Merge branch 'main' into update_vLLM

Signed-off-by: Yongbozzz <yongbo.zhu@intel.com>

.github/env/_build_image.sh

@@ -1,5 +1,5 @@
 # Copyright (C) 2025 Intel Corporation
 # SPDX-License-Identifier: Apache-2.0
 
-export VLLM_VER=v0.8.3
+export VLLM_VER=v0.9.0
 export VLLM_FORK_VER=v0.6.6.post1+Gaudi-1.20.0

AudioQnA/tests/test_compose_multilang_on_xeon.sh

@@ -27,7 +27,7 @@ function build_docker_images() {
 
     git clone https://github.com/vllm-project/vllm.git
     cd ./vllm/
-    VLLM_VER="v0.8.3"
+    VLLM_VER=v0.9.0
     echo "Check out vLLM tag ${VLLM_VER}"
     git checkout ${VLLM_VER} &> /dev/null && cd ../
 

AudioQnA/tests/test_compose_on_xeon.sh

@@ -27,7 +27,7 @@ function build_docker_images() {
 
     git clone https://github.com/vllm-project/vllm.git
     cd ./vllm/
-    VLLM_VER="v0.8.3"
+    VLLM_VER=v0.9.0
     echo "Check out vLLM tag ${VLLM_VER}"
     git checkout ${VLLM_VER} &> /dev/null && cd ../
 

AvatarChatbot/Dockerfile

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

AvatarChatbot/docker_image_build/build.yaml

@@ -5,6 +5,8 @@ services:
   avatarchatbot:
     build:
       args:
+        IMAGE_REPO: ${REGISTRY:-opea}
+        BASE_TAG: ${TAG:-latest}
         http_proxy: ${http_proxy}
         https_proxy: ${https_proxy}
         no_proxy: ${no_proxy}

AvatarChatbot/tests/test_compose_on_gaudi.sh

@@ -24,19 +24,13 @@ ip_address=$(hostname -I | awk '{print $1}')
 
 function build_docker_images() {
     opea_branch=${opea_branch:-"main"}
-    # If the opea_branch isn't main, replace the git clone branch in Dockerfile.
-    if [[ "${opea_branch}" != "main" ]]; then
-        cd $WORKPATH
-        OLD_STRING="RUN git clone --depth 1 https://github.com/opea-project/GenAIComps.git"
-        NEW_STRING="RUN git clone --depth 1 --branch ${opea_branch} https://github.com/opea-project/GenAIComps.git"
-        find . -type f -name "Dockerfile*" | while read -r file; do
-            echo "Processing file: $file"
-            sed -i "s|$OLD_STRING|$NEW_STRING|g" "$file"
-        done
-    fi
 
     cd $WORKPATH/docker_image_build
     git clone --depth 1 --branch ${opea_branch} https://github.com/opea-project/GenAIComps.git
+    pushd GenAIComps
+    echo "GenAIComps test commit is $(git rev-parse HEAD)"
+    docker build --no-cache -t ${REGISTRY}/comps-base:${TAG} --build-arg https_proxy=$https_proxy --build-arg http_proxy=$http_proxy -f Dockerfile .
+    popd && sleep 1s
 
     echo "Build all the images with --no-cache, check docker_image_build.log for details..."
     service_list="avatarchatbot whisper-gaudi speecht5-gaudi wav2lip-gaudi animation"
@@ -128,19 +122,29 @@ function stop_docker() {
 
 
 function main() {
+    echo "::group::stop_docker"
     stop_docker
-    echo y | docker builder prune --all
-    echo y | docker image prune
+    echo "::endgroup::"
+    docker builder prune --all -f
+    docker image prune -f
 
+    echo "::group::build_docker_images"
     if [[ "$IMAGE_REPO" == "opea" ]]; then build_docker_images; fi
-    start_services
-    # validate_microservices
-    validate_megaservice
-    # validate_frontend
+    echo "::endgroup::"
 
+    echo "::group::start_services"
+    start_services
+    echo "::endgroup::"
+
+    echo "::group::validate_megaservice"
+    validate_megaservice
+    echo "::endgroup::"
+
+    echo "::group::stop_docker"
     stop_docker
-    echo y | docker builder prune --all
-    echo y | docker image prune
+    echo "::endgroup::"
+    docker builder prune --all -f
+    docker image prune -f
 
 }
 

AvatarChatbot/tests/test_compose_on_rocm.sh

@@ -25,6 +25,10 @@ ip_address=$(hostname -I | awk '{print $1}')
 function build_docker_images() {
     cd $WORKPATH/docker_image_build
     git clone https://github.com/opea-project/GenAIComps.git && cd GenAIComps && git checkout "${opea_branch:-"main"}" && cd ../
+    pushd GenAIComps
+    echo "GenAIComps test commit is $(git rev-parse HEAD)"
+    docker build --no-cache -t ${REGISTRY}/comps-base:${TAG} --build-arg https_proxy=$https_proxy --build-arg http_proxy=$http_proxy -f Dockerfile .
+    popd && sleep 1s
 
     echo "Build all the images with --no-cache, check docker_image_build.log for details..."
     service_list="avatarchatbot whisper asr speecht5 tts wav2lip animation"
@@ -138,11 +142,6 @@ function validate_megaservice() {
 }
 
 
-#function validate_frontend() {
-
-#}
-
-
 function stop_docker() {
     cd $WORKPATH/docker_compose/amd/gpu/rocm
     docker compose down && docker compose rm -f
@@ -151,19 +150,27 @@ function stop_docker() {
 
 function main() {
 
-    echo $OPENAI_API_KEY
-    echo $OPENAI_KEY
-
+    echo "::group::stop_docker"
     stop_docker
+    echo "::endgroup::"
+
+    echo "::group::build_docker_images"
     if [[ "$IMAGE_REPO" == "opea" ]]; then build_docker_images; fi
-    start_services
-    # validate_microservices
-    sleep 30
-    validate_megaservice
-    # validate_frontend
-    stop_docker
+    echo "::endgroup::"
 
-    echo y | docker system prune
+    echo "::group::start_services"
+    start_services
+    echo "::endgroup::"
+
+    echo "::group::validate_megaservice"
+    validate_megaservice
+    echo "::endgroup::"
+
+    echo "::group::stop_docker"
+    stop_docker
+    echo "::endgroup::"
+
+    docker system prune -f
 
 }
 

AvatarChatbot/tests/test_compose_on_xeon.sh

@@ -24,19 +24,13 @@ ip_address=$(hostname -I | awk '{print $1}')
 
 function build_docker_images() {
     opea_branch=${opea_branch:-"main"}
-    # If the opea_branch isn't main, replace the git clone branch in Dockerfile.
-    if [[ "${opea_branch}" != "main" ]]; then
-        cd $WORKPATH
-        OLD_STRING="RUN git clone --depth 1 https://github.com/opea-project/GenAIComps.git"
-        NEW_STRING="RUN git clone --depth 1 --branch ${opea_branch} https://github.com/opea-project/GenAIComps.git"
-        find . -type f -name "Dockerfile*" | while read -r file; do
-            echo "Processing file: $file"
-            sed -i "s|$OLD_STRING|$NEW_STRING|g" "$file"
-        done
-    fi
 
     cd $WORKPATH/docker_image_build
     git clone --depth 1 --branch ${opea_branch} https://github.com/opea-project/GenAIComps.git
+    pushd GenAIComps
+    echo "GenAIComps test commit is $(git rev-parse HEAD)"
+    docker build --no-cache -t ${REGISTRY}/comps-base:${TAG} --build-arg https_proxy=$https_proxy --build-arg http_proxy=$http_proxy -f Dockerfile .
+    popd && sleep 1s
 
     echo "Build all the images with --no-cache, check docker_image_build.log for details..."
     service_list="avatarchatbot whisper speecht5 wav2lip animation"
@@ -127,16 +121,28 @@ function stop_docker() {
 
 
 function main() {
-    stop_docker
-    if [[ "$IMAGE_REPO" == "opea" ]]; then build_docker_images; fi
-    start_services
-    # validate_microservices
-    validate_megaservice
-    # validate_frontend
-    stop_docker
 
-    echo y | docker builder prune --all
-    echo y | docker image prune
+    echo "::group::stop_docker"
+    stop_docker
+    echo "::endgroup::"
+
+    echo "::group::build_docker_images"
+    if [[ "$IMAGE_REPO" == "opea" ]]; then build_docker_images; fi
+    echo "::endgroup::"
+
+    echo "::group::start_services"
+    start_services
+    echo "::endgroup::"
+
+    echo "::group::validate_megaservice"
+    validate_megaservice
+    echo "::endgroup::"
+
+    echo "::group::stop_docker"
+    stop_docker
+    echo "::endgroup::"
+
+    docker system prune -f
 
 }
 

ChatQnA/tests/test_compose_faqgen_on_xeon.sh

@@ -24,7 +24,7 @@ function build_docker_images() {
     docker build --no-cache -t ${REGISTRY}/comps-base:${TAG} --build-arg https_proxy=$https_proxy --build-arg http_proxy=$http_proxy -f Dockerfile .
     popd && sleep 1s
     git clone https://github.com/vllm-project/vllm.git && cd vllm
-    VLLM_VER="v0.8.3"
+    VLLM_VER=v0.9.0
     echo "Check out vLLM tag ${VLLM_VER}"
     git checkout ${VLLM_VER} &> /dev/null && cd ../
 

ChatQnA/tests/test_compose_faqgen_tgi_on_xeon.sh

@@ -24,7 +24,7 @@ function build_docker_images() {
     docker build --no-cache -t ${REGISTRY}/comps-base:${TAG} --build-arg https_proxy=$https_proxy --build-arg http_proxy=$http_proxy -f Dockerfile .
     popd && sleep 1s
     git clone https://github.com/vllm-project/vllm.git && cd vllm
-    VLLM_VER="v0.8.3"
+    VLLM_VER=v0.9.0
     echo "Check out vLLM tag ${VLLM_VER}"
     git checkout ${VLLM_VER} &> /dev/null && cd ../
 

ChatQnA/tests/test_compose_mariadb_on_xeon.sh

@@ -24,7 +24,7 @@ function build_docker_images() {
     docker build --no-cache -t ${REGISTRY}/comps-base:${TAG} --build-arg https_proxy=$https_proxy --build-arg http_proxy=$http_proxy -f Dockerfile .
     popd && sleep 1s
     git clone https://github.com/vllm-project/vllm.git && cd vllm
-    VLLM_VER="v0.8.3"
+    VLLM_VER=v0.9.0
     echo "Check out vLLM tag ${VLLM_VER}"
     git checkout ${VLLM_VER} &> /dev/null
     # make sure NOT change the pwd

ChatQnA/tests/test_compose_milvus_on_xeon.sh

@@ -25,7 +25,7 @@ function build_docker_images() {
     docker build --no-cache -t ${REGISTRY}/comps-base:${TAG} --build-arg https_proxy=$https_proxy --build-arg http_proxy=$http_proxy -f Dockerfile .
     popd && sleep 1s
     git clone https://github.com/vllm-project/vllm.git && cd vllm
-    VLLM_VER="v0.8.3"
+    VLLM_VER=v0.9.0
     echo "Check out vLLM tag ${VLLM_VER}"
     git checkout ${VLLM_VER} &> /dev/null
     # make sure NOT change the pwd

ChatQnA/tests/test_compose_on_xeon.sh

@@ -24,7 +24,7 @@ function build_docker_images() {
     docker build --no-cache -t ${REGISTRY}/comps-base:${TAG} --build-arg https_proxy=$https_proxy --build-arg http_proxy=$http_proxy -f Dockerfile .
     popd && sleep 1s
     git clone https://github.com/vllm-project/vllm.git && cd vllm
-    VLLM_VER="v0.8.3"
+    VLLM_VER=v0.9.0
     echo "Check out vLLM tag ${VLLM_VER}"
     git checkout ${VLLM_VER} &> /dev/null
     # make sure NOT change the pwd

ChatQnA/tests/test_compose_pinecone_on_xeon.sh

@@ -25,7 +25,7 @@ function build_docker_images() {
     docker build --no-cache -t ${REGISTRY}/comps-base:${TAG} --build-arg https_proxy=$https_proxy --build-arg http_proxy=$http_proxy -f Dockerfile .
     popd && sleep 1s
     git clone https://github.com/vllm-project/vllm.git && cd vllm
-    VLLM_VER="v0.8.3"
+    VLLM_VER=v0.9.0
     echo "Check out vLLM tag ${VLLM_VER}"
     git checkout ${VLLM_VER} &> /dev/null
     # Not change the pwd

ChatQnA/tests/test_compose_qdrant_on_xeon.sh

@@ -24,7 +24,7 @@ function build_docker_images() {
     docker build --no-cache -t ${REGISTRY}/comps-base:${TAG} --build-arg https_proxy=$https_proxy --build-arg http_proxy=$http_proxy -f Dockerfile .
     popd && sleep 1s
     git clone https://github.com/vllm-project/vllm.git && cd vllm
-    VLLM_VER="v0.8.3"
+    VLLM_VER=v0.9.0
     echo "Check out vLLM tag ${VLLM_VER}"
     git checkout ${VLLM_VER} &> /dev/null
     # Not change the pwd

ChatQnA/tests/test_compose_without_rerank_on_xeon.sh

@@ -25,7 +25,7 @@ function build_docker_images() {
     popd && sleep 1s
     git clone https://github.com/vllm-project/vllm.git && cd vllm
 
-    VLLM_VER="v0.8.3"
+    VLLM_VER=v0.9.0
     echo "Check out vLLM tag ${VLLM_VER}"
     git checkout ${VLLM_VER} &> /dev/null
     # Not change the pwd

CodeGen/tests/test_compose_on_xeon.sh

@@ -42,7 +42,7 @@ function build_docker_images() {
     git clone --depth 1 --branch ${opea_branch} https://github.com/opea-project/GenAIComps.git
 
     git clone https://github.com/vllm-project/vllm.git && cd vllm
-    VLLM_VER="v0.8.3"
+    VLLM_VER=v0.9.0
     echo "Check out vLLM tag ${VLLM_VER}"
     git checkout ${VLLM_VER} &> /dev/null
     cd ../

CodeTrans/tests/test_compose_on_xeon.sh

@@ -26,7 +26,7 @@ function build_docker_images() {
     popd && sleep 1s
 
     git clone https://github.com/vllm-project/vllm.git && cd vllm
-    VLLM_VER="v0.8.3"
+    VLLM_VER=v0.9.0
     echo "Check out vLLM tag ${VLLM_VER}"
     git checkout ${VLLM_VER} &> /dev/null
     cd ../

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

@@ -21,35 +21,29 @@ This section describes how to quickly deploy and test the DocSum service manuall
 6. [Test the Pipeline](#test-the-pipeline)
 7. [Cleanup the Deployment](#cleanup-the-deployment)
 
-### Access the Code
+### Access the Code and Set Up Environment
 
 Clone the GenAIExample repository and access the ChatQnA Intel Xeon platform Docker Compose files and supporting scripts:
 
-```
+```bash
 git clone https://github.com/opea-project/GenAIExamples.git
-cd GenAIExamples/DocSum/docker_compose/intel/cpu/xeon/
+cd GenAIExamples/DocSum/docker_compose
+source set_env.sh
+cd intel/cpu/xeon/
 ```
 
-Checkout a released version, such as v1.2:
+NOTE: by default vLLM does "warmup" at start, to optimize its performance for the specified model and the underlying platform, which can take long time. For development (and e.g. autoscaling) it can be skipped with `export VLLM_SKIP_WARMUP=true`.
 
-```
-git checkout v1.2
+Checkout a released version, such as v1.3:
+
+```bash
+git checkout v1.3
 ```
 
 ### Generate a HuggingFace Access Token
 
 Some HuggingFace resources, such as some models, are only accessible if you have an access token. If you do not already have a HuggingFace access token, you can create one by first creating an account by following the steps provided at [HuggingFace](https://huggingface.co/) and then generating a [user access token](https://huggingface.co/docs/transformers.js/en/guides/private#step-1-generating-a-user-access-token).
 
-### Configure the Deployment Environment
-
-To set up environment variables for deploying DocSum services, source the _set_env.sh_ script in this directory:
-
-```
-source ./set_env.sh
-```
-
-The _set_env.sh_ script will prompt for required and optional environment variables used to configure the DocSum services. If a value is not entered, the script will use a default value for the same. It will also generate a _.env_ file defining the desired configuration. Consult the section on [DocSum Service configuration](#docsum-service-configuration) for information on how service specific configuration parameters affect deployments.
-
 ### Deploy the Services Using Docker Compose
 
 To deploy the DocSum services, execute the `docker compose up` command with the appropriate arguments. For a default deployment, execute:
@@ -78,13 +72,13 @@ Please refer to the table below to build different microservices from source:
 
 After running docker compose, check if all the containers launched via docker compose have started:
 
-```
+```bash
 docker ps -a
 ```
 
 For the default deployment, the following 5 containers should have started:
 
-```
+```bash
 CONTAINER ID   IMAGE                                 COMMAND                  CREATED         STATUS                   PORTS                                       NAMES
 748f577b3c78   opea/whisper:latest                   "python whisper_s…"      5 minutes ago   Up About a minute        0.0.0.0:7066->7066/tcp, :::7066->7066/tcp   docsum-xeon-whisper-server
 4eq8b7034fd9   opea/docsum-gradio-ui:latest          "docker-entrypoint.s…"   5 minutes ago   Up About a minute        0.0.0.0:5173->5173/tcp, :::5173->5173/tcp   docsum-xeon-ui-server
@@ -109,7 +103,7 @@ curl -X POST http://${host_ip}:8888/v1/docsum \
 
 To stop the containers associated with the deployment, execute the following command:
 
-```
+```bash
 docker compose -f compose.yaml down
 ```
 

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

@@ -23,35 +23,29 @@ This section describes how to quickly deploy and test the DocSum service manuall
 6. [Test the Pipeline](#test-the-pipeline)
 7. [Cleanup the Deployment](#cleanup-the-deployment)
 
-### Access the Code
+### Access the Code and Set Up Environment
 
-Clone the GenAIExample repository and access the ChatQnA Intel® Gaudi® platform Docker Compose files and supporting scripts:
+Clone the GenAIExample repository and access the DocSum Intel® Gaudi® platform Docker Compose files and supporting scripts:
 
-```
+```bash
 git clone https://github.com/opea-project/GenAIExamples.git
-cd GenAIExamples/DocSum/docker_compose/intel/hpu/gaudi/
+cd GenAIExamples/DocSum/docker_compose
+source set_env.sh
+cd intel/hpu/gaudi/
 ```
 
-Checkout a released version, such as v1.2:
+NOTE: by default vLLM does "warmup" at start, to optimize its performance for the specified model and the underlying platform, which can take long time. For development (and e.g. autoscaling) it can be skipped with `export VLLM_SKIP_WARMUP=true`.
 
-```
-git checkout v1.2
+Checkout a released version, such as v1.3:
+
+```bash
+git checkout v1.3
 ```
 
 ### Generate a HuggingFace Access Token
 
 Some HuggingFace resources, such as some models, are only accessible if you have an access token. If you do not already have a HuggingFace access token, you can create one by first creating an account by following the steps provided at [HuggingFace](https://huggingface.co/) and then generating a [user access token](https://huggingface.co/docs/transformers.js/en/guides/private#step-1-generating-a-user-access-token).
 
-### Configure the Deployment Environment
-
-To set up environment variables for deploying DocSum services, source the _set_env.sh_ script in this directory:
-
-```
-source ./set_env.sh
-```
-
-The _set_env.sh_ script will prompt for required and optional environment variables used to configure the DocSum services. If a value is not entered, the script will use a default value for the same. It will also generate a _.env_ file defining the desired configuration. Consult the section on [DocSum Service configuration](#docsum-service-configuration) for information on how service specific configuration parameters affect deployments.
-
 ### Deploy the Services Using Docker Compose
 
 To deploy the DocSum services, execute the `docker compose up` command with the appropriate arguments. For a default deployment, execute:
@@ -80,13 +74,13 @@ Please refer to the table below to build different microservices from source:
 
 After running docker compose, check if all the containers launched via docker compose have started:
 
-```
+```bash
 docker ps -a
 ```
 
 For the default deployment, the following 5 containers should have started:
 
-```
+```bash
 CONTAINER ID   IMAGE                                 COMMAND                  CREATED         STATUS                   PORTS                                       NAMES
 748f577b3c78   opea/whisper:latest                   "python whisper_s…"      5 minutes ago   Up About a minute        0.0.0.0:7066->7066/tcp, :::7066->7066/tcp   docsum-gaudi-whisper-server
 4eq8b7034fd9   opea/docsum-gradio-ui:latest          "docker-entrypoint.s…"   5 minutes ago   Up About a minute        0.0.0.0:5173->5173/tcp, :::5173->5173/tcp   docsum-gaudi-ui-server
@@ -111,7 +105,7 @@ curl -X POST http://${host_ip}:8888/v1/docsum \
 
 To stop the containers associated with the deployment, execute the following command:
 
-```
+```bash
 docker compose -f compose.yaml down
 ```
 

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

@@ -18,6 +18,7 @@ services:
       OMPI_MCA_btl_vader_single_copy_mechanism: none
       LLM_MODEL_ID: ${LLM_MODEL_ID}
       NUM_CARDS: ${NUM_CARDS}
+      VLLM_SKIP_WARMUP: ${VLLM_SKIP_WARMUP:-false}
       VLLM_TORCH_PROFILER_DIR: "/mnt"
     healthcheck:
       test: ["CMD-SHELL", "curl -f http://localhost:80/health || exit 1"]

DocSum/docker_compose/set_env.sh

@@ -6,10 +6,10 @@ pushd "../../" > /dev/null
 source .set_env.sh
 popd > /dev/null
 
+export host_ip=$(hostname -I | awk '{print $1}') # Example: host_ip="192.168.1.1"
 export no_proxy="${no_proxy},${host_ip}" # Example: no_proxy="localhost, 127.0.0.1, 192.168.1.1"
 export http_proxy=$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 LLM_ENDPOINT_PORT=8008
@@ -29,3 +29,8 @@ export BACKEND_SERVICE_PORT=8888
 export BACKEND_SERVICE_ENDPOINT="http://${host_ip}:${BACKEND_SERVICE_PORT}/v1/docsum"
 
 export LOGFLAG=True
+
+export NUM_CARDS=1
+export BLOCK_SIZE=128
+export MAX_NUM_SEQS=256
+export MAX_SEQ_LEN_TO_CAPTURE=2048

DocSum/tests/test_compose_on_xeon.sh

@@ -46,7 +46,7 @@ function build_docker_images() {
     popd && sleep 1s
 
     git clone https://github.com/vllm-project/vllm.git && cd vllm
-    VLLM_VER="v0.8.3"
+    VLLM_VER=v0.9.0
     echo "Check out vLLM tag ${VLLM_VER}"
     git checkout ${VLLM_VER} &> /dev/null
     cd ../

EdgeCraftRAG/ui/vue/components.d.ts

@@ -18,12 +18,10 @@ declare module 'vue' {
     AConfigProvider: typeof import('ant-design-vue/es')['ConfigProvider']
     ADescriptions: typeof import('ant-design-vue/es')['Descriptions']
     ADescriptionsItem: typeof import('ant-design-vue/es')['DescriptionsItem']
-    ADivider: typeof import('ant-design-vue/es')['Divider']
     ADrawer: typeof import('ant-design-vue/es')['Drawer']
     AEmpty: typeof import('ant-design-vue/es')['Empty']
     AForm: typeof import('ant-design-vue/es')['Form']
     AFormItem: typeof import('ant-design-vue/es')['FormItem']
-    AImage: typeof import('ant-design-vue/es')['Image']
     AInput: typeof import('ant-design-vue/es')['Input']
     AInputNumber: typeof import('ant-design-vue/es')['InputNumber']
     ALayout: typeof import('ant-design-vue/es')['Layout']
@@ -31,7 +29,6 @@ declare module 'vue' {
     ALayoutHeader: typeof import('ant-design-vue/es')['LayoutHeader']
     AModal: typeof import('ant-design-vue/es')['Modal']
     APagination: typeof import('ant-design-vue/es')['Pagination']
-    APopover: typeof import('ant-design-vue/es')['Popover']
     ARadio: typeof import('ant-design-vue/es')['Radio']
     ARadioGroup: typeof import('ant-design-vue/es')['RadioGroup']
     ARow: typeof import('ant-design-vue/es')['Row']

EdgeCraftRAG/ui/vue/package.json

@@ -12,13 +12,16 @@
     "@vueuse/i18n": "^4.0.0-beta.12",
     "ant-design-vue": "^4.0.0-rc.6",
     "axios": "^1.7.9",
+    "clipboard": "^2.0.11",
+    "dayjs": "^1.11.13",
     "echarts": "^5.5.1",
     "event-source-polyfill": "^1.0.31",
+    "highlight.js": "^11.11.1",
     "http": "^0.0.1-security",
     "js-cookie": "^3.0.5",
     "lodash": "^4.17.21",
     "marked": "^15.0.6",
-    "pinia": "^2.3.0",
+    "pinia": "^3.0.2",
     "pinia-plugin-persistedstate": "^4.2.0",
     "qs": "^6.13.1",
     "socket.io-client": "^4.8.1",

WorkflowExecAgent/tests/2_start_vllm_service.sh

@@ -19,7 +19,7 @@ function build_vllm_docker_image() {
     if [ ! -d "./vllm" ]; then
         git clone https://github.com/vllm-project/vllm.git
         cd vllm
-        VLLM_VER="v0.8.3"
+        VLLM_VER=v0.9.0
         echo "Check out vLLM tag ${VLLM_VER}"
         git checkout ${VLLM_VER} &> /dev/null
         git rev-parse HEAD