Fix ui dockerfile. (#1909)

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

.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
-/CodeTrans/ sihan.chen@intel.com
+/CodeGen/ liang1.lv@intel.com xinyao.wang@intel.com
+/CodeTrans/ sihan.chen@intel.com xinyao.wang@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
+/DocSum/ letong.han@intel.com xinyao.wang@intel.com
 /EdgeCraftRAG/ yongbo.zhu@intel.com mingyuan.qi@intel.com
-/FaqGen/ yogesh.pandey@intel.com
+/FaqGen/ yogesh.pandey@intel.com xinyao.wang@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
+/VideoQnA/ huiling.bao@intel.com xinyao.wang@intel.com
 /VisualQnA/ liang1.lv@intel.com sihan.chen@intel.com

.github/workflows/_helm-e2e.yml

@@ -2,9 +2,7 @@
 # SPDX-License-Identifier: Apache-2.0
 
 name: Helm Chart E2e Test For Call
-permissions:
-  contents: read
-
+permissions: read-all
 on:
   workflow_call:
     inputs:
@@ -137,28 +135,16 @@ jobs:
         env:
           example: ${{ inputs.example }}
         run: |
-          if [[ ! "$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}" >> $GITHUB_STEP_SUMMARY
+          CHART_NAME="${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
 
       - name: Helm install
         id: install

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

@@ -19,9 +19,6 @@ 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 }}

ChatQnA/README.md

@@ -96,21 +96,20 @@ 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/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. |
+| 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. |
 
 ## Monitor and Tracing
 

ChatQnA/benchmark_chatqna.yaml

@@ -37,7 +37,7 @@ deploy:
 
     llm:
       engine: vllm  # or tgi
-      model_id: "meta-llama/Llama-3.1-8B-Instruct" # mandatory
+      model_id: "meta-llama/Meta-Llama-3-8B-Instruct" # mandatory
       replicaCount:
         with_teirerank: [7, 15, 31, 63]     # When teirerank.enabled is True
         without_teirerank: [8, 16, 32, 64]   # When teirerank.enabled is False

CodeGen/ui/gradio/codegen_ui_gradio.py

@@ -46,24 +46,13 @@ 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 = add_to_history(prompt, history)[0]
-    response_generator = generate_code(prompt["text"], index, use_agent)
+    history.append([prompt, ""])
+    response_generator = generate_code(prompt, index, use_agent)
     for token in response_generator:
         history[-1][-1] += token
-        yield history, ""
-
-
-def clear_history():
-    return ""
+        yield history
 
 
 def upload_media(media, index=None, chunk_size=1500, chunk_overlap=100):
@@ -298,32 +287,19 @@ def get_file_names(files):
 # Define UI components
 with gr.Blocks() as ui:
     with gr.Tab("Code Generation"):
-        with gr.Row():
-            with gr.Column(scale=2):
+        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):
                 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)
 
-            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],
+        generate_button = gr.Button("Generate Code")
+        generate_button.click(
+            conversation_history, inputs=[prompt_input, database_dropdown, use_agent, chatbot], outputs=chatbot
         )
 
     with gr.Tab("Resource Management"):
@@ -339,7 +315,7 @@ 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 (Shift + Enter)")
+                url_input = gr.Textbox(label="Media to be ingested (Append URL's in a new line)")
                 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)

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=${ip_address}
-export EXTERNAL_HOST_IP=${ip_address}
+export HOST_IP=''
+export EXTERNAL_HOST_IP=''
 
 ### 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=8008
+export CODETRANS_TGI_SERVICE_PORT=18156
 
 ### 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=9000
+export CODETRANS_LLM_SERVICE_PORT=18157
 
 ### 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=5173
+export CODETRANS_FRONTEND_SERVICE_PORT=18155
 
 ### 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=7777
+export CODETRANS_BACKEND_SERVICE_PORT=18154
 
 ### The port of the Nginx reverse proxy for application
-export CODETRANS_NGINX_PORT=8088
+export CODETRANS_NGINX_PORT=18153
 
 ### Endpoint of the backend service
 export CODETRANS_BACKEND_SERVICE_URL="http://${EXTERNAL_HOST_IP}:${CODETRANS_BACKEND_SERVICE_PORT}/v1/codetrans"

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=${ip_address}
-export EXTERNAL_HOST_IP=${ip_address}
+export HOST_IP=''
+export EXTERNAL_HOST_IP=''
 
 ### 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=8008
+export CODETRANS_VLLM_SERVICE_PORT=18156
 
 ### 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=9000
+export CODETRANS_LLM_SERVICE_PORT=18157
 
 ### 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=5173
+export CODETRANS_FRONTEND_SERVICE_PORT=18155
 
 ### 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=7777
+export CODETRANS_BACKEND_SERVICE_PORT=18154
 
 ### The port of the Nginx reverse proxy for application
-export CODETRANS_NGINX_PORT=8088
+export CODETRANS_NGINX_PORT=18153
 
 ### Endpoint of the backend service
 export CODETRANS_BACKEND_SERVICE_URL="http://${EXTERNAL_HOST_IP}:${CODETRANS_BACKEND_SERVICE_PORT}/v1/codetrans"

CodeTrans/tests/README.md

@@ -1,45 +0,0 @@
-# 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
-```

CodeTrans/tests/test_compose_on_gaudi.sh

@@ -42,12 +42,25 @@ function build_docker_images() {
 }
 
 function start_services() {
-    cd $WORKPATH/docker_compose
+    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
     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
 

CodeTrans/tests/test_compose_on_rocm.sh

@@ -42,7 +42,21 @@ function build_docker_images() {
 
 function start_services() {
     cd $WORKPATH/docker_compose/amd/gpu/rocm/
-    source set_env.sh
+    export CODETRANS_TGI_SERVICE_PORT=8008
+    export CODETRANS_LLM_SERVICE_PORT=9000
+    export CODETRANS_LLM_MODEL_ID="Qwen/Qwen2.5-Coder-7B-Instruct"
+    export CODETRANS_TGI_LLM_ENDPOINT="http://${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}
 
     sed -i "s/backend_address/$ip_address/g" $WORKPATH/ui/svelte/.env
 

CodeTrans/tests/test_compose_on_xeon.sh

@@ -44,13 +44,21 @@ function build_docker_images() {
 }
 
 function start_services() {
-    cd $WORKPATH/docker_compose
+    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"
     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
 

CodeTrans/tests/test_compose_tgi_on_gaudi.sh

@@ -40,13 +40,21 @@ function build_docker_images() {
 }
 
 function start_services() {
-    cd $WORKPATH/docker_compose
+    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 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
 

CodeTrans/tests/test_compose_tgi_on_xeon.sh

@@ -40,13 +40,21 @@ function build_docker_images() {
 }
 
 function start_services() {
-    cd $WORKPATH/docker_compose
+    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"
     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
 

CodeTrans/tests/test_compose_vllm_on_rocm.sh

@@ -40,7 +40,22 @@ 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 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}
 
     sed -i "s/backend_address/$ip_address/g" $WORKPATH/ui/svelte/.env
 

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=${ip_address}
+export HOST_IP=''
 export DOCSUM_MAX_INPUT_TOKENS="2048"
 export DOCSUM_MAX_TOTAL_TOKENS="4096"
 export DOCSUM_LLM_MODEL_ID="Intel/neural-chat-7b-v3-3"

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=${ip_address}
+export HOST_IP=''
 export DOCSUM_HUGGINGFACEHUB_API_TOKEN=${HUGGINGFACEHUB_API_TOKEN}
 export DOCSUM_MAX_INPUT_TOKENS=2048
 export DOCSUM_MAX_TOTAL_TOKENS=4096

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 $1}') # Example: host_ip="192.168.1.1"
-export HUGGINGFACEHUB_API_TOKEN=${HUGGINGFACEHUB_API_TOKEN}
+export HUGGINGFACEHUB_API_TOKEN="Your_Huggingface_API_Token"
 
 export LLM_ENDPOINT_PORT=8008
 export LLM_MODEL_ID="Intel/neural-chat-7b-v3-3"
@@ -20,12 +20,10 @@ 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

DocSum/kubernetes/helm/README.md

@@ -16,150 +16,3 @@ 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
-```

DocSum/kubernetes/helm/rocm-tgi-values.yaml

@@ -1,45 +0,0 @@
-# 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

DocSum/kubernetes/helm/rocm-values.yaml

@@ -1,40 +0,0 @@
-# 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

DocSum/tests/README.md

@@ -1,45 +0,0 @@
-# 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
-```

DocSum/tests/test_compose_on_gaudi.sh

@@ -10,22 +10,35 @@ 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}
-source $WORKPATH/docker_compose/set_env.sh
-
-export MODEL_CACHE=${model_cache:-"./data"}
-
+export HUGGINGFACEHUB_API_TOKEN=${HUGGINGFACEHUB_API_TOKEN}
+export LLM_ENDPOINT_PORT=8008
+export LLM_MODEL_ID="Intel/neural-chat-7b-v3-3"
 export NUM_CARDS=1
 export BLOCK_SIZE=128
 export MAX_NUM_SEQS=256
 export MAX_SEQ_LEN_TO_CAPTURE=2048
 export MAX_INPUT_TOKENS=2048
 export MAX_TOTAL_TOKENS=4096
+export LLM_PORT=9000
+export LLM_ENDPOINT="http://${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")")

DocSum/tests/test_compose_on_rocm.sh

@@ -14,8 +14,21 @@ 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}
-source $WORKPATH/docker_compose/amd/gpu/rocm/set_env.sh
+export DOCSUM_MAX_INPUT_TOKENS="2048"
+export DOCSUM_MAX_TOTAL_TOKENS="4096"
+export DOCSUM_LLM_MODEL_ID="Intel/neural-chat-7b-v3-3"
+export DOCSUM_TGI_SERVICE_PORT="8008"
+export DOCSUM_TGI_LLM_ENDPOINT="http://${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"
 
 function build_docker_images() {
     opea_branch=${opea_branch:-"main"}
@@ -116,7 +129,7 @@ function validate_microservices() {
     # whisper microservice
     ulimit -s 65536
     validate_services \
-        "${HOST_IP}:${DOCSUM_WHISPER_PORT}/v1/asr" \
+        "${host_ip}:${DOCSUM_WHISPER_PORT}/v1/asr" \
         '{"asr_result":"well"}' \
         "whisper-service" \
         "whisper-service" \
@@ -124,7 +137,7 @@ 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" \
@@ -132,7 +145,7 @@ 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" \
@@ -145,7 +158,7 @@ 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")
@@ -175,7 +188,7 @@ 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" \
@@ -183,7 +196,7 @@ 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" \
@@ -191,7 +204,7 @@ 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" \

DocSum/tests/test_compose_on_xeon.sh

@@ -10,18 +10,30 @@ 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}
-
-source $WORKPATH/docker_compose/set_env.sh
-export MODEL_CACHE=${model_cache:-"./data"}
-
+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"
 
 # Get the root folder of the current script
 ROOT_FOLDER=$(dirname "$(readlink -f "$0")")

DocSum/tests/test_compose_tgi_on_gaudi.sh

@@ -9,20 +9,32 @@ IMAGE_TAG=${IMAGE_TAG:-"latest"}
 export http_proxy=$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}
-
-source $WORKPATH/docker_compose/set_env.sh
-export MODEL_CACHE=${model_cache:-"./data"}
-
+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"
+
 
 # Get the root folder of the current script
 ROOT_FOLDER=$(dirname "$(readlink -f "$0")")

DocSum/tests/test_compose_tgi_on_xeon.sh

@@ -9,20 +9,31 @@ IMAGE_TAG=${IMAGE_TAG:-"latest"}
 export http_proxy=$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}
-
-source $WORKPATH/docker_compose/set_env.sh
-export MODEL_CACHE=${model_cache:-"./data"}
-
+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"
 
 # Get the root folder of the current script
 ROOT_FOLDER=$(dirname "$(readlink -f "$0")")

DocSum/tests/test_compose_vllm_on_rocm.sh

@@ -16,7 +16,21 @@ WORKPATH=$(dirname "$PWD")
 LOG_PATH="$WORKPATH/tests"
 ip_address=$(hostname -I | awk '{print $1}')
 
-source $WORKPATH/docker_compose/amd/gpu/rocm/set_env_vllm.sh
+export host_ip=${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"
 
 function build_docker_images() {
     opea_branch=${opea_branch:-"main"}
@@ -116,7 +130,7 @@ function validate_microservices() {
     # whisper microservice
     ulimit -s 65536
     validate_services \
-        "${HOST_IP}:${DOCSUM_WHISPER_PORT}/v1/asr" \
+        "${host_ip}:${DOCSUM_WHISPER_PORT}/v1/asr" \
         '{"asr_result":"well"}' \
         "whisper-service" \
         "whisper-service" \
@@ -124,7 +138,7 @@ 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" \
@@ -132,7 +146,7 @@ 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" \
@@ -145,7 +159,7 @@ 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")
@@ -175,7 +189,7 @@ 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" \
@@ -183,7 +197,7 @@ 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" \
@@ -191,7 +205,7 @@ 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" \

EdgeCraftRAG/docker_image_build/build.yaml

@@ -14,19 +14,16 @@ 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}

InstructionTuning/tests/README.md

@@ -1,15 +0,0 @@
-# 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
-```

deploy.py

@@ -192,7 +192,7 @@ def configure_rerank(values, with_rerank, deploy_config, example_type, node_sele
             values["teirerank"]["nodeSelector"] = {key: value for key, value in node_selector.items()}
     else:
         if example_type == "chatqna":
-            values["CHATQNA_TYPE"] = "CHATQNA_NO_RERANK"
+            values["image"] = {"repository": "opea/chatqna-without-rerank"}
         if "teirerank" not in values:
             values["teirerank"] = {"enabled": False}
         elif "enabled" not in values["teirerank"]:

deploy_and_benchmark.py

@@ -143,7 +143,7 @@ def pull_helm_chart(chart_pull_url, version, chart_name):
     return untar_dir
 
 
-def main(yaml_file, target_node=None, test_mode="oob", clean_up=True):
+def main(yaml_file, target_node=None, test_mode="oob"):
     """Main function to process deployment configuration.
 
     Args:
@@ -278,9 +278,6 @@ def main(yaml_file, target_node=None, test_mode="oob", clean_up=True):
                                 chart_dir,
                             ]
                             result = subprocess.run(cmd, check=True, capture_output=True, text=True)
-                            print("Show deploy logs...")
-                            print(result.stdout)
-                            print("End of show deploy logs.")
 
                             match = re.search(r"values_file_path: (\S+)", result.stdout)
                             if match:
@@ -309,9 +306,6 @@ def main(yaml_file, target_node=None, test_mode="oob", clean_up=True):
                                 "--update-service",
                             ]
                             result = subprocess.run(cmd, check=True, capture_output=True, text=True)
-                            print("Show deploy logs...")
-                            print(result.stdout)
-                            print("End of show deploy logs.")
                             if result.returncode != 0:
                                 print(f"Update failed for {node} nodes configuration with {param_name} {batch_param}")
                                 break  # Skip remaining {param_name} for this node
@@ -378,48 +372,36 @@ def main(yaml_file, target_node=None, test_mode="oob", clean_up=True):
                             os.remove(temp_config_file)
 
             finally:
-                if clean_up:
-                    # Uninstall the deployment
-                    print(f"\nUninstalling deployment for {node} nodes...")
-                    cmd = [
-                        python_cmd,
-                        "deploy.py",
-                        "--chart-name",
-                        chart_name,
-                        "--namespace",
-                        namespace,
-                        "--uninstall",
-                    ]
-                    try:
-                        result = subprocess.run(cmd, check=True)
-                        if result.returncode != 0:
-                            print(f"Failed to uninstall deployment for {node} nodes")
-                    except Exception as e:
-                        print(f"Error while uninstalling deployment for {node} nodes: {str(e)}")
+                # Uninstall the deployment
+                print(f"\nUninstalling deployment for {node} nodes...")
+                cmd = [
+                    python_cmd,
+                    "deploy.py",
+                    "--chart-name",
+                    chart_name,
+                    "--namespace",
+                    namespace,
+                    "--uninstall",
+                ]
+                try:
+                    result = subprocess.run(cmd, check=True)
+                    if result.returncode != 0:
+                        print(f"Failed to uninstall deployment for {node} nodes")
+                except Exception as e:
+                    print(f"Error while uninstalling deployment for {node} nodes: {str(e)}")
 
-                    # Delete labels for current node configuration
-                    print(f"Deleting labels for {node} nodes...")
-                    cmd = [
-                        python_cmd,
-                        "deploy.py",
-                        "--chart-name",
-                        chart_name,
-                        "--num-nodes",
-                        str(node),
-                        "--delete-label",
-                    ]
-                    if current_node_names:
-                        cmd.extend(["--node-names"] + current_node_names)
+                # Delete labels for current node configuration
+                print(f"Deleting labels for {node} nodes...")
+                cmd = [python_cmd, "deploy.py", "--chart-name", chart_name, "--num-nodes", str(node), "--delete-label"]
+                if current_node_names:
+                    cmd.extend(["--node-names"] + current_node_names)
 
-                    try:
-                        result = subprocess.run(cmd, check=True)
-                        if result.returncode != 0:
-                            print(f"Failed to delete labels for {node} nodes")
-                    except Exception as e:
-                        print(f"Error while deleting labels for {node} nodes: {str(e)}")
-                else:
-                    print("Skipping cleanup for local debug. Manual cleanup may be required.")
-                    exit(0)
+                try:
+                    result = subprocess.run(cmd, check=True)
+                    if result.returncode != 0:
+                        print(f"Failed to delete labels for {node} nodes")
+                except Exception as e:
+                    print(f"Error while deleting labels for {node} nodes: {str(e)}")
 
         except Exception as e:
             print(f"Error processing configuration for {node} nodes: {str(e)}")
@@ -437,9 +419,6 @@ if __name__ == "__main__":
     parser.add_argument("yaml_file", help="Path to the YAML configuration file")
     parser.add_argument("--target-node", type=int, help="Optional: Target number of nodes to deploy.", default=None)
     parser.add_argument("--test-mode", type=str, help="Test mode, either 'oob' (out of box) or 'tune'.", default="oob")
-    parser.add_argument(
-        "--clean-up", type=bool, help="Clean up after test, which can be closed for local debug.", default=True
-    )
 
     args = parser.parse_args()
-    main(args.yaml_file, args.target_node, args.test_mode, args.clean_up)
+    main(args.yaml_file, args.target_node, args.test_mode)

version.txt

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