increase timeout 10s to 60s

Signed-off-by: ZePan110 <ze.pan@intel.com>

ChatQnA/docker_compose/intel/hpu/gaudi/compose_faqgen.yaml

@@ -102,7 +102,7 @@ services:
     healthcheck:
       test: ["CMD-SHELL", "curl -f http://${host_ip}:${LLM_ENDPOINT_PORT}/health || exit 1"]
       interval: 10s
-      timeout: 10s
+      timeout: 60s
       retries: 100
     runtime: habana
     cap_add:

ChatQnA/docker_compose/intel/hpu/gaudi/set_env.sh

@@ -4,12 +4,20 @@
 # SPDX-License-Identifier: Apache-2.0
 
 # Function to prompt for input and set environment variables
+NON_INTERACTIVE=${NON_INTERACTIVE:-false}
+
 prompt_for_env_var() {
   local var_name="$1"
   local prompt_message="$2"
   local default_value="$3"
   local mandatory="$4"
 
+  if [[ "$NON_INTERACTIVE" == "true" ]]; then
+    echo "Non-interactive environment detected. Setting $var_name to default: $default_value"
+    export "$var_name"="$default_value"
+    return
+  fi
+
   if [[ "$mandatory" == "true" ]]; then
     while [[ -z "$value" ]]; do
       read -p "$prompt_message [default: \"${default_value}\"]: " value
@@ -34,7 +42,7 @@ popd > /dev/null
 
 # Prompt the user for each required environment variable
 prompt_for_env_var "EMBEDDING_MODEL_ID" "Enter the EMBEDDING_MODEL_ID" "BAAI/bge-base-en-v1.5" false
-prompt_for_env_var "HUGGINGFACEHUB_API_TOKEN" "Enter the HUGGINGFACEHUB_API_TOKEN" "" true
+prompt_for_env_var "HUGGINGFACEHUB_API_TOKEN" "Enter the HUGGINGFACEHUB_API_TOKEN" "${HF_TOKEN}" true
 prompt_for_env_var "RERANK_MODEL_ID" "Enter the RERANK_MODEL_ID" "BAAI/bge-reranker-base" false
 prompt_for_env_var "LLM_MODEL_ID" "Enter the LLM_MODEL_ID" "meta-llama/Meta-Llama-3-8B-Instruct" false
 prompt_for_env_var "INDEX_NAME" "Enter the INDEX_NAME" "rag-redis" false
@@ -42,32 +50,39 @@ prompt_for_env_var "NUM_CARDS" "Enter the number of Gaudi devices" "1" false
 prompt_for_env_var "host_ip" "Enter the host_ip" "$(curl ifconfig.me)" false
 
 #Query for enabling http_proxy
-prompt_for_env_var "http_proxy" "Enter the http_proxy." "" false
+prompt_for_env_var "http_proxy" "Enter the http_proxy." "${http_proxy}" false
 
 #Query for enabling https_proxy
-prompt_for_env_var "https_proxy" "Enter the https_proxy." "" false
+prompt_for_env_var "https_proxy" "Enter the https_proxy." "${https_proxy}" false
 
 #Query for enabling no_proxy
-prompt_for_env_var "no_proxy" "Enter the no_proxy." "" false
+prompt_for_env_var "no_proxy" "Enter the no_proxy." "${no_proxy}" false
 
-# Query for enabling logging
+if [[ "$NON_INTERACTIVE" == "true" ]]; then
-read -p "Enable logging? (yes/no): " logging && logging=$(echo "$logging" | tr '[:upper:]' '[:lower:]')
+  # Query for enabling logging
-if [[ "$logging" == "yes" || "$logging" == "y" ]]; then
+  prompt_for_env_var "LOGFLAG" "Enable logging? (yes/no): " "true" false
-  export LOGFLAG=true
 else
-  export LOGFLAG=false
+  # Query for enabling logging
+  read -p "Enable logging? (yes/no): " logging && logging=$(echo "$logging" | tr '[:upper:]' '[:lower:]')
+  if [[ "$logging" == "yes" || "$logging" == "y" ]]; then
+    export LOGFLAG=true
+  else
+    export LOGFLAG=false
+  fi
+
+  # Query for enabling OpenTelemetry Tracing Endpoint
+  read -p "Enable OpenTelemetry Tracing Endpoint? (yes/no): " telemetry && telemetry=$(echo "$telemetry" | tr '[:upper:]' '[:lower:]')
+  if [[ "$telemetry" == "yes" || "$telemetry" == "y" ]]; then
+      export JAEGER_IP=$(ip route get 8.8.8.8 | grep -oP 'src \K[^ ]+')
+      export OTEL_EXPORTER_OTLP_TRACES_ENDPOINT=grpc://$JAEGER_IP:4317
+      export TELEMETRY_ENDPOINT=http://$JAEGER_IP:4318/v1/traces
+      telemetry_flag=true
+  else
+      telemetry_flag=false
+  fi
 fi
 
-# Query for enabling OpenTelemetry Tracing Endpoint
+
-read -p "Enable OpenTelemetry Tracing Endpoint? (yes/no): " telemetry && telemetry=$(echo "$telemetry" | tr '[:upper:]' '[:lower:]')
-if [[ "$telemetry" == "yes" || "$telemetry" == "y" ]]; then
-    export JAEGER_IP=$(ip route get 8.8.8.8 | grep -oP 'src \K[^ ]+')
-    export OTEL_EXPORTER_OTLP_TRACES_ENDPOINT=grpc://$JAEGER_IP:4317
-    export TELEMETRY_ENDPOINT=http://$JAEGER_IP:4318/v1/traces
-    telemetry_flag=true
-else
-    telemetry_flag=false
-fi
 
 # Generate the .env file
 cat <<EOF > .env

ChatQnA/tests/test_compose_faqgen_on_gaudi.sh

@@ -13,7 +13,7 @@ export MODEL_CACHE=${model_cache:-"/data/cache"}
 
 WORKPATH=$(dirname "$PWD")
 LOG_PATH="$WORKPATH/tests"
-ip_address=$(hostname -I | awk '{print $1}')
+host_ip=$(hostname -I | awk '{print $1}')
 
 function build_docker_images() {
     opea_branch=${opea_branch:-"main"}
@@ -44,12 +44,17 @@ function build_docker_images() {
 
 function start_services() {
     cd $WORKPATH/docker_compose/intel/hpu/gaudi
-    export EMBEDDING_MODEL_ID="BAAI/bge-base-en-v1.5"
+    export NON_INTERACTIVE=true
-    export RERANK_MODEL_ID="BAAI/bge-reranker-base"
+    # export EMBEDDING_MODEL_ID="BAAI/bge-base-en-v1.5"
-    export LLM_MODEL_ID="meta-llama/Meta-Llama-3-8B-Instruct"
+    # export RERANK_MODEL_ID="BAAI/bge-reranker-base"
-    export NUM_CARDS=1
+    # export LLM_MODEL_ID="meta-llama/Meta-Llama-3-8B-Instruct"
-    export INDEX_NAME="rag-redis"
+    # export NUM_CARDS=1
-    export host_ip=${ip_address}
+    # export INDEX_NAME="rag-redis"
+    # export host_ip=${host_ip}
+    # export LOGFLAG=True
+    # export http_proxy=${http_proxy}
+    # export https_proxy=${https_proxy}
+
     export LLM_ENDPOINT_PORT=8010
     export LLM_SERVER_PORT=9001
     export CHATQNA_BACKEND_PORT=8888
@@ -61,10 +66,9 @@ function start_services() {
     export LLM_ENDPOINT="http://${host_ip}:${LLM_ENDPOINT_PORT}"
     export HF_TOKEN=${HF_TOKEN}
     export VLLM_SKIP_WARMUP=true
-    export LOGFLAG=True
+
-    export http_proxy=${http_proxy}
+    export no_proxy="${host_ip},redis-vector-db,dataprep-redis-service,tei-embedding-service,retriever,tei-reranking-service,tgi-service,vllm-service,guardrails,llm-faqgen,chatqna-gaudi-backend-server,chatqna-gaudi-ui-server,chatqna-gaudi-nginx-server"
-    export https_proxy=${https_proxy}
+    source set_env.sh
-    export no_proxy="${ip_address},redis-vector-db,dataprep-redis-service,tei-embedding-service,retriever,tei-reranking-service,tgi-service,vllm-service,guardrails,llm-faqgen,chatqna-gaudi-backend-server,chatqna-gaudi-ui-server,chatqna-gaudi-nginx-server"
 
     # Start Docker Containers
     docker compose -f compose_faqgen.yaml up -d > ${LOG_PATH}/start_services_with_compose.log
@@ -123,8 +127,8 @@ function validate_microservices() {
 
     # tei for embedding service
     validate_service \
-        "${ip_address}:8090/embed" \
+        "${host_ip}:8090/embed" \
-        "[[" \
+        "]]" \
         "tei-embedding" \
         "tei-embedding-gaudi-server" \
         '{"inputs":"What is Deep Learning?"}'
@@ -134,28 +138,28 @@ function validate_microservices() {
     # 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/ingest" \
+        "http://${host_ip}:6007/v1/dataprep/ingest" \
         "Data preparation succeeded" \
         "dataprep_upload_file" \
         "dataprep-redis-server"
 
     # test /v1/dataprep upload link
     validate_service \
-        "http://${ip_address}:6007/v1/dataprep/ingest" \
+        "http://${host_ip}:6007/v1/dataprep/ingest" \
         "Data preparation succeeded" \
         "dataprep_upload_link" \
         "dataprep-redis-server"
 
     # test /v1/dataprep/get_file
     validate_service \
-        "http://${ip_address}:6007/v1/dataprep/get" \
+        "http://${host_ip}:6007/v1/dataprep/get" \
         '{"name":' \
         "dataprep_get" \
         "dataprep-redis-server"
 
     # test /v1/dataprep/delete_file
     validate_service \
-        "http://${ip_address}:6007/v1/dataprep/delete" \
+        "http://${host_ip}:6007/v1/dataprep/delete" \
         '{"status":true}' \
         "dataprep_del" \
         "dataprep-redis-server"
@@ -163,8 +167,8 @@ function validate_microservices() {
     # 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" \
+        "${host_ip}:7000/v1/retrieval" \
-        " " \
+        "retrieved_docs" \
         "retrieval" \
         "retriever-redis-server" \
         "{\"text\":\"What is the revenue of Nike in 2023?\",\"embedding\":${test_embedding}}"
@@ -172,7 +176,7 @@ function validate_microservices() {
     # tei for rerank microservice
     echo "validate tei..."
     validate_service \
-        "${ip_address}:8808/rerank" \
+        "${host_ip}:8808/rerank" \
         '{"index":1,"score":' \
         "tei-rerank" \
         "tei-reranking-gaudi-server" \
@@ -181,7 +185,7 @@ function validate_microservices() {
     # vllm for llm service
     echo "validate vllm..."
     validate_service \
-        "${ip_address}:${LLM_ENDPOINT_PORT}/v1/chat/completions" \
+        "${host_ip}:${LLM_ENDPOINT_PORT}/v1/chat/completions" \
         "content" \
         "vllm-llm" \
         "vllm-gaudi-server" \
@@ -190,7 +194,7 @@ function validate_microservices() {
     # faqgen llm microservice
     echo "validate llm-faqgen..."
     validate_service \
-        "${ip_address}:${LLM_SERVER_PORT}/v1/faqgen" \
+        "${host_ip}:${LLM_SERVER_PORT}/v1/faqgen" \
         "text" \
         "llm" \
         "llm-faqgen-server" \
@@ -200,14 +204,14 @@ function validate_microservices() {
 function validate_megaservice() {
     # Curl the Mega Service
     validate_service \
-        "${ip_address}:${CHATQNA_BACKEND_PORT}/v1/chatqna" \
+        "${host_ip}:${CHATQNA_BACKEND_PORT}/v1/chatqna" \
         "Embed" \
         "chatqna-megaservice" \
         "chatqna-gaudi-backend-server" \
         '{"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.","max_tokens":32}'
 
     validate_service \
-        "${ip_address}:${CHATQNA_BACKEND_PORT}/v1/chatqna" \
+        "${host_ip}:${CHATQNA_BACKEND_PORT}/v1/chatqna" \
         "Embed" \
         "chatqna-megaservice" \
         "chatqna-gaudi-backend-server" \
@@ -226,7 +230,7 @@ function validate_frontend() {
     fi
     source activate ${conda_env_name}
 
-    sed -i "s/localhost/$ip_address/g" playwright.config.ts
+    sed -i "s/localhost/$host_ip/g" playwright.config.ts
 
     conda install -c conda-forge nodejs=22.6.0 -y
     npm install && npm ci && npx playwright install --with-deps