Fix ChatQnA Qdrant CI issues

ChatQnA/docker/xeon/compose_qdrant.yaml

@@ -18,21 +18,21 @@ services:
       - qdrant-vector-db
       - tei-embedding-service
     ports:
-      - "6000:6000"
+      - "6043:6007"
     environment:
       no_proxy: ${no_proxy}
       http_proxy: ${http_proxy}
       https_proxy: ${https_proxy}
-      QDRANT: ${host_ip}
+      QDRANT_HOST: ${QDRANT_HOST}
       QDRANT_PORT: 6333
       COLLECTION_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-1.2
+    image: ghcr.io/huggingface/text-embeddings-inference:cpu-1.5
     container_name: tei-embedding-server
     ports:
-      - "6006:80"
+      - "6040:80"
     volumes:
       - "./data:/data"
     shm_size: 1g
@@ -47,39 +47,35 @@ services:
     depends_on:
       - tei-embedding-service
     ports:
-      - "6000:6000"
+      - "6044:6000"
     ipc: host
     environment:
       no_proxy: ${no_proxy}
       http_proxy: ${http_proxy}
       https_proxy: ${https_proxy}
       TEI_EMBEDDING_ENDPOINT: ${TEI_EMBEDDING_ENDPOINT}
-      LANGCHAIN_API_KEY: ${LANGCHAIN_API_KEY}
-      LANGCHAIN_TRACING_V2: ${LANGCHAIN_TRACING_V2}
-      LANGCHAIN_PROJECT: "opea-embedding-service"
     restart: unless-stopped
   retriever:
     image: opea/retriever-qdrant:latest
     container_name: retriever-qdrant-server
     depends_on:
       - qdrant-vector-db
     ports:
-      - "7000:7000"
+      - "6045:7000"
     ipc: host
     environment:
       no_proxy: ${no_proxy}
       http_proxy: ${http_proxy}
       https_proxy: ${https_proxy}
-      QDRANT_HOST: ${host_ip}
+      QDRANT_HOST: ${QDRANT_HOST}
       QDRANT_PORT: 6333
       INDEX_NAME: ${INDEX_NAME}
-      TEI_EMBEDDING_ENDPOINT: ${TEI_EMBEDDING_ENDPOINT}
     restart: unless-stopped
   tei-reranking-service:
     image: ghcr.io/huggingface/text-embeddings-inference:cpu-1.2
     container_name: tei-reranking-server
     ports:
-      - "8808:80"
+      - "6041:80"
     volumes:
       - "./data:/data"
     shm_size: 1g
@@ -97,7 +93,7 @@ services:
     depends_on:
       - tei-reranking-service
     ports:
-      - "8000:8000"
+      - "6046:8000"
     ipc: host
     environment:
       no_proxy: ${no_proxy}
@@ -107,15 +103,12 @@ services:
       HUGGINGFACEHUB_API_TOKEN: ${HUGGINGFACEHUB_API_TOKEN}
       HF_HUB_DISABLE_PROGRESS_BARS: 1
       HF_HUB_ENABLE_HF_TRANSFER: 0
-      LANGCHAIN_API_KEY: ${LANGCHAIN_API_KEY}
-      LANGCHAIN_TRACING_V2: ${LANGCHAIN_TRACING_V2}
-      LANGCHAIN_PROJECT: "opea-reranking-service"
     restart: unless-stopped
   tgi-service:
     image: ghcr.io/huggingface/text-generation-inference:2.1.0
     container_name: tgi-service
     ports:
-      - "9009:80"
+      - "6042:80"
     volumes:
       - "./data:/data"
     shm_size: 1g
@@ -133,7 +126,7 @@ services:
     depends_on:
       - tgi-service
     ports:
-      - "9000:9000"
+      - "6047:9000"
     ipc: host
     environment:
       no_proxy: ${no_proxy}
@@ -143,9 +136,6 @@ services:
       HUGGINGFACEHUB_API_TOKEN: ${HUGGINGFACEHUB_API_TOKEN}
       HF_HUB_DISABLE_PROGRESS_BARS: 1
       HF_HUB_ENABLE_HF_TRANSFER: 0
-      LANGCHAIN_API_KEY: ${LANGCHAIN_API_KEY}
-      LANGCHAIN_TRACING_V2: ${LANGCHAIN_TRACING_V2}
-      LANGCHAIN_PROJECT: "opea-llm-service"
     restart: unless-stopped
   chaqna-xeon-backend-server:
     image: opea/chatqna:latest
@@ -160,16 +150,20 @@ services:
       - tgi-service
       - llm
     ports:
-      - "8888:8888"
+      - "8912:8888"
     environment:
       - no_proxy=${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}
+      - EMBEDDING_SERVICE_PORT=${EMBEDDING_SERVICE_PORT}
       - RETRIEVER_SERVICE_HOST_IP=${RETRIEVER_SERVICE_HOST_IP}
+      - RETRIEVER_SERVICE_PORT=${RETRIEVER_SERVICE_PORT}
       - RERANK_SERVICE_HOST_IP=${RERANK_SERVICE_HOST_IP}
+      - RERANK_SERVICE_PORT=${RERANK_SERVICE_PORT}
       - LLM_SERVICE_HOST_IP=${LLM_SERVICE_HOST_IP}
+      - LLM_SERVICE_PORT=${LLM_SERVICE_PORT}
     ipc: host
     restart: always
   chaqna-xeon-ui-server:

ChatQnA/tests/_test_chatqna_qdrant_on_xeon.sh → ChatQnA/tests/test_chatqna_qdrant_on_xeon.sh

@@ -35,9 +35,9 @@ function start_services() {
     export EMBEDDING_MODEL_ID="BAAI/bge-base-en-v1.5"
     export RERANK_MODEL_ID="BAAI/bge-reranker-base"
     export LLM_MODEL_ID="Intel/neural-chat-7b-v3-3"
-    export TEI_EMBEDDING_ENDPOINT="http://${ip_address}:6006"
-    export TEI_RERANKING_ENDPOINT="http://${ip_address}:8808"
-    export TGI_LLM_ENDPOINT="http://${ip_address}:9009"
+    export TEI_EMBEDDING_ENDPOINT="http://${ip_address}:6040"
+    export TEI_RERANKING_ENDPOINT="http://${ip_address}:6041"
+    export TGI_LLM_ENDPOINT="http://${ip_address}:6042"
     export QDRANT_HOST=${ip_address}
     export QDRANT_PORT=6333
     export INDEX_NAME="rag-qdrant"
@@ -47,8 +47,12 @@ function start_services() {
     export RETRIEVER_SERVICE_HOST_IP=${ip_address}
     export RERANK_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 EMBEDDING_SERVICE_PORT=6044
+    export RETRIEVER_SERVICE_PORT=6045
+    export RERANK_SERVICE_PORT=6046
+    export LLM_SERVICE_PORT=6047
+    export BACKEND_SERVICE_ENDPOINT="http://${ip_address}:8912/v1/chatqna"
+    export DATAPREP_SERVICE_ENDPOINT="http://${ip_address}:6043/v1/dataprep"
 
     sed -i "s/backend_address/$ip_address/g" $WORKPATH/docker/ui/svelte/.env
 
@@ -82,24 +86,34 @@ function validate_services() {
     local DOCKER_NAME="$4"
     local INPUT_DATA="$5"
 
-    local HTTP_STATUS=$(curl -s -o /dev/null -w "%{http_code}" -X POST -d "$INPUT_DATA" -H 'Content-Type: application/json' "$URL")
-    if [ "$HTTP_STATUS" -eq 200 ]; then
-        echo "[ $SERVICE_NAME ] HTTP status is 200. Checking content..."
+    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/"]' "$URL")
+    else
+        HTTP_RESPONSE=$(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')
 
-        local CONTENT=$(curl -s -X POST -d "$INPUT_DATA" -H 'Content-Type: application/json' "$URL" | tee ${LOG_PATH}/${SERVICE_NAME}.log)
+    docker logs ${DOCKER_NAME} >> ${LOG_PATH}/${SERVICE_NAME}.log
 
-        if echo "$CONTENT" | grep -q "$EXPECTED_RESULT"; then
-            echo "[ $SERVICE_NAME ] Content is as expected."
-        else
-            echo "[ $SERVICE_NAME ] Content does not match the expected result: $CONTENT"
-            docker logs ${DOCKER_NAME} >> ${LOG_PATH}/${SERVICE_NAME}.log
-            exit 1
-        fi
-    else
+    # check response status
+    if [ "$HTTP_STATUS" -ne "200" ]; then
         echo "[ $SERVICE_NAME ] HTTP status is not 200. Received status was $HTTP_STATUS"
-        docker logs ${DOCKER_NAME} >> ${LOG_PATH}/${SERVICE_NAME}.log
         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
 }
 
@@ -108,69 +122,82 @@ function validate_microservices() {
 
     # tei for embedding service
     validate_services \
-        "${ip_address}:6006/embed" \
-        "\[\[" \
+        "${ip_address}:6040/embed" \
+        "[[" \
         "tei-embedding" \
         "tei-embedding-server" \
         '{"inputs":"What is Deep Learning?"}'
 
     # embedding microservice
     validate_services \
-        "${ip_address}:6000/v1/embeddings" \
-        '"text":"What is Deep Learning?","embedding":\[' \
+        "${ip_address}:6044/v1/embeddings" \
+        '"text":"What is Deep Learning?","embedding":[' \
         "embedding" \
         "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." > $LOG_PATH/dataprep_file.txt
+    validate_services \
+        "${ip_address}:6043/v1/dataprep" \
+        "Data preparation succeeded" \
+        "dataprep_upload_file" \
+        "dataprep-qdrant-server"
+
+    # test upload link
+    validate_services \
+        "${ip_address}:6043/v1/dataprep" \
+        "Data preparation succeeded" \
+        "dataprep_upload_link" \
+        "dataprep-qdrant-server"
 
     # retrieval microservice
     test_embedding=$(python3 -c "import random; embedding = [random.uniform(-1, 1) for _ in range(768)]; print(embedding)")
     validate_services \
-        "${ip_address}:7000/v1/retrieval" \
-        " " \
+        "${ip_address}:6045/v1/retrieval" \
+        "retrieved_docs" \
         "retrieval" \
         "retriever-qdrant-server" \
-        "{\"text\":\"What is the revenue of Nike in 2023?\",\"embedding\":${test_embedding}}"
+        "{\"text\":\"What is Deep Learning?\",\"embedding\":${test_embedding}}"
 
     # tei for rerank microservice
     validate_services \
-        "${ip_address}:8808/rerank" \
+        "${ip_address}:6041/rerank" \
         '{"index":1,"score":' \
         "tei-rerank" \
         "tei-reranking-server" \
         '{"query":"What is Deep Learning?", "texts": ["Deep Learning is not...", "Deep learning is..."]}'
 
     # rerank microservice
     validate_services \
-        "${ip_address}:8000/v1/reranking" \
+        "${ip_address}:6046/v1/reranking" \
         "Deep learning is..." \
         "rerank" \
         "reranking-tei-xeon-server" \
         '{"initial_query":"What is Deep Learning?", "retrieved_docs": [{"text":"Deep Learning is not..."}, {"text":"Deep learning is..."}]}'
 
     # tgi for llm service
     validate_services \
-        "${ip_address}:9009/generate" \
+        "${ip_address}:6042/generate" \
         "generated_text" \
         "tgi-llm" \
         "tgi-service" \
         '{"inputs":"What is Deep Learning?","parameters":{"max_new_tokens":17, "do_sample": true}}'
 
     # llm microservice
     validate_services \
-        "${ip_address}:9000/v1/chat/completions" \
+        "${ip_address}:6047/v1/chat/completions" \
         "data: " \
         "llm" \
         "llm-tgi-server" \
-        '{"query":"What is Deep Learning?"}'
+        '{"query":"Deep Learning"}'
 
 }
 
 function validate_megaservice() {
     # Curl the Mega Service
     validate_services \
-        "${ip_address}:8888/v1/chatqna" \
+        "${ip_address}:8912/v1/chatqna" \
         "billion" \
         "mega-chatqna" \
         "chatqna-xeon-backend-server" \
@@ -182,13 +209,10 @@ function validate_frontend() {
     cd $WORKPATH/docker/ui/svelte
     local conda_env_name="OPEA_e2e"
     export PATH=${HOME}/miniforge3/bin/:$PATH
-#    conda remove -n ${conda_env_name} --all -y
-#    conda create -n ${conda_env_name} python=3.12 -y
     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
 
@@ -205,7 +229,7 @@ function validate_frontend() {
 
 function stop_docker() {
     cd $WORKPATH/docker/xeon
-    docker compose stop && docker compose rm -f
+    docker compose -f compose_qdrant.yaml stop && docker compose -f compose_qdrant.yaml rm -f
 }
 
 function main() {