Merge branch 'main' into nightly-cancel

Fix ui dockerfile. (#1909 )
Signed-off-by: lkk <33276950+lkk12014402@users.noreply.github.com>
2025-05-06 16:35:38 +08:00 · 2025-05-06 16:34:16 +08:00 · 2025-05-06 16:17:10 +08:00 · 2025-05-06 15:54:43 +08:00 · 2025-05-06 13:41:21 +08:00 · 2025-05-06 13:21:31 +08:00
31 changed files with 518 additions and 278 deletions
--- a/.github/CODEOWNERS
+++ b/.github/CODEOWNERS
@@ -4,13 +4,13 @@
 /AudioQnA/ sihan.chen@intel.com wenjiao.yue@intel.com
 /AvatarChatbot/ chun.tao@intel.com kaokao.lv@intel.com
 /ChatQnA/ liang1.lv@intel.com letong.han@intel.com
-/CodeGen/ liang1.lv@intel.com xinyao.wang@intel.com
-/CodeTrans/ sihan.chen@intel.com xinyao.wang@intel.com
+/CodeGen/ liang1.lv@intel.com
+/CodeTrans/ sihan.chen@intel.com
 /DBQnA/ supriya.krishnamurthi@intel.com liang1.lv@intel.com
 /DocIndexRetriever/ kaokao.lv@intel.com chendi.xue@intel.com
-/DocSum/ letong.han@intel.com xinyao.wang@intel.com
+/DocSum/ letong.han@intel.com
 /EdgeCraftRAG/ yongbo.zhu@intel.com mingyuan.qi@intel.com
-/FaqGen/ yogesh.pandey@intel.com xinyao.wang@intel.com
+/FaqGen/ yogesh.pandey@intel.com
 /GraphRAG/ rita.brugarolas.brufau@intel.com abolfazl.shahbazi@intel.com
 /InstructionTuning/ xinyu.ye@intel.com kaokao.lv@intel.com
 /MultimodalQnA/ melanie.h.buehler@intel.com tiep.le@intel.com
@@ -19,5 +19,5 @@
 /SearchQnA/ sihan.chen@intel.com letong.han@intel.com
 /Text2Image/ wenjiao.yue@intel.com xinyu.ye@intel.com
 /Translation/ liang1.lv@intel.com sihan.chen@intel.com
-/VideoQnA/ huiling.bao@intel.com xinyao.wang@intel.com
+/VideoQnA/ huiling.bao@intel.com
 /VisualQnA/ liang1.lv@intel.com sihan.chen@intel.com
--- a/.github/workflows/_helm-e2e.yml
+++ b/.github/workflows/_helm-e2e.yml
@@ -2,7 +2,9 @@
 # SPDX-License-Identifier: Apache-2.0

 name: Helm Chart E2e Test For Call
-permissions: read-all
+permissions:
+  contents: read
+
 on:
  workflow_call:
    inputs:
@@ -135,16 +137,28 @@ jobs:
        env:
          example: ${{ inputs.example }}
        run: |
-          CHART_NAME="${example,,}"  # CodeGen
-          echo "CHART_NAME=$CHART_NAME" >> $GITHUB_ENV
-          echo "RELEASE_NAME=${CHART_NAME}$(date +%Y%m%d%H%M%S)" >> $GITHUB_ENV
-          echo "NAMESPACE=${CHART_NAME}-$(head -c 4 /dev/urandom | xxd -p)" >> $GITHUB_ENV
-          echo "ROLLOUT_TIMEOUT_SECONDS=600s" >> $GITHUB_ENV
-          echo "TEST_TIMEOUT_SECONDS=600s" >> $GITHUB_ENV
-          echo "KUBECTL_TIMEOUT_SECONDS=60s" >> $GITHUB_ENV
-          echo "should_cleanup=false" >> $GITHUB_ENV
-          echo "skip_validate=false" >> $GITHUB_ENV
-          echo "CHART_FOLDER=${example}/kubernetes/helm" >> $GITHUB_ENV
+          if [[ ! "$example" =~ ^[a-zA-Z]{1,20}$ ]] || [[ "$example" =~ \.\. ]] || [[ "$example" == -* || "$example" == *- ]]; then
+            echo "Error: Invalid input - only lowercase alphanumeric and internal hyphens allowed"
+            exit 1
+          fi
+          # SAFE_PREFIX="kb-"
+          CHART_NAME="${SAFE_PREFIX}$(echo "$example" | tr '[:upper:]' '[:lower:]')"
+          RAND_SUFFIX=$(openssl rand -hex 2 | tr -dc 'a-f0-9')
+
+          cat <<EOF >> $GITHUB_ENV
+          CHART_NAME=${CHART_NAME}
+          RELEASE_NAME=${CHART_NAME}-$(date +%s)
+          NAMESPACE=ns-${CHART_NAME}-${RAND_SUFFIX}
+          ROLLOUT_TIMEOUT_SECONDS=600s
+          TEST_TIMEOUT_SECONDS=600s
+          KUBECTL_TIMEOUT_SECONDS=60s
+          should_cleanup=false
+          skip_validate=false
+          CHART_FOLDER=${example}/kubernetes/helm
+          EOF
+
+          echo "Generated safe variables:" >> $GITHUB_STEP_SUMMARY
+          echo "- CHART_NAME: ${CHART_NAME}" >> $GITHUB_STEP_SUMMARY

      - name: Helm install
        id: install
--- a/.github/workflows/nightly-docker-build-publish.yml
+++ b/.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) }}
--- a/.github/workflows/pr-chart-e2e.yml
+++ b/.github/workflows/pr-chart-e2e.yml
@@ -19,6 +19,9 @@ concurrency:
 jobs:
  job1:
    name: Get-Test-Matrix
+    permissions:
+      contents: read
+      pull-requests: read
    runs-on: ubuntu-latest
    outputs:
      run_matrix: ${{ steps.get-test-matrix.outputs.run_matrix }}
--- a/ChatQnA/README.md
+++ b/ChatQnA/README.md
@@ -96,20 +96,21 @@ flowchart LR

 The table below lists currently available deployment options. They outline in detail the implementation of this example on selected hardware.

-| Category                | Deployment Option            | Description                                                                                                                                                                                                                                                                          |
-| ----------------------- | ---------------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------ |
-| On-premise Deployments  | Docker compose               | [ChatQnA deployment on Xeon](./docker_compose/intel/cpu/xeon)                                                                                                                                                                                                                        |
-|                         |                              | [ChatQnA deployment on AI PC](./docker_compose/intel/cpu/aipc)                                                                                                                                                                                                                       |
-|                         |                              | [ChatQnA deployment on Gaudi](./docker_compose/intel/hpu/gaudi)                                                                                                                                                                                                                      |
-|                         |                              | [ChatQnA deployment on Nvidia GPU](./docker_compose/nvidia/gpu)                                                                                                                                                                                                                      |
-|                         |                              | [ChatQnA deployment on AMD ROCm](./docker_compose/amd/gpu/rocm)                                                                                                                                                                                                                      |
-|                         | Kubernetes                   | [Helm Charts](./kubernetes/helm)                                                                                                                                                                                                                                                     |
-| Cloud Service Providers | AWS                          | [Terraform deployment on 4th Gen Intel Xeon with Intel AMX using meta-llama/Meta-Llama-3-8B-Instruct ](https://github.com/intel/terraform-intel-aws-vm/tree/main/examples/gen-ai-xeon-opea-chatqna)                                                                                  |
-|                         |                              | [Terraform deployment on 4th Gen Intel Xeon with Intel AMX using TII Falcon2-11B](https://github.com/intel/terraform-intel-aws-vm/tree/main/examples/gen-ai-xeon-opea-chatqna-falcon11B)                                                                                             |
-|                         | GCP                          | [Terraform deployment on 5th Gen Intel Xeon with Intel AMX(support Confidential AI by using Intel® TDX](https://github.com/intel/terraform-intel-gcp-vm/tree/main/examples/gen-ai-xeon-opea-chatqna)                                                                                |
-|                         | Azure                        | [Terraform deployment on 4th/5th Gen Intel Xeon with Intel AMX & Intel TDX](https://github.com/intel/terraform-intel-azure-linux-vm/tree/main/examples/azure-gen-ai-xeon-opea-chatqna-tdx)                                                                                           |
-|                         | Intel Tiber AI Cloud         | Coming Soon                                                                                                                                                                                                                                                                          |
-|                         | Any Xeon based Ubuntu system | [ChatQnA Ansible Module for Ubuntu 20.04](https://github.com/intel/optimized-cloud-recipes/tree/main/recipes/ai-opea-chatqna-xeon) .Use this if you are not using Terraform and have provisioned your system either manually or with another tool, including directly on bare metal. |
+| Category                                                                                                                       | Deployment Option            | Description                                                                                                                                                                                                                                                                          |
+| ------------------------------------------------------------------------------------------------------------------------------ | ---------------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------ |
+| On-premise Deployments                                                                                                         | Docker compose               | [ChatQnA deployment on Xeon](./docker_compose/intel/cpu/xeon/README.md)                                                                                                                                                                                                              |
+|                                                                                                                                |                              | [ChatQnA deployment on AI PC](./docker_compose/intel/cpu/aipc/README.md)                                                                                                                                                                                                             |
+|                                                                                                                                |                              | [ChatQnA deployment on Gaudi](./docker_compose/intel/hpu/gaudi/README.md)                                                                                                                                                                                                            |
+|                                                                                                                                |                              | [ChatQnA deployment on Nvidia GPU](./docker_compose/nvidia/gpu/README.md)                                                                                                                                                                                                            |
+|                                                                                                                                |                              | [ChatQnA deployment on AMD ROCm](./docker_compose/amd/gpu/rocm/README.md)                                                                                                                                                                                                            |
+| Cloud Platforms Deployment on AWS, GCP, Azure, IBM Cloud,Oracle Cloud, [Intel® Tiber™ AI Cloud](https://ai.cloud.intel.com/) | Docker Compose               | [Getting Started Guide: Deploy the ChatQnA application across multiple cloud platforms](https://github.com/opea-project/docs/tree/main/getting-started/README.md)                                                                                                                    |
+|                                                                                                                                | Kubernetes                   | [Helm Charts](./kubernetes/helm/README.md)                                                                                                                                                                                                                                           |
+| Automated Terraform Deployment on Cloud Service Providers                                                                      | AWS                          | [Terraform deployment on 4th Gen Intel Xeon with Intel AMX using meta-llama/Meta-Llama-3-8B-Instruct ](https://github.com/intel/terraform-intel-aws-vm/tree/main/examples/gen-ai-xeon-opea-chatqna)                                                                                  |
+|                                                                                                                                |                              | [Terraform deployment on 4th Gen Intel Xeon with Intel AMX using TII Falcon2-11B](https://github.com/intel/terraform-intel-aws-vm/tree/main/examples/gen-ai-xeon-opea-chatqna-falcon11B)                                                                                             |
+|                                                                                                                                | GCP                          | [Terraform deployment on 5th Gen Intel Xeon with Intel AMX(support Confidential AI by using Intel® TDX](https://github.com/intel/terraform-intel-gcp-vm/tree/main/examples/gen-ai-xeon-opea-chatqna)                                                                                |
+|                                                                                                                                | Azure                        | [Terraform deployment on 4th/5th Gen Intel Xeon with Intel AMX & Intel TDX](https://github.com/intel/terraform-intel-azure-linux-vm/tree/main/examples/azure-gen-ai-xeon-opea-chatqna-tdx)                                                                                           |
+|                                                                                                                                | Intel Tiber AI Cloud         | Coming Soon                                                                                                                                                                                                                                                                          |
+|                                                                                                                                | Any Xeon based Ubuntu system | [ChatQnA Ansible Module for Ubuntu 20.04](https://github.com/intel/optimized-cloud-recipes/tree/main/recipes/ai-opea-chatqna-xeon). Use this if you are not using Terraform and have provisioned your system either manually or with another tool, including directly on bare metal. |

 ## Monitor and Tracing

--- a/CodeGen/ui/gradio/codegen_ui_gradio.py
+++ b/CodeGen/ui/gradio/codegen_ui_gradio.py
@@ -46,13 +46,24 @@ dataprep_get_indices_endpoint = f"{DATAPREP_ENDPOINT}/indices"


 # Define the functions that will be used in the app
+
+
+def add_to_history(prompt, history):
+    history.append([prompt["text"], ""])
+    return history, ""
+
+
 def conversation_history(prompt, index, use_agent, history):
    print(f"Generating code for prompt: {prompt} using index: {index} and use_agent is {use_agent}")
-    history.append([prompt, ""])
-    response_generator = generate_code(prompt, index, use_agent)
+    history = add_to_history(prompt, history)[0]
+    response_generator = generate_code(prompt["text"], index, use_agent)
    for token in response_generator:
        history[-1][-1] += token
-        yield history
+        yield history, ""
+
+
+def clear_history():
+    return ""


 def upload_media(media, index=None, chunk_size=1500, chunk_overlap=100):
@@ -287,19 +298,32 @@ def get_file_names(files):
 # Define UI components
 with gr.Blocks() as ui:
    with gr.Tab("Code Generation"):
-        gr.Markdown("### Generate Code from Natural Language")
-        chatbot = gr.Chatbot(label="Chat History")
-        prompt_input = gr.Textbox(label="Enter your query")
-        with gr.Column():
-            with gr.Row(equal_height=True):
+        with gr.Row():
+            with gr.Column(scale=2):
                database_dropdown = gr.Dropdown(choices=get_indices(), label="Select Index", value="None", scale=10)
                db_refresh_button = gr.Button("Refresh Dropdown", scale=0.1)
                db_refresh_button.click(update_indices_dropdown, outputs=database_dropdown)
                use_agent = gr.Checkbox(label="Use Agent", container=False)

-        generate_button = gr.Button("Generate Code")
-        generate_button.click(
-            conversation_history, inputs=[prompt_input, database_dropdown, use_agent, chatbot], outputs=chatbot
+            with gr.Column(scale=9):
+                gr.Markdown("### Generate Code from Natural Language")
+                chatbot = gr.Chatbot(label="Chat History")
+                with gr.Row(equal_height=True):
+                    with gr.Column(scale=8):
+                        prompt_input = gr.MultimodalTextbox(
+                            show_label=False, interactive=True, placeholder="Enter your query", sources=[]
+                        )
+                    with gr.Column(scale=1, min_width=150):
+                        with gr.Row(elem_id="buttons") as button_row:
+                            clear_btn = gr.Button(value="🗑️  Clear", interactive=True)
+                            clear_btn.click(clear_history, None, chatbot)
+
+        prompt_input.submit(add_to_history, inputs=[prompt_input, chatbot], outputs=[chatbot, prompt_input])
+
+        prompt_input.submit(
+            conversation_history,
+            inputs=[prompt_input, database_dropdown, use_agent, chatbot],
+            outputs=[chatbot, prompt_input],
        )

    with gr.Tab("Resource Management"):
@@ -315,7 +339,7 @@ with gr.Blocks() as ui:
                )
            with gr.Column(scale=3):
                file_upload = gr.File(label="Upload Files", file_count="multiple")
-                url_input = gr.Textbox(label="Media to be ingested (Append URL's in a new line)")
+                url_input = gr.Textbox(label="Media to be ingested. Append URL's in a new line (Shift + Enter)")
                upload_button = gr.Button("Upload", variant="primary")
                upload_status = gr.Textbox(label="Upload Status")
                file_upload.change(get_file_names, inputs=file_upload, outputs=url_input)
--- a/CodeTrans/docker_compose/amd/gpu/rocm/set_env.sh
+++ b/CodeTrans/docker_compose/amd/gpu/rocm/set_env.sh
@@ -8,14 +8,14 @@
 # which can be used to connect to the server from the Internet. It must be specified in the EXTERNAL_HOST_IP variable.
 # If the server is used only on the internal network or has a direct external address,
 # specify it in HOST_IP and in EXTERNAL_HOST_IP.
-export HOST_IP=''
-export EXTERNAL_HOST_IP=''
+export HOST_IP=${ip_address}
+export EXTERNAL_HOST_IP=${ip_address}

 ### Model ID
 export CODETRANS_LLM_MODEL_ID="Qwen/Qwen2.5-Coder-7B-Instruct"

 ### The port of the TGI service. On this port, the TGI service will accept connections
-export CODETRANS_TGI_SERVICE_PORT=18156
+export CODETRANS_TGI_SERVICE_PORT=8008

 ### The endpoint of the TGI service to which requests to this service will be sent (formed from previously set variables)
 export CODETRANS_TGI_LLM_ENDPOINT="http://${HOST_IP}:${CODETRANS_TGI_SERVICE_PORT}"
@@ -24,7 +24,7 @@ export CODETRANS_TGI_LLM_ENDPOINT="http://${HOST_IP}:${CODETRANS_TGI_SERVICE_POR
 export CODETRANS_HUGGINGFACEHUB_API_TOKEN=${HUGGINGFACEHUB_API_TOKEN}

 ### The port of the LLM service. On this port, the LLM service will accept connections
-export CODETRANS_LLM_SERVICE_PORT=18157
+export CODETRANS_LLM_SERVICE_PORT=9000

 ### The IP address or domain name of the server for CodeTrans MegaService
 export CODETRANS_MEGA_SERVICE_HOST_IP=${HOST_IP}
@@ -36,7 +36,7 @@ export CODETRANS_LLM_SERVICE_HOST_IP=${HOST_IP}
 export CODETRANS_FRONTEND_SERVICE_IP=${HOST_IP}

 ### The port of the frontend service
-export CODETRANS_FRONTEND_SERVICE_PORT=18155
+export CODETRANS_FRONTEND_SERVICE_PORT=5173

 ### Name of GenAI service for route requests to application
 export CODETRANS_BACKEND_SERVICE_NAME=codetrans
@@ -45,10 +45,10 @@ export CODETRANS_BACKEND_SERVICE_NAME=codetrans
 export CODETRANS_BACKEND_SERVICE_IP=${HOST_IP}

 ### The port of the backend service
-export CODETRANS_BACKEND_SERVICE_PORT=18154
+export CODETRANS_BACKEND_SERVICE_PORT=7777

 ### The port of the Nginx reverse proxy for application
-export CODETRANS_NGINX_PORT=18153
+export CODETRANS_NGINX_PORT=8088

 ### Endpoint of the backend service
 export CODETRANS_BACKEND_SERVICE_URL="http://${EXTERNAL_HOST_IP}:${CODETRANS_BACKEND_SERVICE_PORT}/v1/codetrans"
--- a/CodeTrans/docker_compose/amd/gpu/rocm/set_env_vllm.sh
+++ b/CodeTrans/docker_compose/amd/gpu/rocm/set_env_vllm.sh
@@ -8,14 +8,14 @@
 # which can be used to connect to the server from the Internet. It must be specified in the EXTERNAL_HOST_IP variable.
 # If the server is used only on the internal network or has a direct external address,
 # specify it in HOST_IP and in EXTERNAL_HOST_IP.
-export HOST_IP=''
-export EXTERNAL_HOST_IP=''
+export HOST_IP=${ip_address}
+export EXTERNAL_HOST_IP=${ip_address}

 ### Model ID
 export CODETRANS_LLM_MODEL_ID="Qwen/Qwen2.5-Coder-7B-Instruct"

 ### The port of the TGI service. On this port, the TGI service will accept connections
-export CODETRANS_VLLM_SERVICE_PORT=18156
+export CODETRANS_VLLM_SERVICE_PORT=8008

 ### The endpoint of the TGI service to which requests to this service will be sent (formed from previously set variables)
 export CODETRANS_LLM_ENDPOINT="http://${HOST_IP}:${CODETRANS_VLLM_SERVICE_PORT}"
@@ -24,7 +24,7 @@ export CODETRANS_LLM_ENDPOINT="http://${HOST_IP}:${CODETRANS_VLLM_SERVICE_PORT}"
 export CODETRANS_HUGGINGFACEHUB_API_TOKEN=${HUGGINGFACEHUB_API_TOKEN}

 ### The port of the LLM service. On this port, the LLM service will accept connections
-export CODETRANS_LLM_SERVICE_PORT=18157
+export CODETRANS_LLM_SERVICE_PORT=9000

 ### The IP address or domain name of the server for CodeTrans MegaService
 export CODETRANS_MEGA_SERVICE_HOST_IP=${HOST_IP}
@@ -36,7 +36,7 @@ export CODETRANS_LLM_SERVICE_HOST_IP=${HOST_IP}
 export CODETRANS_FRONTEND_SERVICE_IP=${HOST_IP}

 ### The port of the frontend service
-export CODETRANS_FRONTEND_SERVICE_PORT=18155
+export CODETRANS_FRONTEND_SERVICE_PORT=5173

 ### Name of GenAI service for route requests to application
 export CODETRANS_BACKEND_SERVICE_NAME=codetrans
@@ -45,10 +45,10 @@ export CODETRANS_BACKEND_SERVICE_NAME=codetrans
 export CODETRANS_BACKEND_SERVICE_IP=${HOST_IP}

 ### The port of the backend service
-export CODETRANS_BACKEND_SERVICE_PORT=18154
+export CODETRANS_BACKEND_SERVICE_PORT=7777

 ### The port of the Nginx reverse proxy for application
-export CODETRANS_NGINX_PORT=18153
+export CODETRANS_NGINX_PORT=8088

 ### Endpoint of the backend service
 export CODETRANS_BACKEND_SERVICE_URL="http://${EXTERNAL_HOST_IP}:${CODETRANS_BACKEND_SERVICE_PORT}/v1/codetrans"
--- a/CodeTrans/tests/README.md
+++ b/CodeTrans/tests/README.md
@@ -0,0 +1,45 @@
+# CodeTrans 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
+```
--- a/CodeTrans/tests/test_compose_on_gaudi.sh
+++ b/CodeTrans/tests/test_compose_on_gaudi.sh
@@ -42,25 +42,12 @@ function build_docker_images() {
 }

 function start_services() {
-    cd $WORKPATH/docker_compose/intel/hpu/gaudi
-    export LLM_MODEL_ID="mistralai/Mistral-7B-Instruct-v0.3"
-    export LLM_ENDPOINT="http://${ip_address}:8008"
-    export LLM_COMPONENT_NAME="OpeaTextGenService"
-    export NUM_CARDS=1
-    export BLOCK_SIZE=128
-    export MAX_NUM_SEQS=256
-    export MAX_SEQ_LEN_TO_CAPTURE=2048
+    cd $WORKPATH/docker_compose
    export HUGGINGFACEHUB_API_TOKEN=${HUGGINGFACEHUB_API_TOKEN}
-    export MEGA_SERVICE_HOST_IP=${ip_address}
-    export LLM_SERVICE_HOST_IP=${ip_address}
-    export BACKEND_SERVICE_ENDPOINT="http://${ip_address}:7777/v1/codetrans"
-    export FRONTEND_SERVICE_IP=${ip_address}
-    export FRONTEND_SERVICE_PORT=5173
-    export BACKEND_SERVICE_NAME=codetrans
-    export BACKEND_SERVICE_IP=${ip_address}
-    export BACKEND_SERVICE_PORT=7777
    export NGINX_PORT=80
    export host_ip=${ip_address}
+    source set_env.sh
+    cd intel/hpu/gaudi

    sed -i "s/backend_address/$ip_address/g" $WORKPATH/ui/svelte/.env

--- a/CodeTrans/tests/test_compose_on_rocm.sh
+++ b/CodeTrans/tests/test_compose_on_rocm.sh
@@ -42,21 +42,7 @@ function build_docker_images() {

 function start_services() {
    cd $WORKPATH/docker_compose/amd/gpu/rocm/
-    export CODETRANS_TGI_SERVICE_PORT=8008
-    export CODETRANS_LLM_SERVICE_PORT=9000
-    export CODETRANS_LLM_MODEL_ID="Qwen/Qwen2.5-Coder-7B-Instruct"
-    export CODETRANS_TGI_LLM_ENDPOINT="http://${ip_address}:${CODETRANS_TGI_SERVICE_PORT}"
-    export CODETRANS_HUGGINGFACEHUB_API_TOKEN=${HUGGINGFACEHUB_API_TOKEN}
-    export CODETRANS_MEGA_SERVICE_HOST_IP=${ip_address}
-    export CODETRANS_LLM_SERVICE_HOST_IP=${ip_address}
-    export CODETRANS_FRONTEND_SERVICE_IP=${ip_address}
-    export CODETRANS_FRONTEND_SERVICE_PORT=5173
-    export CODETRANS_BACKEND_SERVICE_NAME=codetrans
-    export CODETRANS_BACKEND_SERVICE_IP=${ip_address}
-    export CODETRANS_BACKEND_SERVICE_PORT=7777
-    export CODETRANS_NGINX_PORT=8088
-    export CODETRANS_BACKEND_SERVICE_URL="http://${ip_address}:${CODETRANS_BACKEND_SERVICE_PORT}/v1/codetrans"
-    export HOST_IP=${ip_address}
+    source set_env.sh

    sed -i "s/backend_address/$ip_address/g" $WORKPATH/ui/svelte/.env

--- a/CodeTrans/tests/test_compose_on_xeon.sh
+++ b/CodeTrans/tests/test_compose_on_xeon.sh
@@ -44,21 +44,13 @@ function build_docker_images() {
 }

 function start_services() {
-    cd $WORKPATH/docker_compose/intel/cpu/xeon/
-    export LLM_MODEL_ID="mistralai/Mistral-7B-Instruct-v0.3"
-    export LLM_ENDPOINT="http://${ip_address}:8008"
-    export LLM_COMPONENT_NAME="OpeaTextGenService"
+    cd $WORKPATH/docker_compose
    export HUGGINGFACEHUB_API_TOKEN=${HUGGINGFACEHUB_API_TOKEN}
-    export MEGA_SERVICE_HOST_IP=${ip_address}
-    export LLM_SERVICE_HOST_IP=${ip_address}
-    export BACKEND_SERVICE_ENDPOINT="http://${ip_address}:7777/v1/codetrans"
-    export FRONTEND_SERVICE_IP=${ip_address}
-    export FRONTEND_SERVICE_PORT=5173
-    export BACKEND_SERVICE_NAME=codetrans
-    export BACKEND_SERVICE_IP=${ip_address}
-    export BACKEND_SERVICE_PORT=7777
+
    export NGINX_PORT=80
    export host_ip=${ip_address}
+    source set_env.sh
+    cd intel/cpu/xeon/

    sed -i "s/backend_address/$ip_address/g" $WORKPATH/ui/svelte/.env

--- a/CodeTrans/tests/test_compose_tgi_on_gaudi.sh
+++ b/CodeTrans/tests/test_compose_tgi_on_gaudi.sh
@@ -40,21 +40,13 @@ function build_docker_images() {
 }

 function start_services() {
-    cd $WORKPATH/docker_compose/intel/hpu/gaudi/
-    export LLM_MODEL_ID="mistralai/Mistral-7B-Instruct-v0.3"
-    export LLM_ENDPOINT="http://${ip_address}:8008"
-    export LLM_COMPONENT_NAME="OpeaTextGenService"
+    cd $WORKPATH/docker_compose
    export HUGGINGFACEHUB_API_TOKEN=${HUGGINGFACEHUB_API_TOKEN}
-    export MEGA_SERVICE_HOST_IP=${ip_address}
-    export LLM_SERVICE_HOST_IP=${ip_address}
-    export BACKEND_SERVICE_ENDPOINT="http://${ip_address}:7777/v1/codetrans"
-    export FRONTEND_SERVICE_IP=${ip_address}
-    export FRONTEND_SERVICE_PORT=5173
-    export BACKEND_SERVICE_NAME=codetrans
-    export BACKEND_SERVICE_IP=${ip_address}
-    export BACKEND_SERVICE_PORT=7777
+
    export NGINX_PORT=80
    export host_ip=${ip_address}
+    source set_env.sh
+    cd intel/hpu/gaudi/

    sed -i "s/backend_address/$ip_address/g" $WORKPATH/ui/svelte/.env

--- a/CodeTrans/tests/test_compose_tgi_on_xeon.sh
+++ b/CodeTrans/tests/test_compose_tgi_on_xeon.sh
@@ -40,21 +40,13 @@ function build_docker_images() {
 }

 function start_services() {
-    cd $WORKPATH/docker_compose/intel/cpu/xeon/
-    export LLM_MODEL_ID="mistralai/Mistral-7B-Instruct-v0.3"
-    export LLM_ENDPOINT="http://${ip_address}:8008"
-    export LLM_COMPONENT_NAME="OpeaTextGenService"
+    cd $WORKPATH/docker_compose
    export HUGGINGFACEHUB_API_TOKEN=${HUGGINGFACEHUB_API_TOKEN}
-    export MEGA_SERVICE_HOST_IP=${ip_address}
-    export LLM_SERVICE_HOST_IP=${ip_address}
-    export BACKEND_SERVICE_ENDPOINT="http://${ip_address}:7777/v1/codetrans"
-    export FRONTEND_SERVICE_IP=${ip_address}
-    export FRONTEND_SERVICE_PORT=5173
-    export BACKEND_SERVICE_NAME=codetrans
-    export BACKEND_SERVICE_IP=${ip_address}
-    export BACKEND_SERVICE_PORT=7777
+
    export NGINX_PORT=80
    export host_ip=${ip_address}
+    source set_env.sh
+    cd intel/cpu/xeon/

    sed -i "s/backend_address/$ip_address/g" $WORKPATH/ui/svelte/.env

--- a/CodeTrans/tests/test_compose_vllm_on_rocm.sh
+++ b/CodeTrans/tests/test_compose_vllm_on_rocm.sh
@@ -40,22 +40,7 @@ function build_docker_images() {

 function start_services() {
    cd $WORKPATH/docker_compose/amd/gpu/rocm/
-    export HOST_IP=${ip_address}
-    export CODETRANS_VLLM_SERVICE_PORT=8008
-    export CODETRANS_LLM_SERVICE_PORT=9000
-    export CODETRANS_LLM_MODEL_ID="Qwen/Qwen2.5-Coder-7B-Instruct"
-    export CODETRANS_LLM_ENDPOINT="http://${ip_address}:${CODETRANS_VLLM_SERVICE_PORT}"
-    export CODETRANS_HUGGINGFACEHUB_API_TOKEN=${HUGGINGFACEHUB_API_TOKEN}
-    export CODETRANS_MEGA_SERVICE_HOST_IP=${ip_address}
-    export CODETRANS_LLM_SERVICE_HOST_IP=${ip_address}
-    export CODETRANS_FRONTEND_SERVICE_IP=${ip_address}
-    export CODETRANS_FRONTEND_SERVICE_PORT=5173
-    export CODETRANS_BACKEND_SERVICE_NAME=codetrans
-    export CODETRANS_BACKEND_SERVICE_IP=${ip_address}
-    export CODETRANS_BACKEND_SERVICE_PORT=7777
-    export CODETRANS_NGINX_PORT=8088
-    export CODETRANS_BACKEND_SERVICE_URL="http://${ip_address}:${CODETRANS_BACKEND_SERVICE_PORT}/v1/codetrans"
-    export HOST_IP=${ip_address}
+    source set_env_vllm.sh

    sed -i "s/backend_address/$ip_address/g" $WORKPATH/ui/svelte/.env

--- a/DocSum/docker_compose/amd/gpu/rocm/set_env.sh
+++ b/DocSum/docker_compose/amd/gpu/rocm/set_env.sh
@@ -3,7 +3,7 @@
 # Copyright (C) 2024 Advanced Micro Devices, Inc.
 # SPDX-License-Identifier: Apache-2.0

-export HOST_IP=''
+export HOST_IP=${ip_address}
 export DOCSUM_MAX_INPUT_TOKENS="2048"
 export DOCSUM_MAX_TOTAL_TOKENS="4096"
 export DOCSUM_LLM_MODEL_ID="Intel/neural-chat-7b-v3-3"
--- a/DocSum/docker_compose/amd/gpu/rocm/set_env_vllm.sh
+++ b/DocSum/docker_compose/amd/gpu/rocm/set_env_vllm.sh
@@ -3,7 +3,7 @@
 # Copyright (C) 2024 Advanced Micro Devices, Inc.
 # SPDX-License-Identifier: Apache-2.0

-export HOST_IP=''
+export HOST_IP=${ip_address}
 export DOCSUM_HUGGINGFACEHUB_API_TOKEN=${HUGGINGFACEHUB_API_TOKEN}
 export DOCSUM_MAX_INPUT_TOKENS=2048
 export DOCSUM_MAX_TOTAL_TOKENS=4096
--- a/DocSum/docker_compose/set_env.sh
+++ b/DocSum/docker_compose/set_env.sh
@@ -10,7 +10,7 @@ export no_proxy="${no_proxy},${host_ip}" # Example: no_proxy="localhost, 127.0.0
 export http_proxy=$http_proxy
 export https_proxy=$https_proxy
 export host_ip=$(hostname -I | awk '{print $1}') # Example: host_ip="192.168.1.1"
-export HUGGINGFACEHUB_API_TOKEN="Your_Huggingface_API_Token"
+export HUGGINGFACEHUB_API_TOKEN=${HUGGINGFACEHUB_API_TOKEN}

 export LLM_ENDPOINT_PORT=8008
 export LLM_MODEL_ID="Intel/neural-chat-7b-v3-3"
@@ -20,10 +20,12 @@ export MAX_TOTAL_TOKENS=2048
 export LLM_PORT=9000
 export LLM_ENDPOINT="http://${host_ip}:${LLM_ENDPOINT_PORT}"
 export DocSum_COMPONENT_NAME="OpeaDocSumvLLM" # OpeaDocSumTgi
-
+export FRONTEND_SERVICE_PORT=5173
 export MEGA_SERVICE_HOST_IP=${host_ip}
 export LLM_SERVICE_HOST_IP=${host_ip}
 export ASR_SERVICE_HOST_IP=${host_ip}

 export BACKEND_SERVICE_PORT=8888
 export BACKEND_SERVICE_ENDPOINT="http://${host_ip}:${BACKEND_SERVICE_PORT}/v1/docsum"
+
+export LOGFLAG=True
--- a/DocSum/kubernetes/helm/README.md
+++ b/DocSum/kubernetes/helm/README.md
@@ -16,3 +16,150 @@ helm install docsum oci://ghcr.io/opea-project/charts/docsum  --set global.HUGGI
 export HFTOKEN="insert-your-huggingface-token-here"
 helm install docsum oci://ghcr.io/opea-project/charts/docsum  --set global.HUGGINGFACEHUB_API_TOKEN=${HFTOKEN} -f gaudi-values.yaml
 ```
+
+## Deploy on AMD ROCm using Helm charts from the binary Helm repository
+
+```bash
+mkdir ~/docsum-k8s-install && cd ~/docsum-k8s-install
+```
+
+### Cloning repos
+
+```bash
+git clone git clone https://github.com/opea-project/GenAIExamples.git
+```
+
+### Go to the installation directory
+
+```bash
+cd GenAIExamples/DocSum/kubernetes/helm
+```
+
+### Settings system variables
+
+```bash
+export HFTOKEN="your_huggingface_token"
+export MODELDIR="/mnt/opea-models"
+export MODELNAME="Intel/neural-chat-7b-v3-3"
+```
+
+### Setting variables in Values files
+
+#### If ROCm vLLM used
+```bash
+nano ~/docsum-k8s-install/GenAIExamples/DocSum/kubernetes/helm/rocm-values.yaml
+```
+
+- HIP_VISIBLE_DEVICES - this variable specifies the ID of the GPU that you want to use.
+  You can specify either one or several comma-separated ones - "0" or "0,1,2,3"
+- TENSOR_PARALLEL_SIZE - must match the number of GPUs used
+- resources:
+  limits:
+  amd.com/gpu: "1" - replace "1" with the number of GPUs used
+
+#### If ROCm TGI used
+
+```bash
+nano ~/docsum-k8s-install/GenAIExamples/DocSum/kubernetes/helm/rocm-tgi-values.yaml
+```
+
+- HIP_VISIBLE_DEVICES - this variable specifies the ID of the GPU that you want to use.
+  You can specify either one or several comma-separated ones - "0" or "0,1,2,3"
+- extraCmdArgs: [ "--num-shard","1" ] - replace "1" with the number of GPUs used
+- resources:
+  limits:
+  amd.com/gpu: "1" - replace "1" with the number of GPUs used
+
+### Installing the Helm Chart
+
+#### If ROCm vLLM used
+```bash
+helm upgrade --install docsum oci://ghcr.io/opea-project/charts/docsum \
+    --set global.HUGGINGFACEHUB_API_TOKEN=${HFTOKEN} \
+    --values rocm-values.yaml
+```
+
+#### If ROCm TGI used
+```bash
+helm upgrade --install docsum oci://ghcr.io/opea-project/charts/docsum \
+    --set global.HUGGINGFACEHUB_API_TOKEN=${HFTOKEN} \
+    --values rocm-tgi-values.yaml
+```
+
+## Deploy on AMD ROCm using Helm charts from Git repositories
+
+### Creating working dirs
+
+```bash
+mkdir ~/docsum-k8s-install && cd ~/docsum-k8s-install
+```
+
+### Cloning repos
+
+```bash
+git clone git clone https://github.com/opea-project/GenAIExamples.git
+git clone git clone https://github.com/opea-project/GenAIInfra.git
+```
+
+### Go to the installation directory
+
+```bash
+cd GenAIExamples/DocSum/kubernetes/helm
+```
+
+### Settings system variables
+
+```bash
+export HFTOKEN="your_huggingface_token"
+export MODELDIR="/mnt/opea-models"
+export MODELNAME="Intel/neural-chat-7b-v3-3"
+```
+
+### Setting variables in Values files
+
+#### If ROCm vLLM used
+```bash
+nano ~/docsum-k8s-install/GenAIExamples/DocSum/kubernetes/helm/rocm-values.yaml
+```
+
+- HIP_VISIBLE_DEVICES - this variable specifies the ID of the GPU that you want to use. 
+You can specify either one or several comma-separated ones - "0" or "0,1,2,3"
+- TENSOR_PARALLEL_SIZE - must match the number of GPUs used
+- resources:
+    limits:
+      amd.com/gpu: "1" - replace "1" with the number of GPUs used
+
+#### If ROCm TGI used
+
+```bash
+nano ~/docsum-k8s-install/GenAIExamples/DocSum/kubernetes/helm/rocm-tgi-values.yaml
+```
+
+- HIP_VISIBLE_DEVICES - this variable specifies the ID of the GPU that you want to use.
+  You can specify either one or several comma-separated ones - "0" or "0,1,2,3"
+- extraCmdArgs: [ "--num-shard","1" ] - replace "1" with the number of GPUs used
+- resources:
+    limits:
+      amd.com/gpu: "1" - replace "1" with the number of GPUs used
+
+### Installing the Helm Chart
+
+#### If ROCm vLLM used
+```bash
+cd ~/docsum-k8s-install/GenAIInfra/helm-charts
+./update_dependency.sh
+helm dependency update docsum
+helm upgrade --install docsum docsum \
+    --set global.HUGGINGFACEHUB_API_TOKEN=${HFTOKEN} \
+    --values ../../GenAIExamples/DocSum/kubernetes/helm/rocm-values.yaml
+```
+
+#### If ROCm TGI used
+```bash
+cd ~/docsum-k8s-install/GenAIInfra/helm-charts
+./update_dependency.sh
+helm dependency update docsum
+helm upgrade --install docsum docsum \
+    --set global.HUGGINGFACEHUB_API_TOKEN=${HFTOKEN} \
+    --values ../../GenAIExamples/DocSum/kubernetes/helm/rocm-tgi-values.yaml
+```
--- a/DocSum/kubernetes/helm/rocm-tgi-values.yaml
+++ b/DocSum/kubernetes/helm/rocm-tgi-values.yaml
@@ -0,0 +1,45 @@
+# Copyright (C) 2025 Advanced Micro Devices, Inc.
+
+tgi:
+  enabled: true
+  accelDevice: "rocm"
+  image:
+    repository: ghcr.io/huggingface/text-generation-inference
+    tag: "2.4.1-rocm"
+  MAX_INPUT_LENGTH: "1024"
+  MAX_TOTAL_TOKENS: "2048"
+  USE_FLASH_ATTENTION: "false"
+  FLASH_ATTENTION_RECOMPUTE: "false"
+  HIP_VISIBLE_DEVICES: "0"
+  MAX_BATCH_SIZE: "4"
+  extraCmdArgs: [ "--num-shard","1" ]
+  resources:
+    limits:
+      amd.com/gpu: "1"
+    requests:
+      cpu: 1
+      memory: 16Gi
+  securityContext:
+    readOnlyRootFilesystem: false
+    runAsNonRoot: false
+    runAsUser: 0
+    capabilities:
+      add:
+        - SYS_PTRACE
+  readinessProbe:
+    initialDelaySeconds: 60
+    periodSeconds: 5
+    timeoutSeconds: 1
+    failureThreshold: 120
+  startupProbe:
+    initialDelaySeconds: 60
+    periodSeconds: 5
+    timeoutSeconds: 1
+    failureThreshold: 120
+
+llm-uservice:
+  DOCSUM_BACKEND: "TGI"
+  retryTimeoutSeconds: 720
+
+vllm:
+  enabled: false
--- a/DocSum/kubernetes/helm/rocm-values.yaml
+++ b/DocSum/kubernetes/helm/rocm-values.yaml
@@ -0,0 +1,40 @@
+# Copyright (C) 2025 Advanced Micro Devices, Inc.
+
+tgi:
+  enabled: false
+
+llm-uservice:
+  DOCSUM_BACKEND: "vLLM"
+  retryTimeoutSeconds: 720
+
+vllm:
+  enabled: true
+  accelDevice: "rocm"
+  image:
+    repository: opea/vllm-rocm
+    tag: latest
+  env:
+    HIP_VISIBLE_DEVICES: "0"
+    TENSOR_PARALLEL_SIZE: "1"
+    HF_HUB_DISABLE_PROGRESS_BARS: "1"
+    HF_HUB_ENABLE_HF_TRANSFER: "0"
+    VLLM_USE_TRITON_FLASH_ATTN: "0"
+    VLLM_WORKER_MULTIPROC_METHOD: "spawn"
+    PYTORCH_JIT: "0"
+    HF_HOME: "/data"
+  extraCmd:
+    command: [ "python3", "/workspace/api_server.py" ]
+  extraCmdArgs: [ "--swap-space", "16",
+                  "--disable-log-requests",
+                  "--dtype", "float16",
+                  "--num-scheduler-steps", "1",
+                  "--distributed-executor-backend", "mp" ]
+  resources:
+    limits:
+      amd.com/gpu: "1"
+  startupProbe:
+    failureThreshold: 180
+  securityContext:
+    readOnlyRootFilesystem: false
+    runAsNonRoot: false
+    runAsUser: 0
--- a/DocSum/tests/README.md
+++ b/DocSum/tests/README.md
@@ -0,0 +1,45 @@
+# DocSum E2E test scripts
+
+## Set the required environment variable
+
+```bash
+export HUGGINGFACEHUB_API_TOKEN="Your_Huggingface_API_Token"
+```
+
+## Run test
+
+On Intel Xeon with vLLM:
+
+```bash
+bash test_compose_on_xeon.sh
+```
+
+On Intel Xeon with TGI:
+
+```bash
+bash test_compose_tgi_on_xeon.sh
+```
+
+On Intel Gaudi with vLLM:
+
+```bash
+bash test_compose_on_gaudi.sh
+```
+
+On Intel Gaudi with TGI:
+
+```bash
+bash test_compose_tgi_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
+```
--- a/DocSum/tests/test_compose_on_gaudi.sh
+++ b/DocSum/tests/test_compose_on_gaudi.sh
@@ -10,35 +10,22 @@ export http_proxy=$http_proxy
 export https_proxy=$https_proxy
 export host_ip=$(hostname -I | awk '{print $1}')

+WORKPATH=$(dirname "$PWD")
+LOG_PATH="$WORKPATH/tests"
 echo "REGISTRY=IMAGE_REPO=${IMAGE_REPO}"
 echo "TAG=IMAGE_TAG=${IMAGE_TAG}"
-export no_proxy="${no_proxy},${host_ip}"
-export MODEL_CACHE=${model_cache:-"./data"}
 export REGISTRY=${IMAGE_REPO}
 export TAG=${IMAGE_TAG}
-export HUGGINGFACEHUB_API_TOKEN=${HUGGINGFACEHUB_API_TOKEN}
-export LLM_ENDPOINT_PORT=8008
-export LLM_MODEL_ID="Intel/neural-chat-7b-v3-3"
+source $WORKPATH/docker_compose/set_env.sh
+
+export MODEL_CACHE=${model_cache:-"./data"}
+
 export NUM_CARDS=1
 export BLOCK_SIZE=128
 export MAX_NUM_SEQS=256
 export MAX_SEQ_LEN_TO_CAPTURE=2048
 export MAX_INPUT_TOKENS=2048
 export MAX_TOTAL_TOKENS=4096
-export LLM_PORT=9000
-export LLM_ENDPOINT="http://${host_ip}:${LLM_ENDPOINT_PORT}"
-export DocSum_COMPONENT_NAME="OpeaDocSumvLLM"
-export MEGA_SERVICE_HOST_IP=${host_ip}
-export LLM_SERVICE_HOST_IP=${host_ip}
-export ASR_SERVICE_HOST_IP=${host_ip}
-export FRONTEND_SERVICE_PORT=5173
-export BACKEND_SERVICE_PORT=8888
-export BACKEND_SERVICE_ENDPOINT="http://${host_ip}:${BACKEND_SERVICE_PORT}/v1/docsum"
-export LOGFLAG=True
-
-WORKPATH=$(dirname "$PWD")
-LOG_PATH="$WORKPATH/tests"
-

 # Get the root folder of the current script
 ROOT_FOLDER=$(dirname "$(readlink -f "$0")")
--- a/DocSum/tests/test_compose_on_rocm.sh
+++ b/DocSum/tests/test_compose_on_rocm.sh
@@ -14,21 +14,8 @@ export MODEL_CACHE=${model_cache:-"./data"}
 WORKPATH=$(dirname "$PWD")
 LOG_PATH="$WORKPATH/tests"
 ip_address=$(hostname -I | awk '{print $1}')
-
-export HOST_IP=${ip_address}
 export host_ip=${ip_address}
-export DOCSUM_MAX_INPUT_TOKENS="2048"
-export DOCSUM_MAX_TOTAL_TOKENS="4096"
-export DOCSUM_LLM_MODEL_ID="Intel/neural-chat-7b-v3-3"
-export DOCSUM_TGI_SERVICE_PORT="8008"
-export DOCSUM_TGI_LLM_ENDPOINT="http://${HOST_IP}:${DOCSUM_TGI_SERVICE_PORT}"
-export DOCSUM_HUGGINGFACEHUB_API_TOKEN=''
-export DOCSUM_WHISPER_PORT="7066"
-export ASR_SERVICE_HOST_IP="${HOST_IP}"
-export DOCSUM_LLM_SERVER_PORT="9000"
-export DOCSUM_BACKEND_SERVER_PORT="18072"
-export DOCSUM_FRONTEND_PORT="18073"
-export BACKEND_SERVICE_ENDPOINT="http://${HOST_IP}:${DOCSUM_BACKEND_SERVER_PORT}/v1/docsum"
+source $WORKPATH/docker_compose/amd/gpu/rocm/set_env.sh

 function build_docker_images() {
    opea_branch=${opea_branch:-"main"}
@@ -129,7 +116,7 @@ function validate_microservices() {
    # whisper microservice
    ulimit -s 65536
    validate_services \
-        "${host_ip}:${DOCSUM_WHISPER_PORT}/v1/asr" \
+        "${HOST_IP}:${DOCSUM_WHISPER_PORT}/v1/asr" \
        '{"asr_result":"well"}' \
        "whisper-service" \
        "whisper-service" \
@@ -137,7 +124,7 @@ function validate_microservices() {

    # tgi for llm service
    validate_services \
-        "${host_ip}:${DOCSUM_TGI_SERVICE_PORT}/generate" \
+        "${HOST_IP}:${DOCSUM_TGI_SERVICE_PORT}/generate" \
        "generated_text" \
        "docsum-tgi-service" \
        "docsum-tgi-service" \
@@ -145,7 +132,7 @@ function validate_microservices() {

    # llm microservice
    validate_services \
-        "${host_ip}:${DOCSUM_LLM_SERVER_PORT}/v1/docsum" \
+        "${HOST_IP}:${DOCSUM_LLM_SERVER_PORT}/v1/docsum" \
        "text" \
        "docsum-llm-server" \
        "docsum-llm-server" \
@@ -158,7 +145,7 @@ function validate_megaservice() {
    local DOCKER_NAME="docsum-backend-server"
    local EXPECTED_RESULT="[DONE]"
    local INPUT_DATA="messages=Text Embeddings Inference (TEI) is a toolkit for deploying and serving open source text embeddings and sequence classification models. TEI enables high-performance extraction for the most popular models, including FlagEmbedding, Ember, GTE and E5."
-    local URL="${host_ip}:${DOCSUM_BACKEND_SERVER_PORT}/v1/docsum"
+    local URL="${HOST_IP}:${DOCSUM_BACKEND_SERVER_PORT}/v1/docsum"
    local DATA_TYPE="type=text"

    local HTTP_STATUS=$(curl -s -o /dev/null -w "%{http_code}" -X POST -F "$DATA_TYPE" -F "$INPUT_DATA" -H 'Content-Type: multipart/form-data' "$URL")
@@ -188,7 +175,7 @@ function validate_megaservice_json() {
    echo ""
    echo ">>> Checking text data with Content-Type: application/json"
    validate_services \
-        "${host_ip}:${DOCSUM_BACKEND_SERVER_PORT}/v1/docsum" \
+        "${HOST_IP}:${DOCSUM_BACKEND_SERVER_PORT}/v1/docsum" \
        "[DONE]" \
        "docsum-backend-server" \
        "docsum-backend-server" \
@@ -196,7 +183,7 @@ function validate_megaservice_json() {

    echo ">>> Checking audio data"
    validate_services \
-        "${host_ip}:${DOCSUM_BACKEND_SERVER_PORT}/v1/docsum" \
+        "${HOST_IP}:${DOCSUM_BACKEND_SERVER_PORT}/v1/docsum" \
        "[DONE]" \
        "docsum-backend-server" \
        "docsum-backend-server" \
@@ -204,7 +191,7 @@ function validate_megaservice_json() {

    echo ">>> Checking video data"
    validate_services \
-        "${host_ip}:${DOCSUM_BACKEND_SERVER_PORT}/v1/docsum" \
+        "${HOST_IP}:${DOCSUM_BACKEND_SERVER_PORT}/v1/docsum" \
        "[DONE]" \
        "docsum-backend-server" \
        "docsum-backend-server" \
--- a/DocSum/tests/test_compose_on_xeon.sh
+++ b/DocSum/tests/test_compose_on_xeon.sh
@@ -10,30 +10,18 @@ export http_proxy=$http_proxy
 export https_proxy=$https_proxy
 export host_ip=$(hostname -I | awk '{print $1}')

-echo "REGISTRY=IMAGE_REPO=${IMAGE_REPO}"
-echo "TAG=IMAGE_TAG=${IMAGE_TAG}"
-export no_proxy="${no_proxy},${host_ip}"
-export MODEL_CACHE=${model_cache:-"./data"}
-export REGISTRY=${IMAGE_REPO}
-export TAG=${IMAGE_TAG}
-export HUGGINGFACEHUB_API_TOKEN=${HUGGINGFACEHUB_API_TOKEN}
-export LLM_ENDPOINT_PORT=8008
-export LLM_MODEL_ID="Intel/neural-chat-7b-v3-3"
-export MAX_INPUT_TOKENS=2048
-export MAX_TOTAL_TOKENS=4096
-export LLM_PORT=9000
-export LLM_ENDPOINT="http://${host_ip}:${LLM_ENDPOINT_PORT}"
-export DocSum_COMPONENT_NAME="OpeaDocSumvLLM"
-export MEGA_SERVICE_HOST_IP=${host_ip}
-export LLM_SERVICE_HOST_IP=${host_ip}
-export ASR_SERVICE_HOST_IP=${host_ip}
-export FRONTEND_SERVICE_PORT=5173
-export BACKEND_SERVICE_PORT=8888
-export BACKEND_SERVICE_ENDPOINT="http://${host_ip}:${BACKEND_SERVICE_PORT}/v1/docsum"
-export LOGFLAG=True
-
 WORKPATH=$(dirname "$PWD")
 LOG_PATH="$WORKPATH/tests"
+echo "REGISTRY=IMAGE_REPO=${IMAGE_REPO}"
+echo "TAG=IMAGE_TAG=${IMAGE_TAG}"
+export REGISTRY=${IMAGE_REPO}
+export TAG=${IMAGE_TAG}
+
+source $WORKPATH/docker_compose/set_env.sh
+export MODEL_CACHE=${model_cache:-"./data"}
+
+export MAX_INPUT_TOKENS=2048
+export MAX_TOTAL_TOKENS=4096

 # Get the root folder of the current script
 ROOT_FOLDER=$(dirname "$(readlink -f "$0")")
--- a/DocSum/tests/test_compose_tgi_on_gaudi.sh
+++ b/DocSum/tests/test_compose_tgi_on_gaudi.sh
@@ -9,32 +9,20 @@ IMAGE_TAG=${IMAGE_TAG:-"latest"}
 export http_proxy=$http_proxy
 export https_proxy=$https_proxy
 export host_ip=$(hostname -I | awk '{print $1}')
-
-echo "REGISTRY=IMAGE_REPO=${IMAGE_REPO}"
-echo "TAG=IMAGE_TAG=${IMAGE_TAG}"
-export no_proxy="${no_proxy},${host_ip}"
-export MODEL_CACHE=${model_cache:-"./data"}
-export REGISTRY=${IMAGE_REPO}
-export TAG=${IMAGE_TAG}
-export HUGGINGFACEHUB_API_TOKEN=${HUGGINGFACEHUB_API_TOKEN}
-export LLM_ENDPOINT_PORT=8008
-export LLM_MODEL_ID="Intel/neural-chat-7b-v3-3"
-export MAX_INPUT_TOKENS=2048
-export MAX_TOTAL_TOKENS=4096
-export LLM_PORT=9000
-export LLM_ENDPOINT="http://${host_ip}:${LLM_ENDPOINT_PORT}"
-export DocSum_COMPONENT_NAME="OpeaDocSumTgi"
-export MEGA_SERVICE_HOST_IP=${host_ip}
-export LLM_SERVICE_HOST_IP=${host_ip}
-export ASR_SERVICE_HOST_IP=${host_ip}
-export FRONTEND_SERVICE_PORT=5173
-export BACKEND_SERVICE_PORT=8888
-export BACKEND_SERVICE_ENDPOINT="http://${host_ip}:${BACKEND_SERVICE_PORT}/v1/docsum"
-export LOGFLAG=True
-
 WORKPATH=$(dirname "$PWD")
 LOG_PATH="$WORKPATH/tests"
+echo "REGISTRY=IMAGE_REPO=${IMAGE_REPO}"
+echo "TAG=IMAGE_TAG=${IMAGE_TAG}"
+export REGISTRY=${IMAGE_REPO}
+export TAG=${IMAGE_TAG}

+source $WORKPATH/docker_compose/set_env.sh
+export MODEL_CACHE=${model_cache:-"./data"}
+
+export MAX_INPUT_TOKENS=2048
+export MAX_TOTAL_TOKENS=4096
+
+export DocSum_COMPONENT_NAME="OpeaDocSumTgi"

 # Get the root folder of the current script
 ROOT_FOLDER=$(dirname "$(readlink -f "$0")")
--- a/DocSum/tests/test_compose_tgi_on_xeon.sh
+++ b/DocSum/tests/test_compose_tgi_on_xeon.sh
@@ -9,31 +9,20 @@ IMAGE_TAG=${IMAGE_TAG:-"latest"}
 export http_proxy=$http_proxy
 export https_proxy=$https_proxy
 export host_ip=$(hostname -I | awk '{print $1}')
-
-echo "REGISTRY=IMAGE_REPO=${IMAGE_REPO}"
-echo "TAG=IMAGE_TAG=${IMAGE_TAG}"
-export no_proxy="${no_proxy},${host_ip}"
-export MODEL_CACHE=${model_cache:-"./data"}
-export REGISTRY=${IMAGE_REPO}
-export TAG=${IMAGE_TAG}
-export HUGGINGFACEHUB_API_TOKEN=${HUGGINGFACEHUB_API_TOKEN}
-export LLM_ENDPOINT_PORT=8008
-export LLM_MODEL_ID="Intel/neural-chat-7b-v3-3"
-export MAX_INPUT_TOKENS=2048
-export MAX_TOTAL_TOKENS=4096
-export LLM_PORT=9000
-export LLM_ENDPOINT="http://${host_ip}:${LLM_ENDPOINT_PORT}"
-export DocSum_COMPONENT_NAME="OpeaDocSumTgi"
-export MEGA_SERVICE_HOST_IP=${host_ip}
-export LLM_SERVICE_HOST_IP=${host_ip}
-export ASR_SERVICE_HOST_IP=${host_ip}
-export FRONTEND_SERVICE_PORT=5173
-export BACKEND_SERVICE_PORT=8888
-export BACKEND_SERVICE_ENDPOINT="http://${host_ip}:${BACKEND_SERVICE_PORT}/v1/docsum"
-export LOGFLAG=True
-
 WORKPATH=$(dirname "$PWD")
 LOG_PATH="$WORKPATH/tests"
+echo "REGISTRY=IMAGE_REPO=${IMAGE_REPO}"
+echo "TAG=IMAGE_TAG=${IMAGE_TAG}"
+export REGISTRY=${IMAGE_REPO}
+export TAG=${IMAGE_TAG}
+
+source $WORKPATH/docker_compose/set_env.sh
+export MODEL_CACHE=${model_cache:-"./data"}
+
+export MAX_INPUT_TOKENS=2048
+export MAX_TOTAL_TOKENS=4096
+
+export DocSum_COMPONENT_NAME="OpeaDocSumTgi"

 # Get the root folder of the current script
 ROOT_FOLDER=$(dirname "$(readlink -f "$0")")
--- a/DocSum/tests/test_compose_vllm_on_rocm.sh
+++ b/DocSum/tests/test_compose_vllm_on_rocm.sh
@@ -16,21 +16,7 @@ WORKPATH=$(dirname "$PWD")
 LOG_PATH="$WORKPATH/tests"
 ip_address=$(hostname -I | awk '{print $1}')

-export host_ip=${ip_address}
-export HOST_IP=${ip_address}
-export EXTERNAL_HOST_IP=${ip_address}
-export DOCSUM_HUGGINGFACEHUB_API_TOKEN="${HUGGINGFACEHUB_API_TOKEN}"
-export DOCSUM_MAX_INPUT_TOKENS=2048
-export DOCSUM_MAX_TOTAL_TOKENS=4096
-export DOCSUM_LLM_MODEL_ID="Intel/neural-chat-7b-v3-3"
-export DOCSUM_VLLM_SERVICE_PORT="8008"
-export DOCSUM_LLM_ENDPOINT="http://${HOST_IP}:${DOCSUM_VLLM_SERVICE_PORT}"
-export DOCSUM_WHISPER_PORT="7066"
-export ASR_SERVICE_HOST_IP="${HOST_IP}"
-export DOCSUM_LLM_SERVER_PORT="9000"
-export DOCSUM_BACKEND_SERVER_PORT="18072"
-export DOCSUM_FRONTEND_PORT="18073"
-export BACKEND_SERVICE_ENDPOINT="http://${EXTERNAL_HOST_IP}:${DOCSUM_BACKEND_SERVER_PORT}/v1/docsum"
+source $WORKPATH/docker_compose/amd/gpu/rocm/set_env_vllm.sh

 function build_docker_images() {
    opea_branch=${opea_branch:-"main"}
@@ -130,7 +116,7 @@ function validate_microservices() {
    # whisper microservice
    ulimit -s 65536
    validate_services \
-        "${host_ip}:${DOCSUM_WHISPER_PORT}/v1/asr" \
+        "${HOST_IP}:${DOCSUM_WHISPER_PORT}/v1/asr" \
        '{"asr_result":"well"}' \
        "whisper-service" \
        "whisper-service" \
@@ -138,7 +124,7 @@ function validate_microservices() {

    # vLLM service
    validate_services \
-        "${host_ip}:${DOCSUM_VLLM_SERVICE_PORT}/v1/chat/completions" \
+        "${HOST_IP}:${DOCSUM_VLLM_SERVICE_PORT}/v1/chat/completions" \
        "content" \
        "docsum-vllm-service" \
        "docsum-vllm-service" \
@@ -146,7 +132,7 @@ function validate_microservices() {

    # llm microservice
    validate_services \
-        "${host_ip}:${DOCSUM_LLM_SERVER_PORT}/v1/docsum" \
+        "${HOST_IP}:${DOCSUM_LLM_SERVER_PORT}/v1/docsum" \
        "text" \
        "docsum-llm-server" \
        "docsum-llm-server" \
@@ -159,7 +145,7 @@ function validate_megaservice() {
    local DOCKER_NAME="docsum-backend-server"
    local EXPECTED_RESULT="[DONE]"
    local INPUT_DATA="messages=Text Embeddings Inference (TEI) is a toolkit for deploying and serving open source text embeddings and sequence classification models. TEI enables high-performance extraction for the most popular models, including FlagEmbedding, Ember, GTE and E5."
-    local URL="${host_ip}:${DOCSUM_BACKEND_SERVER_PORT}/v1/docsum"
+    local URL="${HOST_IP}:${DOCSUM_BACKEND_SERVER_PORT}/v1/docsum"
    local DATA_TYPE="type=text"

    local HTTP_STATUS=$(curl -s -o /dev/null -w "%{http_code}" -X POST -F "$DATA_TYPE" -F "$INPUT_DATA" -H 'Content-Type: multipart/form-data' "$URL")
@@ -189,7 +175,7 @@ function validate_megaservice_json() {
    echo ""
    echo ">>> Checking text data with Content-Type: application/json"
    validate_services \
-        "${host_ip}:${DOCSUM_BACKEND_SERVER_PORT}/v1/docsum" \
+        "${HOST_IP}:${DOCSUM_BACKEND_SERVER_PORT}/v1/docsum" \
        "[DONE]" \
        "docsum-backend-server" \
        "docsum-backend-server" \
@@ -197,7 +183,7 @@ function validate_megaservice_json() {

    echo ">>> Checking audio data"
    validate_services \
-        "${host_ip}:${DOCSUM_BACKEND_SERVER_PORT}/v1/docsum" \
+        "${HOST_IP}:${DOCSUM_BACKEND_SERVER_PORT}/v1/docsum" \
        "[DONE]" \
        "docsum-backend-server" \
        "docsum-backend-server" \
@@ -205,7 +191,7 @@ function validate_megaservice_json() {

    echo ">>> Checking video data"
    validate_services \
-        "${host_ip}:${DOCSUM_BACKEND_SERVER_PORT}/v1/docsum" \
+        "${HOST_IP}:${DOCSUM_BACKEND_SERVER_PORT}/v1/docsum" \
        "[DONE]" \
        "docsum-backend-server" \
        "docsum-backend-server" \
--- a/EdgeCraftRAG/docker_image_build/build.yaml
+++ b/EdgeCraftRAG/docker_image_build/build.yaml
@@ -14,16 +14,19 @@ services:
    image: ${REGISTRY:-opea}/edgecraftrag:${TAG:-latest}
  edgecraftrag-server:
    build:
+      context: ../
      dockerfile: ./Dockerfile.server
    extends: edgecraftrag
    image: ${REGISTRY:-opea}/edgecraftrag-server:${TAG:-latest}
  edgecraftrag-ui:
    build:
+      context: ../
      dockerfile: ./ui/docker/Dockerfile.ui
    extends: edgecraftrag
    image: ${REGISTRY:-opea}/edgecraftrag-ui:${TAG:-latest}
  edgecraftrag-ui-gradio:
    build:
+      context: ../
      dockerfile: ./ui/docker/Dockerfile.gradio
    extends: edgecraftrag
    image: ${REGISTRY:-opea}/edgecraftrag-ui-gradio:${TAG:-latest}
--- a/InstructionTuning/tests/README.md
+++ b/InstructionTuning/tests/README.md
@@ -0,0 +1,15 @@
+# Translation E2E test scripts
+
+## Set the required environment variable
+
+```bash
+export HUGGINGFACEHUB_API_TOKEN="Your_Huggingface_API_Token"
+```
+
+## Run test
+
+On Intel Xeon:
+
+```bash
+bash test_compose_on_xeon.sh
+```
--- a/version.txt
+++ b/version.txt
@@ -1,3 +0,0 @@
-VERSION_MAJOR 1
-VERSION_MINOR 3
-VERSION_PATCH 0
Author	SHA1	Message	Date
ZePan110	ec9db1a3e1	Merge branch 'main' into nightly-cancel	2025-05-06 16:35:38 +08:00
lkk	ff66600ab4	Fix ui dockerfile. (#1909 ) Signed-off-by: lkk <33276950+lkk12014402@users.noreply.github.com>	2025-05-06 16:34:16 +08:00
ZePan110	faf6250590	Fix 1. Signed-off-by: ZePan110 <ze.pan@intel.com>	2025-05-06 16:17:10 +08:00
ZePan110	5375332fb3	Fix security issues for helm test workflow (#1908 ) Signed-off-by: ZePan110 <ze.pan@intel.com> Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com>	2025-05-06 15:54:43 +08:00
Omar Khleif	df33800945	CodeGen Gradio UI Enhancements (#1904 ) Signed-off-by: okhleif-IL <omar.khleif@intel.com>	2025-05-06 13:41:21 +08:00
Ying Hu	40e44dfcd6	Update README.md of ChatQnA for broken URL (#1907 ) Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com> Co-authored-by: Neo Zhang Jianyu <jianyu.zhang@intel.com>	2025-05-06 13:21:31 +08:00
ZePan110	9259ba41a5	Remove invalid codeowner. (#1896 ) Signed-off-by: ZePan110 <ze.pan@intel.com>	2025-04-30 13:24:42 +08:00
ZePan110	5c7f5718ed	Restore context in EdgeCraftRAG build.yaml. (#1895 ) Restore context in EdgeCraftRAG build.yaml to avoid the issue of can't find Dockerfiles. Signed-off-by: ZePan110 <ze.pan@intel.com>	2025-04-30 11:09:21 +08:00
lkk	d334f5c8fd	build cpu agent ui docker image. (#1894 )	2025-04-29 23:58:52 +08:00
ZePan110	670d9f3d18	Fix security issue. (#1892 ) Signed-off-by: ZePan110 <ze.pan@intel.com>	2025-04-29 19:44:48 +08:00
Zhu Yongbo	555c4100b3	Install cpu version for components (#1888 ) Signed-off-by: Yongbozzz <yongbo.zhu@intel.com>	2025-04-29 10:08:23 +08:00
ZePan110	04d527d3b0	Integrate set_env to ut scripts for CodeTrans. (#1868 ) Signed-off-by: ZePan110 <ze.pan@intel.com>	2025-04-28 13:53:50 +08:00
ZePan110	13c4749ca3	Fix security issue (#1884 ) Signed-off-by: ZePan110 <ze.pan@intel.com>	2025-04-28 13:52:50 +08:00
ZePan110	99b62ae49e	Integrate DocSum set_env to ut scripts. (#1860 ) Integrate DocSum set_env to ut scripts. Add README.md for DocSum and InstructionTuning UT scripts. Signed-off-by: ZePan110 <ze.pan@intel.com>	2025-04-28 13:35:05 +08:00
chen, suyue	c546d96e98	downgrade tei version from 1.6 to 1.5, fix the chatqna perf regression (#1886 ) Signed-off-by: chensuyue <suyue.chen@intel.com>	2025-04-25 23:00:36 +08:00
chen, suyue	be5933ad85	Update benchmark scripts (#1883 ) Signed-off-by: chensuyue <suyue.chen@intel.com> Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com>	2025-04-25 17:05:48 +08:00
rbrugaro	18b4f39f27	README fixes Finance Example (#1882 ) Signed-off-by: Rita Brugarolas <rita.brugarolas.brufau@intel.com> Co-authored-by: Ying Hu <ying.hu@intel.com>	2025-04-24 23:58:08 -07:00
chyundunovDatamonsters	ef9290f245	DocSum - refactoring README.md for deploy application on ROCm (#1881 ) Signed-off-by: Chingis Yundunov <YundunovCN@sibedge.com>	2025-04-25 13:36:40 +08:00
chyundunovDatamonsters	3b0bcb80a8	DocSum - Adding files to deploy an application in the K8S environment using Helm (#1758 ) Signed-off-by: Chingis Yundunov <YundunovCN@sibedge.com> Signed-off-by: Chingis Yundunov <c.yundunov@datamonsters.com> Co-authored-by: Chingis Yundunov <YundunovCN@sibedge.com> Co-authored-by: Artem Astafev <a.astafev@datamonsters.com> Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com> Co-authored-by: chen, suyue <suyue.chen@intel.com>	2025-04-25 13:33:08 +08:00
Artem Astafev	ccc145ea1a	Refine README.MD for SearchQnA on AMD ROCm platform (#1876 ) Signed-off-by: Artem Astafev <a.astafev@datamonsters.com>	2025-04-25 10:16:03 +08:00
chyundunovDatamonsters	bb7a675665	ChatQnA - refactoring README.md for deploy application on ROCm (#1857 ) Signed-off-by: Chingis Yundunov <YundunovCN@sibedge.com> Signed-off-by: Chingis Yundunov <c.yundunov@datamonsters.com> Co-authored-by: Chingis Yundunov <YundunovCN@sibedge.com> Co-authored-by: Artem Astafev <a.astafev@datamonsters.com> Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com>	2025-04-25 08:52:24 +08:00
chen, suyue	f90a6d2a8e	[CICD enhance] EdgeCraftRAG run CI with latest base image, group logs in GHA outputs. (#1877 ) Signed-off-by: chensuyue <suyue.chen@intel.com>	2025-04-24 16:18:44 +08:00
chyundunovDatamonsters	1fdab591d9	CodeTrans - refactoring README.md for deploy application on ROCm with Docker Compose (#1875 ) Signed-off-by: Chingis Yundunov <YundunovCN@sibedge.com>	2025-04-24 15:28:57 +08:00
chen, suyue	13ea13862a	Remove proxy in CodeTrans test (#1874 ) Signed-off-by: chensuyue <suyue.chen@intel.com>	2025-04-24 13:47:56 +08:00
ZePan110	1787d1ee98	Update image links. (#1866 ) Signed-off-by: ZePan110 <ze.pan@intel.com>	2025-04-24 13:34:41 +08:00
Artem Astafev	db4bf1a4c3	Refine README.MD for AMD ROCm docker compose deployment (#1856 ) Signed-off-by: Artem Astafev <a.astafev@datamonsters.com>	2025-04-24 11:00:51 +08:00
chen, suyue	f7002fcb70	Set opea_branch for CD test (#1870 ) Signed-off-by: chensuyue <suyue.chen@intel.com>	2025-04-24 09:49:20 +08:00
Artem Astafev	c39c875211	Fix compose file and functional tests for Avatarchatbot on AMD ROCm platform (#1872 ) Signed-off-by: Artem Astafev <a.astafev@datamonsters.com>	2025-04-23 22:58:25 +08:00
Artem Astafev	c2e9a259fe	Refine AuidoQnA README.MD for AMD ROCm docker compose deployment (#1862 ) Signed-off-by: Artem Astafev <a.astafev@datamonsters.com>	2025-04-23 13:55:01 +08:00
Omar Khleif	48eaf9c1c9	Added CodeGen Gradio README link to Docker Images List (#1864 ) Signed-off-by: okhleif-IL <omar.khleif@intel.com> Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com> Co-authored-by: Abolfazl Shahbazi <12436063+ashahba@users.noreply.github.com>	2025-04-22 15:28:49 -07:00
Ervin Castelino	a39824f142	Update README.md of DBQnA (#1855 ) Co-authored-by: Ying Hu <ying.hu@intel.com>	2025-04-22 15:56:37 -04:00
Dina Suehiro Jones	e10e6dd002	Fixes for MultimodalQnA with the Milvus vector db (#1859 ) Signed-off-by: Dina Suehiro Jones <dina.s.jones@intel.com>	2025-04-21 16:05:11 -07:00