jandres/GenAIExamples
1
0
Fork 0
Code Issues Pull Requests Actions 3 Packages Projects Releases Wiki Activity

Support ChatQnA pipeline without rerank microservice (#643)

Browse Source 
Signed-off-by: lvliang-intel <liang1.lv@intel.com>
This commit is contained in:
lvliang-intel
2024-08-22 09:26:54 +08:00
committed by GitHub
parent f3ffcd50b3
commit a54ffd2c1e
7 changed files with 910 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

33
ChatQnA/docker/Dockerfile_without_rerank Normal file
View File

@@ -0,0 +1,33 @@
# Copyright (C) 2024 Intel Corporation
# SPDX-License-Identifier: Apache-2.0
FROM python:3.11-slim
RUN apt-get update -y && apt-get install -y --no-install-recommends --fix-missing \
libgl1-mesa-glx \
libjemalloc-dev \
vim \
git
RUN useradd -m -s /bin/bash user && \
mkdir -p /home/user && \
chown -R user /home/user/
WORKDIR /home/user/
RUN git clone https://github.com/opea-project/GenAIComps.git
WORKDIR /home/user/GenAIComps
RUN pip install --no-cache-dir --upgrade pip && \
pip install --no-cache-dir -r /home/user/GenAIComps/requirements.txt
COPY ./chatqna_without_rerank.py /home/user/chatqna_without_rerank.py
ENV PYTHONPATH=$PYTHONPATH:/home/user/GenAIComps
USER user
WORKDIR /home/user
ENTRYPOINT ["python", "chatqna_without_rerank.py"]

57
ChatQnA/docker/chatqna_without_rerank.py Normal file
View File

@@ -0,0 +1,57 @@
# Copyright (C) 2024 Intel Corporation
# SPDX-License-Identifier: Apache-2.0
import os
from comps import ChatQnAGateway, MicroService, ServiceOrchestrator, ServiceType
MEGA_SERVICE_HOST_IP = os.getenv("MEGA_SERVICE_HOST_IP", "0.0.0.0")
MEGA_SERVICE_PORT = int(os.getenv("MEGA_SERVICE_PORT", 8888))
EMBEDDING_SERVICE_HOST_IP = os.getenv("EMBEDDING_SERVICE_HOST_IP", "0.0.0.0")
EMBEDDING_SERVICE_PORT = int(os.getenv("EMBEDDING_SERVICE_PORT", 6000))
RETRIEVER_SERVICE_HOST_IP = os.getenv("RETRIEVER_SERVICE_HOST_IP", "0.0.0.0")
RETRIEVER_SERVICE_PORT = int(os.getenv("RETRIEVER_SERVICE_PORT", 7000))
LLM_SERVICE_HOST_IP = os.getenv("LLM_SERVICE_HOST_IP", "0.0.0.0")
LLM_SERVICE_PORT = int(os.getenv("LLM_SERVICE_PORT", 9000))
class ChatQnAService:
def __init__(self, host="0.0.0.0", port=8000):
self.host = host
self.port = port
self.megaservice = ServiceOrchestrator()
def add_remote_service(self):
embedding = MicroService(
name="embedding",
host=EMBEDDING_SERVICE_HOST_IP,
port=EMBEDDING_SERVICE_PORT,
endpoint="/v1/embeddings",
use_remote_service=True,
service_type=ServiceType.EMBEDDING,
)
retriever = MicroService(
name="retriever",
host=RETRIEVER_SERVICE_HOST_IP,
port=RETRIEVER_SERVICE_PORT,
endpoint="/v1/retrieval",
use_remote_service=True,
service_type=ServiceType.RETRIEVER,
)
llm = MicroService(
name="llm",
host=LLM_SERVICE_HOST_IP,
port=LLM_SERVICE_PORT,
endpoint="/v1/chat/completions",
use_remote_service=True,
service_type=ServiceType.LLM,
)
self.megaservice.add(embedding).add(retriever).add(llm)
self.megaservice.flow_to(embedding, retriever)
self.megaservice.flow_to(retriever, llm)
self.gateway = ChatQnAGateway(megaservice=self.megaservice, host="0.0.0.0", port=self.port)
if __name__ == "__main__":
chatqna = ChatQnAService(host=MEGA_SERVICE_HOST_IP, port=MEGA_SERVICE_PORT)
chatqna.add_remote_service()

5
ChatQnA/docker/docker_build_compose.yaml
View File

@@ -15,6 +15,11 @@ services:
dockerfile: ./Dockerfile_guardrails
extends: chatqna
image: ${REGISTRY:-opea}/chatqna-guardrails:${TAG:-latest}
chatqna-without-rerank:
build:
dockerfile: ./Dockerfile_without_rerank
extends: chatqna
image: ${REGISTRY:-opea}/chatqna-without-rerank:${TAG:-latest}
chatqna-ui:
build:
context: ui

157
ChatQnA/docker/gaudi/compose_without_rerank.yaml Normal file
View File

@@ -0,0 +1,157 @@
# Copyright (C) 2024 Intel Corporation
# SPDX-License-Identifier: Apache-2.0
services:
redis-vector-db:
image: redis/redis-stack:7.2.0-v9
container_name: redis-vector-db
ports:
- "6379:6379"
- "8001:8001"
dataprep-redis-service:
image: ${REGISTRY:-opea}/dataprep-redis:${TAG:-latest}
container_name: dataprep-redis-server
depends_on:
- redis-vector-db
- tei-embedding-service
ports:
- "6007:6007"
environment:
no_proxy: ${no_proxy}
http_proxy: ${http_proxy}
https_proxy: ${https_proxy}
REDIS_URL: ${REDIS_URL}
INDEX_NAME: ${INDEX_NAME}
TEI_ENDPOINT: ${TEI_EMBEDDING_ENDPOINT}
HUGGINGFACEHUB_API_TOKEN: ${HUGGINGFACEHUB_API_TOKEN}
tei-embedding-service:
image: ${REGISTRY:-opea}/tei-gaudi:${TAG:-latest}
container_name: tei-embedding-gaudi-server
ports:
- "8090:80"
volumes:
- "./data:/data"
runtime: habana
cap_add:
- SYS_NICE
ipc: host
environment:
no_proxy: ${no_proxy}
http_proxy: ${http_proxy}
https_proxy: ${https_proxy}
HABANA_VISIBLE_DEVICES: all
OMPI_MCA_btl_vader_single_copy_mechanism: none
MAX_WARMUP_SEQUENCE_LENGTH: 512
INIT_HCCL_ON_ACQUIRE: 0
ENABLE_EXPERIMENTAL_FLAGS: true
command: --model-id ${EMBEDDING_MODEL_ID} --auto-truncate
embedding:
image: ${REGISTRY:-opea}/embedding-tei:${TAG:-latest}
container_name: embedding-tei-server
depends_on:
- tei-embedding-service
ports:
- "6000:6000"
ipc: host
environment:
no_proxy: ${no_proxy}
http_proxy: ${http_proxy}
https_proxy: ${https_proxy}
TEI_EMBEDDING_ENDPOINT: ${TEI_EMBEDDING_ENDPOINT}
restart: unless-stopped
retriever:
image: ${REGISTRY:-opea}/retriever-redis:${TAG:-latest}
container_name: retriever-redis-server
depends_on:
- redis-vector-db
ports:
- "7000:7000"
ipc: host
environment:
no_proxy: ${no_proxy}
http_proxy: ${http_proxy}
https_proxy: ${https_proxy}
REDIS_URL: ${REDIS_URL}
INDEX_NAME: ${INDEX_NAME}
restart: unless-stopped
tgi-service:
image: ghcr.io/huggingface/tgi-gaudi:2.0.1
container_name: tgi-gaudi-server
ports:
- "8005:80"
volumes:
- "./data:/data"
environment:
no_proxy: ${no_proxy}
http_proxy: ${http_proxy}
https_proxy: ${https_proxy}
HF_TOKEN: ${HUGGINGFACEHUB_API_TOKEN}
HF_HUB_DISABLE_PROGRESS_BARS: 1
HF_HUB_ENABLE_HF_TRANSFER: 0
HABANA_VISIBLE_DEVICES: all
OMPI_MCA_btl_vader_single_copy_mechanism: none
runtime: habana
cap_add:
- SYS_NICE
ipc: host
command: --model-id ${LLM_MODEL_ID} --max-input-length 1024 --max-total-tokens 2048
llm:
image: ${REGISTRY:-opea}/llm-tgi:${TAG:-latest}
container_name: llm-tgi-gaudi-server
depends_on:
- tgi-service
ports:
- "9000:9000"
ipc: host
environment:
no_proxy: ${no_proxy}
http_proxy: ${http_proxy}
https_proxy: ${https_proxy}
TGI_LLM_ENDPOINT: ${TGI_LLM_ENDPOINT}
HUGGINGFACEHUB_API_TOKEN: ${HUGGINGFACEHUB_API_TOKEN}
HF_HUB_DISABLE_PROGRESS_BARS: 1
HF_HUB_ENABLE_HF_TRANSFER: 0
restart: unless-stopped
chaqna-gaudi-backend-server:
image: ${REGISTRY:-opea}/chatqna-without-rerank:${TAG:-latest}
container_name: chatqna-gaudi-backend-server
depends_on:
- redis-vector-db
- tei-embedding-service
- embedding
- retriever
- tgi-service
- llm
ports:
- "8888:8888"
environment:
- no_proxy=${no_proxy}
- https_proxy=${https_proxy}
- http_proxy=${http_proxy}
- MEGA_SERVICE_HOST_IP=${MEGA_SERVICE_HOST_IP}
- EMBEDDING_SERVICE_HOST_IP=${EMBEDDING_SERVICE_HOST_IP}
- RETRIEVER_SERVICE_HOST_IP=${RETRIEVER_SERVICE_HOST_IP}
- LLM_SERVICE_HOST_IP=${LLM_SERVICE_HOST_IP}
ipc: host
restart: always
chaqna-gaudi-ui-server:
image: ${REGISTRY:-opea}/chatqna-ui:${TAG:-latest}
container_name: chatqna-gaudi-ui-server
depends_on:
- chaqna-gaudi-backend-server
ports:
- "5173:5173"
environment:
- no_proxy=${no_proxy}
- https_proxy=${https_proxy}
- http_proxy=${http_proxy}
- CHAT_BASE_URL=${BACKEND_SERVICE_ENDPOINT}
- UPLOAD_FILE_BASE_URL=${DATAPREP_SERVICE_ENDPOINT}
- GET_FILE=${DATAPREP_GET_FILE_ENDPOINT}
- DELETE_FILE=${DATAPREP_DELETE_FILE_ENDPOINT}
ipc: host
restart: always
networks:
default:
driver: bridge

148
ChatQnA/docker/xeon/compose_without_rerank.yaml Normal file
View File

@@ -0,0 +1,148 @@
# Copyright (C) 2024 Intel Corporation
# SPDX-License-Identifier: Apache-2.0
services:
redis-vector-db:
image: redis/redis-stack:7.2.0-v9
container_name: redis-vector-db
ports:
- "6379:6379"
- "8001:8001"
dataprep-redis-service:
image: ${REGISTRY:-opea}/dataprep-redis:${TAG:-latest}
container_name: dataprep-redis-server
depends_on:
- redis-vector-db
- tei-embedding-service
ports:
- "6007:6007"
environment:
no_proxy: ${no_proxy}
http_proxy: ${http_proxy}
https_proxy: ${https_proxy}
REDIS_URL: ${REDIS_URL}
REDIS_HOST: ${REDIS_HOST}
INDEX_NAME: ${INDEX_NAME}
TEI_ENDPOINT: ${TEI_EMBEDDING_ENDPOINT}
HUGGINGFACEHUB_API_TOKEN: ${HUGGINGFACEHUB_API_TOKEN}
tei-embedding-service:
image: ghcr.io/huggingface/text-embeddings-inference:cpu-1.5
container_name: tei-embedding-server
ports:
- "6006:80"
volumes:
- "./data:/data"
shm_size: 1g
environment:
no_proxy: ${no_proxy}
http_proxy: ${http_proxy}
https_proxy: ${https_proxy}
command: --model-id ${EMBEDDING_MODEL_ID} --auto-truncate
embedding:
image: ${REGISTRY:-opea}/embedding-tei:${TAG:-latest}
container_name: embedding-tei-server
depends_on:
- tei-embedding-service
ports:
- "6000:6000"
ipc: host
environment:
no_proxy: ${no_proxy}
http_proxy: ${http_proxy}
https_proxy: ${https_proxy}
TEI_EMBEDDING_ENDPOINT: ${TEI_EMBEDDING_ENDPOINT}
restart: unless-stopped
retriever:
image: ${REGISTRY:-opea}/retriever-redis:${TAG:-latest}
container_name: retriever-redis-server
depends_on:
- redis-vector-db
ports:
- "7000:7000"
ipc: host
environment:
no_proxy: ${no_proxy}
http_proxy: ${http_proxy}
https_proxy: ${https_proxy}
REDIS_URL: ${REDIS_URL}
INDEX_NAME: ${INDEX_NAME}
TEI_EMBEDDING_ENDPOINT: ${TEI_EMBEDDING_ENDPOINT}
HUGGINGFACEHUB_API_TOKEN: ${HUGGINGFACEHUB_API_TOKEN}
restart: unless-stopped
tgi-service:
image: ghcr.io/huggingface/text-generation-inference:sha-e4201f4-intel-cpu
container_name: tgi-service
ports:
- "9009:80"
volumes:
- "./data:/data"
shm_size: 1g
environment:
no_proxy: ${no_proxy}
http_proxy: ${http_proxy}
https_proxy: ${https_proxy}
HF_TOKEN: ${HUGGINGFACEHUB_API_TOKEN}
HF_HUB_DISABLE_PROGRESS_BARS: 1
HF_HUB_ENABLE_HF_TRANSFER: 0
command: --model-id ${LLM_MODEL_ID} --cuda-graphs 0
llm:
image: ${REGISTRY:-opea}/llm-tgi:${TAG:-latest}
container_name: llm-tgi-server
depends_on:
- tgi-service
ports:
- "9000:9000"
ipc: host
environment:
no_proxy: ${no_proxy}
http_proxy: ${http_proxy}
https_proxy: ${https_proxy}
TGI_LLM_ENDPOINT: ${TGI_LLM_ENDPOINT}
HUGGINGFACEHUB_API_TOKEN: ${HUGGINGFACEHUB_API_TOKEN}
HF_HUB_DISABLE_PROGRESS_BARS: 1
HF_HUB_ENABLE_HF_TRANSFER: 0
restart: unless-stopped
chaqna-xeon-backend-server:
image: ${REGISTRY:-opea}/chatqna-without-rerank:${TAG:-latest}
container_name: chatqna-xeon-backend-server
depends_on:
- redis-vector-db
- tei-embedding-service
- embedding
- dataprep-redis-service
- retriever
- tgi-service
- llm
ports:
- "8888:8888"
environment:
- no_proxy=${no_proxy}
- https_proxy=${https_proxy}
- http_proxy=${http_proxy}
- MEGA_SERVICE_HOST_IP=${MEGA_SERVICE_HOST_IP}
- EMBEDDING_SERVICE_HOST_IP=${EMBEDDING_SERVICE_HOST_IP}
- RETRIEVER_SERVICE_HOST_IP=${RETRIEVER_SERVICE_HOST_IP}
- LLM_SERVICE_HOST_IP=${LLM_SERVICE_HOST_IP}
ipc: host
restart: always
chaqna-xeon-ui-server:
image: ${REGISTRY:-opea}/chatqna-ui:${TAG:-latest}
container_name: chatqna-xeon-ui-server
depends_on:
- chaqna-xeon-backend-server
ports:
- "5173:5173"
environment:
- no_proxy=${no_proxy}
- https_proxy=${https_proxy}
- http_proxy=${http_proxy}
- CHAT_BASE_URL=${BACKEND_SERVICE_ENDPOINT}
- UPLOAD_FILE_BASE_URL=${DATAPREP_SERVICE_ENDPOINT}
- GET_FILE=${DATAPREP_GET_FILE_ENDPOINT}
- DELETE_FILE=${DATAPREP_DELETE_FILE_ENDPOINT}
ipc: host
restart: always
networks:
default:
driver: bridge

253
ChatQnA/tests/test_chatqna_without_rerank_on_gaudi.sh Normal file
View File

@@ -0,0 +1,253 @@
#!/bin/bash
# Copyright (C) 2024 Intel Corporation
# SPDX-License-Identifier: Apache-2.0
set -e
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}
WORKPATH=$(dirname "$PWD")
LOG_PATH="$WORKPATH/tests"
ip_address=$(hostname -I | awk '{print $1}')
function build_docker_images() {
cd $WORKPATH/docker
git clone https://github.com/opea-project/GenAIComps.git
git clone https://github.com/huggingface/tei-gaudi
echo "Build all the images with --no-cache, check docker_image_build.log for details..."
service_list="chatqna-without-rerank chatqna-ui dataprep-redis embedding-tei retriever-redis llm-tgi tei-gaudi"
docker compose -f docker_build_compose.yaml build ${service_list} --no-cache > ${LOG_PATH}/docker_image_build.log
docker pull ghcr.io/huggingface/tgi-gaudi:2.0.1
docker pull ghcr.io/huggingface/text-embeddings-inference:cpu-1.5
docker images
}
function start_services() {
cd $WORKPATH/docker/gaudi
export EMBEDDING_MODEL_ID="BAAI/bge-base-en-v1.5"
export LLM_MODEL_ID="Intel/neural-chat-7b-v3-3"
export TEI_EMBEDDING_ENDPOINT="http://${ip_address}:8090"
export TGI_LLM_ENDPOINT="http://${ip_address}:8005"
export REDIS_URL="redis://${ip_address}:6379"
export REDIS_HOST=${ip_address}
export INDEX_NAME="rag-redis"
export HUGGINGFACEHUB_API_TOKEN=${HUGGINGFACEHUB_API_TOKEN}
export MEGA_SERVICE_HOST_IP=${ip_address}
export EMBEDDING_SERVICE_HOST_IP=${ip_address}
export RETRIEVER_SERVICE_HOST_IP=${ip_address}
export LLM_SERVICE_HOST_IP=${ip_address}
export BACKEND_SERVICE_ENDPOINT="http://${ip_address}:8888/v1/chatqna"
export DATAPREP_SERVICE_ENDPOINT="http://${ip_address}:6007/v1/dataprep"
export DATAPREP_GET_FILE_ENDPOINT="http://${ip_address}:6008/v1/dataprep/get_file"
export DATAPREP_DELETE_FILE_ENDPOINT="http://${ip_address}:6009/v1/dataprep/delete_file"
sed -i "s/backend_address/$ip_address/g" $WORKPATH/docker/ui/svelte/.env
# Start Docker Containers
docker compose -f compose_without_rerank.yaml up -d
n=0
until [[ "$n" -ge 400 ]]; do
docker logs tgi-gaudi-server > ${LOG_PATH}/tgi_service_start.log
if grep -q Connected ${LOG_PATH}/tgi_service_start.log; then
break
fi
sleep 1s
n=$((n+1))
done
}
function validate_service() {
local URL="$1"
local EXPECTED_RESULT="$2"
local SERVICE_NAME="$3"
local DOCKER_NAME="$4"
local INPUT_DATA="$5"
if [[ $SERVICE_NAME == *"dataprep_upload_file"* ]]; then
cd $LOG_PATH
HTTP_RESPONSE=$(curl --silent --write-out "HTTPSTATUS:%{http_code}" -X POST -F 'files=@./dataprep_file.txt' -H 'Content-Type: multipart/form-data' "$URL")
elif [[ $SERVICE_NAME == *"dataprep_upload_link"* ]]; then
HTTP_RESPONSE=$(curl --silent --write-out "HTTPSTATUS:%{http_code}" -X POST -F 'link_list=["https://www.ces.tech/"]' "$URL")
elif [[ $SERVICE_NAME == *"dataprep_get"* ]]; then
HTTP_RESPONSE=$(curl --silent --write-out "HTTPSTATUS:%{http_code}" -X POST -H 'Content-Type: application/json' "$URL")
elif [[ $SERVICE_NAME == *"dataprep_del"* ]]; then
HTTP_RESPONSE=$(curl --silent --write-out "HTTPSTATUS:%{http_code}" -X POST -d '{"file_path": "all"}' -H 'Content-Type: application/json' "$URL")
else
HTTP_RESPONSE=$(curl --silent --write-out "HTTPSTATUS:%{http_code}" -X POST -d "$INPUT_DATA" -H 'Content-Type: application/json' "$URL")
fi
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?"}'
# embedding microservice
validate_service \
"${ip_address}:6000/v1/embeddings" \
'"text":"What is Deep Learning?","embedding":[' \
"embedding-microservice" \
"embedding-tei-server" \
'{"text":"What is Deep Learning?"}'
sleep 1m # retrieval can't curl as expected, try to wait for more time
# test /v1/dataprep upload file
echo "Deep learning is a subset of machine learning that utilizes neural networks with multiple layers to analyze various levels of abstract data representations. It enables computers to identify patterns and make decisions with minimal human intervention by learning from large amounts of data." > $LOG_PATH/dataprep_file.txt
validate_service \
"http://${ip_address}:6007/v1/dataprep" \
"Data preparation succeeded" \
"dataprep_upload_file" \
"dataprep-redis-server"
# test /v1/dataprep upload link
validate_service \
"http://${ip_address}:6007/v1/dataprep" \
"Data preparation succeeded" \
"dataprep_upload_link" \
"dataprep-redis-server"
# test /v1/dataprep/get_file
validate_service \
"http://${ip_address}:6007/v1/dataprep/get_file" \
'{"name":' \
"dataprep_get" \
"dataprep-redis-server"
# test /v1/dataprep/delete_file
validate_service \
"http://${ip_address}:6007/v1/dataprep/delete_file" \
'{"status":true}' \
"dataprep_del" \
"dataprep-redis-server"
# retrieval microservice
test_embedding=$(python3 -c "import random; embedding = [random.uniform(-1, 1) for _ in range(768)]; print(embedding)")
validate_service \
"${ip_address}:7000/v1/retrieval" \
"retrieved_docs" \
"retrieval-microservice" \
"retriever-redis-server" \
"{\"text\":\"What is the revenue of Nike in 2023?\",\"embedding\":${test_embedding}}"
# tgi for llm service
validate_service \
"${ip_address}:8005/generate" \
"generated_text" \
"tgi-llm" \
"tgi-gaudi-server" \
'{"inputs":"What is Deep Learning?","parameters":{"max_new_tokens":17, "do_sample": true}}'
# llm microservice
validate_service \
"${ip_address}:9000/v1/chat/completions" \
"data: " \
"llm-microservice" \
"llm-tgi-gaudi-server" \
'{"query":"What is Deep Learning?"}'
}
function validate_megaservice() {
# Curl the Mega Service
validate_service \
"${ip_address}:8888/v1/chatqna" \
"data: " \
"chatqna-megaservice" \
"chatqna-gaudi-backend-server" \
'{"messages": "What is the revenue of Nike in 2023?"}'
}
function validate_frontend() {
cd $WORKPATH/docker/ui/svelte
local conda_env_name="OPEA_e2e"
export PATH=${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 $WORKPATH/docker/gaudi
docker compose -f compose_without_rerank.yaml stop && docker compose -f compose_without_rerank.yaml rm -f
}
function main() {
stop_docker
if [[ "$IMAGE_REPO" == "opea" ]]; then build_docker_images; fi
start_time=$(date +%s)
start_services
end_time=$(date +%s)
duration=$((end_time-start_time))
echo "Mega service start duration is $duration s"
if [ "${mode}" == "perf" ]; then
python3 $WORKPATH/tests/chatqna_benchmark.py
elif [ "${mode}" == "" ]; then
validate_microservices
validate_megaservice
validate_frontend
fi
stop_docker
echo y | docker system prune
}
main

257
ChatQnA/tests/test_chatqna_without_rerank_on_xeon.sh Normal file
View File

@@ -0,0 +1,257 @@
#!/bin/bash
# Copyright (C) 2024 Intel Corporation
# SPDX-License-Identifier: Apache-2.0
set -e
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}
WORKPATH=$(dirname "$PWD")
LOG_PATH="$WORKPATH/tests"
ip_address=$(hostname -I | awk '{print $1}')
function build_docker_images() {
cd $WORKPATH/docker
git clone https://github.com/opea-project/GenAIComps.git
echo "Build all the images with --no-cache, check docker_image_build.log for details..."
service_list="chatqna-without-rerank chatqna-ui chatqna-conversation-ui dataprep-redis embedding-tei retriever-redis llm-tgi"
docker compose -f docker_build_compose.yaml build ${service_list} --no-cache > ${LOG_PATH}/docker_image_build.log
docker pull ghcr.io/huggingface/tgi-gaudi:2.0.1
docker pull ghcr.io/huggingface/text-embeddings-inference:cpu-1.5
docker images
}
function start_services() {
cd $WORKPATH/docker/xeon
export EMBEDDING_MODEL_ID="BAAI/bge-base-en-v1.5"
export LLM_MODEL_ID="Intel/neural-chat-7b-v3-3"
export TEI_EMBEDDING_ENDPOINT="http://${ip_address}:6006"
export TGI_LLM_ENDPOINT="http://${ip_address}:9009"
export REDIS_URL="redis://${ip_address}:6379"
export REDIS_HOST=${ip_address}
export INDEX_NAME="rag-redis"
export HUGGINGFACEHUB_API_TOKEN=${HUGGINGFACEHUB_API_TOKEN}
export MEGA_SERVICE_HOST_IP=${ip_address}
export EMBEDDING_SERVICE_HOST_IP=${ip_address}
export RETRIEVER_SERVICE_HOST_IP=${ip_address}
export LLM_SERVICE_HOST_IP=${ip_address}
export BACKEND_SERVICE_ENDPOINT="http://${ip_address}:8888/v1/chatqna"
export DATAPREP_SERVICE_ENDPOINT="http://${ip_address}:6007/v1/dataprep"
export DATAPREP_GET_FILE_ENDPOINT="http://${ip_address}:6007/v1/dataprep/get_file"
export DATAPREP_DELETE_FILE_ENDPOINT="http://${ip_address}:6007/v1/dataprep/delete_file"
sed -i "s/backend_address/$ip_address/g" $WORKPATH/docker/ui/svelte/.env
# Start Docker Containers
docker compose -f compose_without_rerank.yaml up -d
n=0
until [[ "$n" -ge 500 ]]; do
docker logs tgi-service > ${LOG_PATH}/tgi_service_start.log
if grep -q Connected ${LOG_PATH}/tgi_service_start.log; then
break
fi
sleep 1s
n=$((n+1))
done
}
function validate_service() {
local URL="$1"
local EXPECTED_RESULT="$2"
local SERVICE_NAME="$3"
local DOCKER_NAME="$4"
local INPUT_DATA="$5"
if [[ $SERVICE_NAME == *"dataprep_upload_file"* ]]; then
cd $LOG_PATH
HTTP_RESPONSE=$(curl --silent --write-out "HTTPSTATUS:%{http_code}" -X POST -F 'files=@./dataprep_file.txt' -H 'Content-Type: multipart/form-data' "$URL")
elif [[ $SERVICE_NAME == *"dataprep_upload_link"* ]]; then
HTTP_RESPONSE=$(curl --silent --write-out "HTTPSTATUS:%{http_code}" -X POST -F 'link_list=["https://www.ces.tech/"]' "$URL")
elif [[ $SERVICE_NAME == *"dataprep_get"* ]]; then
HTTP_RESPONSE=$(curl --silent --write-out "HTTPSTATUS:%{http_code}" -X POST -H 'Content-Type: application/json' "$URL")
elif [[ $SERVICE_NAME == *"dataprep_del"* ]]; then
HTTP_RESPONSE=$(curl --silent --write-out "HTTPSTATUS:%{http_code}" -X POST -d '{"file_path": "all"}' -H 'Content-Type: application/json' "$URL")
else
HTTP_RESPONSE=$(curl --silent --write-out "HTTPSTATUS:%{http_code}" -X POST -d "$INPUT_DATA" -H 'Content-Type: application/json' "$URL")
fi
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}:6006/embed" \
"[[" \
"tei-embedding" \
"tei-embedding-server" \
'{"inputs":"What is Deep Learning?"}'
# embedding microservice
validate_service \
"${ip_address}:6000/v1/embeddings" \
'"text":"What is Deep Learning?","embedding":[' \
"embedding-microservice" \
"embedding-tei-server" \
'{"text":"What is Deep Learning?"}'
sleep 1m # retrieval can't curl as expected, try to wait for more time
# test /v1/dataprep upload file
echo "Deep learning is a subset of machine learning that utilizes neural networks with multiple layers to analyze various levels of abstract data representations. It enables computers to identify patterns and make decisions with minimal human intervention by learning from large amounts of data." > $LOG_PATH/dataprep_file.txt
validate_service \
"http://${ip_address}:6007/v1/dataprep" \
"Data preparation succeeded" \
"dataprep_upload_file" \
"dataprep-redis-server"
# test /v1/dataprep upload link
validate_service \
"http://${ip_address}:6007/v1/dataprep" \
"Data preparation succeeded" \
"dataprep_upload_link" \
"dataprep-redis-server"
# test /v1/dataprep/get_file
validate_service \
"http://${ip_address}:6007/v1/dataprep/get_file" \
'{"name":' \
"dataprep_get" \
"dataprep-redis-server"
# test /v1/dataprep/delete_file
validate_service \
"http://${ip_address}:6007/v1/dataprep/delete_file" \
'{"status":true}' \
"dataprep_del" \
"dataprep-redis-server"
# retrieval microservice
test_embedding=$(python3 -c "import random; embedding = [random.uniform(-1, 1) for _ in range(768)]; print(embedding)")
validate_service \
"${ip_address}:7000/v1/retrieval" \
"retrieved_docs" \
"retrieval-microservice" \
"retriever-redis-server" \
"{\"text\":\"What is the revenue of Nike in 2023?\",\"embedding\":${test_embedding}}"
# tgi for llm service
validate_service \
"${ip_address}:9009/generate" \
"generated_text" \
"tgi-llm" \
"tgi-service" \
'{"inputs":"What is Deep Learning?","parameters":{"max_new_tokens":17, "do_sample": true}}'
# llm microservice
validate_service \
"${ip_address}:9000/v1/chat/completions" \
"data: " \
"llm-microservice" \
"llm-tgi-server" \
'{"query":"What is Deep Learning?"}'
}
function validate_megaservice() {
# Curl the Mega Service
validate_service \
"${ip_address}:8888/v1/chatqna" \
"data: " \
"chatqna-megaservice" \
"chatqna-xeon-backend-server" \
'{"messages": "What is the revenue of Nike in 2023?"}'
}
function validate_frontend() {
echo "[ TEST INFO ]: --------- frontend test started ---------"
cd $WORKPATH/docker/ui/svelte
local conda_env_name="OPEA_e2e"
export PATH=${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 ${conda_env_name}
echo "[ TEST INFO ]: --------- conda env activated ---------"
sed -i "s/localhost/$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 $WORKPATH/docker/xeon
docker compose -f compose_without_rerank.yaml stop && docker compose -f compose_without_rerank.yaml rm -f
}
function main() {
stop_docker
if [[ "$IMAGE_REPO" == "opea" ]]; then build_docker_images; fi
start_time=$(date +%s)
start_services
end_time=$(date +%s)
duration=$((end_time-start_time))
echo "Mega service start duration is $duration s" && sleep 1s
if [ "${mode}" == "perf" ]; then
python3 $WORKPATH/tests/chatqna_benchmark.py
elif [ "${mode}" == "" ]; then
validate_microservices
echo "==== microservices validated ===="
validate_megaservice
echo "==== megaservice validated ===="
validate_frontend
echo "==== frontend validated ===="
fi
stop_docker
echo y | docker system prune
}
main