test

Signed-off-by: ZePan110 <ze.pan@intel.com>

.github/workflows/_gmc-e2e.yml

@@ -3,7 +3,8 @@
 
 # This workflow will only test GMC pipeline and will not install GMC any more
 name: Single GMC E2e Test For CD Workflow Call
-
+permissions:
+  contents: read
 on:
   workflow_call:
     inputs:

.github/workflows/_gmc-workflow.yml

@@ -2,7 +2,8 @@
 # SPDX-License-Identifier: Apache-2.0
 
 name: Build and deploy GMC system on call and manual
-
+permissions:
+  contents: read
 on:
   workflow_dispatch:
     inputs:

.github/workflows/dockerhub-description.yml

@@ -2,6 +2,8 @@
 # SPDX-License-Identifier: Apache-2.0
 
 name: Update Docker Hub Description
+permissions:
+  contents: read
 on:
   schedule:
     - cron: "0 0 * * 0"

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

@@ -2,6 +2,8 @@
 # SPDX-License-Identifier: Apache-2.0
 
 name: Clean up container on manual event
+permissions:
+  contents: read
 on:
   workflow_dispatch:
     inputs:

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

@@ -2,7 +2,8 @@
 # SPDX-License-Identifier: Apache-2.0
 
 name: Freeze OPEA images release tag
-
+permissions:
+  contents: read
 on:
   workflow_dispatch:
     inputs:

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

@@ -2,6 +2,8 @@
 # SPDX-License-Identifier: Apache-2.0
 
 name: Build specific images on manual event
+permissions:
+  contents: read
 on:
   workflow_dispatch:
     inputs:

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

@@ -2,6 +2,8 @@
 # SPDX-License-Identifier: Apache-2.0
 
 name: Clean up Local Registry on manual event
+permissions:
+  contents: read
 on:
   workflow_dispatch:
     inputs:

.github/workflows/mix-trellix.yml

@@ -2,7 +2,8 @@
 # SPDX-License-Identifier: Apache-2.0
 
 name: Trellix Command Line Scanner
-
+permissions:
+  contents: read
 on:
   workflow_dispatch:
   schedule:

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

@@ -2,7 +2,8 @@
 # SPDX-License-Identifier: Apache-2.0
 
 name: Nightly build/publish latest docker images
-
+permissions:
+  contents: read
 on:
   schedule:
     - cron: "30 14 * * 1-5" # UTC time

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

@@ -2,7 +2,8 @@
 # SPDX-License-Identifier: Apache-2.0
 
 name: E2E Test with Helm Charts
-
+permissions:
+  contents: read
 on:
   pull_request_target:
     branches: [main]

.github/workflows/pr-check-duplicated-image.yml

@@ -2,7 +2,8 @@
 # SPDX-License-Identifier: Apache-2.0
 
 name: Check Duplicated Images
-
+permissions:
+  contents: read
 on:
   pull_request:
     branches: [main]

.github/workflows/pr-code-scan.yml

@@ -2,7 +2,9 @@
 # SPDX-License-Identifier: Apache-2.0
 
 name: Code Scan
-
+permissions:
+  contents: read
+  security-events: write
 on:
   pull_request:
     branches: [main]

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

@@ -3,6 +3,9 @@
 
 name: E2E test with docker compose
 
+permissions:
+  contents: read
+
 on:
   pull_request_target:
     branches: ["main", "*rc"]

.github/workflows/pr-dockerfile-path-and-build-yaml-scan.yml

@@ -2,7 +2,8 @@
 # SPDX-License-Identifier: Apache-2.0
 
 name: Compose file and dockerfile path checking
-
+permissions:
+  contents: read
 on:
   pull_request:
     branches: [main]

.github/workflows/pr-link-path-scan.yml

@@ -3,6 +3,9 @@
 
 name: Check hyperlinks and relative path validity
 
+permissions:
+  contents: read
+
 on:
   pull_request:
     branches: [main]

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

@@ -3,6 +3,9 @@
 # Test
 name: Build latest images on push event
 
+permissions:
+  contents: read
+
 on:
   push:
     branches: [ 'main' ]

.github/workflows/push-images-path-detection.yml

@@ -3,10 +3,12 @@
 
 name: Check the validity of links in docker_images_list.
 
+permissions:
+  contents: read
+
 on:
   push:
     branches: [main]
-    types: [opened, reopened, ready_for_review, synchronize]
 
 jobs:
   check-dockerfile-paths:

.github/workflows/push-infra-issue-creation.yml

@@ -8,6 +8,10 @@ on:
       - "**/docker_compose/**/compose*.yaml"
 
 name: Create an issue to GenAIInfra on push
+
+permissions:
+  contents: read
+
 jobs:
   job1:
     name: Create issue

.github/workflows/weekly-example-test.yml

@@ -3,13 +3,15 @@
 
 name: Weekly test all examples on multiple HWs
 
+permissions: read-all
+
 on:
   schedule:
     - cron: "30 2 * * 6" # UTC time
   workflow_dispatch:
 
 env:
-  EXAMPLES: ${{ vars.NIGHTLY_RELEASE_EXAMPLES }}
+  EXAMPLES: "CodeTrans"  #${{ vars.NIGHTLY_RELEASE_EXAMPLES }}
   NODES: "gaudi,xeon,rocm,arc"
 
 jobs:

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

@@ -16,7 +16,7 @@ services:
       - chatqna-redis-vector-db
       - chatqna-tei-embedding-service
     ports:
-      - "${CHATQNA_REDIS_DATAPREP_PORT}:5000"
+      - "${CHATQNA_REDIS_DATAPREP_PORT:-18103}:5000"
     environment:
       no_proxy: ${no_proxy}
       http_proxy: ${http_proxy}

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

@@ -16,7 +16,7 @@ services:
       - chatqna-redis-vector-db
       - chatqna-tei-embedding-service
     ports:
-      - "${CHATQNA_REDIS_DATAPREP_PORT}:5000"
+      - "${CHATQNA_REDIS_DATAPREP_PORT:-18103}:5000"
     environment:
       no_proxy: ${no_proxy}
       http_proxy: ${http_proxy}

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

@@ -16,7 +16,7 @@ services:
       - chatqna-redis-vector-db
       - chatqna-tei-embedding-service
     ports:
-      - "${CHATQNA_REDIS_DATAPREP_PORT}:5000"
+      - "${CHATQNA_REDIS_DATAPREP_PORT:-18103}:5000"
     environment:
       no_proxy: ${no_proxy}
       http_proxy: ${http_proxy}

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

@@ -16,7 +16,7 @@ services:
       - chatqna-redis-vector-db
       - chatqna-tei-embedding-service
     ports:
-      - "${CHATQNA_REDIS_DATAPREP_PORT:-5000}:5000"
+      - "${CHATQNA_REDIS_DATAPREP_PORT:-18103}:5000"
     environment:
       no_proxy: ${no_proxy}
       http_proxy: ${http_proxy}

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

@@ -2,17 +2,17 @@
 
 # Copyright (C) 2025 Advanced Micro Devices, Inc.
 
-export HOST_IP=''
-export HOST_IP_EXTERNAL=''
+export HOST_IP=${ip_address}
+export HOST_IP_EXTERNAL=${ip_address}
 
 export CHATQNA_EMBEDDING_MODEL_ID="BAAI/bge-base-en-v1.5"
 export CHATQNA_HUGGINGFACEHUB_API_TOKEN=${HUGGINGFACEHUB_API_TOKEN}
 export CHATQNA_LLM_MODEL_ID="meta-llama/Meta-Llama-3-8B-Instruct"
 export CHATQNA_RERANK_MODEL_ID="BAAI/bge-reranker-base"
 
-export CHATQNA_BACKEND_SERVICE_PORT=18102
-export CHATQNA_FRONTEND_SERVICE_PORT=18101
-export CHATQNA_NGINX_PORT=18104
+export CHATQNA_BACKEND_SERVICE_PORT=8888
+export CHATQNA_FRONTEND_SERVICE_PORT=5173
+export CHATQNA_NGINX_PORT=80
 export CHATQNA_REDIS_DATAPREP_PORT=18103
 export CHATQNA_REDIS_RETRIEVER_PORT=7000
 export CHATQNA_REDIS_VECTOR_INSIGHT_PORT=8001

ChatQnA/docker_compose/amd/gpu/rocm/set_env_faqgen.sh

@@ -2,18 +2,18 @@
 
 # Copyright (C) 2025 Advanced Micro Devices, Inc.
 
-export HOST_IP=''
-export HOST_IP_EXTERNAL=''
+export HOST_IP=${ip_address}
+export HOST_IP_EXTERNAL=${ip_address}
 
 export CHATQNA_EMBEDDING_MODEL_ID="BAAI/bge-base-en-v1.5"
 export CHATQNA_HUGGINGFACEHUB_API_TOKEN=${HUGGINGFACEHUB_API_TOKEN}
 export CHATQNA_LLM_MODEL_ID="meta-llama/Meta-Llama-3-8B-Instruct"
 export CHATQNA_RERANK_MODEL_ID="BAAI/bge-reranker-base"
 
-export CHATQNA_BACKEND_SERVICE_PORT=18102
-export CHATQNA_FRONTEND_SERVICE_PORT=18101
+export CHATQNA_BACKEND_SERVICE_PORT=8888
+export CHATQNA_FRONTEND_SERVICE_PORT=5173
 export CHATQNA_LLM_FAQGEN_PORT=18011
-export CHATQNA_NGINX_PORT=18104
+export CHATQNA_NGINX_PORT=80
 export CHATQNA_REDIS_DATAPREP_PORT=18103
 export CHATQNA_REDIS_RETRIEVER_PORT=7000
 export CHATQNA_REDIS_VECTOR_INSIGHT_PORT=8001

ChatQnA/docker_compose/amd/gpu/rocm/set_env_faqgen_vllm.sh

@@ -2,18 +2,18 @@
 
 # Copyright (C) 2025 Advanced Micro Devices, Inc.
 
-export HOST_IP=''
-export HOST_IP_EXTERNAL=''
+export HOST_IP=${ip_address}
+export HOST_IP_EXTERNAL=${ip_address}
 
 export CHATQNA_EMBEDDING_MODEL_ID="BAAI/bge-base-en-v1.5"
 export CHATQNA_HUGGINGFACEHUB_API_TOKEN=${HUGGINGFACEHUB_API_TOKEN}
 export CHATQNA_LLM_MODEL_ID="meta-llama/Meta-Llama-3-8B-Instruct"
 export CHATQNA_RERANK_MODEL_ID="BAAI/bge-reranker-base"
 
-export CHATQNA_BACKEND_SERVICE_PORT=18102
-export CHATQNA_FRONTEND_SERVICE_PORT=18101
+export CHATQNA_BACKEND_SERVICE_PORT=8888
+export CHATQNA_FRONTEND_SERVICE_PORT=5173
 export CHATQNA_LLM_FAQGEN_PORT=18011
-export CHATQNA_NGINX_PORT=18104
+export CHATQNA_NGINX_PORT=80
 export CHATQNA_REDIS_DATAPREP_PORT=18103
 export CHATQNA_REDIS_RETRIEVER_PORT=7000
 export CHATQNA_REDIS_VECTOR_INSIGHT_PORT=8001

ChatQnA/docker_compose/amd/gpu/rocm/set_env_vllm.sh

@@ -2,17 +2,17 @@
 
 # Copyright (C) 2025 Advanced Micro Devices, Inc.
 
-export HOST_IP=''
-export HOST_IP_EXTERNAL=''
+export HOST_IP=${ip_address}
+export HOST_IP_EXTERNAL=${ip_address}
 
 export CHATQNA_EMBEDDING_MODEL_ID="BAAI/bge-base-en-v1.5"
 export CHATQNA_HUGGINGFACEHUB_API_TOKEN=${HUGGINGFACEHUB_API_TOKEN}
 export CHATQNA_LLM_MODEL_ID="meta-llama/Meta-Llama-3-8B-Instruct"
 export CHATQNA_RERANK_MODEL_ID="BAAI/bge-reranker-base"
 
-export CHATQNA_BACKEND_SERVICE_PORT=18102
-export CHATQNA_FRONTEND_SERVICE_PORT=18101
-export CHATQNA_NGINX_PORT=18104
+export CHATQNA_BACKEND_SERVICE_PORT=8888
+export CHATQNA_FRONTEND_SERVICE_PORT=5173
+export CHATQNA_NGINX_PORT=80
 export CHATQNA_REDIS_DATAPREP_PORT=18103
 export CHATQNA_REDIS_RETRIEVER_PORT=7000
 export CHATQNA_REDIS_VECTOR_INSIGHT_PORT=8001

ChatQnA/docker_compose/intel/cpu/xeon/grafana/dashboards/download_opea_dashboard.sh

@@ -1,6 +1,8 @@
 # Copyright (C) 2025 Intel Corporation
 # SPDX-License-Identifier: Apache-2.0
-rm *.json
+if ls *.json 1> /dev/null 2>&1; then
+    rm *.json
+fi
 wget https://raw.githubusercontent.com/opea-project/GenAIEval/refs/heads/main/evals/benchmark/grafana/chatqna_megaservice_grafana.json
 wget https://raw.githubusercontent.com/opea-project/GenAIEval/refs/heads/main/evals/benchmark/grafana/qdrant_grafana.json
 wget https://raw.githubusercontent.com/opea-project/GenAIEval/refs/heads/main/evals/benchmark/grafana/milvus_grafana.json

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

@@ -7,6 +7,9 @@ pushd "../../../../../" > /dev/null
 source .set_env.sh
 popd > /dev/null
 
+export HUGGINGFACEHUB_API_TOKEN=${HUGGINGFACEHUB_API_TOKEN}
+export HF_TOKEN=${HF_TOKEN}
+export host_ip=${ip_address}
 export EMBEDDING_MODEL_ID="BAAI/bge-base-en-v1.5"
 export RERANK_MODEL_ID="BAAI/bge-reranker-base"
 export LLM_MODEL_ID="meta-llama/Meta-Llama-3-8B-Instruct"

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

@@ -43,7 +43,7 @@ Some HuggingFace resources, such as some models, are only accessible if you have
 
 ### Configure the Deployment Environment
 
-To set up environment variables for deploying ChatQnA services, source the _setup_env.sh_ script in this directory:
+To set up environment variables for deploying ChatQnA services, source the _setup_env.sh_ script in this directory (If using faqgen or guardrails, source the _set_env_faqgen.sh_):
 
 ```
 source ./set_env.sh

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

@@ -4,12 +4,20 @@
 # SPDX-License-Identifier: Apache-2.0
 
 # Function to prompt for input and set environment variables
+NON_INTERACTIVE=${NON_INTERACTIVE:-false}
+
 prompt_for_env_var() {
   local var_name="$1"
   local prompt_message="$2"
   local default_value="$3"
   local mandatory="$4"
 
+  if [[ "$NON_INTERACTIVE" == "true" ]]; then
+    echo "Non-interactive environment detected. Setting $var_name to default: $default_value"
+    export "$var_name"="$default_value"
+    return
+  fi
+
   if [[ "$mandatory" == "true" ]]; then
     while [[ -z "$value" ]]; do
       read -p "$prompt_message [default: \"${default_value}\"]: " value
@@ -34,7 +42,7 @@ popd > /dev/null
 
 # Prompt the user for each required environment variable
 prompt_for_env_var "EMBEDDING_MODEL_ID" "Enter the EMBEDDING_MODEL_ID" "BAAI/bge-base-en-v1.5" false
-prompt_for_env_var "HUGGINGFACEHUB_API_TOKEN" "Enter the HUGGINGFACEHUB_API_TOKEN" "" true
+prompt_for_env_var "HUGGINGFACEHUB_API_TOKEN" "Enter the HUGGINGFACEHUB_API_TOKEN" "${HF_TOKEN}" true
 prompt_for_env_var "RERANK_MODEL_ID" "Enter the RERANK_MODEL_ID" "BAAI/bge-reranker-base" false
 prompt_for_env_var "LLM_MODEL_ID" "Enter the LLM_MODEL_ID" "meta-llama/Meta-Llama-3-8B-Instruct" false
 prompt_for_env_var "INDEX_NAME" "Enter the INDEX_NAME" "rag-redis" false
@@ -42,34 +50,40 @@ prompt_for_env_var "NUM_CARDS" "Enter the number of Gaudi devices" "1" false
 prompt_for_env_var "host_ip" "Enter the host_ip" "$(curl ifconfig.me)" false
 
 #Query for enabling http_proxy
-prompt_for_env_var "http_proxy" "Enter the http_proxy." "" false
+prompt_for_env_var "http_proxy" "Enter the http_proxy." "${http_proxy}" false
 
 #Query for enabling https_proxy
-prompt_for_env_var "https_proxy" "Enter the https_proxy." "" false
+prompt_for_env_var "http_proxy" "Enter the http_proxy." "${https_proxy}" false
 
 #Query for enabling no_proxy
-prompt_for_env_var "no_proxy" "Enter the no_proxy." "" false
+prompt_for_env_var "no_proxy" "Enter the no_proxy." "${no_proxy}" false
 
 # Query for enabling logging
-read -p "Enable logging? (yes/no): " logging && logging=$(echo "$logging" | tr '[:upper:]' '[:lower:]')
-if [[ "$logging" == "yes" || "$logging" == "y" ]]; then
-  export LOGFLAG=true
+if [[ "$NON_INTERACTIVE" == "true" ]]; then
+  # Query for enabling logging
+  prompt_for_env_var "LOGFLAG" "Enable logging? (yes/no): " "true" false
+  export JAEGER_IP=$(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
+  telemetry_flag=true
 else
-  export LOGFLAG=false
-fi
-
-# Query for enabling OpenTelemetry Tracing Endpoint
-read -p "Enable OpenTelemetry Tracing Endpoint? (yes/no): " telemetry && telemetry=$(echo "$telemetry" | tr '[:upper:]' '[:lower:]')
-if [[ "$telemetry" == "yes" || "$telemetry" == "y" ]]; then
-    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://$JAEGER_IP:4318/v1/traces
-    telemetry_flag=true
-    pushd "grafana/dashboards" > /dev/null
-    source download_opea_dashboard.sh
-    popd > /dev/null
-else
-    telemetry_flag=false
+  # Query for enabling logging
+  read -p "Enable logging? (yes/no): " logging && logging=$(echo "$logging" | tr '[:upper:]' '[:lower:]')
+  if [[ "$logging" == "yes" || "$logging" == "y" ]]; then
+    export LOGFLAG=true
+  else
+    export LOGFLAG=false
+  fi
+  # Query for enabling OpenTelemetry Tracing Endpoint
+  read -p "Enable OpenTelemetry Tracing Endpoint? (yes/no): " telemetry && telemetry=$(echo "$telemetry" | tr '[:upper:]' '[:lower:]')
+  if [[ "$telemetry" == "yes" || "$telemetry" == "y" ]]; then
+      export JAEGER_IP=$(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
+      telemetry_flag=true
+  else
+      telemetry_flag=false
+  fi
 fi
 
 # Generate the .env file

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

@@ -0,0 +1,32 @@
+#!/usr/bin/env bash
+
+# Copyright (C) 2024 Intel Corporation
+# SPDX-License-Identifier: Apache-2.0
+
+pushd "../../../../../" > /dev/null
+source .set_env.sh
+popd > /dev/null
+
+export HUGGINGFACEHUB_API_TOKEN=${HUGGINGFACEHUB_API_TOKEN}
+export HF_TOKEN=${HF_TOKEN}
+export host_ip=${ip_address}
+export EMBEDDING_MODEL_ID="BAAI/bge-base-en-v1.5"
+export RERANK_MODEL_ID="BAAI/bge-reranker-base"
+export LLM_MODEL_ID="meta-llama/Meta-Llama-3-8B-Instruct"
+export INDEX_NAME="rag-redis"
+export NUM_CARDS=1
+export VLLM_SKIP_WARMUP=true
+export LOGFLAG=True
+export http_proxy=${http_proxy}
+export https_proxy=${https_proxy}
+export no_proxy="${ip_address},redis-vector-db,dataprep-redis-service,tei-embedding-service,retriever,tei-reranking-service,tgi-service,vllm-service,guardrails,llm-faqgen,chatqna-gaudi-backend-server,chatqna-gaudi-ui-server,chatqna-gaudi-nginx-server"
+
+export LLM_ENDPOINT_PORT=8010
+export LLM_SERVER_PORT=9001
+export CHATQNA_BACKEND_PORT=8888
+export CHATQNA_REDIS_VECTOR_PORT=6377
+export CHATQNA_REDIS_VECTOR_INSIGHT_PORT=8006
+export CHATQNA_FRONTEND_SERVICE_PORT=5175
+export NGINX_PORT=80
+export FAQGen_COMPONENT_NAME="OpeaFaqGenvLLM"
+export LLM_ENDPOINT="http://${host_ip}:${LLM_ENDPOINT_PORT}"

ChatQnA/tests/README.md

@@ -0,0 +1,123 @@
+# ChatQnA E2E test scripts
+
+## Set the required environment variable
+
+```bash
+export HUGGINGFACEHUB_API_TOKEN="Your_Huggingface_API_Token"
+```
+
+## Run test
+
+On Intel Xeon with TGI:
+
+```bash
+bash test_compose_tgi_on_xeon.sh
+```
+
+On Intel Xeon with vLLM:
+
+```bash
+bash test_compose_on_xeon.sh
+```
+
+On Intel Xeon with MariaDB Vector:
+
+```bash
+bash test_compose_mariadb_on_xeon.sh
+```
+
+On Intel Xeon with Pinecone:
+
+```bash
+bash test_compose_pinecone_on_xeon.sh
+```
+
+On Intel Xeon with Milvus
+
+```bash
+bash test_compose_milvus_on_xeon.sh
+```
+
+On Intel Xeon with Qdrant
+
+```bash
+bash test_compose_qdrant_on_xeon.sh
+```
+
+On Intel Xeon without Rerank:
+
+```bash
+bash test_compose_without_rerank_on_xeon.sh
+```
+
+On Intel Gaudi with TGI:
+
+```bash
+bash test_compose_tgi_on_gaudi.sh
+```
+
+On Intel Gaudi with vLLM:
+
+```bash
+bash test_compose_on_gaudi.sh
+```
+
+On Intel Gaudi with Guardrails:
+
+```bash
+bash test_compose_guardrails_on_gaudi.sh
+```
+
+On Intel Gaudi without Rerank:
+
+```bash
+bash test_compose_without_rerank_on_gaudi.sh
+```
+
+On AMD ROCm with TGI:
+
+```bash
+bash test_compose_on_rocm.sh
+```
+
+On AMD ROCm with vLLM:
+
+```bash
+bash test_compose_vllm_on_rocm.sh
+```
+
+Test FAQ Generation On Intel Xeon with TGI:
+
+```bash
+bash test_compose_faqgen_tgi_on_xeon.sh
+```
+
+Test FAQ Generation On Intel Xeon with vLLM:
+
+```bash
+bash test_compose_faqgen_on_xeon.sh
+```
+
+Test FAQ Generation On Intel Gaudi with TGI:
+
+```bash
+bash test_compose_faqgen_tgi_on_gaudi.sh
+```
+
+Test FAQ Generation On Intel Gaudi with vLLM:
+
+```bash
+bash test_compose_faqgen_on_gaudi.sh
+```
+
+Test FAQ Generation On AMD ROCm with TGI:
+
+```bash
+bash test_compose_faqgen_on_rocm.sh
+```
+
+Test FAQ Generation On AMD ROCm with vLLM:
+
+```bash
+bash test_compose_faqgen_vllm_on_rocm.sh
+```

ChatQnA/tests/test_compose_faqgen_on_gaudi.sh

@@ -36,27 +36,7 @@ function build_docker_images() {
 
 function start_services() {
     cd $WORKPATH/docker_compose/intel/hpu/gaudi
-    export EMBEDDING_MODEL_ID="BAAI/bge-base-en-v1.5"
-    export RERANK_MODEL_ID="BAAI/bge-reranker-base"
-    export LLM_MODEL_ID="meta-llama/Meta-Llama-3-8B-Instruct"
-    export NUM_CARDS=1
-    export INDEX_NAME="rag-redis"
-    export host_ip=${ip_address}
-    export LLM_ENDPOINT_PORT=8010
-    export LLM_SERVER_PORT=9001
-    export CHATQNA_BACKEND_PORT=8888
-    export CHATQNA_REDIS_VECTOR_PORT=6377
-    export CHATQNA_REDIS_VECTOR_INSIGHT_PORT=8006
-    export CHATQNA_FRONTEND_SERVICE_PORT=5175
-    export NGINX_PORT=80
-    export FAQGen_COMPONENT_NAME="OpeaFaqGenvLLM"
-    export LLM_ENDPOINT="http://${host_ip}:${LLM_ENDPOINT_PORT}"
-    export HF_TOKEN=${HF_TOKEN}
-    export VLLM_SKIP_WARMUP=true
-    export LOGFLAG=True
-    export http_proxy=${http_proxy}
-    export https_proxy=${https_proxy}
-    export no_proxy="${ip_address},redis-vector-db,dataprep-redis-service,tei-embedding-service,retriever,tei-reranking-service,tgi-service,vllm-service,guardrails,llm-faqgen,chatqna-gaudi-backend-server,chatqna-gaudi-ui-server,chatqna-gaudi-nginx-server"
+    source set_env_faqgen.sh
 
     # Start Docker Containers
     docker compose -f compose_faqgen.yaml up -d > ${LOG_PATH}/start_services_with_compose.log

ChatQnA/tests/test_compose_faqgen_on_rocm.sh

@@ -15,44 +15,7 @@ WORKPATH=$(dirname "$PWD")
 LOG_PATH="$WORKPATH/tests"
 ip_address=$(hostname -I | awk '{print $1}')
 
-export HOST_IP=${ip_address}
-export HOST_IP_EXTERNAL=${ip_address}
-
-export CHATQNA_EMBEDDING_MODEL_ID="BAAI/bge-base-en-v1.5"
-export CHATQNA_HUGGINGFACEHUB_API_TOKEN=${HUGGINGFACEHUB_API_TOKEN}
-export CHATQNA_LLM_MODEL_ID="meta-llama/Meta-Llama-3-8B-Instruct"
-export CHATQNA_RERANK_MODEL_ID="BAAI/bge-reranker-base"
-
-export CHATQNA_BACKEND_SERVICE_PORT=8888
-export CHATQNA_FRONTEND_SERVICE_PORT=5173
-export CHATQNA_LLM_FAQGEN_PORT=18011
-export CHATQNA_NGINX_PORT=80
-export CHATQNA_REDIS_DATAPREP_PORT=18103
-export CHATQNA_REDIS_RETRIEVER_PORT=7000
-export CHATQNA_REDIS_VECTOR_INSIGHT_PORT=8001
-export CHATQNA_REDIS_VECTOR_PORT=6379
-export CHATQNA_TEI_EMBEDDING_PORT=18090
-export CHATQNA_TEI_RERANKING_PORT=18808
-export CHATQNA_TGI_SERVICE_PORT=18008
-
-export CHATQNA_BACKEND_SERVICE_ENDPOINT="http://${HOST_IP_EXTERNAL}:${CHATQNA_BACKEND_SERVICE_PORT}/v1/chatqna"
-export CHATQNA_BACKEND_SERVICE_IP=${HOST_IP}
-export CHATQNA_DATAPREP_DELETE_FILE_ENDPOINT="http://${HOST_IP_EXTERNAL}:${CHATQNA_REDIS_DATAPREP_PORT}/v1/dataprep/delete"
-export CHATQNA_DATAPREP_GET_FILE_ENDPOINT="http://${HOST_IP_EXTERNAL}:${CHATQNA_REDIS_DATAPREP_PORT}/v1/dataprep/get"
-export CHATQNA_DATAPREP_SERVICE_ENDPOINT="http://${HOST_IP_EXTERNAL}:${CHATQNA_REDIS_DATAPREP_PORT}/v1/dataprep/ingest"
-export CHATQNA_EMBEDDING_SERVICE_HOST_IP=${HOST_IP}
-export CHATQNA_FRONTEND_SERVICE_IP=${HOST_IP}
-export CHATQNA_LLM_SERVICE_HOST_IP=${HOST_IP}
-export CHATQNA_LLM_ENDPOINT="http://${HOST_IP}:${CHATQNA_TGI_SERVICE_PORT}"
-export CHATQNA_MEGA_SERVICE_HOST_IP=${HOST_IP}
-export CHATQNA_REDIS_URL="redis://${HOST_IP}:${CHATQNA_REDIS_VECTOR_PORT}"
-export CHATQNA_RERANK_SERVICE_HOST_IP=${HOST_IP}
-export CHATQNA_RETRIEVER_SERVICE_HOST_IP=${HOST_IP}
-export CHATQNA_TEI_EMBEDDING_ENDPOINT="http://${HOST_IP}:${CHATQNA_TEI_EMBEDDING_PORT}"
-
-export CHATQNA_BACKEND_SERVICE_NAME=chatqna
-export CHATQNA_INDEX_NAME="rag-redis"
-export FAQGen_COMPONENT_NAME="OpeaFaqGenTgi"
+source $WORKPATH/docker_compose/amd/gpu/rocm/set_env_faqgen.sh
 
 export PATH="~/miniconda3/bin:$PATH"
 

ChatQnA/tests/test_compose_faqgen_on_xeon.sh

@@ -37,26 +37,16 @@ function build_docker_images() {
 
 function start_services() {
     cd $WORKPATH/docker_compose/intel/cpu/xeon
-    export EMBEDDING_MODEL_ID="BAAI/bge-base-en-v1.5"
-    export RERANK_MODEL_ID="BAAI/bge-reranker-base"
-    export LLM_MODEL_ID="meta-llama/Meta-Llama-3-8B-Instruct"
-    export INDEX_NAME="rag-redis"
-    export host_ip=${ip_address}
-    export LLM_ENDPOINT_PORT=8010
     export LLM_SERVER_PORT=9001
-    export CHATQNA_BACKEND_PORT=8888
     export CHATQNA_REDIS_VECTOR_PORT=6377
     export CHATQNA_REDIS_VECTOR_INSIGHT_PORT=8006
     export CHATQNA_FRONTEND_SERVICE_PORT=5175
-    export NGINX_PORT=80
-    export FAQGen_COMPONENT_NAME="OpeaFaqGenvLLM"
-    export LLM_ENDPOINT="http://${host_ip}:${LLM_ENDPOINT_PORT}"
-    export HF_TOKEN=${HF_TOKEN}
     export VLLM_SKIP_WARMUP=true
     export LOGFLAG=True
     export http_proxy=${http_proxy}
     export https_proxy=${https_proxy}
     export no_proxy="${ip_address},redis-vector-db,dataprep-redis-service,tei-embedding-service,retriever,tei-reranking-service,tgi-service,vllm-service,guardrails,llm-faqgen,chatqna-xeon-backend-server,chatqna-xeon-ui-server,chatqna-xeon-nginx-server"
+    source set_env.sh
 
     # Start Docker Containers
     docker compose -f compose_faqgen.yaml up -d > ${LOG_PATH}/start_services_with_compose.log

ChatQnA/tests/test_compose_faqgen_tgi_on_gaudi.sh

@@ -33,25 +33,8 @@ function build_docker_images() {
 
 function start_services() {
     cd $WORKPATH/docker_compose/intel/hpu/gaudi
-    export EMBEDDING_MODEL_ID="BAAI/bge-base-en-v1.5"
-    export RERANK_MODEL_ID="BAAI/bge-reranker-base"
-    export LLM_MODEL_ID="meta-llama/Meta-Llama-3-8B-Instruct"
-    export INDEX_NAME="rag-redis"
-    export host_ip=${ip_address}
-    export LLM_ENDPOINT_PORT=8010
-    export LLM_SERVER_PORT=9001
-    export CHATQNA_BACKEND_PORT=8888
-    export CHATQNA_REDIS_VECTOR_PORT=6377
-    export CHATQNA_REDIS_VECTOR_INSIGHT_PORT=8006
-    export CHATQNA_FRONTEND_SERVICE_PORT=5175
-    export NGINX_PORT=80
     export FAQGen_COMPONENT_NAME="OpeaFaqGenTgi"
-    export LLM_ENDPOINT="http://${host_ip}:${LLM_ENDPOINT_PORT}"
-    export HF_TOKEN=${HF_TOKEN}
-    export LOGFLAG=True
-    export http_proxy=${http_proxy}
-    export https_proxy=${https_proxy}
-    export no_proxy="${ip_address},redis-vector-db,dataprep-redis-service,tei-embedding-service,retriever,tei-reranking-service,tgi-service,vllm-service,guardrails,llm-faqgen,chatqna-gaudi-backend-server,chatqna-gaudi-ui-server,chatqna-gaudi-nginx-server"
+    source set_env_faqgen.sh
 
     # Start Docker Containers
     docker compose -f compose_faqgen_tgi.yaml up -d > ${LOG_PATH}/start_services_with_compose.log

ChatQnA/tests/test_compose_faqgen_tgi_on_xeon.sh

@@ -37,25 +37,16 @@ function build_docker_images() {
 
 function start_services() {
     cd $WORKPATH/docker_compose/intel/cpu/xeon
-    export EMBEDDING_MODEL_ID="BAAI/bge-base-en-v1.5"
-    export RERANK_MODEL_ID="BAAI/bge-reranker-base"
-    export LLM_MODEL_ID="meta-llama/Meta-Llama-3-8B-Instruct"
-    export INDEX_NAME="rag-redis"
-    export host_ip=${ip_address}
-    export LLM_ENDPOINT_PORT=8010
     export LLM_SERVER_PORT=9001
-    export CHATQNA_BACKEND_PORT=8888
     export CHATQNA_REDIS_VECTOR_PORT=6377
     export CHATQNA_REDIS_VECTOR_INSIGHT_PORT=8006
     export CHATQNA_FRONTEND_SERVICE_PORT=5175
-    export NGINX_PORT=80
     export FAQGen_COMPONENT_NAME="OpeaFaqGenTgi"
-    export LLM_ENDPOINT="http://${host_ip}:${LLM_ENDPOINT_PORT}"
-    export HF_TOKEN=${HF_TOKEN}
     export LOGFLAG=True
     export http_proxy=${http_proxy}
     export https_proxy=${https_proxy}
     export no_proxy="${ip_address},redis-vector-db,dataprep-redis-service,tei-embedding-service,retriever,tei-reranking-service,tgi-service,vllm-service,guardrails,llm-faqgen,chatqna-xeon-backend-server,chatqna-xeon-ui-server,chatqna-xeon-nginx-server"
+    source set_env.sh
 
     # Start Docker Containers
     docker compose -f compose_faqgen_tgi.yaml up -d > ${LOG_PATH}/start_services_with_compose.log

ChatQnA/tests/test_compose_faqgen_vllm_on_rocm.sh

@@ -14,41 +14,7 @@ WORKPATH=$(dirname "$PWD")
 LOG_PATH="$WORKPATH/tests"
 ip_address=$(hostname -I | awk '{print $1}')
 
-export HOST_IP=${ip_address}
-export HOST_IP_EXTERNAL=${ip_address}
-
-export CHATQNA_EMBEDDING_MODEL_ID="BAAI/bge-base-en-v1.5"
-export CHATQNA_HUGGINGFACEHUB_API_TOKEN=${HUGGINGFACEHUB_API_TOKEN}
-export CHATQNA_LLM_MODEL_ID="meta-llama/Meta-Llama-3-8B-Instruct"
-export CHATQNA_RERANK_MODEL_ID="BAAI/bge-reranker-base"
-
-export CHATQNA_BACKEND_SERVICE_PORT=8888
-export CHATQNA_FRONTEND_SERVICE_PORT=5173
-export CHATQNA_LLM_FAQGEN_PORT=18011
-export CHATQNA_NGINX_PORT=80
-export CHATQNA_REDIS_DATAPREP_PORT=18103
-export CHATQNA_REDIS_RETRIEVER_PORT=7000
-export CHATQNA_REDIS_VECTOR_INSIGHT_PORT=8001
-export CHATQNA_REDIS_VECTOR_PORT=6379
-export CHATQNA_TEI_EMBEDDING_PORT=18090
-export CHATQNA_TEI_RERANKING_PORT=18808
-export CHATQNA_VLLM_SERVICE_PORT=18008
-
-export CHATQNA_BACKEND_SERVICE_ENDPOINT="http://${HOST_IP_EXTERNAL}:${CHATQNA_BACKEND_SERVICE_PORT}/v1/chatqna"
-export CHATQNA_BACKEND_SERVICE_IP=${HOST_IP_EXTERNAL}
-export CHATQNA_DATAPREP_DELETE_FILE_ENDPOINT="http://${HOST_IP_EXTERNAL}:${CHATQNA_REDIS_DATAPREP_PORT}/v1/dataprep/delete"
-export CHATQNA_DATAPREP_GET_FILE_ENDPOINT="http://${HOST_IP_EXTERNAL}:${CHATQNA_REDIS_DATAPREP_PORT}/v1/dataprep/get"
-export CHATQNA_DATAPREP_SERVICE_ENDPOINT="http://${HOST_IP_EXTERNAL}:${CHATQNA_REDIS_DATAPREP_PORT}/v1/dataprep/ingest"
-export CHATQNA_FRONTEND_SERVICE_IP=${HOST_IP}
-export CHATQNA_MEGA_SERVICE_HOST_IP=${HOST_IP}
-export CHATQNA_REDIS_URL="redis://${HOST_IP}:${CHATQNA_REDIS_VECTOR_PORT}"
-export CHATQNA_TEI_EMBEDDING_ENDPOINT="http://${HOST_IP}:${CHATQNA_TEI_EMBEDDING_PORT}"
-export LLM_ENDPOINT="http://${HOST_IP}:${CHATQNA_VLLM_SERVICE_PORT}"
-
-export CHATQNA_BACKEND_SERVICE_NAME=chatqna
-export CHATQNA_INDEX_NAME="rag-redis"
-export CHATQNA_TYPE="CHATQNA_FAQGEN"
-export FAQGen_COMPONENT_NAME="OpeaFaqGenvLLM"
+source $WORKPATH/docker_compose/amd/gpu/rocm/set_env_faqgen_vllm.sh
 
 function build_docker_images() {
     opea_branch=${opea_branch:-"main"}

ChatQnA/tests/test_compose_guardrails_on_gaudi.sh

@@ -2,7 +2,7 @@
 # Copyright (C) 2024 Intel Corporation
 # SPDX-License-Identifier: Apache-2.0
 
-set -e
+set -xe
 IMAGE_REPO=${IMAGE_REPO:-"opea"}
 IMAGE_TAG=${IMAGE_TAG:-"latest"}
 echo "REGISTRY=IMAGE_REPO=${IMAGE_REPO}"
@@ -36,14 +36,8 @@ function build_docker_images() {
 
 function start_services() {
     cd $WORKPATH/docker_compose/intel/hpu/gaudi
-    export EMBEDDING_MODEL_ID="BAAI/bge-base-en-v1.5"
-    export RERANK_MODEL_ID="BAAI/bge-reranker-base"
-    export LLM_MODEL_ID="meta-llama/Meta-Llama-3-8B-Instruct"
-    export NUM_CARDS=1
-    export INDEX_NAME="rag-redis"
-    export HUGGINGFACEHUB_API_TOKEN=${HUGGINGFACEHUB_API_TOKEN}
-    export host_ip=${ip_address}
     export GURADRAILS_MODEL_ID="meta-llama/Meta-Llama-Guard-2-8B"
+    source set_env_faqgen.sh
 
     # Start Docker Containers
     docker compose -f compose_guardrails.yaml up -d > ${LOG_PATH}/start_services_with_compose.log

ChatQnA/tests/test_compose_mariadb_on_xeon.sh

@@ -2,7 +2,7 @@
 # Copyright (C) 2025 MariaDB Foundation
 # SPDX-License-Identifier: Apache-2.0
 
-set -e
+set -xe
 IMAGE_REPO=${IMAGE_REPO:-"opea"}
 IMAGE_TAG=${IMAGE_TAG:-"latest"}
 echo "REGISTRY=IMAGE_REPO=${IMAGE_REPO}"
@@ -39,14 +39,8 @@ function build_docker_images() {
 
 function start_services() {
     cd $WORKPATH/docker_compose/intel/cpu/xeon
-    export MARIADB_DATABASE="vectordb"
-    export MARIADB_USER="chatqna"
     export MARIADB_PASSWORD="test"
-    export EMBEDDING_MODEL_ID="BAAI/bge-base-en-v1.5"
-    export RERANK_MODEL_ID="BAAI/bge-reranker-base"
-    export LLM_MODEL_ID="meta-llama/Meta-Llama-3-8B-Instruct"
-    export HUGGINGFACEHUB_API_TOKEN=${HUGGINGFACEHUB_API_TOKEN}
-    export host_ip=${ip_address}
+    source set_env_mariadb.sh
 
     # Start Docker Containers
     docker compose -f compose_mariadb.yaml up -d > ${LOG_PATH}/start_services_with_compose.log

ChatQnA/tests/test_compose_milvus_on_xeon.sh

@@ -2,7 +2,7 @@
 # Copyright (C) 2024 Intel Corporation
 # SPDX-License-Identifier: Apache-2.0
 
-set -e
+set -xe
 IMAGE_REPO=${IMAGE_REPO:-"opea"}
 IMAGE_TAG=${IMAGE_TAG:-"latest"}
 echo "REGISTRY=IMAGE_REPO=${IMAGE_REPO}"
@@ -39,11 +39,8 @@ function build_docker_images() {
 }
 function start_services() {
     cd $WORKPATH/docker_compose/intel/cpu/xeon/
-    export EMBEDDING_MODEL_ID="BAAI/bge-base-en-v1.5"
-    export RERANK_MODEL_ID="BAAI/bge-reranker-base"
-    export LLM_MODEL_ID="meta-llama/Meta-Llama-3-8B-Instruct"
-    export HUGGINGFACEHUB_API_TOKEN=${HUGGINGFACEHUB_API_TOKEN}
     export LOGFLAG=true
+    source set_env.sh
 
     # Start Docker Containers
     docker compose -f compose_milvus.yaml up -d > ${LOG_PATH}/start_services_with_compose.log

ChatQnA/tests/test_compose_on_gaudi.sh

@@ -2,7 +2,7 @@
 # Copyright (C) 2024 Intel Corporation
 # SPDX-License-Identifier: Apache-2.0
 
-set -e
+set -xe
 IMAGE_REPO=${IMAGE_REPO:-"opea"}
 IMAGE_TAG=${IMAGE_TAG:-"latest"}
 echo "REGISTRY=IMAGE_REPO=${IMAGE_REPO}"
@@ -36,16 +36,10 @@ function build_docker_images() {
 
 function start_services() {
     cd $WORKPATH/docker_compose/intel/hpu/gaudi
-    export EMBEDDING_MODEL_ID="BAAI/bge-base-en-v1.5"
-    export RERANK_MODEL_ID="BAAI/bge-reranker-base"
-    export LLM_MODEL_ID="meta-llama/Meta-Llama-3-8B-Instruct"
-    export NUM_CARDS=1
-    export INDEX_NAME="rag-redis"
-    export HUGGINGFACEHUB_API_TOKEN=${HUGGINGFACEHUB_API_TOKEN}
+    export NON_INTERACTIVE=true
     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
+    export telemetry=yes
+    source set_env.sh
 
     # Start Docker Containers
     docker compose -f compose.yaml -f compose.telemetry.yaml up -d > ${LOG_PATH}/start_services_with_compose.log

ChatQnA/tests/test_compose_on_rocm.sh

@@ -15,41 +15,7 @@ WORKPATH=$(dirname "$PWD")
 LOG_PATH="$WORKPATH/tests"
 ip_address=$(hostname -I | awk '{print $1}')
 
-export HOST_IP=${ip_address}
-export HOST_IP_EXTERNAL=${ip_address}
-
-export CHATQNA_EMBEDDING_MODEL_ID="BAAI/bge-base-en-v1.5"
-export CHATQNA_HUGGINGFACEHUB_API_TOKEN=${HUGGINGFACEHUB_API_TOKEN}
-export CHATQNA_LLM_MODEL_ID="meta-llama/Meta-Llama-3-8B-Instruct"
-export CHATQNA_RERANK_MODEL_ID="BAAI/bge-reranker-base"
-
-export CHATQNA_BACKEND_SERVICE_PORT=8888
-export CHATQNA_FRONTEND_SERVICE_PORT=5173
-export CHATQNA_NGINX_PORT=80
-export CHATQNA_REDIS_DATAPREP_PORT=18103
-export CHATQNA_REDIS_RETRIEVER_PORT=7000
-export CHATQNA_REDIS_VECTOR_INSIGHT_PORT=8001
-export CHATQNA_REDIS_VECTOR_PORT=6379
-export CHATQNA_TEI_EMBEDDING_PORT=18090
-export CHATQNA_TEI_RERANKING_PORT=18808
-export CHATQNA_TGI_SERVICE_PORT=18008
-
-export CHATQNA_BACKEND_SERVICE_ENDPOINT="http://${HOST_IP_EXTERNAL}:${CHATQNA_BACKEND_SERVICE_PORT}/v1/chatqna"
-export CHATQNA_BACKEND_SERVICE_IP=${HOST_IP}
-export CHATQNA_DATAPREP_DELETE_FILE_ENDPOINT="http://${HOST_IP_EXTERNAL}:${CHATQNA_REDIS_DATAPREP_PORT}/v1/dataprep/delete"
-export CHATQNA_DATAPREP_GET_FILE_ENDPOINT="http://${HOST_IP_EXTERNAL}:${CHATQNA_REDIS_DATAPREP_PORT}/v1/dataprep/get"
-export CHATQNA_DATAPREP_SERVICE_ENDPOINT="http://${HOST_IP_EXTERNAL}:${CHATQNA_REDIS_DATAPREP_PORT}/v1/dataprep/ingest"
-export CHATQNA_EMBEDDING_SERVICE_HOST_IP=${HOST_IP}
-export CHATQNA_FRONTEND_SERVICE_IP=${HOST_IP}
-export CHATQNA_LLM_SERVICE_HOST_IP=${HOST_IP}
-export CHATQNA_MEGA_SERVICE_HOST_IP=${HOST_IP}
-export CHATQNA_REDIS_URL="redis://${HOST_IP}:${CHATQNA_REDIS_VECTOR_PORT}"
-export CHATQNA_RERANK_SERVICE_HOST_IP=${HOST_IP}
-export CHATQNA_RETRIEVER_SERVICE_HOST_IP=${HOST_IP}
-export CHATQNA_TEI_EMBEDDING_ENDPOINT="http://${HOST_IP}:${CHATQNA_TEI_EMBEDDING_PORT}"
-
-export CHATQNA_BACKEND_SERVICE_NAME=chatqna
-export CHATQNA_INDEX_NAME="rag-redis"
+source $WORKPATH/docker_compose/amd/gpu/rocm/set_env.sh
 
 export PATH="~/miniconda3/bin:$PATH"
 

ChatQnA/tests/test_compose_on_xeon.sh

@@ -2,7 +2,7 @@
 # Copyright (C) 2024 Intel Corporation
 # SPDX-License-Identifier: Apache-2.0
 
-set -e
+set -xe
 IMAGE_REPO=${IMAGE_REPO:-"opea"}
 IMAGE_TAG=${IMAGE_TAG:-"latest"}
 echo "REGISTRY=IMAGE_REPO=${IMAGE_REPO}"
@@ -40,15 +40,7 @@ function build_docker_images() {
 function start_services() {
     cd $WORKPATH/docker_compose/intel/cpu/xeon
 
-    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 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
+    source set_env.sh
 
     # Start Docker Containers
     docker compose -f compose.yaml -f compose.telemetry.yaml up -d > ${LOG_PATH}/start_services_with_compose.log

ChatQnA/tests/test_compose_pinecone_on_xeon.sh

@@ -2,7 +2,7 @@
 # Copyright (C) 2024 Intel Corporation
 # SPDX-License-Identifier: Apache-2.0
 
-set -e
+set -xe
 IMAGE_REPO=${IMAGE_REPO:-"opea"}
 IMAGE_TAG=${IMAGE_TAG:-"latest"}
 echo "REGISTRY=IMAGE_REPO=${IMAGE_REPO}"
@@ -41,14 +41,11 @@ function build_docker_images() {
 function start_services() {
     cd $WORKPATH/docker_compose/intel/cpu/xeon/
     export no_proxy=${no_proxy},${ip_address}
-    export EMBEDDING_MODEL_ID="BAAI/bge-base-en-v1.5"
-    export RERANK_MODEL_ID="BAAI/bge-reranker-base"
-    export LLM_MODEL_ID="meta-llama/Meta-Llama-3-8B-Instruct"
     export PINECONE_API_KEY=${PINECONE_KEY_LANGCHAIN_TEST}
     export PINECONE_INDEX_NAME="langchain-test"
     export INDEX_NAME="langchain-test"
-    export HUGGINGFACEHUB_API_TOKEN=${HUGGINGFACEHUB_API_TOKEN}
     export LOGFLAG=true
+    source set_env.sh
 
     # Start Docker Containers
     docker compose -f compose_pinecone.yaml up -d > ${LOG_PATH}/start_services_with_compose.log

ChatQnA/tests/test_compose_qdrant_on_xeon.sh

@@ -2,7 +2,7 @@
 # Copyright (C) 2024 Intel Corporation
 # SPDX-License-Identifier: Apache-2.0
 
-set -e
+set -xe
 IMAGE_REPO=${IMAGE_REPO:-"opea"}
 IMAGE_TAG=${IMAGE_TAG:-"latest"}
 echo "REGISTRY=IMAGE_REPO=${IMAGE_REPO}"
@@ -40,11 +40,8 @@ function build_docker_images() {
 function start_services() {
     cd $WORKPATH/docker_compose/intel/cpu/xeon
 
-    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-qdrant"
-    export HUGGINGFACEHUB_API_TOKEN=${HUGGINGFACEHUB_API_TOKEN}
+    source set_env.sh
 
     sed -i "s/backend_address/$ip_address/g" $WORKPATH/ui/svelte/.env
 

ChatQnA/tests/test_compose_tgi_on_gaudi.sh

@@ -2,7 +2,7 @@
 # Copyright (C) 2024 Intel Corporation
 # SPDX-License-Identifier: Apache-2.0
 
-set -e
+set -xe
 IMAGE_REPO=${IMAGE_REPO:-"opea"}
 IMAGE_TAG=${IMAGE_TAG:-"latest"}
 echo "REGISTRY=IMAGE_REPO=${IMAGE_REPO}"
@@ -32,15 +32,10 @@ function build_docker_images() {
 
 function start_services() {
     cd $WORKPATH/docker_compose/intel/hpu/gaudi
-    export EMBEDDING_MODEL_ID="BAAI/bge-base-en-v1.5"
-    export RERANK_MODEL_ID="BAAI/bge-reranker-base"
-    export LLM_MODEL_ID="meta-llama/Meta-Llama-3-8B-Instruct"
-    export NUM_CARDS=1
-    export INDEX_NAME="rag-redis"
-    export HUGGINGFACEHUB_API_TOKEN=${HUGGINGFACEHUB_API_TOKEN}
-    export JAEGER_IP=$(ip route get 8.8.8.8 | grep -oP 'src \K[^ ]+')
-    export OTEL_EXPORTER_OTLP_TRACES_ENDPOINT=grpc://$JAEGER_IP:4317
-    export TELEMETRY_ENDPOINT=http://$JAEGER_IP:4318/v1/traces
+    export NON_INTERACTIVE=true
+    export host_ip=${ip_address}
+    export telemetry=yes
+    source set_env.sh
 
     # Start Docker Containers
     docker compose -f compose_tgi.yaml -f compose_tgi.telemetry.yaml up -d > ${LOG_PATH}/start_services_with_compose.log

ChatQnA/tests/test_compose_tgi_on_xeon.sh

@@ -2,7 +2,7 @@
 # Copyright (C) 2024 Intel Corporation
 # SPDX-License-Identifier: Apache-2.0
 
-set -e
+set -xe
 IMAGE_REPO=${IMAGE_REPO:-"opea"}
 IMAGE_TAG=${IMAGE_TAG:-"latest"}
 echo "REGISTRY=IMAGE_REPO=${IMAGE_REPO}"
@@ -33,14 +33,7 @@ function build_docker_images() {
 function start_services() {
     cd $WORKPATH/docker_compose/intel/cpu/xeon
 
-    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 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
+    source set_env.sh
 
     # Start Docker Containers
     docker compose -f compose_tgi.yaml -f compose_tgi.telemetry.yaml up -d > ${LOG_PATH}/start_services_with_compose.log

ChatQnA/tests/test_compose_vllm_on_rocm.sh

@@ -2,7 +2,7 @@
 # Copyright (C) 2024 Intel Corporation
 # SPDX-License-Identifier: Apache-2.0
 
-set -e
+set -xe
 IMAGE_REPO=${IMAGE_REPO:-"opea"}
 IMAGE_TAG=${IMAGE_TAG:-"latest"}
 echo "REGISTRY=IMAGE_REPO=${IMAGE_REPO}"
@@ -14,42 +14,7 @@ WORKPATH=$(dirname "$PWD")
 LOG_PATH="$WORKPATH/tests"
 ip_address=$(hostname -I | awk '{print $1}')
 
-export HOST_IP=${ip_address}
-export HOST_IP_EXTERNAL=${ip_address}
-
-export CHATQNA_EMBEDDING_MODEL_ID="BAAI/bge-base-en-v1.5"
-export CHATQNA_HUGGINGFACEHUB_API_TOKEN=${HUGGINGFACEHUB_API_TOKEN}
-export CHATQNA_LLM_MODEL_ID="meta-llama/Meta-Llama-3-8B-Instruct"
-export CHATQNA_RERANK_MODEL_ID="BAAI/bge-reranker-base"
-
-export CHATQNA_BACKEND_SERVICE_PORT=8888
-export CHATQNA_FRONTEND_SERVICE_PORT=5173
-export CHATQNA_NGINX_PORT=80
-export CHATQNA_REDIS_DATAPREP_PORT=18103
-export CHATQNA_REDIS_RETRIEVER_PORT=7000
-export CHATQNA_REDIS_VECTOR_INSIGHT_PORT=8001
-export CHATQNA_REDIS_VECTOR_PORT=6379
-export CHATQNA_TEI_EMBEDDING_PORT=18090
-export CHATQNA_TEI_RERANKING_PORT=18808
-export CHATQNA_VLLM_SERVICE_PORT=18008
-
-export CHATQNA_BACKEND_SERVICE_ENDPOINT="http://${HOST_IP_EXTERNAL}:${CHATQNA_BACKEND_SERVICE_PORT}/v1/chatqna"
-export CHATQNA_BACKEND_SERVICE_IP=${HOST_IP_EXTERNAL}
-export CHATQNA_DATAPREP_DELETE_FILE_ENDPOINT="http://${HOST_IP_EXTERNAL}:${CHATQNA_REDIS_DATAPREP_PORT}/v1/dataprep/delete"
-export CHATQNA_DATAPREP_GET_FILE_ENDPOINT="http://${HOST_IP_EXTERNAL}:${CHATQNA_REDIS_DATAPREP_PORT}/v1/dataprep/get"
-export CHATQNA_DATAPREP_SERVICE_ENDPOINT="http://${HOST_IP_EXTERNAL}:${CHATQNA_REDIS_DATAPREP_PORT}/v1/dataprep/ingest"
-export CHATQNA_EMBEDDING_SERVICE_HOST_IP=${HOST_IP}
-export CHATQNA_FRONTEND_SERVICE_IP=${HOST_IP}
-export CHATQNA_LLM_SERVICE_HOST_IP=${HOST_IP}
-export CHATQNA_MEGA_SERVICE_HOST_IP=${HOST_IP}
-export CHATQNA_REDIS_URL="redis://${HOST_IP}:${CHATQNA_REDIS_VECTOR_PORT}"
-export CHATQNA_RERANK_SERVICE_HOST_IP=${HOST_IP}
-export CHATQNA_RETRIEVER_SERVICE_HOST_IP=${HOST_IP}
-export CHATQNA_TEI_EMBEDDING_ENDPOINT="http://${HOST_IP}:${CHATQNA_TEI_EMBEDDING_PORT}"
-
-export CHATQNA_BACKEND_SERVICE_NAME=chatqna
-export CHATQNA_INDEX_NAME="rag-redis"
-
+source $WORKPATH/docker_compose/amd/gpu/rocm/set_env_vllm.sh
 
 function build_docker_images() {
     opea_branch=${opea_branch:-"main"}

ChatQnA/tests/test_compose_without_rerank_on_gaudi.sh

@@ -2,7 +2,7 @@
 # Copyright (C) 2024 Intel Corporation
 # SPDX-License-Identifier: Apache-2.0
 
-set -e
+set -xe
 IMAGE_REPO=${IMAGE_REPO:-"opea"}
 IMAGE_TAG=${IMAGE_TAG:-"latest"}
 echo "REGISTRY=IMAGE_REPO=${IMAGE_REPO}"
@@ -36,11 +36,8 @@ function build_docker_images() {
 
 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}
+    export NON_INTERACTIVE=true
+    source set_env.sh
 
     # Start Docker Containers
     docker compose -f compose_without_rerank.yaml up -d > ${LOG_PATH}/start_services_with_compose.log

ChatQnA/tests/test_compose_without_rerank_on_xeon.sh

@@ -2,7 +2,7 @@
 # Copyright (C) 2024 Intel Corporation
 # SPDX-License-Identifier: Apache-2.0
 
-set -e
+set -xe
 IMAGE_REPO=${IMAGE_REPO:-"opea"}
 IMAGE_TAG=${IMAGE_TAG:-"latest"}
 echo "REGISTRY=IMAGE_REPO=${IMAGE_REPO}"
@@ -41,10 +41,7 @@ function build_docker_images() {
 function start_services() {
     cd $WORKPATH/docker_compose/intel/cpu/xeon
 
-    export EMBEDDING_MODEL_ID="BAAI/bge-base-en-v1.5"
-    export LLM_MODEL_ID="meta-llama/Meta-Llama-3-8B-Instruct"
-    export INDEX_NAME="rag-redis"
-    export HUGGINGFACEHUB_API_TOKEN=${HUGGINGFACEHUB_API_TOKEN}
+    source set_env.sh
 
     # Start Docker Containers
     docker compose -f compose_without_rerank.yaml up -d > ${LOG_PATH}/start_services_with_compose.log

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

@@ -52,18 +52,29 @@ This uses the default vLLM-based deployment profile (`codegen-xeon-vllm`).
 
     ```bash
     # Replace with your host's external IP address (do not use localhost or 127.0.0.1)
-    export HOST_IP="your_external_ip_address"
+    export host_ip="your_external_ip_address"
     # Replace with your Hugging Face Hub API token
     export HUGGINGFACEHUB_API_TOKEN="your_huggingface_token"
 
     # Optional: Configure proxy if needed
     # export http_proxy="your_http_proxy"
     # export https_proxy="your_https_proxy"
-    # export no_proxy="localhost,127.0.0.1,${HOST_IP}" # Add other hosts if necessary
+    # export no_proxy="localhost,127.0.0.1,${host_ip}" # Add other hosts if necessary
     source ../../../set_env.sh
     ```
 
-    _Note: The compose file might read additional variables from a `.env` file or expect them defined elsewhere. Ensure all required variables like ports (`LLM_SERVICE_PORT`, `MEGA_SERVICE_PORT`, etc.) are set if not using defaults from the compose file._
+    _Note: The compose file might read additional variables from set_env.sh. Ensure all required variables like ports (`LLM_SERVICE_PORT`, `MEGA_SERVICE_PORT`, etc.) are set if not using defaults from the compose file._
+    like
+
+    ```
+    export LLM_MODEL_ID="Qwen/Qwen2.5-Coder-32B-Instruct"
+    ```
+
+    can be changed to small model if needed
+
+    ```
+    export LLM_MODEL_ID="Qwen/Qwen2.5-Coder-7B-Instruct"
+    ```
 
 2.  **Start Services (vLLM Profile):**
 
@@ -91,7 +102,7 @@ The `compose.yaml` file uses Docker Compose profiles to select the LLM serving b
 - **Services Deployed:** `codegen-tgi-server`, `codegen-llm-server`, `codegen-tei-embedding-server`, `codegen-retriever-server`, `redis-vector-db`, `codegen-dataprep-server`, `codegen-backend-server`, `codegen-gradio-ui-server`.
 - **To Run:**
   ```bash
-  # Ensure environment variables (HOST_IP, HUGGINGFACEHUB_API_TOKEN) are set
+  # Ensure environment variables (host_ip, HUGGINGFACEHUB_API_TOKEN) are set
   docker compose --profile codegen-xeon-tgi up -d
   ```
 
@@ -103,14 +114,14 @@ Key parameters are configured via environment variables set before running `dock
 
 | Environment Variable                    | Description                                                                                                         | Default (Set Externally)                                                                         |
 | :-------------------------------------- | :------------------------------------------------------------------------------------------------------------------ | :----------------------------------------------------------------------------------------------- |
-| `HOST_IP`                               | External IP address of the host machine. **Required.**                                                              | `your_external_ip_address`                                                                       |
+| `host_ip`                               | External IP address of the host machine. **Required.**                                                              | `your_external_ip_address`                                                                       |
 | `HUGGINGFACEHUB_API_TOKEN`              | Your Hugging Face Hub token for model access. **Required.**                                                         | `your_huggingface_token`                                                                         |
 | `LLM_MODEL_ID`                          | Hugging Face model ID for the CodeGen LLM (used by TGI/vLLM service). Configured within `compose.yaml` environment. | `Qwen/Qwen2.5-Coder-7B-Instruct`                                                                 |
 | `EMBEDDING_MODEL_ID`                    | Hugging Face model ID for the embedding model (used by TEI service). Configured within `compose.yaml` environment.  | `BAAI/bge-base-en-v1.5`                                                                          |
 | `LLM_ENDPOINT`                          | Internal URL for the LLM serving endpoint (used by `codegen-llm-server`). Configured in `compose.yaml`.             | `http://codegen-tgi-server:80/generate` or `http://codegen-vllm-server:8000/v1/chat/completions` |
 | `TEI_EMBEDDING_ENDPOINT`                | Internal URL for the Embedding service. Configured in `compose.yaml`.                                               | `http://codegen-tei-embedding-server:80/embed`                                                   |
 | `DATAPREP_ENDPOINT`                     | Internal URL for the Data Preparation service. Configured in `compose.yaml`.                                        | `http://codegen-dataprep-server:80/dataprep`                                                     |
-| `BACKEND_SERVICE_ENDPOINT`              | External URL for the CodeGen Gateway (MegaService). Derived from `HOST_IP` and port `7778`.                         | `http://${HOST_IP}:7778/v1/codegen`                                                              |
+| `BACKEND_SERVICE_ENDPOINT`              | External URL for the CodeGen Gateway (MegaService). Derived from `host_ip` and port `7778`.                         | `http://${host_ip}:7778/v1/codegen`                                                              |
 | `*_PORT` (Internal)                     | Internal container ports (e.g., `80`, `6379`). Defined in `compose.yaml`.                                           | N/A                                                                                              |
 | `http_proxy` / `https_proxy`/`no_proxy` | Network proxy settings (if required).                                                                               | `""`                                                                                             |
 
@@ -150,23 +161,23 @@ Check logs for specific services: `docker compose logs <service_name>`
 
 ### Run Validation Script/Commands
 
-Use `curl` commands to test the main service endpoints. Ensure `HOST_IP` is correctly set in your environment.
+Use `curl` commands to test the main service endpoints. Ensure `host_ip` is correctly set in your environment.
 
-1.  **Validate LLM Serving Endpoint (Example for vLLM on default port 8000 internally, exposed differently):**
+1.  **Validate LLM Serving Endpoint (Example for vLLM on default port 9000 internally, exposed differently):**
 
     ```bash
     # This command structure targets the OpenAI-compatible vLLM endpoint
-    curl http://${HOST_IP}:8000/v1/chat/completions \
+    curl http://${host_ip}:9000/v1/chat/completions \
        -X POST \
        -H 'Content-Type: application/json' \
-       -d '{"model": "Qwen/Qwen2.5-Coder-7B-Instruct", "messages": [{"role": "user", "content": "Implement a basic Python class"}], "max_tokens":32}'
+       -d '{"model": "Qwen/Qwen2.5-Coder-32B-Instruct", "messages": [{"role": "user", "content": "Implement a basic Python class"}], "max_tokens":32}'
     ```
 
     - **Expected Output:** A JSON response with generated code in `choices[0].message.content`.
 
 2.  **Validate CodeGen Gateway (MegaService on default port 7778):**
     ```bash
-    curl http://${HOST_IP}:7778/v1/codegen \
+    curl http://${host_ip}:7778/v1/codegen \
       -H "Content-Type: application/json" \
       -d '{"messages": "Write a Python function that adds two numbers."}'
     ```
@@ -179,8 +190,8 @@ Multiple UI options can be configured via the `compose.yaml`.
 ### Gradio UI (Default)
 
 Access the default Gradio UI by navigating to:
-`http://{HOST_IP}:8080`
-_(Port `8080` is the default host mapping for `codegen-gradio-ui-server`)_
+`http://{host_ip}:5173`
+_(Port `5173` is the default host mapping for `codegen-gradio-ui-server`)_
 
 ![Gradio UI - Code Generation](../../../../assets/img/codegen_gradio_ui_main.png)
 ![Gradio UI - Resource Management](../../../../assets/img/codegen_gradio_ui_dataprep.png)
@@ -189,7 +200,7 @@ _(Port `8080` is the default host mapping for `codegen-gradio-ui-server`)_
 
 1.  Modify `compose.yaml`: Comment out the `codegen-gradio-ui-server` service and uncomment/add the `codegen-xeon-ui-server` (Svelte) service definition, ensuring the port mapping is correct (e.g., `"- 5173:5173"`).
 2.  Restart Docker Compose: `docker compose --profile <profile_name> up -d`
-3.  Access: `http://{HOST_IP}:5173` (or the host port you mapped).
+3.  Access: `http://{host_ip}:5173` (or the host port you mapped).
 
 ![Svelte UI Init](../../../../assets/img/codeGen_ui_init.jpg)
 
@@ -197,7 +208,7 @@ _(Port `8080` is the default host mapping for `codegen-gradio-ui-server`)_
 
 1.  Modify `compose.yaml`: Comment out the default UI service and uncomment/add the `codegen-xeon-react-ui-server` definition, ensuring correct port mapping (e.g., `"- 5174:80"`).
 2.  Restart Docker Compose: `docker compose --profile <profile_name> up -d`
-3.  Access: `http://{HOST_IP}:5174` (or the host port you mapped).
+3.  Access: `http://{host_ip}:5174` (or the host port you mapped).
 
 ![React UI](../../../../assets/img/codegen_react.png)
 
@@ -207,7 +218,7 @@ Users can interact with the backend service using the `Neural Copilot` VS Code e
 
 1.  **Install:** Find and install `Neural Copilot` from the VS Code Marketplace.
     ![Install Copilot](../../../../assets/img/codegen_copilot.png)
-2.  **Configure:** Set the "Service URL" in the extension settings to your CodeGen backend endpoint: `http://${HOST_IP}:7778/v1/codegen` (use the correct port if changed).
+2.  **Configure:** Set the "Service URL" in the extension settings to your CodeGen backend endpoint: `http://${host_ip}:7778/v1/codegen` (use the correct port if changed).
     ![Configure Endpoint](../../../../assets/img/codegen_endpoint.png)
 3.  **Usage:**
     - **Inline Suggestion:** Type a comment describing the code you want (e.g., `# Python function to read a file`) and wait for suggestions.
@@ -218,7 +229,7 @@ Users can interact with the backend service using the `Neural Copilot` VS Code e
 ## Troubleshooting
 
 - **Model Download Issues:** Check `HUGGINGFACEHUB_API_TOKEN`. Ensure internet connectivity or correct proxy settings. Check logs of `tgi-service`/`vllm-service` and `tei-embedding-server`. Gated models need prior Hugging Face access.
-- **Connection Errors:** Verify `HOST_IP` is correct and accessible. Check `docker ps` for port mappings. Ensure `no_proxy` includes `HOST_IP` if using a proxy. Check logs of the service failing to connect (e.g., `codegen-backend-server` logs if it can't reach `codegen-llm-server`).
+- **Connection Errors:** Verify `host_ip` is correct and accessible. Check `docker ps` for port mappings. Ensure `no_proxy` includes `host_ip` if using a proxy. Check logs of the service failing to connect (e.g., `codegen-backend-server` logs if it can't reach `codegen-llm-server`).
 - **"Container name is in use"**: Stop existing containers (`docker compose down`) or change `container_name` in `compose.yaml`.
 - **Resource Issues:** CodeGen models can be memory-intensive. Monitor host RAM usage. Increase Docker resources if needed.
 

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

@@ -53,18 +53,29 @@ This uses the default vLLM-based deployment profile (`codegen-gaudi-vllm`).
 
     ```bash
     # Replace with your host's external IP address (do not use localhost or 127.0.0.1)
-    export HOST_IP="your_external_ip_address"
+    export host_ip="your_external_ip_address"
     # Replace with your Hugging Face Hub API token
     export HUGGINGFACEHUB_API_TOKEN="your_huggingface_token"
 
     # Optional: Configure proxy if needed
     # export http_proxy="your_http_proxy"
     # export https_proxy="your_https_proxy"
-    # export no_proxy="localhost,127.0.0.1,${HOST_IP}" # Add other hosts if necessary
+    # export no_proxy="localhost,127.0.0.1,${host_ip}" # Add other hosts if necessary
     source ../../../set_env.sh
     ```
 
-    _Note: Ensure all required variables like ports (`LLM_SERVICE_PORT`, `MEGA_SERVICE_PORT`, etc.) are set if not using defaults from the compose file._
+    _Note: The compose file might read additional variables from set_env.sh. Ensure all required variables like ports (`LLM_SERVICE_PORT`, `MEGA_SERVICE_PORT`, etc.) are set if not using defaults from the compose file._
+    like
+
+    ```
+    export LLM_MODEL_ID="Qwen/Qwen2.5-Coder-32B-Instruct"
+    ```
+
+    can be changed to small model if needed
+
+    ```
+    export LLM_MODEL_ID="Qwen/Qwen2.5-Coder-7B-Instruct"
+    ```
 
 2.  **Start Services (vLLM Profile):**
 
@@ -94,7 +105,7 @@ The `compose.yaml` file uses Docker Compose profiles to select the LLM serving b
 - **Other Services:** Same CPU-based services as the vLLM profile.
 - **To Run:**
   ```bash
-  # Ensure environment variables (HOST_IP, HUGGINGFACEHUB_API_TOKEN) are set
+  # Ensure environment variables (host_ip, HUGGINGFACEHUB_API_TOKEN) are set
   docker compose --profile codegen-gaudi-tgi up -d
   ```
 
@@ -106,14 +117,14 @@ Key parameters are configured via environment variables set before running `dock
 
 | Environment Variable                    | Description                                                                                                         | Default (Set Externally)                                                                         |
 | :-------------------------------------- | :------------------------------------------------------------------------------------------------------------------ | :----------------------------------------------------------------------------------------------- |
-| `HOST_IP`                               | External IP address of the host machine. **Required.**                                                              | `your_external_ip_address`                                                                       |
+| `host_ip`                               | External IP address of the host machine. **Required.**                                                              | `your_external_ip_address`                                                                       |
 | `HUGGINGFACEHUB_API_TOKEN`              | Your Hugging Face Hub token for model access. **Required.**                                                         | `your_huggingface_token`                                                                         |
-| `LLM_MODEL_ID`                          | Hugging Face model ID for the CodeGen LLM (used by TGI/vLLM service). Configured within `compose.yaml` environment. | `Qwen/Qwen2.5-Coder-7B-Instruct`                                                                 |
+| `LLM_MODEL_ID`                          | Hugging Face model ID for the CodeGen LLM (used by TGI/vLLM service). Configured within `compose.yaml` environment. | `Qwen/Qwen2.5-Coder-32B-Instruct`                                                                |
 | `EMBEDDING_MODEL_ID`                    | Hugging Face model ID for the embedding model (used by TEI service). Configured within `compose.yaml` environment.  | `BAAI/bge-base-en-v1.5`                                                                          |
 | `LLM_ENDPOINT`                          | Internal URL for the LLM serving endpoint (used by `codegen-llm-server`). Configured in `compose.yaml`.             | `http://codegen-tgi-server:80/generate` or `http://codegen-vllm-server:8000/v1/chat/completions` |
 | `TEI_EMBEDDING_ENDPOINT`                | Internal URL for the Embedding service. Configured in `compose.yaml`.                                               | `http://codegen-tei-embedding-server:80/embed`                                                   |
 | `DATAPREP_ENDPOINT`                     | Internal URL for the Data Preparation service. Configured in `compose.yaml`.                                        | `http://codegen-dataprep-server:80/dataprep`                                                     |
-| `BACKEND_SERVICE_ENDPOINT`              | External URL for the CodeGen Gateway (MegaService). Derived from `HOST_IP` and port `7778`.                         | `http://${HOST_IP}:7778/v1/codegen`                                                              |
+| `BACKEND_SERVICE_ENDPOINT`              | External URL for the CodeGen Gateway (MegaService). Derived from `host_ip` and port `7778`.                         | `http://${host_ip}:7778/v1/codegen`                                                              |
 | `*_PORT` (Internal)                     | Internal container ports (e.g., `80`, `6379`). Defined in `compose.yaml`.                                           | N/A                                                                                              |
 | `http_proxy` / `https_proxy`/`no_proxy` | Network proxy settings (if required).                                                                               | `""`                                                                                             |
 
@@ -170,21 +181,21 @@ Check logs: `docker compose logs <service_name>`. Pay attention to `vllm-gaudi-s
 
 ### Run Validation Script/Commands
 
-Use `curl` commands targeting the main service endpoints. Ensure `HOST_IP` is correctly set.
+Use `curl` commands targeting the main service endpoints. Ensure `host_ip` is correctly set.
 
-1.  **Validate LLM Serving Endpoint (Example for vLLM on default port 8000 internally, exposed differently):**
+1.  **Validate LLM Serving Endpoint (Example for vLLM on default port 9000 internally, exposed differently):**
 
     ```bash
     # This command structure targets the OpenAI-compatible vLLM endpoint
-    curl http://${HOST_IP}:8000/v1/chat/completions \
+    curl http://${host_ip}:9000/v1/chat/completions \
        -X POST \
        -H 'Content-Type: application/json' \
-       -d '{"model": "Qwen/Qwen2.5-Coder-7B-Instruct", "messages": [{"role": "user", "content": "Implement a basic Python class"}], "max_tokens":32}'
+       -d '{"model": "Qwen/Qwen2.5-Coder-32B-Instruct", "messages": [{"role": "user", "content": "Implement a basic Python class"}], "max_tokens":32}'
     ```
 
 2.  **Validate CodeGen Gateway (MegaService, default host port 7778):**
     ```bash
-    curl http://${HOST_IP}:7778/v1/codegen \
+    curl http://${host_ip}:7778/v1/codegen \
       -H "Content-Type: application/json" \
       -d '{"messages": "Implement a sorting algorithm in Python."}'
     ```
@@ -197,8 +208,8 @@ UI options are similar to the Xeon deployment.
 ### Gradio UI (Default)
 
 Access the default Gradio UI:
-`http://{HOST_IP}:8080`
-_(Port `8080` is the default host mapping)_
+`http://{host_ip}:5173`
+_(Port `5173` is the default host mapping)_
 
 ![Gradio UI](../../../../assets/img/codegen_gradio_ui_main.png)
 
@@ -206,17 +217,17 @@ _(Port `8080` is the default host mapping)_
 
 1.  Modify `compose.yaml`: Swap Gradio service for Svelte (`codegen-gaudi-ui-server`), check port map (e.g., `5173:5173`).
 2.  Restart: `docker compose --profile <profile_name> up -d`
-3.  Access: `http://{HOST_IP}:5173`
+3.  Access: `http://{host_ip}:5173`
 
 ### React UI (Optional)
 
 1.  Modify `compose.yaml`: Swap Gradio service for React (`codegen-gaudi-react-ui-server`), check port map (e.g., `5174:80`).
 2.  Restart: `docker compose --profile <profile_name> up -d`
-3.  Access: `http://{HOST_IP}:5174`
+3.  Access: `http://{host_ip}:5174`
 
 ### VS Code Extension (Optional)
 
-Use the `Neural Copilot` extension configured with the CodeGen backend URL: `http://${HOST_IP}:7778/v1/codegen`. (See Xeon README for detailed setup screenshots).
+Use the `Neural Copilot` extension configured with the CodeGen backend URL: `http://${host_ip}:7778/v1/codegen`. (See Xeon README for detailed setup screenshots).
 
 ## Troubleshooting
 
@@ -226,7 +237,7 @@ Use the `Neural Copilot` extension configured with the CodeGen backend URL: `htt
   - Verify `runtime: habana` and volume mounts in `compose.yaml`.
   - Gaudi initialization can take significant time and memory. Monitor resource usage.
 - **Model Download Issues:** Check `HUGGINGFACEHUB_API_TOKEN`, internet access, proxy settings. Check LLM service logs.
-- **Connection Errors:** Verify `HOST_IP`, ports, and proxy settings. Use `docker ps` and check service logs.
+- **Connection Errors:** Verify `host_ip`, ports, and proxy settings. Use `docker ps` and check service logs.
 
 ## Stopping the Application
 

CodeTrans/README.md

@@ -22,12 +22,11 @@ This Code Translation use case demonstrates Text Generation Inference across mul
 
 The table below lists currently available deployment options. They outline in detail the implementation of this example on selected hardware.
 
-| Category               | Deployment Option    | Description                                                       |
-| ---------------------- | -------------------- | ----------------------------------------------------------------- |
-| On-premise Deployments | Docker compose       | [CodeTrans deployment on Xeon](./docker_compose/intel/cpu/xeon)   |
-|                        |                      | [CodeTrans deployment on Gaudi](./docker_compose/intel/hpu/gaudi) |
-|                        |                      | [CodeTrans deployment on AMD ROCm](./docker_compose/amd/gpu/rocm) |
-|                        | Kubernetes           | [Helm Charts](./kubernetes/helm)                                  |
-|                        |                      | [GMC](./kubernetes/gmc)                                           |
-|                        | Azure                | Work-in-progress                                                  |
-|                        | Intel Tiber AI Cloud | Work-in-progress                                                  |
+| Category               | Deployment Option    | Description                                                                 |
+| ---------------------- | -------------------- | --------------------------------------------------------------------------- |
+| On-premise Deployments | Docker compose       | [CodeTrans deployment on Xeon](./docker_compose/intel/cpu/xeon/README.md)   |
+|                        |                      | [CodeTrans deployment on Gaudi](./docker_compose/intel/hpu/gaudi/README.md) |
+|                        |                      | [CodeTrans deployment on AMD ROCm](./docker_compose/amd/gpu/rocm/README.md) |
+|                        | Kubernetes           | [Helm Charts](./kubernetes/helm/README.md)                                  |
+|                        | Azure                | Work-in-progress                                                            |
+|                        | Intel Tiber AI Cloud | Work-in-progress                                                            |

CodeTrans/README_miscellaneous.md

@@ -44,3 +44,38 @@ Some HuggingFace resources, such as some models, are only accessible if the deve
 
 2. (Docker only) If all microservices work well, check the port ${host_ip}:7777, the port may be allocated by other users, you can modify the `compose.yaml`.
 3. (Docker only) If you get errors like "The container name is in use", change container name in `compose.yaml`.
+
+## Monitoring OPEA Services with Prometheus and Grafana Dashboard
+
+OPEA microservice deployment can easily be monitored through Grafana dashboards using data collected via Prometheus. Follow the [README](https://github.com/opea-project/GenAIEval/blob/main/evals/benchmark/grafana/README.md) to setup Prometheus and Grafana servers and import dashboards to monitor the OPEA services.
+
+![example dashboards](./assets/img/example_dashboards.png)
+![tgi dashboard](./assets/img/tgi_dashboard.png)
+
+## Tracing with OpenTelemetry and Jaeger
+
+> NOTE: This feature is disabled by default. Please use the compose.telemetry.yaml file to enable this feature.
+
+OPEA microservice and [TGI](https://huggingface.co/docs/text-generation-inference/en/index)/[TEI](https://huggingface.co/docs/text-embeddings-inference/en/index) serving can easily be traced through [Jaeger](https://www.jaegertracing.io/) dashboards in conjunction with [OpenTelemetry](https://opentelemetry.io/) Tracing feature. Follow the [README](https://github.com/opea-project/GenAIComps/tree/main/comps/cores/telemetry#tracing) to trace additional functions if needed.
+
+Tracing data is exported to http://{EXTERNAL_IP}:4318/v1/traces via Jaeger.
+Users could also get the external IP via below command.
+
+```bash
+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 asynchronous function such as `llm/MicroService_asyn_generate` and user needs to check the trace of the asynchronous function in another operation like
+opea:llm_generate_stream.
+![image](https://github.com/user-attachments/assets/a973d283-198f-4ce2-a7eb-58515b77503e)

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

@@ -2,7 +2,11 @@
 
 DocRetriever are the most widely adopted use case for leveraging the different methodologies to match user query against a set of free-text records. DocRetriever is essential to RAG system, which bridges the knowledge gap by dynamically fetching relevant information from external sources, ensuring that responses generated remain factual and current. The core of this architecture are vector databases, which are instrumental in enabling efficient and semantic retrieval of information. These databases store data as vectors, allowing RAG to swiftly access the most pertinent documents or data points based on semantic similarity.
 
-## 1. Build Images for necessary microservices. (Optional after docker image release)
+\_Note:
+
+As the related docker images were published to Docker Hub, you can ignore the below step 1 and 2， quick start from step 3.
+
+## 1. Build Images for necessary microservices. (Optional)
 
 - Embedding TEI Image
 
@@ -30,7 +34,7 @@ DocRetriever are the most widely adopted use case for leveraging the different m
   docker build -t opea/dataprep:latest --build-arg https_proxy=$https_proxy --build-arg http_proxy=$http_proxy -f comps/dataprep/src/Dockerfile .
   ```
 
-## 2. Build Images for MegaService
+## 2. Build Images for MegaService (Optional)
 
 ```bash
 cd ..
@@ -44,6 +48,19 @@ docker build --no-cache -t opea/doc-index-retriever:latest --build-arg https_pro
 ```bash
 export host_ip="YOUR IP ADDR"
 export HUGGINGFACEHUB_API_TOKEN=${your_hf_api_token}
+```
+
+Set environment variables by
+
+```
+cd GenAIExamples/DocIndexRetriever/docker_compose/intel/cpu/xeon
+source set_env.sh
+```
+
+Note: set_env.sh will help to set all required variables. Please ensure all required variables like ports (LLM_SERVICE_PORT, MEGA_SERVICE_PORT, etc.) are set if not using defaults from the compose file.
+or Set environment variables manually
+
+```
 export EMBEDDING_MODEL_ID="BAAI/bge-base-en-v1.5"
 export RERANK_MODEL_ID="BAAI/bge-reranker-base"
 export TEI_EMBEDDING_ENDPOINT="http://${host_ip}:6006"

SearchQnA/README.md

@@ -30,66 +30,38 @@ The architecture of the SearchQnA Application is illustrated below:
 The SearchQnA example is implemented using the component-level microservices defined in [GenAIComps](https://github.com/opea-project/GenAIComps). The flow chart below shows the information flow between different microservices for this example.
 
 ```mermaid
----
-config:
-  flowchart:
-    nodeSpacing: 400
-    rankSpacing: 100
-    curve: linear
-  themeVariables:
-    fontSize: 50px
----
+%% Orange are microservices from third parties that are 'wrapped' as OPEA components.
 flowchart LR
-    %% Colors %%
-    classDef blue fill:#ADD8E6,stroke:#ADD8E6,stroke-width:2px,fill-opacity:0.5
-    classDef orange fill:#FBAA60,stroke:#ADD8E6,stroke-width:2px,fill-opacity:0.5
-    classDef orchid fill:#C26DBC,stroke:#ADD8E6,stroke-width:2px,fill-opacity:0.5
-    classDef invisible fill:transparent,stroke:transparent;
-    style SearchQnA-MegaService stroke:#000000
+    User["User"] --> Nginx["Nginx<br>searchqna-nginx-server"]
+    Nginx --> UI["UI<br>searchqna-ui-server"] & Gateway & User
+    UI --> Nginx
+    Gateway --> Nginx & Embedding
+    Embedding --> Retriever
+    Retriever --> Reranker
+    Reranker --> LLM
+    LLM --> Gateway
+    LLM <-.-> TGI_Service["LLM<br>tgi-service"]
+    Embedding <-.-> TEI_Embedding["TEI Embedding<br>tei-embedding-server"]
+    Reranker <-.-> TEI_Reranker["TEI Reranker<br>tei-reranking-server"]
 
-    %% Subgraphs %%
-    subgraph SearchQnA-MegaService["SearchQnA MegaService "]
-        direction LR
-        EM([Embedding MicroService]):::blue
-        RET([Web Retrieval MicroService]):::blue
-        RER([Rerank MicroService]):::blue
-        LLM([LLM MicroService]):::blue
-    end
-    subgraph UserInterface[" User Interface "]
-        direction LR
-        a([User Input Query]):::orchid
-        UI([UI server<br>]):::orchid
-    end
-
-
-
-    TEI_RER{{Reranking service<br>}}
-    TEI_EM{{Embedding service <br>}}
-    VDB{{Vector DB<br><br>}}
-    R_RET{{Web Retriever service <br>}}
-    LLM_gen{{LLM Service <br>}}
-    GW([SearchQnA GateWay<br>]):::orange
-
-    %% Questions interaction
-    direction LR
-    a[User Input Query] --> UI
-    UI --> GW
-    GW <==> SearchQnA-MegaService
-    EM ==> RET
-    RET ==> RER
-    RER ==> LLM
-
-    %% Embedding service flow
-    direction LR
-    EM <-.-> TEI_EM
-    RET <-.-> R_RET
-    RER <-.-> TEI_RER
-    LLM <-.-> LLM_gen
+     TEI_Embedding:::ext
+     TEI_Reranker:::ext
+     TGI_Service:::ext
 
+ subgraph MegaService["MegaService"]
+        LLM["LLM<br>llm-textgen-server"]
+        Reranker["Reranker<br>reranking-tei-server"]
+        Retriever["Retriever<br>web-retriever-server"]
+        Embedding["Embedding<br>embedding-server"]
+  end
+ subgraph Backend["searchqna-backend-server"]
     direction TB
-    %% Vector DB interaction
-    R_RET <-.-> VDB
-
+        MegaService
+        Gateway["Backend Endpoint"]
+ end
+    classDef default fill:#fff,stroke:#000,color:#000
+    classDef ext fill:#f9cb9c,stroke:#000,color:#000
+    style MegaService margin-top:20px,margin-bottom:20px
 ```
 
 This SearchQnA use case performs Search-augmented Question Answering across multiple platforms. Currently, we provide the example for Intel® Gaudi® 2 and Intel® Xeon® Scalable Processors, and we invite contributions from other hardware vendors to expand OPEA ecosystem.
@@ -98,8 +70,8 @@ This SearchQnA use case performs Search-augmented Question Answering across mult
 
 The table below lists the available deployment options and their implementation details for different hardware platforms.
 
-| Category               | Deployment Option      | Description                                                    |
-| ---------------------- | ---------------------- | -------------------------------------------------------------- |
-| On-premise Deployments | Docker Compose (Xeon)  | [DocSum deployment on Xeon](./docker_compose/intel/cpu/xeon)   |
-|                        | Docker Compose (Gaudi) | [DocSum deployment on Gaudi](./docker_compose/intel/hpu/gaudi) |
-|                        | Docker Compose (ROCm)  | [DocSum deployment on AMD ROCm](./docker_compose/amd/gpu/rocm) |
+| Category               | Deployment Option      | Description                                                                 |
+| ---------------------- | ---------------------- | --------------------------------------------------------------------------- |
+| On-premise Deployments | Docker Compose (Xeon)  | [SearchQnA deployment on Xeon](./docker_compose/intel/cpu/xeon/README.md)   |
+|                        | Docker Compose (Gaudi) | [SearchQnA deployment on Gaudi](./docker_compose/intel/hpu/gaudi/README.md) |
+|                        | Docker Compose (ROCm)  | [SearchQnA deployment on AMD ROCm](./docker_compose/amd/gpu/rocm/README.md) |

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

@@ -170,7 +170,25 @@ services:
       no_proxy: ${no_proxy}
       https_proxy: ${https_proxy}
       http_proxy: ${http_proxy}
-      BACKEND_BASE_URL: ${SEARCH_BACKEND_SERVICE_ENDPOINT}
+    ipc: host
+    restart: always
+  search-nginx-server:
+    image: ${REGISTRY:-opea}/nginx:${TAG:-latest}
+    container_name: search-nginx-server
+    depends_on:
+      - search-backend-server
+      - search-ui-server
+    ports:
+      - "${NGINX_PORT:-80}:80"
+    environment:
+      - no_proxy=${no_proxy}
+      - https_proxy=${https_proxy}
+      - http_proxy=${http_proxy}
+      - FRONTEND_SERVICE_IP=search-ui-server
+      - FRONTEND_SERVICE_PORT=5173
+      - BACKEND_SERVICE_NAME=search
+      - BACKEND_SERVICE_IP=search-backend-server
+      - BACKEND_SERVICE_PORT=8888
     ipc: host
     restart: always
 

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

@@ -176,10 +176,27 @@ services:
       no_proxy: ${no_proxy}
       https_proxy: ${https_proxy}
       http_proxy: ${http_proxy}
-      BACKEND_BASE_URL: ${SEARCH_BACKEND_SERVICE_ENDPOINT}
     ipc: host
     restart: always
-
+  search-nginx-server:
+    image: ${REGISTRY:-opea}/nginx:${TAG:-latest}
+    container_name: search-nginx-server
+    depends_on:
+      - search-backend-server
+      - search-ui-server
+    ports:
+      - "${NGINX_PORT:-80}:80"
+    environment:
+      - no_proxy=${no_proxy}
+      - https_proxy=${https_proxy}
+      - http_proxy=${http_proxy}
+      - FRONTEND_SERVICE_IP=search-ui-server
+      - FRONTEND_SERVICE_PORT=5173
+      - BACKEND_SERVICE_NAME=search
+      - BACKEND_SERVICE_IP=search-backend-server
+      - BACKEND_SERVICE_PORT=8888
+    ipc: host
+    restart: always
 networks:
   default:
     driver: bridge

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

@@ -168,10 +168,27 @@ services:
       - no_proxy=${no_proxy}
       - https_proxy=${https_proxy}
       - http_proxy=${http_proxy}
-      - BACKEND_BASE_URL=${BACKEND_SERVICE_ENDPOINT}
     ipc: host
     restart: always
-
+  searchqna-xeon-nginx-server:
+    image: ${REGISTRY:-opea}/nginx:${TAG:-latest}
+    container_name: searchqna-xeon-nginx-server
+    depends_on:
+      - searchqna-xeon-backend-server
+      - searchqna-xeon-ui-server
+    ports:
+      - "${NGINX_PORT:-80}:80"
+    environment:
+      - no_proxy=${no_proxy}
+      - https_proxy=${https_proxy}
+      - http_proxy=${http_proxy}
+      - FRONTEND_SERVICE_IP=searchqna-xeon-ui-server
+      - FRONTEND_SERVICE_PORT=5173
+      - BACKEND_SERVICE_NAME=searchqna
+      - BACKEND_SERVICE_IP=searchqna-xeon-backend-server
+      - BACKEND_SERVICE_PORT=8888
+    ipc: host
+    restart: always
 
 networks:
   default:

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

@@ -187,7 +187,25 @@ services:
       - no_proxy=${no_proxy}
       - https_proxy=${https_proxy}
       - http_proxy=${http_proxy}
-      - BACKEND_BASE_URL=${BACKEND_SERVICE_ENDPOINT}
+    ipc: host
+    restart: always
+  searchqna-gaudi-nginx-server:
+    image: ${REGISTRY:-opea}/nginx:${TAG:-latest}
+    container_name: searchqna-gaudi-nginx-server
+    depends_on:
+      - searchqna-gaudi-backend-server
+      - searchqna-gaudi-ui-server
+    ports:
+      - "${NGINX_PORT:-80}:80"
+    environment:
+      - no_proxy=${no_proxy}
+      - https_proxy=${https_proxy}
+      - http_proxy=${http_proxy}
+      - FRONTEND_SERVICE_IP=searchqna-gaudi-ui-server
+      - FRONTEND_SERVICE_PORT=5173
+      - BACKEND_SERVICE_NAME=searchqna
+      - BACKEND_SERVICE_IP=searchqna-gaudi-backend-server
+      - BACKEND_SERVICE_PORT=8888
     ipc: host
     restart: always
 

SearchQnA/docker_image_build/build.yaml

@@ -46,3 +46,9 @@ services:
       context: GenAIComps
       dockerfile: comps/third_parties/vllm/src/Dockerfile.amd_gpu
     image: ${REGISTRY:-opea}/vllm-rocm:${TAG:-latest}
+  nginx:
+    build:
+      context: GenAIComps
+      dockerfile: comps/third_parties/nginx/src/Dockerfile
+    extends: searchqna
+    image: ${REGISTRY:-opea}/nginx:${TAG:-latest}

SearchQnA/tests/test_compose_on_gaudi.sh

@@ -32,7 +32,7 @@ function build_docker_images() {
     git clone --depth 1 --branch ${opea_branch} https://github.com/opea-project/GenAIComps.git
 
     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"
+    service_list="searchqna searchqna-ui embedding web-retriever reranking llm-textgen nginx"
     docker compose -f build.yaml build ${service_list} --no-cache > ${LOG_PATH}/docker_image_build.log
 
     docker pull ghcr.io/huggingface/text-embeddings-inference:cpu-1.6

SearchQnA/tests/test_compose_on_rocm.sh

@@ -20,7 +20,7 @@ function build_docker_images() {
     git clone https://github.com/opea-project/GenAIComps.git && cd GenAIComps && git checkout "${opea_branch:-"main"}" && cd ../
 
     echo "Build all the images with --no-cache, check docker_image_build.log for details..."
-    service_list="searchqna searchqna-ui embedding web-retriever reranking llm-textgen"
+    service_list="searchqna searchqna-ui embedding web-retriever reranking llm-textgen nginx"
     docker compose -f build.yaml build ${service_list} --no-cache > ${LOG_PATH}/docker_image_build.log
 
     docker pull ghcr.io/huggingface/text-embeddings-inference:cpu-1.6

SearchQnA/tests/test_compose_on_xeon.sh

@@ -32,7 +32,7 @@ function build_docker_images() {
     git clone --depth 1 --branch ${opea_branch} https://github.com/opea-project/GenAIComps.git
 
     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"
+    service_list="searchqna searchqna-ui embedding web-retriever reranking llm-textgen nginx"
     docker compose -f build.yaml build ${service_list} --no-cache > ${LOG_PATH}/docker_image_build.log
 
     docker pull ghcr.io/huggingface/text-embeddings-inference:cpu-1.6

SearchQnA/tests/test_compose_vllm_on_rocm.sh

@@ -20,7 +20,7 @@ function build_docker_images() {
     git clone https://github.com/opea-project/GenAIComps.git && cd GenAIComps && git checkout "${opea_branch:-"main"}" && cd ../
 
     echo "Build all the images with --no-cache, check docker_image_build.log for details..."
-    service_list="searchqna searchqna-ui embedding web-retriever reranking llm-textgen vllm-rocm"
+    service_list="searchqna searchqna-ui embedding web-retriever reranking llm-textgen vllm-rocm nginx"
     docker compose -f build.yaml build ${service_list} --no-cache > ${LOG_PATH}/docker_image_build.log
 
     docker pull ghcr.io/huggingface/text-embeddings-inference:cpu-1.5

SearchQnA/ui/svelte/.env

@@ -1 +1 @@
-BACKEND_BASE_URL = 'http://backend_address:3008/v1/searchqna'
+BACKEND_BASE_URL = '/v1/searchqna'

SearchQnA/ui/svelte/playwright.config.ts

@@ -38,7 +38,7 @@ export default defineConfig({
 		/* Maximum time each action such as `click()` can take. Defaults to 0 (no limit). */
 		actionTimeout: 0,
 		/* Base URL to use in actions like `await page.goto('/')`. */
-		baseURL: "http://localhost:5173",
+		baseURL: "http://localhost:80",
 
 		/* Collect trace when retrying the failed test. See https://playwright.dev/docs/trace-viewer */
 		trace: "on-first-retry",