Refactor text2sql. (#1304)

Signed-off-by: Yao, Qing <qing.yao@intel.com> Signed-off-by: chensuyue <suyue.chen@intel.com>
2025-01-02 10:52:21 +08:00
parent 6169ea4921
commit 72f8079289
7 changed files with 55 additions and 65 deletions
--- a/DBQnA/docker_compose/intel/cpu/xeon/README.md
+++ b/DBQnA/docker_compose/intel/cpu/xeon/README.md
@@ -11,7 +11,7 @@ First of all, you need to build Docker Images locally. This step can be ignored
 ```bash
 git clone https://github.com/opea-project/GenAIComps.git
 cd GenAIComps
-docker build --no-cache -t opea/texttosql:comps -f comps/texttosql/langchain/Dockerfile .
+docker build --no-cache -t opea/text2sql:comps -f comps/text2sql/src/Dockerfile .

 ```

@@ -21,13 +21,13 @@ Build the frontend Docker image based on react framework via below command:

 ```bash
 cd GenAIExamples/DBQnA/ui
-docker build --no-cache -t opea/texttosql-react-ui:latest -f docker/Dockerfile.react .
+docker build --no-cache -t opea/text2sql-react-ui:latest -f docker/Dockerfile.react .

 ```

 Then run the command `docker images`, you will have the following Docker Images:

-1. `opea/texttosql:latest`
+1. `opea/text2sql:latest`
 2. `opea/dbqna-react-ui:latest`

 ## 🚀 Start Microservices
@@ -62,7 +62,7 @@ export LLM_MODEL_ID="mistralai/Mistral-7B-Instruct-v0.3"
 export POSTGRES_USER=postgres
 export POSTGRES_PASSWORD=testpwd
 export POSTGRES_DB=chinook
-export texttosql_port=9090
+export text2sql_port=9090
 ```

 Note: Please replace with `your_ip` with your external IP address, do not use localhost.
@@ -90,14 +90,14 @@ We will use [Chinook](https://github.com/lerocha/chinook-database) sample databa

 ```bash

-docker run --name test-texttosql-postgres --ipc=host -e POSTGRES_USER=${POSTGRES_USER} -e POSTGRES_HOST_AUTH_METHOD=trust -e POSTGRES_DB=${POSTGRES_DB} -e POSTGRES_PASSWORD=${POSTGRES_PASSWORD} -p 5442:5432 -d -v $WORKPATH/comps/texttosql/langchain/chinook.sql:/docker-entrypoint-initdb.d/chinook.sql postgres:latest
+docker run --name test-text2sql-postgres --ipc=host -e POSTGRES_USER=${POSTGRES_USER} -e POSTGRES_HOST_AUTH_METHOD=trust -e POSTGRES_DB=${POSTGRES_DB} -e POSTGRES_PASSWORD=${POSTGRES_PASSWORD} -p 5442:5432 -d -v $WORKPATH/comps/text2sql/langchain/chinook.sql:/docker-entrypoint-initdb.d/chinook.sql postgres:latest
 ```

 - Start TGI Service

 ```bash

-docker run -d --name="test-texttosql-tgi-endpoint" --ipc=host -p $TGI_PORT:80 -v ./data:/data --shm-size 1g -e HUGGINGFACEHUB_API_TOKEN=${HUGGINGFACEHUB_API_TOKEN} -e HF_TOKEN=${HF_TOKEN} -e model=${model} ghcr.io/huggingface/text-generation-inference:2.1.0 --model-id $model
+docker run -d --name="test-text2sql-tgi-endpoint" --ipc=host -p $TGI_PORT:80 -v ./data:/data --shm-size 1g -e HUGGINGFACEHUB_API_TOKEN=${HUGGINGFACEHUB_API_TOKEN} -e HF_TOKEN=${HF_TOKEN} -e model=${model} ghcr.io/huggingface/text-generation-inference:2.1.0 --model-id $model
 ```

 - Start Text-to-SQL Service
@@ -105,7 +105,7 @@ docker run -d --name="test-texttosql-tgi-endpoint" --ipc=host -p $TGI_PORT:80 -v
 ```bash
 unset http_proxy

-docker run -d --name="test-texttosql-server" --ipc=host -p ${texttosql_port}:8090 --ipc=host -e http_proxy=$http_proxy -e https_proxy=$https_proxy -e TGI_LLM_ENDPOINT=$TGI_LLM_ENDPOINT opea/texttosql:latest
+docker run -d --name="test-text2sql-server" --ipc=host -p ${text2sql_port}:8090 --ipc=host -e http_proxy=$http_proxy -e https_proxy=$https_proxy -e TGI_LLM_ENDPOINT=$TGI_LLM_ENDPOINT opea/text2sql:latest
 ```

 - Start React UI service
@@ -141,7 +141,7 @@ curl --location http://${your_ip}:9090/v1/postgres/health \
 #### 3.2.2 Invoke the microservice.

 ```bash
-curl http://${your_ip}:9090/v1/texttosql\
+curl http://${your_ip}:9090/v1/text2sql\
    -X POST \
    -d '{"input_text": "Find the total number of Albums.","conn_str": {"user": "'${POSTGRES_USER}'","password": "'${POSTGRES_PASSWORD}'","host": "'${your_ip}'", "port": "5442", "database": "'${POSTGRES_DB}'"}}' \
    -H 'Content-Type: application/json'
--- a/DBQnA/docker_compose/intel/cpu/xeon/compose.yaml
+++ b/DBQnA/docker_compose/intel/cpu/xeon/compose.yaml
@@ -15,7 +15,8 @@ services:
      no_proxy: ${no_proxy}
      http_proxy: ${http_proxy}
      https_proxy: ${https_proxy}
-      HF_TOKEN: ${HF_TOKEN}
+      HF_TOKEN: ${HUGGINGFACEHUB_API_TOKEN}
+      HUGGINGFACEHUB_API_TOKEN: ${HUGGINGFACEHUB_API_TOKEN}
    shm_size: 1g
    command: --model-id ${LLM_MODEL_ID}

@@ -32,19 +33,19 @@ services:
    volumes:
      - ./chinook.sql:/docker-entrypoint-initdb.d/chinook.sql

-  texttosql-service:
-    image: opea/texttosql:latest
-    container_name: texttosql-service
+  text2sql-service:
+    image: ${REGISTRY:-opea}/text2sql:${TAG:-latest}
+    container_name: text2sql-service
    ports:
-      - "9090:8090"
+      - "9090:8080"
    environment:
      - TGI_LLM_ENDPOINT=${TGI_LLM_ENDPOINT}

  dbqna-xeon-react-ui-server:
-    image: opea/dbqna-react-ui:latest
+    image: ${REGISTRY:-opea}/text2sql-react-ui:${TAG:-latest}
    container_name: dbqna-xeon-react-ui-server
    depends_on:
-      - texttosql-service
+      - text2sql-service
    ports:
      - "5174:80"
    environment:
--- a/DBQnA/docker_image_build/build.yaml
+++ b/DBQnA/docker_image_build/build.yaml
@@ -2,16 +2,16 @@
 # SPDX-License-Identifier: Apache-2.0

 services:
-  texttosql:
+  text2sql:
    build:
      context: GenAIComps
-      dockerfile: comps/texttosql/langchain/Dockerfile
+      dockerfile: comps/text2sql/src/Dockerfile
      args:
        http_proxy: ${http_proxy}
        https_proxy: ${https_proxy}
        no_proxy: ${no_proxy}
-    image: ${REGISTRY:-opea}/texttosql:${TAG:-latest}
-  texttosql-react-ui:
+    image: ${REGISTRY:-opea}/text2sql:${TAG:-latest}
+  text2sql-react-ui:
    build:
      context: ../ui
      dockerfile: ./docker/Dockerfile.react
@@ -19,4 +19,4 @@ services:
        http_proxy: ${http_proxy}
        https_proxy: ${https_proxy}
        no_proxy: ${no_proxy}
-    image: ${REGISTRY:-opea}/texttosql-react-ui:${TAG:-latest}
+    image: ${REGISTRY:-opea}/text2sql-react-ui:${TAG:-latest}
--- a/DBQnA/tests/test_compose_on_xeon.sh
+++ b/DBQnA/tests/test_compose_on_xeon.sh
@@ -4,66 +4,54 @@

 set -xe

+IMAGE_REPO=${IMAGE_REPO:-"opea"}
+IMAGE_TAG=${IMAGE_TAG:-"latest"}
+echo "REGISTRY=IMAGE_REPO=${IMAGE_REPO}"
+echo "TAG=IMAGE_TAG=${IMAGE_TAG}"
+export REGISTRY=${IMAGE_REPO}
+export TAG=${IMAGE_TAG}
+
 WORKPATH=$(dirname "$PWD")
 LOG_PATH="$WORKPATH/tests"
 ip_address=$(hostname -I | awk '{print $1}')
 tgi_port=8008
-tgi_volume=$WORKPATH/data
-
-export model="meta-llama/Meta-Llama-3-8B-Instruct"
-export HUGGINGFACEHUB_API_TOKEN=${HUGGINGFACEHUB_API_TOKEN}
-export POSTGRES_USER=postgres
-export POSTGRES_PASSWORD=testpwd
-export POSTGRES_DB=chinook
-export TEXTTOSQL_PORT=9090
-export TGI_LLM_ENDPOINT="http://${ip_address}:${tgi_port}"
-

 function build_docker_images() {
-    echo $WORKPATH
-    OPEAPATH=$(realpath "$WORKPATH/../..")
-
-    echo "Building Text to Sql service..."
-    cd $OPEAPATH
-    rm -rf GenAIComps/
-    git clone https://github.com/opea-project/GenAIComps.git
-    cd $OPEAPATH/GenAIComps
-    docker build --no-cache -t opea/texttosql:latest -f comps/texttosql/langchain/Dockerfile .
-
-    echo "Building React UI service..."
-    cd $OPEAPATH/GenAIExamples/DBQnA/ui
-    docker build --no-cache -t opea/dbqna-react-ui:latest -f docker/Dockerfile.react .
+    cd $WORKPATH/docker_image_build
+    git clone https://github.com/opea-project/GenAIComps.git && cd GenAIComps && git checkout "${opea_branch:-"main"}" && cd ../

+    echo "Build all the images with --no-cache, check docker_image_build.log for details..."
+    docker compose -f build.yaml build --no-cache > ${LOG_PATH}/docker_image_build.log
 }

 function start_service() {
+    cd $WORKPATH/docker_compose/intel/cpu/xeon
+    export model="mistralai/Mistral-7B-Instruct-v0.3"
+    export LLM_MODEL_ID=${model}
+    export HUGGINGFACEHUB_API_TOKEN=${HUGGINGFACEHUB_API_TOKEN}
+    export POSTGRES_USER=postgres
+    export POSTGRES_PASSWORD=testpwd
+    export POSTGRES_DB=chinook
+    export TEXT2SQL_PORT=9090
+    export TGI_LLM_ENDPOINT="http://${ip_address}:${tgi_port}"

-    docker run --name test-texttosql-postgres --ipc=host -e POSTGRES_USER=${POSTGRES_USER} -e POSTGRES_HOST_AUTH_METHOD=trust -e POSTGRES_DB=${POSTGRES_DB} -e POSTGRES_PASSWORD=${POSTGRES_PASSWORD} -p 5442:5432 -d -v $WORKPATH/docker_compose/intel/cpu/xeon/chinook.sql:/docker-entrypoint-initdb.d/chinook.sql postgres:latest
-
-    docker run -d --name="test-texttosql-tgi-endpoint" --ipc=host -p $tgi_port:80 -v ./data:/data --shm-size 1g -e HUGGINGFACEHUB_API_TOKEN=${HUGGINGFACEHUB_API_TOKEN} -e HF_TOKEN=${HUGGINGFACEHUB_API_TOKEN} -e model=${model} ghcr.io/huggingface/text-generation-inference:2.1.0 --model-id $model
-
-
-    docker run -d --name="test-texttosql-server" --ipc=host -p $TEXTTOSQL_PORT:8090 --ipc=host -e http_proxy=$http_proxy -e https_proxy=$https_proxy -e TGI_LLM_ENDPOINT=$TGI_LLM_ENDPOINT opea/texttosql:latest
+    # Start Docker Containers
+    docker compose -f compose.yaml up -d > ${LOG_PATH}/start_services_with_compose.log

    # check whether tgi is fully ready.
    n=0
    until [[ "$n" -ge 100 ]] || [[ $ready == true ]]; do
-        docker logs test-texttosql-tgi-endpoint > ${LOG_PATH}/tgi.log
+        docker logs tgi-service > ${LOG_PATH}/tgi.log
        n=$((n+1))
        if grep -q Connected ${LOG_PATH}/tgi.log; then
            break
        fi
        sleep 5s
    done
-    sleep 5s
-
-    # Run the UI container
-    docker run -d --name="test-dbqna-react-ui-server" --ipc=host -p 5174:80 -e no_proxy=$no_proxy -e https_proxy=$https_proxy -e http_proxy=$http_proxy opea/dbqna-react-ui:latest
-
 }

 function validate_microservice() {
-    result=$(http_proxy="" curl --connect-timeout 5 --max-time 120000 http://${ip_address}:$TEXTTOSQL_PORT/v1/texttosql\
+    result=$(http_proxy="" curl --connect-timeout 5 --max-time 120000 http://${ip_address}:$TEXT2SQL_PORT/v1/text2sql\
        -X POST \
        -d '{"input_text": "Find the total number of Albums.","conn_str": {"user": "'${POSTGRES_USER}'","password": "'${POSTGRES_PASSWORD}'","host": "'${ip_address}'", "port": "5442", "database": "'${POSTGRES_DB}'" }}' \
        -H 'Content-Type: application/json')
@@ -73,8 +61,8 @@ function validate_microservice() {
        echo "Result correct."
    else
        echo "Result wrong. Received was $result"
-        docker logs test-texttosql-server > ${LOG_PATH}/texttosql.log
-        docker logs test-texttosql-tgi-endpoint > ${LOG_PATH}/tgi.log
+        docker logs text2sql-service > ${LOG_PATH}/text2sql.log
+        docker logs tgi-service > ${LOG_PATH}/tgi.log
        exit 1
    fi

@@ -110,8 +98,8 @@ function validate_frontend() {
 }

 function stop_docker() {
-    cid=$(docker ps -aq --filter "name=test-*")
-    if [[ ! -z "$cid" ]]; then docker stop $cid && docker rm $cid && sleep 1s; fi
+    cd $WORKPATH/docker_compose/intel/cpu/xeon
+    docker compose stop && docker compose rm -f
 }

 function main() {
--- a/DBQnA/ui/react/src/App.test.tsx
+++ b/DBQnA/ui/react/src/App.test.tsx
@@ -21,7 +21,7 @@ const getHostIP = () => {
 test('testing api with dynamic host', async () => {
  // Get the dynamic host IP
  const host = await getHostIP();
-  const endpointUrl = `http://${host}:9090/v1/texttosql`;
+  const endpointUrl = `http://${host}:9090/v1/text2sql`;

  const formData = {
    user: 'postgres',
@@ -43,9 +43,10 @@ test('testing api with dynamic host', async () => {
  expect(response.status).toBe(200);

  const result = response.data.result;
+  console.log(result);
  expect(result.hasOwnProperty('sql')).toBe(true);
  expect(result.hasOwnProperty('output')).toBe(true);
  expect(result.hasOwnProperty('input')).toBe(true);
-  expect(result.input).toBe(question);
+  expect(result.input.input_text).toBe(question);

 }, apiTimeOutInSeconds * 1000);
--- a/DBQnA/ui/react/src/components/DbConnect/DBConnect.tsx
+++ b/DBQnA/ui/react/src/components/DbConnect/DBConnect.tsx
@@ -79,7 +79,7 @@ const DBConnect: React.FC = () => {
      };

      let api_response: Record<string, any>;
-      api_response = await axios.post(`${TEXT_TO_SQL_URL}/texttosql`, payload);
+      api_response = await axios.post(`${TEXT_TO_SQL_URL}/text2sql`, payload);

      setSqlQuery(api_response.data.result.sql); // Assuming the API returns an SQL query
      setQueryOutput(api_response.data.result.output);
@@ -163,7 +163,7 @@ const DBConnect: React.FC = () => {
      </div>

      {/* DBQnA Section */}
-      <div className={styleClasses.textToSQLSection}>
+      <div className={styleClasses.text2SQLSection}>
        <Title order={1}>DBQnA</Title>
        {isConnected && (
          <form className={styleClasses.form} onSubmit={handleGenerateSQL}>
--- a/DBQnA/ui/react/src/components/DbConnect/dbconnect.module.scss
+++ b/DBQnA/ui/react/src/components/DbConnect/dbconnect.module.scss
@@ -19,7 +19,7 @@
  }

  .dbConnectSection,
-  .textToSQLSection {
+  .text2SQLSection {
    flex: 1; /* Allow each section to take up equal space */
    padding: 20px;
    background-color: white;