Integrate DocSum set_env to ut scripts. (#1860)

ZePan110 · web-flow · commit 99b62ae49e76 · 2025-04-28T13:35:05.000+08:00
Integrate DocSum set_env to ut scripts.
Add README.md for DocSum and InstructionTuning UT scripts.

Signed-off-by: ZePan110 &lt;ze.pan@intel.com&gt;
diff --git a/DocSum/docker_compose/amd/gpu/rocm/set_env.sh b/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=''
+export HOST_IP=${ip_address}
 export DOCSUM_MAX_INPUT_TOKENS="2048"
 export DOCSUM_MAX_TOTAL_TOKENS="4096"
 export DOCSUM_LLM_MODEL_ID="Intel/neural-chat-7b-v3-3"
diff --git a/DocSum/docker_compose/amd/gpu/rocm/set_env_vllm.sh b/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=''
+export HOST_IP=${ip_address}
 export DOCSUM_HUGGINGFACEHUB_API_TOKEN=${HUGGINGFACEHUB_API_TOKEN}
 export DOCSUM_MAX_INPUT_TOKENS=2048
 export DOCSUM_MAX_TOTAL_TOKENS=4096
diff --git a/DocSum/docker_compose/set_env.sh b/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 $1}') # Example: host_ip="192.168.1.1"
-export HUGGINGFACEHUB_API_TOKEN="Your_Huggingface_API_Token"
+export HUGGINGFACEHUB_API_TOKEN=${HUGGINGFACEHUB_API_TOKEN}
 
 export LLM_ENDPOINT_PORT=8008
 export LLM_MODEL_ID="Intel/neural-chat-7b-v3-3"
@@ -20,10 +20,12 @@ 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
diff --git a/DocSum/tests/README.md b/DocSum/tests/README.md
@@ -0,0 +1,45 @@
+# 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
+```
diff --git a/DocSum/tests/test_compose_on_gaudi.sh b/DocSum/tests/test_compose_on_gaudi.sh
@@ -10,35 +10,22 @@ 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}
-export HUGGINGFACEHUB_API_TOKEN=${HUGGINGFACEHUB_API_TOKEN}
-export LLM_ENDPOINT_PORT=8008
-export LLM_MODEL_ID="Intel/neural-chat-7b-v3-3"
+source $WORKPATH/docker_compose/set_env.sh
+
+export MODEL_CACHE=${model_cache:-"./data"}
+
 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 "$0")")
diff --git a/DocSum/tests/test_compose_on_rocm.sh b/DocSum/tests/test_compose_on_rocm.sh
@@ -14,21 +14,8 @@ export MODEL_CACHE=${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=${ip_address}
-export DOCSUM_MAX_INPUT_TOKENS="2048"
-export DOCSUM_MAX_TOTAL_TOKENS="4096"
-export DOCSUM_LLM_MODEL_ID="Intel/neural-chat-7b-v3-3"
-export DOCSUM_TGI_SERVICE_PORT="8008"
-export DOCSUM_TGI_LLM_ENDPOINT="http://${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"
+source $WORKPATH/docker_compose/amd/gpu/rocm/set_env.sh
 
 function build_docker_images() {
     opea_branch=${opea_branch:-"main"}
@@ -129,23 +116,23 @@ function validate_microservices() {
     # whisper microservice
     ulimit -s 65536
     validate_services \
-        "${host_ip}:${DOCSUM_WHISPER_PORT}/v1/asr" \
+        "${HOST_IP}:${DOCSUM_WHISPER_PORT}/v1/asr" \
         '{"asr_result":"well"}' \
         "whisper-service" \
         "whisper-service" \
         "{\"audio\": \"$(input_data_for_test "audio")\"}"
 
     # 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" \
         '{"inputs":"What is Deep Learning?","parameters":{"max_new_tokens":17, "do_sample": true}}'
 
     # 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" \
@@ -158,7 +145,7 @@ 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")
@@ -188,23 +175,23 @@ 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" \
         '{"type": "text", "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."}'
 
     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" \
         "{\"type\": \"audio\",  \"messages\": \"$(input_data_for_test "audio")\"}"
 
     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" \
diff --git a/DocSum/tests/test_compose_on_xeon.sh b/DocSum/tests/test_compose_on_xeon.sh
@@ -10,30 +10,18 @@ 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}
-export HUGGINGFACEHUB_API_TOKEN=${HUGGINGFACEHUB_API_TOKEN}
-export LLM_ENDPOINT_PORT=8008
-export LLM_MODEL_ID="Intel/neural-chat-7b-v3-3"
+
+source $WORKPATH/docker_compose/set_env.sh
+export MODEL_CACHE=${model_cache:-"./data"}
+
 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 "$0")")
diff --git a/DocSum/tests/test_compose_tgi_on_gaudi.sh b/DocSum/tests/test_compose_tgi_on_gaudi.sh
@@ -9,32 +9,20 @@ IMAGE_TAG=${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=${IMAGE_TAG}
-export HUGGINGFACEHUB_API_TOKEN=${HUGGINGFACEHUB_API_TOKEN}
-export LLM_ENDPOINT_PORT=8008
-export LLM_MODEL_ID="Intel/neural-chat-7b-v3-3"
+
+source $WORKPATH/docker_compose/set_env.sh
+export MODEL_CACHE=${model_cache:-"./data"}
+
 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"
 
+export DocSum_COMPONENT_NAME="OpeaDocSumTgi"
 
 # Get the root folder of the current script
 ROOT_FOLDER=$(dirname "$(readlink -f "$0")")
diff --git a/DocSum/tests/test_compose_tgi_on_xeon.sh b/DocSum/tests/test_compose_tgi_on_xeon.sh
@@ -9,31 +9,20 @@ IMAGE_TAG=${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=${IMAGE_TAG}
-export HUGGINGFACEHUB_API_TOKEN=${HUGGINGFACEHUB_API_TOKEN}
-export LLM_ENDPOINT_PORT=8008
-export LLM_MODEL_ID="Intel/neural-chat-7b-v3-3"
+
+source $WORKPATH/docker_compose/set_env.sh
+export MODEL_CACHE=${model_cache:-"./data"}
+
 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"
+export DocSum_COMPONENT_NAME="OpeaDocSumTgi"
 
 # Get the root folder of the current script
 ROOT_FOLDER=$(dirname "$(readlink -f "$0")")
diff --git a/DocSum/tests/test_compose_vllm_on_rocm.sh b/DocSum/tests/test_compose_vllm_on_rocm.sh
diff --git a/InstructionTuning/tests/README.md b/InstructionTuning/tests/README.md
