Fix InstructionTuning and RerankFinetuning tests (opea-project#785)

Signed-off-by: Ye, Xinyu <xinyu.ye@intel.com>

Author: XinyuYe-Intel

InstructionTuning/tests/test_compose_on_xeon.sh

@@ -2,7 +2,7 @@
 # Copyright (C) 2024 Intel Corporation
 # SPDX-License-Identifier: Apache-2.0
 
-set -ex
+set -x
 
 WORKPATH=$(dirname "$PWD")
 LOG_PATH="$WORKPATH/tests"
@@ -12,8 +12,11 @@ ray_port=8265
 
 function build_docker_images() {
     cd $WORKPATH
-    echo $(pwd)
-    git clone https://github.com/opea-project/GenAIComps.git && cd GenAIComps && git checkout "${opea_branch:-"main"}"
+    if [ ! -d "GenAIComps" ] ; then
+        git clone https://github.com/opea-project/GenAIComps.git
+    fi
+    cd GenAIComps
+    echo PWD: $(pwd)
     docker build -t opea/finetuning:latest --build-arg https_proxy=$https_proxy --build-arg http_proxy=$http_proxy --build-arg HF_TOKEN=$HF_TOKEN -f comps/finetuning/Dockerfile .
     if [ $? -ne 0 ]; then
         echo "opea/finetuning built fail"
@@ -34,21 +37,30 @@ function validate_microservice() {
     export no_proxy="localhost,127.0.0.1,"${ip_address}
 
     # test /v1/dataprep upload file
-    URL="http://${ip_address}:$finetuning_service_port/v1/finetune/upload_training_files"
+    URL="http://${ip_address}:$finetuning_service_port/v1/files"
     echo '[{"instruction": "Give three tips for staying healthy.", "input": "", "output": "1.Eat a balanced diet and make sure to include plenty of fruits and vegetables. \n2. Exercise regularly to keep your body active and strong. \n3. Get enough sleep and maintain a consistent sleep schedule."},{"instruction": "Give three tips for staying healthy.", "input": "", "output": "1.Eat a balanced diet and make sure to include plenty of fruits and vegetables. \n2. Exercise regularly to keep your body active and strong. \n3. Get enough sleep and maintain a consistent sleep schedule."},{"instruction": "Give three tips for staying healthy.", "input": "", "output": "1.Eat a balanced diet and make sure to include plenty of fruits and vegetables. \n2. Exercise regularly to keep your body active and strong. \n3. Get enough sleep and maintain a consistent sleep schedule."},{"instruction": "Give three tips for staying healthy.", "input": "", "output": "1.Eat a balanced diet and make sure to include plenty of fruits and vegetables. \n2. Exercise regularly to keep your body active and strong. \n3. Get enough sleep and maintain a consistent sleep schedule."},{"instruction": "Give three tips for staying healthy.", "input": "", "output": "1.Eat a balanced diet and make sure to include plenty of fruits and vegetables. \n2. Exercise regularly to keep your body active and strong. \n3. Get enough sleep and maintain a consistent sleep schedule."},{"instruction": "Give three tips for staying healthy.", "input": "", "output": "1.Eat a balanced diet and make sure to include plenty of fruits and vegetables. \n2. Exercise regularly to keep your body active and strong. \n3. Get enough sleep and maintain a consistent sleep schedule."},{"instruction": "Give three tips for staying healthy.", "input": "", "output": "1.Eat a balanced diet and make sure to include plenty of fruits and vegetables. \n2. Exercise regularly to keep your body active and strong. \n3. Get enough sleep and maintain a consistent sleep schedule."},{"instruction": "Give three tips for staying healthy.", "input": "", "output": "1.Eat a balanced diet and make sure to include plenty of fruits and vegetables. \n2. Exercise regularly to keep your body active and strong. \n3. Get enough sleep and maintain a consistent sleep schedule."},{"instruction": "Give three tips for staying healthy.", "input": "", "output": "1.Eat a balanced diet and make sure to include plenty of fruits and vegetables. \n2. Exercise regularly to keep your body active and strong. \n3. Get enough sleep and maintain a consistent sleep schedule."},{"instruction": "Give three tips for staying healthy.", "input": "", "output": "1.Eat a balanced diet and make sure to include plenty of fruits and vegetables. \n2. Exercise regularly to keep your body active and strong. \n3. Get enough sleep and maintain a consistent sleep schedule."},{"instruction": "Give three tips for staying healthy.", "input": "", "output": "1.Eat a balanced diet and make sure to include plenty of fruits and vegetables. \n2. Exercise regularly to keep your body active and strong. \n3. Get enough sleep and maintain a consistent sleep schedule."},{"instruction": "Give three tips for staying healthy.", "input": "", "output": "1.Eat a balanced diet and make sure to include plenty of fruits and vegetables. \n2. Exercise regularly to keep your body active and strong. \n3. Get enough sleep and maintain a consistent sleep schedule."},{"instruction": "Give three tips for staying healthy.", "input": "", "output": "1.Eat a balanced diet and make sure to include plenty of fruits and vegetables. \n2. Exercise regularly to keep your body active and strong. \n3. Get enough sleep and maintain a consistent sleep schedule."},{"instruction": "Give three tips for staying healthy.", "input": "", "output": "1.Eat a balanced diet and make sure to include plenty of fruits and vegetables. \n2. Exercise regularly to keep your body active and strong. \n3. Get enough sleep and maintain a consistent sleep schedule."},{"instruction": "Give three tips for staying healthy.", "input": "", "output": "1.Eat a balanced diet and make sure to include plenty of fruits and vegetables. \n2. Exercise regularly to keep your body active and strong. \n3. Get enough sleep and maintain a consistent sleep schedule."},{"instruction": "Give three tips for staying healthy.", "input": "", "output": "1.Eat a balanced diet and make sure to include plenty of fruits and vegetables. \n2. Exercise regularly to keep your body active and strong. \n3. Get enough sleep and maintain a consistent sleep schedule."},{"instruction": "Give three tips for staying healthy.", "input": "", "output": "1.Eat a balanced diet and make sure to include plenty of fruits and vegetables. \n2. Exercise regularly to keep your body active and strong. \n3. Get enough sleep and maintain a consistent sleep schedule."},{"instruction": "Give three tips for staying healthy.", "input": "", "output": "1.Eat a balanced diet and make sure to include plenty of fruits and vegetables. \n2. Exercise regularly to keep your body active and strong. \n3. Get enough sleep and maintain a consistent sleep schedule."},{"instruction": "Give three tips for staying healthy.", "input": "", "output": "1.Eat a balanced diet and make sure to include plenty of fruits and vegetables. \n2. Exercise regularly to keep your body active and strong. \n3. Get enough sleep and maintain a consistent sleep schedule."},{"instruction": "Give three tips for staying healthy.", "input": "", "output": "1.Eat a balanced diet and make sure to include plenty of fruits and vegetables. \n2. Exercise regularly to keep your body active and strong. \n3. Get enough sleep and maintain a consistent sleep schedule."}]' > $LOG_PATH/test_data.json
-    HTTP_RESPONSE=$(curl --silent --write-out "HTTPSTATUS:%{http_code}" -X POST -F 'files=@./test_data.json' -H 'Content-Type: multipart/form-data' "$URL")
+    HTTP_RESPONSE=$(curl --silent --write-out "HTTPSTATUS:%{http_code}" -X POST -F 'file=@./test_data.json' -F purpose="fine-tune" -H 'Content-Type: multipart/form-data' "$URL")
     HTTP_STATUS=$(echo $HTTP_RESPONSE | tr -d '\n' | sed -e 's/.*HTTPSTATUS://')
     RESPONSE_BODY=$(echo $HTTP_RESPONSE | sed -e 's/HTTPSTATUS\:.*//g')
     SERVICE_NAME="finetuning-server - upload - file"
 
+    # Parse the JSON response
+    purpose=$(echo "$RESPONSE_BODY" | jq -r '.purpose')
+    filename=$(echo "$RESPONSE_BODY" | jq -r '.filename')
+
+    # Define expected values
+    expected_purpose="fine-tune"
+    expected_filename="test_data.json"
+
     if [ "$HTTP_STATUS" -ne "200" ]; then
         echo "[ $SERVICE_NAME ] HTTP status is not 200. Received status was $HTTP_STATUS"
         docker logs finetuning-server >> ${LOG_PATH}/finetuning-server_upload_file.log
         exit 1
     else
         echo "[ $SERVICE_NAME ] HTTP status is 200. Checking content..."
     fi
-    if [[ "$RESPONSE_BODY" != *"Training files uploaded"* ]]; then
+    # Check if the parsed values match the expected values
+    if [[ "$purpose" != "$expected_purpose" || "$filename" != "$expected_filename" ]]; then
         echo "[ $SERVICE_NAME ] Content does not match the expected result: $RESPONSE_BODY"
         docker logs finetuning-server >> ${LOG_PATH}/finetuning-server_upload_file.log
         exit 1

RerankFinetuning/tests/test_compose_on_xeon.sh

@@ -1,8 +1,7 @@
-#!/bin/bash
 # Copyright (C) 2024 Intel Corporation
 # SPDX-License-Identifier: Apache-2.0
 
-set -ex
+set -x
 
 WORKPATH=$(dirname "$PWD")
 LOG_PATH="$WORKPATH/tests"
@@ -12,9 +11,18 @@ ray_port=8265
 
 function build_docker_images() {
     cd $WORKPATH
-    echo $(pwd)
-    git clone https://github.com/opea-project/GenAIComps.git && cd GenAIComps && git checkout "${opea_branch:-"main"}"
+    if [ ! -d "GenAIComps" ] ; then
+        git clone https://github.com/opea-project/GenAIComps.git
+    fi
+    cd GenAIComps
+    echo PWD: $(pwd)
     docker build -t opea/finetuning:latest --build-arg https_proxy=$https_proxy --build-arg http_proxy=$http_proxy --build-arg HF_TOKEN=$HF_TOKEN -f comps/finetuning/Dockerfile .
+    if [ $? -ne 0 ]; then
+        echo "opea/finetuning built fail"
+        exit 1
+    else
+        echo "opea/finetuning built successful"
+    fi
 }
 
 function start_service() {
@@ -28,7 +36,7 @@ function validate_microservice() {
     export no_proxy="localhost,127.0.0.1,"${ip_address}
 
     # test /v1/dataprep upload file
-    URL="http://${ip_address}:$finetuning_service_port/v1/finetune/upload_training_files"
+    URL="http://${ip_address}:$finetuning_service_port/v1/files"
     cat <<EOF > test_data.json
 {"query": "Five women walk along a beach wearing flip-flops.", "pos": ["Some women with flip-flops on, are walking along the beach"], "neg": ["The 4 women are sitting on the beach.", "There was a reform in 1996.", "She's not going to court to clear her record.", "The man is talking about hawaii.", "A woman is standing outside.", "The battle was over. ", "A group of people plays volleyball."]}
 {"query": "A woman standing on a high cliff on one leg looking over a river.", "pos": ["A woman is standing on a cliff."], "neg": ["A woman sits on a chair.", "George Bush told the Republicans there was no way he would let them even consider this foolish idea, against his top advisors advice.", "The family was falling apart.", "no one showed up to the meeting", "A boy is sitting outside playing in the sand.", "Ended as soon as I received the wire.", "A child is reading in her bedroom."]}
@@ -37,19 +45,28 @@ function validate_microservice() {
 {"query": "A yellow dog running along a forest path.", "pos": ["a dog is running"], "neg": ["a cat is running", "Steele did not keep her original story.", "The rule discourages people to pay their child support.", "A man in a vest sits in a car.", "Person in black clothing, with white bandanna and sunglasses waits at a bus stop.", "Neither the Globe or Mail had comments on the current state of Canada's road system. ", "The Spring Creek facility is old and outdated."]}
 {"query": "It sets out essential activities in each phase along with critical factors related to those activities.", "pos": ["Critical factors for essential activities are set out."], "neg": ["It lays out critical activities but makes no provision for critical factors related to those activities.", "People are assembled in protest.", "The state would prefer for you to do that.", "A girl sits beside a boy.", "Two males are performing.", "Nobody is jumping", "Conrad was being plotted against, to be hit on the head."]}
 EOF
-    HTTP_RESPONSE=$(curl --silent --write-out "HTTPSTATUS:%{http_code}" -X POST -F 'files=@./test_data.json' -H 'Content-Type: multipart/form-data' "$URL")
+    HTTP_RESPONSE=$(curl --silent --write-out "HTTPSTATUS:%{http_code}" -X POST -F 'file=@./test_data.json' -F purpose="fine-tune" -H 'Content-Type: multipart/form-data' "$URL")
     HTTP_STATUS=$(echo $HTTP_RESPONSE | tr -d '\n' | sed -e 's/.*HTTPSTATUS://')
     RESPONSE_BODY=$(echo $HTTP_RESPONSE | sed -e 's/HTTPSTATUS\:.*//g')
     SERVICE_NAME="finetuning-server - upload - file"
 
+    # Parse the JSON response
+    purpose=$(echo "$RESPONSE_BODY" | jq -r '.purpose')
+    filename=$(echo "$RESPONSE_BODY" | jq -r '.filename')
+
+    # Define expected values
+    expected_purpose="fine-tune"
+    expected_filename="test_data.json"
+
     if [ "$HTTP_STATUS" -ne "200" ]; then
         echo "[ $SERVICE_NAME ] HTTP status is not 200. Received status was $HTTP_STATUS"
         docker logs finetuning-server >> ${LOG_PATH}/finetuning-server_upload_file.log
         exit 1
     else
         echo "[ $SERVICE_NAME ] HTTP status is 200. Checking content..."
     fi
-    if [[ "$RESPONSE_BODY" != *"Training files uploaded"* ]]; then
+    # Check if the parsed values match the expected values
+    if [[ "$purpose" != "$expected_purpose" || "$filename" != "$expected_filename" ]]; then
         echo "[ $SERVICE_NAME ] Content does not match the expected result: $RESPONSE_BODY"
         docker logs finetuning-server >> ${LOG_PATH}/finetuning-server_upload_file.log
         exit 1
@@ -59,7 +76,7 @@ EOF
 
     # test /v1/fine_tuning/jobs
     URL="http://${ip_address}:$finetuning_service_port/v1/fine_tuning/jobs"
-    HTTP_RESPONSE=$(curl --silent --write-out "HTTPSTATUS:%{http_code}" -X POST -H 'Content-Type: application/json' -d '{"training_file": "test_data.json","model": "BAAI/bge-reranker-base"}' "$URL")
+    HTTP_RESPONSE=$(curl --silent --write-out "HTTPSTATUS:%{http_code}" -X POST -H 'Content-Type: application/json' -d '{"training_file": "test_data.json","model": "BAAI/bge-reranker-base","General":{"task":"rerank","lora_config":null}}' "$URL")
     HTTP_STATUS=$(echo $HTTP_RESPONSE | tr -d '\n' | sed -e 's/.*HTTPSTATUS://')
     RESPONSE_BODY=$(echo $HTTP_RESPONSE | sed -e 's/HTTPSTATUS\:.*//g')
     SERVICE_NAME="finetuning-server - create finetuning job"
@@ -79,7 +96,7 @@ EOF
         echo "[ $SERVICE_NAME ] Content is as expected."
     fi
 
-    sleep 3m
+    sleep 10m
 }
 
 function stop_docker() {