200. Received status was $HTTP_STATUS"
-        docker logs finetuning-server >> ${LOG_PATH}/finetuning-server_create.log
-        exit 1
-    else
-        echo "[ $SERVICE_NAME ] HTTP status is 200. Checking content..."
-    fi
-    if [[ "$RESPONSE_BODY" != *'{"id":"ft-job'* ]]; then
-        echo "[ $SERVICE_NAME ] Content does not match the expected result: $RESPONSE_BODY"
-        docker logs finetuning-server >> ${LOG_PATH}/finetuning-server_create.log
-        exit 1
-    else
-        echo "[ $SERVICE_NAME ] Content is as expected."
-    fi
-
-    sleep 3m
-
-    docker logs finetuning-server 2>&1 | tee ${LOG_PATH}/finetuning-server_create.log
-    FINETUNING_LOG=$(grep "succeeded" ${LOG_PATH}/finetuning-server_create.log)
-    if [[ "$FINETUNING_LOG" != *'succeeded'* ]]; then
-        echo "Finetuning failed."
-        RAY_JOBID=$(grep "Submitted Ray job" ${LOG_PATH}/finetuning-server_create.log | sed 's/.*raysubmit/raysubmit/' | cut -d' ' -f 1)
-        docker exec finetuning-server python -c "import os;os.environ['RAY_ADDRESS']='http://localhost:8265';from ray.job_submission import JobSubmissionClient;client = JobSubmissionClient();print(client.get_job_logs('${RAY_JOBID}'))" 2>&1 | tee ${LOG_PATH}/finetuning.log
-        exit 1
-    else
-        echo "Finetuning succeeded."
-    fi
-}
-
-function stop_docker() {
-    cid=$(docker ps -aq --filter "name=finetuning-server*")
-    if [[ ! -z "$cid" ]]; then docker stop $cid && docker rm $cid && sleep 1s; fi
-}
-
-function main() {
-
-    stop_docker
-
-    build_docker_images
-    start_service
-
-    validate_microservice
-
-    stop_docker
-    echo y | docker system prune
-
-}
-
-main

RerankFinetuning/tests/test_compose_on_xeon.sh

@@ -14,14 +14,13 @@ LOG_PATH="$WORKPATH/tests"
 ip_address=$(hostname -I | awk '{print $1}')
 finetuning_service_port=8015
 ray_port=8265
-service_name=finetuning
 
 function build_docker_images() {
     cd $WORKPATH/docker_image_build
     if [ ! -d "GenAIComps" ] ; then
         git clone --depth 1 --branch ${opea_branch:-"main"} https://github.com/opea-project/GenAIComps.git
     fi
-    docker compose -f build.yaml build ${service_name} --no-cache > ${LOG_PATH}/docker_image_build.log
+    docker compose -f build.yaml build --no-cache > ${LOG_PATH}/docker_image_build.log
 }
 
 function start_service() {
@@ -95,18 +94,7 @@ EOF
         echo "[ $SERVICE_NAME ] Content is as expected."
     fi
 
-    sleep 3m
-
-    docker logs finetuning-server 2>&1 | tee ${LOG_PATH}/finetuning-server_create.log
-    FINETUNING_LOG=$(grep "succeeded" ${LOG_PATH}/finetuning-server_create.log)
-    if [[ "$FINETUNING_LOG" != *'succeeded'* ]]; then
-        echo "Finetuning failed."
-        RAY_JOBID=$(grep "Submitted Ray job" ${LOG_PATH}/finetuning-server_create.log | sed 's/.*raysubmit/raysubmit/' | cut -d' ' -f 1)
-        docker exec finetuning-server python -c "import os;os.environ['RAY_ADDRESS']='http://localhost:8265';from ray.job_submission import JobSubmissionClient;client = JobSubmissionClient();print(client.get_job_logs('${RAY_JOBID}'))" 2>&1 | tee ${LOG_PATH}/finetuning.log
-        exit 1
-    else
-        echo "Finetuning succeeded."
-    fi
+    sleep 1s
 }
 
 function stop_docker() {

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

@@ -1,179 +0,0 @@
-# Build and deploy SearchQnA Application on AMD GPU (ROCm)
-
-## Build images
-
-### Build Embedding Image
-
-```bash
-git clone https://github.com/opea-project/GenAIComps.git
-cd GenAIComps
-docker build --no-cache -t opea/embedding-tei:latest --build-arg https_proxy=$https_proxy --build-arg http_proxy=$http_proxy -f comps/embeddings/src/Dockerfile .
-```
-
-### Build Retriever Image
-
-```bash
-docker build --no-cache -t opea/web-retriever-chroma:latest --build-arg https_proxy=$https_proxy --build-arg http_proxy=$http_proxy -f comps/web_retrievers/src/Dockerfile .
-```
-
-### Build Rerank Image
-
-```bash
-docker build --no-cache -t opea/reranking-tei:latest --build-arg https_proxy=$https_proxy --build-arg http_proxy=$http_proxy -f comps/rerankings/src/Dockerfile .
-```
-
-### Build the LLM Docker Image
-
-```bash
-docker build -t opea/llm-tgi:latest --build-arg https_proxy=$https_proxy --build-arg http_proxy=$http_proxy -f comps/llms/src/text-generation/Dockerfile .
-```
-
-### Build the MegaService Docker Image
-
-```bash
-git clone https://github.com/opea-project/GenAIExamples.git
-cd GenAIExamples/SearchQnA
-docker build --no-cache -t opea/searchqna:latest --build-arg https_proxy=$https_proxy --build-arg http_proxy=$http_proxy -f Dockerfile .
-```
-
-### Build the UI Docker Image
-
-```bash
-cd GenAIExamples/SearchQnA/ui
-docker build --no-cache -t opea/opea/searchqna-ui:latest --build-arg https_proxy=$https_proxy --build-arg http_proxy=$http_proxy -f ./docker/Dockerfile .
-```
-
-## Deploy SearchQnA Application
-
-### Features of Docker compose for AMD GPUs
-
-1. Added forwarding of GPU devices to the container TGI service with instructions:
-
-```yaml
-shm_size: 1g
-devices:
-  - /dev/kfd:/dev/kfd
-  - /dev/dri/:/dev/dri/
-cap_add:
-  - SYS_PTRACE
-group_add:
-  - video
-security_opt:
-  - seccomp:unconfined
-```
-
-In this case, all GPUs are thrown. To reset a specific GPU, you need to use specific device names cardN and renderN.
-
-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
-```
-
-To find out which GPU device IDs cardN and renderN correspond to the same GPU, use the GPU driver utility
-
-### Go to the directory with the Docker compose file
-
-```bash
-cd GenAIExamples/SearchQnA/docker_compose/amd/gpu/rocm
-```
-
-### Set environments
-
-In the file "GenAIExamples/SearchQnA/docker_compose/amd/gpu/rocm/set_env.sh " it is necessary to set the required values. Parameter assignments are specified in the comments for each variable setting command
-
-```bash
-chmod +x set_env.sh
-. set_env.sh
-```
-
-### Run services
-
-```
-docker compose up -d
-```
-
-# Validate the MicroServices and MegaService
-
-## Validate TEI service
-
-```bash
-curl http://${SEARCH_HOST_IP}:3001/embed \
-    -X POST \
-    -d '{"inputs":"What is Deep Learning?"}' \
-    -H 'Content-Type: application/json'
-```
-
-## Validate Embedding service
-
-```bash
-curl http://${SEARCH_HOST_IP}:3002/v1/embeddings\
-  -X POST \
-  -d '{"text":"hello"}' \
-  -H 'Content-Type: application/json'
-```
-
-## Validate Web Retriever service
-
-```bash
-export your_embedding=$(python3 -c "import random; embedding = [random.uniform(-1, 1) for _ in range(768)]; print(embedding)")
-curl http://${SEARCH_HOST_IP}:3003/v1/web_retrieval \
-  -X POST \
-  -d "{\"text\":\"What is the 2024 holiday schedule?\",\"embedding\":${your_embedding}}" \
-  -H 'Content-Type: application/json'
-```
-
-## Validate TEI Reranking service
-
-```bash
-curl http://${SEARCH_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'
-```
-
-## Validate Reranking service
-
-```bash
-curl http://${SEARCH_HOST_IP}:3005/v1/reranking\
-  -X POST \
-  -d '{"initial_query":"What is Deep Learning?", "retrieved_docs": [{"text":"Deep Learning is not..."}, {"text":"Deep learning is..."}]}' \
-  -H 'Content-Type: application/json'
-```
-
-## Validate TGI service
-
-```bash
-curl http://${SEARCH_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'
-```
-
-## Validate LLM service
-
-```bash
-curl http://${SEARCH_HOST_IP}:3007/v1/chat/completions\
-  -X POST \
-  -d '{"query":"What is Deep Learning?","max_tokens":17,"top_k":10,"top_p":0.95,"typical_p":0.95,"temperature":0.01,"repetition_penalty":1.03,"streaming":true}' \
-  -H 'Content-Type: application/json'
-```
-
-## Validate MegaService
-
-```bash
-curl http://${SEARCH_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"
-     }'
-```

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

@@ -1,173 +0,0 @@
-# Copyright (C) 2024 Intel Corporation
-# SPDX-License-Identifier: Apache-2.0
-
-# SPDX-License-Identifier: Apache-2.0
-
-services:
-  search-tei-embedding-service:
-    image: ghcr.io/huggingface/text-embeddings-inference:cpu-1.5
-    container_name: search-tei-embedding-server
-    ports:
-      - "3001:80"
-    volumes:
-      - "./data:/data"
-    shm_size: 1g
-    environment:
-      no_proxy: ${no_proxy}
-      http_proxy: ${http_proxy}
-      https_proxy: ${https_proxy}
-      HF_TOKEN: ${SEARCH_HUGGINGFACEHUB_API_TOKEN}
-      HUGGING_FACE_HUB_TOKEN: ${SEARCH_HUGGINGFACEHUB_API_TOKEN}
-      HUGGINGFACEHUB_API_TOKEN: ${SEARCH_HUGGINGFACEHUB_API_TOKEN}
-    command: --model-id ${SEARCH_EMBEDDING_MODEL_ID} --auto-truncate
-  search-embedding:
-    image: ${REGISTRY:-opea}/embedding:${TAG:-latest}
-    container_name: search-embedding-server
-    depends_on:
-      - search-tei-embedding-service
-    ports:
-      - "3002:6000"
-    ipc: host
-    environment:
-      no_proxy: ${no_proxy}
-      http_proxy: ${http_proxy}
-      https_proxy: ${https_proxy}
-      TEI_EMBEDDING_HOST_IP: ${SEARCH_HOST_IP}
-      TEI_EMBEDDING_ENDPOINT: ${SEARCH_TEI_EMBEDDING_ENDPOINT}
-      HF_TOKEN: ${SEARCH_HUGGINGFACEHUB_API_TOKEN}
-    restart: unless-stopped
-  search-web-retriever:
-    image: ${REGISTRY:-opea}/web-retriever:${TAG:-latest}
-    container_name: search-web-retriever-server
-    ports:
-      - "3003:7077"
-    ipc: host
-    environment:
-      no_proxy: ${no_proxy}
-      http_proxy: ${http_proxy}
-      https_proxy: ${https_proxy}
-      TEI_EMBEDDING_ENDPOINT: ${SEARCH_TEI_EMBEDDING_ENDPOINT}
-      GOOGLE_API_KEY: ${SEARCH_GOOGLE_API_KEY}
-      GOOGLE_CSE_ID: ${SEARCH_GOOGLE_CSE_ID}
-    restart: unless-stopped
-  search-tei-reranking-service:
-    image: ghcr.io/huggingface/text-embeddings-inference:cpu-1.5
-    container_name: search-tei-reranking-server
-    ports:
-      - "3004:80"
-    volumes:
-      - "./data:/data"
-    shm_size: 1g
-    environment:
-      no_proxy: ${no_proxy}
-      http_proxy: ${http_proxy}
-      https_proxy: ${https_proxy}
-    command: --model-id ${SEARCH_RERANK_MODEL_ID} --auto-truncate
-  search-reranking:
-    image: ${REGISTRY:-opea}/reranking:${TAG:-latest}
-    container_name: search-reranking-server
-    depends_on:
-      - search-tei-reranking-service
-    ports:
-      - "3005:8000"
-    ipc: host
-    environment:
-      no_proxy: ${no_proxy}
-      http_proxy: ${http_proxy}
-      https_proxy: ${https_proxy}
-      TEI_RERANKING_ENDPOINT: ${SEARCH_TEI_RERANKING_ENDPOINT}
-      HF_TOKEN: ${SEARCH_HUGGINGFACEHUB_API_TOKEN}
-      HUGGING_FACE_HUB_TOKEN: ${SEARCH_HUGGINGFACEHUB_API_TOKEN}
-      HUGGINGFACEHUB_API_TOKEN: ${SEARCH_HUGGINGFACEHUB_API_TOKEN}
-    restart: unless-stopped
-  search-tgi-service:
-    image: ghcr.io/huggingface/text-generation-inference:2.3.1-rocm
-    container_name: search-tgi-service
-    ports:
-      - "3006:80"
-    volumes:
-      - "./data:/data"
-    environment:
-      no_proxy: ${no_proxy}
-      http_proxy: ${http_proxy}
-      https_proxy: ${https_proxy}
-      HUGGING_FACE_HUB_TOKEN: ${SEARCH_HUGGINGFACEHUB_API_TOKEN}
-      HUGGINGFACEHUB_API_TOKEN: ${SEARCH_HUGGINGFACEHUB_API_TOKEN}
-    shm_size: 1g
-    devices:
-      - /dev/kfd:/dev/kfd
-      - /dev/dri/:/dev/dri/
-    cap_add:
-      - SYS_PTRACE
-    group_add:
-      - video
-    security_opt:
-      - seccomp:unconfined
-    ipc: host
-    command: --model-id ${SEARCH_LLM_MODEL_ID} --max-input-length 1024 --max-total-tokens 2048
-  search-llm:
-    image: ${REGISTRY:-opea}/llm-textgen:${TAG:-latest}
-    container_name: search-llm-server
-    depends_on:
-      - search-tgi-service
-    ports:
-      - "3007:9000"
-    ipc: host
-    environment:
-      no_proxy: ${no_proxy}
-      http_proxy: ${http_proxy}
-      https_proxy: ${https_proxy}
-      TGI_LLM_ENDPOINT: ${SEARCH_TGI_LLM_ENDPOINT}
-      HUGGINGFACEHUB_API_TOKEN: ${SEARCH_HUGGINGFACEHUB_API_TOKEN}
-      LLM_ENDPOINT: ${SEARCH_TGI_LLM_ENDPOINT}
-      LLM_MODEL_ID: ${SEARCH_LLM_MODEL_ID}
-      LLM_MODEL: ${SEARCH_LLM_MODEL_ID}
-      HF_TOKEN: ${SEARCH_HUGGINGFACEHUB_API_TOKEN}
-      OPENAI_API_KEY: ${SEARCH_OPENAI_API_KEY}
-    restart: unless-stopped
-  search-backend-server:
-    image: ${REGISTRY:-opea}/searchqna:${TAG:-latest}
-    container_name: search-backend-server
-    depends_on:
-      - search-tei-embedding-service
-      - search-embedding
-      - search-web-retriever
-      - search-tei-reranking-service
-      - search-reranking
-      - search-tgi-service
-      - search-llm
-    ports:
-      - "${SEARCH_BACKEND_SERVICE_PORT:-3008}:8888"
-    environment:
-      - no_proxy=${no_proxy}
-      - https_proxy=${https_proxy}
-      - http_proxy=${http_proxy}
-      - MEGA_SERVICE_HOST_IP=${SEARCH_MEGA_SERVICE_HOST_IP}
-      - EMBEDDING_SERVICE_HOST_IP=${SEARCH_EMBEDDING_SERVICE_HOST_IP}
-      - WEB_RETRIEVER_SERVICE_HOST_IP=${SEARCH_WEB_RETRIEVER_SERVICE_HOST_IP}
-      - RERANK_SERVICE_HOST_IP=${SEARCH_RERANK_SERVICE_HOST_IP}
-      - LLM_SERVICE_HOST_IP=${SEARCH_LLM_SERVICE_HOST_IP}
-      - EMBEDDING_SERVICE_PORT=${SEARCH_EMBEDDING_SERVICE_PORT}
-      - WEB_RETRIEVER_SERVICE_PORT=${SEARCH_WEB_RETRIEVER_SERVICE_PORT}
-      - RERANK_SERVICE_PORT=${SEARCH_RERANK_SERVICE_PORT}
-      - LLM_SERVICE_PORT=${SEARCH_LLM_SERVICE_PORT}
-    ipc: host
-    restart: always
-  search-ui-server:
-    image: ${REGISTRY:-opea}/searchqna-ui:${TAG:-latest}
-    container_name: search-ui-server
-    depends_on:
-      - search-backend-server
-    ports:
-      - "${SEARCH_FRONTEND_SERVICE_PORT:-5173}:5173"
-    environment:
-      - no_proxy=${no_proxy}
-      - https_proxy=${https_proxy}
-      - http_proxy=${http_proxy}
-      - BACKEND_BASE_URL=${SEARCH_BACKEND_SERVICE_ENDPOINT}
-    ipc: host
-    restart: always
-
-networks:
-  default:
-    driver: bridge

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

@@ -1,36 +0,0 @@
-#!/usr/bin/env bash
-
-# Copyright (C) 2024 Intel Corporation
-# SPDX-License-Identifier: Apache-2.0
-
-# SPDX-License-Identifier: Apache-2.0
-
-export SEARCH_HOST_IP=10.53.22.29
-export SEARCH_EXTERNAL_HOST_IP=68.69.180.77
-export SEARCH_EMBEDDING_MODEL_ID='BAAI/bge-base-en-v1.5'
-export SEARCH_TEI_EMBEDDING_ENDPOINT=http://${SEARCH_HOST_IP}:3001
-export SEARCH_RERANK_MODEL_ID='BAAI/bge-reranker-base'
-export SEARCH_TEI_RERANKING_ENDPOINT=http://${SEARCH_HOST_IP}:3004
-export SEARCH_HUGGINGFACEHUB_API_TOKEN=${HUGGINGFACEHUB_API_TOKEN}
-export SEARCH_OPENAI_API_KEY=${OPENAI_API_KEY}
-
-export SEARCH_TGI_LLM_ENDPOINT=http://${SEARCH_HOST_IP}:3006
-export SEARCH_LLM_MODEL_ID='Intel/neural-chat-7b-v3-3'
-
-export SEARCH_MEGA_SERVICE_HOST_IP=${SEARCH_EXTERNAL_HOST_IP}
-export SEARCH_EMBEDDING_SERVICE_HOST_IP=${SEARCH_HOST_IP}
-export SEARCH_WEB_RETRIEVER_SERVICE_HOST_IP=${SEARCH_HOST_IP}
-export SEARCH_RERANK_SERVICE_HOST_IP=${SEARCH_HOST_IP}
-export SEARCH_LLM_SERVICE_HOST_IP=${SEARCH_HOST_IP}
-
-export SEARCH_EMBEDDING_SERVICE_PORT=3002
-export SEARCH_WEB_RETRIEVER_SERVICE_PORT=3003
-export SEARCH_RERANK_SERVICE_PORT=3005
-export SEARCH_LLM_SERVICE_PORT=3007
-
-export SEARCH_FRONTEND_SERVICE_PORT=18143
-export SEARCH_BACKEND_SERVICE_PORT=18142
-export SEARCH_BACKEND_SERVICE_ENDPOINT=http://${SEARCH_EXTERNAL_HOST_IP}:${SEARCH_BACKEND_SERVICE_PORT}/v1/searchqna
-
-export SEARCH_GOOGLE_API_KEY=${GOOGLE_API_KEY}
-export SEARCH_GOOGLE_CSE_ID=${GOOGLE_CSE_ID}

SearchQnA/tests/test_compose_on_rocm.sh

@@ -1,137 +0,0 @@
-#!/bin/bash
-# Copyright (C) 2024 Intel Corporation
-# SPDX-License-Identifier: Apache-2.0
-
-set -xe
-IMAGE_REPO=${IMAGE_REPO:-"opea"}
-IMAGE_TAG=${IMAGE_TAG:-"latest"}
-echo "REGISTRY=IMAGE_REPO=${IMAGE_REPO}"
-echo "TAG=IMAGE_TAG=${IMAGE_TAG}"
-export REGISTRY=${IMAGE_REPO}
-export TAG=${IMAGE_TAG}
-
-WORKPATH=$(dirname "$PWD")
-LOG_PATH="$WORKPATH/tests"
-ip_address=$(hostname -I | awk '{print $1}')
-
-function build_docker_images() {
-    cd $WORKPATH/docker_image_build
-    git clone https://github.com/opea-project/GenAIComps.git && cd GenAIComps && git checkout "${opea_branch:-"main"}" && cd ../
-
-    echo "Build all the images with --no-cache, check docker_image_build.log for details..."
-    service_list="searchqna searchqna-ui embedding web-retriever reranking llm-textgen"
-    docker compose -f build.yaml build ${service_list} --no-cache > ${LOG_PATH}/docker_image_build.log
-
-    docker pull ghcr.io/huggingface/text-embeddings-inference:cpu-1.5
-    docker pull ghcr.io/huggingface/text-generation-inference:2.3.1-rocm
-    docker images && sleep 1s
-}
-
-function start_services() {
-    cd $WORKPATH/docker_compose/amd/gpu/rocm/
-    export SEARCH_HOST_IP=${ip_address}
-    export SEARCH_EXTERNAL_HOST_IP=${ip_address}
-    export SEARCH_EMBEDDING_MODEL_ID='BAAI/bge-base-en-v1.5'
-    export SEARCH_TEI_EMBEDDING_ENDPOINT=http://${SEARCH_HOST_IP}:3001
-    export SEARCH_RERANK_MODEL_ID='BAAI/bge-reranker-base'
-    export SEARCH_TEI_RERANKING_ENDPOINT=http://${SEARCH_HOST_IP}:3004
-    export SEARCH_HUGGINGFACEHUB_API_TOKEN=${HUGGINGFACEHUB_API_TOKEN}
-    export SEARCH_OPENAI_API_KEY=${OPENAI_API_KEY}
-    export SEARCH_TGI_LLM_ENDPOINT=http://${SEARCH_HOST_IP}:3006
-    export SEARCH_LLM_MODEL_ID='Intel/neural-chat-7b-v3-3'
-    export SEARCH_MEGA_SERVICE_HOST_IP=${SEARCH_EXTERNAL_HOST_IP}
-    export SEARCH_EMBEDDING_SERVICE_HOST_IP=${SEARCH_HOST_IP}
-    export SEARCH_WEB_RETRIEVER_SERVICE_HOST_IP=${SEARCH_HOST_IP}
-    export SEARCH_RERANK_SERVICE_HOST_IP=${SEARCH_HOST_IP}
-    export SEARCH_LLM_SERVICE_HOST_IP=${SEARCH_HOST_IP}
-    export SEARCH_EMBEDDING_SERVICE_PORT=3002
-    export SEARCH_WEB_RETRIEVER_SERVICE_PORT=3003
-    export SEARCH_RERANK_SERVICE_PORT=3005
-    export SEARCH_LLM_SERVICE_PORT=3007
-    export SEARCH_FRONTEND_SERVICE_PORT=5173
-    export SEARCH_BACKEND_SERVICE_PORT=3008
-    export SEARCH_BACKEND_SERVICE_ENDPOINT=http://${SEARCH_HOST_IP}:${SEARCH_BACKEND_SERVICE_PORT}/v1/searchqna
-    export SEARCH_GOOGLE_API_KEY=${GOOGLE_API_KEY}
-    export SEARCH_GOOGLE_CSE_ID=${GOOGLE_CSE_ID}
-
-    sed -i "s/backend_address/$ip_address/g" $WORKPATH/ui/svelte/.env
-
-    # Start Docker Containers
-    docker compose up -d > ${LOG_PATH}/start_services_with_compose.log
-    n=0
-    until [[ "$n" -ge 100 ]]; do
-        docker logs search-tgi-service > $LOG_PATH/search-tgi-service_start.log
-        if grep -q Connected $LOG_PATH/search-tgi-service_start.log; then
-            break
-        fi
-        sleep 5s
-        n=$((n+1))
-    done
-}
-
-
-function validate_megaservice() {
-    result=$(http_proxy="" curl http://${ip_address}:3008/v1/searchqna -XPOST -d '{"messages": "What is black myth wukong?", "stream": "False"}' -H 'Content-Type: application/json')
-    echo $result
-
-    if [[ $result == *"the"* ]]; then
-        docker logs search-web-retriever-server
-        docker logs search-backend-server
-        echo "Result correct."
-    else
-        docker logs search-web-retriever-server
-        docker logs search-backend-server
-        echo "Result wrong."
-        exit 1
-    fi
-
-}
-
-function validate_frontend() {
-    cd $WORKPATH/ui/svelte
-    local conda_env_name="OPEA_e2e"
-    export PATH=${HOME}/miniconda3/bin/:$PATH
-    if conda info --envs | grep -q "$conda_env_name"; then
-        echo "$conda_env_name exist!"
-    else
-        conda create -n ${conda_env_name} python=3.12 -y
-    fi
-    source activate ${conda_env_name}
-
-    sed -i "s/localhost/$ip_address/g" playwright.config.ts
-
-    conda install -c conda-forge nodejs=22.6.0 -y
-    npm install && npm ci && npx playwright install --with-deps
-    node -v && npm -v && pip list
-
-    exit_status=0
-    npx playwright test || exit_status=$?
-
-    if [ $exit_status -ne 0 ]; then
-       echo "[TEST INFO]: ---------frontend test failed---------"
-       exit $exit_status
-    else
-       echo "[TEST INFO]: ---------frontend test passed---------"
-    fi
-}
-
-function stop_docker() {
-    cd $WORKPATH/docker_compose/amd/gpu/rocm/
-    docker compose stop && docker compose rm -f
-}
-
-function main() {
-
-    stop_docker
-    if [[ "$IMAGE_REPO" == "opea" ]]; then build_docker_images; fi
-    start_services
-
-    validate_megaservice
-    validate_frontend
-
-    stop_docker
-    echo y | docker system prune
-
-}
-
-main

VisualQnA/ui/svelte/package.json

@@ -23,7 +23,6 @@
     "@tailwindcss/typography": "0.5.7",
     "@types/debug": "4.1.7",
     "@types/node": "^20.12.13",
-    "@types/pica": "^9.0.5",
     "@typescript-eslint/eslint-plugin": "^5.27.0",
     "@typescript-eslint/parser": "^5.27.0",
     "autoprefixer": "^10.4.16",
@@ -52,7 +51,6 @@
     "flowbite-svelte-icons": "^1.4.0",
     "fuse.js": "^6.6.2",
     "lodash": "^4.17.21",
-    "pica": "^9.0.1",
     "playwright": "^1.44.0",
     "ramda": "^0.29.0",
     "sse.js": "^0.6.1",

VisualQnA/ui/svelte/src/lib/modules/chat/ChatMessage.svelte

@@ -31,7 +31,9 @@
 	class={msg.role === 0
 		? "flex w-full gap-3"
 		: "flex w-full items-center gap-3"}
-	data-testid={msg.role === 0 ? "display-answer" : "display-question"}
+	data-testid={msg.role === 0
+		? "display-answer"
+		: "display-question"}
 >
 	<div
 		class={msg.role === 0
@@ -42,15 +44,10 @@
 	</div>
 	<div class="group relative flex items-start">
 		<div class="flex flex-col items-start">
-			{#if msg.imgSrc}
-				<img
-					src={msg.imgSrc}
-					alt="Uploaded Image"
-					class="max-w-28 m-2 max-h-28"
-				/>
-			{/if}
+			<img src={msg.imgSrc} alt="Uploaded Image" class="m-2 max-w-28 max-h-28" />
+
 			<p
-				class="max-w-[60vw] items-start whitespace-pre-line break-keep text-[0.8rem] leading-5 sm:max-w-[50rem] xl:max-w-[65vw]"
+				class="xl:max-w-[65vw] max-w-[60vw] items-start whitespace-pre-line break-keep text-[0.8rem] leading-5 sm:max-w-[50rem]"
 			>
 				{@html msg.content}
 			</p>

VisualQnA/ui/svelte/src/lib/modules/upload/imagePrompt.svelte

@@ -5,98 +5,93 @@
 
 <script>
 	import { createEventDispatcher } from "svelte";
-	import extreme_ironing from "$lib/assets/imageData/extreme_ironing.png";
-	import waterview from "$lib/assets/imageData/waterview.png";
+  import extreme_ironing from '$lib/assets/imageData/extreme_ironing.jpg';
+  import waterview from '$lib/assets/imageData/waterview.jpg';
 	import { base64ImageStore } from "$lib/shared/stores/common/Store";
 
-	let dispatch = createEventDispatcher();
+  let dispatch = createEventDispatcher();
 
-	let images = [
-		{
-			id: 1,
-			alt: "Waterview",
-			imgurl: waterview,
-			prompt:
-				"What are the things I should be cautious about when I visit here?",
-		},
-		{
-			id: 0,
-			alt: "Extreme Ironing",
-			imgurl: extreme_ironing,
-			prompt: "What is unusual about this image?",
-		},
-	];
+  let images = [
+    {
+      id: 1,
+      alt: 'Waterview',
+      imgurl: waterview,
+      prompt: 'What are the things I should be cautious about when I visit here?'
+    },
+    {
+      id: 0,
+      alt: 'Extreme Ironing',
+      imgurl: extreme_ironing,
+      prompt: 'What is unusual about this image?'
+    }
+  ];
 
-	let currentIndex = 0;
+  let currentIndex = 0;
 
-	function nextImage() {
-		currentIndex = (currentIndex + 1) % images.length;
-	}
+  function nextImage() {
+    currentIndex = (currentIndex + 1) % images.length;
+  }
 
-	function prevImage() {
-		currentIndex = (currentIndex - 1 + images.length) % images.length;
-	}
+  function prevImage() {
+    currentIndex = (currentIndex - 1 + images.length) % images.length;
+  }
 
-	async function handleImageClick() {
-		const imgUrl = images[currentIndex].imgurl;
 
-		const base64Data = await convertImageToBase64(imgUrl);
+  async function handleImageClick() {
+    const imgUrl = images[currentIndex].imgurl;
+    const base64Data = await convertImageToBase64(imgUrl);
+    const currentPrompt = images[currentIndex].prompt;
+    dispatch("imagePrompt", { content: currentPrompt });
+    base64ImageStore.set(base64Data);
+  }
 
-		base64ImageStore.set(base64Data);
-
-		const currentPrompt = images[currentIndex].prompt;
-		dispatch("imagePrompt", { content: currentPrompt });
-	}
-
-	async function convertImageToBase64(url) {
-		const response = await fetch(url);
-		const blob = await response.blob();
-		return new Promise((resolve, reject) => {
-			const reader = new FileReader();
-			reader.onloadend = () => resolve(reader.result);
-			reader.onerror = reject;
-			reader.readAsDataURL(blob);
-		});
-	}
+  async function convertImageToBase64(url) {
+    const response = await fetch(url);
+    const blob = await response.blob();
+    return new Promise((resolve, reject) => {
+      const reader = new FileReader();
+      reader.onloadend = () => resolve(reader.result);
+      reader.onerror = reject;
+      reader.readAsDataURL(blob);
+    });
+  }
 </script>
 
-<div class="my-2 flex w-full flex-col gap-3 rounded-xl bg-white p-5">
-	<p>Example</p>
-	<div class="relative mx-auto w-full max-w-4xl">
-		<button
-			class="absolute left-0 top-1/2 z-10 h-8 w-8 -translate-y-1/2 transform rounded-full bg-white/30 group-hover:bg-white/50 group-focus:outline-none group-focus:ring-4 group-focus:ring-white dark:bg-gray-800/30 dark:group-hover:bg-gray-800/60 dark:group-focus:ring-gray-800/70 sm:h-10 sm:w-10"
-			on:click={prevImage}
-			aria-label="Previous image"
-		>
-			&#10094;
-		</button>
+<div class="flex w-full flex-col gap-3 rounded-xl bg-white p-5 my-2">
+  <p>Example</p>
+  <div class="relative w-full max-w-4xl mx-auto">
+    <button
+      class="absolute left-0 top-1/2 transform -translate-y-1/2 z-10  w-8 h-8 rounded-full sm:w-10 sm:h-10 bg-white/30 dark:bg-gray-800/30 group-hover:bg-white/50 dark:group-hover:bg-gray-800/60 group-focus:ring-4 group-focus:ring-white dark:group-focus:ring-gray-800/70 group-focus:outline-none"
+      on:click={prevImage}
+      aria-label="Previous image"
+    >
+      &#10094;
+    </button>
 
-		<div class="relative">
-			<img
-				src={images[currentIndex].imgurl}
-				alt={images[currentIndex].alt}
-				class="carousel-image h-auto w-full cursor-pointer"
-				on:click={handleImageClick}
-			/>
-			<div
-				class="absolute bottom-0 left-0 w-full bg-black bg-opacity-55 p-3 text-white"
-			>
-				<p>{images[currentIndex].prompt}</p>
-			</div>
-		</div>
+    <div class="relative">
+      <img
+        src={images[currentIndex].imgurl}
+        alt={images[currentIndex].alt}
+        class="carousel-image w-full h-auto cursor-pointer"
+        on:click={handleImageClick}
+      />
+      <div class="absolute bottom-0 left-0 bg-opacity-55 bg-black text-white p-3 w-full">
+        <p>{images[currentIndex].prompt}</p>
+      </div>
+    </div>
 
-		<button
-			class="absolute right-0 top-1/2 z-10 h-8 w-8 -translate-y-1/2 transform rounded-full bg-white/30 group-hover:bg-white/50 group-focus:outline-none group-focus:ring-4 group-focus:ring-white dark:bg-gray-800/30 dark:group-hover:bg-gray-800/60 dark:group-focus:ring-gray-800/70 sm:h-10 sm:w-10"
-			on:click={nextImage}
-			aria-label="Next image"
-		>
-			&#10095;
-		</button>
-	</div>
+    <button
+      class="absolute right-0 top-1/2 transform -translate-y-1/2 z-10  w-8 h-8 rounded-full sm:w-10 sm:h-10 bg-white/30 dark:bg-gray-800/30 group-hover:bg-white/50 dark:group-hover:bg-gray-800/60 group-focus:ring-4 group-focus:ring-white dark:group-focus:ring-gray-800/70 group-focus:outline-none"
+      on:click={nextImage}
+      aria-label="Next image"
+    >
+      &#10095;
+    </button>
+  </div>
 </div>
 
 <style>
-	.relative img {
-		object-fit: cover;
-	}
+  .relative img {
+    object-fit: cover;
+  }
 </style>

VisualQnA/ui/svelte/src/lib/modules/upload/uploadImg.svelte

@@ -6,12 +6,11 @@
 <script lang="ts">
 	import { base64ImageStore } from "$lib/shared/stores/common/Store";
 	import { Dropzone } from "flowbite-svelte";
-	import Pica from 'pica';
 
 	let value = [];
 	export let imageUrl = "";
 
-	$: if (imageUrl !== "") {
+	$: if (imageUrl) {
 		uploadImage();
 	}
 
@@ -48,7 +47,7 @@
 	};
 
 	const handleChange = (event) => {
-				const files = event.target.files;
+		const files = event.target.files;
 		if (files.length > 0) {
 			value = [files[0].name]; // Allow only one file selection
 			readFileAsBase64(files[0]); // Convert to Base64
@@ -56,73 +55,14 @@
 	};
 
 	const readFileAsBase64 = (file) => {
-    const reader = new FileReader();
-    reader.onload = () => {
-        const base64Data = reader.result;
-        const fileType = file.type;
-
-        if (!fileType.includes("png")) {
-            convertImageToPNG(base64Data); // Convert if not PNG
-        } else {
-            base64ImageStore.set(base64Data); // Store Base64
-        }
-
-        imageUrl = URL.createObjectURL(file); // Create URL for preview
-    };
-    reader.readAsDataURL(file); // Read file as Data URL
-};
-
-const convertImageToPNG = async (base64Data) => {
-    if (!base64Data || !base64Data.startsWith("data:image/")) {
-        console.error("Invalid Base64 data");
-        return;
-    }
-
-    console.log("Starting image conversion...");
-
-    const img = new Image();
-    img.src = base64Data;
-
-    img.onload = async () => {
-        const canvas = document.createElement("canvas");
-        const ctx = canvas.getContext("2d");
-        let width = img.width;
-        let height = img.height;
-
-        // Set resize factor to 1 (no scaling) to keep the original size
-        const scaleFactor = 0.1; // Resize factor (keep original size)
-        width = Math.floor(width * scaleFactor);
-        height = Math.floor(height * scaleFactor);
-
-        canvas.width = width;
-        canvas.height = height;
-
-        ctx.drawImage(img, 0, 0, width, height); // Draw the original image (no resizing)
-
-        const outputCanvas = document.createElement("canvas");
-        outputCanvas.width = width;
-        outputCanvas.height = height;
-
-        const pica = new Pica();
-
-        try {
-            // Resize and compress the image using Pica
-            await pica.resize(canvas, outputCanvas);
-
-            // Convert canvas to PNG format with data URL
-            const pngDataUrl = outputCanvas.toDataURL("image/png", 0.8); // Adjust quality (0.9 is high, between 0-1)
-
-            // Store the Base64 PNG image
-            base64ImageStore.set(pngDataUrl);
-        } catch (err) {
-            console.error("Error during image processing:", err);
-        }
-    };
-
-    img.onerror = (err) => {
-        console.error("Error loading image:", err);
-    };
-};
+		const reader = new FileReader();
+		reader.onload = () => {
+			const base64Data = reader.result; // Get Base64 data
+			base64ImageStore.set(base64Data); // Store the Base64 string in the store
+			imageUrl = URL.createObjectURL(file); // Keep the object URL for preview
+		};
+		reader.readAsDataURL(file); // Read the file as a Data URL
+	};
 
 	const showFiles = (files) => {
 		if (files.length === 1) return files[0];

docker_images_list.md

@@ -2,44 +2,34 @@
 
 A list of released OPEA docker images in https://hub.docker.com/, contains all relevant images from the GenAIExamples, GenAIComps and GenAIInfra projects. Please expect more public available images in the future release.
 
-Take ChatQnA for example. ChatQnA is a chatbot application service based on the Retrieval Augmented Generation (RAG) architecture. It consists of [opea/embedding](https://hub.docker.com/r/opea/embedding), [opea/retriever](https://hub.docker.com/r/opea/retriever-redis), [opea/reranking-tei](https://hub.docker.com/r/opea/reranking-tei), [opea/llm-textgen](https://hub.docker.com/r/opea/llm-textgen), [opea/dataprep](https://hub.docker.com/r/opea/dataprep), [opea/chatqna](https://hub.docker.com/r/opea/chatqna), [opea/chatqna-ui](https://hub.docker.com/r/opea/chatqna-ui) and [opea/chatqna-conversation-ui](https://hub.docker.com/r/opea/chatqna-conversation-ui) (Optional) multiple microservices. Other services are similar, see the corresponding README for details.
+Take ChatQnA for example. ChatQnA is a chatbot application service based on the Retrieval Augmented Generation (RAG) architecture. It consists of [opea/embedding](https://hub.docker.com/r/opea/embedding), [opea/retriever](https://hub.docker.com/r/opea/retriever-redis), [opea/reranking-tei](https://hub.docker.com/r/opea/reranking-tei), [opea/llm-textgen](https://hub.docker.com/r/opea/llm-textgen), [opea/dataprep](), [opea/chatqna](https://hub.docker.com/r/opea/chatqna), [opea/chatqna-ui](https://hub.docker.com/r/opea/chatqna-ui) and [opea/chatqna-conversation-ui](https://hub.docker.com/r/opea/chatqna-conversation-ui) (Optional) multiple microservices. Other services are similar, see the corresponding README for details.
 
 ## Example images
 
 | Example Images                                                                                              | Dockerfile                                                                                                   | Description                                                                                                                                                                                                                                                                            |
 | ----------------------------------------------------------------------------------------------------------- | ------------------------------------------------------------------------------------------------------------ | -------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
-| [opea/audioqna](https://hub.docker.com/r/opea/audioqna)                                                     | [Link](https://github.com/opea-project/GenAIExamples/blob/main/AudioQnA/Dockerfile)                          | The docker image served as an audioqna gateway and using language modeling to generate answers to user queries by converting audio input to text, and then use text-to-speech (TTS) to convert those answers back to speech for interaction.                                           |
-| [opea/audioqna-ui](https://hub.docker.com/r/opea/audioqna-ui)                                               | [Link](https://github.com/opea-project/GenAIExamples/blob/main/AudioQnA/ui/docker/Dockerfile)                | The docker image acted as the audioqna UI entry for enabling seamless interaction with users                                                                                                                                                                                           |
-| [opea/audioqna-multilang](https://hub.docker.com/r/opea/audioqna-multilang)                                 | [Link](https://github.com/opea-project/GenAIExamples/blob/main/AudioQnA/Dockerfile.multilang)                | The docker image served as an audioqna gateway and using language modeling to generate answers to user queries by converting multilingual audio input to text, and then use multilingual text-to-speech (TTS) to convert those answers back to speech for interaction.                 |
-| [opea/avatarchatbot](https://hub.docker.com/r/opea/avatarchatbot)                                           | [Link](https://github.com/opea-project/GenAIExamples/blob/main/AvatarChatbot/Dockerfile)                     | The docker image served as a avatarchatbot gateway and interacted with users by  understanding their questions and providing relevant answers.                                                                                                                                         |
-| [opea/chatqna](https://hub.docker.com/r/opea/chatqna)                                                       | [Link](https://github.com/opea-project/GenAIExamples/blob/main/ChatQnA/Dockerfile)                           | The  docker image served as a chatqna gateway and interacted with users by understanding their questions and providing relevant answers.                                                                                                                                               |
-| [opea/chatqna-without-rerank](https://hub.docker.com/r/opea/chatqna-without-rerank)                         | [Link](https://github.com/opea-project/GenAIExamples/blob/main/ChatQnA/Dockerfile.without_rerank)            | The purpose of the docker image is to provide a user interface for chat-based Q&A using React. It allows for interaction with users and supports continuing conversations with a history that is stored in the browser's local storage.                                                |
+| [opea/audioqna](https://hub.docker.com/r/opea/audioqna)                                                     | [Link](https://github.com/opea-project/GenAIExamples/blob/main/AudioQnA/Dockerfile)                          | The docker image served as a chatqna gateway and using language modeling to generate answers to user queries by converting audio input to text, and then using text-to-speech (TTS) to convert those answers back to speech for interaction.                                           |
+| [opea/chatqna](https://hub.docker.com/r/opea/chatqna)                                                       | [Link](https://github.com/opea-project/GenAIExamples/blob/main/ChatQnA/Dockerfile)                           | The docker image served as a chatqna gateway and interacted with users by understanding their questions and providing relevant answers.                                                                                                                                                |
 | [opea/chatqna-ui](https://hub.docker.com/r/opea/chatqna-ui)                                                 | [Link](https://github.com/opea-project/GenAIExamples/blob/main/ChatQnA/ui/docker/Dockerfile)                 | The docker image acted as the chatqna UI entry for facilitating interaction with users for question answering                                                                                                                                                                          |
 | [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)           | The purpose of the docker image is to provide a user interface for chat-based Q&A using React. It allows for interaction with users and supports continuing conversations with a history that is stored in the browser's local storage.                                                |
 | [opea/chatqna-guardrails](https://hub.docker.com/r/opea/chatqna-guardrails)                                 | [Link](https://github.com/opea-project/GenAIExamples/blob/main/ChatQnA/Dockerfile.guardrails)                | This docker image is used to encapsulate chatqna's LLM service to secure model inputs and outputs. Guardrails proactively prevents models from interacting with insecure content and signals in time to stop insecure behavior.                                                        |
+| [opea/chatqna-without-rerank](https://hub.docker.com/r/opea/chatqna-without-rerank)                         | [Link](https://github.com/opea-project/GenAIExamples/blob/main/ChatQnA/Dockerfile.without_rerank)            | This docker image is used as a chatqna-without-rerank gateway to provide the chatqna service without rerank to Xeon customers who cannot run the Rerank service on HPUs, but need high performance and accuracy.                                                                       |
 | [opea/codegen](https://hub.docker.com/r/opea/codegen)                                                       | [Link](https://github.com/opea-project/GenAIExamples/blob/main/CodeGen/Dockerfile)                           | The docker image served as the codegen gateway to provide service of the automatic creation of source code from a higher-level representation                                                                                                                                          |
 | [opea/codegen-ui](https://hub.docker.com/r/opea/codegen-ui)                                                 | [Link](https://github.com/opea-project/GenAIExamples/blob/main/CodeGen/ui/docker/Dockerfile)                 | The docker image acted as the codegen UI entry for facilitating interaction with users for automatically generating code from user's description                                                                                                                                       |
 | [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)           | The purpose of the docker image is to provide a user interface for Codegen using React. It allows generating the appropriate code based on the current user input.                                                                                                                     |
 | [opea/codetrans](https://hub.docker.com/r/opea/codetrans)                                                   | [Link](https://github.com/opea-project/GenAIExamples/blob/main/CodeTrans/Dockerfile)                         | The docker image served as a codetrans gateway to provide service of converting source code written in one programming language into an equivalent version in another programming language                                                                                             |
 | [opea/codetrans-ui](https://hub.docker.com/r/opea/codetrans-ui)                                             | [Link](https://github.com/opea-project/GenAIExamples/blob/main/CodeTrans/ui/docker/Dockerfile)               | The docker image acted as the codetrans UI entry for facilitating interaction with users for translating one programming language to another one                                                                                                                                       |
-| [opea/doc-index-retriever](https://hub.docker.com/r/opea/doc-index-retriever)                               | [Link](https://github.com/opea-project/GenAIExamples/blob/main/DocIndexRetriever/Dockerfile)                 | The docker image acts as a DocRetriever gateway, It uses different methods to match user queries with a set of free text records.                                                                                                                                                      |
+| [opea/doc-index-retriever](https://hub.docker.com/r/opea/doc-index-retriever)                               | [Link](https://github.com/opea-project/GenAIExamples/blob/main/DocIndexRetriever/Dockerfile)                 | The docker image acts as a DocRetriever gateway, It uses different methods to match user queries with a set of free text records.                                                                                                                                                      |
 | [opea/docsum](https://hub.docker.com/r/opea/docsum)                                                         | [Link](https://github.com/opea-project/GenAIExamples/blob/main/DocSum/Dockerfile)                            | The docker image served as a docsum gateway to provide service of capturing the main points and essential details of the original text                                                                                                                                                 |
 | [opea/docsum-ui](https://hub.docker.com/r/opea/docsum-ui)                                                   | [Link](https://github.com/opea-project/GenAIExamples/blob/main/DocSum/ui/docker/Dockerfile)                  | The docker image acted as the docsum UI entry for facilitating interaction with users for document summarization                                                                                                                                                                       |
 | [opea/docsum-react-ui](https://hub.docker.com/r/opea/docsum-react-ui)                                       | [Link](https://github.com/opea-project/GenAIExamples/blob/main/DocSum/ui/docker/Dockerfile.react)            | The purpose of the docker image is to provide a user interface for document summary using React. It allows upload a file or paste text and then click on “Generate Summary” to get a condensed summary of the generated content and automatically scroll to the bottom of the summary. |
-| [opea/docsum-gradio-ui](https://hub.docker.com/r/opea/docsum-gradio-ui)                                     | [Link](https://github.com/opea-project/GenAIExamples/blob/main/DocSum/ui/docker/Dockerfile.gradio)           | The purpose of the docker image is to provides a user interface for summarizing documents and text using a Dockerized frontend application. Users can upload files or paste text to generate summaries.                                                                                |
-| [opea/edgecraftrag](https://hub.docker.com/r/opea/edgecraftrag)                                             | [Link](https://github.com/opea-project/GenAIExamples/blob/main/EdgeCraftRAG/Dockerfile)                      | The docker image served as an Edge Craft RAG (EC-RAG) gateway, delivering a customizable and production-ready Retrieval-Augmented Generation system optimized for edge solutions.                                                                                                      |
-| [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)         | The docker image acted as the Edge Craft RAG (EC-RAG) UI entry. It ensuring high-quality, performant interactions tailored for edge environments.                                                                                                                                      |
-| [opea/edgecraftrag-server](https://hub.docker.com/r/opea/edgecraftrag-server)                               | [Link](https://github.com/opea-project/GenAIExamples/blob/main/EdgeCraftRAG/Dockerfile.server)               | The docker image served as an Edge Craft RAG (EC-RAG) server, delivering a customizable and production-ready Retrieval-Augmented Generation system optimized for edge solutions.                                                                                                       |
 | [opea/faqgen](https://hub.docker.com/r/opea/faqgen)                                                         | [Link](https://github.com/opea-project/GenAIExamples/blob/main/FaqGen/Dockerfile)                            | The docker image served as a faqgen gateway and automatically generating comprehensive, natural sounding Frequently Asked Questions (FAQs) from documents, legal texts, customer inquiries and other sources.                                                                          |
-| [opea/faqgen-ui](https://hub.docker.com/r/opea/faqgen-ui)                                                   | [Link](https://github.com/opea-project/GenAIExamples/blob/main/FaqGen/ui/docker/Dockerfile)                  | The docker image serves as the faqgen UI entry point for easy interaction with users, generating FAQs by pasting in question text.                                                                                                                                                     |
+| [opea/faqgen-ui](https://hub.docker.com/r/opea/faqgen-ui)                                                   | [Link](https://github.com/opea-project/GenAIExamples/blob/main/FaqGen/ui/docker/Dockerfile)                  | The docker image serves as the docsum UI entry point for easy interaction with users, generating FAQs by pasting in question text.                                                                                                                                                     |
 | [opea/faqgen-react-ui](https://hub.docker.com/r/opea/faqgen-react-ui)                                       | [Link](https://github.com/opea-project/GenAIExamples/blob/main/FaqGen/ui/docker/Dockerfile.react)            | The purpose of the docker image is to provide a user interface for Generate FAQs using React. It allows generating FAQs by uploading files or pasting text.                                                                                                                            |
-| [opea/graphrag](https://hub.docker.com/r/opea/graphrag)                                                     | [Link](https://github.com/opea-project/GenAIExamples/blob/main/GraphRAG/Dockerfile)                          | The docker image served as a GraphRAG gateway, leveraging a knowledge graph derived from source documents to address both local and global queries.                                                                                                                                    |
-| [opea/graphrag-ui](https://hub.docker.com/r/opea/graphrag-ui)                                               | [Link](https://github.com/opea-project/GenAIExamples/blob/main/GraphRAG/ui/docker/Dockerfile)                | The docker image acted as the GraphRAG UI entry for facilitating interaction with users                                                                                                                                                                                                |
-| [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)          | The purpose of the docker image is to provide a user interface for GraphRAG using React.                                                                                                                                                                                               |
-| [opea/multimodalqna](https://hub.docker.com/r/opea/multimodalqna)                                           | [Link](https://github.com/opea-project/GenAIExamples/blob/main/MultimodalQnA/Dockerfile)                     | The docker image served as a multimodalqna gateway and dynamically fetches the most relevant multimodal information (frames, transcripts, and/or subtitles) from the user's video collection to solve the problem.                                                                     |
-| [opea/multimodalqna-ui](https://hub.docker.com/r/opea/multimodalqna-ui)                                     | [Link](https://github.com/opea-project/GenAIExamples/blob/main/MultimodalQnA/ui/docker/Dockerfile)           | The docker image serves as the multimodalqna UI entry point for easy interaction with users. Answers to questions are generated from videos uploaded by users..                                                                                                                        |
+| [opea/multimodalqna](https://hub.docker.com/r/opea/multimodalqna)                                           | [Link](https://github.com/opea-project/GenAIExamples/blob/main/MultimodalQnA/Dockerfile)                     | The docker image served as a multimodalqna gateway and dynamically fetches the most relevant multimodal information (frames, transcripts, and/or subtitles) from the user's video, image, or audio collection to solve the problem.                                                    |
+| [opea/multimodalqna-ui](https://hub.docker.com/r/opea/multimodalqna-ui)                                     | [Link](https://github.com/opea-project/GenAIExamples/blob/main/MultimodalQnA/ui/docker/Dockerfile)           | The docker image serves as the multimodalqna UI entry point for easy interaction with users. Answers to questions are generated from uploaded by users.                                                                                                                                |
 | [opea/productivity-suite-react-ui-server](https://hub.docker.com/r/opea/productivity-suite-react-ui-server) | [Link](https://github.com/opea-project/GenAIExamples/blob/main/ProductivitySuite/ui/docker/Dockerfile.react) | The purpose of the docker image is to provide a user interface for Productivity Suite Application using React. It allows interaction by uploading documents and inputs.                                                                                                                |
-| [opea/searchqna](https://hub.docker.com/r/opea/searchqna)                                                   | [Link](https://github.com/opea-project/GenAIExamples/blob/main/SearchQnA/Dockerfile)                         | The docker image served as the searchqna gateway to provide service of retrieving accurate and relevant answers to user queries from a knowledge base or dataset                                                                                                                       |
+| [opea/searchqna](https://hub.docker.com/r/opea/searchqna/tags)                                              | [Link](https://github.com/opea-project/GenAIExamples/blob/main/SearchQnA/Dockerfile)                         | The docker image served as the searchqna gateway to provide service of retrieving accurate and relevant answers to user queries from a knowledge base or dataset                                                                                                                       |
 | [opea/searchqna-ui](https://hub.docker.com/r/opea/searchqna-ui)                                             | [Link](https://github.com/opea-project/GenAIExamples/blob/main/SearchQnA/ui/docker/Dockerfile)               | The docker image acted as the searchqna UI entry for facilitating interaction with users for question answering                                                                                                                                                                        |
 | [opea/translation](https://hub.docker.com/r/opea/translation)                                               | [Link](https://github.com/opea-project/GenAIExamples/blob/main/Translation/Dockerfile)                       | The docker image served as the translation gateway to provide service of language translation                                                                                                                                                                                          |
 | [opea/translation-ui](https://hub.docker.com/r/opea/translation-ui)                                         | [Link](https://github.com/opea-project/GenAIExamples/blob/main/Translation/ui/docker/Dockerfile)             | The docker image acted as the translation UI entry for facilitating interaction with users for language translation                                                                                                                                                                    |
@@ -50,65 +40,46 @@ Take ChatQnA for example. ChatQnA is a chatbot application service based on the
 
 ## Microservice images
 
-| Microservice Images                                                                                                 | Dockerfile                                                                                                                        | Description                                                                                                                                                                                                   |
-| ------------------------------------------------------------------------------------------------------------------- | --------------------------------------------------------------------------------------------------------------------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
-| [opea/agent](https://hub.docker.com/r/opea/agent)                                                                   | [Link](https://github.com/opea-project/GenAIComps/blob/main/comps/agent/src/Dockerfile)                                           | The docker image exposed the OPEA agent microservice for GenAI application use                                                                                                                                |
-| [opea/agent-ui](https://hub.docker.com/r/opea/agent-ui)                                                             | [Link](https://github.com/opea-project/GenAIExamples/blob/main/AgentQnA/ui/docker/Dockerfile)                                     | The docker image exposed the OPEA agent microservice UI entry for GenAI application use                                                                                                                       |
-| [opea/asr](https://hub.docker.com/r/opea/asr)                                                                       | [Link](https://github.com/opea-project/GenAIComps/blob/main/comps/asr/src/Dockerfile)                                             | The docker image exposed the OPEA Audio-Speech-Recognition microservice for GenAI application use                                                                                                             |
-| [opea/animation](https://hub.docker.com/r/opea/animation)                                                           | [Link](https://github.com/opea-project/GenAIComps/blob/main/comps/animation/src/Dockerfile)                                       | The purpose of the Docker image is to expose the OPEA Avatar Animation microservice for GenAI application use.                                                                                                |
-| [opea/chathistory-mongo-server](https://hub.docker.com/r/opea/chathistory-mongo-server)                             | [Link](https://github.com/opea-project/GenAIComps/blob/main/comps/chathistory/src/Dockerfile)                                     | The docker image exposes OPEA Chat History microservice which based on MongoDB database, designed to allow user to store, retrieve and manage chat conversations                                              |
-| [opea/dataprep](https://hub.docker.com/r/opea/dataprep)                                                             | [Link](https://github.com/opea-project/GenAIComps/blob/main/comps/dataprep/src/Dockerfile)                                        | The docker image exposed the OPEA dataprep microservice for GenAI application use                                                                                                                             |
-| [opea/embedding](https://hub.docker.com/r/opea/embedding)                                                           | [Link](https://github.com/opea-project/GenAIComps/blob/main/comps/embeddings/src/Dockerfile)                                      | The docker image exposed the OPEA mosec embedding microservice  for GenAI application use                                                                                                                     |
-| [opea/embedding-multimodal-clip](https://hub.docker.com/r/opea/embedding-multimodal-clip)                           | [Link](https://github.com/opea-project/GenAIComps/blob/main/comps/third_parties/clip/src/Dockerfile)                              | The docker image exposed the OPEA mosec embedding microservice base on Langchain framework for GenAI application use                                                                                          |
-| [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)                       | The docker image exposes OPEA multimodal embedded microservices based on bridgetower for use by GenAI applications                                                                                            |
-| [opea/embedding-multimodal-bridgetower-gaudi](https://hub.docker.com/r/opea/embedding-multimodal-bridgetower-gaudi) | [Link](https://github.com/opea-project/GenAIComps/blob/main/comps/third_parties/bridgetower/src/Dockerfile.intel_hpu)             | The docker image exposes OPEA multimodal embedded microservices based on bridgetower for use by GenAI applications on the Gaudi                                                                               |
-| [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)                             | The docker image exposes that the OPEA feedback management microservice uses a MongoDB database for GenAI applications.                                                                                       |
-| [opea/finetuning](https://hub.docker.com/r/opea/finetuning)                                                         | [Link](https://github.com/opea-project/GenAIComps/blob/main/comps/finetuning/src/Dockerfile)                                      | The docker image exposed the OPEA Fine-tuning microservice for GenAI application use                                                                                                                          |
-| [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)                            | The docker image exposed the OPEA Fine-tuning microservice for GenAI application use on the Gaudi                                                                                                             |
-| [opea/guardrails](https://hub.docker.com/r/opea/guardrails)                                                         | [Link](https://github.com/opea-project/GenAIComps/blob/main/comps/guardrails/src/guardrails/Dockerfile)                           | The docker image exposed the OPEA guardrail microservice for GenAI application use                                                                                                                            |
-| [opea/guardrails-toxicity-predictionguard](https://hub.docker.com/r/opea/guardrails-toxicity-predictionguard)       | [Link](https://github.com/opea-project/GenAIComps/blob/main/comps/guardrails/src/toxicity_detection/Dockerfile)                   | The docker image exposed the OPEA guardrail microservice to provide toxicity detection for GenAI application use                                                                                              |
-| [opea/guardrails-pii-predictionguard](https://hub.docker.com/r/opea/guardrails-pii-predictionguard)                 | [Link](https://github.com/opea-project/GenAIComps/blob/main/comps/guardrails/src/pii_detection/Dockerfile)                        | The docker image exposed the OPEA guardrail microservice to provide PII detection for GenAI application use                                                                                                   |
-| [opea/guardrails-injection-predictionguard](https://hub.docker.com/r/opea/guardrails-injection-predictionguard)     | [Link](https://github.com/opea-project/GenAIComps/blob/main/comps/guardrails/src/prompt_injection/Dockerfile)                     | The docker image exposed the OPEA guardrail microservice to provide injection predictionguard for GenAI application use                                                                                       |
-| [opea/guardrails-hallucination-detection](https://hub.docker.com/r/opea/guardrails-hallucination-detection)         | [Link](https://github.com/opea-project/GenAIComps/blob/main/comps/guardrails/src/hallucination_detection/Dockerfile)              | The docker image exposed the OPEA guardrail microservice to provide hallucination detection for GenAI application use                                                                                         |
-| [opea/guardrails-factuality-predictionguard](https://hub.docker.com/r/opea/guardrails-factuality-predictionguard)   | [Link](https://github.com/opea-project/GenAIComps/blob/main/comps/guardrails/src/factuality_alignment/Dockerfile)                 | The docker image exposed the OPEA guardrail microservice to provide factuality predictionguard for GenAI application use                                                                                      |
-| [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)                       | The docker image exposed the OPEA guardrail microservice to provide bias detection for GenAI application use                                                                                                  |
-| [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)                           | The purpose of the Docker image is to expose the OPEA Image-to-Image microservice for GenAI application use on the Gaudi.                                                                                     |
-| [opea/image2image](https://hub.docker.com/r/opea/image2image)                                                       | [Link](https://github.com/opea-project/GenAIComps/blob/main/comps/image2image/src/Dockerfile)                                     | The purpose of the Docker image is to expose the OPEA Image-to-Image microservice for GenAI application use.                                                                                                  |
-| [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)                           | The purpose of the Docker image is to expose the OPEA image-to-video microservice for GenAI application use on the Gaudi.                                                                                     |
-| [opea/image2video](https://hub.docker.com/r/opea/image2video)                                                       | [Link](https://github.com/opea-project/GenAIComps/blob/main/comps/image2video/src/Dockerfile)                                     | The purpose of the Docker image is to expose the OPEA image-to-video microservice for GenAI application use.                                                                                                  |
-| [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)                            | The docker image exposed the OPEA LLM microservice upon textgen docker image for GenAI application use                                                                                                        |
-| [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)                  | The docker image exposed the OPEA LLM microservice upon textgen docker image for GenAI application use on the Gaudi2                                                                                          |
-| [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)                                  | The docker image exposed the OPEA LLM microservice upon eval docker image for GenAI application use                                                                                                           |
-| [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)                          | The docker image exposed the OPEA LLM microservice upon docsum docker image for GenAI application use                                                                                                         |
-| [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)                             | This docker image is designed to build a frequently asked questions microservice using the HuggingFace Text Generation Inference(TGI) framework. The microservice accepts document input and generates a FAQ. |
-| [opea/lvm](https://hub.docker.com/r/opea/lvm)                                                                       | [Link](https://github.com/opea-project/GenAIComps/blob/main/comps/lvms/src/Dockerfile)                                            | The docker image exposed the OPEA large visual model (LVM) microservice for GenAI application use                                                                                                             |
-| [opea/lvm-llava](https://hub.docker.com/r/opea/lvm-llava)                                                           | [Link](https://github.com/opea-project/GenAIComps/blob/main/comps/lvms/src/integrations/dependency/llava/Dockerfile)              | The docker image exposed the OPEA microservice running LLaVA as a large visual model (LVM) server for GenAI application use                                                                                   |
-| [opea/lvm-video-llama](https://hub.docker.com/r/opea/lvm-video-llama)                                               | [Link](https://github.com/opea-project/GenAIComps/blob/main/comps/lvms/src/integrations/dependency/video-llama/Dockerfile)        | The docker image exposed the OPEA microservice running Video-Llama as a large visual model (LVM) for GenAI application use                                                                                    |
-| [opea/lvm-predictionguard](https://hub.docker.com/r/opea/lvm-predictionguard)                                       | [Link](https://github.com/opea-project/GenAIComps/blob/main/comps/lvms/src/integrations/dependency/predictionguard/Dockerfile)    | The docker image exposed the OPEA microservice running predictionguard as a large visual model (LVM) server for GenAI application use                                                                         |
-| [opea/llava-gaudi](https://hub.docker.com/r/opea/llava-gaudi)                                                       | [Link](https://github.com/opea-project/GenAIComps/blob/main/comps/lvms/src/integrations/dependency/llava/Dockerfile.intel_hpu)    | The docker image exposed the OPEA microservice running LLaVA as a large visual model (LVM) service for GenAI application use on the Gaudi2                                                                    |
-| [opea/lvm-llama-vision](https://hub.docker.com/r/opea/lvm-llama-vision)                                             | [Link](https://github.com/opea-project/GenAIComps/blob/main/comps/lvms/src/integrations/dependency/llama-vision/Dockerfile)       | The docker image exposed the OPEA microservice running Llama Vision as the base large visual model service for GenAI application use                                                                          |
-| [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/lvms/src/integrations/dependency/llama-vision/Dockerfile.tp)    | The docker image exposed the OPEA microservice running Llama Vision with deepspeed as the base large visual model service for GenAI application use                                                           |
-| [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/lvms/src/integrations/dependency/llama-vision/Dockerfile.guard) | The docker image exposed the OPEA microservice running Llama Vision Guard as the base large visual model service for GenAI application use                                                                    |
-| [opea/promptregistry-mongo](https://hub.docker.com/r/opea/promptregistry-mongo)                                     | [Link](https://github.com/opea-project/GenAIComps/blob/main/comps/prompt_registry/src/Dockerfile)                                 | The docker image exposes the OPEA Prompt Registry microservices which based on MongoDB database, designed to store and retrieve user's preferred prompts                                                      |
-| [opea/reranking](https://hub.docker.com/r/opea/reranking)                                                           | [Link](https://github.com/opea-project/GenAIComps/blob/main/comps/rerankings/src/Dockerfile)                                      | The docker image exposed the OPEA reranking microservice for GenAI application use                                                                                                                            |
-| [opea/retriever](https://hub.docker.com/r/opea/retriever)                                                           | [Link](https://github.com/opea-project/GenAIComps/blob/main/comps/retrievers/src/Dockerfile)                                      | The docker image exposed the OPEA retrieval microservice for GenAI application use                                                                                                                            |
-| [opea/text2image](https://hub.docker.com/r/opea/text2image)                                                         | [Link](https://github.com/opea-project/GenAIComps/blob/main/comps/text2image/src/Dockerfile)                                      | The docker image exposed the OPEA text-to-image microservice for GenAI application use                                                                                                                        |
-| [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)                            | The docker image exposed the OPEA text-to-image microservice for GenAI application use on the Gaudi                                                                                                           |
-| [opea/text2image-ui](https://hub.docker.com/r/opea/text2image-ui)                                                   | [Link](https://github.com/opea-project/GenAIExamples/blob/main/Text2Image/ui/docker/Dockerfile)                                   | The docker image exposed the OPEA text-to-image microservice UI entry for GenAI application use                                                                                                               |
-| [opea/text2sql](https://hub.docker.com/r/opea/text2sql)                                                             | [Link](https://github.com/opea-project/GenAIComps/blob/main/comps/text2sql/src/Dockerfile)                                        | The docker image exposed the OPEA text to Structured Query Language microservice for GenAI application use                                                                                                    |
-| [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)                                  | The docker image exposed the OPEA text to Structured Query Language microservice react UI entry for GenAI application use                                                                                     |
-| [opea/tts](https://hub.docker.com/r/opea/tts)                                                                       | [Link](https://github.com/opea-project/GenAIComps/blob/main/comps/tts/src/Dockerfile)                                             | The docker image exposed the OPEA Text-To-Speech microservice for GenAI application use                                                                                                                       |
-| [opea/speecht5](https://hub.docker.com/r/opea/speecht5)                                                             | [Link](https://github.com/opea-project/GenAIComps/blob/main/comps/tts/src/integrations/dependency/speecht5/Dockerfile)            | The docker image exposed the OPEA SpeechT5 service for GenAI application use                                                                                                                                  |
-| [opea/speecht5-gaudi](https://hub.docker.com/r/opea/speecht5-gaudi)                                                 | [Link](https://github.com/opea-project/GenAIComps/blob/main/comps/tts/src/integrations/dependency/speecht5/Dockerfile.intel_hpu)  | The docker image exposed the OPEA SpeechT5 service on Gaudi2 for GenAI application use                                                                                                                        |
-| [opea/gpt-sovits](https://hub.docker.com/r/opea/gpt-sovits)                                                         | [Link](https://github.com/opea-project/GenAIComps/blob/main/comps/tts/src/integrations/dependency/gpt-sovits/Dockerfile)          | The docker image exposed the OPEA gpt-sovits service for GenAI application use                                                                                                                                |
-| [opea/nginx](https://hub.docker.com/r/opea/nginx)                                                                   | [Link](https://github.com/opea-project/GenAIComps/blob/main/comps/third_parties/nginx/src/Dockerfile)                             | The docker image exposed the OPEA nginx microservice for GenAI application use                                                                                                                                |
-| [opea/vectorstore-pathway](https://hub.docker.com/r/opea/vectorstore-pathway)                                       | [Link](https://github.com/opea-project/GenAIComps/blob/main/comps/third_parties/pathway/src/Dockerfile)                           | The docker image exposed the OPEA Vectorstores microservice with Pathway for GenAI application use                                                                                                            |
-| [opea/wav2lip](https://hub.docker.com/r/opea/wav2lip)                                                               | [Link](https://github.com/opea-project/GenAIComps/blob/main/comps/third_parties/wav2lip/src/Dockerfile)                           | The docker image exposed the OPEA Generate lip movements from audio files microservice with Pathway for GenAI application use                                                                                 |
-| [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)                 | The docker image exposed the OPEA Generate lip movements from audio files microservice with Pathway for GenAI application use on the Gaudi2                                                                   |
-| [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)                    | The docker image powered by vllm-project for deploying and serving vllm Models on Arc                                                                                                                         |
-| [opea/vllm-openvino](https://hub.docker.com/r/opea/vllm-openvino)                                                   | [Link](https://github.com/vllm-project/vllm/blob/main/Dockerfile.openvino)                                                        | The docker image powered by vllm-project for deploying and serving vllm Models of the Openvino Framework                                                                                                      |
-| [opea/vllm-gaudi](https://hub.docker.com/r/opea/vllm-gaudi)                                                         | [Link](https://github.com/HabanaAI/vllm-fork/blob/habana_main/Dockerfile.hpu)                                                     | The docker image powered by vllm-project for deploying and serving vllm Models on Gaudi2                                                                                                                      |
-| [opea/vllm](https://hub.docker.com/r/opea/vllm)                                                                     | [Link](https://github.com/HabanaAI/vllm-fork/blob/habana_main/Dockerfile.cpu)                                                     | The docker image powered by vllm-project for deploying and serving vllm Models                                                                                                                                |
-| [opea/whisper-gaudi](https://hub.docker.com/r/opea/whisper-gaudi)                                                   | [Link](https://github.com/opea-project/GenAIComps/blob/main/comps/asr/src/integrations/dependency/whisper/Dockerfile.intel_hpu)   | The docker image exposed the OPEA Whisper service on Gaudi2 for GenAI application use                                                                                                                         |
-| [opea/whisper](https://hub.docker.com/r/opea/whisper)                                                               | [Link](https://github.com/opea-project/GenAIComps/blob/main/comps/asr/src/integrations/dependency/whisper/Dockerfile)             | The docker image exposed the OPEA Whisper service for GenAI application use                                                                                                                                   |
-| [opea/web-retriever](https://hub.docker.com/r/opea/web-retriever)                                                   | [Link](https://github.com/opea-project/GenAIComps/blob/main/comps/web_retrievers/src/Dockerfile)                                  | The docker image exposed the OPEA retrieval microservice based on chroma vectordb for GenAI application use                                                                                                   |
+| Microservice Images                                                                                                 | Dockerfile                                                                                                                       | Description                                                                                                                                                                                                            |
+| ------------------------------------------------------------------------------------------------------------------- | -------------------------------------------------------------------------------------------------------------------------------- | ---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
+| [opea/agent]()                                                                                                      | [Link](https://github.com/opea-project/GenAIComps/blob/main/comps/agent/src/Dockerfile)                                          | The docker image exposed the OPEA agent microservice for GenAI application use                                                                                                                                         |
+| [opea/asr](https://hub.docker.com/r/opea/asr)                                                                       | [Link](https://github.com/opea-project/GenAIComps/blob/main/comps/asr/src/Dockerfile)                                            | The docker image exposed the OPEA Audio-Speech-Recognition microservice for GenAI application use                                                                                                                      |
+| [opea/chathistory-mongo-server](https://hub.docker.com/r/opea/chathistory-mongo-server)                             | [Link](https://github.com/opea-project/GenAIComps/blob/main/comps/chathistory/src/Dockerfile)                                    | The docker image exposes OPEA Chat History microservice which based on MongoDB database, designed to allow user to store, retrieve and manage chat conversations                                                       |
+| [opea/dataprep]()                                                                                                   | [Link](https://github.com/opea-project/GenAIComps/blob/main/comps/dataprep/src/Dockerfile)                                       | The docker image exposed the OPEA dataprep microservice based on many vectordbs for GenAI application use                                                                                                              |
+| [opea/embedding-multimodal-clip](https://hub.docker.com/r/opea/embedding-multimodal-clip)                           | [Link](https://github.com/opea-project/GenAIComps/blob/main/comps/third_parties/clip/src/Dockerfile)                             | The docker image exposes OPEA multimodal CLIP-based embedded microservices for use by GenAI applications                                                                                                               |
+| [opea/embedding](https://hub.docker.com/r/opea/embedding)                                                           | [Link](https://github.com/opea-project/GenAIComps/blob/main/comps/embeddings/src/Dockerfile)                                     | The docker image exposes OPEA multimodal embedded microservices for use by GenAI applications                                                                                                                          |
+| [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)                      | The docker image exposes OPEA multimodal embedded microservices based on bridgetower for use by GenAI applications                                                                                                     |
+| [opea/embedding-multimodal-bridgetower-gaudi](https://hub.docker.com/r/opea/embedding-multimodal-bridgetower-gaudi) | [Link](https://github.com/opea-project/GenAIComps/blob/main/comps/third_parties/bridgetower/src/Dockerfile.intel_hpu)            | The docker image exposes OPEA multimodal embedded microservices based on bridgetower for use by GenAI applications on the Gaudi                                                                                        |
+| [opea/feedbackmanagement](https://hub.docker.com/r/opea/feedbackmanagement)                                         | [Link](https://github.com/opea-project/GenAIComps/blob/main/comps/feedback_management/src/Dockerfile)                            | The docker image exposes that the OPEA feedback management microservice uses a MongoDB database for GenAI applications.                                                                                                |
+| [opea/finetuning](https://hub.docker.com/r/opea/finetuning)                                                         | [Link](https://github.com/opea-project/GenAIComps/blob/main/comps/finetuning/src/Dockerfile)                                     | The docker image exposed the OPEA Fine-tuning microservice for GenAI application use                                                                                                                                   |
+| [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)                           | The docker image exposed the OPEA Fine-tuning microservice for GenAI application use on the Gaudi                                                                                                                      |
+| [opea/gmcrouter](https://hub.docker.com/r/opea/gmcrouter)                                                           | [Link](https://github.com/opea-project/GenAIInfra/blob/main/microservices-connector/Dockerfile.manager)                          | The docker image served as one of key parts of the OPEA GenAI Microservice Connector(GMC) to route the traffic among the microservices defined in GMC                                                                  |
+| [opea/gmcmanager](https://hub.docker.com/r/opea/gmcmanager)                                                         | [Link](https://github.com/opea-project/GenAIInfra/blob/main/microservices-connector/Dockerfile.router)                           | The docker image served as one of key parts of the OPEA GenAI Microservice Connector(GMC) to be controller manager to handle GMC CRD                                                                                   |
+| [opea/guardrails]()                                                                                                 | [Link](https://github.com/opea-project/GenAIComps/blob/main/comps/guardrails/src/guardrails/Dockerfile)                          | The docker image exposed the OPEA guardrail microservice to provide content review for GenAI application use                                                                                                           |
+| [opea/guardrails-toxicity-detection](https://hub.docker.com/r/opea/guardrails-toxicity-detection)                   | [Link](https://github.com/opea-project/GenAIComps/blob/main/comps/guardrails/src/toxicity_detection/Dockerfile)                  | The docker image exposed the OPEA guardrail microservice to provide toxicity detection for GenAI application use                                                                                                       |
+| [opea/guardrails-pii-detection](https://hub.docker.com/r/opea/guardrails-pii-detection)                             | [Link](https://github.com/opea-project/GenAIComps/blob/main/comps/guardrails/src/pii_detection/Dockerfile)                       | The docker image exposed the OPEA guardrail microservice to provide PII detection for GenAI application use                                                                                                            |
+| [opea/llm-docsum]()                                                                                                 | [Link](https://github.com/opea-project/GenAIComps/blob/main/comps/llms/src/doc-summarization/Dockerfile)                         | This docker image is designed to build a document summarization microservice using the HuggingFace Text Generation Inference(TGI) framework. The microservice accepts document input and generates a document summary. |
+| [opea/llm-faqgen]()                                                                                                 | [Link](https://github.com/opea-project/GenAIComps/blob/main/comps/llms/src/faq-generation/Dockerfile)                            | This docker image is designed to build a frequently asked questions microservice using the HuggingFace Text Generation Inference(TGI) framework. The microservice accepts document input and generates a FAQ.          |
+| [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)                           | The docker image exposed the OPEA LLM microservice upon TGI docker image for GenAI application use                                                                                                                     |
+| [opea/llava-gaudi](https://hub.docker.com/r/opea/llava-hpu)                                                         | [Link](https://github.com/opea-project/GenAIComps/blob/main/comps/lvms/src/integrations/dependency/llava/Dockerfile.intel_hpu)   | The docker image exposed the OPEA microservice running LLaVA as a large visual model (LVM) service for GenAI application use on the Gaudi                                                                              |
+| [opea/lvm]()                                                                                                        | [Link](https://github.com/opea-project/GenAIComps/blob/main/comps/lvms/src/Dockerfile)                                           | This docker image is designed to build a large visual model (LVM) unified wrapper service                                                                                                                              |
+| [opea/lvm-llava](https://hub.docker.com/r/opea/lvm-llava)                                                           | [Link](https://github.com/opea-project/GenAIComps/blob/main/comps/lvms/src/integrations/dependency/llava/Dockerfile)             | The docker image exposed the OPEA microservice running LLaVA as a large visual model (LVM) server for GenAI application use                                                                                            |
+| [opea/lvm-video-llama](https://hub.docker.com/r/opea/lvm-video-llama)                                               | [Link](https://github.com/opea-project/GenAIComps/blob/main/comps/lvms/src/integrations/dependency/video-llama/Dockerfile)       | The docker image exposed the OPEA microservice running Video LLaMA as a large visual model (LVM) server for GenAI application use                                                                                      |
+| [opea/lvm-llama-vision]()                                                                                           | [Link](https://github.com/opea-project/GenAIComps/blob/main/comps/lvms/src/integrations/dependency/llama-vision/Dockerfile)      | The docker image exposed the OPEA microservice running LLaMA Vision as a large visual model (LVM) server for GenAI application use                                                                                     |
+| [opea/lvm-predictionguard](https://hub.docker.com/r/opea/lvm-predictionguard)                                       | [Link](https://github.com/opea-project/GenAIComps/blob/main/comps/lvms/src/integrations/dependency/predictionguard/Dockerfile)   | The docker image exposed the OPEA microservice running PredictionGuard as a large visual model (LVM) server for GenAI application use                                                                                  |
+| [opea/nginx](https://hub.docker.com/r/opea/nginx)                                                                   | [Link](https://github.com/opea-project/GenAIComps/blob/main/comps/third_parties/nginx/src/Dockerfile)                            | The docker image exposed the OPEA nginx microservice for GenAI application use                                                                                                                                         |
+| [opea/pathway](https://hub.docker.com/r/opea/vectorstore-pathway)                                                   | [Link](https://github.com/opea-project/GenAIComps/blob/main/comps/third_parties/pathway/src/Dockerfile)                          | The docker image exposed the OPEA Vectorstores microservice with Pathway for GenAI application use                                                                                                                     |
+| [opea/promptregistry-mongo-server](https://hub.docker.com/r/opea/promptregistry-mongo-server)                       | [Link](https://github.com/opea-project/GenAIComps/blob/main/comps/prompt_registry/src/Dockerfile)                                | The docker image exposes the OPEA Prompt Registry microservices which based on MongoDB database, designed to store and retrieve user's preferred prompts                                                               |
+| [opea/reranking]()                                                                                                  | [Link](https://github.com/opea-project/GenAIComps/blob/main/comps/rerankings/src/Dockerfile)                                     | The docker image exposed the OPEA reranking microservice based on tei docker image for GenAI application use                                                                                                           |
+| [opea/retriever]()                                                                                                  | [Link](https://github.com/opea-project/GenAIComps/blob/main/comps/retrievers/src/Dockerfile)                                     | The docker image exposed the OPEA retrieval microservice based on milvus vectordb for GenAI application use                                                                                                            |
+| [opea/speecht5](https://hub.docker.com/r/opea/speecht5)                                                             | [Link](https://github.com/opea-project/GenAIComps/blob/main/comps/tts/src/integrations/dependency/speecht5/Dockerfile)           | The docker image exposed the OPEA SpeechT5 service for GenAI application use                                                                                                                                           |
+| [opea/speecht5-gaudi](https://hub.docker.com/r/opea/speecht5-gaudi)                                                 | [Link](https://github.com/opea-project/GenAIComps/blob/main/comps/tts/src/integrations/dependency/speecht5/Dockerfile.intel_hpu) | The docker image exposed the OPEA SpeechT5 service on Gaudi2 for GenAI application use                                                                                                                                 |
+| [opea/tei-gaudi](https://hub.docker.com/r/opea/tei-gaudi/tags)                                                      | [Link](https://github.com/huggingface/tei-gaudi/blob/habana-main/Dockerfile-hpu)                                                 | The docker image powered by HuggingFace Text Embedding Inference (TEI) on Gaudi2 for deploying and serving Embedding Models                                                                                            |
+| [opea/lvm-video-llama](https://hub.docker.com/r/opea/lvm-video-llama)                                               | [Link](https://github.com/opea-project/GenAIComps/blob/main/comps/lvms/src/integrations/dependency/video-llama/Dockerfile)       | The docker image exposed the OPEA microservice running Video-Llama as a large visual model (LVM) server for GenAI application use                                                                                      |
+| [opea/tts](https://hub.docker.com/r/opea/tts)                                                                       | [Link](https://github.com/opea-project/GenAIComps/blob/main/comps/tts/src/Dockerfile)                                            | The docker image exposed the OPEA Text-To-Speech microservice for GenAI application use                                                                                                                                |
+| [opea/vllm](https://hub.docker.com/r/opea/vllm)                                                                     | [Link](https://github.com/vllm-project/vllm/blob/main/Dockerfile.cpu)                                                            | The docker image powered by vllm-project for deploying and serving vllm Models                                                                                                                                         |
+| [opea/vllm-gaudi]()                                                                                                 | [Link](https://github.com/HabanaAI/vllm-fork/blob/habana_main/Dockerfile.hpu)                                                    | The docker image powered by vllm-fork for deploying and serving vllm-gaudi Models                                                                                                                                      |
+| [opea/vllm-openvino](https://hub.docker.com/r/opea/vllm-openvino)                                                   | [Link](https://github.com/vllm-project/vllm/blob/main/Dockerfile.openvino)                                                       | The docker image powered by vllm-project for deploying and serving vllm Models of the Openvino Framework                                                                                                               |
+| [opea/web-retriever]()                                                                                              | [Link](https://github.com/opea-project/GenAIComps/tree/main/comps/web_retrievers/src/Dockerfile)                                 | The docker image exposed the OPEA web retrieval microservice based on a search engine and vector DB                                                                                                                    |
+| [opea/whisper](https://hub.docker.com/r/opea/whisper)                                                               | [Link](https://github.com/opea-project/GenAIComps/blob/main/comps/asr/src/integrations/dependency/whisper/Dockerfile)            | The docker image exposed the OPEA Whisper service for GenAI application use                                                                                                                                            |
+| [opea/whisper-gaudi](https://hub.docker.com/r/opea/whisper-gaudi)                                                   | [Link](https://github.com/opea-project/GenAIComps/blob/main/comps/asr/src/integrations/dependency/whisper/Dockerfile.intel_hpu)  | The docker image exposed the OPEA Whisper service on Gaudi2 for GenAI application use                                                                                                                                  |

version.txt

@@ -0,0 +1,3 @@
+VERSION_MAJOR 1
+VERSION_MINOR 2
+VERSION_PATCH 0