Remove FaqGen from ProductivitySuite (#1709)

Signed-off-by: Xinyao Wang <[email protected]>

Author: XinyaoWa

ProductivitySuite/docker_compose/intel/cpu/xeon/README.md

@@ -81,13 +81,6 @@ cd GenAIExamples/CodeGen
 docker build --no-cache -t opea/codegen:latest --build-arg https_proxy=$https_proxy --build-arg http_proxy=$http_proxy -f Dockerfile .
 ```
 
-#### 8.4 Build FAQGen Megaservice Docker Images
-
-```bash
-cd GenAIExamples/FaqGen
-docker build --no-cache -t opea/faqgen:latest --build-arg https_proxy=$https_proxy --build-arg http_proxy=$http_proxy -f Dockerfile .
-```
-
 ### 9. Build UI Docker Image
 
 Build frontend Docker image that enables via below command:
@@ -159,7 +152,6 @@ export TGI_LLM_ENDPOINT_FAQGEN="http://${host_ip}:9009"
 export TGI_LLM_ENDPOINT_DOCSUM="http://${host_ip}:9009"
 export BACKEND_SERVICE_ENDPOINT_CHATQNA="http://${host_ip}:8888/v1/chatqna"
 export DATAPREP_DELETE_FILE_ENDPOINT="http://${host_ip}:5000/v1/dataprep/delete"
-export BACKEND_SERVICE_ENDPOINT_FAQGEN="http://${host_ip}:8889/v1/faqgen"
 export BACKEND_SERVICE_ENDPOINT_CODEGEN="http://${host_ip}:7778/v1/codegen"
 export BACKEND_SERVICE_ENDPOINT_DOCSUM="http://${host_ip}:8890/v1/docsum"
 export DATAPREP_SERVICE_ENDPOINT="http://${host_ip}:5000/v1/dataprep/ingest"
@@ -316,31 +308,23 @@ Please refer to **[keycloak_setup_guide](keycloak_setup_guide.md)** for more det
          }'
     ```
 
-13. FAQGen MegaService
-
-    ```bash
-    curl http://${host_ip}:8889/v1/faqgen -H "Content-Type: application/json" -d '{
-         "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."
-         }'
-    ```
-
-14. DocSum MegaService
+13. DocSum MegaService
 
     ```bash
     curl http://${host_ip}:8890/v1/docsum -H "Content-Type: application/json" -d '{
          "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."
          }'
     ```
 
-15. CodeGen MegaService
+14. CodeGen MegaService
 
     ```bash
     curl http://${host_ip}:7778/v1/codegen -H "Content-Type: application/json" -d '{
          "messages": "def print_hello_world():"
          }'
     ```
 
-16. Dataprep Microservice
+15. Dataprep Microservice
 
     If you want to update the default knowledge base, you can use the following commands:
 
@@ -390,7 +374,7 @@ Please refer to **[keycloak_setup_guide](keycloak_setup_guide.md)** for more det
          -H "Content-Type: application/json"
     ```
 
-17. Prompt Registry Microservice
+16. Prompt Registry Microservice
 
     If you want to update the default Prompts in the application for your user, you can use the following commands:
 
@@ -433,7 +417,7 @@ Please refer to **[keycloak_setup_guide](keycloak_setup_guide.md)** for more det
       "user": "test", "prompt_id":"{prompt_id to be deleted}"}'
     ```
 
-18. Chat History Microservice
+17. Chat History Microservice
 
     To validate the chatHistory Microservice, you can use the following commands.
 

ProductivitySuite/docker_compose/intel/cpu/xeon/compose.yaml

@@ -280,24 +280,6 @@ services:
       FAQGen_COMPONENT_NAME: ${FAQGen_COMPONENT_NAME}
       LOGFLAG: ${LOGFLAG:-False}
     restart: unless-stopped
-  faqgen-xeon-backend-server:
-    image: ${REGISTRY:-opea}/faqgen:${TAG:-latest}
-    container_name: faqgen-xeon-backend-server
-    depends_on:
-      - tgi_service
-      - llm_faqgen
-    ports:
-      - "8889:8888"
-    environment:
-      no_proxy: ${no_proxy}
-      https_proxy: ${https_proxy}
-      http_proxy: ${http_proxy}
-      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}
-      LOGFLAG: ${LOGFLAG}
-    ipc: host
-    restart: always
   mongo:
     image: mongo:7.0.11
     container_name: mongodb
@@ -362,7 +344,6 @@ services:
       - APP_BACKEND_SERVICE_ENDPOINT_CHATQNA=${BACKEND_SERVICE_ENDPOINT_CHATQNA}
       - APP_BACKEND_SERVICE_ENDPOINT_CODEGEN=${BACKEND_SERVICE_ENDPOINT_CODEGEN}
       - APP_BACKEND_SERVICE_ENDPOINT_DOCSUM=${BACKEND_SERVICE_ENDPOINT_DOCSUM}
-      - APP_BACKEND_SERVICE_ENDPOINT_FAQGEN=${BACKEND_SERVICE_ENDPOINT_FAQGEN}
       - APP_DATAPREP_SERVICE_ENDPOINT=${DATAPREP_SERVICE_ENDPOINT}
       - APP_DATAPREP_GET_FILE_ENDPOINT=${DATAPREP_GET_FILE_ENDPOINT}
       - APP_DATAPREP_DELETE_FILE_ENDPOINT=${DATAPREP_DELETE_FILE_ENDPOINT}

ProductivitySuite/docker_compose/intel/cpu/xeon/set_env.sh

@@ -33,7 +33,6 @@ export TGI_LLM_ENDPOINT_FAQGEN="http://${host_ip}:9009"
 export TGI_LLM_ENDPOINT_DOCSUM="http://${host_ip}:9009"
 export BACKEND_SERVICE_ENDPOINT_CHATQNA="http://${host_ip}:8888/v1/chatqna"
 export DATAPREP_DELETE_FILE_ENDPOINT="http://${host_ip}:5000/v1/dataprep/delete"
-export BACKEND_SERVICE_ENDPOINT_FAQGEN="http://${host_ip}:8889/v1/faqgen"
 export BACKEND_SERVICE_ENDPOINT_CODEGEN="http://${host_ip}:7778/v1/codegen"
 export BACKEND_SERVICE_ENDPOINT_DOCSUM="http://${host_ip}:8890/v1/docsum"
 export DATAPREP_SERVICE_ENDPOINT="http://${host_ip}:5000/v1/dataprep/ingest"

ProductivitySuite/docker_image_build/build.yaml

@@ -68,18 +68,12 @@ services:
       context: ../../CodeGen/
       dockerfile: ./Dockerfile
     image: ${REGISTRY:-opea}/codegen:${TAG:-latest}
-  faqgen:
+  llm-faqgen:
     build:
       args:
         http_proxy: ${http_proxy}
         https_proxy: ${https_proxy}
         no_proxy: ${no_proxy}
-      context: ../../FaqGen/
-      dockerfile: ./Dockerfile
-    image: ${REGISTRY:-opea}/faqgen:${TAG:-latest}
-  llm-faqgen:
-    build:
       context: GenAIComps
       dockerfile: comps/llms/src/faq-generation/Dockerfile
-    extends: faqgen
     image: ${REGISTRY:-opea}/llm-faqgen:${TAG:-latest}

ProductivitySuite/tests/test_compose_on_xeon.sh

@@ -58,7 +58,6 @@ function start_services() {
     export TGI_LLM_ENDPOINT_FAQGEN="http://${ip_address}:9009"
     export TGI_LLM_ENDPOINT_DOCSUM="http://${ip_address}:9009"
     export BACKEND_SERVICE_ENDPOINT_CHATQNA="http://${ip_address}:8888/v1/chatqna"
-    export BACKEND_SERVICE_ENDPOINT_FAQGEN="http://${ip_address}:8889/v1/faqgen"
     export DATAPREP_DELETE_FILE_ENDPOINT="http://${ip_address}:5000/v1/dataprep/delete"
     export BACKEND_SERVICE_ENDPOINT_CODEGEN="http://${ip_address}:7778/v1/codegen"
     export DATAPREP_SERVICE_ENDPOINT="http://${ip_address}:5000/v1/dataprep/ingest"
@@ -116,9 +115,6 @@ function validate_service() {
         HTTP_RESPONSE=$(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 [[ $SERVICE_NAME == *"faqgen-xeon-backend-server"* ]]; then
-        local INPUT_DATA="messages=Text Embeddings Inference (TEI) is a toolkit for deploying and serving open source text embeddings and sequence classification models. TEI enables high-performance extraction for the most popular models, including FlagEmbedding, Ember, GTE and E5."
-        HTTP_RESPONSE=$(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
@@ -145,33 +141,6 @@ function validate_service() {
     sleep 1s
 }
 
-function validate_faqgen_megaservice() {
-    local URL="$1"
-    local SERVICE_NAME="$2"
-    local DOCKER_NAME="$3"
-    local EXPECTED_RESULT="Embeddings"
-    local INPUT_DATA="messages=Text Embeddings Inference (TEI) is a toolkit for deploying and serving open source text embeddings and sequence classification models. TEI enables high-performance extraction for the most popular models, including FlagEmbedding, Ember, GTE and E5."
-    local HTTP_STATUS=$(curl -s -o /dev/null -w "%{http_code}" -X POST -F "$INPUT_DATA" -F "max_tokens=32" -F "stream=False" -H 'Content-Type: multipart/form-data' "$URL")
-    if [ "$HTTP_STATUS" -eq 200 ]; then
-        echo "[ $SERVICE_NAME ] HTTP status is 200. Checking content..."
-
-        local CONTENT=$(curl -s -X POST -F "$INPUT_DATA"  -F "max_tokens=32" -F "stream=False" -H 'Content-Type: multipart/form-data' "$URL" | tee ${LOG_PATH}/${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
-        echo "[ $SERVICE_NAME ] HTTP status is not 200. Received status was $HTTP_STATUS"
-        docker logs ${DOCKER_NAME} >> ${LOG_PATH}/${SERVICE_NAME}.log
-        exit 1
-    fi
-    sleep 1s
-}
-
 function validate_faqgen() {
     local URL="$1"
     local EXPECTED_RESULT="$2"
@@ -351,12 +320,6 @@ function validate_megaservice() {
         "chatqna-xeon-backend-server" \
         '{"messages": "What is the revenue of Nike in 2023?"}'\
 
-    # Curl the FAQGenMega Service
-    validate_faqgen_megaservice \
-        "${ip_address}:8889/v1/faqgen" \
-        "faqgen-xeon-backend-server" \
-        "faqgen-xeon-backend-server"
-
     # Curl the CodeGen Mega Service
     validate_service \
     "${ip_address}:7778/v1/codegen" \