225 lines
6.8 KiB
Bash
225 lines
6.8 KiB
Bash
#!/bin/bash
|
|
# Copyright (C) 2024 Intel Corporation
|
|
# SPDX-License-Identifier: Apache-2.0
|
|
|
|
set -xe
|
|
IMAGE_REPO=${IMAGE_REPO:-"opea"}
|
|
IMAGE_TAG=${IMAGE_TAG:-"latest"}
|
|
echo "REGISTRY=IMAGE_REPO=${IMAGE_REPO}"
|
|
echo "TAG=IMAGE_TAG=${IMAGE_TAG}"
|
|
export REGISTRY=${IMAGE_REPO}
|
|
export TAG=${IMAGE_TAG}
|
|
export MODEL_CACHE=${model_cache:-"./data"}
|
|
|
|
WORKPATH=$(dirname "$PWD")
|
|
LOG_PATH="$WORKPATH/tests"
|
|
ip_address=$(hostname -I | awk '{print $1}')
|
|
|
|
function build_docker_images() {
|
|
opea_branch=${opea_branch:-"main"}
|
|
cd $WORKPATH/docker_image_build
|
|
git clone --depth 1 --branch ${opea_branch} https://github.com/opea-project/GenAIComps.git
|
|
pushd GenAIComps
|
|
echo "GenAIComps test commit is $(git rev-parse HEAD)"
|
|
docker build --no-cache -t ${REGISTRY}/comps-base:${TAG} --build-arg https_proxy=$https_proxy --build-arg http_proxy=$http_proxy -f Dockerfile .
|
|
popd && sleep 1s
|
|
git clone https://github.com/HabanaAI/vllm-fork.git && cd vllm-fork
|
|
VLLM_FORK_VER=v0.6.6.post1+Gaudi-1.20.0
|
|
git checkout ${VLLM_FORK_VER} &> /dev/null && cd ../
|
|
|
|
echo "Build all the images with --no-cache, check docker_image_build.log for details..."
|
|
service_list="chatqna chatqna-ui dataprep retriever vllm-gaudi guardrails nginx"
|
|
docker compose -f build.yaml build ${service_list} --no-cache > ${LOG_PATH}/docker_image_build.log
|
|
|
|
docker images && sleep 1s
|
|
}
|
|
|
|
function start_services() {
|
|
cd $WORKPATH/docker_compose/intel/hpu/gaudi
|
|
export GURADRAILS_MODEL_ID="meta-llama/Meta-Llama-Guard-2-8B"
|
|
source set_env_faqgen.sh
|
|
|
|
# Start Docker Containers
|
|
docker compose -f compose_guardrails.yaml up -d > ${LOG_PATH}/start_services_with_compose.log
|
|
n=0
|
|
until [[ "$n" -ge 200 ]]; do
|
|
echo "n=$n"
|
|
docker logs vllm-gaudi-server > vllm_service_start.log
|
|
if grep -q "Warmup finished" vllm_service_start.log; then
|
|
break
|
|
fi
|
|
sleep 5s
|
|
n=$((n+1))
|
|
done
|
|
|
|
# Make sure vllm guardrails service is ready
|
|
m=0
|
|
until [[ "$m" -ge 200 ]]; do
|
|
echo "m=$m"
|
|
docker logs vllm-guardrails-server > vllm_guardrails_service_start.log
|
|
if grep -q "Warmup finished" vllm_guardrails_service_start.log; then
|
|
break
|
|
fi
|
|
sleep 5s
|
|
m=$((m+1))
|
|
done
|
|
}
|
|
|
|
function validate_service() {
|
|
local URL="$1"
|
|
local EXPECTED_RESULT="$2"
|
|
local SERVICE_NAME="$3"
|
|
local DOCKER_NAME="$4"
|
|
local INPUT_DATA="$5"
|
|
|
|
HTTP_RESPONSE=$(curl --silent --write-out "HTTPSTATUS:%{http_code}" -X POST -d "$INPUT_DATA" -H 'Content-Type: application/json' "$URL")
|
|
HTTP_STATUS=$(echo $HTTP_RESPONSE | tr -d '\n' | sed -e 's/.*HTTPSTATUS://')
|
|
RESPONSE_BODY=$(echo $HTTP_RESPONSE | sed -e 's/HTTPSTATUS\:.*//g')
|
|
|
|
docker logs ${DOCKER_NAME} >> ${LOG_PATH}/${SERVICE_NAME}.log
|
|
|
|
# check response status
|
|
if [ "$HTTP_STATUS" -ne "200" ]; then
|
|
echo "[ $SERVICE_NAME ] HTTP status is not 200. Received status was $HTTP_STATUS"
|
|
exit 1
|
|
else
|
|
echo "[ $SERVICE_NAME ] HTTP status is 200. Checking content..."
|
|
fi
|
|
# check response body
|
|
if [[ "$RESPONSE_BODY" != *"$EXPECTED_RESULT"* ]]; then
|
|
echo "[ $SERVICE_NAME ] Content does not match the expected result: $RESPONSE_BODY"
|
|
exit 1
|
|
else
|
|
echo "[ $SERVICE_NAME ] Content is as expected."
|
|
fi
|
|
|
|
sleep 1s
|
|
}
|
|
|
|
function validate_microservices() {
|
|
# Check if the microservices are running correctly.
|
|
|
|
# tei for embedding service
|
|
validate_service \
|
|
"${ip_address}:8090/embed" \
|
|
"[[" \
|
|
"tei-embedding" \
|
|
"tei-embedding-gaudi-server" \
|
|
'{"inputs":"What is Deep Learning?"}'
|
|
|
|
sleep 1m # retrieval can't curl as expected, try to wait for more time
|
|
|
|
# retrieval microservice
|
|
test_embedding=$(python3 -c "import random; embedding = [random.uniform(-1, 1) for _ in range(768)]; print(embedding)")
|
|
validate_service \
|
|
"${ip_address}:7000/v1/retrieval" \
|
|
"retrieved_docs" \
|
|
"retrieval" \
|
|
"retriever-redis-server" \
|
|
"{\"text\":\"What is the revenue of Nike in 2023?\",\"embedding\":${test_embedding}}"
|
|
|
|
# tei for rerank microservice
|
|
validate_service \
|
|
"${ip_address}:8808/rerank" \
|
|
'{"index":1,"score":' \
|
|
"tei-rerank" \
|
|
"tei-reranking-gaudi-server" \
|
|
'{"query":"What is Deep Learning?", "texts": ["Deep Learning is not...", "Deep learning is..."]}'
|
|
|
|
# vllm for llm service
|
|
validate_service \
|
|
"${ip_address}:8008/v1/chat/completions" \
|
|
"content" \
|
|
"vllm-llm" \
|
|
"vllm-gaudi-server" \
|
|
'{"model": "meta-llama/Meta-Llama-3-8B-Instruct", "messages": [{"role": "user", "content": "What is Deep Learning?"}], "max_tokens":17}'
|
|
|
|
# guardrails microservice
|
|
validate_service \
|
|
"${ip_address}:9090/v1/guardrails" \
|
|
"Violated policies" \
|
|
"guardrails" \
|
|
"guardrails-gaudi-server" \
|
|
'{"text":"How do you buy a tiger in the US?"}'
|
|
}
|
|
|
|
function validate_megaservice() {
|
|
# Curl the Mega Service
|
|
validate_service \
|
|
"${ip_address}:8888/v1/chatqna" \
|
|
"Nike" \
|
|
"mega-chatqna" \
|
|
"chatqna-gaudi-guardrails-server" \
|
|
'{"messages": "What is the revenue of Nike in 2023?"}'
|
|
|
|
}
|
|
|
|
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=22.6.0 -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 $WORKPATH/docker_compose/intel/hpu/gaudi
|
|
docker compose -f compose_guardrails.yaml down
|
|
}
|
|
|
|
function main() {
|
|
|
|
echo "::group::stop_docker"
|
|
stop_docker
|
|
echo "::endgroup::"
|
|
|
|
echo "::group::build_docker_images"
|
|
if [[ "$IMAGE_REPO" == "opea" ]]; then build_docker_images; fi
|
|
echo "::endgroup::"
|
|
|
|
echo "::group::start_services"
|
|
start_services
|
|
echo "::endgroup::"
|
|
|
|
echo "::group::validate_microservices"
|
|
validate_microservices
|
|
echo "::endgroup::"
|
|
|
|
echo "::group::validate_megaservice"
|
|
validate_megaservice
|
|
echo "::endgroup::"
|
|
|
|
echo "::group::validate_frontend"
|
|
validate_frontend
|
|
echo "::endgroup::"
|
|
|
|
echo "::group::stop_docker"
|
|
stop_docker
|
|
echo "::endgroup::"
|
|
|
|
docker system prune -f
|
|
|
|
}
|
|
|
|
main
|