Added compose example for VisualQnA deployment on AMD ROCm systems (#1201)
Signed-off-by: artem-astafev <a.astafev@datamonsters.com> Signed-off-by: Artem Astafev <a.astafev@datamonsters.com> Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com>
This commit is contained in:
Artem Astafev
212
VisualQnA/tests/test_compose_on_rocm.sh
Normal file
212
VisualQnA/tests/test_compose_on_rocm.sh
Normal file
@@ -0,0 +1,212 @@
|
||||
#!/bin/bash
|
||||
# Copyright (C) 2024 Advanced Micro Devices, Inc.
|
||||
# SPDX-License-Identifier: Apache-2.0
|
||||
|
||||
set -x
|
||||
IMAGE_REPO=${IMAGE_REPO:-"opea"}
|
||||
IMAGE_TAG=${IMAGE_TAG:-"latest"}
|
||||
echo "REGISTRY=IMAGE_REPO=${IMAGE_REPO}"
|
||||
echo "TAG=IMAGE_TAG=${IMAGE_TAG}"
|
||||
|
||||
WORKPATH=$(dirname "$PWD")
|
||||
LOG_PATH="$WORKPATH/tests"
|
||||
ip_address=$(hostname -I | awk '{print $1}')
|
||||
|
||||
export REGISTRY=${IMAGE_REPO}
|
||||
export TAG=${IMAGE_TAG}
|
||||
export HOST_IP=${ip_address}
|
||||
export VISUALQNA_TGI_SERVICE_PORT="8399"
|
||||
export VISUALQNA_HUGGINGFACEHUB_API_TOKEN=${HUGGINGFACEHUB_API_TOKEN}
|
||||
export VISUALQNA_CARD_ID="card1"
|
||||
export VISUALQNA_RENDER_ID="renderD136"
|
||||
export LVM_MODEL_ID="Xkev/Llama-3.2V-11B-cot"
|
||||
export MODEL="llava-hf/llava-v1.6-mistral-7b-hf"
|
||||
export LVM_ENDPOINT="http://${HOST_IP}:8399"
|
||||
export LVM_SERVICE_PORT=9399
|
||||
export MEGA_SERVICE_HOST_IP=${HOST_IP}
|
||||
export LVM_SERVICE_HOST_IP=${HOST_IP}
|
||||
export BACKEND_SERVICE_ENDPOINT="http://${HOST_IP}:${BACKEND_SERVICE_PORT}/v1/visualqna"
|
||||
export FRONTEND_SERVICE_IP=${HOST_IP}
|
||||
export FRONTEND_SERVICE_PORT=5173
|
||||
export BACKEND_SERVICE_NAME=visualqna
|
||||
export BACKEND_SERVICE_IP=${HOST_IP}
|
||||
export BACKEND_SERVICE_PORT=8888
|
||||
export NGINX_PORT=18003
|
||||
export PATH="~/miniconda3/bin:$PATH"
|
||||
|
||||
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 ../
|
||||
|
||||
echo "Build all the images with --no-cache, check docker_image_build.log for details..."
|
||||
docker compose -f build.yaml build --no-cache > ${LOG_PATH}/docker_image_build.log
|
||||
|
||||
docker pull ghcr.io/huggingface/text-generation-inference:2.4.1-rocm
|
||||
docker images && sleep 1s
|
||||
}
|
||||
|
||||
function start_services() {
|
||||
cd $WORKPATH/docker_compose/amd/gpu/rocm
|
||||
|
||||
sed -i "s/backend_address/$ip_address/g" $WORKPATH/ui/svelte/.env
|
||||
|
||||
# Start Docker Containers
|
||||
docker compose up -d > ${LOG_PATH}/start_services_with_compose.log
|
||||
|
||||
n=0
|
||||
until [[ "$n" -ge 100 ]]; do
|
||||
docker logs visualqna-tgi-service > ${LOG_PATH}/lvm_tgi_service_start.log
|
||||
if grep -q Connected ${LOG_PATH}/lvm_tgi_service_start.log; then
|
||||
break
|
||||
fi
|
||||
sleep 5s
|
||||
n=$((n+1))
|
||||
done
|
||||
}
|
||||
|
||||
function validate_services() {
|
||||
local URL="$1"
|
||||
local EXPECTED_RESULT="$2"
|
||||
local SERVICE_NAME="$3"
|
||||
local DOCKER_NAME="$4"
|
||||
local INPUT_DATA="$5"
|
||||
|
||||
local HTTP_STATUS=$(curl -s -o /dev/null -w "%{http_code}" -X POST -d "$INPUT_DATA" -H 'Content-Type: application/json' "$URL")
|
||||
if [ "$HTTP_STATUS" -eq 200 ]; then
|
||||
echo "[ $SERVICE_NAME ] HTTP status is 200. Checking content..."
|
||||
|
||||
local CONTENT=$(curl -s -X POST -d "$INPUT_DATA" -H 'Content-Type: application/json' "$URL" | tee ${LOG_PATH}/${SERVICE_NAME}.log)
|
||||
|
||||
if echo "$CONTENT" | grep -q "$EXPECTED_RESULT"; then
|
||||
echo "[ $SERVICE_NAME ] Content is as expected."
|
||||
else
|
||||
echo "[ $SERVICE_NAME ] Content does not match the expected result: $CONTENT"
|
||||
docker logs ${DOCKER_NAME} >> ${LOG_PATH}/${SERVICE_NAME}.log
|
||||
exit 1
|
||||
fi
|
||||
else
|
||||
echo "[ $SERVICE_NAME ] HTTP status is not 200. Received status was $HTTP_STATUS"
|
||||
docker logs ${DOCKER_NAME} >> ${LOG_PATH}/${SERVICE_NAME}.log
|
||||
exit 1
|
||||
fi
|
||||
sleep 1s
|
||||
}
|
||||
|
||||
function validate_microservices() {
|
||||
# Check if the microservices are running correctly.
|
||||
|
||||
# lvm microservice
|
||||
validate_services \
|
||||
"${ip_address}:9399/v1/lvm" \
|
||||
"The image" \
|
||||
"lvm-tgi" \
|
||||
"visualqna-tgi-service" \
|
||||
'{"image": "iVBORw0KGgoAAAANSUhEUgAAAAoAAAAKCAYAAACNMs+9AAAAFUlEQVR42mP8/5+hnoEIwDiqkL4KAcT9GO0U4BxoAAAAAElFTkSuQmCC", "prompt":"What is this?"}'
|
||||
}
|
||||
|
||||
function validate_megaservice() {
|
||||
# Curl the Mega Service
|
||||
validate_services \
|
||||
"${ip_address}:8888/v1/visualqna" \
|
||||
"The image" \
|
||||
"visualqna-rocm-backend-server" \
|
||||
"visualqna-rocm-backend-server" \
|
||||
'{
|
||||
"messages": [
|
||||
{
|
||||
"role": "user",
|
||||
"content": [
|
||||
{
|
||||
"type": "text",
|
||||
"text": "What'\''s in this image?"
|
||||
},
|
||||
{
|
||||
"type": "image_url",
|
||||
"image_url": {
|
||||
"url": "https://www.ilankelman.org/stopsigns/australia.jpg"
|
||||
}
|
||||
}
|
||||
]
|
||||
}
|
||||
],
|
||||
"max_tokens": 300
|
||||
}'
|
||||
|
||||
# test the megeservice via nginx
|
||||
validate_services \
|
||||
"${ip_address}:${NGINX_PORT}/v1/visualqna" \
|
||||
"The image" \
|
||||
"visualqna-rocm-nginx-server" \
|
||||
"visualqna-rocm-nginx-server" \
|
||||
'{
|
||||
"messages": [
|
||||
{
|
||||
"role": "user",
|
||||
"content": [
|
||||
{
|
||||
"type": "text",
|
||||
"text": "What'\''s in this image?"
|
||||
},
|
||||
{
|
||||
"type": "image_url",
|
||||
"image_url": {
|
||||
"url": "https://www.ilankelman.org/stopsigns/australia.jpg"
|
||||
}
|
||||
}
|
||||
]
|
||||
}
|
||||
],
|
||||
"max_tokens": 300
|
||||
}'
|
||||
}
|
||||
|
||||
function validate_frontend() {
|
||||
cd $WORKPATH/ui/svelte
|
||||
local conda_env_name="OPEA_e2e"
|
||||
export PATH=${HOME}/miniforge3/bin/:$PATH
|
||||
if conda info --envs | grep -q "$conda_env_name"; then
|
||||
echo "$conda_env_name exist!"
|
||||
else
|
||||
conda create -n ${conda_env_name} python=3.12 -y
|
||||
fi
|
||||
source activate ${conda_env_name}
|
||||
|
||||
sed -i "s/localhost/$ip_address/g" playwright.config.ts
|
||||
|
||||
conda install -c conda-forge nodejs -y
|
||||
npm install && npm ci && npx playwright install --with-deps
|
||||
node -v && npm -v && pip list
|
||||
|
||||
exit_status=0
|
||||
npx playwright test || exit_status=$?
|
||||
|
||||
if [ $exit_status -ne 0 ]; then
|
||||
echo "[TEST INFO]: ---------frontend test failed---------"
|
||||
exit $exit_status
|
||||
else
|
||||
echo "[TEST INFO]: ---------frontend test passed---------"
|
||||
fi
|
||||
}
|
||||
|
||||
function stop_docker() {
|
||||
cd $WORKPATH/docker_compose/amd/gpu/rocm/
|
||||
docker compose stop && docker compose rm -f
|
||||
}
|
||||
|
||||
function main() {
|
||||
|
||||
stop_docker
|
||||
|
||||
if [[ "$IMAGE_REPO" == "opea" ]]; then build_docker_images; fi
|
||||
start_services
|
||||
|
||||
validate_microservices
|
||||
validate_megaservice
|
||||
#validate_frontend
|
||||
|
||||
stop_docker
|
||||
echo y | docker system prune
|
||||
|
||||
}
|
||||
|
||||
main
|
||||
Reference in New Issue
Block a user