Only test

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

.github/env/_build_image.sh

@@ -1,5 +0,0 @@
-# Copyright (C) 2025 Intel Corporation
-# SPDX-License-Identifier: Apache-2.0
-
-export VLLM_VER=v0.8.3
-export VLLM_FORK_VER=v0.6.6.post1+Gaudi-1.20.0

.github/workflows/_build_image.yml

@@ -75,12 +75,17 @@ jobs:
         run: |
           cd ${{ github.workspace }}/${{ inputs.example }}/docker_image_build
           docker_compose_path=${{ github.workspace }}/${{ inputs.example }}/docker_image_build/build.yaml
-          source ${{ github.workspace }}/.github/env/_build_image.sh
           if [[ $(grep -c "vllm:" ${docker_compose_path}) != 0 ]]; then
-              git clone -b ${VLLM_VER} --single-branch https://github.com/vllm-project/vllm.git
+              git clone https://github.com/vllm-project/vllm.git && cd vllm
+              VLLM_VER=v0.8.3
+              echo "Check out vLLM tag ${VLLM_VER}"
+              git checkout ${VLLM_VER} &> /dev/null && cd ../
           fi
           if [[ $(grep -c "vllm-gaudi:" ${docker_compose_path}) != 0 ]]; then
-              git clone -b ${VLLM_FORK_VER} --single-branch https://github.com/HabanaAI/vllm-fork.git
+              git clone https://github.com/HabanaAI/vllm-fork.git && cd vllm-fork
+              VLLM_VER=v0.6.6.post1+Gaudi-1.20.0
+              echo "Check out vLLM tag ${VLLM_VER}"
+              git checkout ${VLLM_VER} &> /dev/null && cd ../
           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

@@ -137,7 +137,7 @@ jobs:
         env:
           example: ${{ inputs.example }}
         run: |
-          if [[ ! "$example" =~ ^[a-zA-Z0-9]{1,20}$ ]] || [[ "$example" =~ \.\. ]] || [[ "$example" == -* || "$example" == *- ]]; then
+          if [[ ! "$example" =~ ^[a-zA-Z]{1,20}$ ]] || [[ "$example" =~ \.\. ]] || [[ "$example" == -* || "$example" == *- ]]; then
             echo "Error: Invalid input - only lowercase alphanumeric and internal hyphens allowed"
             exit 1
           fi

.github/workflows/daily-update-vllm-version.yml

@@ -1,94 +0,0 @@
-# Copyright (C) 2025 Intel Corporation
-# SPDX-License-Identifier: Apache-2.0
-
-name: Daily update vLLM & vLLM-fork version
-
-on:
-  schedule:
-    - cron: "30 22 * * *"
-  workflow_dispatch:
-
-env:
-  BRANCH_NAME: "update"
-  USER_NAME: "CICD-at-OPEA"
-  USER_EMAIL: "CICD@opea.dev"
-
-jobs:
-  freeze-tag:
-    runs-on: ubuntu-latest
-    strategy:
-      matrix:
-        include:
-          - repo: vLLM
-            repo_name: vllm-project/vllm
-            ver_name: VLLM_VER
-          - repo: vLLM-fork
-            repo_name: HabanaAI/vllm-fork
-            ver_name: VLLM_FORK_VER
-      fail-fast: false
-    permissions:
-      contents: write
-      pull-requests: write
-    steps:
-      - name: Checkout repository
-        uses: actions/checkout@v4
-        with:
-          fetch-depth: 0
-          ref: ${{ github.ref }}
-
-      - name: Set up Git
-        run: |
-          git config --global user.name ${{ env.USER_NAME }}
-          git config --global user.email ${{ env.USER_EMAIL }}
-          git remote set-url origin https://${{ env.USER_NAME }}:"${{ secrets.ACTION_TOKEN }}"@github.com/${{ github.repository }}.git
-          git fetch
-
-          if git ls-remote https://github.com/${{ github.repository }}.git "refs/heads/${{ env.BRANCH_NAME }}_${{ matrix.repo }}" | grep -q "refs/heads/${{ env.BRANCH_NAME }}_${{ matrix.repo }}"; then
-            echo "branch ${{ env.BRANCH_NAME }}_${{ matrix.repo }} exists"
-            git checkout ${{ env.BRANCH_NAME }}_${{ matrix.repo }}
-          else
-            echo "branch ${{ env.BRANCH_NAME }}_${{ matrix.repo }} not exists"
-            git checkout -b ${{ env.BRANCH_NAME }}_${{ matrix.repo }}
-            git push origin ${{ env.BRANCH_NAME }}_${{ matrix.repo }}
-            echo "branch ${{ env.BRANCH_NAME }}_${{ matrix.repo }} created successfully"
-          fi
-
-      - name: Run script
-        run: |
-          latest_vllm_ver=$(curl -s "https://api.github.com/repos/${{ matrix.repo_name }}/tags" | jq '.[0].name' -)
-          latest_vllm_ver=$(echo "$latest_vllm_ver" | sed 's/"//g')
-          echo "latest_vllm_ver=${latest_vllm_ver}" >> "$GITHUB_ENV"
-          find . -type f -name "*.sh" -exec sed -i "s/${{ matrix.ver_name }}=.*/${{ matrix.ver_name }}=${latest_vllm_ver}/" {} \;
-
-      - name: Commit changes
-        run: |
-          git add .
-          if git diff-index --quiet HEAD --; then
-            echo "No changes detected, skipping commit."
-            exit 1
-          else
-            git commit -s -m "Update ${{ matrix.repo }} version to ${latest_vllm_ver}"
-            git push --set-upstream origin ${{ env.BRANCH_NAME }}_${{ matrix.repo }}
-          fi
-
-      - name: Create Pull Request
-        env:
-          GH_TOKEN: ${{ secrets.ACTION_TOKEN }}
-        run: |
-          pr_count=$(curl -H "Authorization: token ${{ secrets.ACTION_TOKEN }}" -s "https://api.github.com/repos/${{ github.repository }}/pulls?state=all&head=${{ env.USER_NAME }}:${{ env.BRANCH_NAME }}_${{ matrix.repo }}" | jq '. | length')
-          if [ $pr_count -gt 0 ]; then
-            echo "Pull Request exists"
-            pr_number=$(curl -H "Authorization: token ${{ secrets.ACTION_TOKEN }}" -s "https://api.github.com/repos/${{ github.repository }}/pulls?state=all&head=${{ env.USER_NAME }}:${{ env.BRANCH_NAME }}_${{ matrix.repo }}" | jq '.[0].number')
-            gh pr edit ${pr_number} \
-              --title "Update ${{ matrix.repo }} version to ${latest_vllm_ver}" \
-              --body "Update ${{ matrix.repo }} version to ${latest_vllm_ver}"
-            echo "Pull Request updated successfully"
-          else
-            echo "Pull Request does not exists..."
-            gh pr create \
-              -B main \
-              -H ${{ env.BRANCH_NAME }}_${{ matrix.repo }} \
-              --title "Update ${{ matrix.repo }} version to ${latest_vllm_ver}" \
-              --body "Update ${{ matrix.repo }} version to ${latest_vllm_ver}"
-            echo "Pull Request created successfully"
-          fi

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

@@ -9,7 +9,7 @@ on:
   workflow_dispatch:
 
 env:
-  EXAMPLES: ${{ vars.NIGHTLY_RELEASE_EXAMPLES }}
+  EXAMPLES: CodeGen,CodeTrans #${{ vars.NIGHTLY_RELEASE_EXAMPLES }}
   TAG: "latest"
   PUBLISH_TAGS: "latest"
 
@@ -75,7 +75,7 @@ jobs:
 
   publish:
     needs: [get-build-matrix, get-image-list, build-images]
-    if: always()
+    if: ${{ success() }}
     strategy:
       matrix:
         image: ${{ fromJSON(needs.get-image-list.outputs.matrix) }}

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

@@ -23,7 +23,6 @@ jobs:
       - name: Check the Validity of Hyperlinks
         run: |
           cd ${{github.workspace}}
-          delay=15
           fail="FALSE"
           merged_commit=$(git log -1 --format='%H')
           changed_files="$(git diff --name-status --diff-filter=ARM ${{ github.event.pull_request.base.sha }} ${merged_commit} | awk '/\.md$/ {print $NF}')"
@@ -36,20 +35,15 @@ jobs:
                   # echo $url_line
                   url=$(echo "$url_line"|cut -d '(' -f2 | cut -d ')' -f1|sed 's/\.git$//')
                   path=$(echo "$url_line"|cut -d':' -f1 | cut -d'/' -f2-)
-                  if [[ "$url" == "https://platform.openai.com/api-keys"* ]]; then
-                    echo "Link "$url" from ${{github.workspace}}/$path needs to be verified by a real person."
-                  else
-                    sleep $delay
-                    response=$(curl -L -s -o /dev/null -w "%{http_code}" "$url")|| true
-                    if [ "$response" -ne 200 ]; then
-                      echo "**********Validation failed ($response), try again**********"
-                      response_retry=$(curl -s -o /dev/null -w "%{http_code}" "$url")
-                      if [ "$response_retry" -eq 200 ]; then
-                        echo "*****Retry successfully*****"
-                      else
-                        echo "Invalid link ($response_retry) from ${{github.workspace}}/$path: $url"
-                        fail="TRUE"
-                      fi
+                  response=$(curl -L -s -o /dev/null -w "%{http_code}" "$url")|| true
+                  if [ "$response" -ne 200 ]; then
+                    echo "**********Validation failed, try again**********"
+                    response_retry=$(curl -s -o /dev/null -w "%{http_code}" "$url")
+                    if [ "$response_retry" -eq 200 ]; then
+                      echo "*****Retry successfully*****"
+                    else
+                      echo "Invalid link from ${{github.workspace}}/$path: $url"
+                      fail="TRUE"
                     fi
                   fi
                 done

AgentQnA/README.md

@@ -99,7 +99,7 @@ flowchart LR
 
 #### First, clone the `GenAIExamples` repo.
 
-```bash
+```
 export WORKDIR=<your-work-directory>
 cd $WORKDIR
 git clone https://github.com/opea-project/GenAIExamples.git
@@ -109,7 +109,7 @@ git clone https://github.com/opea-project/GenAIExamples.git
 
 ##### For proxy environments only
 
-```bash
+```
 export http_proxy="Your_HTTP_Proxy"
 export https_proxy="Your_HTTPs_Proxy"
 # Example: no_proxy="localhost, 127.0.0.1, 192.168.1.1"
@@ -118,24 +118,14 @@ export no_proxy="Your_No_Proxy"
 
 ##### For using open-source llms
 
-Set up a [HuggingFace](https://huggingface.co/) account and generate a [user access token](https://huggingface.co/docs/transformers.js/en/guides/private#step-1-generating-a-user-access-token).
-
-Then set an environment variable with the token and another for a directory to download the models:
-
-```bash
+```
 export HUGGINGFACEHUB_API_TOKEN=<your-HF-token>
-export HF_CACHE_DIR=<directory-where-llms-are-downloaded> #  to avoid redownloading models
+export HF_CACHE_DIR=<directory-where-llms-are-downloaded> #so that no need to redownload every time
 ```
 
-##### [Optional] OPENAI_API_KEY to use OpenAI models or Intel® AI for Enterprise Inference
+##### [Optional] OPANAI_API_KEY to use OpenAI models
 
-To use OpenAI models, generate a key following these [instructions](https://platform.openai.com/api-keys).
-
-To use a remote server running Intel® AI for Enterprise Inference, contact the cloud service provider or owner of the on-prem machine for a key to access the desired model on the server.
-
-Then set the environment variable `OPENAI_API_KEY` with the key contents:
-
-```bash
+```
 export OPENAI_API_KEY=<your-openai-key>
 ```
 
@@ -143,18 +133,16 @@ export OPENAI_API_KEY=<your-openai-key>
 
 ##### Gaudi
 
-```bash
+```
 source $WORKDIR/GenAIExamples/AgentQnA/docker_compose/intel/hpu/gaudi/set_env.sh
 ```
 
 ##### Xeon
 
-```bash
+```
 source $WORKDIR/GenAIExamples/AgentQnA/docker_compose/intel/cpu/xeon/set_env.sh
 ```
 
-For running
-
 ### 2. Launch the multi-agent system. </br>
 
 We make it convenient to launch the whole system with docker compose, which includes microservices for LLM, agents, UI, retrieval tool, vector database, dataprep, and telemetry. There are 3 docker compose files, which make it easy for users to pick and choose. Users can choose a different retrieval tool other than the `DocIndexRetriever` example provided in our GenAIExamples repo. Users can choose not to launch the telemetry containers.
@@ -196,37 +184,14 @@ docker compose -f $WORKDIR/GenAIExamples/DocIndexRetriever/docker_compose/intel/
 
 #### Launch on Xeon
 
-On Xeon, OpenAI models and models deployed on a remote server are supported. Both methods require an API key.
+On Xeon, only OpenAI models are supported. The command below will launch the multi-agent system with the `DocIndexRetriever` as the retrieval tool for the Worker RAG agent.
 
 ```bash
 export OPENAI_API_KEY=<your-openai-key>
 cd $WORKDIR/GenAIExamples/AgentQnA/docker_compose/intel/cpu/xeon
-```
-
-##### OpenAI Models
-
-The command below will launch the multi-agent system with the `DocIndexRetriever` as the retrieval tool for the Worker RAG agent.
-
-```bash
 docker compose -f $WORKDIR/GenAIExamples/DocIndexRetriever/docker_compose/intel/cpu/xeon/compose.yaml -f compose_openai.yaml up -d
 ```
 
-##### Models on Remote Server
-
-When models are deployed on a remote server with Intel® AI for Enterprise Inference, a base URL and an API key are required to access them. To run the Agent microservice on Xeon while using models deployed on a remote server, add `compose_remote.yaml` to the `docker compose` command and set additional environment variables.
-
-###### Notes
-
-- `OPENAI_API_KEY` is already set in a previous step.
-- `model` is used to overwrite the value set for this environment variable in `set_env.sh`.
-- `LLM_ENDPOINT_URL` is the base URL given from the owner of the on-prem machine or cloud service provider. It will follow this format: "https://<DNS>". Here is an example: "https://api.inference.example.com".
-
-```bash
-export model=<name-of-model-card>
-export LLM_ENDPOINT_URL=<http-endpoint-of-remote-server>
-docker compose -f $WORKDIR/GenAIExamples/DocIndexRetriever/docker_compose/intel/cpu/xeon/compose.yaml -f compose_openai.yaml -f compose_remote.yaml up -d
-```
-
 ### 3. Ingest Data into the vector database
 
 The `run_ingest_data.sh` script will use an example jsonl file to ingest example documents into a vector database. Other ways to ingest data and other types of documents supported can be found in the OPEA dataprep microservice located in the opea-project/GenAIComps repo.
@@ -243,18 +208,12 @@ bash run_ingest_data.sh
 The UI microservice is launched in the previous step with the other microservices.
 To see the UI, open a web browser to `http://${ip_address}:5173` to access the UI. Note the `ip_address` here is the host IP of the UI microservice.
 
-1. Click on the arrow above `Get started`. Create an admin account with a name, email, and password.
-2. Add an OpenAI-compatible API endpoint. In the upper right, click on the circle button with the user's initial, go to `Admin Settings`->`Connections`. Under `Manage OpenAI API Connections`, click on the `+` to add a connection. Fill in these fields:
-
-- **URL**: `http://${ip_address}:9090/v1`, do not forget the `v1`
-- **Key**: any value
-- **Model IDs**: any name i.e. `opea-agent`, then press `+` to add it
-
-Click "Save".
+1. `create Admin Account` with a random value
+2. add opea agent endpoint `http://$ip_address:9090/v1` which is a openai compatible api
 
 ![opea-agent-setting](assets/img/opea-agent-setting.png)
 
-3. Test OPEA agent with UI. Return to `New Chat` and ensure the model (i.e. `opea-agent`) is selected near the upper left. Enter in any prompt to interact with the agent.
+3. test opea agent with ui
 
 ![opea-agent-test](assets/img/opea-agent-test.png)
 

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

@@ -1,18 +0,0 @@
-# Copyright (C) 2025 Intel Corporation
-# SPDX-License-Identifier: Apache-2.0
-
-services:
-  worker-rag-agent:
-    environment:
-      llm_endpoint_url: ${LLM_ENDPOINT_URL}
-      api_key: ${OPENAI_API_KEY}
-
-  worker-sql-agent:
-    environment:
-      llm_endpoint_url: ${LLM_ENDPOINT_URL}
-      api_key: ${OPENAI_API_KEY}
-
-  supervisor-react-agent:
-    environment:
-      llm_endpoint_url: ${LLM_ENDPOINT_URL}
-      api_key: ${OPENAI_API_KEY}

AgentQnA/tests/step1_build_images.sh

@@ -37,8 +37,8 @@ function build_agent_docker_image_gaudi_vllm() {
     get_genai_comps
 
     git clone https://github.com/HabanaAI/vllm-fork.git && cd vllm-fork
-    VLLM_FORK_VER=v0.6.6.post1+Gaudi-1.20.0
-    git checkout ${VLLM_FORK_VER} &> /dev/null && cd ../
+    VLLM_VER=v0.6.6.post1+Gaudi-1.20.0
+    git checkout ${VLLM_VER} &> /dev/null && cd ../
 
     echo "Build agent image with --no-cache..."
     service_list="agent agent-ui vllm-gaudi"

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

@@ -6,8 +6,8 @@
 
 # export host_ip=<your External Public IP>    # export host_ip=$(hostname -I | awk '{print $1}')
 
-export host_ip=${ip_address}
-export HUGGINGFACEHUB_API_TOKEN=${HUGGINGFACEHUB_API_TOKEN}
+export host_ip="192.165.1.21"
+export HUGGINGFACEHUB_API_TOKEN=${YOUR_HUGGINGFACEHUB_API_TOKEN}
 # <token>
 
 export LLM_MODEL_ID=Intel/neural-chat-7b-v3-3

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

@@ -6,8 +6,8 @@
 
 # export host_ip=<your External Public IP>    # export host_ip=$(hostname -I | awk '{print $1}')
 
-export host_ip=${ip_address}
-export external_host_ip=${ip_address}
+export host_ip=""
+export external_host_ip=""
 export HUGGINGFACEHUB_API_TOKEN=${HUGGINGFACEHUB_API_TOKEN}
 export HF_CACHE_DIR="./data"
 export LLM_MODEL_ID="Intel/neural-chat-7b-v3-3"

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

@@ -14,8 +14,7 @@ export MEGA_SERVICE_HOST_IP=${host_ip}
 export WHISPER_SERVER_HOST_IP=${host_ip}
 export SPEECHT5_SERVER_HOST_IP=${host_ip}
 export LLM_SERVER_HOST_IP=${host_ip}
-export GPT_SOVITS_SERVER_HOST_IP=${host_ip}
-export GPT_SOVITS_SERVER_PORT=9880
+
 export WHISPER_SERVER_PORT=7066
 export SPEECHT5_SERVER_PORT=7055
 export LLM_SERVER_PORT=3006

AudioQnA/tests/README.md

@@ -1,45 +0,0 @@
-# AudioQnA 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 Gaudi with TGI:
-
-```bash
-bash test_compose_tgi_on_gaudi.sh
-```
-
-On Intel Gaudi with vLLM:
-
-```bash
-bash test_compose_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
-```

AudioQnA/tests/test_compose_multilang_on_xeon.sh

@@ -40,8 +40,21 @@ function build_docker_images() {
 
 function start_services() {
     cd $WORKPATH/docker_compose/intel/cpu/xeon/
+    export HUGGINGFACEHUB_API_TOKEN=${HUGGINGFACEHUB_API_TOKEN}
+    export LLM_MODEL_ID=meta-llama/Meta-Llama-3-8B-Instruct
+
+    export MEGA_SERVICE_HOST_IP=${ip_address}
+    export WHISPER_SERVER_HOST_IP=${ip_address}
+    export GPT_SOVITS_SERVER_HOST_IP=${ip_address}
+    export LLM_SERVER_HOST_IP=${ip_address}
+
+    export WHISPER_SERVER_PORT=7066
+    export GPT_SOVITS_SERVER_PORT=9880
+    export LLM_SERVER_PORT=3006
+
+    export BACKEND_SERVICE_ENDPOINT=http://${ip_address}:3008/v1/audioqna
     export host_ip=${ip_address}
-    source set_env.sh
+
     # sed -i "s/backend_address/$ip_address/g" $WORKPATH/ui/svelte/.env
 
     # Start Docker Containers

AudioQnA/tests/test_compose_on_gaudi.sh

@@ -27,9 +27,9 @@ function build_docker_images() {
 
     git clone https://github.com/HabanaAI/vllm-fork.git
     cd vllm-fork/
-    VLLM_FORK_VER=v0.6.6.post1+Gaudi-1.20.0
-    echo "Check out vLLM tag ${VLLM_FORK_VER}"
-    git checkout ${VLLM_FORK_VER} &> /dev/null && cd ../
+    VLLM_VER=v0.6.6.post1+Gaudi-1.20.0
+    echo "Check out vLLM tag ${VLLM_VER}"
+    git checkout ${VLLM_VER} &> /dev/null && cd ../
 
     echo "Build all the images with --no-cache, check docker_image_build.log for details..."
     service_list="audioqna audioqna-ui whisper-gaudi speecht5-gaudi vllm-gaudi"
@@ -40,8 +40,24 @@ function build_docker_images() {
 
 function start_services() {
     cd $WORKPATH/docker_compose/intel/hpu/gaudi
+    export HUGGINGFACEHUB_API_TOKEN=${HUGGINGFACEHUB_API_TOKEN}
+    export LLM_MODEL_ID=meta-llama/Meta-Llama-3-8B-Instruct
+    export NUM_CARDS=1
+    export BLOCK_SIZE=128
+    export MAX_NUM_SEQS=256
+    export MAX_SEQ_LEN_TO_CAPTURE=2048
+
+    export MEGA_SERVICE_HOST_IP=${ip_address}
+    export WHISPER_SERVER_HOST_IP=${ip_address}
+    export SPEECHT5_SERVER_HOST_IP=${ip_address}
+    export LLM_SERVER_HOST_IP=${ip_address}
+
+    export WHISPER_SERVER_PORT=7066
+    export SPEECHT5_SERVER_PORT=7055
+    export LLM_SERVER_PORT=3006
+
+    export BACKEND_SERVICE_ENDPOINT=http://${ip_address}:3008/v1/audioqna
     export host_ip=${ip_address}
-    source set_env.sh
     # sed -i "s/backend_address/$ip_address/g" $WORKPATH/ui/svelte/.env
 
     # Start Docker Containers

AudioQnA/tests/test_compose_on_rocm.sh

@@ -35,7 +35,20 @@ function build_docker_images() {
 
 function start_services() {
     cd $WORKPATH/docker_compose/amd/gpu/rocm/
-    source set_env.sh
+    export HUGGINGFACEHUB_API_TOKEN=${HUGGINGFACEHUB_API_TOKEN}
+    export LLM_MODEL_ID=Intel/neural-chat-7b-v3-3
+
+    export MEGA_SERVICE_HOST_IP=${ip_address}
+    export WHISPER_SERVER_HOST_IP=${ip_address}
+    export SPEECHT5_SERVER_HOST_IP=${ip_address}
+    export LLM_SERVER_HOST_IP=${ip_address}
+
+    export WHISPER_SERVER_PORT=7066
+    export SPEECHT5_SERVER_PORT=7055
+    export LLM_SERVER_PORT=3006
+
+    export BACKEND_SERVICE_ENDPOINT=http://${ip_address}:3008/v1/audioqna
+
     # Start Docker Containers
     docker compose up -d > ${LOG_PATH}/start_services_with_compose.log
     n=0

AudioQnA/tests/test_compose_on_xeon.sh

@@ -40,8 +40,21 @@ function build_docker_images() {
 
 function start_services() {
     cd $WORKPATH/docker_compose/intel/cpu/xeon/
+    export HUGGINGFACEHUB_API_TOKEN=${HUGGINGFACEHUB_API_TOKEN}
+    export LLM_MODEL_ID=meta-llama/Meta-Llama-3-8B-Instruct
+
+    export MEGA_SERVICE_HOST_IP=${ip_address}
+    export WHISPER_SERVER_HOST_IP=${ip_address}
+    export SPEECHT5_SERVER_HOST_IP=${ip_address}
+    export LLM_SERVER_HOST_IP=${ip_address}
+
+    export WHISPER_SERVER_PORT=7066
+    export SPEECHT5_SERVER_PORT=7055
+    export LLM_SERVER_PORT=3006
+
+    export BACKEND_SERVICE_ENDPOINT=http://${ip_address}:3008/v1/audioqna
     export host_ip=${ip_address}
-    source set_env.sh
+
     # sed -i "s/backend_address/$ip_address/g" $WORKPATH/ui/svelte/.env
 
     # Start Docker Containers

AudioQnA/tests/test_compose_tgi_on_gaudi.sh

@@ -34,8 +34,21 @@ function build_docker_images() {
 
 function start_services() {
     cd $WORKPATH/docker_compose/intel/hpu/gaudi
+    export HUGGINGFACEHUB_API_TOKEN=${HUGGINGFACEHUB_API_TOKEN}
+    export LLM_MODEL_ID=meta-llama/Meta-Llama-3-8B-Instruct
+
+    export MEGA_SERVICE_HOST_IP=${ip_address}
+    export WHISPER_SERVER_HOST_IP=${ip_address}
+    export SPEECHT5_SERVER_HOST_IP=${ip_address}
+    export LLM_SERVER_HOST_IP=${ip_address}
+
+    export WHISPER_SERVER_PORT=7066
+    export SPEECHT5_SERVER_PORT=7055
+    export LLM_SERVER_PORT=3006
+
+    export BACKEND_SERVICE_ENDPOINT=http://${ip_address}:3008/v1/audioqna
     export host_ip=${ip_address}
-    source set_env.sh
+
     # Start Docker Containers
     docker compose -f compose_tgi.yaml up -d > ${LOG_PATH}/start_services_with_compose.log
     n=0

AudioQnA/tests/test_compose_tgi_on_xeon.sh

@@ -34,8 +34,21 @@ function build_docker_images() {
 
 function start_services() {
     cd $WORKPATH/docker_compose/intel/cpu/xeon/
+    export HUGGINGFACEHUB_API_TOKEN=${HUGGINGFACEHUB_API_TOKEN}
+    export LLM_MODEL_ID=meta-llama/Meta-Llama-3-8B-Instruct
+
+    export MEGA_SERVICE_HOST_IP=${ip_address}
+    export WHISPER_SERVER_HOST_IP=${ip_address}
+    export SPEECHT5_SERVER_HOST_IP=${ip_address}
+    export LLM_SERVER_HOST_IP=${ip_address}
+
+    export WHISPER_SERVER_PORT=7066
+    export SPEECHT5_SERVER_PORT=7055
+    export LLM_SERVER_PORT=3006
+
+    export BACKEND_SERVICE_ENDPOINT=http://${ip_address}:3008/v1/audioqna
     export host_ip=${ip_address}
-    source set_env.sh
+
     # Start Docker Containers
     docker compose -f compose_tgi.yaml up -d > ${LOG_PATH}/start_services_with_compose.log
     n=0

AudioQnA/tests/test_compose_vllm_on_rocm.sh

@@ -33,7 +33,27 @@ function build_docker_images() {
 
 function start_services() {
     cd $WORKPATH/docker_compose/amd/gpu/rocm/
-    source set_env_vllm.sh
+
+    export host_ip=${ip_address}
+    export external_host_ip=${ip_address}
+    export HUGGINGFACEHUB_API_TOKEN=${HUGGINGFACEHUB_API_TOKEN}
+    export HF_CACHE_DIR="./data"
+    export LLM_MODEL_ID="Intel/neural-chat-7b-v3-3"
+    export VLLM_SERVICE_PORT="8081"
+
+    export MEGA_SERVICE_HOST_IP=${host_ip}
+    export WHISPER_SERVER_HOST_IP=${host_ip}
+    export SPEECHT5_SERVER_HOST_IP=${host_ip}
+    export LLM_SERVER_HOST_IP=${host_ip}
+
+    export WHISPER_SERVER_PORT=7066
+    export SPEECHT5_SERVER_PORT=7055
+    export LLM_SERVER_PORT=${VLLM_SERVICE_PORT}
+    export BACKEND_SERVICE_PORT=3008
+    export FRONTEND_SERVICE_PORT=5173
+
+    export BACKEND_SERVICE_ENDPOINT=http://${external_host_ip}:${BACKEND_SERVICE_PORT}/v1/audioqna
+
     sed -i "s/backend_address/$ip_address/g" $WORKPATH/ui/svelte/.env
 
     # Start Docker Containers

ChatQnA/docker_compose/install_docker.sh

@@ -0,0 +1,35 @@
+#!/bin/bash
+
+# Copyright (C) 2024 Intel Corporation
+# SPDX-License-Identifier: Apache-2.0
+
+# Update the package index
+sudo apt-get -y update
+
+# Install prerequisites
+sudo apt-get -y install ca-certificates curl
+
+# Create the directory for the Docker GPG key
+sudo install -m 0755 -d /etc/apt/keyrings
+
+# Add Docker's official GPG key
+sudo curl -fsSL https://download.docker.com/linux/ubuntu/gpg -o /etc/apt/keyrings/docker.asc
+
+# Set permissions for the GPG key
+sudo chmod a+r /etc/apt/keyrings/docker.asc
+
+# Add Docker repository to the sources list
+echo "deb [arch=$(dpkg --print-architecture) signed-by=/etc/apt/keyrings/docker.asc] https://download.docker.com/linux/ubuntu \
+  $(. /etc/os-release && echo "$VERSION_CODENAME") stable" | sudo tee /etc/apt/sources.list.d/docker.list > /dev/null
+
+# Update the package index with Docker packages
+sudo apt-get -y update
+
+# Install Docker packages
+sudo apt-get -y install docker-ce docker-ce-cli containerd.io docker-buildx-plugin docker-compose-plugin
+
+# add existing user
+sudo usermod -aG docker $USER
+
+# Optional: Verify that Docker is installed correctly
+sudo docker --version

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

@@ -156,7 +156,6 @@ In the context of deploying a ChatQnA pipeline on an Intel® Xeon® platform, we
 | [compose_faqgen_tgi.yaml](./compose_faqgen_tgi.yaml)         | Enables FAQ generation using TGI as the LLM serving framework. For more details, refer to [README_faqgen.md](./README_faqgen.md).                                     |
 | [compose.telemetry.yaml](./compose.telemetry.yaml)           | Helper file for telemetry features for vllm. Can be used along with any compose files that serves vllm                                                                |
 | [compose_tgi.telemetry.yaml](./compose_tgi.telemetry.yaml)   | Helper file for telemetry features for tgi. Can be used along with any compose files that serves tgi                                                                  |
-| [compose_mariadb.yaml](./compose_mariadb.yaml)               | Uses MariaDB Server as the vector database. All other configurations remain the same as the default                                                                   |
 
 ## ChatQnA with Conversational UI (Optional)
 

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

@@ -1,259 +0,0 @@
-# Deploying ChatQnA with MariaDB Vector on Intel® Xeon® Processors
-
-This document outlines the deployment process for a ChatQnA application utilizing the [GenAIComps](https://github.com/opea-project/GenAIComps.git) microservice pipeline on Intel® Xeon® servers. The pipeline integrates **MariaDB Vector** as the vector database and includes microservices such as `embedding`, `retriever`, `rerank`, and `llm`.
-
----
-
-## Table of Contents
-
-1. [Build Docker Images](#build-docker-images)
-2. [Validate Microservices](#validate-microservices)
-3. [Launch the UI](#launch-the-ui)
-4. [Launch the Conversational UI (Optional)](#launch-the-conversational-ui-optional)
-
----
-
-## Build Docker Images
-
-First of all, you need to build Docker Images locally and install the python package of it.
-
-```bash
-git clone https://github.com/opea-project/GenAIComps.git
-cd GenAIComps
-```
-
-### 1. Build Retriever Image
-
-```bash
-docker build --no-cache -t opea/retriever:latest --build-arg https_proxy=$https_proxy --build-arg http_proxy=$http_proxy -f comps/retrievers/src/Dockerfile .
-```
-
-### 2. Build Dataprep Image
-
-```bash
-docker build --no-cache -t opea/dataprep:latest --build-arg https_proxy=$https_proxy --build-arg http_proxy=$http_proxy -f comps/dataprep/src/Dockerfile .
-cd ..
-```
-
-### 3. Build MegaService Docker Image
-
-To construct the Mega Service, we utilize the [GenAIComps](https://github.com/opea-project/GenAIComps.git) microservice pipeline within the `chatqna.py` Python script. Build MegaService Docker image via below command:
-
-```bash
-git clone https://github.com/opea-project/GenAIExamples.git
-cd GenAIExamples/ChatQnA/
-docker build --no-cache -t opea/chatqna:latest --build-arg https_proxy=$https_proxy --build-arg http_proxy=$http_proxy -f Dockerfile .
-cd ../..
-```
-
-### 4. Build UI Docker Image
-
-Build frontend Docker image via below command:
-
-```bash
-cd GenAIExamples/ChatQnA/ui
-docker build --no-cache -t opea/chatqna-ui:latest --build-arg https_proxy=$https_proxy --build-arg http_proxy=$http_proxy -f ./docker/Dockerfile .
-cd ../../..
-```
-
-### 5. Build Conversational React UI Docker Image (Optional)
-
-Build frontend Docker image that enables Conversational experience with ChatQnA megaservice via below command:
-
-**Export the value of the public IP address of your Xeon server to the `host_ip` environment variable**
-
-```bash
-cd GenAIExamples/ChatQnA/ui
-export BACKEND_SERVICE_ENDPOINT="http://${host_ip}:8912/v1/chatqna"
-export DATAPREP_SERVICE_ENDPOINT="http://${host_ip}:6043/v1/dataprep/ingest"
-docker build --no-cache -t opea/chatqna-conversation-ui:latest --build-arg https_proxy=$https_proxy --build-arg http_proxy=$http_proxy --build-arg BACKEND_SERVICE_ENDPOINT=$BACKEND_SERVICE_ENDPOINT --build-arg DATAPREP_SERVICE_ENDPOINT=$DATAPREP_SERVICE_ENDPOINT -f ./docker/Dockerfile.react .
-cd ../../..
-```
-
-### 6. Build Nginx Docker Image
-
-```bash
-cd GenAIComps
-docker build -t opea/nginx:latest --build-arg https_proxy=$https_proxy --build-arg http_proxy=$http_proxy -f comps/third_parties/nginx/src/Dockerfile .
-```
-
-Then run the command `docker images`, you will have the following 5 Docker Images:
-
-1. `opea/dataprep:latest`
-2. `opea/retriever:latest`
-3. `opea/chatqna:latest`
-4. `opea/chatqna-ui:latest`
-5. `opea/nginx:latest`
-
-## Start Microservices
-
-### Required Models
-
-By default, the embedding, reranking and LLM models are set to a default value as listed below:
-
-| Service   | Model                               |
-| --------- | ----------------------------------- |
-| Embedding | BAAI/bge-base-en-v1.5               |
-| Reranking | BAAI/bge-reranker-base              |
-| LLM       | meta-llama/Meta-Llama-3-8B-Instruct |
-
-Change the `xxx_MODEL_ID` below for your needs.
-
-### Setup Environment Variables
-
-Since the `compose.yaml` will consume some environment variables, you need to set them up in advance as below.
-
-**Export the value of the public IP address of your Xeon server to the `host_ip` environment variable**
-
-> Change the External_Public_IP below with the actual IPV4 value
-
-```bash
-export host_ip="External_Public_IP"
-```
-
-> Change to your actual Huggingface API Token value
-
-```bash
-export HUGGINGFACEHUB_API_TOKEN="Your_Huggingface_API_Token"
-```
-
-**Append the value of the public IP address to the no_proxy list if you are in a proxy environment**
-
-```bash
-export no_proxy=${your_no_proxy},chatqna-xeon-ui-server,chatqna-xeon-backend-server,dataprep-mariadb-vector,tei-embedding-service,retriever,tei-reranking-service,tgi-service,vllm-service
-```
-
-```bash
-export no_proxy=${your_no_proxy}
-export http_proxy=${your_http_proxy}
-export https_proxy=${your_http_proxy}
-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 MARIADB_DATABASE="vectordb"
-export MARIADB_USER="chatqna"
-export MARIADB_PASSWORD="password"
-```
-
-Note: Please replace with `host_ip` with you external IP address, do not use localhost.
-
-### Start all the services Docker Containers
-
-> Before running the docker compose command, you need to be in the folder that has the docker compose yaml file
-
-```bash
-cd GenAIExamples/ChatQnA/docker_compose/intel/cpu/xeon/
-docker compose -f compose_mariadb.yaml up -d
-```
-
-### Validate Microservices
-
-Follow the instructions to validate MicroServices.
-For details on how to verify the correctness of the response, refer to [how-to-validate_service](../../hpu/gaudi/how_to_validate_service.md).
-
-1. TEI Embedding Service
-
-   ```bash
-   curl ${host_ip}:6040/embed \
-       -X POST \
-       -d '{"inputs":"What is Deep Learning?"}' \
-       -H 'Content-Type: application/json'
-   ```
-
-2. Retriever Microservice
-
-   To consume the retriever microservice, you need to generate a mock embedding vector by Python script. The length of embedding vector
-   is determined by the embedding model.
-   Here we use the model `EMBEDDING_MODEL_ID="BAAI/bge-base-en-v1.5"`, which vector size is 768.
-
-   Check the vector dimension of your embedding model, set `your_embedding` dimension equals to it.
-
-   ```bash
-   export your_embedding=$(python3 -c "import random; embedding = [random.uniform(-1, 1) for _ in range(768)]; print(embedding)")
-   curl http://${host_ip}:6045/v1/retrieval \
-     -X POST \
-     -d '{"text":"What is the revenue of Nike in 2023?","embedding":"'"${your_embedding}"'"}' \
-     -H 'Content-Type: application/json'
-   ```
-
-3. TEI Reranking Service
-
-   ```bash
-   curl http://${host_ip}:6041/rerank \
-       -X POST \
-       -d '{"query":"What is Deep Learning?", "texts": ["Deep Learning is not...", "Deep learning is..."]}' \
-       -H 'Content-Type: application/json'
-   ```
-
-4. LLM Backend Service
-
-   In the first startup, this service will take more time to download, load and warm up the model. After it's finished, the service will be ready.
-
-   Try the command below to check whether the LLM service is ready.
-
-   ```bash
-   docker logs vllm-service 2>&1 | grep complete
-   ```
-
-   If the service is ready, you will get the response like below.
-
-   ```text
-   INFO: Application startup complete.
-   ```
-
-   Then try the `cURL` command below to validate vLLM service.
-
-   ```bash
-   curl http://${host_ip}:6042/v1/chat/completions \
-     -X POST \
-     -d '{"model": "meta-llama/Meta-Llama-3-8B-Instruct", "messages": [{"role": "user", "content": "What is Deep Learning?"}], "max_tokens":17}' \
-     -H 'Content-Type: application/json'
-   ```
-
-5. MegaService
-
-   ```bash
-   curl http://${host_ip}:8912/v1/chatqna -H "Content-Type: application/json" -d '{
-        "messages": "What is the revenue of Nike in 2023?"
-        }'
-   ```
-
-6. Dataprep Microservice（Optional）
-
-   If you want to update the default knowledge base, you can use the following commands:
-
-   Update Knowledge Base via Local File Upload:
-
-   ```bash
-   curl -X POST "http://${host_ip}:6043/v1/dataprep/ingest" \
-        -H "Content-Type: multipart/form-data" \
-        -F "files=@./your_file.pdf"
-   ```
-
-   This command updates a knowledge base by uploading a local file for processing. Update the file path according to your environment.
-
-   Add Knowledge Base via HTTP Links:
-
-   ```bash
-   curl -X POST "http://${host_ip}:6043/v1/dataprep/ingest" \
-        -H "Content-Type: multipart/form-data" \
-        -F 'link_list=["https://opea.dev"]'
-   ```
-
-## Launch the UI
-
-To access the frontend, open the following URL in your browser: http://{host_ip}:5173. By default, the UI runs on port 5173 internally. If you prefer to use a different host port to access the frontend, you can modify the port mapping in the `compose.yaml` file as shown below:
-
-```yaml
-  chatqna-xeon-ui-server:
-    image: opea/chatqna-ui:latest
-    ...
-    ports:
-      - "80:5173"
-```
-
-![project-screenshot](../../../../assets/img/chat_ui_init.png)
-
-Here is an example of running ChatQnA:
-
-![project-screenshot](../../../../assets/img/chat_ui_response.png)

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

@@ -1,185 +0,0 @@
-# Copyright (C) 2025 MariaDB Foundation
-# SPDX-License-Identifier: Apache-2.0
-
-services:
-  mariadb-server:
-    image: mariadb:latest
-    container_name: mariadb-server
-    ports:
-      - "3306:3306"
-    environment:
-      - MARIADB_DATABASE=${MARIADB_DATABASE}
-      - MARIADB_USER=${MARIADB_USER}
-      - MARIADB_PASSWORD=${MARIADB_PASSWORD}
-      - MARIADB_RANDOM_ROOT_PASSWORD=1
-    healthcheck:
-      test: ["CMD", "healthcheck.sh", "--connect", "--innodb_initialized"]
-      start_period: 10s
-      interval: 10s
-      timeout: 5s
-      retries: 3
-  dataprep-mariadb-vector:
-    image: ${REGISTRY:-opea}/dataprep:${TAG:-latest}
-    container_name: dataprep-mariadb-vector
-    depends_on:
-      mariadb-server:
-        condition: service_healthy
-      tei-embedding-service:
-        condition: service_started
-    ports:
-      - "6007:5000"
-    environment:
-      no_proxy: ${no_proxy}
-      http_proxy: ${http_proxy}
-      https_proxy: ${https_proxy}
-      DATAPREP_COMPONENT_NAME: "OPEA_DATAPREP_MARIADBVECTOR"
-      MARIADB_CONNECTION_URL: mariadb+mariadbconnector://${MARIADB_USER}:${MARIADB_PASSWORD}@mariadb-server:3306/${MARIADB_DATABASE}
-      TEI_ENDPOINT: http://tei-embedding-service:80
-      HUGGINGFACEHUB_API_TOKEN: ${HUGGINGFACEHUB_API_TOKEN}
-    healthcheck:
-      test: ["CMD-SHELL", "curl -f http://localhost:5000/v1/health_check || exit 1"]
-      interval: 10s
-      timeout: 5s
-      retries: 50
-    restart: unless-stopped
-  tei-embedding-service:
-    image: ghcr.io/huggingface/text-embeddings-inference:cpu-1.5
-    container_name: tei-embedding-server
-    ports:
-      - "6006:80"
-    volumes:
-      - "${MODEL_CACHE:-./data}:/data"
-    shm_size: 1g
-    environment:
-      no_proxy: ${no_proxy}
-      http_proxy: ${http_proxy}
-      https_proxy: ${https_proxy}
-    command: --model-id ${EMBEDDING_MODEL_ID} --auto-truncate
-  retriever:
-    image: ${REGISTRY:-opea}/retriever:${TAG:-latest}
-    container_name: retriever-mariadb-vector
-    depends_on:
-      mariadb-server:
-        condition: service_healthy
-    ports:
-      - "7000:7000"
-    ipc: host
-    environment:
-      no_proxy: ${no_proxy}
-      http_proxy: ${http_proxy}
-      https_proxy: ${https_proxy}
-      MARIADB_CONNECTION_URL: mariadb+mariadbconnector://${MARIADB_USER}:${MARIADB_PASSWORD}@mariadb-server:3306/${MARIADB_DATABASE}
-      HUGGINGFACEHUB_API_TOKEN: ${HUGGINGFACEHUB_API_TOKEN}
-      LOGFLAG: ${LOGFLAG}
-      RETRIEVER_COMPONENT_NAME: "OPEA_RETRIEVER_MARIADBVECTOR"
-    restart: unless-stopped
-  tei-reranking-service:
-    image: ghcr.io/huggingface/text-embeddings-inference:cpu-1.5
-    container_name: tei-reranking-server
-    ports:
-      - "8808:80"
-    volumes:
-      - "${MODEL_CACHE:-./data}:/data"
-    shm_size: 1g
-    environment:
-      no_proxy: ${no_proxy}
-      http_proxy: ${http_proxy}
-      https_proxy: ${https_proxy}
-      HUGGINGFACEHUB_API_TOKEN: ${HUGGINGFACEHUB_API_TOKEN}
-      HF_HUB_DISABLE_PROGRESS_BARS: 1
-      HF_HUB_ENABLE_HF_TRANSFER: 0
-    command: --model-id ${RERANK_MODEL_ID} --auto-truncate
-  vllm-service:
-    image: ${REGISTRY:-opea}/vllm:${TAG:-latest}
-    container_name: vllm-service
-    ports:
-      - "9009:80"
-    volumes:
-      - "${MODEL_CACHE:-./data}:/root/.cache/huggingface/hub"
-    shm_size: 128g
-    environment:
-      no_proxy: ${no_proxy}
-      http_proxy: ${http_proxy}
-      https_proxy: ${https_proxy}
-      HF_TOKEN: ${HUGGINGFACEHUB_API_TOKEN}
-      LLM_MODEL_ID: ${LLM_MODEL_ID}
-      VLLM_TORCH_PROFILER_DIR: "/mnt"
-      VLLM_CPU_KVCACHE_SPACE: 40
-    healthcheck:
-      test: ["CMD-SHELL", "curl -f http://$host_ip:9009/health || exit 1"]
-      interval: 10s
-      timeout: 10s
-      retries: 100
-    command: --model $LLM_MODEL_ID --host 0.0.0.0 --port 80
-  chatqna-xeon-backend-server:
-    image: ${REGISTRY:-opea}/chatqna:${TAG:-latest}
-    container_name: chatqna-xeon-backend-server
-    depends_on:
-      mariadb-server:
-        condition: service_healthy
-      dataprep-mariadb-vector:
-        condition: service_healthy
-      tei-embedding-service:
-        condition: service_started
-      retriever:
-        condition: service_started
-      tei-reranking-service:
-        condition: service_started
-      vllm-service:
-        condition: service_healthy
-    ports:
-      - "8888:8888"
-    environment:
-      - no_proxy=${no_proxy}
-      - https_proxy=${https_proxy}
-      - http_proxy=${http_proxy}
-      - MEGA_SERVICE_HOST_IP=chatqna-xeon-backend-server
-      - EMBEDDING_SERVER_HOST_IP=tei-embedding-service
-      - EMBEDDING_SERVER_PORT=${EMBEDDING_SERVER_PORT:-80}
-      - RETRIEVER_SERVICE_HOST_IP=retriever
-      - RERANK_SERVER_HOST_IP=tei-reranking-service
-      - RERANK_SERVER_PORT=${RERANK_SERVER_PORT:-80}
-      - LLM_SERVER_HOST_IP=vllm-service
-      - LLM_SERVER_PORT=80
-      - LLM_MODEL=${LLM_MODEL_ID}
-      - LOGFLAG=${LOGFLAG}
-    ipc: host
-    restart: always
-  chatqna-xeon-ui-server:
-    image: ${REGISTRY:-opea}/chatqna-ui:${TAG:-latest}
-    container_name: chatqna-xeon-ui-server
-    depends_on:
-      - chatqna-xeon-backend-server
-    ports:
-      - "5173:5173"
-    environment:
-      - no_proxy=${no_proxy}
-      - https_proxy=${https_proxy}
-      - http_proxy=${http_proxy}
-    ipc: host
-    restart: always
-  chatqna-xeon-nginx-server:
-    image: ${REGISTRY:-opea}/nginx:${TAG:-latest}
-    container_name: chatqna-xeon-nginx-server
-    depends_on:
-      - chatqna-xeon-backend-server
-      - chatqna-xeon-ui-server
-    ports:
-      - "${NGINX_PORT:-80}:80"
-    environment:
-      - no_proxy=${no_proxy}
-      - https_proxy=${https_proxy}
-      - http_proxy=${http_proxy}
-      - FRONTEND_SERVICE_IP=chatqna-xeon-ui-server
-      - FRONTEND_SERVICE_PORT=5173
-      - BACKEND_SERVICE_NAME=chatqna
-      - BACKEND_SERVICE_IP=chatqna-xeon-backend-server
-      - BACKEND_SERVICE_PORT=8888
-      - DATAPREP_SERVICE_IP=dataprep-mariadb-vector
-      - DATAPREP_SERVICE_PORT=5000
-    ipc: host
-    restart: always
-
-networks:
-  default:
-    driver: bridge

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

@@ -1,25 +0,0 @@
-#!/usr/bin/env bash
-
-# Copyright (C) 2025 MariaDB Foundation
-# SPDX-License-Identifier: Apache-2.0
-
-pushd "../../../../../" > /dev/null
-source .set_env.sh
-popd > /dev/null
-
-if [ -z "${HUGGINGFACEHUB_API_TOKEN}" ]; then
-    echo "Error: HUGGINGFACEHUB_API_TOKEN is not set. Please set HUGGINGFACEHUB_API_TOKEN."
-fi
-
-export host_ip=$(hostname -I | awk '{print $1}')
-export MARIADB_DATABASE="vectordb"
-export MARIADB_USER="chatqna"
-export MARIADB_PASSWORD="password"
-export HUGGINGFACEHUB_API_TOKEN=${HUGGINGFACEHUB_API_TOKEN}
-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 LOGFLAG=""
-export no_proxy="$no_proxy,chatqna-xeon-ui-server,chatqna-xeon-backend-server,dataprep-redis-service,tei-embedding-service,retriever,tei-reranking-service,tgi-service,vllm-service,jaeger,prometheus,grafana,node-exporter"
-export LLM_SERVER_PORT=9000
-export NGINX_PORT=80

ChatQnA/tests/test_compose_faqgen_on_gaudi.sh

@@ -24,8 +24,8 @@ function build_docker_images() {
     docker build --no-cache -t ${REGISTRY}/comps-base:${TAG} --build-arg https_proxy=$https_proxy --build-arg http_proxy=$http_proxy -f Dockerfile .
     popd && sleep 1s
     git clone https://github.com/HabanaAI/vllm-fork.git && cd vllm-fork
-    VLLM_FORK_VER=v0.6.6.post1+Gaudi-1.20.0
-    git checkout ${VLLM_FORK_VER} &> /dev/null && cd ../
+    VLLM_VER=v0.6.6.post1+Gaudi-1.20.0
+    git checkout ${VLLM_VER} &> /dev/null && cd ../
 
     echo "Build all the images with --no-cache, check docker_image_build.log for details..."
     service_list="chatqna chatqna-ui dataprep retriever llm-faqgen vllm-gaudi nginx"

ChatQnA/tests/test_compose_guardrails_on_gaudi.sh

@@ -24,8 +24,8 @@ function build_docker_images() {
     docker build --no-cache -t ${REGISTRY}/comps-base:${TAG} --build-arg https_proxy=$https_proxy --build-arg http_proxy=$http_proxy -f Dockerfile .
     popd && sleep 1s
     git clone https://github.com/HabanaAI/vllm-fork.git && cd vllm-fork
-    VLLM_FORK_VER=v0.6.6.post1+Gaudi-1.20.0
-    git checkout ${VLLM_FORK_VER} &> /dev/null && cd ../
+    VLLM_VER=v0.6.6.post1+Gaudi-1.20.0
+    git checkout ${VLLM_VER} &> /dev/null && cd ../
 
     echo "Build all the images with --no-cache, check docker_image_build.log for details..."
     service_list="chatqna chatqna-ui dataprep retriever vllm-gaudi guardrails nginx"

ChatQnA/tests/test_compose_mariadb_on_xeon.sh

@@ -1,176 +0,0 @@
-#!/bin/bash
-# Copyright (C) 2025 MariaDB Foundation
-# 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}
-export MODEL_CACHE=${model_cache:-"./data"}
-
-WORKPATH=$(dirname "$PWD")
-LOG_PATH="$WORKPATH/tests"
-ip_address=$(hostname -I | awk '{print $1}')
-
-function build_docker_images() {
-    opea_branch=${opea_branch:-"main"}
-    cd $WORKPATH/docker_image_build
-    git clone --depth 1 --branch ${opea_branch} https://github.com/opea-project/GenAIComps.git
-    pushd GenAIComps
-    echo "GenAIComps test commit is $(git rev-parse HEAD)"
-    docker build --no-cache -t ${REGISTRY}/comps-base:${TAG} --build-arg https_proxy=$https_proxy --build-arg http_proxy=$http_proxy -f Dockerfile .
-    popd && sleep 1s
-    git clone https://github.com/vllm-project/vllm.git && cd vllm
-    VLLM_VER="v0.8.3"
-    echo "Check out vLLM tag ${VLLM_VER}"
-    git checkout ${VLLM_VER} &> /dev/null
-    # make sure NOT change the pwd
-    cd ../
-
-    echo "Build all the images with --no-cache, check docker_image_build.log for details..."
-    service_list="chatqna chatqna-ui dataprep retriever vllm nginx"
-    docker compose -f build.yaml build ${service_list} --no-cache > ${LOG_PATH}/docker_image_build.log
-
-    docker images && sleep 1s
-}
-
-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}
-
-    # Start Docker Containers
-    docker compose -f compose_mariadb.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
-        if grep -q complete ${LOG_PATH}/vllm_service_start.log; then
-            break
-        fi
-        sleep 5s
-        n=$((n+1))
-    done
-}
-
-function validate_service() {
-    local URL="$1"
-    local EXPECTED_RESULT="$2"
-    local SERVICE_NAME="$3"
-    local DOCKER_NAME="$4"
-    local INPUT_DATA="$5"
-
-    local HTTP_STATUS=$(curl -s -o /dev/null -w "%{http_code}" -X POST -d "$INPUT_DATA" -H 'Content-Type: application/json' "$URL")
-    if [ "$HTTP_STATUS" -eq 200 ]; then
-        echo "[ $SERVICE_NAME ] HTTP status is 200. Checking content..."
-
-        local CONTENT=$(curl -s -X POST -d "$INPUT_DATA" -H 'Content-Type: application/json' "$URL" | tee ${LOG_PATH}/${SERVICE_NAME}.log)
-
-        if echo "$CONTENT" | grep -q "$EXPECTED_RESULT"; then
-            echo "[ $SERVICE_NAME ] Content is as expected."
-        else
-            echo "[ $SERVICE_NAME ] Content does not match the expected result: $CONTENT"
-            docker logs ${DOCKER_NAME} >> ${LOG_PATH}/${SERVICE_NAME}.log
-            exit 1
-        fi
-    else
-        echo "[ $SERVICE_NAME ] HTTP status is not 200. Received status was $HTTP_STATUS"
-        docker logs ${DOCKER_NAME} >> ${LOG_PATH}/${SERVICE_NAME}.log
-        exit 1
-    fi
-    sleep 1s
-}
-
-function validate_microservices() {
-    # Check if the microservices are running correctly.
-    sleep 3m
-
-    # tei for embedding service
-    validate_service \
-        "${ip_address}:6006/embed" \
-        "\[\[" \
-        "tei-embedding" \
-        "tei-embedding-server" \
-        '{"inputs":"What is Deep Learning?"}'
-
-    # retrieval microservice
-    test_embedding=$(python3 -c "import random; embedding = [random.uniform(-1, 1) for _ in range(768)]; print(embedding)")
-    validate_service \
-        "${ip_address}:7000/v1/retrieval" \
-        " " \
-        "retrieval" \
-        "retriever-mariadb-vector" \
-        "{\"text\":\"What is the revenue of Nike in 2023?\",\"embedding\":${test_embedding}}"
-
-    # tei for rerank microservice
-    validate_service \
-        "${ip_address}:8808/rerank" \
-        '{"index":1,"score":' \
-        "tei-rerank" \
-        "tei-reranking-server" \
-        '{"query":"What is Deep Learning?", "texts": ["Deep Learning is not...", "Deep learning is..."]}'
-
-    # vllm for llm service
-    validate_service \
-        "${ip_address}:9009/v1/chat/completions" \
-        "content" \
-        "vllm-llm" \
-        "vllm-service" \
-        '{"model": "meta-llama/Meta-Llama-3-8B-Instruct", "messages": [{"role": "user", "content": "What is Deep Learning?"}], "max_tokens": 17}'
-}
-
-function validate_megaservice() {
-    # Curl the Mega Service
-    validate_service \
-        "${ip_address}:8888/v1/chatqna" \
-        "Nike" \
-        "mega-chatqna" \
-        "chatqna-xeon-backend-server" \
-        '{"messages": "What is the revenue of Nike in 2023?"}'
-
-}
-
-function stop_docker() {
-    cd $WORKPATH/docker_compose/intel/cpu/xeon
-    docker compose down
-}
-
-function main() {
-
-    echo "::group::stop_docker"
-    stop_docker
-    echo "::endgroup::"
-
-    echo "::group::build_docker_images"
-    if [[ "$IMAGE_REPO" == "opea" ]]; then build_docker_images; fi
-    echo "::endgroup::"
-
-    echo "::group::start_services"
-    start_services
-    echo "::endgroup::"
-
-    echo "::group::validate_microservices"
-    validate_microservices
-    echo "::endgroup::"
-
-    echo "::group::validate_megaservice"
-    validate_megaservice
-    echo "::endgroup::"
-
-    echo "::group::stop_docker"
-    stop_docker
-    echo "::endgroup::"
-
-    docker system prune -f
-
-}
-
-main

ChatQnA/tests/test_compose_on_gaudi.sh

@@ -24,8 +24,8 @@ function build_docker_images() {
     docker build --no-cache -t ${REGISTRY}/comps-base:${TAG} --build-arg https_proxy=$https_proxy --build-arg http_proxy=$http_proxy -f Dockerfile .
     popd && sleep 1s
     git clone https://github.com/HabanaAI/vllm-fork.git && cd vllm-fork
-    VLLM_FORK_VER=v0.6.6.post1+Gaudi-1.20.0
-    git checkout ${VLLM_FORK_VER} &> /dev/null && cd ../
+    VLLM_VER=v0.6.6.post1+Gaudi-1.20.0
+    git checkout ${VLLM_VER} &> /dev/null && cd ../
 
     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"

ChatQnA/tests/test_compose_without_rerank_on_gaudi.sh

@@ -24,8 +24,8 @@ function build_docker_images() {
     docker build --no-cache -t ${REGISTRY}/comps-base:${TAG} --build-arg https_proxy=$https_proxy --build-arg http_proxy=$http_proxy -f Dockerfile .
     popd && sleep 1s
     git clone https://github.com/HabanaAI/vllm-fork.git && cd vllm-fork
-    VLLM_FORK_VER=v0.6.6.post1+Gaudi-1.20.0
-    git checkout ${VLLM_FORK_VER} &> /dev/null && cd ../
+    VLLM_VER=v0.6.6.post1+Gaudi-1.20.0
+    git checkout ${VLLM_VER} &> /dev/null && cd ../
 
     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"

CodeGen/tests/test_compose_on_gaudi.sh

@@ -43,9 +43,9 @@ function build_docker_images() {
 
     # Download Gaudi vllm of latest tag
     git clone https://github.com/HabanaAI/vllm-fork.git && cd vllm-fork
-    VLLM_FORK_VER=v0.6.6.post1+Gaudi-1.20.0
-    echo "Check out vLLM tag ${VLLM_FORK_VER}"
-    git checkout ${VLLM_FORK_VER} &> /dev/null && cd ../
+    VLLM_VER=v0.6.6.post1+Gaudi-1.20.0
+    echo "Check out vLLM tag ${VLLM_VER}"
+    git checkout ${VLLM_VER} &> /dev/null && cd ../
 
     echo "Build all the images with --no-cache, check docker_image_build.log for details..."
     service_list="codegen codegen-gradio-ui llm-textgen vllm-gaudi dataprep retriever embedding"

CodeTrans/Dockerfile

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

CodeTrans/docker_image_build/build.yaml

@@ -5,8 +5,6 @@ services:
   codetrans:
     build:
       args:
-        IMAGE_REPO: ${REGISTRY:-opea}
-        BASE_TAG: ${TAG:-latest}
         http_proxy: ${http_proxy}
         https_proxy: ${https_proxy}
         no_proxy: ${no_proxy}
@@ -47,5 +45,4 @@ services:
     build:
       context: GenAIComps
       dockerfile: comps/third_parties/vllm/src/Dockerfile.amd_gpu
-    extends: codetrans
     image: ${REGISTRY:-opea}/vllm-rocm:${TAG:-latest}

CodeTrans/tests/test_compose_on_gaudi.sh

@@ -17,17 +17,22 @@ ip_address=$(hostname -I | awk '{print $1}')
 
 function build_docker_images() {
     opea_branch=${opea_branch:-"main"}
+    # If the opea_branch isn't main, replace the git clone branch in Dockerfile.
+    if [[ "${opea_branch}" != "main" ]]; then
+        cd $WORKPATH
+        OLD_STRING="RUN git clone --depth 1 https://github.com/opea-project/GenAIComps.git"
+        NEW_STRING="RUN git clone --depth 1 --branch ${opea_branch} https://github.com/opea-project/GenAIComps.git"
+        find . -type f -name "Dockerfile*" | while read -r file; do
+            echo "Processing file: $file"
+            sed -i "s|$OLD_STRING|$NEW_STRING|g" "$file"
+        done
+    fi
 
     cd $WORKPATH/docker_image_build
     git clone --depth 1 --branch ${opea_branch} https://github.com/opea-project/GenAIComps.git
-    pushd GenAIComps
-    echo "GenAIComps test commit is $(git rev-parse HEAD)"
-    docker build --no-cache -t ${REGISTRY}/comps-base:${TAG} --build-arg https_proxy=$https_proxy --build-arg http_proxy=$http_proxy -f Dockerfile .
-    popd && sleep 1s
-
     git clone https://github.com/HabanaAI/vllm-fork.git && cd vllm-fork
-    VLLM_FORK_VER=v0.6.6.post1+Gaudi-1.20.0
-    git checkout ${VLLM_FORK_VER} &> /dev/null && cd ../
+    VLLM_VER=v0.6.6.post1+Gaudi-1.20.0
+    git checkout ${VLLM_VER} &> /dev/null && cd ../
 
     echo "Build all the images with --no-cache, check docker_image_build.log for details..."
     service_list="codetrans codetrans-ui llm-textgen vllm-gaudi nginx"
@@ -155,35 +160,17 @@ function stop_docker() {
 
 function main() {
 
-    echo "::group::stop_docker"
     stop_docker
-    echo "::endgroup::"
 
-    echo "::group::build_docker_images"
     if [[ "$IMAGE_REPO" == "opea" ]]; then build_docker_images; fi
-    echo "::endgroup::"
-
-    echo "::group::start_services"
     start_services
-    echo "::endgroup::"
 
-    echo "::group::validate_microservices"
     validate_microservices
-    echo "::endgroup::"
-
-    echo "::group::validate_megaservice"
     validate_megaservice
-    echo "::endgroup::"
-
-    echo "::group::validate_frontend"
     validate_frontend
-    echo "::endgroup::"
 
-    echo "::group::stop_docker"
     stop_docker
-    echo "::endgroup::"
-
-    docker system prune -f
+    echo y | docker system prune
 
 }
 

CodeTrans/tests/test_compose_on_rocm.sh

@@ -18,13 +18,19 @@ ip_address=$(hostname -I | awk '{print $1}')
 
 function build_docker_images() {
     opea_branch=${opea_branch:-"main"}
+    # If the opea_branch isn't main, replace the git clone branch in Dockerfile.
+    if [[ "${opea_branch}" != "main" ]]; then
+        cd $WORKPATH
+        OLD_STRING="RUN git clone --depth 1 https://github.com/opea-project/GenAIComps.git"
+        NEW_STRING="RUN git clone --depth 1 --branch ${opea_branch} https://github.com/opea-project/GenAIComps.git"
+        find . -type f -name "Dockerfile*" | while read -r file; do
+            echo "Processing file: $file"
+            sed -i "s|$OLD_STRING|$NEW_STRING|g" "$file"
+        done
+    fi
 
     cd $WORKPATH/docker_image_build
     git clone --depth 1 --branch ${opea_branch} https://github.com/opea-project/GenAIComps.git
-    pushd GenAIComps
-    echo "GenAIComps test commit is $(git rev-parse HEAD)"
-    docker build --no-cache -t ${REGISTRY}/comps-base:${TAG} --build-arg https_proxy=$https_proxy --build-arg http_proxy=$http_proxy -f Dockerfile .
-    popd && sleep 1s
 
     echo "Build all the images with --no-cache, check docker_image_build.log for details..."
     service_list="codetrans codetrans-ui llm-textgen nginx"
@@ -155,35 +161,17 @@ function stop_docker() {
 
 function main() {
 
-    echo "::group::stop_docker"
     stop_docker
-    echo "::endgroup::"
 
-    echo "::group::build_docker_images"
     if [[ "$IMAGE_REPO" == "opea" ]]; then build_docker_images; fi
-    echo "::endgroup::"
-
-    echo "::group::start_services"
     start_services
-    echo "::endgroup::"
 
-    echo "::group::validate_microservices"
     validate_microservices
-    echo "::endgroup::"
-
-    echo "::group::validate_megaservice"
     validate_megaservice
-    echo "::endgroup::"
-
-    echo "::group::validate_frontend"
     validate_frontend
-    echo "::endgroup::"
 
-    echo "::group::stop_docker"
     stop_docker
-    echo "::endgroup::"
-
-    docker system prune -f
+    echo y | docker system prune
 
 }
 

CodeTrans/tests/test_compose_on_xeon.sh

@@ -17,14 +17,19 @@ ip_address=$(hostname -I | awk '{print $1}')
 
 function build_docker_images() {
     opea_branch=${opea_branch:-"main"}
+    # If the opea_branch isn't main, replace the git clone branch in Dockerfile.
+    if [[ "${opea_branch}" != "main" ]]; then
+        cd $WORKPATH
+        OLD_STRING="RUN git clone --depth 1 https://github.com/opea-project/GenAIComps.git"
+        NEW_STRING="RUN git clone --depth 1 --branch ${opea_branch} https://github.com/opea-project/GenAIComps.git"
+        find . -type f -name "Dockerfile*" | while read -r file; do
+            echo "Processing file: $file"
+            sed -i "s|$OLD_STRING|$NEW_STRING|g" "$file"
+        done
+    fi
 
     cd $WORKPATH/docker_image_build
     git clone --depth 1 --branch ${opea_branch} https://github.com/opea-project/GenAIComps.git
-    pushd GenAIComps
-    echo "GenAIComps test commit is $(git rev-parse HEAD)"
-    docker build --no-cache -t ${REGISTRY}/comps-base:${TAG} --build-arg https_proxy=$https_proxy --build-arg http_proxy=$http_proxy -f Dockerfile .
-    popd && sleep 1s
-
     git clone https://github.com/vllm-project/vllm.git && cd vllm
     VLLM_VER="v0.8.3"
     echo "Check out vLLM tag ${VLLM_VER}"
@@ -158,35 +163,17 @@ function stop_docker() {
 
 function main() {
 
-    echo "::group::stop_docker"
     stop_docker
-    echo "::endgroup::"
 
-    echo "::group::build_docker_images"
     if [[ "$IMAGE_REPO" == "opea" ]]; then build_docker_images; fi
-    echo "::endgroup::"
-
-    echo "::group::start_services"
     start_services
-    echo "::endgroup::"
 
-    echo "::group::validate_microservices"
     validate_microservices
-    echo "::endgroup::"
-
-    echo "::group::validate_megaservice"
     validate_megaservice
-    echo "::endgroup::"
-
-    echo "::group::validate_frontend"
     validate_frontend
-    echo "::endgroup::"
 
-    echo "::group::stop_docker"
     stop_docker
-    echo "::endgroup::"
-
-    docker system prune -f
+    echo y | docker system prune
 
 }
 

CodeTrans/tests/test_compose_tgi_on_gaudi.sh

@@ -17,13 +17,19 @@ ip_address=$(hostname -I | awk '{print $1}')
 
 function build_docker_images() {
     opea_branch=${opea_branch:-"main"}
+    # If the opea_branch isn't main, replace the git clone branch in Dockerfile.
+    if [[ "${opea_branch}" != "main" ]]; then
+        cd $WORKPATH
+        OLD_STRING="RUN git clone --depth 1 https://github.com/opea-project/GenAIComps.git"
+        NEW_STRING="RUN git clone --depth 1 --branch ${opea_branch} https://github.com/opea-project/GenAIComps.git"
+        find . -type f -name "Dockerfile*" | while read -r file; do
+            echo "Processing file: $file"
+            sed -i "s|$OLD_STRING|$NEW_STRING|g" "$file"
+        done
+    fi
 
     cd $WORKPATH/docker_image_build
     git clone --depth 1 --branch ${opea_branch} https://github.com/opea-project/GenAIComps.git
-    pushd GenAIComps
-    echo "GenAIComps test commit is $(git rev-parse HEAD)"
-    docker build --no-cache -t ${REGISTRY}/comps-base:${TAG} --build-arg https_proxy=$https_proxy --build-arg http_proxy=$http_proxy -f Dockerfile .
-    popd && sleep 1s
 
     echo "Build all the images with --no-cache, check docker_image_build.log for details..."
     service_list="codetrans codetrans-ui llm-textgen nginx"
@@ -161,35 +167,17 @@ function stop_docker() {
 
 function main() {
 
-    echo "::group::stop_docker"
     stop_docker
-    echo "::endgroup::"
 
-    echo "::group::build_docker_images"
     if [[ "$IMAGE_REPO" == "opea" ]]; then build_docker_images; fi
-    echo "::endgroup::"
-
-    echo "::group::start_services"
     start_services
-    echo "::endgroup::"
 
-    echo "::group::validate_microservices"
     validate_microservices
-    echo "::endgroup::"
-
-    echo "::group::validate_megaservice"
     validate_megaservice
-    echo "::endgroup::"
-
-    echo "::group::validate_frontend"
     validate_frontend
-    echo "::endgroup::"
 
-    echo "::group::stop_docker"
     stop_docker
-    echo "::endgroup::"
-
-    docker system prune -f
+    echo y | docker system prune
 
 }
 

CodeTrans/tests/test_compose_tgi_on_xeon.sh

@@ -17,13 +17,19 @@ ip_address=$(hostname -I | awk '{print $1}')
 
 function build_docker_images() {
     opea_branch=${opea_branch:-"main"}
+    # If the opea_branch isn't main, replace the git clone branch in Dockerfile.
+    if [[ "${opea_branch}" != "main" ]]; then
+        cd $WORKPATH
+        OLD_STRING="RUN git clone --depth 1 https://github.com/opea-project/GenAIComps.git"
+        NEW_STRING="RUN git clone --depth 1 --branch ${opea_branch} https://github.com/opea-project/GenAIComps.git"
+        find . -type f -name "Dockerfile*" | while read -r file; do
+            echo "Processing file: $file"
+            sed -i "s|$OLD_STRING|$NEW_STRING|g" "$file"
+        done
+    fi
 
     cd $WORKPATH/docker_image_build
     git clone --depth 1 --branch ${opea_branch} https://github.com/opea-project/GenAIComps.git
-    pushd GenAIComps
-    echo "GenAIComps test commit is $(git rev-parse HEAD)"
-    docker build --no-cache -t ${REGISTRY}/comps-base:${TAG} --build-arg https_proxy=$https_proxy --build-arg http_proxy=$http_proxy -f Dockerfile .
-    popd && sleep 1s
 
     echo "Build all the images with --no-cache, check docker_image_build.log for details..."
     service_list="codetrans codetrans-ui llm-textgen nginx"
@@ -161,35 +167,17 @@ function stop_docker() {
 
 function main() {
 
-    echo "::group::stop_docker"
     stop_docker
-    echo "::endgroup::"
 
-    echo "::group::build_docker_images"
     if [[ "$IMAGE_REPO" == "opea" ]]; then build_docker_images; fi
-    echo "::endgroup::"
-
-    echo "::group::start_services"
     start_services
-    echo "::endgroup::"
 
-    echo "::group::validate_microservices"
     validate_microservices
-    echo "::endgroup::"
-
-    echo "::group::validate_megaservice"
     validate_megaservice
-    echo "::endgroup::"
-
-    echo "::group::validate_frontend"
     validate_frontend
-    echo "::endgroup::"
 
-    echo "::group::stop_docker"
     stop_docker
-    echo "::endgroup::"
-
-    docker system prune -f
+    echo y | docker system prune
 
 }
 

CodeTrans/tests/test_compose_vllm_on_rocm.sh

@@ -17,13 +17,19 @@ ip_address=$(hostname -I | awk '{print $1}')
 
 function build_docker_images() {
     opea_branch=${opea_branch:-"main"}
+    # If the opea_branch isn't main, replace the git clone branch in Dockerfile.
+    if [[ "${opea_branch}" != "main" ]]; then
+        cd $WORKPATH
+        OLD_STRING="RUN git clone --depth 1 https://github.com/opea-project/GenAIComps.git"
+        NEW_STRING="RUN git clone --depth 1 --branch ${opea_branch} https://github.com/opea-project/GenAIComps.git"
+        find . -type f -name "Dockerfile*" | while read -r file; do
+            echo "Processing file: $file"
+            sed -i "s|$OLD_STRING|$NEW_STRING|g" "$file"
+        done
+    fi
 
     cd $WORKPATH/docker_image_build
     git clone --depth 1 --branch ${opea_branch} https://github.com/opea-project/GenAIComps.git
-    pushd GenAIComps
-    echo "GenAIComps test commit is $(git rev-parse HEAD)"
-    docker build --no-cache -t ${REGISTRY}/comps-base:${TAG} --build-arg https_proxy=$https_proxy --build-arg http_proxy=$http_proxy -f Dockerfile .
-    popd && sleep 1s
 
     echo "Build all the images with --no-cache, check docker_image_build.log for details..."
     service_list="vllm-rocm llm-textgen codetrans codetrans-ui nginx"
@@ -154,35 +160,17 @@ function stop_docker() {
 
 function main() {
 
-    echo "::group::stop_docker"
     stop_docker
-    echo "::endgroup::"
 
-    echo "::group::build_docker_images"
     if [[ "$IMAGE_REPO" == "opea" ]]; then build_docker_images; fi
-    echo "::endgroup::"
-
-    echo "::group::start_services"
     start_services
-    echo "::endgroup::"
 
-    echo "::group::validate_microservices"
     validate_microservices
-    echo "::endgroup::"
-
-    echo "::group::validate_megaservice"
     validate_megaservice
-    echo "::endgroup::"
-
-    echo "::group::validate_frontend"
     validate_frontend
-    echo "::endgroup::"
 
-    echo "::group::stop_docker"
     stop_docker
-    echo "::endgroup::"
-
-    docker system prune -f
+    echo y | docker system prune
 
 }
 

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

@@ -3,13 +3,8 @@
 # Copyright (C) 2024 Intel Corporation
 # SPDX-License-Identifier: Apache-2.0
 
-pushd "../../" > /dev/null
-ls -l
-source .set_env.sh
-popd > /dev/null
-
-export host_ip=${ip_address}
-export DBQNA_HUGGINGFACEHUB_API_TOKEN=${HUGGINGFACEHUB_API_TOKEN}
+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"
@@ -19,4 +14,3 @@ 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"

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

@@ -2,19 +2,26 @@
 
 # Copyright (C) 2024 Intel Corporation
 # SPDX-License-Identifier: Apache-2.0
-
 pushd "../../../../../" > /dev/null
 source .set_env.sh
 popd > /dev/null
 
-export host_ip=${ip_address}
+#export host_ip=$(hostname -I | awk '{print $1}')
+
+if [ -z "${HUGGINGFACEHUB_API_TOKEN}" ]; then
+    echo "Error: HUGGINGFACEHUB_API_TOKEN is not set. Please set HUGGINGFACEHUB_API_TOKEN."
+fi
+
+if [ -z "${host_ip}" ]; then
+    echo "Error: host_ip is not set. Please set host_ip first."
+fi
 export no_proxy=$no_proxy,$host_ip,dbqna-xeon-react-ui-server,text2sql-service,tgi-service,postgres-container
 export HUGGINGFACEHUB_API_TOKEN=${HUGGINGFACEHUB_API_TOKEN}
-export HF_TOKEN=${HUGGINGFACEHUB_API_TOKEN}
+export TGI_PORT=8008
+export TGI_LLM_ENDPOINT="http://${host_ip}:${TGI_PORT}"
+export LLM_MODEL_ID="mistralai/Mistral-7B-Instruct-v0.3"
 export POSTGRES_USER=postgres
 export POSTGRES_PASSWORD=testpwd
 export POSTGRES_DB=chinook
-export TGI_PORT=8008
 export TEXT2SQL_PORT=9090
-export TGI_LLM_ENDPOINT="http://${host_ip}:${TGI_PORT}"
-export LLM_MODEL_ID="mistralai/Mistral-7B-Instruct-v0.3"
+"set_env.sh" 27L, 974B

DBQnA/docker_compose/set_env.sh

@@ -0,0 +1,11 @@
+#!/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 TGI_PORT=8008
+export TGI_LLM_ENDPOINT="http://${your_ip}:${TGI_PORT}"
+export LLM_MODEL_ID="mistralai/Mistral-7B-Instruct-v0.3"

DBQnA/docker_image_build/build.yaml

@@ -7,8 +7,6 @@ services:
       context: GenAIComps
       dockerfile: comps/text2sql/src/Dockerfile
       args:
-        IMAGE_REPO: ${REGISTRY:-opea}
-        BASE_TAG: ${TAG:-latest}
         http_proxy: ${http_proxy}
         https_proxy: ${https_proxy}
         no_proxy: ${no_proxy}
@@ -18,6 +16,8 @@ services:
       context: ../ui
       dockerfile: ./docker/Dockerfile.react
       args:
+        http_proxy: ${http_proxy}
+        https_proxy: ${https_proxy}
+        no_proxy: ${no_proxy}
         texttosql_url: ${build_texttosql_url}
-    extends: text2sql
     image: ${REGISTRY:-opea}/text2sql-react-ui:${TAG:-latest}

DBQnA/tests/README.md

@@ -1,21 +0,0 @@
-# DBQnA 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_on_xeon.sh
-```
-
-On AMD ROCm with TGI:
-
-```bash
-bash test_compose_on_rocm.sh
-```

DBQnA/tests/test_compose_on_rocm.sh

@@ -4,20 +4,24 @@
 
 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 $1}')
+tgi_port=8008
+tgi_volume=$WORKPATH/data
 
 export host_ip=${ip_address}
-source $WORKPATH/docker_compose/amd/gpu/rocm/set_env.sh
-
+export DBQNA_HUGGINGFACEHUB_API_TOKEN=${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}:${DBQNA_TEXT_TO_SQL_PORT}/v1"
 export MODEL_CACHE=${model_cache:-"/var/lib/GenAI/data"}
 
 function build_docker_images() {
@@ -32,7 +36,7 @@ function build_docker_images() {
     docker images && sleep 1s
 }
 
-function start_services() {
+function start_service() {
     cd "$WORKPATH"/docker_compose/amd/gpu/rocm
     # Start Docker Containers
     docker compose up -d > "${LOG_PATH}"/start_services_with_compose.log
@@ -53,8 +57,7 @@ function validate_microservice() {
         -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 echo "$result" | jq -e '.result.output' > /dev/null 2>&1; then
-    # if [[ $result == *"output"* ]]; then
+    if [[ $result == *"output"* ]]; then
         echo $result
         echo "Result correct."
     else
@@ -102,31 +105,16 @@ function stop_docker() {
 
 function main() {
 
-    echo "::group::stop_docker"
     stop_docker
-    echo "::endgroup::"
 
-    echo "::group::build_docker_images"
-    if [[ "$IMAGE_REPO" == "opea" ]]; then build_docker_images; fi
-    echo "::endgroup::"
-
-    echo "::group::start_services"
-    start_services
-    echo "::endgroup::"
-
-    echo "::group::validate_microservice"
+    build_docker_images
+    start_service
+    sleep 10s
     validate_microservice
-    echo "::endgroup::"
-
-    echo "::group::validate_frontend"
     validate_frontend
-    echo "::endgroup::"
 
-    echo "::group::stop_docker"
     stop_docker
-    echo "::endgroup::"
-
-    docker system prune -f
+    echo y | docker system prune
 
 }
 

DBQnA/tests/test_compose_on_xeon.sh

@@ -15,6 +15,7 @@ export MODEL_CACHE=${model_cache:-"./data"}
 WORKPATH=$(dirname "$PWD")
 LOG_PATH="$WORKPATH/tests"
 ip_address=$(hostname -I | awk '{print $1}')
+tgi_port=8008
 
 function build_docker_images() {
     cd $WORKPATH/docker_image_build
@@ -27,9 +28,16 @@ function build_docker_images() {
     docker images && sleep 1s
 }
 
-function start_services() {
+function start_service() {
     cd $WORKPATH/docker_compose/intel/cpu/xeon
-    source ./set_env.sh
+    export model="mistralai/Mistral-7B-Instruct-v0.3"
+    export LLM_MODEL_ID=${model}
+    export HUGGINGFACEHUB_API_TOKEN=${HUGGINGFACEHUB_API_TOKEN}
+    export POSTGRES_USER=postgres
+    export POSTGRES_PASSWORD=testpwd
+    export POSTGRES_DB=chinook
+    export TEXT2SQL_PORT=9090
+    export TGI_LLM_ENDPOINT="http://${ip_address}:${tgi_port}"
 
     # Start Docker Containers
     docker compose -f compose.yaml up -d > ${LOG_PATH}/start_services_with_compose.log
@@ -52,8 +60,7 @@ function validate_microservice() {
         -d '{"input_text": "Find the total number of Albums.","conn_str": {"user": "'${POSTGRES_USER}'","password": "'${POSTGRES_PASSWORD}'","host": "'${ip_address}'", "port": "5442", "database": "'${POSTGRES_DB}'" }}' \
         -H 'Content-Type: application/json')
 
-    if echo "$result" | jq -e '.result.output' > /dev/null 2>&1; then
-    # if [[ $result == *"output"* ]]; then
+    if [[ $result == *"output"* ]]; then
         echo $result
         echo "Result correct."
     else
@@ -101,31 +108,16 @@ function stop_docker() {
 
 function main() {
 
-    echo "::group::stop_docker"
     stop_docker
-    echo "::endgroup::"
 
-    echo "::group::build_docker_images"
-    if [[ "$IMAGE_REPO" == "opea" ]]; then build_docker_images; fi
-    echo "::endgroup::"
+    build_docker_images
+    start_service
 
-    echo "::group::start_services"
-    start_services
-    echo "::endgroup::"
-
-    echo "::group::validate_microservice"
     validate_microservice
-    echo "::endgroup::"
-
-    echo "::group::validate_frontend"
     validate_frontend
-    echo "::endgroup::"
 
-    echo "::group::stop_docker"
     stop_docker
-    echo "::endgroup::"
-
-    docker system prune -f
+    echo y | docker system prune
 
 }
 

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

@@ -5,25 +5,3 @@
 pushd "../../../../../" > /dev/null
 source .set_env.sh
 popd > /dev/null
-
-ip_address=$(hostname -I | awk '{print $1}')
-export EMBEDDING_MODEL_ID="BAAI/bge-base-en-v1.5"
-export RERANK_MODEL_ID="BAAI/bge-reranker-base"
-export TEI_EMBEDDING_ENDPOINT="http://${ip_address}:6006"
-export TEI_RERANKING_ENDPOINT="http://${ip_address}:8808"
-export TGI_LLM_ENDPOINT="http://${ip_address}:8008"
-export HUGGINGFACEHUB_API_TOKEN=${HUGGINGFACEHUB_API_TOKEN}
-export MEGA_SERVICE_HOST_IP=${ip_address}
-export EMBEDDING_SERVICE_HOST_IP=${ip_address}
-export RETRIEVER_SERVICE_HOST_IP=${ip_address}
-export RERANK_SERVICE_HOST_IP=${ip_address}
-export LLM_SERVICE_HOST_IP=${ip_address}
-export host_ip=${ip_address}
-export RERANK_TYPE="tei"
-export LOGFLAG=true
-
-export REDIS_URL="redis://${ip_address}:6379"
-export INDEX_NAME="rag-redis"
-
-export MILVUS_HOST=${ip_address}
-export DATAPREP_SERVICE_ENDPOINT="http://${host_ip}:6007/v1/dataprep/ingest"

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

@@ -5,26 +5,3 @@
 pushd "../../../../../" > /dev/null
 source .set_env.sh
 popd > /dev/null
-
-ip_address=$(hostname -I | awk '{print $1}')
-export EMBEDDING_MODEL_ID="BAAI/bge-base-en-v1.5"
-export RERANK_MODEL_ID="BAAI/bge-reranker-base"
-export TEI_EMBEDDING_ENDPOINT="http://${ip_address}:8090"
-export TEI_RERANKING_ENDPOINT="http://${ip_address}:8808"
-export HUGGINGFACEHUB_API_TOKEN=${HUGGINGFACEHUB_API_TOKEN}
-export MEGA_SERVICE_HOST_IP=${ip_address}
-export EMBEDDING_SERVICE_HOST_IP=${ip_address}
-export RETRIEVER_SERVICE_HOST_IP=${ip_address}
-export RERANK_SERVICE_HOST_IP=${ip_address}
-export host_ip=${ip_address}
-export RERANK_TYPE="tei"
-export LOGFLAG=true
-
-export REDIS_URL="redis://${ip_address}:6379"
-export INDEX_NAME="rag-redis"
-
-
-export TGI_LLM_ENDPOINT="http://${ip_address}:8008"
-export MILVUS_HOST=${ip_address}
-export LLM_SERVICE_HOST_IP=${ip_address}
-export DATAPREP_SERVICE_ENDPOINT="http://${host_ip}:6007/v1/dataprep/ingest"

DocIndexRetriever/tests/README.md

@@ -1,33 +0,0 @@
-# DocIndexRetriever 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_on_xeon.sh
-```
-
-On Intel Gaudi with TGI:
-
-```bash
-bash test_compose_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
-```

DocIndexRetriever/tests/test_compose_milvus_on_gaudi.sh

@@ -36,7 +36,22 @@ function build_docker_images() {
 function start_services() {
     echo "Starting Docker Services...."
     cd $WORKPATH/docker_compose/intel/hpu/gaudi
-    source ./set_env.sh
+    export EMBEDDING_MODEL_ID="BAAI/bge-base-en-v1.5"
+    export RERANK_MODEL_ID="BAAI/bge-reranker-base"
+    export TEI_EMBEDDING_ENDPOINT="http://${ip_address}:8090"
+    export TEI_RERANKING_ENDPOINT="http://${ip_address}:8808"
+    export TGI_LLM_ENDPOINT="http://${ip_address}:8008"
+    export MILVUS_HOST=${ip_address}
+    export HUGGINGFACEHUB_API_TOKEN=${HUGGINGFACEHUB_API_TOKEN}
+    export MEGA_SERVICE_HOST_IP=${ip_address}
+    export EMBEDDING_SERVICE_HOST_IP=${ip_address}
+    export RETRIEVER_SERVICE_HOST_IP=${ip_address}
+    export RERANK_SERVICE_HOST_IP=${ip_address}
+    export LLM_SERVICE_HOST_IP=${ip_address}
+    export host_ip=${ip_address}
+    export DATAPREP_SERVICE_ENDPOINT="http://${host_ip}:6007/v1/dataprep/ingest"
+    export RERANK_TYPE="tei"
+    export LOGFLAG=true
 
     # Start Docker Containers
     docker compose -f compose_milvus.yaml up -d

DocIndexRetriever/tests/test_compose_milvus_on_xeon.sh

@@ -35,7 +35,22 @@ function build_docker_images() {
 function start_services() {
     echo "Starting Docker Services...."
     cd $WORKPATH/docker_compose/intel/cpu/xeon
-    source ./set_env.sh
+    export EMBEDDING_MODEL_ID="BAAI/bge-base-en-v1.5"
+    export RERANK_MODEL_ID="BAAI/bge-reranker-base"
+    export TEI_EMBEDDING_ENDPOINT="http://${ip_address}:6006"
+    export TEI_RERANKING_ENDPOINT="http://${ip_address}:8808"
+    export TGI_LLM_ENDPOINT="http://${ip_address}:8008"
+    export MILVUS_HOST=${ip_address}
+    export HUGGINGFACEHUB_API_TOKEN=${HUGGINGFACEHUB_API_TOKEN}
+    export MEGA_SERVICE_HOST_IP=${ip_address}
+    export EMBEDDING_SERVICE_HOST_IP=${ip_address}
+    export RETRIEVER_SERVICE_HOST_IP=${ip_address}
+    export RERANK_SERVICE_HOST_IP=${ip_address}
+    export LLM_SERVICE_HOST_IP=${ip_address}
+    export host_ip=${ip_address}
+    export DATAPREP_SERVICE_ENDPOINT="http://${host_ip}:6007/v1/dataprep/ingest"
+    export RERANK_TYPE="tei"
+    export LOGFLAG=true
 
     # Start Docker Containers
     docker compose -f compose_milvus.yaml up -d

DocIndexRetriever/tests/test_compose_on_gaudi.sh

@@ -34,7 +34,20 @@ function build_docker_images() {
 function start_services() {
     echo "Starting Docker Services...."
     cd $WORKPATH/docker_compose/intel/hpu/gaudi
-    source ./set_env.sh
+    export EMBEDDING_MODEL_ID="BAAI/bge-base-en-v1.5"
+    export RERANK_MODEL_ID="BAAI/bge-reranker-base"
+    export TEI_EMBEDDING_ENDPOINT="http://${ip_address}:8090"
+    export TEI_RERANKING_ENDPOINT="http://${ip_address}:8808"
+    export REDIS_URL="redis://${ip_address}:6379"
+    export INDEX_NAME="rag-redis"
+    export HUGGINGFACEHUB_API_TOKEN=${HUGGINGFACEHUB_API_TOKEN}
+    export MEGA_SERVICE_HOST_IP=${ip_address}
+    export EMBEDDING_SERVICE_HOST_IP=${ip_address}
+    export RETRIEVER_SERVICE_HOST_IP=${ip_address}
+    export RERANK_SERVICE_HOST_IP=${ip_address}
+    export host_ip=${ip_address}
+    export RERANK_TYPE="tei"
+    export LOGFLAG=true
 
     # Start Docker Containers
     docker compose up -d

DocIndexRetriever/tests/test_compose_on_xeon.sh

@@ -34,7 +34,22 @@ function build_docker_images() {
 function start_services() {
     echo "Starting Docker Services...."
     cd $WORKPATH/docker_compose/intel/cpu/xeon
-    source ./set_env.sh
+    export EMBEDDING_MODEL_ID="BAAI/bge-base-en-v1.5"
+    export RERANK_MODEL_ID="BAAI/bge-reranker-base"
+    export TEI_EMBEDDING_ENDPOINT="http://${ip_address}:6006"
+    export TEI_RERANKING_ENDPOINT="http://${ip_address}:8808"
+    export TGI_LLM_ENDPOINT="http://${ip_address}:8008"
+    export REDIS_URL="redis://${ip_address}:6379"
+    export INDEX_NAME="rag-redis"
+    export HUGGINGFACEHUB_API_TOKEN=${HUGGINGFACEHUB_API_TOKEN}
+    export MEGA_SERVICE_HOST_IP=${ip_address}
+    export EMBEDDING_SERVICE_HOST_IP=${ip_address}
+    export RETRIEVER_SERVICE_HOST_IP=${ip_address}
+    export RERANK_SERVICE_HOST_IP=${ip_address}
+    export LLM_SERVICE_HOST_IP=${ip_address}
+    export host_ip=${ip_address}
+    export RERANK_TYPE="tei"
+    export LOGFLAG=true
 
     # Start Docker Containers
     docker compose up -d

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

@@ -239,16 +239,13 @@ curl http://${HOST_IP}:${DOCSUM_BACKEND_SERVER_PORT}/v1/docsum \
    -F "language=en" \
 ```
 
-Note that the `-F "messages="` flag is required, even for file uploads. Multiple files can be uploaded in a single call with multiple `-F "files=@/path"` inputs.
-
 ### Query with audio and video
 
-> Audio and video can be passed as base64 strings or uploaded by providing a local file path.
+> Audio and Video file uploads are not supported in docsum with curl request, please use the Gradio-UI.
 
 Audio:
 
 ```bash
-# Send base64 string
 curl -X POST http://${HOST_IP}:${DOCSUM_BACKEND_SERVER_PORT}/v1/docsum \
    -H "Content-Type: application/json" \
    -d '{"type": "audio", "messages": "UklGRigAAABXQVZFZm10IBIAAAABAAEARKwAAIhYAQACABAAAABkYXRhAgAAAAEA"}'
@@ -260,21 +257,11 @@ curl http://${HOST_IP}:${DOCSUM_BACKEND_SERVER_PORT}/v1/docsum \
    -F "max_tokens=32" \
    -F "language=en" \
    -F "stream=True"
-
-# Upload file
-curl http://${HOST_IP}:${DOCSUM_BACKEND_SERVER_PORT}/v1/docsum \
-   -H "Content-Type: multipart/form-data" \
-   -F "type=audio" \
-   -F "messages=" \
-   -F "files=@/path to your file (.mp3, .wav)" \
-   -F "max_tokens=32" \
-   -F "language=en"
 ```
 
 Video:
 
 ```bash
-# Send base64 string
 curl -X POST http://${HOST_IP}:${DOCSUM_BACKEND_SERVER_PORT}/v1/docsum \
    -H "Content-Type: application/json" \
    -d '{"type": "video", "messages": "convert your video to base64 data type"}'
@@ -286,15 +273,6 @@ curl http://${HOST_IP}:${DOCSUM_BACKEND_SERVER_PORT}/v1/docsum \
    -F "max_tokens=32" \
    -F "language=en" \
    -F "stream=True"
-
-# Upload file
-curl http://${HOST_IP}:${DOCSUM_BACKEND_SERVER_PORT}/v1/docsum \
-   -H "Content-Type: multipart/form-data" \
-   -F "type=video" \
-   -F "messages=" \
-   -F "files=@/path to your file (.mp4)" \
-   -F "max_tokens=32" \
-   -F "language=en"
 ```
 
 ### Query with long context

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

@@ -156,19 +156,16 @@ curl http://${host_ip}:8888/v1/docsum \
    -F "messages=" \
    -F "files=@/path to your file (.txt, .docx, .pdf)" \
    -F "max_tokens=32" \
-   -F "language=en"
+   -F "language=en" \
 ```
 
-Note that the `-F "messages="` flag is required, even for file uploads. Multiple files can be uploaded in a single call with multiple `-F "files=@/path"` inputs.
-
 ### Query with audio and video
 
-> Audio and video can be passed as base64 strings or uploaded by providing a local file path.
+> Audio and Video file uploads are not supported in docsum with curl request, please use the Gradio-UI.
 
 Audio:
 
 ```bash
-# Send base64 string
 curl -X POST http://${host_ip}:8888/v1/docsum \
    -H "Content-Type: application/json" \
    -d '{"type": "audio", "messages": "UklGRigAAABXQVZFZm10IBIAAAABAAEARKwAAIhYAQACABAAAABkYXRhAgAAAAEA"}'
@@ -180,21 +177,11 @@ curl http://${host_ip}:8888/v1/docsum \
    -F "max_tokens=32" \
    -F "language=en" \
    -F "stream=True"
-
-# Upload file
-curl http://${host_ip}:8888/v1/docsum \
-   -H "Content-Type: multipart/form-data" \
-   -F "type=audio" \
-   -F "messages=" \
-   -F "files=@/path to your file (.mp3, .wav)" \
-   -F "max_tokens=32" \
-   -F "language=en"
 ```
 
 Video:
 
 ```bash
-# Send base64 string
 curl -X POST http://${host_ip}:8888/v1/docsum \
    -H "Content-Type: application/json" \
    -d '{"type": "video", "messages": "convert your video to base64 data type"}'
@@ -206,15 +193,6 @@ curl http://${host_ip}:8888/v1/docsum \
    -F "max_tokens=32" \
    -F "language=en" \
    -F "stream=True"
-
-# Upload file
-curl http://${host_ip}:8888/v1/docsum \
-   -H "Content-Type: multipart/form-data" \
-   -F "type=video" \
-   -F "messages=" \
-   -F "files=@/path to your file (.mp4)" \
-   -F "max_tokens=32" \
-   -F "language=en"
 ```
 
 ### Query with long context

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

@@ -161,16 +161,13 @@ curl http://${host_ip}:8888/v1/docsum \
    -F "language=en" \
 ```
 
-Note that the `-F "messages="` flag is required, even for file uploads. Multiple files can be uploaded in a single call with multiple `-F "files=@/path"` inputs.
-
 ### Query with audio and video
 
-> Audio and video can be passed as base64 strings or uploaded by providing a local file path.
+> Audio and Video file uploads are not supported in docsum with curl request, please use the Gradio-UI.
 
 Audio:
 
 ```bash
-# Send base64 string
 curl -X POST http://${host_ip}:8888/v1/docsum \
    -H "Content-Type: application/json" \
    -d '{"type": "audio", "messages": "UklGRigAAABXQVZFZm10IBIAAAABAAEARKwAAIhYAQACABAAAABkYXRhAgAAAAEA"}'
@@ -182,21 +179,11 @@ curl http://${host_ip}:8888/v1/docsum \
    -F "max_tokens=32" \
    -F "language=en" \
    -F "stream=True"
-
-# Upload file
-curl http://${host_ip}:8888/v1/docsum \
-   -H "Content-Type: multipart/form-data" \
-   -F "type=audio" \
-   -F "messages=" \
-   -F "files=@/path to your file (.mp3, .wav)" \
-   -F "max_tokens=32" \
-   -F "language=en"
 ```
 
 Video:
 
 ```bash
-# Send base64 string
 curl -X POST http://${host_ip}:8888/v1/docsum \
    -H "Content-Type: application/json" \
    -d '{"type": "video", "messages": "convert your video to base64 data type"}'
@@ -208,15 +195,6 @@ curl http://${host_ip}:8888/v1/docsum \
    -F "max_tokens=32" \
    -F "language=en" \
    -F "stream=True"
-
-# Upload file
-curl http://${host_ip}:8888/v1/docsum \
-   -H "Content-Type: multipart/form-data" \
-   -F "type=video" \
-   -F "messages=" \
-   -F "files=@/path to your file (.mp4)" \
-   -F "max_tokens=32" \
-   -F "language=en"
 ```
 
 ### Query with long context

DocSum/docsum.py

@@ -63,20 +63,6 @@ def read_pdf(file):
     return docs
 
 
-def encode_file_to_base64(file_path):
-    """Encode the content of a file to a base64 string.
-
-    Args:
-        file_path (str): The path to the file to be encoded.
-
-    Returns:
-        str: The base64 encoded string of the file content.
-    """
-    with open(file_path, "rb") as f:
-        base64_str = base64.b64encode(f.read()).decode("utf-8")
-    return base64_str
-
-
 def video2audio(
     video_base64: str,
 ) -> str:
@@ -177,6 +163,7 @@ class DocSumService:
 
     async def handle_request(self, request: Request, files: List[UploadFile] = File(default=None)):
         """Accept pure text, or files .txt/.pdf.docx, audio/video base64 string."""
+
         if "application/json" in request.headers.get("content-type"):
             data = await request.json()
             stream_opt = data.get("stream", True)
@@ -206,24 +193,25 @@ class DocSumService:
                     uid = str(uuid.uuid4())
                     file_path = f"/tmp/{uid}"
 
-                    import aiofiles
+                    if data_type is not None and data_type in ["audio", "video"]:
+                        raise ValueError(
+                            "Audio and Video file uploads are not supported in docsum with curl request, \
+                                please use the UI or pass base64 string of the content directly."
+                        )
 
-                    async with aiofiles.open(file_path, "wb") as f:
-                        await f.write(await file.read())
+                    else:
+                        import aiofiles
+
+                        async with aiofiles.open(file_path, "wb") as f:
+                            await f.write(await file.read())
 
-                    if data_type == "text":
                         docs = read_text_from_file(file, file_path)
-                    elif data_type in ["audio", "video"]:
-                        docs = encode_file_to_base64(file_path)
-                    else:
-                        raise ValueError(f"Data type not recognized: {data_type}")
+                        os.remove(file_path)
 
-                    os.remove(file_path)
-
-                    if isinstance(docs, list):
-                        file_summaries.extend(docs)
-                    else:
-                        file_summaries.append(docs)
+                        if isinstance(docs, list):
+                            file_summaries.extend(docs)
+                        else:
+                            file_summaries.append(docs)
 
             if file_summaries:
                 prompt = handle_message(chat_request.messages) + "\n".join(file_summaries)

DocSum/kubernetes/helm/README.md

@@ -147,7 +147,7 @@ nano ~/docsum-k8s-install/GenAIExamples/DocSum/kubernetes/helm/rocm-tgi-values.y
 #### If ROCm vLLM used
 ```bash
 cd ~/docsum-k8s-install/GenAIInfra/helm-charts
-scripts/update_dependency.sh
+./update_dependency.sh
 helm dependency update docsum
 helm upgrade --install docsum docsum \
     --set global.HUGGINGFACEHUB_API_TOKEN=${HFTOKEN} \
@@ -157,7 +157,7 @@ helm upgrade --install docsum docsum \
 #### If ROCm TGI used
 ```bash
 cd ~/docsum-k8s-install/GenAIInfra/helm-charts
-scripts/update_dependency.sh
+./update_dependency.sh
 helm dependency update docsum
 helm upgrade --install docsum docsum \
     --set global.HUGGINGFACEHUB_API_TOKEN=${HFTOKEN} \

DocSum/tests/test_compose_on_gaudi.sh

@@ -50,8 +50,8 @@ function build_docker_images() {
     popd && sleep 1s
 
     git clone https://github.com/HabanaAI/vllm-fork.git && cd vllm-fork
-    VLLM_FORK_VER=v0.6.6.post1+Gaudi-1.20.0
-    git checkout ${VLLM_FORK_VER} &> /dev/null && cd ../
+    VLLM_VER=v0.6.6.post1+Gaudi-1.20.0
+    git checkout ${VLLM_VER} &> /dev/null && cd ../
 
     echo "Build all the images with --no-cache, check docker_image_build.log for details..."
     service_list="docsum docsum-gradio-ui whisper llm-docsum vllm-gaudi"
@@ -237,20 +237,6 @@ function validate_megaservice_multimedia() {
         "language=en" \
         "stream=False"
 
-    echo ">>> Checking audio data in form format, upload file"
-    validate_service \
-        "${host_ip}:${BACKEND_SERVICE_PORT}/v1/docsum" \
-        "well" \
-        "docsum-gaudi-backend-server" \
-        "docsum-gaudi-backend-server" \
-        "media" "" \
-        "type=audio" \
-        "messages=" \
-        "files=@$ROOT_FOLDER/data/test.wav" \
-        "max_tokens=32" \
-        "language=en" \
-        "stream=False"
-
     echo ">>> Checking video data in json format"
     validate_service \
         "${host_ip}:${BACKEND_SERVICE_PORT}/v1/docsum" \
@@ -272,20 +258,6 @@ function validate_megaservice_multimedia() {
         "max_tokens=32" \
         "language=en" \
         "stream=False"
-
-    echo ">>> Checking video data in form format, upload file"
-    validate_service \
-        "${host_ip}:${BACKEND_SERVICE_PORT}/v1/docsum" \
-        "bye" \
-        "docsum-gaudi-backend-server" \
-        "docsum-gaudi-backend-server" \
-        "media" "" \
-        "type=video" \
-        "messages=" \
-        "files=@$ROOT_FOLDER/data/test.mp4" \
-        "max_tokens=32" \
-        "language=en" \
-        "stream=False"
 }
 
 function validate_megaservice_long_text() {

DocSum/tests/test_compose_on_xeon.sh

@@ -237,20 +237,6 @@ function validate_megaservice_multimedia() {
         "language=en" \
         "stream=False"
 
-    echo ">>> Checking audio data in form format, upload file"
-    validate_service \
-        "${host_ip}:${BACKEND_SERVICE_PORT}/v1/docsum" \
-        "well" \
-        "docsum-xeon-backend-server" \
-        "docsum-xeon-backend-server" \
-        "media" "" \
-        "type=audio" \
-        "messages=" \
-        "files=@$ROOT_FOLDER/data/test.wav" \
-        "max_tokens=32" \
-        "language=en" \
-        "stream=False"
-
     echo ">>> Checking video data in json format"
     validate_service \
         "${host_ip}:${BACKEND_SERVICE_PORT}/v1/docsum" \
@@ -272,20 +258,6 @@ function validate_megaservice_multimedia() {
         "max_tokens=32" \
         "language=en" \
         "stream=False"
-
-    echo ">>> Checking video data in form format, upload file"
-    validate_service \
-        "${host_ip}:${BACKEND_SERVICE_PORT}/v1/docsum" \
-        "bye" \
-        "docsum-xeon-backend-server" \
-        "docsum-xeon-backend-server" \
-        "media" "" \
-        "type=video" \
-        "messages=" \
-        "files=@$ROOT_FOLDER/data/test.mp4" \
-        "max_tokens=32" \
-        "language=en" \
-        "stream=False"
 }
 
 function validate_megaservice_long_text() {

DocSum/tests/test_compose_tgi_on_gaudi.sh

@@ -229,20 +229,6 @@ function validate_megaservice_multimedia() {
         "language=en" \
         "stream=False"
 
-    echo ">>> Checking audio data in form format, upload file"
-    validate_service \
-        "${host_ip}:${BACKEND_SERVICE_PORT}/v1/docsum" \
-        "well" \
-        "docsum-gaudi-backend-server" \
-        "docsum-gaudi-backend-server" \
-        "media" "" \
-        "type=audio" \
-        "messages=" \
-        "files=@$ROOT_FOLDER/data/test.wav" \
-        "max_tokens=32" \
-        "language=en" \
-        "stream=False"
-
     echo ">>> Checking video data in json format"
     validate_service \
         "${host_ip}:${BACKEND_SERVICE_PORT}/v1/docsum" \
@@ -264,20 +250,6 @@ function validate_megaservice_multimedia() {
         "max_tokens=32" \
         "language=en" \
         "stream=False"
-
-    echo ">>> Checking video data in form format, upload file"
-    validate_service \
-        "${host_ip}:${BACKEND_SERVICE_PORT}/v1/docsum" \
-        "bye" \
-        "docsum-gaudi-backend-server" \
-        "docsum-gaudi-backend-server" \
-        "media" "" \
-        "type=video" \
-        "messages=" \
-        "files=@$ROOT_FOLDER/data/test.mp4" \
-        "max_tokens=32" \
-        "language=en" \
-        "stream=False"
 }
 
 function validate_megaservice_long_text() {

DocSum/tests/test_compose_tgi_on_xeon.sh

@@ -229,20 +229,6 @@ function validate_megaservice_multimedia() {
         "language=en" \
         "stream=False"
 
-    echo ">>> Checking audio data in form format, upload file"
-    validate_service \
-        "${host_ip}:${BACKEND_SERVICE_PORT}/v1/docsum" \
-        "well" \
-        "docsum-xeon-backend-server" \
-        "docsum-xeon-backend-server" \
-        "media" "" \
-        "type=audio" \
-        "messages=" \
-        "files=@$ROOT_FOLDER/data/test.wav" \
-        "max_tokens=32" \
-        "language=en" \
-        "stream=False"
-
     echo ">>> Checking video data in json format"
     validate_service \
         "${host_ip}:${BACKEND_SERVICE_PORT}/v1/docsum" \
@@ -264,20 +250,6 @@ function validate_megaservice_multimedia() {
         "max_tokens=32" \
         "language=en" \
         "stream=False"
-
-    echo ">>> Checking video data in form format, upload file"
-    validate_service \
-        "${host_ip}:${BACKEND_SERVICE_PORT}/v1/docsum" \
-        "bye" \
-        "docsum-xeon-backend-server" \
-        "docsum-xeon-backend-server" \
-        "media" "" \
-        "type=video" \
-        "messages=" \
-        "files=@$ROOT_FOLDER/data/test.mp4" \
-        "max_tokens=32" \
-        "language=en" \
-        "stream=False"
 }
 
 function validate_megaservice_long_text() {

DocSum/ui/gradio/docsum_ui_gradio.py

@@ -22,12 +22,76 @@ logger = logging.getLogger(__name__)
 class DocSumUI:
     def __init__(self):
         """Initialize the DocSumUI class with accepted file types, headers, and backend service endpoint."""
-        self.ACCEPTED_TEXT_FILE_TYPES = [".pdf", ".doc", ".docx"]
-        self.ACCEPTED_AUDIO_FILE_TYPES = [".mp3", ".wav"]
-        self.ACCEPTED_VIDEO_FILE_TYPES = [".mp4"]
+        self.ACCEPTED_FILE_TYPES = ["pdf", "doc", "docx"]
         self.HEADERS = {"Content-Type": "application/json"}
         self.BACKEND_SERVICE_ENDPOINT = os.getenv("BACKEND_SERVICE_ENDPOINT", "http://localhost:8888/v1/docsum")
 
+    def encode_file_to_base64(self, file_path):
+        """Encode the content of a file to a base64 string.
+
+        Args:
+            file_path (str): The path to the file to be encoded.
+
+        Returns:
+            str: The base64 encoded string of the file content.
+        """
+        logger.info(">>> Encoding file to base64: %s", file_path)
+        with open(file_path, "rb") as f:
+            base64_str = base64.b64encode(f.read()).decode("utf-8")
+        return base64_str
+
+    def read_file(self, file):
+        """Read and process the content of a file.
+
+        Args:
+            file (file-like object): The file to be read.
+
+        Returns:
+            str: The content of the file or an error message if the file type is unsupported.
+        """
+        self.page_content = ""
+        self.pages = []
+
+        if file.name.endswith(".pdf"):
+            loader = PyPDFLoader(file)
+        elif file.name.endswith((".doc", ".docx")):
+            loader = Docx2txtLoader(file)
+        else:
+            msg = f"Unsupported file type '{file.name}'. Choose from {self.ACCEPTED_FILE_TYPES}"
+            logger.error(msg)
+            return msg
+
+        for page in loader.lazy_load():
+            self.page_content += page.page_content
+
+        return self.page_content
+
+    def read_audio_file(self, file):
+        """Read and process the content of an audio file.
+
+        Args:
+            file (file-like object): The audio file to be read.
+
+        Returns:
+            str: The base64 encoded content of the audio file.
+        """
+        logger.info(">>> Reading audio file: %s", file.name)
+        base64_str = self.encode_file_to_base64(file)
+        return base64_str
+
+    def read_video_file(self, file):
+        """Read and process the content of a video file.
+
+        Args:
+            file (file-like object): The video file to be read.
+
+        Returns:
+            str: The base64 encoded content of the video file.
+        """
+        logger.info(">>> Reading video file: %s", file.name)
+        base64_str = self.encode_file_to_base64(file)
+        return base64_str
+
     def is_valid_url(self, url):
         try:
             result = urlparse(url)
@@ -64,107 +128,78 @@ class DocSumUI:
 
         return self.page_content
 
-    def process_response(self, response):
-        if response.status_code == 200:
-            try:
-                # Check if the specific log path is in the response text
-                if "/logs/LLMChain/final_output" in response.text:
-                    # Extract the relevant part of the response
-                    temp = ast.literal_eval(
-                        [
-                            i.split("data: ")[1]
-                            for i in response.text.split("\n\n")
-                            if "/logs/LLMChain/final_output" in i
-                        ][0]
-                    )["ops"]
-
-                    # Find the final output value
-                    final_output = [i["value"] for i in temp if i["path"] == "/logs/LLMChain/final_output"][0]
-                    return final_output["text"]
-                else:
-                    # Perform string replacements to clean the response text
-                    cleaned_text = response.text
-                    replacements = [
-                        ("'\n\ndata: b'", ""),
-                        ("data: b' ", ""),
-                        ("</s>'\n\ndata: [DONE]\n\n", ""),
-                        ("\n\ndata: b", ""),
-                        ("'\n\n", ""),
-                        ("'\n", ""),
-                        ('''\'"''', ""),
-                    ]
-                    for old, new in replacements:
-                        cleaned_text = cleaned_text.replace(old, new)
-                    return cleaned_text
-            except (IndexError, KeyError, ValueError) as e:
-                # Handle potential errors during parsing
-                logger.error("Error parsing response: %s", e)
-                return response.text
-
-    def generate_summary(self, document, document_type="text"):
+    def generate_summary(self, doc_content, document_type="text"):
         """Generate a summary for the given document content.
 
         Args:
-            document (str): The content or path of the document.
+            doc_content (str): The content of the document.
             document_type (str): The type of the document (default is "text").
 
         Returns:
             str: The generated summary or an error message.
         """
+
         logger.info(">>> BACKEND_SERVICE_ENDPOINT - %s", self.BACKEND_SERVICE_ENDPOINT)
 
-        data = {"max_tokens": 256, "type": document_type, "messages": ""}
+        data = {"max_tokens": 256, "type": document_type, "messages": doc_content}
 
-        if os.path.exists(document):
-            file_header = "text/plain"
-            file_ext = os.path.splitext(document)[-1]
-            if file_ext == ".pdf":
-                file_header = "application/pdf"
-            elif file_ext in [".doc", ".docx"]:
-                file_header = "application/octet-stream"
-            elif file_ext in self.ACCEPTED_AUDIO_FILE_TYPES + self.ACCEPTED_VIDEO_FILE_TYPES:
-                file_header = f"{document_type}/{file_ext[-3:]}"
-            files = {"files": (os.path.basename(document), open(document, "rb"), file_header)}
-            try:
-                response = requests.post(
-                    url=self.BACKEND_SERVICE_ENDPOINT,
-                    headers={},
-                    files=files,
-                    data=data,
-                    proxies={"http_proxy": os.environ["http_proxy"], "https_proxy": os.environ["https_proxy"]},
-                )
+        try:
+            response = requests.post(
+                url=self.BACKEND_SERVICE_ENDPOINT,
+                headers=self.HEADERS,
+                data=json.dumps(data),
+                proxies={"http_proxy": os.environ["http_proxy"], "https_proxy": os.environ["https_proxy"]},
+            )
 
-                return self.process_response(response)
+            if response.status_code == 200:
+                try:
+                    # Check if the specific log path is in the response text
+                    if "/logs/LLMChain/final_output" in response.text:
+                        # Extract the relevant part of the response
+                        temp = ast.literal_eval(
+                            [
+                                i.split("data: ")[1]
+                                for i in response.text.split("\n\n")
+                                if "/logs/LLMChain/final_output" in i
+                            ][0]
+                        )["ops"]
 
-            except requests.exceptions.RequestException as e:
-                logger.error("Request exception: %s", e)
-                return str(e)
+                        # Find the final output value
+                        final_output = [i["value"] for i in temp if i["path"] == "/logs/LLMChain/final_output"][0]
+                        return final_output["text"]
+                    else:
+                        # Perform string replacements to clean the response text
+                        cleaned_text = response.text
+                        replacements = [
+                            ("'\n\ndata: b'", ""),
+                            ("data: b' ", ""),
+                            ("</s>'\n\ndata: [DONE]\n\n", ""),
+                            ("\n\ndata: b", ""),
+                            ("'\n\n", ""),
+                            ("'\n", ""),
+                            ('''\'"''', ""),
+                        ]
+                        for old, new in replacements:
+                            cleaned_text = cleaned_text.replace(old, new)
+                        return cleaned_text
+                except (IndexError, KeyError, ValueError) as e:
+                    # Handle potential errors during parsing
+                    logger.error("Error parsing response: %s", e)
+                    return response.text
 
-        else:
-            data["messages"] = document
-            try:
-                response = requests.post(
-                    url=self.BACKEND_SERVICE_ENDPOINT,
-                    headers=self.HEADERS,
-                    data=json.dumps(data),
-                    proxies={"http_proxy": os.environ["http_proxy"], "https_proxy": os.environ["https_proxy"]},
-                )
-
-                return self.process_response(response)
-
-            except requests.exceptions.RequestException as e:
-                logger.error("Request exception: %s", e)
-                return str(e)
+        except requests.exceptions.RequestException as e:
+            logger.error("Request exception: %s", e)
+            return str(e)
 
         return str(response.status_code)
 
-    def create_upload_ui(self, label, file_types, document_type="text"):
+    def create_upload_ui(self, label, file_types, process_function, document_type="text"):
         """Create a Gradio UI for file uploads.
 
         Args:
             label (str): The label for the upload button.
             file_types (list): The list of accepted file types.
-            document_type (str): The document type (text, audio, or video). Default is text.
+            process_function (function): The function to process the uploaded file.
 
         Returns:
             gr.Blocks: The Gradio Blocks object representing the upload UI.
@@ -179,7 +214,7 @@ class DocSumUI:
                         label="Text Summary", placeholder="Summarized text will be displayed here"
                     )
             upload_btn.upload(
-                lambda file: self.generate_summary(file, document_type=document_type),
+                lambda file: self.generate_summary(process_function(file), document_type=document_type),
                 upload_btn,
                 generated_text,
             )
@@ -228,21 +263,24 @@ class DocSumUI:
 
         # File Upload UI
         file_ui = self.create_upload_ui(
-            label=f"Please upload a document ({', '.join(self.ACCEPTED_TEXT_FILE_TYPES)})",
-            file_types=self.ACCEPTED_TEXT_FILE_TYPES,
+            label="Please upload a document (.pdf, .doc, .docx)",
+            file_types=[".pdf", ".doc", ".docx"],
+            process_function=self.read_file,
         )
 
         # Audio Upload UI
         audio_ui = self.create_upload_ui(
-            label=f"Please upload audio file ({', '.join(self.ACCEPTED_AUDIO_FILE_TYPES)})",
-            file_types=self.ACCEPTED_AUDIO_FILE_TYPES,
+            label="Please upload audio file (.wav, .mp3)",
+            file_types=[".wav", ".mp3"],
+            process_function=self.read_audio_file,
             document_type="audio",
         )
 
         # Video Upload UI
         video_ui = self.create_upload_ui(
-            label=f"Please upload video file ({', '.join(self.ACCEPTED_VIDEO_FILE_TYPES)})",
-            file_types=self.ACCEPTED_VIDEO_FILE_TYPES,
+            label="Please upload Video file (.mp4)",
+            file_types=[".mp4"],
+            process_function=self.read_video_file,
             document_type="video",
         )
 

FinanceAgent/tests/test_compose_on_gaudi.sh

@@ -59,9 +59,9 @@ function build_vllm_docker_image() {
         git clone https://github.com/HabanaAI/vllm-fork.git
     fi
     cd ./vllm-fork
-
-    VLLM_FORK_VER=v0.6.6.post1+Gaudi-1.20.0
-    git checkout ${VLLM_FORK_VER} &> /dev/null
+    # VLLM_VER=$(git describe --tags "$(git rev-list --tags --max-count=1)")
+    VLLM_VER=v0.6.6.post1+Gaudi-1.20.0
+    git checkout ${VLLM_VER} &> /dev/null
     docker build --no-cache -f Dockerfile.hpu -t $vllm_image --shm-size=128g . --build-arg https_proxy=$https_proxy --build-arg http_proxy=$http_proxy
     if [ $? -ne 0 ]; then
         echo "$vllm_image failed"

GraphRAG/README.md

@@ -18,7 +18,7 @@ Quick Start Deployment Steps:
 2. Run Docker Compose.
 3. Consume the GraphRAG Service.
 
-Note: If you do not have Docker installed you can [install Docker](https://docs.docker.com/engine/install/) first
+Note: If you do not have docker installed you can run this script to install docker : `bash docker_compose/install_docker.sh`
 
 ### Quick Start: 1.Setup Environment Variable
 

GraphRAG/docker_compose/install_docker.sh

@@ -0,0 +1,35 @@
+#!/usr/bin/env bash
+
+# Copyright (C) 2024 Intel Corporation
+# SPDX-License-Identifier: Apache-2.0
+
+# Update the package index
+sudo apt-get -y update
+
+# Install prerequisites
+sudo apt-get -y install ca-certificates curl --no-install-recommends --fix-missing
+
+# Create the directory for the Docker GPG key
+sudo install -m 0755 -d /etc/apt/keyrings
+
+# Add Docker's official GPG key
+sudo curl -fsSL https://download.docker.com/linux/ubuntu/gpg -o /etc/apt/keyrings/docker.asc
+
+# Set permissions for the GPG key
+sudo chmod a+r /etc/apt/keyrings/docker.asc
+
+# Add Docker repository to the sources list
+echo "deb [arch=$(dpkg --print-architecture) signed-by=/etc/apt/keyrings/docker.asc] https://download.docker.com/linux/ubuntu \
+  $(. /etc/os-release && echo "$VERSION_CODENAME") stable" | sudo tee /etc/apt/sources.list.d/docker.list > /dev/null
+
+# Update the package index with Docker packages
+sudo apt-get -y update
+
+# Install Docker packages
+sudo apt-get -y install docker-ce docker-ce-cli containerd.io docker-buildx-plugin docker-compose-plugin --no-install-recommends --fix-missing
+
+# add existing user
+sudo usermod -aG docker $USER
+
+# Optional: Verify that Docker is installed correctly
+sudo docker --version

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

@@ -10,9 +10,6 @@ pushd "../../../../../" > /dev/null
 source .set_env.sh
 popd > /dev/null
 
-host_ip=$(hostname -I | awk '{print $1}')
-export HUGGINGFACEHUB_API_TOKEN=${HUGGINGFACEHUB_API_TOKEN}
-export HF_TOKEN=${HUGGINGFACEHUB_API_TOKEN}
 export TEI_EMBEDDER_PORT=11633
 export LLM_ENDPOINT_PORT=11634
 export EMBEDDING_MODEL_ID="BAAI/bge-base-en-v1.5"
@@ -20,6 +17,7 @@ export OPENAI_EMBEDDING_MODEL="text-embedding-3-small"
 export LLM_MODEL_ID="meta-llama/Meta-Llama-3.1-8B-Instruct"
 export OPENAI_LLM_MODEL="gpt-4o"
 export TEI_EMBEDDING_ENDPOINT="http://${host_ip}:${TEI_EMBEDDER_PORT}"
+export LLM_MODEL_ID="meta-llama/Meta-Llama-3.1-8B-Instruct"
 export TGI_LLM_ENDPOINT="http://${host_ip}:${LLM_ENDPOINT_PORT}"
 export NEO4J_PORT1=11631
 export NEO4J_PORT2=11632
@@ -34,4 +32,3 @@ export MAX_TOTAL_TOKENS=8192
 export DATA_PATH="/mnt/nvme2n1/hf_cache"
 export DATAPREP_PORT=11103
 export RETRIEVER_PORT=11635
-export MEGA_SERVICE_PORT=8888

GraphRAG/tests/README.md

@@ -1,15 +0,0 @@
-# GraphRAG E2E test scripts
-
-## Set the required environment variable
-
-```bash
-export HUGGINGFACEHUB_API_TOKEN="Your_Huggingface_API_Token"
-```
-
-## Run test
-
-On Intel Gaudi:
-
-```bash
-bash test_compose_on_gaudi.sh
-```

GraphRAG/tests/test_compose_on_gaudi.sh

@@ -41,7 +41,31 @@ function build_docker_images() {
 
 function start_services() {
     cd $WORKPATH/docker_compose/intel/hpu/gaudi
-    source set_env.sh
+    export HUGGINGFACEHUB_API_TOKEN=${HUGGINGFACEHUB_API_TOKEN}
+    export HF_TOKEN=${HUGGINGFACEHUB_API_TOKEN}
+
+    export TEI_EMBEDDER_PORT=11633
+    export LLM_ENDPOINT_PORT=11634
+    export EMBEDDING_MODEL_ID="BAAI/bge-base-en-v1.5"
+    export OPENAI_EMBEDDING_MODEL="text-embedding-3-small"
+    export LLM_MODEL_ID="meta-llama/Meta-Llama-3.1-8B-Instruct"
+    export OPENAI_LLM_MODEL="gpt-4o"
+    export TEI_EMBEDDING_ENDPOINT="http://${host_ip}:${TEI_EMBEDDER_PORT}"
+    export LLM_MODEL_ID="meta-llama/Meta-Llama-3.1-8B-Instruct"
+    export TGI_LLM_ENDPOINT="http://${host_ip}:${LLM_ENDPOINT_PORT}"
+    export NEO4J_PORT1=11631
+    export NEO4J_PORT2=11632
+    export NEO4J_URI="bolt://${host_ip}:${NEO4J_PORT2}"
+    export NEO4J_URL="bolt://${host_ip}:${NEO4J_PORT2}"
+    export NEO4J_USERNAME="neo4j"
+    export NEO4J_PASSWORD="neo4jtest"
+    export DATAPREP_SERVICE_ENDPOINT="http://${host_ip}:5000/v1/dataprep/ingest"
+    export LOGFLAG=True
+    export MAX_INPUT_TOKENS=4096
+    export MAX_TOTAL_TOKENS=8192
+    export DATAPREP_PORT=11103
+    export RETRIEVER_PORT=11635
+    export MEGA_SERVICE_PORT=8888
     unset OPENAI_API_KEY
 
     # Start Docker Containers

docker_images_list.md

@@ -111,7 +111,7 @@ Take ChatQnA for example. ChatQnA is a chatbot application service based on the
 | [opea/vllm-arc](https://hub.docker.com/r/opea/vllm-arc)                                                             | [Link](https://github.com/opea-project/GenAIComps/blob/main/comps/third_parties/vllm/src/Dockerfile.intel_gpu)        | Deploying and servicing VLLM models on Arc based on VLLM projects                                                                                                                            | [Link](https://github.com/opea-project/GenAIComps/blob/main/comps/third_parties/vllm/README.md)                          |
 | [opea/vllm-gaudi](https://hub.docker.com/r/opea/vllm-gaudi)                                                         | [Link](https://github.com/HabanaAI/vllm-fork/blob/v0.6.6.post1%2BGaudi-1.20.0/Dockerfile.hpu)                         | Deploying and servicing VLLM models on Gaudi2 based on VLLM project                                                                                                                          | [Link](https://github.com/HabanaAI/vllm-fork/blob/habana_main/README.md)                                                 |
 | [opea/vllm-openvino](https://hub.docker.com/r/opea/vllm-openvino)                                                   | [Link](https://github.com/vllm-project/vllm/blob/v0.6.1/Dockerfile.openvino)                                          | VLLM Model for Deploying and Serving Openvino Framework Based on VLLM Project                                                                                                                | [Link](https://github.com/vllm-project/vllm/blob/main/README.md)                                                         |
-| [opea/vllm-rocm](https://hub.docker.com/r/opea/vllm-rocm)                                                           | [Link](https://github.com/opea-project/GenAIComps/blob/main/comps/third_parties/vllm/src/Dockerfile.amd_gpu)          | Deploying and servicing VLLM models on AMD Rocm based on VLLM project                                                                                                                        | [Link](https://github.com/opea-project/GenAIComps/blob/main/comps/third_parties/vllm/README.md)                          |
+| [opea/vllm-rocm](https://hub.docker.com/r/opea/vllm-rocm)                                                           | [Link](https://github.com/opea-project/GenAIComps/blob/main/comps/third_parties/vllm/src/Dockerfile.amd_gpu)          | Deploying and servicing VLLM models on AMD Rocm based on VLLM project                                                                                                                        |                                                                                                                          |
 | [opea/wav2lip](https://hub.docker.com/r/opea/wav2lip)                                                               | [Link](https://github.com/opea-project/GenAIComps/blob/main/comps/third_parties/wav2lip/src/Dockerfile)               | OPEA Generate lip movements from audio files microservice with Pathway for GenAI application                                                                                                 | [Link](https://github.com/opea-project/GenAIComps/blob/main/comps/third_parties/wav2lip/deployment/kubernetes/README.md) |
 | [opea/wav2lip-gaudi](https://hub.docker.com/r/opea/wav2lip-gaudi)                                                   | [Link](https://github.com/opea-project/GenAIComps/blob/main/comps/third_parties/wav2lip/src/Dockerfile.intel_hpu)     | OPEA Generate lip movements from audio files microservice with Pathway for GenAI application use on the Gaudi2                                                                               | [Link](https://github.com/opea-project/GenAIComps/blob/main/comps/third_parties/wav2lip/deployment/kubernetes/README.md) |
 | [opea/web-retriever](https://hub.docker.com/r/opea/web-retriever)<br>                                               | [Link](https://github.com/opea-project/GenAIComps/blob/main/comps/web_retrievers/src/Dockerfile)                      | OPEA retrieval microservice based on chroma vectordb for GenAI application                                                                                                                   | [Link](https://github.com/opea-project/GenAIComps/blob/main/comps/web_retrievers/src/README.md)                          |