Update Code and README for GenAIComps Refactor (#1285)

Signed-off-by: lvliang-intel <liang1.lv@intel.com> Signed-off-by: chensuyue <suyue.chen@intel.com> Signed-off-by: Xinyao Wang <xinyao.wang@intel.com> Signed-off-by: letonghan <letong.han@intel.com> Signed-off-by: ZePan110 <ze.pan@intel.com> Signed-off-by: WenjiaoYue <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>
2025-01-02 20:03:26 +08:00
parent 72f8079289
commit 5c7a5bd850
103 changed files with 655 additions and 438 deletions
--- a/ProductivitySuite/docker_compose/intel/cpu/xeon/README.md
+++ b/ProductivitySuite/docker_compose/intel/cpu/xeon/README.md
@@ -13,7 +13,7 @@ First of all, you need to build Docker Images locally and install the python pac
 ```bash
 git clone https://github.com/opea-project/GenAIComps.git
 cd GenAIComps
-docker build --no-cache -t opea/embedding-tei:latest --build-arg https_proxy=$https_proxy --build-arg http_proxy=$http_proxy -f comps/embeddings/tei/langchain/Dockerfile .
+docker build --no-cache -t opea/embedding-tei:latest --build-arg https_proxy=$https_proxy --build-arg http_proxy=$http_proxy -f comps/embeddings/src/Dockerfile .
 ```

 ### 2. Build Retriever Image
@@ -25,7 +25,7 @@ docker build --no-cache -t opea/retriever-redis:latest --build-arg https_proxy=$
 ### 3. Build Rerank Image

 ```bash
-docker build --no-cache -t opea/reranking-tei:latest --build-arg https_proxy=$https_proxy --build-arg http_proxy=$http_proxy -f comps/reranks/tei/Dockerfile .
+docker build --no-cache -t opea/reranking-tei:latest --build-arg https_proxy=$https_proxy --build-arg http_proxy=$http_proxy -f comps/reranks/src/Dockerfile .
 ```

 ### 4. Build LLM Image
@@ -33,7 +33,7 @@ docker build --no-cache -t opea/reranking-tei:latest --build-arg https_proxy=$ht
 #### Use TGI as backend

 ```bash
-docker build --no-cache -t opea/llm-tgi:latest --build-arg https_proxy=$https_proxy --build-arg http_proxy=$http_proxy -f comps/llms/text-generation/tgi/Dockerfile .
+docker build --no-cache -t opea/llm-tgi:latest --build-arg https_proxy=$https_proxy --build-arg http_proxy=$http_proxy -f comps/llms/src/text-generation/Dockerfile .
 ```

 ### 5. Build Dataprep Image
--- a/ProductivitySuite/docker_compose/intel/cpu/xeon/compose.yaml
+++ b/ProductivitySuite/docker_compose/intel/cpu/xeon/compose.yaml
@@ -28,10 +28,13 @@ services:
      REDIS_URL: ${REDIS_URL}
      REDIS_HOST: redis-vector-db
      INDEX_NAME: ${INDEX_NAME}
-      TEI_ENDPOINT: ${TEI_EMBEDDING_ENDPOINT}
+      TEI_EMBEDDING_ENDPOINT: ${TEI_EMBEDDING_ENDPOINT}
      HUGGINGFACEHUB_API_TOKEN: ${HUGGINGFACEHUB_API_TOKEN}
+      DATAPREP_TYPE: ${DATAPREP_TYPE}
+      LOGFLAG: ${LOGFLAG}
  tei-embedding-service:
    image: ghcr.io/huggingface/text-embeddings-inference:cpu-1.5
+    entrypoint: /bin/sh -c "apt-get update && apt-get install -y curl && text-embeddings-router --json-output --model-id ${EMBEDDING_MODEL_ID} --auto-truncate"
    container_name: tei-embedding-server
    ports:
      - "6006:80"
@@ -42,12 +45,18 @@ services:
      no_proxy: ${no_proxy}
      http_proxy: ${http_proxy}
      https_proxy: ${https_proxy}
-    command: --model-id ${EMBEDDING_MODEL_ID} --auto-truncate
+      host_ip: ${host_ip}
+    healthcheck:
+      test: ["CMD-SHELL", "curl -f http://$host_ip:6006/health || exit 1"]
+      interval: 10s
+      timeout: 10s
+      retries: 60
  embedding:
    image: ${REGISTRY:-opea}/embedding-tei:${TAG:-latest}
    container_name: embedding-tei-server
    depends_on:
-      - tei-embedding-service
+      tei-embedding-service:
+        condition: service_healthy
    ports:
      - "6000:6000"
    ipc: host
@@ -56,9 +65,8 @@ services:
      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"
+      HF_TOKEN: ${HUGGINGFACEHUB_API_TOKEN}
+      LOGFLAG: ${LOGFLAG}
    restart: unless-stopped
  retriever:
    image: ${REGISTRY:-opea}/retriever-redis:${TAG:-latest}
@@ -77,9 +85,12 @@ services:
      INDEX_NAME: ${INDEX_NAME}
      TEI_EMBEDDING_ENDPOINT: ${TEI_EMBEDDING_ENDPOINT}
      HUGGINGFACEHUB_API_TOKEN: ${HUGGINGFACEHUB_API_TOKEN}
+      RETRIEVER_TYPE: ${RETRIEVER_TYPE}
+      LOGFLAG: ${LOGFLAG}
    restart: unless-stopped
  tei-reranking-service:
    image: ghcr.io/huggingface/text-embeddings-inference:cpu-1.5
+    entrypoint: /bin/sh -c "apt-get update && apt-get install -y curl && text-embeddings-router --json-output --model-id ${RERANK_MODEL_ID} --auto-truncate"
    container_name: tei-reranking-server
    ports:
      - "8808:80"
@@ -93,12 +104,18 @@ services:
      HUGGINGFACEHUB_API_TOKEN: ${HUGGINGFACEHUB_API_TOKEN}
      HF_HUB_DISABLE_PROGRESS_BARS: 1
      HF_HUB_ENABLE_HF_TRANSFER: 0
-    command: --model-id ${RERANK_MODEL_ID} --auto-truncate
+      host_ip: ${host_ip}
+    healthcheck:
+      test: ["CMD-SHELL", "curl -f http://$host_ip:8808/health || exit 1"]
+      interval: 10s
+      timeout: 10s
+      retries: 60
  reranking:
    image: ${REGISTRY:-opea}/reranking-tei:${TAG:-latest}
    container_name: reranking-tei-xeon-server
    depends_on:
-      - tei-reranking-service
+      tei-reranking-service:
+        condition: service_healthy
    ports:
      - "8000:8000"
    ipc: host
@@ -106,13 +123,12 @@ services:
      no_proxy: ${no_proxy}
      http_proxy: ${http_proxy}
      https_proxy: ${https_proxy}
+      RERANK_TYPE: ${RERANK_TYPE}
      TEI_RERANKING_ENDPOINT: ${TEI_RERANKING_ENDPOINT}
      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"
+      LOGFLAG: ${LOGFLAG}
    restart: unless-stopped
  tgi_service:
    image: ghcr.io/huggingface/text-generation-inference:2.4.0-intel-cpu
@@ -129,12 +145,19 @@ services:
      HF_TOKEN: ${HUGGINGFACEHUB_API_TOKEN}
      HF_HUB_DISABLE_PROGRESS_BARS: 1
      HF_HUB_ENABLE_HF_TRANSFER: 0
+      host_ip: ${host_ip}
+    healthcheck:
+      test: ["CMD-SHELL", "curl -f http://$host_ip:9009/health || exit 1"]
+      interval: 10s
+      timeout: 10s
+      retries: 100
    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
+      tgi_service:
+        condition: service_healthy
    ports:
      - "9000:9000"
    ipc: host
@@ -142,13 +165,12 @@ services:
      no_proxy: ${no_proxy}
      http_proxy: ${http_proxy}
      https_proxy: ${https_proxy}
-      TGI_LLM_ENDPOINT: ${TGI_LLM_ENDPOINT_CHATQNA}
+      LLM_ENDPOINT: ${TGI_LLM_ENDPOINT_CHATQNA}
+      LLM_MODEL_ID: ${LLM_MODEL_ID}
      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"
+      LOGFLAG: ${LOGFLAG}
    restart: unless-stopped
  chatqna-xeon-backend-server:
    image: ${REGISTRY:-opea}/chatqna:${TAG:-latest}
@@ -194,12 +216,19 @@ services:
      http_proxy: ${http_proxy}
      https_proxy: ${https_proxy}
      HF_TOKEN: ${HUGGINGFACEHUB_API_TOKEN}
+      host_ip: ${host_ip}
+    healthcheck:
+      test: ["CMD-SHELL", "curl -f http://$host_ip:8028/health || exit 1"]
+      interval: 10s
+      timeout: 10s
+      retries: 30
    command: --model-id ${LLM_MODEL_ID_CODEGEN}
  llm_codegen:
    image: ${REGISTRY:-opea}/llm-tgi:${TAG:-latest}
    container_name: llm-tgi-server-codegen
    depends_on:
-      - tgi_service_codegen
+      tgi_service_codegen:
+        condition: service_healthy
    ports:
      - "9001:9000"
    ipc: host
@@ -207,11 +236,10 @@ services:
      no_proxy: ${no_proxy}
      http_proxy: ${http_proxy}
      https_proxy: ${https_proxy}
-      TGI_LLM_ENDPOINT: ${TGI_LLM_ENDPOINT_CODEGEN}
+      LLM_ENDPOINT: ${TGI_LLM_ENDPOINT_CODEGEN}
+      LLM_MODEL_ID: ${LLM_MODEL_ID}
      HUGGINGFACEHUB_API_TOKEN: ${HUGGINGFACEHUB_API_TOKEN}
-      LANGCHAIN_API_KEY: ${LANGCHAIN_API_KEY}
-      LANGCHAIN_TRACING_V2: ${LANGCHAIN_TRACING_V2}
-      LANGCHAIN_PROJECT: "opea-llm-service"
+      LOGFLAG: ${LOGFLAG}
    restart: unless-stopped
  codegen-xeon-backend-server:
    image: ${REGISTRY:-opea}/codegen:${TAG:-latest}
@@ -227,6 +255,7 @@ services:
      MEGA_SERVICE_HOST_IP: ${MEGA_SERVICE_HOST_IP}
      LLM_SERVICE_HOST_IP: ${LLM_SERVICE_HOST_IP_CODEGEN}
      LLM_SERVICE_PORT: ${LLM_SERVICE_HOST_PORT_CODEGEN}
+      LOGFLAG: ${LOGFLAG}
    ipc: host
    restart: always
  llm_faqgen:
@@ -243,9 +272,6 @@ services:
      https_proxy: ${https_proxy}
      TGI_LLM_ENDPOINT: ${TGI_LLM_ENDPOINT_FAQGEN}
      HUGGINGFACEHUB_API_TOKEN: ${HUGGINGFACEHUB_API_TOKEN}
-      LANGCHAIN_API_KEY: ${LANGCHAIN_API_KEY}
-      LANGCHAIN_TRACING_V2: ${LANGCHAIN_TRACING_V2}
-      LANGCHAIN_PROJECT: "opea-llm-service"
    restart: unless-stopped
  faqgen-xeon-backend-server:
    image: ${REGISTRY:-opea}/faqgen:${TAG:-latest}
@@ -262,41 +288,7 @@ services:
      MEGA_SERVICE_HOST_IP: ${MEGA_SERVICE_HOST_IP}
      LLM_SERVICE_PORT: ${LLM_SERVICE_HOST_PORT_FAQGEN}
      LLM_SERVICE_HOST_IP: ${LLM_SERVICE_HOST_IP_FAQGEN}
-    ipc: host
-    restart: always
-  llm_docsum_server:
-    image: ${REGISTRY:-opea}/llm-docsum-tgi:${TAG:-latest}
-    container_name: llm-docsum-server
-    depends_on:
-      - tgi_service
-    ports:
-      - "9003:9000"
-    ipc: host
-    environment:
-      no_proxy: ${no_proxy}
-      http_proxy: ${http_proxy}
-      https_proxy: ${https_proxy}
-      TGI_LLM_ENDPOINT: ${TGI_LLM_ENDPOINT_DOCSUM}
-      HUGGINGFACEHUB_API_TOKEN: ${HUGGINGFACEHUB_API_TOKEN}
-      LANGCHAIN_API_KEY: ${LANGCHAIN_API_KEY}
-      LANGCHAIN_TRACING_V2: ${LANGCHAIN_TRACING_V2}
-      LANGCHAIN_PROJECT: "opea-llm-service"
-    restart: unless-stopped
-  docsum-xeon-backend-server:
-    image: ${REGISTRY:-opea}/docsum:${TAG:-latest}
-    container_name: docsum-xeon-backend-server
-    depends_on:
-      - tgi_service
-      - llm_docsum_server
-    ports:
-      - "8890:8888"
-    environment:
-      no_proxy: ${no_proxy}
-      https_proxy: ${https_proxy}
-      http_proxy: ${http_proxy}
-      LLM_SERVICE_PORT: ${LLM_SERVICE_HOST_PORT_DOCSUM}
-      MEGA_SERVICE_HOST_IP: ${MEGA_SERVICE_HOST_IP}
-      LLM_SERVICE_HOST_IP: ${LLM_SERVICE_HOST_IP_DOCSUM}
+      LOGFLAG: ${LOGFLAG}
    ipc: host
    restart: always
  mongo:
@@ -323,6 +315,7 @@ services:
      MONGO_HOST: ${MONGO_HOST}
      MONGO_PORT: ${MONGO_PORT}
      COLLECTION_NAME: ${COLLECTION_NAME}
+      LOGFLAG: ${LOGFLAG}
    restart: unless-stopped

  promptregistry-mongo:
@@ -338,6 +331,7 @@ services:
      MONGO_HOST: ${MONGO_HOST}
      MONGO_PORT: ${MONGO_PORT}
      COLLECTION_NAME: ${PROMPT_COLLECTION_NAME}
+      LOGFLAG: ${LOGFLAG}
    restart: unless-stopped
  keycloak:
    image: quay.io/keycloak/keycloak:25.0.2
@@ -371,6 +365,7 @@ services:
      - APP_PROMPT_SERVICE_GET_ENDPOINT=${PROMPT_SERVICE_GET_ENDPOINT}
      - APP_PROMPT_SERVICE_CREATE_ENDPOINT=${PROMPT_SERVICE_CREATE_ENDPOINT}
      - APP_KEYCLOAK_SERVICE_ENDPOINT=${KEYCLOAK_SERVICE_ENDPOINT}
+      - LOGFLAG=${LOGFLAG}
    ipc: host
    restart: always
 networks:
--- a/ProductivitySuite/docker_image_build/build.yaml
+++ b/ProductivitySuite/docker_image_build/build.yaml
@@ -14,7 +14,7 @@ services:
  embedding-tei:
    build:
      context: GenAIComps
-      dockerfile: comps/embeddings/tei/langchain/Dockerfile
+      dockerfile: comps/embeddings/src/Dockerfile
    extends: chatqna
    image: ${REGISTRY:-opea}/embedding-tei:${TAG:-latest}
  retriever-redis:
@@ -26,13 +26,13 @@ services:
  reranking-tei:
    build:
      context: GenAIComps
-      dockerfile: comps/reranks/tei/Dockerfile
+      dockerfile: comps/reranks/src/Dockerfile
    extends: chatqna
    image: ${REGISTRY:-opea}/reranking-tei:${TAG:-latest}
  llm-tgi:
    build:
      context: GenAIComps
-      dockerfile: comps/llms/text-generation/tgi/Dockerfile
+      dockerfile: comps/llms/src/text-generation/Dockerfile
    extends: chatqna
    image: ${REGISTRY:-opea}/llm-tgi:${TAG:-latest}
  dataprep-redis:
@@ -68,15 +68,6 @@ services:
      context: ../../CodeGen/
      dockerfile: ./Dockerfile
    image: ${REGISTRY:-opea}/codegen:${TAG:-latest}
-  docsum:
-    build:
-      args:
-        http_proxy: ${http_proxy}
-        https_proxy: ${https_proxy}
-        no_proxy: ${no_proxy}
-      context: ../../DocSum/
-      dockerfile: ./Dockerfile
-    image: ${REGISTRY:-opea}/docsum:${TAG:-latest}
  faqgen:
    build:
      args:
@@ -92,9 +83,3 @@ services:
      dockerfile: comps/llms/faq-generation/tgi/langchain/Dockerfile
    extends: faqgen
    image: ${REGISTRY:-opea}/llm-faqgen-tgi:${TAG:-latest}
-  llm-docsum-tgi:
-    build:
-      context: GenAIComps
-      dockerfile: comps/llms/summarization/tgi/langchain/Dockerfile
-    extends: docsum
-    image: ${REGISTRY:-opea}/llm-docsum-tgi:${TAG:-latest}
--- a/ProductivitySuite/tests/test_compose_on_xeon.sh
+++ b/ProductivitySuite/tests/test_compose_on_xeon.sh
@@ -30,9 +30,12 @@ function start_services() {
    cd $WORKPATH/docker_compose/intel/cpu/xeon/

    export EMBEDDING_MODEL_ID="BAAI/bge-base-en-v1.5"
+    export RERANK_TYPE="tei"
    export RERANK_MODEL_ID="BAAI/bge-reranker-base"
    export LLM_MODEL_ID="Intel/neural-chat-7b-v3-3"
    export LLM_MODEL_ID_CODEGEN="Intel/neural-chat-7b-v3-3"
+    export DATAPREP_TYPE="redis"
+    export RETRIEVER_TYPE="redis"
    export TEI_EMBEDDING_ENDPOINT="http://${ip_address}:6006"
    export TEI_RERANKING_ENDPOINT="http://${ip_address}:8808"
    export TGI_LLM_ENDPOINT="http://${ip_address}:9009"
@@ -57,9 +60,8 @@ function start_services() {
    export BACKEND_SERVICE_ENDPOINT_FAQGEN="http://${ip_address}:8889/v1/faqgen"
    export DATAPREP_DELETE_FILE_ENDPOINT="http://${ip_address}:6009/v1/dataprep/delete_file"
    export BACKEND_SERVICE_ENDPOINT_CODEGEN="http://${ip_address}:7778/v1/codegen"
-    export BACKEND_SERVICE_ENDPOINT_DOCSUM="http://${ip_address}:8890/v1/docsum"
-    export DATAPREP_SERVICE_ENDPOINT="http://${ip_address}:6007/v1/dataprep"
-    export DATAPREP_GET_FILE_ENDPOINT="http://${ip_address}:6008/v1/dataprep/get_file"
+    export DATAPREP_SERVICE_ENDPOINT="http://${ip_address}:6007/v1/dataprep/ingest"
+    export DATAPREP_GET_FILE_ENDPOINT="http://${ip_address}:6008/v1/dataprep/get"
    export CHAT_HISTORY_CREATE_ENDPOINT="http://${ip_address}:6012/v1/chathistory/create"
    export CHAT_HISTORY_CREATE_ENDPOINT="http://${ip_address}:6012/v1/chathistory/create"
    export CHAT_HISTORY_DELETE_ENDPOINT="http://${ip_address}:6012/v1/chathistory/delete"
@@ -73,11 +75,12 @@ function start_services() {
    export COLLECTION_NAME="Conversations"
    export LLM_SERVICE_HOST_PORT_FAQGEN=9002
    export LLM_SERVICE_HOST_PORT_CODEGEN=9001
-    export LLM_SERVICE_HOST_PORT_DOCSUM=9003
    export RERANK_SERVER_PORT=8808
    export EMBEDDING_SERVER_PORT=6006
    export LLM_SERVER_PORT=9009
    export PROMPT_COLLECTION_NAME="prompt"
+    export host_ip=${ip_address}
+    export LOGFLAG=true

    # Start Docker Containers
    docker compose up -d > ${LOG_PATH}/start_services_with_compose.log
@@ -101,6 +104,8 @@ function start_services() {
        sleep 5s
        n=$((n+1))
    done
+
+    sleep 10s
 }

 function validate_service() {
@@ -119,9 +124,9 @@ function validate_service() {
        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")
-    elif [[ $SERVICE_NAME == *"docsum-xeon-backend-server"* ]]; then
-	local INPUT_DATA="messages=Text Embeddings Inference (TEI) is a toolkit for deploying and serving open source text embeddings and sequence classification models. TEI enables high-performance extraction for the most popular models, including FlagEmbedding, Ember, GTE and E5."
-        HTTP_RESPONSE=$(curl --silent --write-out "HTTPSTATUS:%{http_code}" -X POST -F "$INPUT_DATA" -H 'Content-Type: multipart/form-data' "$URL")
+    elif [[ $SERVICE_NAME == *"faqgen-xeon-backend-server"* ]]; then
+        local INPUT_DATA="messages=Text Embeddings Inference (TEI) is a toolkit for deploying and serving open source text embeddings and sequence classification models. TEI enables high-performance extraction for the most popular models, including FlagEmbedding, Ember, GTE and E5."
+        HTTP_RESPONSE=$(curl --silent --write-out "HTTPSTATUS:%{http_code}" -X POST -F "$INPUT_DATA" -F "max_tokens=32" -F "stream=False" -H 'Content-Type: multipart/form-data' "$URL")
    else
        HTTP_RESPONSE=$(curl --silent --write-out "HTTPSTATUS:%{http_code}" -X POST -d "$INPUT_DATA" -H 'Content-Type: application/json' "$URL")
    fi
@@ -162,13 +167,20 @@ function validate_microservices() {
    # embedding microservice
    validate_service \
        "${ip_address}:6000/v1/embeddings" \
-        '"text":"What is Deep Learning?","embedding":[' \
+        '"embedding":[' \
        "embedding-microservice" \
        "embedding-tei-server" \
-        '{"text":"What is Deep Learning?"}'
+        '{"input":"What is Deep Learning?"}'

    sleep 1m # retrieval can't curl as expected, try to wait for more time

+    # test /v1/dataprep/delete_file
+    validate_service \
+        "http://${ip_address}:6007/v1/dataprep/delete_file" \
+        '{"status":true}' \
+        "dataprep_del" \
+        "dataprep-redis-server"
+
    # 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 \
@@ -191,13 +203,6 @@ function validate_microservices() {
        "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 \
@@ -247,14 +252,6 @@ function validate_microservices() {
        "llm-faqgen-server" \
        '{"query":"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."}'

-    # Docsum llm microservice
-    validate_service \
-        "${ip_address}:9003/v1/chat/docsum" \
-        "data: " \
-        "llm_docsum" \
-        "llm-docsum-server" \
-        '{"query":"Text Embeddings Inference (TEI) is a toolkit for deploying and serving open source text embeddings and sequence classification models. TEI enables high-performance extraction for the most popular models, including FlagEmbedding, Ember, GTE and E5."}'
-
    # CodeGen llm microservice
    validate_service \
        "${ip_address}:9001/v1/chat/completions" \
@@ -309,7 +306,6 @@ function validate_megaservice() {
        "chatqna-xeon-backend-server" \
        '{"messages": "What is the revenue of Nike in 2023?"}'\

-
    # Curl the FAQGen Service
    validate_service \
        "${ip_address}:8889/v1/faqgen" \
@@ -318,15 +314,6 @@ function validate_megaservice() {
        "faqgen-xeon-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."}'\

-    # Curl the DocSum Mega Service
-    validate_service \
-        "${ip_address}:8890/v1/docsum" \
-        "embedding" \
-        "docsum-xeon-backend-server" \
-        "docsum-xeon-backend-server" \
-        '{"messages": "Text Embeddings Inference (TEI) is a toolkit for deploying and serving open source text embeddings and sequence classification models. TEI enables high-performance extraction for the most popular models, including FlagEmbedding, Ember, GTE and E5."}'
-
-
    # Curl the CodeGen Mega Service
    validate_service \
    "${ip_address}:7778/v1/codegen" \