init
This commit is contained in:
+28
-1
@@ -1,6 +1,7 @@
|
||||
# Python 虚拟环境
|
||||
venv/
|
||||
.venv/
|
||||
env/
|
||||
|
||||
# Python 缓存文件
|
||||
__pycache__/
|
||||
@@ -8,11 +9,37 @@ __pycache__/
|
||||
*.pyo
|
||||
*.pyd
|
||||
|
||||
# IDE 配置（可选）
|
||||
# IDE 配置
|
||||
.idea/
|
||||
.vscode/
|
||||
*.swp
|
||||
*.swo
|
||||
|
||||
# 项目临时文件
|
||||
.DS_Store
|
||||
Thumbs.db
|
||||
|
||||
# 日志文件
|
||||
logs/
|
||||
*.log
|
||||
|
||||
# 测试相关
|
||||
.pytest_cache/
|
||||
.coverage
|
||||
htmlcov/
|
||||
.tox/
|
||||
|
||||
# Docker
|
||||
docker-compose.override.yml
|
||||
.env.docker
|
||||
|
||||
# 数据库
|
||||
*.db
|
||||
*.sqlite
|
||||
*.sqlite3
|
||||
|
||||
# 临时文件
|
||||
tmp/
|
||||
temp/
|
||||
*.tmp
|
||||
|
||||
|
||||
Vendored
-231
@@ -1,231 +0,0 @@
|
||||
pipeline {
|
||||
agent any
|
||||
|
||||
environment {
|
||||
// GitLab配置
|
||||
GITLAB_URL = 'https://gitlab.xpaas.lenovo.com'
|
||||
GITLAB_REPO = 'artificial-intelligence-platform/lenovo-ipc'
|
||||
GITLAB_CREDENTIALS_ID = 'git-ipc'
|
||||
|
||||
// 镜像仓库配置 (10.128.62.130:8843)
|
||||
REGISTRY_URL = '10.128.62.130:8843'
|
||||
REGISTRY_CREDENTIALS_ID = 'docker-registry-130'
|
||||
|
||||
// 镜像配置
|
||||
IMAGE_NAME = 'more_dots'
|
||||
FULL_IMAGE_NAME = "${REGISTRY_URL}/${IMAGE_NAME}"
|
||||
|
||||
// 是否跳过构建（运行时赋值）
|
||||
SKIP_BUILD = 'false'
|
||||
|
||||
K8S_NAMESPACE = 'more-dots'
|
||||
}
|
||||
|
||||
parameters {
|
||||
choice(name: 'DEPLOY_ENV', choices: ['dev', 'staging', 'prod'], description: '选择部署环境')
|
||||
choice(name: 'TARGET_CLUSTER', choices: ['cluster1', 'cluster2', 'both'], description: '选择目标集群')
|
||||
}
|
||||
|
||||
stages {
|
||||
stage('Checkout') {
|
||||
steps {
|
||||
git(
|
||||
url: "${GITLAB_URL}/${GITLAB_REPO}.git",
|
||||
credentialsId: GITLAB_CREDENTIALS_ID,
|
||||
branch: 'master'
|
||||
)
|
||||
script {
|
||||
env.GIT_COMMIT = sh(script: 'git rev-parse HEAD', returnStdout: true).trim()
|
||||
env.SOURCE_TREE = sh(script: 'git rev-parse HEAD:more_dots', returnStdout: true).trim()
|
||||
env.IMAGE_TAG = env.SOURCE_TREE.take(12)
|
||||
|
||||
echo "GIT_COMMIT: ${env.GIT_COMMIT}"
|
||||
echo "SOURCE_TREE: ${env.SOURCE_TREE}"
|
||||
echo "IMAGE_TAG: ${env.IMAGE_TAG}"
|
||||
echo "FULL_IMAGE_NAME: ${FULL_IMAGE_NAME}:${env.IMAGE_TAG}"
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
stage('Check Code Changes') {
|
||||
steps {
|
||||
script {
|
||||
def prev = env.GIT_PREVIOUS_SUCCESSFUL_COMMIT ?: ''
|
||||
|
||||
if (!prev?.trim()) {
|
||||
echo "未找到上次成功构建提交，默认执行构建"
|
||||
env.SKIP_BUILD = 'false'
|
||||
} else {
|
||||
int rc = sh(
|
||||
script: "git diff --quiet ${prev} HEAD -- more_dots",
|
||||
returnStatus: true
|
||||
)
|
||||
env.SKIP_BUILD = (rc == 0) ? 'true' : 'false'
|
||||
}
|
||||
|
||||
echo "代码变更检查结果: SKIP_BUILD=${env.SKIP_BUILD}"
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
stage('Build Docker Image') {
|
||||
when {
|
||||
expression { env.SKIP_BUILD != 'true' }
|
||||
}
|
||||
steps {
|
||||
dir('more_dots') {
|
||||
sh """
|
||||
docker build --progress=plain \
|
||||
--build-arg PIP_OPTIONS="--no-hash-check" \
|
||||
-t ${IMAGE_NAME}:${env.IMAGE_TAG} .
|
||||
"""
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
stage('Push to Registry') {
|
||||
when {
|
||||
expression { env.SKIP_BUILD != 'true' }
|
||||
}
|
||||
steps {
|
||||
script {
|
||||
withCredentials([usernamePassword(
|
||||
credentialsId: REGISTRY_CREDENTIALS_ID,
|
||||
usernameVariable: 'REGISTRY_USER',
|
||||
passwordVariable: 'REGISTRY_PASS'
|
||||
)]) {
|
||||
sh """
|
||||
set -eux
|
||||
echo "登录到镜像仓库 ${REGISTRY_URL}..."
|
||||
echo "${REGISTRY_PASS}" | docker login ${REGISTRY_URL} -u ${REGISTRY_USER} --password-stdin
|
||||
"""
|
||||
}
|
||||
|
||||
sh """
|
||||
set -eux
|
||||
echo "打标签: ${IMAGE_NAME}:${IMAGE_TAG} -> ${FULL_IMAGE_NAME}:${IMAGE_TAG}"
|
||||
docker tag ${IMAGE_NAME}:${IMAGE_TAG} ${FULL_IMAGE_NAME}:${IMAGE_TAG}
|
||||
|
||||
echo "推送镜像到仓库..."
|
||||
docker push ${FULL_IMAGE_NAME}:${IMAGE_TAG}
|
||||
|
||||
echo "镜像推送完成: ${FULL_IMAGE_NAME}:${IMAGE_TAG}"
|
||||
"""
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
stage('Deploy to k3s') {
|
||||
steps {
|
||||
script {
|
||||
// 检查 k8s 配置文件是否存在
|
||||
if (!fileExists('more_dots/k8s/deployment.yaml')) {
|
||||
error "错误: more_dots/k8s/deployment.yaml 文件不存在于代码仓库中"
|
||||
}
|
||||
|
||||
def fullImageWithTag = "${FULL_IMAGE_NAME}:${env.IMAGE_TAG}"
|
||||
def cluster = params.TARGET_CLUSTER
|
||||
|
||||
if (cluster == 'cluster1' || cluster == 'both') {
|
||||
deployToCluster('k3s-cluster1-config', fullImageWithTag, params.DEPLOY_ENV)
|
||||
}
|
||||
|
||||
if (cluster == 'cluster2' || cluster == 'both') {
|
||||
deployToCluster('k3s-cluster2-config', fullImageWithTag, params.DEPLOY_ENV)
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
post {
|
||||
always {
|
||||
script {
|
||||
sh """
|
||||
docker logout ${REGISTRY_URL} || true
|
||||
docker rmi ${FULL_IMAGE_NAME}:${env.IMAGE_TAG} || true
|
||||
"""
|
||||
}
|
||||
cleanWs()
|
||||
echo "构建结束。镜像标签: ${env.IMAGE_TAG}"
|
||||
echo "完整镜像: ${FULL_IMAGE_NAME}:${env.IMAGE_TAG}"
|
||||
echo "是否跳过构建: ${env.SKIP_BUILD}"
|
||||
echo "部署环境: ${params.DEPLOY_ENV}"
|
||||
echo "目标集群: ${params.TARGET_CLUSTER}"
|
||||
}
|
||||
failure {
|
||||
echo "构建失败，请检查日志"
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
// 部署函数
|
||||
def deployToCluster(String clusterConfigId, String fullImageWithTag, String deployEnv) {
|
||||
withCredentials([
|
||||
file(credentialsId: clusterConfigId, variable: 'KUBECONFIG'),
|
||||
usernamePassword(credentialsId: REGISTRY_CREDENTIALS_ID,
|
||||
usernameVariable: 'REGISTRY_USER',
|
||||
passwordVariable: 'REGISTRY_PASS')
|
||||
]) {
|
||||
sh """
|
||||
set -eux
|
||||
|
||||
# 查找kubectl路径
|
||||
KUBECTL_PATH=\$(command -v kubectl 2>/dev/null || true)
|
||||
if [ -z "\$KUBECTL_PATH" ]; then
|
||||
for p in /usr/local/bin/kubectl /usr/bin/kubectl /bin/kubectl; do
|
||||
if [ -x "\$p" ]; then
|
||||
KUBECTL_PATH="\$p"
|
||||
break
|
||||
fi
|
||||
done
|
||||
fi
|
||||
|
||||
if [ -z "\$KUBECTL_PATH" ]; then
|
||||
echo "kubectl 未找到，请检查 Jenkins 节点环境"
|
||||
exit 1
|
||||
fi
|
||||
|
||||
echo "使用kubectl路径: \$KUBECTL_PATH"
|
||||
echo "部署到集群: ${clusterConfigId}"
|
||||
echo "部署环境: ${deployEnv}"
|
||||
echo "镜像: ${fullImageWithTag}"
|
||||
echo "命名空间: ${K8S_NAMESPACE}"
|
||||
|
||||
# 定义kubectl函数
|
||||
k() {
|
||||
sudo \$KUBECTL_PATH --kubeconfig=${KUBECONFIG} "\$@"
|
||||
}
|
||||
|
||||
# 检查命名空间
|
||||
k get namespace ${K8S_NAMESPACE} || k create namespace ${K8S_NAMESPACE}
|
||||
|
||||
# 创建imagePullSecret
|
||||
k create secret docker-registry regcred-130 \\
|
||||
--docker-server=${REGISTRY_URL} \\
|
||||
--docker-username=${REGISTRY_USER} \\
|
||||
--docker-password=${REGISTRY_PASS} \\
|
||||
--namespace=${K8S_NAMESPACE} \\
|
||||
--dry-run=client -o yaml | k apply -f -
|
||||
|
||||
# 替换镜像标签和环境变量并部署
|
||||
sed -e "s|image:.*more_dots:.*|image: ${fullImageWithTag}|g" \\
|
||||
-e "s|value: \".*\"|value: \"${deployEnv}\"|g" \\
|
||||
more_dots/k8s/deployment.yaml > /tmp/deployment-${K8S_NAMESPACE}.yaml
|
||||
|
||||
echo "部署配置:"
|
||||
cat /tmp/deployment-${K8S_NAMESPACE}.yaml
|
||||
|
||||
# 应用配置到 more-dots 命名空间
|
||||
k apply -f /tmp/deployment-${K8S_NAMESPACE}.yaml -n ${K8S_NAMESPACE}
|
||||
|
||||
# 等待部署完成
|
||||
echo "等待部署完成..."
|
||||
k rollout status deployment/more-dots -n ${K8S_NAMESPACE} --timeout=300s
|
||||
|
||||
# 显示部署状态
|
||||
echo "部署完成，查看pod状态："
|
||||
k get pods -n ${K8S_NAMESPACE} -l app=more-dots
|
||||
"""
|
||||
}
|
||||
}
|
||||
-203
@@ -1,203 +0,0 @@
|
||||
pipeline {
|
||||
agent any
|
||||
|
||||
environment {
|
||||
GITLAB_URL = 'https://gitlab.xpaas.lenovo.com'
|
||||
GITLAB_REPO = 'artificial-intelligence-platform/lenovo-ipc'
|
||||
GITLAB_CREDENTIALS_ID = 'git-ipc'
|
||||
|
||||
REGISTRY_URL = '10.128.62.130:8843'
|
||||
REGISTRY_CREDENTIALS_ID = 'docker-registry-130'
|
||||
|
||||
IMAGE_NAME = 'more_dots'
|
||||
FULL_IMAGE_NAME = "${REGISTRY_URL}/${IMAGE_NAME}"
|
||||
|
||||
SKIP_BUILD = 'false'
|
||||
K8S_NAMESPACE = 'more-dots'
|
||||
|
||||
CLUSTER_CONFIG_ID = 'k3s-cluster1-config'
|
||||
CLUSTER_NAME = 'cluster1'
|
||||
}
|
||||
|
||||
stages {
|
||||
stage('Checkout') {
|
||||
steps {
|
||||
git(
|
||||
url: "${GITLAB_URL}/${GITLAB_REPO}.git",
|
||||
credentialsId: GITLAB_CREDENTIALS_ID,
|
||||
branch: 'master'
|
||||
)
|
||||
script {
|
||||
env.GIT_COMMIT = sh(script: 'git rev-parse HEAD', returnStdout: true).trim()
|
||||
env.SOURCE_TREE = sh(script: 'git rev-parse HEAD:more_dots', returnStdout: true).trim()
|
||||
env.IMAGE_TAG = env.SOURCE_TREE.take(12)
|
||||
|
||||
echo "GIT_COMMIT: ${env.GIT_COMMIT}"
|
||||
echo "SOURCE_TREE: ${env.SOURCE_TREE}"
|
||||
echo "IMAGE_TAG: ${env.IMAGE_TAG}"
|
||||
echo "FULL_IMAGE_NAME: ${FULL_IMAGE_NAME}:${env.IMAGE_TAG}"
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
stage('Check Code Changes') {
|
||||
steps {
|
||||
script {
|
||||
def prev = env.GIT_PREVIOUS_SUCCESSFUL_COMMIT ?: ''
|
||||
if (!prev?.trim()) {
|
||||
echo "未找到上次成功构建提交，默认执行构建"
|
||||
env.SKIP_BUILD = 'false'
|
||||
} else {
|
||||
int rc = sh(
|
||||
script: "git diff --quiet ${prev} HEAD -- more_dots",
|
||||
returnStatus: true
|
||||
)
|
||||
env.SKIP_BUILD = (rc == 0) ? 'true' : 'false'
|
||||
}
|
||||
|
||||
echo "代码变更检查结果: SKIP_BUILD=${env.SKIP_BUILD}"
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
stage('Build Docker Image') {
|
||||
when {
|
||||
expression { env.SKIP_BUILD != 'true' }
|
||||
}
|
||||
steps {
|
||||
dir('more_dots') {
|
||||
sh """
|
||||
docker build --progress=plain \
|
||||
--build-arg PIP_OPTIONS=\"--no-hash-check\" \
|
||||
-t ${IMAGE_NAME}:${env.IMAGE_TAG} .
|
||||
"""
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
stage('Push to Registry') {
|
||||
when {
|
||||
expression { env.SKIP_BUILD != 'true' }
|
||||
}
|
||||
steps {
|
||||
script {
|
||||
withCredentials([usernamePassword(
|
||||
credentialsId: REGISTRY_CREDENTIALS_ID,
|
||||
usernameVariable: 'REGISTRY_USER',
|
||||
passwordVariable: 'REGISTRY_PASS'
|
||||
)]) {
|
||||
sh '''
|
||||
set -eux
|
||||
echo "登录到镜像仓库 ${REGISTRY_URL}..."
|
||||
printf '%s' "$REGISTRY_PASS" | docker login "$REGISTRY_URL" -u "$REGISTRY_USER" --password-stdin
|
||||
'''
|
||||
}
|
||||
|
||||
sh '''
|
||||
set -eux
|
||||
echo "打标签: ${IMAGE_NAME}:${IMAGE_TAG} -> ${FULL_IMAGE_NAME}:${IMAGE_TAG}"
|
||||
docker tag "${IMAGE_NAME}:${IMAGE_TAG}" "${FULL_IMAGE_NAME}:${IMAGE_TAG}"
|
||||
|
||||
echo "推送镜像到仓库..."
|
||||
docker push "${FULL_IMAGE_NAME}:${IMAGE_TAG}"
|
||||
|
||||
echo "镜像推送完成: ${FULL_IMAGE_NAME}:${IMAGE_TAG}"
|
||||
'''
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
stage('Deploy to k3s') {
|
||||
steps {
|
||||
script {
|
||||
if (!fileExists('more_dots/k8s/deployment.yaml')) {
|
||||
error "错误: more_dots/k8s/deployment.yaml 文件不存在于代码仓库中"
|
||||
}
|
||||
|
||||
def fullImageWithTag = "${FULL_IMAGE_NAME}:${env.IMAGE_TAG}"
|
||||
deployToCluster(CLUSTER_CONFIG_ID, fullImageWithTag)
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
post {
|
||||
always {
|
||||
script {
|
||||
sh '''
|
||||
docker logout "${REGISTRY_URL}" || true
|
||||
docker rmi "${FULL_IMAGE_NAME}:${IMAGE_TAG}" || true
|
||||
'''
|
||||
}
|
||||
cleanWs()
|
||||
echo "构建结束。镜像标签: ${env.IMAGE_TAG}"
|
||||
echo "完整镜像: ${FULL_IMAGE_NAME}:${env.IMAGE_TAG}"
|
||||
echo "是否跳过构建: ${env.SKIP_BUILD}"
|
||||
echo "目标集群: ${CLUSTER_NAME}"
|
||||
}
|
||||
failure {
|
||||
echo "构建失败，请检查日志"
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
def deployToCluster(String clusterConfigId, String fullImageWithTag) {
|
||||
withCredentials([
|
||||
file(credentialsId: clusterConfigId, variable: 'KUBECONFIG'),
|
||||
usernamePassword(credentialsId: REGISTRY_CREDENTIALS_ID,
|
||||
usernameVariable: 'REGISTRY_USER',
|
||||
passwordVariable: 'REGISTRY_PASS')
|
||||
]) {
|
||||
withEnv([
|
||||
"FULL_IMAGE_WITH_TAG=${fullImageWithTag}"
|
||||
]) {
|
||||
sh '''
|
||||
set -eux
|
||||
|
||||
KUBECTL_PATH=$(command -v kubectl 2>/dev/null || true)
|
||||
if [ -z "$KUBECTL_PATH" ]; then
|
||||
for p in /usr/local/bin/kubectl /usr/bin/kubectl /bin/kubectl; do
|
||||
if [ -x "$p" ]; then
|
||||
KUBECTL_PATH="$p"
|
||||
break
|
||||
fi
|
||||
done
|
||||
fi
|
||||
|
||||
if [ -z "$KUBECTL_PATH" ]; then
|
||||
echo "kubectl 未找到，请检查 Jenkins 节点环境"
|
||||
exit 1
|
||||
fi
|
||||
|
||||
echo "使用kubectl路径: $KUBECTL_PATH"
|
||||
echo "部署到集群: ${CLUSTER_NAME}"
|
||||
echo "镜像: ${FULL_IMAGE_WITH_TAG}"
|
||||
echo "命名空间: ${K8S_NAMESPACE}"
|
||||
|
||||
k() {
|
||||
sudo "$KUBECTL_PATH" --kubeconfig="$KUBECONFIG" "$@"
|
||||
}
|
||||
|
||||
k get namespace "${K8S_NAMESPACE}" || k create namespace "${K8S_NAMESPACE}"
|
||||
|
||||
k create secret docker-registry regcred-130 \
|
||||
--docker-server="${REGISTRY_URL}" \
|
||||
--docker-username="${REGISTRY_USER}" \
|
||||
--docker-password="${REGISTRY_PASS}" \
|
||||
--namespace="${K8S_NAMESPACE}" \
|
||||
--dry-run=client -o yaml | k apply -f -
|
||||
|
||||
sed -E "s|^([[:space:]]*image:).*$|\1 ${FULL_IMAGE_WITH_TAG}|" \
|
||||
more_dots/k8s/deployment.yaml > /tmp/deployment-${K8S_NAMESPACE}.yaml
|
||||
|
||||
k apply -f /tmp/deployment-${K8S_NAMESPACE}.yaml -n "${K8S_NAMESPACE}"
|
||||
|
||||
echo "等待部署完成..."
|
||||
k rollout status deployment/more-dots -n "${K8S_NAMESPACE}" --timeout=300s
|
||||
|
||||
echo "部署完成，查看pod状态："
|
||||
k get pods -n "${K8S_NAMESPACE}" -l app=more-dots
|
||||
'''
|
||||
}
|
||||
}
|
||||
}
|
||||
@@ -1,203 +0,0 @@
|
||||
pipeline {
|
||||
agent any
|
||||
|
||||
environment {
|
||||
GITLAB_URL = 'https://gitlab.xpaas.lenovo.com'
|
||||
GITLAB_REPO = 'artificial-intelligence-platform/lenovo-ipc'
|
||||
GITLAB_CREDENTIALS_ID = 'git-ipc'
|
||||
|
||||
REGISTRY_URL = '10.128.62.130:8843'
|
||||
REGISTRY_CREDENTIALS_ID = 'docker-registry-130'
|
||||
|
||||
IMAGE_NAME = 'more_dots'
|
||||
FULL_IMAGE_NAME = "${REGISTRY_URL}/${IMAGE_NAME}"
|
||||
|
||||
SKIP_BUILD = 'false'
|
||||
K8S_NAMESPACE = 'more-dots'
|
||||
|
||||
CLUSTER_CONFIG_ID = 'k3s-cluster2-config'
|
||||
CLUSTER_NAME = 'cluster2'
|
||||
}
|
||||
|
||||
stages {
|
||||
stage('Checkout') {
|
||||
steps {
|
||||
git(
|
||||
url: "${GITLAB_URL}/${GITLAB_REPO}.git",
|
||||
credentialsId: GITLAB_CREDENTIALS_ID,
|
||||
branch: 'master'
|
||||
)
|
||||
script {
|
||||
env.GIT_COMMIT = sh(script: 'git rev-parse HEAD', returnStdout: true).trim()
|
||||
env.SOURCE_TREE = sh(script: 'git rev-parse HEAD:more_dots', returnStdout: true).trim()
|
||||
env.IMAGE_TAG = env.SOURCE_TREE.take(12)
|
||||
|
||||
echo "GIT_COMMIT: ${env.GIT_COMMIT}"
|
||||
echo "SOURCE_TREE: ${env.SOURCE_TREE}"
|
||||
echo "IMAGE_TAG: ${env.IMAGE_TAG}"
|
||||
echo "FULL_IMAGE_NAME: ${FULL_IMAGE_NAME}:${env.IMAGE_TAG}"
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
stage('Check Code Changes') {
|
||||
steps {
|
||||
script {
|
||||
def prev = env.GIT_PREVIOUS_SUCCESSFUL_COMMIT ?: ''
|
||||
if (!prev?.trim()) {
|
||||
echo "未找到上次成功构建提交，默认执行构建"
|
||||
env.SKIP_BUILD = 'false'
|
||||
} else {
|
||||
int rc = sh(
|
||||
script: "git diff --quiet ${prev} HEAD -- more_dots",
|
||||
returnStatus: true
|
||||
)
|
||||
env.SKIP_BUILD = (rc == 0) ? 'true' : 'false'
|
||||
}
|
||||
|
||||
echo "代码变更检查结果: SKIP_BUILD=${env.SKIP_BUILD}"
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
stage('Build Docker Image') {
|
||||
when {
|
||||
expression { env.SKIP_BUILD != 'true' }
|
||||
}
|
||||
steps {
|
||||
dir('more_dots') {
|
||||
sh """
|
||||
docker build --progress=plain \
|
||||
--build-arg PIP_OPTIONS=\"--no-hash-check\" \
|
||||
-t ${IMAGE_NAME}:${env.IMAGE_TAG} .
|
||||
"""
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
stage('Push to Registry') {
|
||||
when {
|
||||
expression { env.SKIP_BUILD != 'true' }
|
||||
}
|
||||
steps {
|
||||
script {
|
||||
withCredentials([usernamePassword(
|
||||
credentialsId: REGISTRY_CREDENTIALS_ID,
|
||||
usernameVariable: 'REGISTRY_USER',
|
||||
passwordVariable: 'REGISTRY_PASS'
|
||||
)]) {
|
||||
sh '''
|
||||
set -eux
|
||||
echo "登录到镜像仓库 ${REGISTRY_URL}..."
|
||||
printf '%s' "$REGISTRY_PASS" | docker login "$REGISTRY_URL" -u "$REGISTRY_USER" --password-stdin
|
||||
'''
|
||||
}
|
||||
|
||||
sh '''
|
||||
set -eux
|
||||
echo "打标签: ${IMAGE_NAME}:${IMAGE_TAG} -> ${FULL_IMAGE_NAME}:${IMAGE_TAG}"
|
||||
docker tag "${IMAGE_NAME}:${IMAGE_TAG}" "${FULL_IMAGE_NAME}:${IMAGE_TAG}"
|
||||
|
||||
echo "推送镜像到仓库..."
|
||||
docker push "${FULL_IMAGE_NAME}:${IMAGE_TAG}"
|
||||
|
||||
echo "镜像推送完成: ${FULL_IMAGE_NAME}:${IMAGE_TAG}"
|
||||
'''
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
stage('Deploy to k3s') {
|
||||
steps {
|
||||
script {
|
||||
if (!fileExists('more_dots/k8s/deployment.yaml')) {
|
||||
error "错误: more_dots/k8s/deployment.yaml 文件不存在于代码仓库中"
|
||||
}
|
||||
|
||||
def fullImageWithTag = "${FULL_IMAGE_NAME}:${env.IMAGE_TAG}"
|
||||
deployToCluster(CLUSTER_CONFIG_ID, fullImageWithTag)
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
post {
|
||||
always {
|
||||
script {
|
||||
sh '''
|
||||
docker logout "${REGISTRY_URL}" || true
|
||||
docker rmi "${FULL_IMAGE_NAME}:${IMAGE_TAG}" || true
|
||||
'''
|
||||
}
|
||||
cleanWs()
|
||||
echo "构建结束。镜像标签: ${env.IMAGE_TAG}"
|
||||
echo "完整镜像: ${FULL_IMAGE_NAME}:${env.IMAGE_TAG}"
|
||||
echo "是否跳过构建: ${env.SKIP_BUILD}"
|
||||
echo "目标集群: ${CLUSTER_NAME}"
|
||||
}
|
||||
failure {
|
||||
echo "构建失败，请检查日志"
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
def deployToCluster(String clusterConfigId, String fullImageWithTag) {
|
||||
withCredentials([
|
||||
file(credentialsId: clusterConfigId, variable: 'KUBECONFIG'),
|
||||
usernamePassword(credentialsId: REGISTRY_CREDENTIALS_ID,
|
||||
usernameVariable: 'REGISTRY_USER',
|
||||
passwordVariable: 'REGISTRY_PASS')
|
||||
]) {
|
||||
withEnv([
|
||||
"FULL_IMAGE_WITH_TAG=${fullImageWithTag}"
|
||||
]) {
|
||||
sh '''
|
||||
set -eux
|
||||
|
||||
KUBECTL_PATH=$(command -v kubectl 2>/dev/null || true)
|
||||
if [ -z "$KUBECTL_PATH" ]; then
|
||||
for p in /usr/local/bin/kubectl /usr/bin/kubectl /bin/kubectl; do
|
||||
if [ -x "$p" ]; then
|
||||
KUBECTL_PATH="$p"
|
||||
break
|
||||
fi
|
||||
done
|
||||
fi
|
||||
|
||||
if [ -z "$KUBECTL_PATH" ]; then
|
||||
echo "kubectl 未找到，请检查 Jenkins 节点环境"
|
||||
exit 1
|
||||
fi
|
||||
|
||||
echo "使用kubectl路径: $KUBECTL_PATH"
|
||||
echo "部署到集群: ${CLUSTER_NAME}"
|
||||
echo "镜像: ${FULL_IMAGE_WITH_TAG}"
|
||||
echo "命名空间: ${K8S_NAMESPACE}"
|
||||
|
||||
k() {
|
||||
sudo "$KUBECTL_PATH" --kubeconfig="$KUBECONFIG" "$@"
|
||||
}
|
||||
|
||||
k get namespace "${K8S_NAMESPACE}" || k create namespace "${K8S_NAMESPACE}"
|
||||
|
||||
k create secret docker-registry regcred-130 \
|
||||
--docker-server="${REGISTRY_URL}" \
|
||||
--docker-username="${REGISTRY_USER}" \
|
||||
--docker-password="${REGISTRY_PASS}" \
|
||||
--namespace="${K8S_NAMESPACE}" \
|
||||
--dry-run=client -o yaml | k apply -f -
|
||||
|
||||
sed -E "s|^([[:space:]]*image:).*$|\1 ${FULL_IMAGE_WITH_TAG}|" \
|
||||
more_dots/k8s/deployment.yaml > /tmp/deployment-${K8S_NAMESPACE}.yaml
|
||||
|
||||
k apply -f /tmp/deployment-${K8S_NAMESPACE}.yaml -n "${K8S_NAMESPACE}"
|
||||
|
||||
echo "等待部署完成..."
|
||||
k rollout status deployment/more-dots -n "${K8S_NAMESPACE}" --timeout=300s
|
||||
|
||||
echo "部署完成，查看pod状态："
|
||||
k get pods -n "${K8S_NAMESPACE}" -l app=more-dots
|
||||
'''
|
||||
}
|
||||
}
|
||||
}
|
||||
@@ -0,0 +1,503 @@
|
||||
# More Dots 项目全面分析报告
|
||||
|
||||
**分析日期**: 2026-03-12
|
||||
**项目版本**: 1.0.0
|
||||
**分析范围**: 架构、代码质量、依赖、安全、性能
|
||||
|
||||
---
|
||||
|
||||
## 📊 执行摘要
|
||||
|
||||
### 项目评分
|
||||
|
||||
| 维度 | 评分 | 说明 |
|
||||
|------|------|------|
|
||||
| **架构设计** | ⭐⭐⭐⭐⭐ | 企业级分层架构，核心与业务分离 |
|
||||
| **代码质量** | ⭐⭐⭐⭐ | 代码规范，注释清晰 |
|
||||
| **可维护性** | ⭐⭐⭐⭐⭐ | 模块化设计，职责清晰 |
|
||||
| **可扩展性** | ⭐⭐⭐⭐⭐ | 易于添加新功能和代理 |
|
||||
| **文档完整性** | ⭐⭐⭐⭐⭐ | 文档详细，示例丰富 |
|
||||
| **测试覆盖** | ⭐⭐ | 测试较少，需要加强 |
|
||||
| **安全性** | ⭐⭐⭐⭐ | 配置管理良好，需加强输入验证 |
|
||||
| **性能优化** | ⭐⭐⭐ | 基础优化已做，可进一步优化 |
|
||||
|
||||
**总体评分**: ⭐⭐⭐⭐ (4.2/5)
|
||||
|
||||
---
|
||||
|
||||
## 🏗️ 架构分析
|
||||
|
||||
### 1. 目录结构
|
||||
|
||||
```
|
||||
more_dots/
|
||||
├── agent/ # Agent 模块（核心与扩展分离）⭐⭐⭐⭐⭐
|
||||
│ ├── core/ # 核心模块（基础功能）
|
||||
│ │ ├── base_agent.py # BaseAgent 基类
|
||||
│ │ ├── state.py # Agent 状态定义
|
||||
│ │ └── nodes.py # 节点执行逻辑
|
||||
│ ├── agents/ # 代理实现（业务扩展）
|
||||
│ │ ├── conversation.py # ConversationAgent
|
||||
│ │ └── tool.py # ToolAgent
|
||||
│ └── README.md # 详细文档
|
||||
│
|
||||
├── api/ # API 接口层 ⭐⭐⭐⭐
|
||||
│ ├── endpoints.py # FastAPI 路由
|
||||
│ └── dependencies.py # 依赖注入
|
||||
│
|
||||
├── config/ # 配置层 ⭐⭐⭐⭐⭐
|
||||
│ ├── core/ # 配置管理
|
||||
│ └── prompts/ # 提示词配置
|
||||
│
|
||||
├── services/ # 服务层 ⭐⭐⭐⭐
|
||||
│ ├── llm_factory.py # LLM 工厂
|
||||
│ ├── message_storage.py # MySQL 消息存储
|
||||
│ ├── nacos_service.py # Nacos 服务发现
|
||||
│ └── ragflow_client.py # RAGFlow 客户端
|
||||
│
|
||||
├── schemas/ # 数据模型层 ⭐⭐⭐⭐⭐
|
||||
│ └── 7 个 Pydantic DTO
|
||||
│
|
||||
├── tools/ # 工具模块 ⭐⭐⭐⭐
|
||||
│ └── 4 个工具类
|
||||
│
|
||||
├── workflows/ # 工作流管理 ⭐⭐⭐⭐⭐
|
||||
│ └── workflow_manager.py
|
||||
│
|
||||
├── docs/ # 文档 ⭐⭐⭐⭐⭐
|
||||
│ ├── streaming_conversation_flow.md
|
||||
│ └── conversation_code_analysis.md
|
||||
│
|
||||
└── tests/ # 测试 ⭐⭐
|
||||
└── 基础测试
|
||||
```
|
||||
|
||||
### 2. 架构模式
|
||||
|
||||
| 模式 | 应用位置 | 评分 |
|
||||
|------|----------|------|
|
||||
| **分层架构** | 整体架构 | ⭐⭐⭐⭐⭐ |
|
||||
| **依赖注入** | FastAPI lifespan | ⭐⭐⭐⭐⭐ |
|
||||
| **工厂模式** | llm_factory.py | ⭐⭐⭐⭐⭐ |
|
||||
| **策略模式** | Agent 响应生成 | ⭐⭐⭐⭐⭐ |
|
||||
| **状态模式** | LangGraph StateGraph | ⭐⭐⭐⭐⭐ |
|
||||
| **责任链** | Agent 节点处理 | ⭐⭐⭐⭐⭐ |
|
||||
| **单例模式** | 服务实例管理 | ⭐⭐⭐⭐ |
|
||||
|
||||
### 3. 模块依赖关系
|
||||
|
||||
```
|
||||
┌─────────────────────────────────────────────┐
|
||||
│ FastAPI (server.py) │
|
||||
└─────────────────┬───────────────────────────┘
|
||||
│
|
||||
┌─────────┴─────────┐
|
||||
│ │
|
||||
┌───────▼───────┐ ┌──────▼──────┐
|
||||
│ API Layer │ │Workflows │
|
||||
│ (endpoints) │ │(Manager) │
|
||||
└───────┬───────┘ └──────┬──────┘
|
||||
│ │
|
||||
└─────────┬─────────┘
|
||||
│
|
||||
┌─────────▼─────────┐
|
||||
│ Agent Layer │
|
||||
│ (core + agents) │
|
||||
└─────────┬─────────┘
|
||||
│
|
||||
┌─────────┴─────────┐
|
||||
│ │
|
||||
┌───────▼───────┐ ┌──────▼──────┐
|
||||
│ Services │ │ Tools │
|
||||
│ (11 modules) │ │ (4 tools) │
|
||||
└───────────────┘ └─────────────┘
|
||||
```
|
||||
|
||||
---
|
||||
|
||||
## 💻 代码质量分析
|
||||
|
||||
### 1. 代码规范
|
||||
|
||||
| 检查项 | 状态 | 说明 |
|
||||
|--------|------|------|
|
||||
| **类型注解** | ✅ 优秀 | 全面使用 typing 模块 |
|
||||
| **文档字符串** | ✅ 优秀 | 所有类和方法都有 docstring |
|
||||
| **命名规范** | ✅ 优秀 | 符合 PEP 8 |
|
||||
| **异常处理** | ✅ 良好 | 适当的 try-except |
|
||||
| **日志记录** | ✅ 优秀 | 结构化日志 |
|
||||
| **代码复用** | ✅ 优秀 | 继承和组合使用得当 |
|
||||
|
||||
### 2. 代码度量
|
||||
|
||||
| 指标 | 数值 | 评价 |
|
||||
|------|------|------|
|
||||
| **总行数** | ~5,000 行 | 中等规模 |
|
||||
| **平均函数长度** | 20-30 行 | 合理 |
|
||||
| **最大函数长度** | ~100 行 | 可接受 |
|
||||
| **类数量** | 20+ | 合理 |
|
||||
| **函数数量** | 50+ | 合理 |
|
||||
| **注释率** | ~15% | 良好 |
|
||||
|
||||
### 3. 代码异味（Code Smells）
|
||||
|
||||
| 问题 | 位置 | 严重程度 | 建议 |
|
||||
|------|------|----------|------|
|
||||
| 魔法数字 | conversation.py:75 | 低 | 已配置化 |
|
||||
| 过长函数 | workflow_manager.py | 中 | 可拆分 |
|
||||
| 重复代码 | nodes.py | 低 | 可提取公共逻辑 |
|
||||
|
||||
---
|
||||
|
||||
## 🔧 功能模块分析
|
||||
|
||||
### 1. Agent 模块 ⭐⭐⭐⭐⭐
|
||||
|
||||
**优点**:
|
||||
- ✅ 核心与业务分离
|
||||
- ✅ 继承关系清晰
|
||||
- ✅ 职责单一
|
||||
- ✅ 易于扩展
|
||||
|
||||
**改进建议**:
|
||||
- ⚠️ 可添加更多 Agent 类型（如：数据分析 Agent）
|
||||
- ⚠️ 可考虑添加 Agent 工厂模式
|
||||
|
||||
### 2. API 模块 ⭐⭐⭐⭐
|
||||
|
||||
**优点**:
|
||||
- ✅ RESTful 设计
|
||||
- ✅ 流式响应支持
|
||||
- ✅ 依赖注入规范
|
||||
|
||||
**改进建议**:
|
||||
- ⚠️ 添加 API 版本管理（/api/v1/）
|
||||
- ⚠️ 添加请求限流
|
||||
- ⚠️ 添加 API 文档（Swagger/OpenAPI）
|
||||
|
||||
### 3. Services 模块 ⭐⭐⭐⭐
|
||||
|
||||
**优点**:
|
||||
- ✅ 职责清晰
|
||||
- ✅ 工厂模式
|
||||
- ✅ 单例模式
|
||||
|
||||
**改进建议**:
|
||||
- ⚠️ cache.py 未使用，考虑移除或集成
|
||||
- ⚠️ 添加服务健康检查
|
||||
- ⚠️ 添加性能监控
|
||||
|
||||
### 4. Tools 模块 ⭐⭐⭐⭐
|
||||
|
||||
**优点**:
|
||||
- ✅ 工具化设计
|
||||
- ✅ 统一接口
|
||||
- ✅ 易于扩展
|
||||
|
||||
**改进建议**:
|
||||
- ⚠️ WebSearchTool 是占位符，需实现
|
||||
- ⚠️ 添加更多实用工具
|
||||
|
||||
---
|
||||
|
||||
## 📦 依赖分析
|
||||
|
||||
### 1. 核心依赖
|
||||
|
||||
| 依赖 | 版本 | 用途 | 状态 |
|
||||
|------|------|------|------|
|
||||
| langchain-core | >=1.2.6 | 核心功能 | ✅ 最新 |
|
||||
| langchain | >=1.2.1 | LLM 框架 | ✅ 最新 |
|
||||
| langgraph | >=1.0.5 | 工作流 | ✅ 最新 |
|
||||
| langchain-openai | >=1.1.6 | OpenAI 集成 | ✅ 最新 |
|
||||
| pydantic | >=2.0.0 | 数据验证 | ✅ 最新 |
|
||||
| fastapi | >=0.110.0 | Web 框架 | ✅ 最新 |
|
||||
|
||||
### 2. 可选依赖
|
||||
|
||||
| 依赖 | 版本 | 用途 | 状态 |
|
||||
|------|------|------|------|
|
||||
| redis | >=5.0.0 | 缓存 | ⚠️ 已安装但未使用 |
|
||||
| pymysql | >=1.1.1 | MySQL | ✅ 已使用 |
|
||||
| nacos-sdk-python | ==2.0.9 | 服务发现 | ✅ 已使用 |
|
||||
|
||||
### 3. 开发依赖
|
||||
|
||||
| 依赖 | 版本 | 用途 | 状态 |
|
||||
|------|------|------|------|
|
||||
| pytest | >=7.4.0 | 测试框架 | ✅ 已配置 |
|
||||
| black | >=23.7.0 | 代码格式化 | ✅ 已配置 |
|
||||
| flake8 | >=6.1.0 | 代码检查 | ✅ 已配置 |
|
||||
|
||||
---
|
||||
|
||||
## 🔒 安全性分析
|
||||
|
||||
### 1. 配置安全 ⭐⭐⭐⭐⭐
|
||||
|
||||
**优点**:
|
||||
- ✅ API Key 通过配置文件管理
|
||||
- ✅ config.ini 在 .gitignore 中
|
||||
- ✅ 提供 config.ini.example 模板
|
||||
|
||||
**改进建议**:
|
||||
- ⚠️ 考虑使用环境变量覆盖敏感配置
|
||||
- ⚠️ 添加配置加密支持
|
||||
|
||||
### 2. 输入验证 ⭐⭐⭐⭐
|
||||
|
||||
**优点**:
|
||||
- ✅ Pydantic 数据验证
|
||||
- ✅ SQL 参数化（通过 SR API）
|
||||
- ✅ 错误处理完善
|
||||
|
||||
**改进建议**:
|
||||
- ⚠️ 添加更严格的 SQL 注入防护
|
||||
- ⚠️ 添加输入长度限制
|
||||
- ⚠️ 添加频率限制
|
||||
|
||||
### 3. 错误处理 ⭐⭐⭐⭐⭐
|
||||
|
||||
**优点**:
|
||||
- ✅ 统一的错误码定义
|
||||
- ✅ 结构化错误响应
|
||||
- ✅ 日志记录完整
|
||||
|
||||
---
|
||||
|
||||
## ⚡ 性能分析
|
||||
|
||||
### 1. 当前性能
|
||||
|
||||
| 指标 | 估计值 | 说明 |
|
||||
|------|--------|------|
|
||||
| **响应时间** | 500ms-2s | 取决于 LLM 和 SQL 执行 |
|
||||
| **并发能力** | 100+ QPS | FastAPI 异步特性 |
|
||||
| **内存占用** | ~200MB | 正常范围 |
|
||||
|
||||
### 2. 性能优化点
|
||||
|
||||
**已实现**:
|
||||
- ✅ FastAPI 异步处理
|
||||
- ✅ LLM 流式输出
|
||||
- ✅ SQL 异步执行
|
||||
|
||||
**可优化**:
|
||||
- ⚠️ 添加 Redis 缓存（已安装未使用）
|
||||
- ⚠️ 添加 LLM 响应缓存
|
||||
- ⚠️ 添加数据库连接池
|
||||
- ⚠️ 添加异步日志写入
|
||||
|
||||
---
|
||||
|
||||
## 🧪 测试分析
|
||||
|
||||
### 1. 当前测试覆盖
|
||||
|
||||
| 测试类型 | 状态 | 说明 |
|
||||
|----------|------|------|
|
||||
| **单元测试** | ⚠️ 不足 | 只有基础测试 |
|
||||
| **集成测试** | ❌ 缺失 | 需要添加 |
|
||||
| **端到端测试** | ❌ 缺失 | 需要添加 |
|
||||
| **性能测试** | ❌ 缺失 | 需要添加 |
|
||||
|
||||
### 2. 测试建议
|
||||
|
||||
**优先级 1**:
|
||||
- ✅ Agent 核心逻辑测试
|
||||
- ✅ 工作流管理测试
|
||||
- ✅ API 端点测试
|
||||
|
||||
**优先级 2**:
|
||||
- ⚠️ Services 层测试
|
||||
- ⚠️ Tools 层测试
|
||||
- ⚠️ 集成测试
|
||||
|
||||
**优先级 3**:
|
||||
- ⚠️ 性能测试
|
||||
- ⚠️ 压力测试
|
||||
- ⚠️ 回归测试
|
||||
|
||||
---
|
||||
|
||||
## 📚 文档分析 ⭐⭐⭐⭐⭐
|
||||
|
||||
### 1. 文档完整性
|
||||
|
||||
| 文档 | 状态 | 质量 |
|
||||
|------|------|------|
|
||||
| **README.md** | ✅ 完整 | ⭐⭐⭐⭐⭐ |
|
||||
| **agent/README.md** | ✅ 完整 | ⭐⭐⭐⭐⭐ |
|
||||
| **docs/流程图** | ✅ 完整 | ⭐⭐⭐⭐⭐ |
|
||||
| **docs/代码分析** | ✅ 完整 | ⭐⭐⭐⭐⭐ |
|
||||
| **配置示例** | ✅ 完整 | ⭐⭐⭐⭐⭐ |
|
||||
|
||||
### 2. 文档优点
|
||||
|
||||
- ✅ 结构清晰
|
||||
- ✅ 示例丰富
|
||||
- ✅ 图表直观
|
||||
- ✅ 更新及时
|
||||
|
||||
---
|
||||
|
||||
## 🎯 改进建议
|
||||
|
||||
### 高优先级（立即执行）
|
||||
|
||||
1. **完善测试覆盖**
|
||||
```bash
|
||||
# 添加单元测试
|
||||
pytest tests/ --cov=agent --cov=services
|
||||
|
||||
# 目标：覆盖率 > 80%
|
||||
```
|
||||
|
||||
2. **集成 Redis 缓存**
|
||||
```python
|
||||
# services/cache.py 已存在但未使用
|
||||
from services.cache import RedisCache
|
||||
|
||||
cache = RedisCache(url="redis://localhost:6379")
|
||||
```
|
||||
|
||||
3. **添加 API 版本管理**
|
||||
```python
|
||||
# 将 /api/workflows 改为 /api/v1/workflows
|
||||
```
|
||||
|
||||
### 中优先级（近期执行）
|
||||
|
||||
4. **实现 WebSearchTool**
|
||||
```python
|
||||
# tools/web_search.py 目前是占位符
|
||||
```
|
||||
|
||||
5. **添加性能监控**
|
||||
```python
|
||||
# 添加 Prometheus + Grafana
|
||||
```
|
||||
|
||||
6. **添加健康检查端点**
|
||||
```python
|
||||
# GET /healthz - 详细健康检查
|
||||
```
|
||||
|
||||
### 低优先级（可选）
|
||||
|
||||
7. **添加更多 Agent 类型**
|
||||
- 数据分析 Agent
|
||||
- 文档总结 Agent
|
||||
- 代码生成 Agent
|
||||
|
||||
8. **优化日志系统**
|
||||
- 添加日志轮转
|
||||
- 添加日志分析
|
||||
|
||||
9. **添加 CI/CD 流水线**
|
||||
- 自动化测试
|
||||
- 自动化部署
|
||||
|
||||
---
|
||||
|
||||
## 📊 SWOT 分析
|
||||
|
||||
### 优势（Strengths）
|
||||
|
||||
- ✅ 企业级架构设计
|
||||
- ✅ 代码质量高
|
||||
- ✅ 文档完善
|
||||
- ✅ 易于扩展
|
||||
- ✅ 技术栈先进
|
||||
|
||||
### 劣势（Weaknesses）
|
||||
|
||||
- ⚠️ 测试覆盖不足
|
||||
- ⚠️ 部分功能未实现（WebSearch）
|
||||
- ⚠️ 性能监控缺失
|
||||
|
||||
### 机会（Opportunities）
|
||||
|
||||
- 🚀 可扩展更多业务场景
|
||||
- 🚀 可集成更多 AI 能力
|
||||
- 🚀 可产品化输出
|
||||
|
||||
### 威胁（Threats）
|
||||
|
||||
- ⚠️ LLM API 成本
|
||||
- ⚠️ 技术更新快
|
||||
- ⚠️ 安全要求提高
|
||||
|
||||
---
|
||||
|
||||
## 🎓 学习价值
|
||||
|
||||
### 适合学习的点
|
||||
|
||||
1. **LangChain + LangGraph 应用** ⭐⭐⭐⭐⭐
|
||||
2. **FastAPI 最佳实践** ⭐⭐⭐⭐⭐
|
||||
3. **企业级架构设计** ⭐⭐⭐⭐⭐
|
||||
4. **依赖注入模式** ⭐⭐⭐⭐⭐
|
||||
5. **配置管理** ⭐⭐⭐⭐⭐
|
||||
|
||||
### 不适合学习的点
|
||||
|
||||
1. ❌ 测试实践（测试不足）
|
||||
2. ❌ 性能优化（基础水平）
|
||||
|
||||
---
|
||||
|
||||
## 📈 项目成熟度
|
||||
|
||||
| 阶段 | 状态 | 说明 |
|
||||
|------|------|------|
|
||||
| **原型阶段** | ✅ 已完成 | MVP 功能完整 |
|
||||
| **开发阶段** | ✅ 已完成 | 核心功能稳定 |
|
||||
| **测试阶段** | ⚠️ 进行中 | 需要完善测试 |
|
||||
| **生产阶段** | ⚠️ 准生产 | 可小规模使用 |
|
||||
| **成熟阶段** | ❌ 未达到 | 需要时间验证 |
|
||||
|
||||
**当前阶段**: 准生产（Production-Ready）
|
||||
|
||||
---
|
||||
|
||||
## 🎯 总结
|
||||
|
||||
### 项目亮点
|
||||
|
||||
1. ✅ **优秀的架构设计** - 核心与业务分离
|
||||
2. ✅ **高质量的代码** - 规范、清晰、易维护
|
||||
3. ✅ **完善的文档** - 详细、直观、及时更新
|
||||
4. ✅ **先进的技术栈** - LangChain + FastAPI
|
||||
5. ✅ **易于扩展** - 模块化、插件化设计
|
||||
|
||||
### 需要改进
|
||||
|
||||
1. ⚠️ **测试覆盖** - 当前最大的短板
|
||||
2. ⚠️ **性能监控** - 缺少可观测性
|
||||
3. ⚠️ **功能完整性** - 部分功能未实现
|
||||
|
||||
### 推荐指数
|
||||
|
||||
**⭐⭐⭐⭐⭐ (5/5)**
|
||||
|
||||
**推荐理由**:
|
||||
- 非常适合学习现代 AI 应用开发
|
||||
- 企业级架构设计值得借鉴
|
||||
- 代码质量高，易于理解和扩展
|
||||
- 文档完善，学习曲线平缓
|
||||
|
||||
---
|
||||
|
||||
## 📞 联系与建议
|
||||
|
||||
如有问题或建议，请参考：
|
||||
- [README.md](README.md) - 项目说明
|
||||
- [agent/README.md](agent/README.md) - Agent 模块详解
|
||||
- [docs/](docs/) - 详细文档
|
||||
|
||||
---
|
||||
|
||||
**报告生成时间**: 2026-03-12
|
||||
**分析师**: AI Assistant
|
||||
**版本**: v1.0
|
||||
@@ -1,266 +1,33 @@
|
||||
# LangChain + LangGraph Scaffolding
|
||||
# APBO Boat Agent
|
||||
|
||||
一个使用 LangChain 和 LangGraph 构建的 AI 应用脚手架项目，提供模块化的代理和工作流管理。
|
||||
基于 LangChain + LangGraph 的问数 Agent 项目，提供 SQL 生成、执行与流式返回能力。
|
||||
|
||||
## 特性
|
||||
## 核心流程
|
||||
|
||||
- 🚀 **模块化架构**: 基于代理和工作流的模块化设计
|
||||
- 🔧 **工具集成**: 支持自定义工具和函数调用
|
||||
- 💬 **多轮对话**: 内置对话状态管理和上下文维护
|
||||
- 📊 **工作流管理**: 多种工作流类型，支持会话和工具使用
|
||||
- ⚙️ **配置管理**: 统一的环境变量和配置管理
|
||||
- 🧩 **FastAPI 接入**: 提供 HTTP 接口对外服务
|
||||
- 🧭 **Nacos 注册**: 支持服务注册与心跳
|
||||
- 🧪 **测试支持**: 包含基础测试和示例代码
|
||||
完整流程图见 [docs/README.md](./docs/README.md)。
|
||||
|
||||
## 项目结构
|
||||
主链路：
|
||||
|
||||
```
|
||||
more_dots/
|
||||
├── agent/ # Agent 核心逻辑层
|
||||
│ ├── graph.py # LangGraph 图结构定义
|
||||
│ ├── nodes.py # 节点执行逻辑
|
||||
│ ├── state.py # Agent 状态定义
|
||||
│ ├── conversation.py # 对话代理
|
||||
│ └── tool.py # 工具代理
|
||||
├── api/ # API 接口层
|
||||
│ ├── endpoints.py # FastAPI 路由定义
|
||||
│ └── dependencies.py # API 依赖注入
|
||||
├── services/ # 服务层
|
||||
│ ├── llm_factory.py # LLM 实例工厂
|
||||
│ └── nacos_service.py # Nacos 集成
|
||||
├── schemas/ # 数据模型层
|
||||
│ ├── agent_input.py # 输入模型
|
||||
│ └── agent_output.py # 输出模型
|
||||
├── config/ # 配置层
|
||||
│ └── settings.py # 配置读取
|
||||
│ └── prompts.yaml # 提示词配置
|
||||
│ └── table_retrieval_prompts/ # 表名检索提示词（表名 -> 模板列表）
|
||||
├── tools/ # 工具模块
|
||||
│ ├── calculator.py # 计算器工具
|
||||
│ └── web_search.py # 网络搜索工具（占位符）
|
||||
├── workflows/ # 工作流管理
|
||||
│ └── workflow_manager.py
|
||||
├── examples/ # 使用示例
|
||||
│ └── basic_usage.py
|
||||
├── tests/ # 测试文件
|
||||
│ └── test_basic.py
|
||||
├── requirements.txt # 依赖包列表
|
||||
├── config/
|
||||
│ ├── config.ini.example # 配置文件示例
|
||||
│ ├── config.ini # 本地配置（需自行创建）
|
||||
│ └── prompts.yaml # 提示词配置
|
||||
├── server.py # FastAPI 服务入口
|
||||
├── main.py # CLI 入口
|
||||
└── README.md # 项目说明
|
||||
```
|
||||
`analyze_intent -> process_input -> normalize_input -> classify_query_mode -> match_table -> load_sql_prompt -> build_sql_plan -> generate_sql -> execute_sql -> generate_response -> update_context`
|
||||
|
||||
## 快速开始
|
||||
## 顶层模块
|
||||
|
||||
### 1. 安装依赖
|
||||
- [agent/README.md](./agent/README.md)：Agent 状态与节点编排
|
||||
- [api/README.md](./api/README.md)：FastAPI 接口层
|
||||
- [config/README.md](./config/README.md)：配置与提示词资源
|
||||
- [docs/README.md](./docs/README.md)：核心流程图
|
||||
- [examples/README.md](./examples/README.md)：最小示例
|
||||
- [k8s/README.md](./k8s/README.md)：部署清单
|
||||
- [schemas/README.md](./schemas/README.md)：请求响应模型
|
||||
- [scripts/README.md](./scripts/README.md)：调试与同步脚本
|
||||
- [services/README.md](./services/README.md)：基础服务层
|
||||
- [tests/README.md](./tests/README.md)：自动化测试
|
||||
- [tools/README.md](./tools/README.md)：工具实现
|
||||
- [workflows/README.md](./workflows/README.md)：工作流管理
|
||||
|
||||
## 快速启动
|
||||
|
||||
```bash
|
||||
pip install -r requirements.txt
|
||||
```
|
||||
|
||||
### 2. 配置 config.ini
|
||||
|
||||
```bash
|
||||
# 复制配置文件
|
||||
cp config/config.ini.example config/config.ini
|
||||
|
||||
# 编辑 config/config.ini，设置你的 API Key，并可添加多个模型配置
|
||||
[General]
|
||||
DEFAULT_MODEL_SECTION = gpt-4o
|
||||
MAX_RETRIES = 3
|
||||
TIMEOUT = 30
|
||||
|
||||
[gpt-4o]
|
||||
MODEL_NAME = gpt-4o
|
||||
OPENAI_API_KEY = your_openai_api_key_here
|
||||
|
||||
[gpt-3.5-turbo]
|
||||
MODEL_NAME = gpt-3.5-turbo
|
||||
OPENAI_API_KEY = your_openai_api_key_here
|
||||
```
|
||||
|
||||
### 3. 运行示例
|
||||
|
||||
```bash
|
||||
# 运行基础示例
|
||||
python examples/basic_usage.py
|
||||
|
||||
# 运行交互式 CLI（默认模型）
|
||||
python main.py
|
||||
|
||||
# 运行交互式 CLI（指定模型配置段）
|
||||
python main.py gpt-3.5-turbo
|
||||
|
||||
# 运行 FastAPI 服务
|
||||
python server.py
|
||||
```
|
||||
|
||||
## 使用指南
|
||||
|
||||
### 基础用法
|
||||
|
||||
```python
|
||||
from workflows.workflow_manager import WorkflowManager, WorkflowType
|
||||
|
||||
# 创建工作流管理器（默认模型）
|
||||
manager = WorkflowManager()
|
||||
|
||||
# 创建工作流管理器（指定模型配置段）
|
||||
manager_alt = WorkflowManager(default_model_section="gpt-3.5-turbo")
|
||||
|
||||
### FastAPI 接口
|
||||
|
||||
启动服务后，可使用以下接口：
|
||||
|
||||
- `GET /health`：健康检查
|
||||
- `GET /nacos/status`：查看 Nacos 注册状态
|
||||
- `POST /api/workflows`：执行工作流
|
||||
|
||||
示例请求体：
|
||||
|
||||
```json
|
||||
{
|
||||
"query": "你好，帮我算 1 + 2",
|
||||
"conversation_id": null,
|
||||
"workflow_type": "conversation",
|
||||
"response_mode": "blocking",
|
||||
"user": "demo",
|
||||
"inputs": {}
|
||||
}
|
||||
```
|
||||
|
||||
### Nacos 配置
|
||||
|
||||
在 `config/config.ini` 中开启 Nacos：
|
||||
|
||||
```ini
|
||||
[nacos]
|
||||
enabled = true
|
||||
server = localhost:8848
|
||||
namespace = public
|
||||
group_name = DEFAULT_GROUP
|
||||
cluster_name = DEFAULT
|
||||
heartbeat_interval = 5
|
||||
```
|
||||
|
||||
### RAGFlow 模板同步
|
||||
|
||||
模板文件位于 `config/table_retrieval_prompts/tables.json`，单文件包含多个表名与模板列表。
|
||||
同步脚本：
|
||||
|
||||
```bash
|
||||
python scripts/sync_ragflow_templates.py
|
||||
```
|
||||
|
||||
请在 `config/config.ini` 中配置 `ragflow.upload` 上传接口，并分别设置：
|
||||
`table_retrieval_dataset_id` 与 `sql_gen_dataset_id`。
|
||||
|
||||
默认使用覆盖更新模式（`ragflow.upload_mode = overwrite`）。
|
||||
|
||||
热更新接口：
|
||||
- `POST /api/ragflow/table-retrieval/reload`
|
||||
- `POST /api/ragflow/sql-gen/reload`
|
||||
|
||||
# 使用对话工作流
|
||||
result = manager.execute_workflow(
|
||||
WorkflowType.CONVERSATION,
|
||||
"Hello! How can you help me?"
|
||||
)
|
||||
|
||||
# 使用工具工作流
|
||||
result = manager.execute_workflow(
|
||||
WorkflowType.TOOL_USING,
|
||||
"Calculate 15 * 3 + 7"
|
||||
)
|
||||
```
|
||||
|
||||
### 自定义工具
|
||||
|
||||
创建新的工具类：
|
||||
|
||||
```python
|
||||
from langchain_core.tools import BaseTool
|
||||
|
||||
class CustomTool(BaseTool):
|
||||
name = "custom_tool"
|
||||
description = "A custom tool for specific tasks"
|
||||
|
||||
def _run(self, input: str) -> str:
|
||||
# 实现工具逻辑
|
||||
return f"Processed: {input}"
|
||||
```
|
||||
|
||||
### 扩展代理
|
||||
|
||||
创建新的代理类型：
|
||||
|
||||
```python
|
||||
from agent.graph import BaseAgent
|
||||
|
||||
class CustomAgent(BaseAgent):
|
||||
def _build_graph(self):
|
||||
# 实现自定义图结构
|
||||
pass
|
||||
|
||||
def _custom_node(self, state):
|
||||
# 自定义节点逻辑
|
||||
return state
|
||||
```
|
||||
|
||||
## 工作流类型
|
||||
|
||||
| 工作流类型 | 描述 | 适用场景 |
|
||||
|-----------|------|----------|
|
||||
| `conversation` | 多轮对话代理 | 聊天机器人、客服系统 |
|
||||
| `tool_using` | 工具使用代理 | 任务执行、数据分析 |
|
||||
|
||||
## 开发指南
|
||||
|
||||
### 添加新功能
|
||||
|
||||
1. **新工具**: 在 `tools/` 目录下创建新的工具类
|
||||
2. **新代理**: 在 `agent/` 目录下继承 `BaseAgent` 类
|
||||
3. **新工作流**: 在 `workflows/` 目录下扩展工作流管理器
|
||||
|
||||
### 测试
|
||||
|
||||
```bash
|
||||
# 运行所有测试
|
||||
python -m pytest tests/
|
||||
|
||||
# 运行特定测试
|
||||
python -m pytest tests/test_basic.py
|
||||
```
|
||||
|
||||
### 调试
|
||||
|
||||
项目使用标准的 Python 日志系统，可以通过设置环境变量启用调试模式：
|
||||
|
||||
```python
|
||||
import logging
|
||||
logging.basicConfig(level=logging.DEBUG)
|
||||
```
|
||||
|
||||
## 依赖项
|
||||
|
||||
主要依赖包：
|
||||
|
||||
- `langchain-core`: LangChain 核心功能
|
||||
- `langchain`: LangChain 主包
|
||||
- `langgraph`: LangGraph 图工作流
|
||||
- `langchain-openai`: OpenAI 集成
|
||||
- `pydantic`: 数据验证
|
||||
|
||||
## 许可证
|
||||
|
||||
MIT License
|
||||
|
||||
## 贡献
|
||||
|
||||
欢迎提交 Issue 和 Pull Request 来改进这个项目！
|
||||
|
||||
|
||||
@@ -0,0 +1,37 @@
|
||||
# Agent 模块
|
||||
|
||||
## 目录说明
|
||||
|
||||
`agent` 负责定义 Agent 运行时状态、节点逻辑与具体代理类型。
|
||||
|
||||
```
|
||||
agent/
|
||||
├── agents/ # 具体代理实现（ConversationAgent / ToolAgent）
|
||||
├── core/ # 状态图与共享节点
|
||||
├── utils.py # Agent 通用工具函数
|
||||
└── README.md
|
||||
```
|
||||
|
||||
## 核心能力
|
||||
|
||||
- 统一的 SQL 工作流编排
|
||||
- 多轮对话上下文维护
|
||||
- 节点级状态推进与错误收集
|
||||
|
||||
## 关键流程
|
||||
|
||||
共享 SQL 主链路：
|
||||
|
||||
`process_input -> normalize_input -> classify_query_mode -> match_table -> load_sql_prompt -> build_sql_plan -> generate_sql -> execute_sql -> generate_response`
|
||||
|
||||
对话代理会在前后追加：
|
||||
|
||||
`analyze_intent` 与 `update_context`
|
||||
|
||||
## 文件
|
||||
|
||||
- `core/base_agent.py`：共享图注册和节点编排
|
||||
- `core/nodes.py`：SQL 主流程节点实现
|
||||
- `core/state.py`：AgentState 与上下文同步
|
||||
- `agents/conversation.py`：会话型 Agent
|
||||
- `agents/tool.py`：工具调用型 Agent
|
||||
+6
-4
@@ -1,6 +1,8 @@
|
||||
from .state import AgentState
|
||||
from .graph import BaseAgent
|
||||
from .conversation import ConversationAgent
|
||||
from .tool import ToolAgent
|
||||
"""Agent 模块 - 提供智能代理功能"""
|
||||
|
||||
from agent.core.state import AgentState
|
||||
from agent.core.base_agent import BaseAgent
|
||||
from agent.agents.conversation import ConversationAgent
|
||||
from agent.agents.tool import ToolAgent
|
||||
|
||||
__all__ = ["AgentState", "BaseAgent", "ConversationAgent", "ToolAgent"]
|
||||
|
||||
@@ -0,0 +1,6 @@
|
||||
"""代理实现模块 - 具体的代理实现"""
|
||||
|
||||
from .conversation import ConversationAgent
|
||||
from .tool import ToolAgent
|
||||
|
||||
__all__ = ["ConversationAgent", "ToolAgent"]
|
||||
@@ -0,0 +1,112 @@
|
||||
from typing import Dict, Any, Optional, cast
|
||||
from langchain_core.messages import HumanMessage, AIMessage
|
||||
from langgraph.graph import StateGraph, END
|
||||
|
||||
from agent.core.base_agent import BaseAgent
|
||||
from agent.core.state import AgentState
|
||||
from agent.core import nodes
|
||||
from config import CONVERSATION_MAX_HISTORY_MESSAGES
|
||||
|
||||
|
||||
class ConversationAgent(BaseAgent):
|
||||
"""处理多轮对话的代理"""
|
||||
|
||||
def __init__(self, model_section: Optional[str] = None):
|
||||
super().__init__(model_section)
|
||||
|
||||
def _build_graph(self) -> Any:
|
||||
"""构建对话专用图"""
|
||||
workflow = StateGraph(cast(Any, AgentState))
|
||||
|
||||
workflow.add_node("analyze_intent", cast(Any, self._analyze_intent))
|
||||
self._add_shared_sql_nodes(workflow)
|
||||
workflow.add_node("update_context", cast(Any, self._update_context))
|
||||
|
||||
workflow.add_edge("analyze_intent", "process_input")
|
||||
self._add_shared_sql_edges(workflow, start_node="process_input", end_node="generate_response")
|
||||
workflow.add_edge("generate_response", "update_context")
|
||||
workflow.add_edge("update_context", END)
|
||||
|
||||
workflow.set_entry_point("analyze_intent")
|
||||
|
||||
return workflow.compile()
|
||||
|
||||
def _analyze_intent(self, state: AgentState) -> AgentState:
|
||||
"""分析用户意图与对话上下文"""
|
||||
user_message = state.messages[-1] if state.messages else None
|
||||
|
||||
if user_message and isinstance(user_message, HumanMessage):
|
||||
content = user_message.content.lower()
|
||||
|
||||
if any(word in content for word in ["hello", "hi", "hey", "greetings"]):
|
||||
state.intent = "greeting"
|
||||
elif any(word in content for word in ["help", "assist", "support"]):
|
||||
state.intent = "help"
|
||||
elif any(token in content for token in ["sql", "查询", "统计", "汇总", "top", "eta", "so ", "soid", "订单"]):
|
||||
state.intent = "sql_query"
|
||||
elif "?" in content:
|
||||
state.intent = "question"
|
||||
else:
|
||||
state.intent = "general"
|
||||
|
||||
state.sync_context()
|
||||
state.set_current_step("intent_analyzed")
|
||||
return state
|
||||
|
||||
def _generate_response(self, state: AgentState) -> AgentState:
|
||||
"""优先返回 SQL 执行结果，其次返回生成 SQL，再回退到模型回复"""
|
||||
return nodes.generate_response(state, self.model)
|
||||
|
||||
def _update_context(self, state: AgentState) -> AgentState:
|
||||
"""更新当前会话的对话上下文与历史。"""
|
||||
conversation_history = list(state.context.get("conversation_history") or [])
|
||||
for message in state.messages:
|
||||
if isinstance(message, (HumanMessage, AIMessage)):
|
||||
conversation_history.append(message)
|
||||
|
||||
# 使用配置文件中的最大消息数限制
|
||||
max_messages = CONVERSATION_MAX_HISTORY_MESSAGES
|
||||
if len(conversation_history) > max_messages:
|
||||
conversation_history = conversation_history[-max_messages:]
|
||||
|
||||
state.context["conversation_history"] = conversation_history
|
||||
|
||||
state.sync_context()
|
||||
last_context = dict(state.context)
|
||||
last_context.pop("conversation_history", None)
|
||||
last_context.pop("last_context", None)
|
||||
state.context["last_context"] = last_context
|
||||
state.set_current_step("context_updated")
|
||||
return state
|
||||
|
||||
def run(self, user_input: str, **kwargs) -> Dict[str, Any]:
|
||||
"""运行对话，历史与上下文由调用方按会话维度传入。"""
|
||||
context = dict(kwargs)
|
||||
context["conversation_history"] = list(context.get("conversation_history") or [])
|
||||
context["last_context"] = dict(context.get("last_context") or {})
|
||||
initial_state = AgentState(
|
||||
messages=[HumanMessage(content=user_input)],
|
||||
context=context
|
||||
)
|
||||
|
||||
result = self.graph.invoke(initial_state)
|
||||
final_state = self._coerce_state(initial_state, result)
|
||||
|
||||
return {
|
||||
"messages": final_state.messages,
|
||||
"context": final_state.sync_context(),
|
||||
"conversation_history": list(final_state.context.get("conversation_history") or []),
|
||||
"final_step": final_state.current_step,
|
||||
}
|
||||
|
||||
def stream_run(self, user_input: str, **kwargs):
|
||||
"""流式运行对话；会话历史需由调用方显式传入。"""
|
||||
conversation_history = list(kwargs.get("conversation_history") or [])
|
||||
all_messages = conversation_history + [HumanMessage(content=user_input)]
|
||||
full_text = ""
|
||||
|
||||
for chunk in self.model.stream(all_messages):
|
||||
if hasattr(chunk, "content") and chunk.content:
|
||||
full_text += chunk.content
|
||||
yield chunk.content
|
||||
|
||||
@@ -1,11 +1,11 @@
|
||||
from typing import Dict, Any, List, Optional
|
||||
from langchain_core.messages import BaseMessage, HumanMessage
|
||||
from typing import Dict, Any, List, Optional, cast
|
||||
from langchain_core.messages import HumanMessage
|
||||
from langchain_core.tools import BaseTool
|
||||
from langgraph.graph import StateGraph, END
|
||||
from langgraph.prebuilt import ToolNode
|
||||
|
||||
from .graph import BaseAgent
|
||||
from .state import AgentState
|
||||
from agent.core.base_agent import BaseAgent
|
||||
from agent.core.state import AgentState
|
||||
from tools.calculator import CalculatorTool
|
||||
from tools.web_search import WebSearchTool
|
||||
from tools.rest_api_tool import RestApiTool
|
||||
@@ -23,17 +23,16 @@ class ToolAgent(BaseAgent):
|
||||
self.tool_node = ToolNode(tools)
|
||||
super().__init__(model_section)
|
||||
|
||||
def _build_graph(self) -> StateGraph:
|
||||
def _build_graph(self) -> Any:
|
||||
"""构建可使用工具的图"""
|
||||
workflow = StateGraph(AgentState)
|
||||
workflow = StateGraph(cast(Any, AgentState))
|
||||
|
||||
workflow.add_node("normalize_input", self._normalize_input)
|
||||
workflow.add_node("generate_sql", self._generate_sql)
|
||||
workflow.add_node("agent", self._agent_node)
|
||||
workflow.add_node("tools", self.tool_node)
|
||||
self._add_shared_sql_nodes(workflow)
|
||||
workflow.add_node("agent", cast(Any, self._agent_node))
|
||||
workflow.add_node("tools", cast(Any, self.tool_node))
|
||||
|
||||
workflow.add_edge("normalize_input", "generate_sql")
|
||||
workflow.add_edge("generate_sql", "agent")
|
||||
workflow.set_entry_point("process_input")
|
||||
self._add_shared_sql_edges(workflow, start_node="process_input", end_node="agent")
|
||||
workflow.add_edge("tools", "agent")
|
||||
|
||||
workflow.add_conditional_edges(
|
||||
@@ -45,9 +44,7 @@ class ToolAgent(BaseAgent):
|
||||
}
|
||||
)
|
||||
|
||||
workflow.set_entry_point("normalize_input")
|
||||
|
||||
return workflow.compile()
|
||||
return cast(Any, workflow.compile())
|
||||
|
||||
def _agent_node(self, state: AgentState) -> AgentState:
|
||||
"""决定是否调用工具的代理节点"""
|
||||
@@ -67,11 +64,6 @@ class ToolAgent(BaseAgent):
|
||||
|
||||
return state
|
||||
|
||||
def _generate_sql(self, state: AgentState) -> AgentState:
|
||||
"""生成 SQL"""
|
||||
from . import nodes
|
||||
return nodes.generate_sql(state, self.model)
|
||||
|
||||
def _should_use_tools(self, state: AgentState) -> str:
|
||||
"""判断是否需要使用工具"""
|
||||
last_message = state.messages[-1]
|
||||
@@ -89,10 +81,11 @@ class ToolAgent(BaseAgent):
|
||||
)
|
||||
|
||||
result = self.graph.invoke(initial_state)
|
||||
final_state = self._coerce_state(initial_state, result)
|
||||
|
||||
return {
|
||||
"messages": result.get("messages", []),
|
||||
"context": result.get("context", {}),
|
||||
"messages": final_state.messages,
|
||||
"context": final_state.sync_context(),
|
||||
"tools_used": [tool.name for tool in self.tools],
|
||||
"final_step": result.get("current_step", "unknown")
|
||||
"final_step": final_state.current_step,
|
||||
}
|
||||
@@ -1,109 +0,0 @@
|
||||
from typing import Dict, Any, List, Optional
|
||||
from langchain_core.messages import BaseMessage, HumanMessage, AIMessage
|
||||
from langgraph.graph import StateGraph, END
|
||||
|
||||
from .graph import BaseAgent
|
||||
from .state import AgentState
|
||||
|
||||
|
||||
class ConversationAgent(BaseAgent):
|
||||
"""处理多轮对话的代理"""
|
||||
|
||||
def __init__(self, model_section: Optional[str] = None):
|
||||
super().__init__(model_section)
|
||||
self.conversation_history: List[BaseMessage] = []
|
||||
|
||||
def _build_graph(self) -> StateGraph:
|
||||
"""构建对话专用图"""
|
||||
workflow = StateGraph(AgentState)
|
||||
|
||||
workflow.add_node("analyze_intent", self._analyze_intent)
|
||||
workflow.add_node("normalize_input", self._normalize_input)
|
||||
workflow.add_node("generate_sql", self._generate_sql)
|
||||
workflow.add_node("generate_response", self._generate_response)
|
||||
workflow.add_node("update_context", self._update_context)
|
||||
|
||||
workflow.add_edge("analyze_intent", "normalize_input")
|
||||
workflow.add_edge("normalize_input", "generate_sql")
|
||||
workflow.add_edge("generate_sql", "generate_response")
|
||||
workflow.add_edge("generate_response", "update_context")
|
||||
workflow.add_edge("update_context", END)
|
||||
|
||||
workflow.set_entry_point("analyze_intent")
|
||||
|
||||
return workflow.compile()
|
||||
|
||||
def _analyze_intent(self, state: AgentState) -> AgentState:
|
||||
"""分析用户意图与对话上下文"""
|
||||
user_message = state.messages[-1] if state.messages else None
|
||||
|
||||
if user_message and isinstance(user_message, HumanMessage):
|
||||
content = user_message.content.lower()
|
||||
|
||||
if any(word in content for word in ["hello", "hi", "hey", "greetings"]):
|
||||
state.context["intent"] = "greeting"
|
||||
elif any(word in content for word in ["help", "assist", "support"]):
|
||||
state.context["intent"] = "help"
|
||||
elif "?" in content:
|
||||
state.context["intent"] = "question"
|
||||
else:
|
||||
state.context["intent"] = "general"
|
||||
|
||||
state.current_step = "intent_analyzed"
|
||||
return state
|
||||
|
||||
def _generate_response(self, state: AgentState) -> AgentState:
|
||||
"""优先返回 SQL 执行结果，其次返回生成 SQL，再回退到模型回复"""
|
||||
from . import nodes
|
||||
state = nodes.generate_response(state, self.model)
|
||||
state.current_step = "response_generated"
|
||||
return state
|
||||
|
||||
def _generate_sql(self, state: AgentState) -> AgentState:
|
||||
"""生成 SQL"""
|
||||
from . import nodes
|
||||
return nodes.generate_sql(state, self.model)
|
||||
|
||||
def _update_context(self, state: AgentState) -> AgentState:
|
||||
"""更新对话上下文与历史"""
|
||||
for message in state.messages:
|
||||
if isinstance(message, (HumanMessage, AIMessage)):
|
||||
self.conversation_history.append(message)
|
||||
|
||||
if len(self.conversation_history) > 10:
|
||||
self.conversation_history = self.conversation_history[-10:]
|
||||
|
||||
state.current_step = "context_updated"
|
||||
return state
|
||||
|
||||
def run(self, user_input: str, **kwargs) -> Dict[str, Any]:
|
||||
"""运行对话并维护历史"""
|
||||
initial_state = AgentState(
|
||||
messages=[HumanMessage(content=user_input)],
|
||||
context=kwargs
|
||||
)
|
||||
|
||||
result = self.graph.invoke(initial_state)
|
||||
|
||||
return {
|
||||
"messages": result.get("messages", []),
|
||||
"context": result.get("context", {}),
|
||||
"conversation_history": self.conversation_history,
|
||||
"final_step": result.get("current_step", "unknown")
|
||||
}
|
||||
|
||||
def stream_run(self, user_input: str):
|
||||
"""流式运行对话并维护历史"""
|
||||
all_messages = self.conversation_history + [HumanMessage(content=user_input)]
|
||||
full_text = ""
|
||||
|
||||
for chunk in self.model.stream(all_messages):
|
||||
if hasattr(chunk, "content") and chunk.content:
|
||||
full_text += chunk.content
|
||||
yield chunk.content
|
||||
|
||||
self.conversation_history.append(HumanMessage(content=user_input))
|
||||
self.conversation_history.append(AIMessage(content=full_text))
|
||||
|
||||
if len(self.conversation_history) > 10:
|
||||
self.conversation_history = self.conversation_history[-10:]
|
||||
@@ -0,0 +1,29 @@
|
||||
"""核心模块 - 提供代理的基础功能"""
|
||||
|
||||
from .base_agent import BaseAgent
|
||||
from .state import AgentState
|
||||
from .nodes import (
|
||||
process_input,
|
||||
normalize_input,
|
||||
classify_query_mode,
|
||||
match_table,
|
||||
load_sql_prompt,
|
||||
build_sql_plan,
|
||||
generate_sql,
|
||||
execute_sql,
|
||||
generate_response,
|
||||
)
|
||||
|
||||
__all__ = [
|
||||
"BaseAgent",
|
||||
"AgentState",
|
||||
"process_input",
|
||||
"normalize_input",
|
||||
"classify_query_mode",
|
||||
"match_table",
|
||||
"load_sql_prompt",
|
||||
"build_sql_plan",
|
||||
"generate_sql",
|
||||
"execute_sql",
|
||||
"generate_response",
|
||||
]
|
||||
@@ -0,0 +1,88 @@
|
||||
from typing import Any, Dict, Optional, cast
|
||||
from langchain_core.messages import HumanMessage
|
||||
from langgraph.graph import StateGraph, END
|
||||
|
||||
from services.core.llm_factory import create_chat_model
|
||||
from .state import AgentState
|
||||
from . import nodes
|
||||
|
||||
|
||||
class BaseAgent:
|
||||
"""包含通用功能的基础代理类"""
|
||||
|
||||
def __init__(self, model_section: Optional[str] = None):
|
||||
self.model = create_chat_model(model_section)
|
||||
self.graph = self._build_graph()
|
||||
|
||||
def _build_graph(self) -> Any:
|
||||
"""构建代理状态图"""
|
||||
workflow = StateGraph(cast(Any, AgentState))
|
||||
|
||||
self._add_shared_sql_nodes(workflow)
|
||||
self._add_shared_sql_edges(workflow, start_node="process_input", end_node="generate_response")
|
||||
workflow.add_edge("generate_response", END)
|
||||
|
||||
workflow.set_entry_point("process_input")
|
||||
|
||||
return workflow.compile()
|
||||
|
||||
def _add_shared_sql_nodes(self, workflow: Any) -> None:
|
||||
"""注册 SQL 规划相关共享节点。"""
|
||||
workflow.add_node("process_input", cast(Any, nodes.process_input))
|
||||
workflow.add_node("normalize_input", cast(Any, self._normalize_input))
|
||||
workflow.add_node("classify_query_mode", cast(Any, nodes.classify_query_mode))
|
||||
workflow.add_node("match_table", cast(Any, nodes.match_table))
|
||||
workflow.add_node("load_sql_prompt", cast(Any, nodes.load_sql_prompt))
|
||||
workflow.add_node("build_sql_plan", cast(Any, nodes.build_sql_plan))
|
||||
workflow.add_node("generate_sql", cast(Any, self._generate_sql))
|
||||
workflow.add_node("execute_sql", cast(Any, nodes.execute_sql))
|
||||
workflow.add_node("check_empty_result", cast(Any, nodes.check_empty_result))
|
||||
workflow.add_node("generate_response", cast(Any, self._generate_response))
|
||||
|
||||
@staticmethod
|
||||
def _add_shared_sql_edges(workflow: Any, start_node: str, end_node: str) -> None:
|
||||
"""串联标准 SQL 工作流。"""
|
||||
workflow.add_edge(start_node, "normalize_input")
|
||||
workflow.add_edge("normalize_input", "classify_query_mode")
|
||||
workflow.add_edge("classify_query_mode", "match_table")
|
||||
workflow.add_edge("match_table", "load_sql_prompt")
|
||||
workflow.add_edge("load_sql_prompt", "build_sql_plan")
|
||||
workflow.add_edge("build_sql_plan", "generate_sql")
|
||||
workflow.add_edge("generate_sql", "execute_sql")
|
||||
workflow.add_edge("execute_sql", "check_empty_result")
|
||||
workflow.add_edge("check_empty_result", end_node)
|
||||
|
||||
def _generate_response(self, state: AgentState) -> AgentState:
|
||||
"""使用 LLM 生成回复"""
|
||||
return nodes.generate_response(state, self.model)
|
||||
|
||||
def _normalize_input(self, state: AgentState) -> AgentState:
|
||||
"""规范化用户输入"""
|
||||
return nodes.normalize_input(state, self.model)
|
||||
|
||||
def _generate_sql(self, state: AgentState) -> AgentState:
|
||||
"""生成 SQL"""
|
||||
return nodes.generate_sql(state, self.model)
|
||||
|
||||
@staticmethod
|
||||
def _coerce_state(initial_state: AgentState, result: Any) -> AgentState:
|
||||
"""兼容 LangGraph 返回 AgentState 或 dict。"""
|
||||
if isinstance(result, AgentState):
|
||||
return result
|
||||
return initial_state.apply_graph_result(result)
|
||||
|
||||
def run(self, user_input: str, **kwargs) -> Dict[str, Any]:
|
||||
"""运行代理并处理用户输入"""
|
||||
initial_state = AgentState(
|
||||
messages=[HumanMessage(content=user_input)],
|
||||
context=kwargs
|
||||
)
|
||||
|
||||
result = self.graph.invoke(initial_state)
|
||||
final_state = self._coerce_state(initial_state, result)
|
||||
|
||||
return {
|
||||
"messages": final_state.messages,
|
||||
"context": final_state.sync_context(),
|
||||
"final_step": final_state.current_step,
|
||||
}
|
||||
@@ -0,0 +1,571 @@
|
||||
import html
|
||||
import json
|
||||
import re
|
||||
from typing import Any, Dict, List
|
||||
|
||||
from langchain_core.messages import HumanMessage, SystemMessage, AIMessage
|
||||
|
||||
from .state import AgentState
|
||||
from config import Config
|
||||
from services.core.prompt_manager import get_prompt_manager
|
||||
from services.core.template_matcher import get_template_matcher
|
||||
from services.core.sql_prompt_manager import get_sql_prompt_manager
|
||||
from tools.sr_api_tool import SrApiQueryTool
|
||||
|
||||
|
||||
def _short(value, max_len: int = 500) -> str:
|
||||
text = str(value)
|
||||
return text if len(text) <= max_len else text[:max_len] + "..."
|
||||
|
||||
|
||||
def _trace(state: AgentState, label: str, value: Any | None = None, *, clip: bool = True) -> None:
|
||||
if not state.context.get("debug_node_trace"):
|
||||
return
|
||||
if value is None:
|
||||
print(label)
|
||||
else:
|
||||
print(label, _short(value) if clip else value)
|
||||
|
||||
|
||||
FOLLOW_UP_HINTS = (
|
||||
"那",
|
||||
"那么",
|
||||
"然后",
|
||||
"改成",
|
||||
"改为",
|
||||
"换成",
|
||||
"只看",
|
||||
"那如果",
|
||||
"how about",
|
||||
"what about",
|
||||
"same",
|
||||
"also",
|
||||
)
|
||||
|
||||
TOPN_RE = re.compile(r"\btop\s*(\d+)\b", re.IGNORECASE)
|
||||
TOPN_CN_RE = re.compile(r"前\s*(?:\d+|[一二三四五六七八九十百千万]+)")
|
||||
NUMBER_RE = re.compile(r"\b\d{8,14}\b")
|
||||
DATE_RE = re.compile(r"\b\d{4}-\d{2}-\d{2}\b|\b\d{1,2}/\d{1,2}(?:/\d{2,4})?\b")
|
||||
AGGREGATE_ENGLISH_RE = re.compile(
|
||||
r"\b(?:count|summary|summarize|aggregate|sum)\b|\bgroup\s+by\b",
|
||||
re.IGNORECASE,
|
||||
)
|
||||
HISTORY_ENGLISH_RE = re.compile(r"\b(?:history|historical|changelog)\b", re.IGNORECASE)
|
||||
|
||||
|
||||
def _has_topn_hint(text: str) -> bool:
|
||||
lowered = (text or "").lower()
|
||||
if TOPN_RE.search(lowered):
|
||||
return True
|
||||
if TOPN_CN_RE.search(text or ""):
|
||||
return True
|
||||
return any(token in (text or "") for token in ["排名", "最高", "最大", "最小"])
|
||||
|
||||
|
||||
def _last_human_message(state: AgentState) -> HumanMessage | None:
|
||||
for message in reversed(state.messages):
|
||||
if isinstance(message, HumanMessage):
|
||||
return message
|
||||
return None
|
||||
|
||||
|
||||
def _looks_like_follow_up(text: str) -> bool:
|
||||
lowered = (text or "").strip().lower()
|
||||
return any(hint in lowered for hint in FOLLOW_UP_HINTS)
|
||||
|
||||
|
||||
def _detect_query_mode(text: str) -> str:
|
||||
lowered = (text or "").lower()
|
||||
if not lowered:
|
||||
return "detail"
|
||||
if HISTORY_ENGLISH_RE.search(lowered) or any(token in lowered for token in ["历史", "变更记录", "历史变更", "change record", "change log", "changes"]):
|
||||
return "history"
|
||||
if AGGREGATE_ENGLISH_RE.search(lowered) or any(token in lowered for token in ["聚合", "统计", "汇总", "计数", "数量", "多少", "几个", "分组", "求和", "总计", "合计"]):
|
||||
return "aggregate"
|
||||
if _has_topn_hint(text):
|
||||
return "topn"
|
||||
return "detail"
|
||||
|
||||
|
||||
def _extract_query_entities(text: str, prompt_data: Dict[str, Any] | None = None) -> Dict[str, Any]:
|
||||
lowered = (text or "").lower()
|
||||
entity_numbers = NUMBER_RE.findall(text or "")
|
||||
entity_dates = DATE_RE.findall(text or "")
|
||||
|
||||
top_n = None
|
||||
match = TOPN_RE.search(lowered)
|
||||
if match:
|
||||
try:
|
||||
top_n = int(match.group(1))
|
||||
except Exception:
|
||||
top_n = None
|
||||
elif _has_topn_hint(text):
|
||||
top_n = 10
|
||||
|
||||
sort_direction = "desc"
|
||||
if any(token in lowered for token in ["从小到大", "升序", "ascending", "asc"]):
|
||||
sort_direction = "asc"
|
||||
elif any(token in lowered for token in ["从大到小", "降序", "descending", "desc"]):
|
||||
sort_direction = "desc"
|
||||
|
||||
countries: List[str] = []
|
||||
regions: List[str] = []
|
||||
if prompt_data:
|
||||
additional_fields = (((prompt_data.get("field_mapping_reference") or {}).get("additional_fields") or {}))
|
||||
countries = list((((additional_fields.get("ship_to_country") or {}).get("values")) or []))
|
||||
regions = list((((additional_fields.get("region") or {}).get("values")) or []))
|
||||
|
||||
words = re.findall(r"\b[A-Z]{2,10}\b", text or "")
|
||||
matched_countries = [word for word in words if word in countries]
|
||||
matched_regions = [word for word in words if word in regions]
|
||||
|
||||
return {
|
||||
"numbers": entity_numbers,
|
||||
"dates": entity_dates,
|
||||
"top_n": top_n,
|
||||
"sort_direction": sort_direction,
|
||||
"country_codes": matched_countries,
|
||||
"regions": matched_regions,
|
||||
"mentions_eta_info": "eta信息" in lowered or "eta info" in lowered,
|
||||
"mentions_history": any(token in lowered for token in ["history", "historical", "changelog", "历史", "变更记录", "历史变更"]),
|
||||
}
|
||||
|
||||
|
||||
def _get_default_table_name() -> str | None:
|
||||
cfg = Config.get_section("ragflow")
|
||||
table_name = str(cfg.get("default_table_name") or "").strip()
|
||||
return table_name or None
|
||||
|
||||
|
||||
def _looks_like_json(text: str) -> bool:
|
||||
stripped = (text or "").strip()
|
||||
return stripped.startswith("{") or stripped.startswith("[")
|
||||
|
||||
|
||||
def _try_json_loads(value: Any) -> Any:
|
||||
if isinstance(value, (dict, list)):
|
||||
return value
|
||||
if isinstance(value, str) and _looks_like_json(value):
|
||||
try:
|
||||
return json.loads(value)
|
||||
except Exception:
|
||||
return value
|
||||
return value
|
||||
|
||||
|
||||
def _parse_sr_api_result(raw_result: Any) -> Any:
|
||||
parsed = _try_json_loads(raw_result)
|
||||
if isinstance(parsed, dict) and "text" in parsed:
|
||||
text_payload = _try_json_loads(parsed.get("text"))
|
||||
parsed = {**parsed, "text": text_payload}
|
||||
return parsed
|
||||
|
||||
|
||||
def _extract_result_rows(value: Any) -> list[Any] | None:
|
||||
if isinstance(value, list):
|
||||
return value
|
||||
|
||||
if isinstance(value, dict):
|
||||
for key in ("data", "rows", "records", "items", "list", "result", "values"):
|
||||
rows = value.get(key)
|
||||
if isinstance(rows, list):
|
||||
return rows
|
||||
|
||||
nested = value.get("text")
|
||||
if isinstance(nested, (dict, list)):
|
||||
return _extract_result_rows(nested)
|
||||
|
||||
return None
|
||||
|
||||
|
||||
def _is_empty_sr_api_result(raw_result: Any) -> bool:
|
||||
parsed = _parse_sr_api_result(raw_result)
|
||||
|
||||
rows = _extract_result_rows(parsed)
|
||||
if rows is not None:
|
||||
return len(rows) == 0
|
||||
|
||||
if isinstance(parsed, dict):
|
||||
total = parsed.get("total")
|
||||
if isinstance(total, int):
|
||||
return total == 0
|
||||
|
||||
text_payload = parsed.get("text")
|
||||
if isinstance(text_payload, dict):
|
||||
total = text_payload.get("total")
|
||||
if isinstance(total, int):
|
||||
return total == 0
|
||||
|
||||
return False
|
||||
|
||||
|
||||
def _format_empty_result_response(query: str, llm_response: str) -> str:
|
||||
"""将空结果的 LLM 回复格式化为纯文本格式，与 endpoints._build_rich_answer_html 保持一致"""
|
||||
safe_query = html.escape((query or "").strip())
|
||||
safe_response = html.escape((llm_response or "").strip())
|
||||
|
||||
return (
|
||||
f"Question: {safe_query}\n"
|
||||
f"{safe_response}\n"
|
||||
f"Rows: 0"
|
||||
)
|
||||
|
||||
|
||||
def _default_normalizer_prompt() -> str:
|
||||
return (
|
||||
"You are a translation and normalization assistant. "
|
||||
"Convert the user's input to a clear, grammatically correct English sentence suitable for SQL intent. "
|
||||
"Preserve business identifiers, codes, country abbreviations, order numbers, and field aliases exactly when possible. "
|
||||
"Return only the final English sentence without extra explanations."
|
||||
)
|
||||
|
||||
|
||||
def process_input(state: AgentState) -> AgentState:
|
||||
"""处理用户输入"""
|
||||
_trace(state, "[process_input][in] messages=", _short(state.messages))
|
||||
last_message = _last_human_message(state)
|
||||
if last_message:
|
||||
state.original_input = str(last_message.content)
|
||||
state.context["is_follow_up"] = _looks_like_follow_up(state.original_input)
|
||||
state.set_current_step("processed")
|
||||
_trace(state, "[process_input][out] current_step=", state.current_step)
|
||||
return state
|
||||
|
||||
|
||||
def normalize_input(state: AgentState, model) -> AgentState:
|
||||
"""将用户输入规范化为保留业务标识的标准英文语句"""
|
||||
last_message = _last_human_message(state)
|
||||
if not last_message:
|
||||
return state
|
||||
|
||||
_trace(state, "[normalize_input][in] user_input=", _short(last_message.content))
|
||||
|
||||
prompt_manager = get_prompt_manager()
|
||||
normalizer_prompt = (
|
||||
prompt_manager.get("user", "english_normalizer")
|
||||
or prompt_manager.get("system", "english_normalizer")
|
||||
or _default_normalizer_prompt()
|
||||
)
|
||||
system_prompt = SystemMessage(content=normalizer_prompt)
|
||||
|
||||
try:
|
||||
response = model.invoke([system_prompt, HumanMessage(content=last_message.content)])
|
||||
normalized = response.content if hasattr(response, "content") else str(response)
|
||||
except Exception as exc:
|
||||
normalized = str(last_message.content)
|
||||
state.add_error(f"normalize_input_failed:{exc}")
|
||||
|
||||
state.original_input = str(last_message.content)
|
||||
state.normalized_input = normalized.strip() or str(last_message.content)
|
||||
state.sync_context()
|
||||
state.set_current_step("normalized")
|
||||
_trace(state, "[normalize_input][out] normalized=", _short(state.normalized_input))
|
||||
return state
|
||||
|
||||
|
||||
def classify_query_mode(state: AgentState) -> AgentState:
|
||||
"""识别查询模式：detail / aggregate / topn / history。"""
|
||||
text = "\n".join(filter(None, [state.original_input, state.normalized_input]))
|
||||
state.query_mode = _detect_query_mode(text)
|
||||
|
||||
if not state.intent:
|
||||
state.intent = "sql_query" if state.original_input else "general"
|
||||
|
||||
state.query_entities = _extract_query_entities(text)
|
||||
state.sync_context()
|
||||
state.set_current_step("query_mode_classified")
|
||||
_trace(state, "[classify_query_mode][out] query_mode=", state.query_mode)
|
||||
_trace(state, "[classify_query_mode][out] query_entities=", _short(state.query_entities))
|
||||
return state
|
||||
|
||||
|
||||
def match_table(state: AgentState) -> AgentState:
|
||||
"""根据规范化输入检索候选表，并在追问场景下回退到上一轮表或配置默认表。"""
|
||||
query = state.normalized_input or state.original_input
|
||||
if not query:
|
||||
return state
|
||||
|
||||
_trace(state, "[match_table][in] query=", _short(query))
|
||||
matcher = get_template_matcher()
|
||||
match_result = matcher.match(query)
|
||||
table_name = (match_result or {}).get("table_name")
|
||||
candidate_tables = list((match_result or {}).get("candidates") or [])
|
||||
|
||||
if not table_name and state.context.get("is_follow_up"):
|
||||
last_context = state.context.get("last_context") or {}
|
||||
fallback_table = last_context.get("table_name") or ((last_context.get("table_match") or {}).get("table_name"))
|
||||
if fallback_table:
|
||||
table_name = fallback_table
|
||||
candidate_tables = candidate_tables or [{"table_name": fallback_table, "source": "last_context"}]
|
||||
match_result = {
|
||||
"table_name": fallback_table,
|
||||
"candidates": candidate_tables,
|
||||
"raw": {"source": "last_context"},
|
||||
}
|
||||
state.context["table_match_fallback"] = "last_context"
|
||||
|
||||
if not table_name:
|
||||
default_table = _get_default_table_name()
|
||||
if default_table:
|
||||
table_name = default_table
|
||||
candidate_tables = candidate_tables or [{"table_name": default_table, "source": "config_default"}]
|
||||
match_result = {
|
||||
"table_name": default_table,
|
||||
"candidates": candidate_tables,
|
||||
"raw": {"source": "config_default"},
|
||||
}
|
||||
state.context["table_match_fallback"] = "config_default"
|
||||
state.context["default_table_name"] = default_table
|
||||
|
||||
state.table_match = dict(match_result or {})
|
||||
state.candidate_tables = candidate_tables
|
||||
state.table_name = table_name
|
||||
state.sync_context()
|
||||
state.set_current_step("table_matched")
|
||||
_trace(state, "[match_table][out] table_name=", state.table_name)
|
||||
return state
|
||||
|
||||
|
||||
def load_sql_prompt(state: AgentState) -> AgentState:
|
||||
"""加载目标表对应的 SQL prompt JSON。"""
|
||||
if not state.table_name:
|
||||
_trace(state, "[load_sql_prompt][skip] missing table_name")
|
||||
return state
|
||||
|
||||
prompt_manager = get_sql_prompt_manager()
|
||||
prompt_data, source = prompt_manager.get_prompt_with_source(state.table_name)
|
||||
if not prompt_data:
|
||||
state.add_error(f"sql_prompt_not_found:{state.table_name}")
|
||||
_trace(state, "[load_sql_prompt][skip] prompt not found for table=", state.table_name)
|
||||
return state
|
||||
|
||||
state.sql_prompt = prompt_data
|
||||
state.sql_prompt_source = source
|
||||
state.sync_context()
|
||||
state.set_current_step("sql_prompt_loaded")
|
||||
_trace(state, f"[load_sql_prompt][out] table_name={state.table_name} source={source}")
|
||||
return state
|
||||
|
||||
|
||||
def build_sql_plan(state: AgentState) -> AgentState:
|
||||
"""构建结构化 SQL 计划，为最终 SQL 生成提供显式上下文。"""
|
||||
prompt_data = state.sql_prompt or {}
|
||||
business_rules = (prompt_data.get("business_logic_rules") or {})
|
||||
data_model = (prompt_data.get("data_model_specification") or {})
|
||||
meta = (prompt_data.get("meta") or {})
|
||||
default_fields = ((data_model.get("mandatory_display_fields") or {}).get("default_fields")) or ""
|
||||
|
||||
text = "\n".join(filter(None, [state.original_input, state.normalized_input]))
|
||||
extracted = _extract_query_entities(text, prompt_data)
|
||||
if state.query_entities:
|
||||
extracted = {**state.query_entities, **{k: v for k, v in extracted.items() if v not in (None, [], {}, "")}}
|
||||
|
||||
state.query_entities = extracted
|
||||
state.sql_plan = {
|
||||
"intent": state.intent or "sql_query",
|
||||
"query_mode": state.query_mode or "detail",
|
||||
"selected_table": state.table_name,
|
||||
"candidate_tables": [item.get("table_name", item) for item in state.candidate_tables],
|
||||
"data_source": meta.get("data_source"),
|
||||
"domain": meta.get("domain"),
|
||||
"default_select_fields": default_fields,
|
||||
"default_filters": list(business_rules.get("default_filters") or []),
|
||||
"aggregate_rules": dict(business_rules.get("aggregate_rules") or {}),
|
||||
"top_n_rules": dict(business_rules.get("top_n_rules") or {}),
|
||||
"query_entities": extracted,
|
||||
"previous_context": {
|
||||
key: (state.context.get("last_context") or {}).get(key)
|
||||
for key in ("table_name", "query_mode", "final_sql", "sql_plan")
|
||||
if (state.context.get("last_context") or {}).get(key) is not None
|
||||
},
|
||||
}
|
||||
state.sync_context()
|
||||
state.set_current_step("sql_plan_built")
|
||||
_trace(state, "[build_sql_plan][out] sql_plan=", _short(state.sql_plan))
|
||||
return state
|
||||
|
||||
|
||||
def generate_sql(state: AgentState, model) -> AgentState:
|
||||
"""根据表 prompt + 结构化计划生成 SQL。"""
|
||||
if not state.table_name or not state.normalized_input:
|
||||
_trace(state, "[generate_sql][skip] missing table_name or normalized_input")
|
||||
return state
|
||||
|
||||
prompt_data = state.sql_prompt
|
||||
if not prompt_data:
|
||||
_trace(state, "[generate_sql][skip] missing sql_prompt")
|
||||
return state
|
||||
|
||||
_trace(state, "[generate_sql][in] table_name=", state.table_name)
|
||||
_trace(state, "[generate_sql][in] query_mode=", state.query_mode)
|
||||
|
||||
prompt_text = json.dumps(prompt_data, ensure_ascii=False, indent=2)
|
||||
plan_text = json.dumps(state.sql_plan or {}, ensure_ascii=False, indent=2)
|
||||
prompt_manager = get_prompt_manager()
|
||||
system_template = prompt_manager.get("system", "sql_mysql_select_only")
|
||||
system_content = system_template.format(table_prompt_json=prompt_text)
|
||||
user_content = (
|
||||
f"Original user question: {state.original_input}\n"
|
||||
f"Normalized user question: {state.normalized_input}\n"
|
||||
f"Detected query mode: {state.query_mode or 'detail'}\n"
|
||||
f"SQL planning context JSON:\n{plan_text}\n"
|
||||
"Generate the best SQL for the selected table and query mode. "
|
||||
"If the query mode is topn and the plan contains top_n, LIMIT is allowed and required. "
|
||||
"If update_date is used as a filter, do not add data_flag. "
|
||||
"Return only the final SQL."
|
||||
)
|
||||
response = model.invoke([SystemMessage(content=system_content), HumanMessage(content=user_content)])
|
||||
sql_text = response.content if hasattr(response, "content") else str(response)
|
||||
state.final_sql = sql_text.strip()
|
||||
state.sync_context()
|
||||
state.set_current_step("sql_generated")
|
||||
_trace(state, "[generate_sql][out] sql=", state.final_sql, clip=False)
|
||||
return state
|
||||
|
||||
|
||||
def execute_sql(state: AgentState) -> AgentState:
|
||||
"""在需要时执行生成后的 SQL。skip_sr_api=True 时跳过执行。"""
|
||||
if not state.final_sql:
|
||||
_trace(state, "[execute_sql][skip] missing final_sql")
|
||||
state.set_current_step("sql_execution_skipped")
|
||||
return state
|
||||
|
||||
if state.skip_sr_api:
|
||||
_trace(state, "[execute_sql][skip] skip_sr_api=true")
|
||||
state.set_current_step("sql_execution_skipped")
|
||||
return state
|
||||
|
||||
try:
|
||||
tool = SrApiQueryTool()
|
||||
state.sr_api_result = tool.run(json.dumps({"sql": state.final_sql}, ensure_ascii=False))
|
||||
_trace(state, "[execute_sql][out] sr_api_result=", _short(state.sr_api_result))
|
||||
except Exception as exc:
|
||||
state.add_error(f"sql_execution_failed:{exc}")
|
||||
_trace(state, "[execute_sql][error]", exc)
|
||||
state.sync_context()
|
||||
state.set_current_step("sql_executed")
|
||||
return state
|
||||
|
||||
|
||||
def check_empty_result(state: AgentState) -> AgentState:
|
||||
"""检查 SQL 执行结果是否为空，设置 is_empty_result 标记。"""
|
||||
sr_api_result = state.sr_api_result
|
||||
|
||||
if not sr_api_result:
|
||||
state.context["is_empty_result"] = None
|
||||
state.context["result_checked"] = False
|
||||
_trace(state, "[check_empty_result][skip] no sr_api_result")
|
||||
state.set_current_step("result_checked")
|
||||
return state
|
||||
|
||||
is_empty = _is_empty_sr_api_result(sr_api_result)
|
||||
state.context["is_empty_result"] = is_empty
|
||||
state.context["result_checked"] = True
|
||||
|
||||
if is_empty:
|
||||
_trace(state, "[check_empty_result][out] is_empty=True")
|
||||
else:
|
||||
result_rows = _extract_result_rows(sr_api_result)
|
||||
row_count = len(result_rows) if result_rows else 0
|
||||
state.context["result_row_count"] = row_count
|
||||
_trace(state, f"[check_empty_result][out] is_empty=False, row_count={row_count}")
|
||||
|
||||
state.sync_context()
|
||||
state.set_current_step("result_checked")
|
||||
return state
|
||||
|
||||
|
||||
def generate_response(state: AgentState, model) -> AgentState:
|
||||
"""使用 SQL 执行结果、SQL 本身或模型回退生成最终回复。"""
|
||||
_trace(state, "[generate_response][in] context_keys=", list((state.context or {}).keys()))
|
||||
|
||||
# 优先使用 context 中的 is_empty_result（由 check_empty_result 节点设置）
|
||||
is_empty_result = state.context.get("is_empty_result")
|
||||
sr_api_result = state.sr_api_result
|
||||
|
||||
# 如果有执行结果且标记为空
|
||||
if sr_api_result and is_empty_result is True:
|
||||
sql_plan_text = json.dumps(state.sql_plan or {}, ensure_ascii=False, indent=2)
|
||||
|
||||
fallback_system = SystemMessage(
|
||||
content=(
|
||||
"You are a friendly business query assistant. "
|
||||
"The query executed successfully but returned no data. "
|
||||
"Answer the user in a concise and helpful way. "
|
||||
"IMPORTANT RULES:\n"
|
||||
"1. DO NOT show any SQL statements, technical field names, or database terminology to the user\n"
|
||||
"2. Use business language that non-technical users can understand\n"
|
||||
"3. Clearly state that no matching data was found\n"
|
||||
"4. Provide specific suggestions about which conditions might be too restrictive\n"
|
||||
"5. Use the query context to suggest alternatives, but express them in plain language\n"
|
||||
"6. For example, say 'try removing the country filter' instead of 'remove ship_to_country condition'\n"
|
||||
"7. For example, say 'try searching all records instead of just the latest' instead of 'remove data_flag filter'"
|
||||
)
|
||||
)
|
||||
fallback_user = HumanMessage(
|
||||
content=(
|
||||
f"Original user question: {state.original_input}\n"
|
||||
f"Query mode: {state.query_mode or 'detail'}\n"
|
||||
f"SQL plan context (for your reference only, DO NOT show to user):\n{sql_plan_text}\n"
|
||||
"Please answer the user in plain business language without any SQL or technical terms."
|
||||
)
|
||||
)
|
||||
|
||||
try:
|
||||
response = model.invoke([fallback_system, fallback_user])
|
||||
llm_content = response.content if hasattr(response, "content") else str(response)
|
||||
state.messages.append(response)
|
||||
|
||||
formatted_html = _format_empty_result_response(
|
||||
state.original_input,
|
||||
llm_content
|
||||
)
|
||||
state.context["formatted_answer"] = formatted_html
|
||||
state.context["response_source"] = "model_empty_result_fallback"
|
||||
_trace(state, "[generate_response][out] source=model_empty_result_fallback")
|
||||
except Exception as exc:
|
||||
state.add_error(f"empty_result_fallback_failed:{exc}")
|
||||
fixed_content = "未查询到符合条件的数据，请尝试调整筛选条件后再查询。"
|
||||
state.messages.append(AIMessage(content=fixed_content))
|
||||
|
||||
formatted_html = _format_empty_result_response(
|
||||
state.original_input,
|
||||
fixed_content
|
||||
)
|
||||
state.context["formatted_answer"] = formatted_html
|
||||
state.context["response_source"] = "empty_result_fixed_fallback"
|
||||
_trace(state, "[generate_response][out] source=empty_result_fixed_fallback")
|
||||
|
||||
state.sync_context()
|
||||
state.set_current_step("response_generated")
|
||||
return state
|
||||
|
||||
# 有执行结果且不为空
|
||||
if sr_api_result:
|
||||
state.context["is_empty_result"] = False
|
||||
state.context["response_source"] = "sr_api_result"
|
||||
state.messages.append(AIMessage(content=str(sr_api_result)))
|
||||
_trace(state, "[generate_response][out] source=sr_api_result")
|
||||
state.sync_context()
|
||||
state.set_current_step("response_generated")
|
||||
return state
|
||||
|
||||
# 没有执行结果，返回 SQL（skip_sr_api=True 的情况）
|
||||
final_sql = state.final_sql
|
||||
if final_sql:
|
||||
state.context["response_source"] = "final_sql"
|
||||
state.messages.append(AIMessage(content=final_sql))
|
||||
_trace(state, "[generate_response][out] source=final_sql")
|
||||
state.sync_context()
|
||||
state.set_current_step("response_generated")
|
||||
return state
|
||||
|
||||
# 兜底：使用模型生成回复
|
||||
if state.messages:
|
||||
response = model.invoke(state.messages)
|
||||
state.messages.append(response)
|
||||
state.context["response_source"] = "model_invoke"
|
||||
_trace(state, "[generate_response][out] source=model_invoke")
|
||||
state.sync_context()
|
||||
state.set_current_step("response_generated")
|
||||
return state
|
||||
@@ -0,0 +1,124 @@
|
||||
from dataclasses import dataclass, field
|
||||
from typing import Any, Dict, List, Optional
|
||||
from langchain_core.messages import BaseMessage
|
||||
|
||||
|
||||
@dataclass
|
||||
class AgentState:
|
||||
"""代理工作流的状态定义"""
|
||||
messages: List[BaseMessage] = field(default_factory=list)
|
||||
current_step: str = "start"
|
||||
context: Dict[str, Any] = field(default_factory=dict)
|
||||
intent: Optional[str] = None
|
||||
original_input: str = ""
|
||||
normalized_input: str = ""
|
||||
query_mode: str = ""
|
||||
query_entities: Dict[str, Any] = field(default_factory=dict)
|
||||
candidate_tables: List[Dict[str, Any]] = field(default_factory=list)
|
||||
table_match: Dict[str, Any] = field(default_factory=dict)
|
||||
table_name: Optional[str] = None
|
||||
sql_prompt: Dict[str, Any] = field(default_factory=dict)
|
||||
sql_prompt_source: str = ""
|
||||
sql_plan: Dict[str, Any] = field(default_factory=dict)
|
||||
final_sql: str = ""
|
||||
sr_api_result: Any = None
|
||||
skip_sr_api: bool = False
|
||||
validation_errors: List[str] = field(default_factory=list)
|
||||
errors: List[str] = field(default_factory=list)
|
||||
|
||||
def __post_init__(self) -> None:
|
||||
self.context = dict(self.context or {})
|
||||
self.messages = list(self.messages or [])
|
||||
self.intent = self.context.get("intent", self.intent)
|
||||
self.original_input = str(self.context.get("original_input") or self.original_input or "")
|
||||
self.normalized_input = str(self.context.get("normalized_input") or self.normalized_input or "")
|
||||
self.query_mode = str(self.context.get("query_mode") or self.query_mode or "")
|
||||
self.query_entities = dict(self.context.get("query_entities") or self.query_entities or {})
|
||||
self.candidate_tables = list(self.context.get("candidate_tables") or self.candidate_tables or [])
|
||||
self.table_match = dict(self.context.get("table_match") or self.table_match or {})
|
||||
self.table_name = self.context.get("table_name") or self.table_name or self.table_match.get("table_name")
|
||||
self.sql_prompt = dict(self.context.get("sql_prompt") or self.sql_prompt or {})
|
||||
self.sql_prompt_source = str(self.context.get("sql_prompt_source") or self.sql_prompt_source or "")
|
||||
self.sql_plan = dict(self.context.get("sql_plan") or self.sql_plan or {})
|
||||
self.final_sql = str(self.context.get("final_sql") or self.final_sql or "")
|
||||
self.sr_api_result = self.context.get("sr_api_result", self.sr_api_result)
|
||||
self.skip_sr_api = bool(self.context.get("skip_sr_api", self.skip_sr_api))
|
||||
self.validation_errors = list(self.context.get("validation_errors") or self.validation_errors or [])
|
||||
self.errors = list(self.context.get("errors") or self.errors or [])
|
||||
self.sync_context()
|
||||
|
||||
def sync_context(self) -> Dict[str, Any]:
|
||||
"""将显式状态字段回写到兼容 context。"""
|
||||
self.context["current_step"] = self.current_step
|
||||
self.context["skip_sr_api"] = self.skip_sr_api
|
||||
|
||||
optional_values = {
|
||||
"intent": self.intent,
|
||||
"original_input": self.original_input,
|
||||
"normalized_input": self.normalized_input,
|
||||
"query_mode": self.query_mode,
|
||||
"query_entities": self.query_entities,
|
||||
"candidate_tables": self.candidate_tables,
|
||||
"table_match": self.table_match,
|
||||
"table_name": self.table_name,
|
||||
"sql_prompt": self.sql_prompt,
|
||||
"sql_prompt_source": self.sql_prompt_source,
|
||||
"sql_plan": self.sql_plan,
|
||||
"final_sql": self.final_sql,
|
||||
"sr_api_result": self.sr_api_result,
|
||||
"validation_errors": self.validation_errors,
|
||||
"errors": self.errors,
|
||||
}
|
||||
|
||||
for key, value in optional_values.items():
|
||||
empty = value in (None, "", [], {})
|
||||
if empty:
|
||||
self.context.pop(key, None)
|
||||
else:
|
||||
self.context[key] = value
|
||||
return self.context
|
||||
|
||||
def set_current_step(self, step: str) -> None:
|
||||
self.current_step = step
|
||||
self.sync_context()
|
||||
|
||||
def add_error(self, message: str) -> None:
|
||||
if message and message not in self.errors:
|
||||
self.errors.append(message)
|
||||
self.sync_context()
|
||||
|
||||
def apply_graph_result(self, result: Any) -> "AgentState":
|
||||
"""兼容 LangGraph 返回 dict 或 AgentState 两种形式。"""
|
||||
if isinstance(result, AgentState):
|
||||
return result
|
||||
if isinstance(result, dict):
|
||||
self.messages = result.get("messages", self.messages)
|
||||
self.current_step = result.get("current_step", self.current_step)
|
||||
self.context.update(result.get("context", {}))
|
||||
self.intent = self.context.get("intent")
|
||||
self.original_input = str(self.context.get("original_input") or self.original_input)
|
||||
self.normalized_input = str(self.context.get("normalized_input") or self.normalized_input)
|
||||
self.query_mode = str(self.context.get("query_mode") or self.query_mode)
|
||||
self.query_entities = dict(self.context.get("query_entities") or self.query_entities)
|
||||
self.candidate_tables = list(self.context.get("candidate_tables") or self.candidate_tables)
|
||||
self.table_match = dict(self.context.get("table_match") or self.table_match)
|
||||
self.table_name = self.context.get("table_name") or self.table_name or self.table_match.get("table_name")
|
||||
self.sql_prompt = dict(self.context.get("sql_prompt") or self.sql_prompt)
|
||||
self.sql_prompt_source = str(self.context.get("sql_prompt_source") or self.sql_prompt_source)
|
||||
self.sql_plan = dict(self.context.get("sql_plan") or self.sql_plan)
|
||||
self.final_sql = str(self.context.get("final_sql") or self.final_sql)
|
||||
self.sr_api_result = self.context.get("sr_api_result", self.sr_api_result)
|
||||
self.skip_sr_api = bool(self.context.get("skip_sr_api", self.skip_sr_api))
|
||||
self.validation_errors = list(self.context.get("validation_errors") or self.validation_errors)
|
||||
self.errors = list(self.context.get("errors") or self.errors)
|
||||
self.sync_context()
|
||||
return self
|
||||
|
||||
def to_result(self) -> Dict[str, Any]:
|
||||
"""输出与现有 API 兼容的结果结构。"""
|
||||
self.sync_context()
|
||||
return {
|
||||
"messages": self.messages,
|
||||
"current_step": self.current_step,
|
||||
"context": self.context,
|
||||
}
|
||||
@@ -1,60 +0,0 @@
|
||||
from typing import Any, Dict, Optional
|
||||
from langchain_core.messages import HumanMessage
|
||||
from langgraph.graph import StateGraph, END
|
||||
|
||||
from services.llm_factory import create_chat_model
|
||||
from .state import AgentState
|
||||
from . import nodes
|
||||
|
||||
|
||||
class BaseAgent:
|
||||
"""包含通用功能的基础代理类"""
|
||||
|
||||
def __init__(self, model_section: Optional[str] = None):
|
||||
self.model = create_chat_model(model_section)
|
||||
self.graph = self._build_graph()
|
||||
|
||||
def _build_graph(self) -> StateGraph:
|
||||
"""构建代理状态图"""
|
||||
workflow = StateGraph(AgentState)
|
||||
|
||||
workflow.add_node("process_input", nodes.process_input)
|
||||
workflow.add_node("normalize_input", self._normalize_input)
|
||||
workflow.add_node("generate_sql", self._generate_sql)
|
||||
workflow.add_node("generate_response", self._generate_response)
|
||||
|
||||
workflow.add_edge("process_input", "normalize_input")
|
||||
workflow.add_edge("normalize_input", "generate_sql")
|
||||
workflow.add_edge("generate_sql", "generate_response")
|
||||
workflow.add_edge("generate_response", END)
|
||||
|
||||
workflow.set_entry_point("process_input")
|
||||
|
||||
return workflow.compile()
|
||||
|
||||
def _generate_response(self, state: AgentState) -> AgentState:
|
||||
"""使用 LLM 生成回复"""
|
||||
return nodes.generate_response(state, self.model)
|
||||
|
||||
def _normalize_input(self, state: AgentState) -> AgentState:
|
||||
"""规范化用户输入"""
|
||||
return nodes.normalize_input(state, self.model)
|
||||
|
||||
def _generate_sql(self, state: AgentState) -> AgentState:
|
||||
"""生成 SQL"""
|
||||
return nodes.generate_sql(state, self.model)
|
||||
|
||||
def run(self, user_input: str, **kwargs) -> Dict[str, Any]:
|
||||
"""运行代理并处理用户输入"""
|
||||
initial_state = AgentState(
|
||||
messages=[HumanMessage(content=user_input)],
|
||||
context=kwargs
|
||||
)
|
||||
|
||||
result = self.graph.invoke(initial_state)
|
||||
|
||||
return {
|
||||
"messages": result.get("messages", []),
|
||||
"context": result.get("context", {}),
|
||||
"final_step": result.get("current_step", "unknown")
|
||||
}
|
||||
-107
@@ -1,107 +0,0 @@
|
||||
import json
|
||||
|
||||
from langchain_core.messages import BaseMessage, HumanMessage, SystemMessage, AIMessage
|
||||
from .state import AgentState
|
||||
from services.prompt_manager import get_prompt_manager
|
||||
from services.template_matcher import get_template_matcher
|
||||
from services.sql_prompt_manager import get_sql_prompt_manager
|
||||
from tools.sr_api_tool import SrApiQueryTool
|
||||
|
||||
|
||||
def _short(value, max_len: int = 500) -> str:
|
||||
text = str(value)
|
||||
return text if len(text) <= max_len else text[:max_len] + "..."
|
||||
|
||||
|
||||
def process_input(state: AgentState) -> AgentState:
|
||||
"""处理用户输入"""
|
||||
print("[process_input][in] messages=", _short(state.messages))
|
||||
state.current_step = "processed"
|
||||
print("[process_input][out] current_step=", state.current_step)
|
||||
return state
|
||||
|
||||
|
||||
def generate_response(state: AgentState, model) -> AgentState:
|
||||
"""使用 LLM 生成回复"""
|
||||
print("[generate_response][in] context_keys=", list((state.context or {}).keys()))
|
||||
sr_api_result = state.context.get("sr_api_result")
|
||||
if sr_api_result:
|
||||
state.messages.append(AIMessage(content=str(sr_api_result)))
|
||||
print("[generate_response][out] source=sr_api_result")
|
||||
return state
|
||||
final_sql = state.context.get("final_sql")
|
||||
if final_sql:
|
||||
state.messages.append(AIMessage(content=final_sql))
|
||||
print("[generate_response][out] source=final_sql")
|
||||
return state
|
||||
if state.messages:
|
||||
response = model.invoke(state.messages)
|
||||
state.messages.append(response)
|
||||
print("[generate_response][out] source=model_invoke")
|
||||
return state
|
||||
|
||||
|
||||
def normalize_input(state: AgentState, model) -> AgentState:
|
||||
"""将用户输入规范化为标准英文语句"""
|
||||
if not state.messages:
|
||||
return state
|
||||
|
||||
last_message = state.messages[-1]
|
||||
if not isinstance(last_message, HumanMessage):
|
||||
return state
|
||||
|
||||
print("[normalize_input][in] user_input=", _short(last_message.content))
|
||||
|
||||
prompt_manager = get_prompt_manager()
|
||||
normalizer_prompt = (
|
||||
prompt_manager.get("system", "english_normalizer")
|
||||
or prompt_manager.get("user", "english_normalizer")
|
||||
)
|
||||
system_prompt = SystemMessage(content=normalizer_prompt)
|
||||
|
||||
response = model.invoke([system_prompt, HumanMessage(content=last_message.content)])
|
||||
normalized = response.content if hasattr(response, "content") else str(response)
|
||||
print("[normalize_input][out] normalized=", _short(normalized))
|
||||
|
||||
state.context["original_input"] = last_message.content
|
||||
state.context["normalized_input"] = normalized
|
||||
|
||||
matcher = get_template_matcher()
|
||||
state.context["table_match"] = matcher.match(normalized)
|
||||
print("[normalize_input][out] table_match=", _short(state.context.get("table_match")))
|
||||
return state
|
||||
|
||||
|
||||
def generate_sql(state: AgentState, model) -> AgentState:
|
||||
"""根据表名与提示词生成 SQL"""
|
||||
table_match = state.context.get("table_match") or {}
|
||||
table_name = table_match.get("table_name")
|
||||
normalized = state.context.get("normalized_input")
|
||||
|
||||
if not table_name or not normalized:
|
||||
print("[generate_sql][skip] missing table_name or normalized")
|
||||
return state
|
||||
|
||||
print("[generate_sql][in] table_name=", table_name)
|
||||
print("[generate_sql][in] normalized=", _short(normalized))
|
||||
|
||||
prompt_manager = get_sql_prompt_manager()
|
||||
prompt_data = prompt_manager.get_prompt(table_name)
|
||||
if not prompt_data:
|
||||
print("[generate_sql][skip] prompt not found for table=", table_name)
|
||||
return state
|
||||
|
||||
prompt_text = json.dumps(prompt_data, ensure_ascii=False, indent=2)
|
||||
system_template = get_prompt_manager().get("system", "sql_mysql_select_only")
|
||||
system_content = system_template.format(table_prompt_json=prompt_text)
|
||||
user_content = f"User question (normalized English): {normalized}"
|
||||
response = model.invoke([SystemMessage(content=system_content), HumanMessage(content=user_content)])
|
||||
sql_text = response.content if hasattr(response, "content") else str(response)
|
||||
print("[generate_sql][out] sql=", _short(sql_text))
|
||||
|
||||
state.context["final_sql"] = sql_text
|
||||
if not state.context.get("skip_sr_api"):
|
||||
tool = SrApiQueryTool()
|
||||
state.context["sr_api_result"] = tool.run(json.dumps({"sql": sql_text}, ensure_ascii=False))
|
||||
print("[generate_sql][out] sr_api_result=", _short(state.context.get("sr_api_result")))
|
||||
return state
|
||||
@@ -1,14 +0,0 @@
|
||||
from typing import Any, Dict, List
|
||||
from langchain_core.messages import BaseMessage
|
||||
|
||||
|
||||
class AgentState:
|
||||
"""代理工作流的状态定义"""
|
||||
messages: List[BaseMessage]
|
||||
current_step: str
|
||||
context: Dict[str, Any]
|
||||
|
||||
def __init__(self, messages: List[BaseMessage] = None, current_step: str = "start", context: Dict[str, Any] = None):
|
||||
self.messages = messages or []
|
||||
self.current_step = current_step
|
||||
self.context = context or {}
|
||||
@@ -0,0 +1,10 @@
|
||||
# API 模块
|
||||
|
||||
## 作用
|
||||
|
||||
对外提供 FastAPI 接口，承接工作流执行、流式返回、工具调用与管理操作。
|
||||
|
||||
## 文件
|
||||
|
||||
- `endpoints.py`：路由定义与请求处理
|
||||
- `dependencies.py`：依赖注入与公共对象获取
|
||||
+5
-1
@@ -1 +1,5 @@
|
||||
"""API 包"""
|
||||
"""API 接口层"""
|
||||
|
||||
from .endpoints import router
|
||||
|
||||
__all__ = ["router"]
|
||||
|
||||
+516
-240
@@ -1,30 +1,180 @@
|
||||
def safe_json_dumps(obj):
|
||||
try:
|
||||
return json.dumps(obj, ensure_ascii=False, default=str)
|
||||
except Exception as e:
|
||||
return f"<unserializable: {e}>"
|
||||
import asyncio
|
||||
import html
|
||||
import json
|
||||
import time
|
||||
import uuid
|
||||
from typing import Any
|
||||
|
||||
from fastapi import APIRouter, HTTPException, Depends
|
||||
from fastapi.responses import StreamingResponse
|
||||
|
||||
from config import Config
|
||||
from schemas.agent_input import AgentInput
|
||||
from schemas.agent_output import AgentOutput
|
||||
from schemas.tool_input import ToolInput
|
||||
from schemas.tool_output import ToolOutput
|
||||
from schemas.chat_message_response import ChatMessageResponseDTO
|
||||
from schemas.chat_message_request import ChatMessageRequestDTO
|
||||
from schemas.super_agent import SuperAgentRequest, SuperAgentResponse, SuperAgentStreamEvent
|
||||
from schemas.chat_message_response import ChatMessageResponseDTO
|
||||
from schemas.message_feedback_request import MessageFeedbackRequestDTO
|
||||
from workflows.workflow_manager import WorkflowType
|
||||
from api.dependencies import get_workflow_manager, get_nacos_manager, get_service_config, get_tool_router, get_prompt_manager
|
||||
from services.app_errors import AppError, ErrorCode
|
||||
from services.ragflow_sync import RagflowSync
|
||||
from services.structured_logger import get_structured_logger
|
||||
from services.common.app_errors import AppError, ErrorCode
|
||||
from services.common.datetime_utils import DateTimeGenerator
|
||||
from services.integrations.ragflow_sync import RagflowSync
|
||||
from services.storage.structured_logger import get_structured_logger
|
||||
from services.storage.message_storage import get_message_storage
|
||||
from tools.sr_api_tool import SrApiQueryTool
|
||||
|
||||
|
||||
router = APIRouter()
|
||||
|
||||
|
||||
def _try_json_loads(value: Any) -> Any:
|
||||
if isinstance(value, (dict, list)):
|
||||
return value
|
||||
if isinstance(value, str):
|
||||
stripped = value.strip()
|
||||
if stripped.startswith("{") or stripped.startswith("["):
|
||||
try:
|
||||
return json.loads(stripped)
|
||||
except Exception:
|
||||
return value
|
||||
return value
|
||||
|
||||
|
||||
def _extract_total_rows(raw_sql_result: Any) -> int:
|
||||
parsed = _try_json_loads(raw_sql_result)
|
||||
if isinstance(parsed, dict):
|
||||
inner = _try_json_loads(parsed.get("text")) if "text" in parsed else parsed
|
||||
if isinstance(inner, dict):
|
||||
if isinstance(inner.get("total"), int):
|
||||
return int(inner.get("total") or 0)
|
||||
data = inner.get("data")
|
||||
if isinstance(data, list):
|
||||
return len(data)
|
||||
if isinstance(data, dict):
|
||||
rows = data.get("rows") or data.get("list") or data.get("records")
|
||||
if isinstance(rows, list):
|
||||
return len(rows)
|
||||
if isinstance(parsed, list):
|
||||
return len(parsed)
|
||||
return 0
|
||||
|
||||
|
||||
def _build_final_answer(raw_sql_result: Any) -> str:
|
||||
total = _extract_total_rows(raw_sql_result)
|
||||
if total <= 0:
|
||||
return "未查询到符合条件的数据，请尝试调整筛选条件后再查询。"
|
||||
return f"查询完成，共返回 {total} 条记录。"
|
||||
|
||||
|
||||
def _extract_sql_rows(raw_sql_result: Any) -> list[dict[str, Any]]:
|
||||
parsed = _try_json_loads(raw_sql_result)
|
||||
payload = parsed
|
||||
if isinstance(parsed, dict):
|
||||
payload = _try_json_loads(parsed.get("text")) if "text" in parsed else parsed
|
||||
|
||||
if isinstance(payload, dict):
|
||||
rows = payload.get("data")
|
||||
if isinstance(rows, list):
|
||||
normalized: list[dict[str, Any]] = []
|
||||
for item in rows:
|
||||
if isinstance(item, dict):
|
||||
normalized.append(item)
|
||||
else:
|
||||
normalized.append({"value": item})
|
||||
return normalized
|
||||
if isinstance(payload, list):
|
||||
normalized = []
|
||||
for item in payload:
|
||||
if isinstance(item, dict):
|
||||
normalized.append(item)
|
||||
else:
|
||||
normalized.append({"value": item})
|
||||
return normalized
|
||||
return []
|
||||
|
||||
|
||||
def _rows_to_html_table(rows: list[dict[str, Any]]) -> str:
|
||||
if not rows:
|
||||
return "No data~"
|
||||
|
||||
headers: list[str] = []
|
||||
for row in rows:
|
||||
for key in row.keys():
|
||||
if key not in headers:
|
||||
headers.append(str(key))
|
||||
|
||||
if not headers:
|
||||
return "No data~"
|
||||
|
||||
thead = "".join(f"<th>{html.escape(header)}</th>" for header in headers)
|
||||
body_rows = []
|
||||
for row in rows:
|
||||
cells = []
|
||||
for header in headers:
|
||||
value = row.get(header)
|
||||
cell_text = "" if value is None else str(value)
|
||||
cells.append(f"<td>{html.escape(cell_text)}</td>")
|
||||
body_rows.append(f"<tr>{''.join(cells)}</tr>")
|
||||
|
||||
return f"<table><thead><tr>{thead}</tr></thead><tbody>{''.join(body_rows)}</tbody></table>"
|
||||
|
||||
|
||||
def _extract_etl_version(rows: list[dict[str, Any]]) -> str:
|
||||
versions: list[tuple[int, str]] = []
|
||||
for row in rows:
|
||||
if not isinstance(row, dict):
|
||||
continue
|
||||
|
||||
etl_value = row.get("etl_time")
|
||||
if etl_value in (None, ""):
|
||||
continue
|
||||
|
||||
etl_text = str(etl_value).strip()
|
||||
if not etl_text:
|
||||
continue
|
||||
|
||||
try:
|
||||
bundle = DateTimeGenerator.bundle(etl_value, default_to_now=False)
|
||||
versions.append((bundle.epoch_millis, bundle.datetime_str))
|
||||
except Exception:
|
||||
versions.append((0, etl_text))
|
||||
|
||||
if not versions:
|
||||
return "Unknown"
|
||||
|
||||
versions.sort(key=lambda item: item[0], reverse=True)
|
||||
return versions[0][1]
|
||||
|
||||
|
||||
def _build_rich_answer_html(query: str, rows: list[dict[str, Any]], etl_version: str = None) -> str:
|
||||
safe_query = html.escape((query or "").strip())
|
||||
row_count = len(rows or [])
|
||||
if etl_version is None:
|
||||
etl_version = _extract_etl_version(rows)
|
||||
|
||||
if row_count <= 0:
|
||||
# 空数据返回纯文本，避免前端直接显示 HTML 标签
|
||||
return (
|
||||
f"Question: {safe_query}\n"
|
||||
"No data~\n"
|
||||
f"Rows: {row_count}\n"
|
||||
f"Data Version: {etl_version}"
|
||||
)
|
||||
|
||||
table_html = _rows_to_html_table(rows)
|
||||
|
||||
return (
|
||||
f"<div><strong>Question:</strong> {safe_query}</div>"
|
||||
f"<div style='margin-top:8px;'>{table_html}</div>"
|
||||
f"<div style='margin-top:8px;'><strong>Rows:</strong> {row_count}</div>"
|
||||
f"<div><strong>Data Version:</strong> {etl_version}</div>"
|
||||
)
|
||||
|
||||
|
||||
def _resolve_workflow_type(value: str) -> WorkflowType:
|
||||
try:
|
||||
return WorkflowType(value)
|
||||
@@ -42,6 +192,122 @@ def _to_http_error(e: Exception) -> HTTPException:
|
||||
return HTTPException(status_code=500, detail={"code": ErrorCode.INTERNAL_ERROR.value, "message": str(e)})
|
||||
|
||||
|
||||
def _require_query_text(payload: ChatMessageRequestDTO) -> str:
|
||||
query = payload.query
|
||||
if not isinstance(query, str) or not query.strip():
|
||||
raise _to_http_error(
|
||||
AppError(
|
||||
code=ErrorCode.INVALID_REQUEST,
|
||||
message="query 不能为空",
|
||||
status_code=400,
|
||||
detail={"field": "query", "reason": "missing_or_blank"},
|
||||
)
|
||||
)
|
||||
return query
|
||||
|
||||
|
||||
def _build_conversation_name(query: str, max_chars: int = 20) -> str:
|
||||
return (query or "")[:max_chars]
|
||||
|
||||
|
||||
def _storage_enabled(msg_storage) -> bool:
|
||||
return bool(getattr(msg_storage, "enabled", False))
|
||||
|
||||
|
||||
def _handle_conversation(payload: ChatMessageRequestDTO, current_timestamp: int, msg_storage) -> str:
|
||||
provided_conversation_id = (payload.conversation_id or "").strip() if isinstance(payload.conversation_id, str) else ""
|
||||
if not _storage_enabled(msg_storage):
|
||||
return provided_conversation_id or uuid.uuid4().hex
|
||||
|
||||
if not provided_conversation_id:
|
||||
conversation_id = uuid.uuid4().hex
|
||||
created = msg_storage.create_conversation(
|
||||
conversation_id=conversation_id,
|
||||
user=payload.user,
|
||||
name=_build_conversation_name(payload.query or ""),
|
||||
status="normal",
|
||||
introduction=None,
|
||||
created_at=current_timestamp,
|
||||
updated_at=current_timestamp,
|
||||
)
|
||||
if not created:
|
||||
raise AppError(
|
||||
code=ErrorCode.CONVERSATION_CREATE_FAILED,
|
||||
message="会话创建失败",
|
||||
status_code=500,
|
||||
detail={"conversation_id": conversation_id},
|
||||
)
|
||||
return conversation_id
|
||||
|
||||
conversation = msg_storage.get_conversation_by_id(provided_conversation_id)
|
||||
if conversation is None:
|
||||
raise AppError(
|
||||
code=ErrorCode.CONVERSATION_NOT_FOUND,
|
||||
message="会话不存在",
|
||||
status_code=400,
|
||||
detail={"conversation_id": provided_conversation_id},
|
||||
)
|
||||
|
||||
updated = msg_storage.update_conversation_updated_at(provided_conversation_id, current_timestamp)
|
||||
if not updated:
|
||||
raise AppError(
|
||||
code=ErrorCode.CONVERSATION_UPDATE_FAILED,
|
||||
message="会话更新时间失败",
|
||||
status_code=500,
|
||||
detail={"conversation_id": provided_conversation_id},
|
||||
)
|
||||
return provided_conversation_id
|
||||
|
||||
|
||||
def _extract_answer_text(result_payload: Any) -> str:
|
||||
result_obj = (result_payload or {}).get("result") if isinstance(result_payload, dict) else None
|
||||
if isinstance(result_obj, dict):
|
||||
messages = result_obj.get("messages")
|
||||
if isinstance(messages, list):
|
||||
for msg in reversed(messages):
|
||||
content = getattr(msg, "content", None)
|
||||
if content:
|
||||
return str(content)
|
||||
context = result_obj.get("context")
|
||||
if isinstance(context, dict) and context.get("final_sql"):
|
||||
return str(context.get("final_sql"))
|
||||
return json.dumps(result_obj or {}, ensure_ascii=False, default=str)
|
||||
|
||||
|
||||
def _safe_save_message(msg_storage, **kwargs) -> bool:
|
||||
if hasattr(msg_storage, "save_message"):
|
||||
try:
|
||||
return bool(msg_storage.save_message(**kwargs))
|
||||
except Exception:
|
||||
return False
|
||||
return False
|
||||
|
||||
|
||||
def _persist_message_or_raise(msg_storage, slog, trace_id: str, **kwargs) -> None:
|
||||
if not _storage_enabled(msg_storage):
|
||||
return
|
||||
|
||||
saved = _safe_save_message(msg_storage, **kwargs)
|
||||
if not saved:
|
||||
slog.log(
|
||||
"ERROR",
|
||||
"message_save_failed",
|
||||
trace_id,
|
||||
payload={"conversation_id": kwargs.get("conversation_id"), "message_id": kwargs.get("message_id")},
|
||||
)
|
||||
raise _to_http_error(
|
||||
AppError(
|
||||
code=ErrorCode.MESSAGE_SAVE_FAILED,
|
||||
message="消息保存失败",
|
||||
status_code=500,
|
||||
detail={
|
||||
"conversation_id": kwargs.get("conversation_id"),
|
||||
"message_id": kwargs.get("message_id"),
|
||||
},
|
||||
)
|
||||
)
|
||||
|
||||
|
||||
@router.get("/health")
|
||||
def health_check(service_config=Depends(get_service_config)):
|
||||
return {
|
||||
@@ -57,50 +323,90 @@ def nacos_status(nacos_manager=Depends(get_nacos_manager)):
|
||||
|
||||
|
||||
@router.post("/api/workflows", response_model=AgentOutput)
|
||||
def run_workflow(payload: AgentInput, workflow_manager=Depends(get_workflow_manager)):
|
||||
trace_id = uuid.uuid4().hex
|
||||
slog = get_structured_logger()
|
||||
slog.log("INFO", "run_workflow.start", trace_id, {"workflow_type": payload.workflow_type})
|
||||
def run_workflow(payload: ChatMessageRequestDTO, workflow_manager=Depends(get_workflow_manager)):
|
||||
query = _require_query_text(payload)
|
||||
msg_storage = get_message_storage()
|
||||
current_timestamp = DateTimeGenerator.now().epoch_millis
|
||||
try:
|
||||
workflow_type = _resolve_workflow_type(payload.workflow_type)
|
||||
conversation_id = _handle_conversation(payload, current_timestamp, msg_storage)
|
||||
except Exception as e:
|
||||
slog.log("ERROR", "run_workflow.invalid_type", trace_id, error_code=ErrorCode.INVALID_WORKFLOW_TYPE.value, payload={"workflow_type": payload.workflow_type})
|
||||
raise _to_http_error(e)
|
||||
trace_id = uuid.uuid4().hex
|
||||
message_id = uuid.uuid4().hex
|
||||
slog = get_structured_logger()
|
||||
workflow_type = WorkflowType.CONVERSATION
|
||||
save_logs: list[str] = [f"run_workflow.start response_mode={payload.response_mode}"]
|
||||
slog.log("INFO", "run_workflow.start", trace_id, {"workflow_type": workflow_type.value, "response_mode": payload.response_mode})
|
||||
|
||||
try:
|
||||
result = workflow_manager.execute_workflow(
|
||||
workflow_type=workflow_type,
|
||||
user_input=payload.query,
|
||||
session_id=payload.conversation_id,
|
||||
user_input=query,
|
||||
session_id=conversation_id,
|
||||
user=payload.user,
|
||||
inputs=payload.inputs,
|
||||
files=[item.model_dump() for item in payload.files],
|
||||
)
|
||||
save_logs.append(f"run_workflow.success session_id={result.get('session_id')}")
|
||||
slog.log("INFO", "run_workflow.success", trace_id, {"session_id": result.get("session_id")})
|
||||
except Exception as e:
|
||||
save_logs.append(f"run_workflow.failed error={e}")
|
||||
slog.log("ERROR", "run_workflow.failed", trace_id, error_code=ErrorCode.INTERNAL_ERROR.value, payload={"error": str(e)})
|
||||
raise _to_http_error(e)
|
||||
|
||||
answer_text = _extract_answer_text(result)
|
||||
_persist_message_or_raise(
|
||||
msg_storage,
|
||||
slog,
|
||||
trace_id,
|
||||
conversation_id=conversation_id,
|
||||
message_id=message_id,
|
||||
query=query,
|
||||
answer=answer_text,
|
||||
workflow_type=WorkflowType.CONVERSATION.value,
|
||||
user=payload.user,
|
||||
metadata={
|
||||
"trace_id": trace_id,
|
||||
"response_mode": payload.response_mode,
|
||||
"inputs": payload.inputs,
|
||||
"files": [item.model_dump() for item in payload.files],
|
||||
},
|
||||
created_at=current_timestamp,
|
||||
updated_at=current_timestamp,
|
||||
logs=save_logs,
|
||||
)
|
||||
if _storage_enabled(msg_storage):
|
||||
slog.log("INFO", "run_workflow.message_saved", trace_id, {"conversation_id": conversation_id, "message_id": message_id})
|
||||
|
||||
return AgentOutput(
|
||||
session_id=result["session_id"],
|
||||
session_id=conversation_id,
|
||||
workflow_type=result["workflow_type"],
|
||||
result=result["result"],
|
||||
)
|
||||
|
||||
|
||||
@router.post("/api/sql/generate")
|
||||
def generate_sql(payload: AgentInput, workflow_manager=Depends(get_workflow_manager)):
|
||||
def generate_sql(payload: ChatMessageRequestDTO, workflow_manager=Depends(get_workflow_manager)):
|
||||
"""仅生成 SQL，不调用 SR API"""
|
||||
query = _require_query_text(payload)
|
||||
msg_storage = get_message_storage()
|
||||
current_timestamp = DateTimeGenerator.now().epoch_millis
|
||||
try:
|
||||
conversation_id = _handle_conversation(payload, current_timestamp, msg_storage)
|
||||
except Exception as e:
|
||||
raise _to_http_error(e)
|
||||
trace_id = uuid.uuid4().hex
|
||||
slog = get_structured_logger()
|
||||
try:
|
||||
workflow_type = _resolve_workflow_type(payload.workflow_type)
|
||||
except Exception as e:
|
||||
slog.log("ERROR", "generate_sql.invalid_type", trace_id, error_code=ErrorCode.INVALID_WORKFLOW_TYPE.value)
|
||||
raise _to_http_error(e)
|
||||
workflow_type = WorkflowType.CONVERSATION
|
||||
|
||||
result = workflow_manager.execute_workflow(
|
||||
workflow_type=workflow_type,
|
||||
user_input=payload.query,
|
||||
session_id=payload.conversation_id,
|
||||
user_input=query,
|
||||
session_id=conversation_id,
|
||||
skip_sr_api=True,
|
||||
user=payload.user,
|
||||
inputs=payload.inputs,
|
||||
files=[item.model_dump() for item in payload.files],
|
||||
)
|
||||
|
||||
context = (result.get("result") or {}).get("context") or {}
|
||||
@@ -113,7 +419,7 @@ def generate_sql(payload: AgentInput, workflow_manager=Depends(get_workflow_mana
|
||||
slog.log("INFO", "generate_sql.success", trace_id, {"sql_len": len(sql_text)})
|
||||
|
||||
return {
|
||||
"session_id": result.get("session_id"),
|
||||
"session_id": conversation_id,
|
||||
"workflow_type": result.get("workflow_type"),
|
||||
"sql": sql_text,
|
||||
}
|
||||
@@ -121,122 +427,200 @@ def generate_sql(payload: AgentInput, workflow_manager=Depends(get_workflow_mana
|
||||
|
||||
@router.post("/api/workflows/stream")
|
||||
def run_workflow_stream(payload: ChatMessageRequestDTO, workflow_manager=Depends(get_workflow_manager)):
|
||||
query = _require_query_text(payload)
|
||||
trace_id = uuid.uuid4().hex
|
||||
slog = get_structured_logger()
|
||||
msg_storage = get_message_storage()
|
||||
current_timestamp = DateTimeGenerator.now().epoch_millis
|
||||
try:
|
||||
conversation_id = _handle_conversation(payload, current_timestamp, msg_storage)
|
||||
except Exception as e:
|
||||
raise _to_http_error(e)
|
||||
|
||||
if payload.response_mode != "streaming":
|
||||
raise _to_http_error(AppError(code=ErrorCode.INVALID_WORKFLOW_TYPE, message="/api/workflows/stream 仅支持 response_mode=streaming", status_code=400))
|
||||
raise _to_http_error(
|
||||
AppError(
|
||||
code=ErrorCode.INVALID_RESPONSE_MODE,
|
||||
message="/api/workflows/stream 仅支持 response_mode=streaming",
|
||||
status_code=400,
|
||||
)
|
||||
)
|
||||
|
||||
stream_cfg = Config.get_section("stream")
|
||||
progress_interval = float(stream_cfg.get("progress_interval", 0.3))
|
||||
task_id = uuid.uuid4().hex
|
||||
message_id = task_id
|
||||
chunk_size = 1024
|
||||
|
||||
def _build_message(conversation_id: str, answer: str) -> str:
|
||||
def _build_stream_chunk(conversation_id: str, answer: str, event: str = "message") -> str:
|
||||
dto = ChatMessageResponseDTO(
|
||||
id=uuid.uuid4().hex,
|
||||
event="message",
|
||||
event=event,
|
||||
task_id=task_id,
|
||||
message_id=uuid.uuid4().hex,
|
||||
message_id=message_id,
|
||||
conversation_id=conversation_id,
|
||||
answer=answer,
|
||||
created_at=int(time.time()),
|
||||
created_at=DateTimeGenerator.now().epoch_seconds,
|
||||
)
|
||||
return f"event: message\ndata: {json.dumps(dto.model_dump(), ensure_ascii=False)}\n\n"
|
||||
return f"data: {json.dumps(dto.model_dump(), ensure_ascii=False)}\n\n"
|
||||
|
||||
def _record_stream_message(stage: str, active_conversation_id: str, final_answer: str, *, sql_text: str | None = None, execution_result: Any = None, extra_metadata: dict[str, Any] | None = None) -> None:
|
||||
if not _storage_enabled(msg_storage):
|
||||
return
|
||||
|
||||
saved = _safe_save_message(
|
||||
msg_storage,
|
||||
conversation_id=active_conversation_id,
|
||||
message_id=message_id,
|
||||
query=query,
|
||||
answer=final_answer,
|
||||
workflow_type=WorkflowType.CONVERSATION.value,
|
||||
user=payload.user,
|
||||
sql_query=sql_text,
|
||||
execution_result=execution_result,
|
||||
metadata={
|
||||
"trace_id": trace_id,
|
||||
"stage": stage,
|
||||
"inputs": payload.inputs,
|
||||
"files": [item.model_dump() for item in payload.files],
|
||||
**(extra_metadata or {}),
|
||||
},
|
||||
created_at=current_timestamp,
|
||||
updated_at=current_timestamp,
|
||||
logs=stream_logs,
|
||||
)
|
||||
if not saved:
|
||||
slog.log("ERROR", "stream.message_save_failed", trace_id, payload={"conversation_id": active_conversation_id, "message_id": message_id, "stage": stage})
|
||||
else:
|
||||
slog.log("INFO", "stream.message_saved", trace_id, {"conversation_id": active_conversation_id, "message_id": message_id, "stage": stage})
|
||||
|
||||
async def event_stream():
|
||||
active_conversation_id = conversation_id
|
||||
answer_parts: list[str] = []
|
||||
try:
|
||||
stream_logs.append(json.dumps({"event": "start", "conversation_id": active_conversation_id}, ensure_ascii=False))
|
||||
slog.log("INFO", "stream.start", trace_id, {"workflow_type": WorkflowType.CONVERSATION.value})
|
||||
# 1) 先仅生成 SQL（不执行 SR API）
|
||||
|
||||
# 执行 workflow（skip_sr_api=False，SQL 执行在 workflow 内部完成）
|
||||
result = await asyncio.to_thread(
|
||||
workflow_manager.execute_workflow,
|
||||
WorkflowType.CONVERSATION,
|
||||
payload.query,
|
||||
payload.conversation_id,
|
||||
skip_sr_api=True,
|
||||
query,
|
||||
active_conversation_id,
|
||||
skip_sr_api=False, # 在 workflow 内部执行 SQL
|
||||
user=payload.user,
|
||||
inputs=payload.inputs,
|
||||
files=[item.model_dump() for item in payload.files],
|
||||
)
|
||||
conversation_id = str(result.get("session_id") or payload.conversation_id or task_id)
|
||||
active_conversation_id = str(result.get("session_id") or active_conversation_id or task_id)
|
||||
stream_logs.append(json.dumps({"event": "workflow_success", "session_id": active_conversation_id}, ensure_ascii=False))
|
||||
|
||||
context = (result.get("result") or {}).get("context") or {}
|
||||
|
||||
# 记录关键节点信息
|
||||
workflow_steps = {
|
||||
"event": "workflow_steps",
|
||||
"normalized_input": context.get("normalized_input"),
|
||||
"query_mode": context.get("query_mode"),
|
||||
"table_name": context.get("table_name"),
|
||||
"current_step": context.get("current_step"),
|
||||
"is_empty_result": context.get("is_empty_result"),
|
||||
}
|
||||
stream_logs.append(json.dumps(workflow_steps, ensure_ascii=False))
|
||||
|
||||
sql_text = str(context.get("final_sql") or "")
|
||||
stream_logs.append(json.dumps({"event": "sql_generated", "sql": sql_text}, ensure_ascii=False))
|
||||
|
||||
# 从 context 获取完整表名
|
||||
table_name = None
|
||||
sql_plan = context.get("sql_plan") or {}
|
||||
if sql_plan.get("data_source"):
|
||||
table_name = sql_plan["data_source"]
|
||||
elif context.get("table_name"):
|
||||
table_name = context["table_name"]
|
||||
elif isinstance(context.get("table_match"), dict):
|
||||
table_name = context["table_match"].get("table_name")
|
||||
stream_logs.append(json.dumps({"event": "table_name_extracted", "table_name": table_name}, ensure_ascii=False))
|
||||
|
||||
if not sql_text:
|
||||
reason = "SQL 生成失败，可能是表未匹配或对应 SQL 提示词不存在"
|
||||
slog.log("ERROR", "stream.sql_generation_failed", trace_id, error_code=ErrorCode.SQL_GENERATION_FAILED.value, payload={"conversation_id": conversation_id})
|
||||
yield _build_message(conversation_id, reason)
|
||||
yield "event: end\ndata: [DONE]\n\n"
|
||||
return
|
||||
# 查询表的 etl_time
|
||||
etl_version = None
|
||||
if table_name:
|
||||
try:
|
||||
etl_version = get_table_etl_time(table_name)
|
||||
stream_logs.append(json.dumps({"event": "etl_version", "table": table_name, "etl_version": etl_version}, ensure_ascii=False))
|
||||
except Exception as e:
|
||||
stream_logs.append(json.dumps({"event": "etl_version_failed", "table": table_name, "error": str(e)}, ensure_ascii=False))
|
||||
etl_version = None
|
||||
else:
|
||||
stream_logs.append(json.dumps({"event": "etl_version_skipped", "reason": "no_table"}, ensure_ascii=False))
|
||||
|
||||
# 2) 先流式返回 SQL
|
||||
yield _build_message(conversation_id, sql_text)
|
||||
# 从 context 获取结果（SQL 已在 workflow 内执行）
|
||||
sr_api_result = context.get("sr_api_result")
|
||||
result_rows = _extract_sql_rows(sr_api_result) if sr_api_result else []
|
||||
sample_rows = result_rows[:3] if result_rows else []
|
||||
row_count = len(result_rows)
|
||||
stream_logs.append(json.dumps({"event": "result_rows", "count": row_count, "sample": sample_rows}, ensure_ascii=False))
|
||||
|
||||
# 检查是否为空结果
|
||||
is_empty_result = context.get("is_empty_result", False)
|
||||
if is_empty_result and context.get("formatted_answer"):
|
||||
result_text = context["formatted_answer"]
|
||||
stream_logs.append(json.dumps({"event": "empty_result_formatted"}, ensure_ascii=False))
|
||||
elif sr_api_result:
|
||||
result_text = _build_rich_answer_html(query, result_rows, etl_version=etl_version)
|
||||
stream_logs.append(json.dumps({"event": "rich_answer_html", "etl_version": etl_version}, ensure_ascii=False))
|
||||
else:
|
||||
result_text = "查询执行完成，但未获取到结果数据。"
|
||||
stream_logs.append(json.dumps({"event": "no_result"}, ensure_ascii=False))
|
||||
|
||||
# 3) 异步执行 SQL，并及时流式返回执行结果
|
||||
tool = SrApiQueryTool()
|
||||
task = asyncio.create_task(
|
||||
asyncio.to_thread(tool.run, json.dumps({"sql": sql_text}, ensure_ascii=False))
|
||||
for index in range(0, len(result_text), chunk_size):
|
||||
chunk = result_text[index:index + chunk_size]
|
||||
answer_parts.append(chunk)
|
||||
yield _build_stream_chunk(active_conversation_id, chunk)
|
||||
|
||||
yield _build_stream_chunk(active_conversation_id, "", event="message_end")
|
||||
_record_stream_message(
|
||||
"success",
|
||||
active_conversation_id,
|
||||
"".join(answer_parts),
|
||||
sql_text=sql_text,
|
||||
execution_result={"status": "success", "row_count": row_count, "sample": sample_rows, "is_empty": is_empty_result},
|
||||
)
|
||||
except Exception as e:
|
||||
stream_logs.append(f"stream.failed error={e}")
|
||||
slog.log("ERROR", "stream.failed", trace_id, error_code=ErrorCode.INTERNAL_ERROR.value, payload={"error": str(e)})
|
||||
error_conversation_id = str(active_conversation_id or payload.conversation_id or task_id)
|
||||
error_text = str(e)
|
||||
answer_parts.append(error_text)
|
||||
yield _build_stream_chunk(error_conversation_id, error_text)
|
||||
yield _build_stream_chunk(error_conversation_id, "", event="message_end")
|
||||
_record_stream_message(
|
||||
"exception",
|
||||
error_conversation_id,
|
||||
"".join(answer_parts),
|
||||
extra_metadata={"error": str(e)},
|
||||
)
|
||||
|
||||
while not task.done():
|
||||
yield _build_message(conversation_id, "executing_sql")
|
||||
await asyncio.sleep(progress_interval)
|
||||
|
||||
sql_result = await task
|
||||
slog.log("INFO", "stream.sql_executed", trace_id, {"result_len": len(str(sql_result))})
|
||||
yield _build_message(conversation_id, str(sql_result))
|
||||
yield "event: end\ndata: [DONE]\n\n"
|
||||
except Exception as e:
|
||||
slog.log("ERROR", "stream.failed", trace_id, error_code=ErrorCode.INTERNAL_ERROR.value, payload={"error": str(e)})
|
||||
conversation_id = str(payload.conversation_id or task_id)
|
||||
yield _build_message(conversation_id, str(e))
|
||||
yield "event: end\ndata: [DONE]\n\n"
|
||||
|
||||
stream_logs: list[str] = []
|
||||
return StreamingResponse(event_stream(), media_type="text/event-stream")
|
||||
|
||||
|
||||
@router.get("/api/workflows/list")
|
||||
def list_workflows(workflow_manager=Depends(get_workflow_manager)):
|
||||
"""列出所有可用工作流"""
|
||||
workflows = workflow_manager.get_available_workflows()
|
||||
result = []
|
||||
for name in workflows:
|
||||
info = workflow_manager.get_workflow_info(name)
|
||||
if info:
|
||||
result.append(info)
|
||||
return {"workflows": result}
|
||||
|
||||
|
||||
@router.get("/api/workflows/{workflow_name}")
|
||||
def get_workflow_detail(workflow_name: str, workflow_manager=Depends(get_workflow_manager)):
|
||||
"""获取工作流详情"""
|
||||
info = workflow_manager.get_workflow_info(workflow_name)
|
||||
if not info:
|
||||
raise HTTPException(status_code=404, detail=f"工作流不存在: {workflow_name}")
|
||||
return info
|
||||
|
||||
|
||||
@router.get("/api/tools/list")
|
||||
def list_tools(tool_router=Depends(get_tool_router)):
|
||||
"""列出所有可用工具"""
|
||||
tools = tool_router.list_tools()
|
||||
result = []
|
||||
for name in tools:
|
||||
info = tool_router.get_tool_info(name)
|
||||
if info:
|
||||
result.append(info)
|
||||
return {"tools": result}
|
||||
|
||||
|
||||
@router.get("/api/tools/{tool_name}")
|
||||
def get_tool_detail(tool_name: str, tool_router=Depends(get_tool_router)):
|
||||
"""获取工具详情"""
|
||||
info = tool_router.get_tool_info(tool_name)
|
||||
if not info:
|
||||
raise HTTPException(status_code=404, detail=f"工具不存在: {tool_name}")
|
||||
return info
|
||||
|
||||
|
||||
@router.get("/api/tools/stats")
|
||||
def get_tools_stats(tool_router=Depends(get_tool_router)):
|
||||
"""获取工具执行统计"""
|
||||
return tool_router.get_all_stats()
|
||||
@router.post("/api/messages/feedback")
|
||||
def write_message_feedback(payload: MessageFeedbackRequestDTO):
|
||||
msg_storage = get_message_storage()
|
||||
updated = msg_storage.update_feedback_by_message_id(
|
||||
message_id=payload.message_id,
|
||||
feedback=payload.feedback,
|
||||
feedback_content=payload.feedback_content,
|
||||
)
|
||||
if not updated:
|
||||
raise _to_http_error(
|
||||
AppError(
|
||||
code=ErrorCode.INVALID_REQUEST,
|
||||
message="反馈写回失败，message_id 不存在或存储未启用",
|
||||
status_code=400,
|
||||
detail={"field": "message_id", "reason": "not_found_or_storage_disabled"},
|
||||
)
|
||||
)
|
||||
return {"ok": True, "message_id": payload.message_id}
|
||||
|
||||
|
||||
@router.post("/api/tools/execute", response_model=ToolOutput)
|
||||
@@ -302,133 +686,25 @@ def update_sql_gen():
|
||||
raise HTTPException(status_code=500, detail=str(e))
|
||||
|
||||
|
||||
@router.post("/api/super-agent/query", response_model=SuperAgentResponse)
|
||||
def super_agent_query(payload: SuperAgentRequest, workflow_manager=Depends(get_workflow_manager)):
|
||||
"""Super Agent 同步查询接口"""
|
||||
trace_id = uuid.uuid4().hex
|
||||
slog = get_structured_logger()
|
||||
slog.log("INFO", "super_agent.query.start", trace_id, {
|
||||
"query": payload.query[:100],
|
||||
"workflow_type": payload.workflow_type,
|
||||
"user_id": payload.user_id,
|
||||
})
|
||||
|
||||
conversation_id = payload.conversation_id or uuid.uuid4().hex
|
||||
|
||||
def get_table_etl_time(table_name: str) -> str:
|
||||
"""
|
||||
查询指定表的最大 etl_time，若失败或无数据则返回 Unknown。
|
||||
"""
|
||||
if not table_name:
|
||||
return "Unknown"
|
||||
try:
|
||||
workflow_type = _resolve_workflow_type(payload.workflow_type)
|
||||
except Exception as e:
|
||||
slog.log("ERROR", "super_agent.query.invalid_type", trace_id, error_code=ErrorCode.INVALID_WORKFLOW_TYPE.value)
|
||||
return SuperAgentResponse(
|
||||
conversation_id=conversation_id,
|
||||
workflow_type=payload.workflow_type,
|
||||
status="error",
|
||||
error=f"不支持的工作流类型: {payload.workflow_type}",
|
||||
)
|
||||
|
||||
try:
|
||||
result = workflow_manager.execute_workflow(
|
||||
workflow_type=workflow_type,
|
||||
user_input=payload.query,
|
||||
session_id=conversation_id,
|
||||
)
|
||||
|
||||
context = (result.get("result") or {}).get("context") or {}
|
||||
sql_text = context.get("final_sql")
|
||||
sr_api_result = context.get("sr_api_result")
|
||||
|
||||
slog.log("INFO", "super_agent.query.success", trace_id, {
|
||||
"conversation_id": conversation_id,
|
||||
"has_sql": bool(sql_text),
|
||||
"has_result": bool(sr_api_result),
|
||||
})
|
||||
|
||||
return SuperAgentResponse(
|
||||
conversation_id=conversation_id,
|
||||
workflow_type=workflow_type.value,
|
||||
status="success",
|
||||
sql=sql_text,
|
||||
result=str(sr_api_result) if sr_api_result else None,
|
||||
metadata={"trace_id": trace_id},
|
||||
)
|
||||
|
||||
except Exception as e:
|
||||
slog.log("ERROR", "super_agent.query.failed", trace_id, error_code=ErrorCode.INTERNAL_ERROR.value, payload={"error": str(e)})
|
||||
return SuperAgentResponse(
|
||||
conversation_id=conversation_id,
|
||||
workflow_type=payload.workflow_type,
|
||||
status="error",
|
||||
error=str(e),
|
||||
metadata={"trace_id": trace_id},
|
||||
)
|
||||
|
||||
|
||||
@router.post("/api/super-agent/stream")
|
||||
def super_agent_stream(payload: SuperAgentRequest, workflow_manager=Depends(get_workflow_manager)):
|
||||
"""Super Agent 流式查询接口"""
|
||||
trace_id = uuid.uuid4().hex
|
||||
slog = get_structured_logger()
|
||||
stream_cfg = Config.get_section("stream")
|
||||
progress_interval = float(stream_cfg.get("progress_interval", 0.3))
|
||||
|
||||
conversation_id = payload.conversation_id or uuid.uuid4().hex
|
||||
|
||||
def _build_sse_event(event: str, data: str) -> str:
|
||||
dto = SuperAgentStreamEvent(
|
||||
conversation_id=conversation_id,
|
||||
event=event,
|
||||
data=data,
|
||||
timestamp=int(time.time() * 1000),
|
||||
)
|
||||
return f"event: {event}\ndata: {json.dumps(dto.model_dump(), ensure_ascii=False)}\n\n"
|
||||
|
||||
async def event_stream():
|
||||
try:
|
||||
slog.log("INFO", "super_agent.stream.start", trace_id, {
|
||||
"query": payload.query[:100],
|
||||
"user_id": payload.user_id,
|
||||
})
|
||||
|
||||
workflow_type = _resolve_workflow_type(payload.workflow_type)
|
||||
|
||||
result = await asyncio.to_thread(
|
||||
workflow_manager.execute_workflow,
|
||||
workflow_type,
|
||||
payload.query,
|
||||
conversation_id,
|
||||
skip_sr_api=True,
|
||||
)
|
||||
|
||||
context = (result.get("result") or {}).get("context") or {}
|
||||
sql_text = context.get("final_sql")
|
||||
|
||||
if not sql_text:
|
||||
slog.log("ERROR", "super_agent.stream.sql_failed", trace_id, error_code=ErrorCode.SQL_GENERATION_FAILED.value)
|
||||
yield _build_sse_event("error", "SQL 生成失败")
|
||||
yield _build_sse_event("done", "")
|
||||
return
|
||||
|
||||
yield _build_sse_event("sql_generated", sql_text)
|
||||
|
||||
yield _build_sse_event("sql_executing", "")
|
||||
|
||||
tool = SrApiQueryTool()
|
||||
task = asyncio.create_task(
|
||||
asyncio.to_thread(tool.run, json.dumps({"sql": sql_text}, ensure_ascii=False))
|
||||
)
|
||||
|
||||
while not task.done():
|
||||
yield _build_sse_event("sql_executing", "")
|
||||
await asyncio.sleep(progress_interval)
|
||||
|
||||
sql_result = await task
|
||||
slog.log("INFO", "super_agent.stream.success", trace_id, {"result_len": len(str(sql_result))})
|
||||
yield _build_sse_event("result", str(sql_result))
|
||||
|
||||
except Exception as e:
|
||||
slog.log("ERROR", "super_agent.stream.failed", trace_id, error_code=ErrorCode.INTERNAL_ERROR.value, payload={"error": str(e)})
|
||||
yield _build_sse_event("error", str(e))
|
||||
|
||||
yield _build_sse_event("done", "")
|
||||
|
||||
return StreamingResponse(event_stream(), media_type="text/event-stream")
|
||||
tool = SrApiQueryTool()
|
||||
sql = f"SELECT MAX(etl_time) AS etl_time FROM {table_name}"
|
||||
result = tool.run(json.dumps({"sql": sql}, ensure_ascii=False))
|
||||
rows = _extract_sql_rows(result)
|
||||
if rows and rows[0].get("etl_time"):
|
||||
etl_value = rows[0]["etl_time"]
|
||||
# 使用 DateTimeGenerator 转换为格式化字符串
|
||||
try:
|
||||
bundle = DateTimeGenerator.bundle(etl_value, default_to_now=False)
|
||||
return bundle.datetime_str
|
||||
except Exception:
|
||||
return str(etl_value)
|
||||
except Exception:
|
||||
pass
|
||||
return "Unknown"
|
||||
|
||||
@@ -1,5 +0,0 @@
|
||||
"""兼容导出：请优先使用 config 包"""
|
||||
|
||||
from config.settings import Config
|
||||
|
||||
__all__ = ["Config"]
|
||||
@@ -0,0 +1,13 @@
|
||||
# Config 模块
|
||||
|
||||
## 作用
|
||||
|
||||
维护运行配置与提示词资源，是模型、RAG、缓存与工作流参数的配置中心。
|
||||
|
||||
## 内容
|
||||
|
||||
- `config.ini` / `config.ini.example`：环境配置
|
||||
- `prompts.yaml`：系统与用户提示词模板
|
||||
- `settings.py`：配置读取入口
|
||||
- `sql_gen_prompts/`：按表维度的 SQL 提示词 JSON
|
||||
- `table_retrieval_prompts/`：表检索提示词数据
|
||||
+20
-2
@@ -1,3 +1,21 @@
|
||||
from .settings import Config
|
||||
from . import settings as _settings
|
||||
|
||||
__all__ = ["Config"]
|
||||
Config = _settings.Config
|
||||
DEFAULT_MODEL_SECTION = _settings.DEFAULT_MODEL_SECTION
|
||||
MAX_RETRIES = _settings.MAX_RETRIES
|
||||
TIMEOUT = _settings.TIMEOUT
|
||||
CONVERSATION_MAX_HISTORY_MESSAGES = _settings.CONVERSATION_MAX_HISTORY_MESSAGES
|
||||
CONVERSATION_ENABLE_MULTI_TURN = _settings.CONVERSATION_ENABLE_MULTI_TURN
|
||||
CONVERSATION_ENABLE_COMPRESSION = _settings.CONVERSATION_ENABLE_COMPRESSION
|
||||
CONVERSATION_COMPRESSION_THRESHOLD = _settings.CONVERSATION_COMPRESSION_THRESHOLD
|
||||
|
||||
__all__ = [
|
||||
"Config",
|
||||
"DEFAULT_MODEL_SECTION",
|
||||
"MAX_RETRIES",
|
||||
"TIMEOUT",
|
||||
"CONVERSATION_MAX_HISTORY_MESSAGES",
|
||||
"CONVERSATION_ENABLE_MULTI_TURN",
|
||||
"CONVERSATION_ENABLE_COMPRESSION",
|
||||
"CONVERSATION_COMPRESSION_THRESHOLD",
|
||||
]
|
||||
|
||||
+44
-5
@@ -24,6 +24,7 @@ URL = http://led-gateway.lenovo.com:30089/intranet/qwen3-next-80b-a3b-instruct/v
|
||||
url = http://ipc.lenovo.com/gateway/bgs-ai/Report/fetchData
|
||||
llzAppkey = e0578e6a-f045-4f3e-93c0-5957c8b1915e
|
||||
llzSercret = BFhItTCY5FqgtHAdn0eaxAGix/25oR8YfxYKfSPgrJb8zxYG06kBeoip0DEGjekfh43223atdBDXBwUmw18NXp/2piZamnUwlFWYFAGfpBCwy3K+921KI5ZaWRWcMCCcCKOYF/2feMg72owUhno2JXqSUcb8HBhang==
|
||||
default_rows = 1000
|
||||
|
||||
|
||||
[ragflow]
|
||||
@@ -34,21 +35,59 @@ retrieval_top_k = 3
|
||||
cache_ttl = 600
|
||||
table_retrieval_dataset_id = 9945baf512ea11f18ccb6a681b3130b2
|
||||
sql_gen_dataset_id = ee68f53a12ec11f18e436a681b3130b2
|
||||
default_table_name = apbo_eta_ful
|
||||
|
||||
[redis]
|
||||
enabled = true
|
||||
host = ipc-redis.lenovo.com
|
||||
port = 30401
|
||||
password = bgs123456
|
||||
database = 2
|
||||
sql_prompt_ttl = 600
|
||||
# 是否使用 Redis 作为 SQL 提示词主存储（启用后优先从 Redis 读取）
|
||||
sql_prompt_redis_primary = true
|
||||
|
||||
[stream]
|
||||
progress_interval = 0.3
|
||||
|
||||
[conversation]
|
||||
# 是否启用按会话自动续接上下文的多轮对话
|
||||
enable_multi_turn = false
|
||||
# 对话记忆最大消息数（默认 10 条，约 5 轮对话）
|
||||
# 每条对话包含用户消息和 AI 回复，10 条消息约等于 5 轮完整对话
|
||||
max_history_messages = 10
|
||||
# 是否启用记忆压缩（可选，未来扩展）
|
||||
enable_memory_compression = false
|
||||
# 记忆压缩阈值（超过此数量时触发压缩，未来扩展）
|
||||
compression_threshold = 8
|
||||
|
||||
[logging_mysql]
|
||||
enabled = true
|
||||
entity_debug_enabled = false
|
||||
host = 10.122.132.204
|
||||
port = 3306
|
||||
user = root
|
||||
password = bgs20250901
|
||||
database = ipc_apbo
|
||||
table = structured_logs
|
||||
messages_table = ipc_apbo.messages
|
||||
conversation_table = ipc_apbo.conversations
|
||||
connect_timeout = 5
|
||||
|
||||
|
||||
[app]
|
||||
service_name = local-model-streaming-api
|
||||
service_name = apbo-boat-agent
|
||||
host = 0.0.0.0
|
||||
port = 8000
|
||||
port = 26004
|
||||
version = 1.0.0
|
||||
|
||||
[nacos]
|
||||
enabled = false
|
||||
enabled = true
|
||||
server = 10.122.132.204:8848
|
||||
namespace = prod
|
||||
group_name = BGS
|
||||
namespace = apbo_dev
|
||||
group_name = apbo
|
||||
username = nacos
|
||||
password = bgs20250901
|
||||
# 可选：仅用于 Nacos 注册的端口（不影响应用监听端口 app.port）
|
||||
register_port = 26004
|
||||
|
||||
|
||||
@@ -37,11 +37,52 @@ retrieval = /api/v1/retrieval
|
||||
retrieval_top_k = 3
|
||||
table_retrieval_dataset_id =
|
||||
sql_gen_dataset_id =
|
||||
# 当表检索未命中时，使用该默认表继续生成 SQL
|
||||
default_table_name = apbo_eta_ful
|
||||
|
||||
[redis]
|
||||
# 是否启用 Redis 缓存（用于 sql_gen_prompts）
|
||||
enabled = false
|
||||
url = redis://localhost:6379/0
|
||||
db = 0
|
||||
# SQL 提示词缓存过期秒数
|
||||
sql_prompt_ttl = 600
|
||||
# 是否使用 Redis 作为 SQL 提示词主存储（启用后优先从 Redis 读取，支持热更新）
|
||||
sql_prompt_redis_primary = false
|
||||
|
||||
[stream]
|
||||
# /api/workflows/stream 进度事件间隔（秒）
|
||||
progress_interval = 0.3
|
||||
|
||||
[conversation]
|
||||
# 是否启用按会话自动续接上下文的多轮对话
|
||||
enable_multi_turn = false
|
||||
# 对话记忆最大消息数（默认 10 条，约 5 轮对话）
|
||||
# 每条对话包含用户消息和 AI 回复，10 条消息约等于 5 轮完整对话
|
||||
max_history_messages = 10
|
||||
# 是否启用记忆压缩（可选，未来扩展）
|
||||
enable_memory_compression = false
|
||||
# 记忆压缩阈值（超过此数量时触发压缩，未来扩展）
|
||||
compression_threshold = 8
|
||||
|
||||
[logging_mysql]
|
||||
# 是否启用结构化日志写入 MySQL
|
||||
enabled = false
|
||||
# 是否输出 conversations/messages 实体读写阶段调试日志到控制台
|
||||
entity_debug_enabled = false
|
||||
host = 127.0.0.1
|
||||
port = 3306
|
||||
user = root
|
||||
password =
|
||||
database = more_dots
|
||||
# 结构化日志表
|
||||
table = structured_logs
|
||||
# 消息落库表（Messages 实体）
|
||||
messages_table = ipc_apbo.messages
|
||||
# 会话表名（用于 conversation_id 创建/校验/更新时间）
|
||||
conversation_table = ipc_apbo.conversations
|
||||
connect_timeout = 5
|
||||
|
||||
[nacos]
|
||||
# 是否启用 Nacos 注册
|
||||
enabled = false
|
||||
@@ -57,6 +98,9 @@ cluster_name = DEFAULT
|
||||
username =
|
||||
# 密码（可选）
|
||||
password =
|
||||
# 可选：仅用于 Nacos 注册的端口（不影响应用监听端口 app.port）
|
||||
# 未配置时默认使用 app.port
|
||||
register_port = 26004
|
||||
# 心跳间隔（秒）
|
||||
heartbeat_interval = 5
|
||||
# 权重
|
||||
|
||||
@@ -19,6 +19,18 @@ user:
|
||||
You are a translation and normalization assistant.
|
||||
Convert the user's input to a clear, grammatically correct English sentence suitable for SQL intent.
|
||||
If the input is already English, polish it.
|
||||
|
||||
Apply the following business glossary mappings when the terms appear as standalone business keywords:
|
||||
- BO -> backlog order
|
||||
- SO -> service order id
|
||||
- WO -> service order id
|
||||
- ETA信息 -> eta information
|
||||
- 明细 -> detail
|
||||
- 汇总 -> aggregate summary
|
||||
- 排名前N -> top N ranking
|
||||
|
||||
Keep country codes, region codes, model names, order numbers, and field aliases unchanged when possible.
|
||||
Expand business abbreviations according to the glossary above.
|
||||
Return only the final English sentence without extra explanations.
|
||||
|
||||
business:
|
||||
|
||||
+87
-22
@@ -1,34 +1,58 @@
|
||||
import os
|
||||
import configparser
|
||||
from typing import Optional
|
||||
from pathlib import Path
|
||||
|
||||
|
||||
class Config:
|
||||
"""从 config.ini 读取的应用配置"""
|
||||
|
||||
_config = configparser.ConfigParser()
|
||||
_root_dir = os.path.dirname(os.path.dirname(__file__))
|
||||
_config_path = os.path.join(_root_dir, 'config', 'config.ini')
|
||||
|
||||
# 在类初始化时加载配置
|
||||
if not os.path.exists(_config_path):
|
||||
raise FileNotFoundError(
|
||||
f"Configuration file not found at: {_config_path}. "
|
||||
"Please copy 'config/config.ini.example' to 'config/config.ini' and fill in your details."
|
||||
)
|
||||
|
||||
try:
|
||||
with open(_config_path, "r", encoding="utf-8") as f:
|
||||
_config.read_file(f)
|
||||
except UnicodeDecodeError:
|
||||
with open(_config_path, "r", encoding="gbk") as f:
|
||||
_config.read_file(f)
|
||||
|
||||
# 通用设置
|
||||
DEFAULT_MODEL_SECTION: str = _config.get('General', 'DEFAULT_MODEL_SECTION', fallback='gpt-4o')
|
||||
MAX_RETRIES: int = _config.getint('General', 'MAX_RETRIES', fallback=3)
|
||||
TIMEOUT: int = _config.getint('General', 'TIMEOUT', fallback=30)
|
||||
|
||||
_config_loaded = False
|
||||
DEFAULT_MODEL_SECTION = "gpt-4o"
|
||||
MAX_RETRIES = 3
|
||||
TIMEOUT = 30
|
||||
CONVERSATION_MAX_HISTORY_MESSAGES = 10
|
||||
CONVERSATION_ENABLE_MULTI_TURN = False
|
||||
CONVERSATION_ENABLE_COMPRESSION = False
|
||||
CONVERSATION_COMPRESSION_THRESHOLD = 8
|
||||
|
||||
@classmethod
|
||||
def _get_config_path(cls) -> Path:
|
||||
"""获取配置文件路径（支持环境变量覆盖）"""
|
||||
env_path = os.getenv("CONFIG_PATH")
|
||||
if env_path:
|
||||
return Path(env_path)
|
||||
|
||||
project_root = Path(__file__).parent.parent
|
||||
return project_root / 'config' / 'config.ini'
|
||||
|
||||
@classmethod
|
||||
def _load_config(cls):
|
||||
"""懒加载配置"""
|
||||
if cls._config_loaded:
|
||||
return
|
||||
|
||||
config_path = cls._get_config_path()
|
||||
|
||||
if not config_path.exists():
|
||||
raise FileNotFoundError(
|
||||
f"Configuration file not found at: {config_path}. "
|
||||
"Please copy 'config/config.ini.example' to 'config/config.ini' and fill in your details."
|
||||
)
|
||||
|
||||
with open(config_path, "r", encoding="utf-8") as f:
|
||||
cls._config.read_file(f)
|
||||
|
||||
cls._config_loaded = True
|
||||
|
||||
@classmethod
|
||||
def reload(cls):
|
||||
"""重新加载配置（支持热重载）"""
|
||||
cls._config_loaded = False
|
||||
cls._load_config()
|
||||
_refresh_runtime_constants()
|
||||
|
||||
@classmethod
|
||||
def get_model_config(cls, section: Optional[str] = None) -> dict:
|
||||
"""
|
||||
@@ -71,6 +95,47 @@ class Config:
|
||||
raise ValueError(f"Configuration validation failed: {e}")
|
||||
|
||||
|
||||
DEFAULT_MODEL_SECTION = Config.DEFAULT_MODEL_SECTION
|
||||
MAX_RETRIES = Config.MAX_RETRIES
|
||||
TIMEOUT = Config.TIMEOUT
|
||||
CONVERSATION_MAX_HISTORY_MESSAGES = Config.CONVERSATION_MAX_HISTORY_MESSAGES
|
||||
CONVERSATION_ENABLE_MULTI_TURN = Config.CONVERSATION_ENABLE_MULTI_TURN
|
||||
CONVERSATION_ENABLE_COMPRESSION = Config.CONVERSATION_ENABLE_COMPRESSION
|
||||
CONVERSATION_COMPRESSION_THRESHOLD = Config.CONVERSATION_COMPRESSION_THRESHOLD
|
||||
|
||||
|
||||
def _refresh_runtime_constants() -> None:
|
||||
"""同步模块级常量与 Config 类属性，兼容两种访问方式。"""
|
||||
global DEFAULT_MODEL_SECTION
|
||||
global MAX_RETRIES
|
||||
global TIMEOUT
|
||||
global CONVERSATION_MAX_HISTORY_MESSAGES
|
||||
global CONVERSATION_ENABLE_MULTI_TURN
|
||||
global CONVERSATION_ENABLE_COMPRESSION
|
||||
global CONVERSATION_COMPRESSION_THRESHOLD
|
||||
|
||||
DEFAULT_MODEL_SECTION = Config._config.get('General', 'DEFAULT_MODEL_SECTION', fallback='gpt-4o')
|
||||
MAX_RETRIES = Config._config.getint('General', 'MAX_RETRIES', fallback=3)
|
||||
TIMEOUT = Config._config.getint('General', 'TIMEOUT', fallback=30)
|
||||
CONVERSATION_MAX_HISTORY_MESSAGES = Config._config.getint('conversation', 'max_history_messages', fallback=10)
|
||||
CONVERSATION_ENABLE_MULTI_TURN = Config._config.getboolean('conversation', 'enable_multi_turn', fallback=False)
|
||||
CONVERSATION_ENABLE_COMPRESSION = Config._config.getboolean('conversation', 'enable_memory_compression', fallback=False)
|
||||
CONVERSATION_COMPRESSION_THRESHOLD = Config._config.getint('conversation', 'compression_threshold', fallback=8)
|
||||
|
||||
Config.DEFAULT_MODEL_SECTION = DEFAULT_MODEL_SECTION
|
||||
Config.MAX_RETRIES = MAX_RETRIES
|
||||
Config.TIMEOUT = TIMEOUT
|
||||
Config.CONVERSATION_MAX_HISTORY_MESSAGES = CONVERSATION_MAX_HISTORY_MESSAGES
|
||||
Config.CONVERSATION_ENABLE_MULTI_TURN = CONVERSATION_ENABLE_MULTI_TURN
|
||||
Config.CONVERSATION_ENABLE_COMPRESSION = CONVERSATION_ENABLE_COMPRESSION
|
||||
Config.CONVERSATION_COMPRESSION_THRESHOLD = CONVERSATION_COMPRESSION_THRESHOLD
|
||||
|
||||
|
||||
# 在类定义完成后加载配置
|
||||
Config._load_config()
|
||||
_refresh_runtime_constants()
|
||||
|
||||
|
||||
# 如有需要可在导入时做初始校验，
|
||||
# 但已移到 main.py 以便更可控地执行。
|
||||
# 如需在导入时校验，可在此调用 Config.validate_config()
|
||||
|
||||
@@ -1,4 +0,0 @@
|
||||
本目录存放业务 SQL 提示词（JSON 格式）。
|
||||
|
||||
约定：每个 JSON 文件对应一个数据库表模型。
|
||||
示例文件：order.json、customer.json 等。
|
||||
@@ -3,59 +3,105 @@
|
||||
"domain": "订单物料最新状态与历史变更查询",
|
||||
"description": "此模型用于查询订单物料的最新状态和ETA相关信息，支持查询历史变更记录。该表包含最新状态数据（data_flag='Newest'）和历史变更数据（data_flag='Changelog'）的联合结果。所有日期字段在查询时自动转换为字符类型。通过data_flag区分最新状态和历史变更，实现订单全生命周期追踪。",
|
||||
"data_source": "dwd_ai.apbo_eta_ful",
|
||||
"system_flag_limit": "任何条件下，都不允许在SELECT子句中查询is_passdue, is_dummy, data_flag字段，仅用于WHERE过滤，该规则优先级最高！"
|
||||
"system_flag_limit": "任何条件下，都不允许在SELECT子句中查询data_flag字段，仅用于WHERE过滤，且update_date和data_flag两个字段在where条件中互斥,使用了update_date则不使用data_flag，该规则优先级最高！"
|
||||
},
|
||||
"data_model_specification": {
|
||||
"fields_list": [
|
||||
"service_order_id", "soid", "part_number", "topmost_pn", "commodity_code", "ship_to_country",
|
||||
"region", "dc_plant", "mtm", "machine_sn", "machine_type", "whether_premier", "stm_planner",
|
||||
"category", "lenovo_ref_no", "case_number", "service_order_creation_date", "eta", "so_eta",
|
||||
"status", "status_date", "update_date", "parts_sales", "warranty", "aging_day", "action",
|
||||
"is_passdue", "is_dummy", "data_flag", "model", "aging_range", "recovery_day", "recovery_range",
|
||||
"order_type", "key_lenovo_ref_no", "service_type", "customer", "life_cycle", "hawb", "bol", "dn", "po", "prid"
|
||||
"service_order_id", "soid", "part_number", "topmost_pn", "commodity_code", "ship_to_country",
|
||||
"region", "dc_plant", "mtm", "machine_sn", "machine_type", "whether_premier", "stm_planner",
|
||||
"category", "lenovo_ref_no", "case_number", "service_order_creation_date", "eta", "so_eta",
|
||||
"status", "status_date", "update_date", "parts_sales", "warranty", "aging_day", "action",
|
||||
"data_flag", "model", "aging_range", "recovery_day", "recovery_range",
|
||||
"order_type", "key_lenovo_ref_no", "service_type", "customer", "life_cycle", "owner", "bu", "multiple_flag", "country_dc_premier_stock", "potential_ww_stock", "potential_opo_stock", "potential_other_dc_stock", "potential_reverse_stock", "hawb", "bol", "dn", "po", "prid"
|
||||
],
|
||||
"mandatory_display_fields": {
|
||||
"rule1": "默认展示字段（按以下顺序）：service_order_id, soid, cast(service_order_creation_date as varchar(4096)) as service_order_creation_date, ship_to_country, part_number, topmost_pn, commodity_code, category, cast(eta as varchar(4096)) as eta, cast(so_eta as varchar(4096)) as so_eta, key_lenovo_ref_no, order_type, stm_planner, region, dc_plant, mtm, machine_sn, whether_premier, service_type, warranty, parts_sales, customer, life_cycle, model, aging_range, lenovo_ref_no, action, cast(update_date as varchar(4096)) as update_date",
|
||||
"rule2": "用户明确提到的字段优先原则：如果用户问题中明确提到了某些字段，这些字段应在SELECT子句中排在最前面，按用户问题中出现的顺序排列",
|
||||
"rule3": "字段去重：用户提到的字段和默认字段有重叠时，每个字段只出现一次",
|
||||
"rule4": "日期字段必须转换为字符类型：cast(column as varchar(4096)) as column",
|
||||
"rule5": "where子句中出现的字段，必须加入select中查询展示",
|
||||
"rule6": "禁止使用limit",
|
||||
"rule7": "请确认生成的sql中,用户使用的是mt(machine_type)还是mtm, 注意!! MTM SN = machine_sn, MT SN = machine_sn, mt = machine_type",
|
||||
"rule8": "当用户要求:展示所有信息，所有字段，全字段等需求时候，额外加入展示的字段:machine_type,case_number,status_date,aging_day,is_passdue,is_dummy,data_flag,recovery_day,recovery_range,hawb,bol,dn,po,prid",
|
||||
"rule9": "where条件禁止使用status字段过滤",
|
||||
"rule10": "用户输入了汇总，统计，分组等关键词，但未明确统计方式时候，默认使用count(*)进行汇总，注意group by必须和聚合函数成对出现，聚合查询后默认按照聚合的值从小到大排序",
|
||||
"rule11": "如果用户输入的关键字有:VN,AU,IN,HK,PH,KR,ID,TW,MO,FJ,LK,MY,SG,NZ,TH,JP,BD，则视为国家字段的数值过滤条件,增加ship_to_country = '国家代码'",
|
||||
"rule12": "MM/DD类似格式日期转换为 like '%-MM-DD%' ，DD等格式转换为 like '%-DD%'",
|
||||
"rule13": "用户指定日期时，去掉data_flag = 'Newest'的过滤条件，如：查询2026年1月26的eta信息，则where子句中不包含data_flag = 'Newest'，而是update_date = '2025-12-31'",
|
||||
"rule14": "聚合查询中，如未使用group by进行分组，select中默认增加使用update_date字段"
|
||||
"default_fields": "service_order_id, soid, cast(service_order_creation_date as varchar(4096)) as service_order_creation_date, ship_to_country, part_number, topmost_pn, commodity_code, category, cast(eta as varchar(4096)) as eta, cast(so_eta as varchar(4096)) as so_eta, key_lenovo_ref_no, order_type, stm_planner, region, dc_plant, mtm, machine_sn, whether_premier, service_type, warranty, parts_sales, customer, life_cycle, owner, model, aging_range, lenovo_ref_no, action, cast(update_date as varchar(4096)) as update_date",
|
||||
"date_cast_rule": "日期字段必须转换为字符类型：cast(column as varchar(4096)) as column"
|
||||
},
|
||||
"optional_fields": {
|
||||
"key_identifier_fields": ["service_order_id", "soid", "part_number","topmost_pn", "commodity_code"],
|
||||
"milestone_date_fields": ["eta", "so_eta", "status_date", "update_date", "service_order_creation_date"],
|
||||
"location_fields": ["ship_to_country", "region", "dc_plant"],
|
||||
"machine_fields": ["mtm", "machine_sn", "machine_type", "model"],
|
||||
"service_fields": ["whether_premier", "stm_planner", "category", "lenovo_ref_no", "case_number", "key_lenovo_ref_no", "service_type"],
|
||||
"service_fields": ["whether_premier", "stm_planner", "category", "lenovo_ref_no", "case_number", "key_lenovo_ref_no", "service_type", "owner"],
|
||||
"status_fields": ["status", "status_date"],
|
||||
"additional_fields": ["parts_sales", "warranty", "aging_day", "action", "aging_range", "recovery_day", "recovery_range", "order_type", "customer", "life_cycle", "hawb", "bol", "dn", "po", "prid"],
|
||||
"system_filter_fields": ["is_passdue", "is_dummy", "data_flag"]
|
||||
"additional_fields": ["parts_sales", "warranty", "aging_day", "action", "aging_range", "recovery_day", "recovery_range", "order_type", "customer", "life_cycle", "owner", "bu", "multiple_flag", "country_dc_premier_stock", "potential_ww_stock", "potential_opo_stock", "potential_other_dc_stock", "potential_reverse_stock", "hawb", "bol", "dn", "po", "prid"],
|
||||
"system_filter_fields": ["data_flag"]
|
||||
}
|
||||
},
|
||||
"business_logic_rules": {
|
||||
"soid_or_service_order_id": "禁止使用WHERE soid = 'xxx'或WHERE service_order_id = 'xxx'单独过滤，必须使用(service_order_id = 'xxx' or soid = 'xxx')进行过滤",
|
||||
"sorting": "默认使用如下字段排序: soid, eta desc",
|
||||
"query_recognition_rules": {
|
||||
"detail_mode_triggers": ["明细", "明细查询", "详细", "具体", "记录"],
|
||||
"aggregate_mode_triggers": ["聚合", "统计", "汇总", "count", "计数", "数量", "多少", "几个", "分组", "summary", "group by","summarize by","summarize","aggregate by","aggregate","sum", "求和", "总计", "合计"],
|
||||
"aggregate_mode_enforcement": "当用户问题命中任意aggregate_mode_triggers关键字时，必须强制使用聚合模式：SELECT子句必须包含count(soid) as qty，分组字段必须加入GROUP BY。如用户指定了具体维度，按该维度分组；如未指定，默认按part_number分组"
|
||||
},
|
||||
"field_selection_logic": {
|
||||
"priority_order": [
|
||||
{
|
||||
"level": 0,
|
||||
"name": "明细模式",
|
||||
"rule": "默认模式；未命中聚合关键词时",
|
||||
"action": "使用明细字段与默认展示字段"
|
||||
},
|
||||
{
|
||||
"level": 1,
|
||||
"name": "聚合模式",
|
||||
"rule": "命中聚合关键词（如：聚合/统计/count/汇总/分组/sum/求和/总计/合计）时，必须使用聚合模式",
|
||||
"action": "使用聚合字段（count(soid) as qty）与分组维度"
|
||||
}
|
||||
]
|
||||
},
|
||||
"aggregate_rules": {
|
||||
"metric_definitions": {
|
||||
"qty": "count(soid)",
|
||||
"premier_qty": "sum(if(whether_premier='Premier',1,0))"
|
||||
},
|
||||
"count_distinct_rule": "当用户指定对某列进行count统计时（如：统计SO数量、统计PN数量、统计订单数等），必须使用 count(distinct 列名) 而非 count(列名)，以避免重复计数。例如：统计SO数量 → count(distinct service_order_id)，统计PN数量 → count(distinct part_number)",
|
||||
"group_by_rule": "所有非聚合字段必须出现在 GROUP BY",
|
||||
"default_sorting": "qty DESC",
|
||||
"fallback_group_by": "聚合查询中，如未使用group by进行分组，select中默认增加使用update_date字段"
|
||||
},
|
||||
"default_behavior": {
|
||||
"detail_sorting": "soid, eta desc",
|
||||
"aggregate_sorting": "qty DESC",
|
||||
"limit": "如用户未要求，默认不加limit"
|
||||
},
|
||||
"alias_usage": "WHERE子句中支持使用字段别名进行查询，SELECT子句中使用原始字段名或别名均可",
|
||||
"select_alias_rename_rule": "生成SQL时，若用户在问题中使用了字段别名/字段名表达（如 country、tp、topmost、owner_name 等），SELECT子句需按用户表述进行重命名：SELECT 原始字段 AS 用户字段名，并保持用户字段出现顺序",
|
||||
"date_conversion": "所有日期字段必须使用cast(column as varchar(4096)) as column转为字符类型",
|
||||
"default_filters": ["is_dummy = '0'", "data_flag = 'Newest'"],
|
||||
"default_filters": ["data_flag = 'Newest'"],
|
||||
"data_flag_keyword_rule": "当用户问题包含'最新'、'Newest'、'latest'、'recent'等关键词时，使用 data_flag = 'Newest' 进行过滤",
|
||||
"eta_info_keyword_rule": "当用户问题包含'eta信息'时，仅展示eta信息指定字段",
|
||||
"eta_info_display_fields": "service_order_id as \"Service Order ID\", soid as \"SOID\", cast(service_order_creation_date as varchar(4096)) as \"Service Order Creation Date\", ship_to_country as \"Ship To Country\", part_number as \"Part Number\", topmost_pn as \"Topmost_PN\", commodity_code as \"Commodity_Code\", category as \"Category\", cast(eta as varchar(4096)) as \"ETA\", cast(so_eta as varchar(4096)) as \"SO ETA\", key_lenovo_ref_no as \"key_Lenovo Ref No\", order_type as \"order_type\", stm_planner as \"STM Planner\", region as \"Region\", dc_plant as \"DC Plant\", mtm as \"MTM\", machine_sn as \"Machine SN\", whether_premier as \"Whether_Premier\", service_type as \"Service_type\", warranty as \"Warranty\", parts_sales as \"Parts_sales\", customer as \"Customer\", life_cycle as \"TM_lifecycle\", model as \"Model\", aging_range as \"Aging_range\", lenovo_ref_no as \"Lenovo Ref No\", action as \"Action\", cast(update_date as varchar(4096)) as \"Update_date\"",
|
||||
"potential_stock_keyword_rule": "当用户问题包含'potential_stock'或'潜在库存'或'潜在stock'或'潜在库存信息'关键字时，必须同时查询以下所有库存字段：potential_ww_stock, potential_opo_stock, potential_other_dc_stock, potential_reverse_stock",
|
||||
"premier_qty_keyword_rule": "当用户问题包含'premier qty'、'premier_qty'、'premier数量'、'premier计数'、'premier统计'等关键词时，必须在SELECT中使用 sum(if(whether_premier='Premier',1,0)) as premier_qty 进行统计",
|
||||
"sub_rule_keyword_rule": "当用户问题包含'sub rule'、'Sub Rule'、'SUB RULE'、'sub_rule'、'不接受sub'、'Not accept sub'等关键词时，必须在WHERE子句中添加 action = 'Not accept sub' 进行精确过滤。该条件与data_flag = 'Newest'一起使用，生成格式为：WHERE ... AND action = 'Not accept sub' AND data_flag = 'Newest'",
|
||||
"passdue_keyword_rule": "当用户问题包含'passdue'、'past due'、'Passdue'、'PASSDUE'、'past_due'、'逾期'、'超期'、'过期'、'延误'等关键词时，必须在WHERE子句中添加 cast(update_date as date) - cast(eta as date) > 0 进行过滤，表示订单已超过预计到达日期。该条件使用日期类型减法比较，确保日期格式正确。生成格式为：WHERE ... AND cast(update_date as date) - cast(eta as date) > 0 AND data_flag = 'Newest'",
|
||||
"null_handling": "日期字段转换时保留NULL值",
|
||||
"model_query_rule": "查询model字段时必须使用like匹配，如: model like '%X13%'",
|
||||
"field_extraction_rule": "使用正则表达式和关键词匹配提取用户明确提到的字段，建立字段别名映射表",
|
||||
"field_order_rule": "用户提到的字段按问题中出现顺序排列在最前面，然后补充默认展示字段中未提及的字段",
|
||||
"topmost_pn and part_number_distinction": "确保区分topmost_pn(tp,tm,topmost)和part_number(pn)字段，避免混淆",
|
||||
"todays_date_handling": "当用户查询包含“今天”或“当前日期”的信息时，替换为系统当前日期进行过滤"
|
||||
"where_field_must_select": "where子句中出现的字段，必须加入select中查询展示",
|
||||
"no_status_filter": "where条件禁止使用status字段过滤",
|
||||
"country_code_mapping": "如果用户输入的关键字有:VN,AU,IN,HK,PH,KR,ID,TW,MO,FJ,LK,MY,SG,NZ,TH,JP,BD，则视为国家字段的数值过滤条件,增加ship_to_country = '国家代码'",
|
||||
"date_like_rule": "MM/DD类似格式日期转换为 like '%-MM-DD%' ，DD等格式转换为 like '%-DD%'",
|
||||
"topmost_pn_and_part_number_distinction": "确保区分topmost_pn(tp,tm,topmost,TOPMOST,TM)和part_number(pn)字段，避免混淆",
|
||||
"alias_priority_rules": "别名匹配需大小写不敏感；tm/TM/topmost/TOPMOST/topmost pn均映射为topmost_pn；mtm只映射mtm，不得与tm混淆",
|
||||
"order_type_warranty_disambiguation": "order_type与warranty可能共享值集合（如MDOA/OPT/CLW/DOA/FOC/OOW/OBL/ADW）。生成SQL时必须根据用户问题中的字段名或语义确认过滤目标字段；若用户未明确字段名且值仅命中该集合，不得擅自选择字段，需优先使用上下文关键词（订单类型/保修/质保）进行判断",
|
||||
"todays_date_handling": "当用户查询包含'今天'或'当前日期'或'today'的信息时，使用update_date = substr(now(),1,10)进行过滤",
|
||||
"top_n_rules": {
|
||||
"recognition_triggers": ["top", "Top", "TOP", "前", "最高", "最大", "最小", "排名"],
|
||||
"require_limit": "识别为TopN查询时，必须使用LIMIT N",
|
||||
"require_order_by": "识别为TopN查询时，必须包含ORDER BY排序字段",
|
||||
"default_limit": "用户未明确N时，默认使用LIMIT 10",
|
||||
"default_order_by": "用户未指定排序字段时，默认使用count(soid)作为排序键",
|
||||
"dimension_topn_rule": "当用户表达为'by {维度} top N'或'按{维度} top N'时，只能选择该维度字段 + qty(count(soid))，禁止选择其他明细字段；必须对该维度GROUP BY，并使用count(soid) as qty排序：ORDER BY qty DESC",
|
||||
"dimension_topn_default": "TopN查询默认使用用户指定的维度 + count(soid) as qty 作为排序结果",
|
||||
"dimension_topn_where_rule": "维度过滤条件仅用于WHERE（如 model 使用lower(model) like '%x%'），但SELECT仍只保留维度字段 + qty"
|
||||
}
|
||||
},
|
||||
"field_mapping_reference": {
|
||||
"critical_note": "此表包含最新状态数据和历史变更数据的联合，通过data_flag区分。最新数据（Newest）每条订单只有一条记录，历史数据（Changelog）每条订单有多条记录。所有日期字段在查询时自动转换为字符类型。请注意检查用户是否使用了字段的alias，不要忽略！！！系统字段（is_passdue, data_flag）仅用于WHERE过滤，不显示在SELECT结果中。用户提到的字段应优先显示在SELECT子句最前面。",
|
||||
"critical_note": "此表包含最新状态数据和历史变更数据的联合，通过data_flag区分。最新数据（Newest）每条订单只有一条记录，历史数据（Changelog）每条订单有多条记录。所有日期字段在查询时自动转换为字符类型。请注意检查用户是否使用了字段的alias，不要忽略！！！系统字段（data_flag）仅用于WHERE过滤，不显示在SELECT结果中。用户提到的字段应优先显示在SELECT子句最前面。",
|
||||
"critical_note1": {"type":"字段类型", "desc":"字段描述", "format": "数据格式", "query_format": "查询时数据格式" ,"example":"字段示例值", "values":"枚举值", "alias":"字段别名"},
|
||||
"key_identifiers": {
|
||||
"service_order_id": {
|
||||
@@ -77,14 +123,14 @@
|
||||
"alias": ["pn", "part", "parts", "物料号", "零件号", "Part Number", "材料号", "物料编码", "零件编码"]
|
||||
}
|
||||
},
|
||||
|
||||
|
||||
"milestone_date_fields": {
|
||||
"service_order_creation_date": {
|
||||
"type": "datetime",
|
||||
"desc": "开单日期",
|
||||
"desc": "开单日期/开单时间，即这条记录的创建时间，即 Backlog Order 的创建/新增时间，即 BO 的创建/新增时间。业务含义：当前数据的 update_date 与 service_order_creation_date 相减即为该订单的存续时间（订单从创建到当前状态的时间跨度）",
|
||||
"format": "YYYY-MM-DD HH:MM:SS",
|
||||
"query_format": "作为字符串展示",
|
||||
"alias": ["create_date", "创建时间", "下单时间", "开单日期", "SO创建时间", "开单时间", "Order Creation Date", "created_date", "创建日期"]
|
||||
"alias": ["create_date", "创建时间", "create 时间", "开单日期", "SO创建时间", "开单时间", "Order Creation Date", "created_date", "创建日期", "存续时间", "订单时长", "BO创建时间", "BO新增时间", "Backlog Order创建时间", "Backlog Order新增时间", "记录创建时间", "记录新增时间"]
|
||||
},
|
||||
"eta": {
|
||||
"type": "date",
|
||||
@@ -115,19 +161,60 @@
|
||||
"alias": ["更新时间", "更新日期", "历史数据状态更新日期", "修改时间"]
|
||||
}
|
||||
},
|
||||
|
||||
|
||||
"additional_fields": {
|
||||
"bu": {
|
||||
"type": "varchar(4096)",
|
||||
"desc": "业务单元",
|
||||
"alias": ["bu", "BU", "业务单元", "业务线"]
|
||||
},
|
||||
"multiple_flag": {
|
||||
"type": "varchar(4096)",
|
||||
"desc": "多重影响标识",
|
||||
"alias": ["multiple_flag", "multi_flag", "多重标识", "多标识"]
|
||||
},
|
||||
"country_dc_premier_stock": {
|
||||
"type": "varchar(4096)",
|
||||
"desc": "国家DC Premier库存",
|
||||
"alias": ["country_dc_premier_stock", "premier_stock", "premier stock","国家DC优先库存", "国家DC优先库存量"]
|
||||
},
|
||||
"potential_ww_stock": {
|
||||
"type": "varchar(63355)",
|
||||
"desc": "潜在全球库存",
|
||||
"alias": ["potential_ww_stock", "ww_stock", "潜在全球库存", "潜在WW库存"]
|
||||
},
|
||||
"potential_opo_stock": {
|
||||
"type": "varchar(63355)",
|
||||
"desc": "潜在OPO库存",
|
||||
"alias": ["potential_opo_stock", "opo_stock", "潜在OPO库存", "OPO库存"]
|
||||
},
|
||||
"potential_other_dc_stock": {
|
||||
"type": "varchar(63355)",
|
||||
"desc": "潜在其他DC库存",
|
||||
"alias": ["potential_other_dc_stock", "other_dc_stock", "潜在其他DC库存", "其他DC库存"]
|
||||
},
|
||||
"potential_reverse_stock": {
|
||||
"type": "varchar(63355)",
|
||||
"desc": "潜在逆向库存",
|
||||
"alias": ["potential_reverse_stock", "reverse_stock", "潜在逆向库存", "逆向库存"]
|
||||
},
|
||||
"owner": {
|
||||
"type": "varchar(4096)",
|
||||
"desc": "负责人/归属人, 查询时必须转换为小写并使用like匹配, 如: lower(owner) like '%senilaf%' ",
|
||||
"example": "senilaf",
|
||||
"alias": ["owner", "负责人", "归属人", "owner_name", "责任人", "持有人"]
|
||||
},
|
||||
"topmost_pn": {
|
||||
"type": "varchar(4096)",
|
||||
"desc": "最紧缺物料号, 注意与pn区分, 这是topmost pn, 这是topmost pn, 这是topmost pn, 不是PN",
|
||||
"example": "5CB1L57599",
|
||||
"alias": ["tp","tm", "最紧缺物料号", "Topmost Part Number", "topmost", "topmost pn"]
|
||||
"alias": ["tp", "tm", "TM", "TOPMOST", "Topmost", "Topmost Part Number", "topmost", "topmost pn", "TOPMOST PN", "topmost_pn", "top-most"]
|
||||
},
|
||||
"commodity_code": {
|
||||
"type": "varchar(4096)",
|
||||
"desc": "商品编码",
|
||||
"example": "PL",
|
||||
"alias": ["commodity", "商品代码", "编码", "cc", "物料分类", "Commodity Code", "商品类别", "物料类型", "商品编码"]
|
||||
"alias": ["commodity", "商品代码", "CC", "cc", "物料分类", "Commodity Code", "商品类别", "物料类型", "商品编码"]
|
||||
},
|
||||
"ship_to_country": {
|
||||
"type": "varchar(4096)",
|
||||
@@ -167,7 +254,7 @@
|
||||
},
|
||||
"model": {
|
||||
"type": "varchar(4096)",
|
||||
"desc": "Lenovo的机型, 禁止使用model = 'model_name', 查询时必须转换为小写并使用like匹配，如: lower(model) like '%X13%'",
|
||||
"desc": "Lenovo的机型, 禁止使用model = 'model_name', 查询时model_name必须转换为小写并使用like匹配，如: lower(model) like '%x13%'",
|
||||
"example": ["Yoga 7 16IAH7", "X13 GEN3", "T16 Gen4 AMD", "Legion 7 16ACHg6"],
|
||||
"alias": ["model", "机型", "型号", "Model", "设备型号", "机器型号"]
|
||||
},
|
||||
@@ -190,7 +277,7 @@
|
||||
},
|
||||
"whether_premier": {
|
||||
"type": "varchar(4096)",
|
||||
"desc": "优先级标识，默认查询 'Premier'",
|
||||
"desc": "优先级标识，默认查询 'Premier'。当用户需要统计Premier订单数量时，使用 sum(if(whether_premier='Premier',1,0)) as premier_qty",
|
||||
"values": ["Starndard", "Premier"],
|
||||
"alias": ["premier", "优质服务", "是否优质", "是否Premier", "Premier服务", "是否优先", "Whether Premier", "优先服务标识", "VIP服务"]
|
||||
},
|
||||
@@ -210,9 +297,16 @@
|
||||
"desc": "零件销售信息",
|
||||
"alias": ["零件销售", "销售信息", "部件销售", "配件销售", "销售数据"]
|
||||
},
|
||||
"action": {
|
||||
"type": "varchar(4096)",
|
||||
"desc": "操作/动作标识，用于标识订单当前执行的操作类型。当用户提到'sub rule'时，该字段精确匹配 action = 'Not accept sub'",
|
||||
"example": "Not accept sub",
|
||||
"alias": ["action", "操作", "动作", "Action", "操作类型", "sub rule", "Sub Rule", "SUB RULE", "sub_rule", "不接受sub", "Not accept sub"]
|
||||
},
|
||||
"warranty": {
|
||||
"type": "varchar(4096)",
|
||||
"desc": "保修信息",
|
||||
"values": ["MDOA", "OPT", "CLW", "DOA", "FOC", "OOW", "OBL", "ADW"],
|
||||
"alias": ["保修", "保修信息", "质保", "保修条款", "保修状态"]
|
||||
},
|
||||
"aging_day": {
|
||||
@@ -239,12 +333,6 @@
|
||||
"values": ["0-7D", "8-14D", "15-21D", "22-28D", "28D+", "null"],
|
||||
"alias": ["账龄天数", "账龄", "recovery range", "账期分类", "账龄分类", "天数分类"]
|
||||
},
|
||||
"action": {
|
||||
"type": "varchar(4096)",
|
||||
"desc": "操作/规则",
|
||||
"example": "Not accept sub",
|
||||
"alias": ["sub_rule", "操作", "规则", "限制规则", "操作类型", "处理规则"]
|
||||
},
|
||||
"order_type":{
|
||||
"type": "varchar(4096)",
|
||||
"desc": "订单类型",
|
||||
@@ -275,30 +363,40 @@
|
||||
"type": "varchar(4096)",
|
||||
"desc": "house air way bill",
|
||||
"examples": ["DIM042186899"],
|
||||
"alias": ["分运单号", "运单号", "代理运单", "分运单", "house air way bill"]
|
||||
"alias": ["hawb", "HAWB", "Hawb", "分运单号", "运单号", "代理运单", "分运单", "house air way bill", "house airway bill", "house air waybill", "house airway waybill", "air way bill", "air waybill", "HAWB No", "HAWB NO", "HAWB号码", "HAWB号", "分运单", "分运单编号", "分运单号码"]
|
||||
},
|
||||
"bol": {
|
||||
"type": "varchar(4096)",
|
||||
"desc": "bill of lading",
|
||||
"examples": ["OOLU2678082490"],
|
||||
"alias": ["bol", "BOL", "Bol", "bill of lading", "B/L", "b/l", "提单", "提单号", "提单编号", "海运提单", "货运提单", "BOL No", "BOL NO", "BOL号", "BOL号码"]
|
||||
},
|
||||
"dn": {
|
||||
"type": "varchar(4096)",
|
||||
"desc": "delivery note / delivery number",
|
||||
"examples": ["0081234567"],
|
||||
"alias": ["dn", "DN", "Dn", "delivery note", "delivery number", "delivery no", "送货单", "送货单号", "交货单", "交货单号", "出货单", "出货单号", "DN No", "DN NO", "DN号", "DN号码"]
|
||||
},
|
||||
"po": {
|
||||
"type": "varchar(4096)",
|
||||
"desc": "purchase order",
|
||||
"examples": ["4501234567"],
|
||||
"alias": ["po", "PO", "Po", "purchase order", "purchase order number", "采购单", "采购单号", "采购订单", "采购订单号", "PO No", "PO NO", "PO号", "PO号码"]
|
||||
},
|
||||
"prid": {
|
||||
"type": "varchar(4096)",
|
||||
"desc": "采购申请/内部请求标识",
|
||||
"examples": ["PR12345678"],
|
||||
"alias": ["prid", "PRID", "Prid", "pr id", "PR ID", "purchase request id", "采购申请号", "采购申请编号", "申请单号", "请求单号", "内部请求号", "PRID号", "PRID号码"]
|
||||
}
|
||||
},
|
||||
|
||||
|
||||
"system_flag_fields": {
|
||||
"is_passdue": {
|
||||
"type": "varchar(64)",
|
||||
"desc": "是否逾期：'1'表示逾期，'0'表示正常",
|
||||
"business_rule": "根据用户要求过滤, 禁止出现在SELECT中",
|
||||
"display_rule": "仅用于WHERE过滤，不显示",
|
||||
"alias": ["passdue", "逾期标志", "是否逾期", "overdue", "超期标志", "逾期标识"]
|
||||
},
|
||||
"is_dummy": {
|
||||
"type": "varchar(64)",
|
||||
"desc": "是否为虚拟/测试数据：'1'表示是dummy数据，'0'表示真实数据",
|
||||
"business_rule": "默认过滤掉dummy数据（is_dummy='0'），除非用户指定, 禁止出现在SELECT中",
|
||||
"display_rule": "仅用于WHERE过滤，不显示",
|
||||
"alias": ["dummy", "虚拟标志", "是否虚拟", "测试数据", "假数据标识", "模拟数据"]
|
||||
},
|
||||
"data_flag": {
|
||||
"type": "varchar(64)",
|
||||
"desc": "数据标志：'Newest'表示最新状态，'Changelog'表示历史变更",
|
||||
"example": "Newest",
|
||||
"business_rule": "默认查询最新状态（Newest），查询历史时使用Changelog, 禁止出现在SELECT中",
|
||||
"business_rule": "默认查询最新状态（Newest），查询历史时使用Changelog, 禁止出现在SELECT中,where条件中出现update_date则不使用data_flag进行过滤",
|
||||
"display_rule": "仅用于WHERE过滤，不显示",
|
||||
"alias": ["数据标志", "数据类型", "数据状态", "记录类型", "数据分类"]
|
||||
}
|
||||
@@ -306,59 +404,84 @@
|
||||
},
|
||||
"examples": {
|
||||
"newest_status_all_fields": {
|
||||
"user": "请查询SO:4020986743的全部字段",
|
||||
"sql": "SELECT service_order_id, soid, cast(service_order_creation_date as varchar(4096)) as service_order_creation_date, ship_to_country, part_number, topmost_pn, commodity_code, category, cast(eta as varchar(4096)) as eta, cast(so_eta as varchar(4096)) as so_eta, key_lenovo_ref_no, order_type, stm_planner, region, dc_plant, mtm, machine_sn, whether_premier, service_type, warranty, parts_sales, customer, life_cycle, model, aging_range, lenovo_ref_no, action, cast(update_date as varchar(4096)) as update_date FROM dwd_ai.apbo_eta_ful WHERE (service_order_id = '4020986743' or soid = '4020986743') AND is_dummy = '0' AND data_flag = 'Newest' ORDER BY soid, eta DESC",
|
||||
"user": "How about the ETA of 4020731111 and 4020947030?",
|
||||
"sql": "SELECT service_order_id, soid, cast(service_order_creation_date as varchar(4096)) as service_order_creation_date, ship_to_country, part_number, topmost_pn, commodity_code, category, cast(eta as varchar(4096)) as eta, cast(so_eta as varchar(4096)) as so_eta, key_lenovo_ref_no, order_type, stm_planner, region, dc_plant, mtm, machine_sn, whether_premier, service_type, warranty, parts_sales, customer, life_cycle, model, aging_range, lenovo_ref_no, action, cast(update_date as varchar(4096)) as update_date FROM dwd_ai.apbo_eta_ful WHERE (service_order_id in ('4020731111', '4020947030') or soid in ('4020731111', '4020947030')) AND data_flag = 'Newest' ORDER BY soid, eta DESC",
|
||||
"field_selection_reason": "默认查询最新状态，按默认展示字段顺序显示所有字段（除系统字段），日期字段转换为字符类型"
|
||||
},
|
||||
"history_records_all_fields": {
|
||||
"user": "查看2025年12月31的so为4020438779的历史变更记录",
|
||||
"sql": "SELECT service_order_id, soid, cast(service_order_creation_date as varchar(4096)) as service_order_creation_date, ship_to_country, part_number, topmost_pn, commodity_code, category, cast(eta as varchar(4096)) as eta, cast(so_eta as varchar(4096)) as so_eta, key_lenovo_ref_no, order_type, stm_planner, region, dc_plant, mtm, machine_sn, whether_premier, service_type, warranty, parts_sales, customer, life_cycle, model, aging_range, lenovo_ref_no, action, cast(update_date as varchar(4096)) as update_date FROM dwd_ai.apbo_eta_ful WHERE (service_order_id = '4020438779' or soid = '4020438779') AND cast(update_date as varchar(4096)) like '%2025-12-31%' AND is_dummy = '0' AND data_flag = 'Changelog' ORDER BY soid, eta DESC",
|
||||
"field_selection_reason": "查询历史变更记录，按默认展示字段顺序显示所有字段（除系统字段），日期字段转换为字符类型"
|
||||
"sql": "SELECT service_order_id, soid, cast(service_order_creation_date as varchar(4096)) as service_order_creation_date, ship_to_country, part_number, topmost_pn, commodity_code, category, cast(eta as varchar(4096)) as eta, cast(so_eta as varchar(4096)) as so_eta, key_lenovo_ref_no, order_type, stm_planner, region, dc_plant, mtm, machine_sn, whether_premier, service_type, warranty, parts_sales, customer, life_cycle, model, aging_range, lenovo_ref_no, action, cast(update_date as varchar(4096)) as update_date FROM dwd_ai.apbo_eta_ful WHERE service_order_id = '4020438779' AND cast(update_date as varchar(4096)) like '%2025-12-31%' ORDER BY soid, eta DESC",
|
||||
"field_selection_reason": "查询历史变更记录，按默认展示字段顺序显示所有字段（除系统字段），日期字段转换为字符类型，且用户指定了update_date进行过滤，去掉data_flag = 'Newest'的默认过滤条件"
|
||||
},
|
||||
"specific_fields_query": {
|
||||
"user": "查询SO为4020438779的country, eta, order_type",
|
||||
"sql": "SELECT ship_to_country, cast(eta as varchar(4096)) as eta, order_type, service_order_id, soid, cast(service_order_creation_date as varchar(4096)) as service_order_creation_date, part_number, topmost_pn, commodity_code, category, cast(so_eta as varchar(4096)) as so_eta, key_lenovo_ref_no, stm_planner, region, dc_plant, mtm, machine_sn, whether_premier, service_type, warranty, parts_sales, customer, life_cycle, model, aging_range, lenovo_ref_no, action, cast(update_date as varchar(4096)) as update_date FROM dwd_ai.apbo_eta_ful WHERE (service_order_id = '4020438779' or soid = '4020438779') AND is_dummy = '0' AND data_flag = 'Newest' ORDER BY soid, eta DESC",
|
||||
"sql": "SELECT ship_to_country, cast(eta as varchar(4096)) as eta, order_type, service_order_id, soid, cast(service_order_creation_date as varchar(4096)) as service_order_creation_date, part_number, topmost_pn, commodity_code, category, cast(so_eta as varchar(4096)) as so_eta, key_lenovo_ref_no, stm_planner, region, dc_plant, mtm, machine_sn, whether_premier, service_type, warranty, parts_sales, customer, life_cycle, model, aging_range, lenovo_ref_no, action, cast(update_date as varchar(4096)) as update_date FROM dwd_ai.apbo_eta_ful WHERE service_order_id = '4020438779' AND data_flag = 'Newest' ORDER BY soid, eta DESC",
|
||||
"field_selection_reason": "用户提到的字段(ship_to_country, eta, order_type)优先显示在最前面，然后补充其他默认展示字段"
|
||||
},
|
||||
"aggragate_query": {
|
||||
"user": "by country, key_Lenovo Ref No, eta 汇总REGION=CAP passdue 信息, 并从小到大排序",
|
||||
"sql": "SELECT region, ship_to_country, key_lenovo_ref_no, cast(eta as varchar(4096)) as eta, count(1) FROM dwd_ai.apbo_eta_ful WHERE is_passdue = '1' AND is_dummy = '0' AND data_flag = 'Newest' AND region = 'CAP' group by region, ship_to_country, key_lenovo_ref_no, cast(eta as varchar(4096)) ORDER BY count(1) ASC",
|
||||
"field_selection_reason": "查询特定账龄的订单，按默认展示字段顺序显示，日期字段转换为字符类型"
|
||||
"user": "by country, key_Lenovo Ref No, eta 汇总REGION=CAP 信息, 并从小到大排序",
|
||||
"sql": "SELECT region, ship_to_country, key_lenovo_ref_no, cast(eta as varchar(4096)) as eta, count(soid) as qty FROM dwd_ai.apbo_eta_ful WHERE data_flag = 'Newest' AND region = 'CAP' group by region, ship_to_country, key_lenovo_ref_no, cast(eta as varchar(4096)) ORDER BY qty DESC",
|
||||
"field_selection_reason": "聚合查询，qty默认降序排序"
|
||||
},
|
||||
"overdue_orders_all_fields": {
|
||||
"user": "查询所有passdue/逾期的订单",
|
||||
"sql": "SELECT service_order_id, soid, cast(service_order_creation_date as varchar(4096)) as service_order_creation_date, ship_to_country, part_number, topmost_pn, commodity_code, category, cast(eta as varchar(4096)) as eta, cast(so_eta as varchar(4096)) as so_eta, key_lenovo_ref_no, order_type, stm_planner, region, dc_plant, mtm, machine_sn, whether_premier, service_type, warranty, parts_sales, customer, life_cycle, model, aging_range, lenovo_ref_no, action, cast(update_date as varchar(4096)) as update_date FROM dwd_ai.apbo_eta_ful WHERE is_passdue = '1' AND is_dummy = '0' AND data_flag = 'Newest' ORDER BY soid, eta DESC",
|
||||
"field_selection_reason": "查询逾期订单，按默认展示字段顺序显示，日期字段转换为字符类型"
|
||||
"topn_by_topmost_pn_model_qty": {
|
||||
"user": "by topmost_pn, model 查询 top 10",
|
||||
"sql": "SELECT topmost_pn, model, count(soid) as qty FROM dwd_ai.apbo_eta_ful WHERE data_flag = 'Newest' GROUP BY topmost_pn, model ORDER BY qty DESC LIMIT 10",
|
||||
"field_selection_reason": "按维度TopN，仅输出维度字段+qty"
|
||||
},
|
||||
"topn_by_country_qty": {
|
||||
"user": "CC为LT ,by country 查询 top 20",
|
||||
"sql": "SELECT commodity_code,ship_to_country, count(soid) as qty FROM dwd_ai.apbo_eta_ful WHERE data_flag = 'Newest' AND commodity_code = 'LT'GROUP BY commodity_code, ship_to_country ORDER BY qty DESC LIMIT 20",
|
||||
"field_selection_reason": "按维度TopN，默认使用维度+qty排序，仅输出维度字段+qty"
|
||||
},
|
||||
"Machine_sn_query": {
|
||||
"user": "SN PF4C8CBL的order 信息",
|
||||
"sql": "SELECT machine_sn, service_order_id, soid, cast(service_order_creation_date as varchar(4096)) as service_order_creation_date, ship_to_country, part_number, topmost_pn, commodity_code, category, cast(eta as varchar(4096)) as eta, cast(so_eta as varchar(4096)) as so_eta, key_lenovo_ref_no, order_type, stm_planner, region, dc_plant, mtm, whether_premier, service_type, warranty, parts_sales, customer, life_cycle, model, aging_range, lenovo_ref_no, action, cast(update_date as varchar(4096)) as update_date FROM dwd_ai.apbo_eta_ful WHERE machine_sn = 'PF4C8CBL' AND is_dummy = '0' AND data_flag = 'Newest' ORDER BY soid, eta DESC",
|
||||
"sql": "SELECT machine_sn, service_order_id, soid, cast(service_order_creation_date as varchar(4096)) as service_order_creation_date, ship_to_country, part_number, topmost_pn, commodity_code, category, cast(eta as varchar(4096)) as eta, cast(so_eta as varchar(4096)) as so_eta, key_lenovo_ref_no, order_type, stm_planner, region, dc_plant, mtm, whether_premier, service_type, warranty, parts_sales, customer, life_cycle, model, aging_range, lenovo_ref_no, action, cast(update_date as varchar(4096)) as update_date FROM dwd_ai.apbo_eta_ful WHERE machine_sn = 'PF4C8CBL' AND data_flag = 'Newest' ORDER BY soid, eta DESC",
|
||||
"field_selection_reason": "用户提到的字段(machine_sn)优先显示在最前面，然后补充其他默认展示字段"
|
||||
},
|
||||
"status_query": {
|
||||
"user": "查询状态为wrong order的订单",
|
||||
"sql": "SELECT status, service_order_id, soid, cast(service_order_creation_date as varchar(4096)) as service_order_creation_date, ship_to_country, part_number, topmost_pn, commodity_code, category, cast(eta as varchar(4096)) as eta, cast(so_eta as varchar(4096)) as so_eta, key_lenovo_ref_no, order_type, stm_planner, region, dc_plant, mtm, machine_sn, whether_premier, service_type, warranty, parts_sales, customer, life_cycle, model, aging_range, lenovo_ref_no, action, cast(update_date as varchar(4096)) as update_date FROM dwd_ai.apbo_eta_ful WHERE status = 'wrong order' AND is_dummy = '0' AND data_flag = 'Newest' ORDER BY soid, eta DESC",
|
||||
"sql": "SELECT status, service_order_id, soid, cast(service_order_creation_date as varchar(4096)) as service_order_creation_date, ship_to_country, part_number, topmost_pn, commodity_code, category, cast(eta as varchar(4096)) as eta, cast(so_eta as varchar(4096)) as so_eta, key_lenovo_ref_no, order_type, stm_planner, region, dc_plant, mtm, machine_sn, whether_premier, service_type, warranty, parts_sales, customer, life_cycle, model, aging_range, lenovo_ref_no, action, cast(update_date as varchar(4096)) as update_date FROM dwd_ai.apbo_eta_ful WHERE status = 'wrong order' AND data_flag = 'Newest' ORDER BY soid, eta DESC",
|
||||
"field_selection_reason": "用户提到的字段(status)优先显示在最前面，然后补充其他默认展示字段"
|
||||
},
|
||||
"multiple_fields_query": {
|
||||
"user": "查看SN为PF4C8CBL的订单状态和机器型号",
|
||||
"sql": "SELECT machine_sn, status, model, service_order_id, soid, cast(service_order_creation_date as varchar(4096)) as service_order_creation_date, ship_to_country, part_number, topmost_pn, commodity_code, category, cast(eta as varchar(4096)) as eta, cast(so_eta as varchar(4096)) as so_eta, key_lenovo_ref_no, order_type, stm_planner, region, dc_plant, mtm, whether_premier, service_type, warranty, parts_sales, customer, life_cycle, aging_range, lenovo_ref_no, action, cast(update_date as varchar(4096)) as update_date FROM dwd_ai.apbo_eta_ful WHERE machine_sn = 'PF4C8CBL' AND is_dummy = '0' AND data_flag = 'Newest' ORDER BY soid, eta DESC",
|
||||
"sql": "SELECT machine_sn, status, model, service_order_id, soid, cast(service_order_creation_date as varchar(4096)) as service_order_creation_date, ship_to_country, part_number, topmost_pn, commodity_code, category, cast(eta as varchar(4096)) as eta, cast(so_eta as varchar(4096)) as so_eta, key_lenovo_ref_no, order_type, stm_planner, region, dc_plant, mtm, whether_premier, service_type, warranty, parts_sales, customer, life_cycle, aging_range, lenovo_ref_no, action, cast(update_date as varchar(4096)) as update_date FROM dwd_ai.apbo_eta_ful WHERE machine_sn = 'PF4C8CBL' AND data_flag = 'Newest' ORDER BY soid, eta DESC",
|
||||
"field_selection_reason": "用户提到的字段(machine_sn, status, model)按问题中出现的顺序优先显示在最前面，然后补充其他默认展示字段"
|
||||
},
|
||||
"model_query_all_fields": {
|
||||
"user": "查询机型包含X13的订单",
|
||||
"sql": "SELECT service_order_id, soid, cast(service_order_creation_date as varchar(4096)) as service_order_creation_date, ship_to_country, part_number, topmost_pn, commodity_code, category, cast(eta as varchar(4096)) as eta, cast(so_eta as varchar(4096)) as so_eta, key_lenovo_ref_no, order_type, stm_planner, region, dc_plant, mtm, machine_sn, whether_premier, service_type, warranty, parts_sales, customer, life_cycle, model, aging_range, lenovo_ref_no, action, cast(update_date as varchar(4096)) as update_date FROM dwd_ai.apbo_eta_ful WHERE model like '%X13%' AND is_dummy = '0' AND data_flag = 'Newest' ORDER BY soid, eta DESC",
|
||||
"sql": "SELECT service_order_id, soid, cast(service_order_creation_date as varchar(4096)) as service_order_creation_date, ship_to_country, part_number, topmost_pn, commodity_code, category, cast(eta as varchar(4096)) as eta, cast(so_eta as varchar(4096)) as so_eta, key_lenovo_ref_no, order_type, stm_planner, region, dc_plant, mtm, machine_sn, whether_premier, service_type, warranty, parts_sales, customer, life_cycle, model, aging_range, lenovo_ref_no, action, cast(update_date as varchar(4096)) as update_date FROM dwd_ai.apbo_eta_ful WHERE lower(model) like '%x13%' AND data_flag = 'Newest' ORDER BY soid, eta DESC",
|
||||
"field_selection_reason": "查询特定机型的订单，使用like匹配model字段，按默认展示字段顺序显示"
|
||||
},
|
||||
"order_type_query_all_fields": {
|
||||
"user": "查询订单类型为MDOA的订单",
|
||||
"sql": "SELECT service_order_id, soid, cast(service_order_creation_date as varchar(4096)) as service_order_creation_date, ship_to_country, part_number, topmost_pn, commodity_code, category, cast(eta as varchar(4096)) as eta, cast(so_eta as varchar(4096)) as so_eta, key_lenovo_ref_no, order_type, stm_planner, region, dc_plant, mtm, machine_sn, whether_premier, service_type, warranty, parts_sales, customer, life_cycle, model, aging_range, lenovo_ref_no, action, cast(update_date as varchar(4096)) as update_date FROM dwd_ai.apbo_eta_ful WHERE order_type = 'MDOA' AND is_dummy = '0' AND data_flag = 'Newest' ORDER BY soid, eta DESC",
|
||||
"sql": "SELECT service_order_id, soid, cast(service_order_creation_date as varchar(4096)) as service_order_creation_date, ship_to_country, part_number, topmost_pn, commodity_code, category, cast(eta as varchar(4096)) as eta, cast(so_eta as varchar(4096)) as so_eta, key_lenovo_ref_no, order_type, stm_planner, region, dc_plant, mtm, machine_sn, whether_premier, service_type, warranty, parts_sales, customer, life_cycle, model, aging_range, lenovo_ref_no, action, cast(update_date as varchar(4096)) as update_date FROM dwd_ai.apbo_eta_ful WHERE order_type = 'MDOA' AND data_flag = 'Newest' ORDER BY soid, eta DESC",
|
||||
"field_selection_reason": "查询特定订单类型的订单，按默认展示字段顺序显示"
|
||||
},
|
||||
"passdue_info_query": {
|
||||
"user": "region = ANZ 的passdue 信息",
|
||||
"sql": "SELECT region, service_order_id, soid, cast(service_order_creation_date as varchar(4096)) as service_order_creation_date, ship_to_country, part_number, topmost_pn, commodity_code, category, cast(eta as varchar(4096)) as eta, cast(so_eta as varchar(4096)) as so_eta, key_lenovo_ref_no, order_type, stm_planner, dc_plant, mtm, machine_sn, whether_premier, service_type, warranty, parts_sales, customer, life_cycle, model, aging_range, lenovo_ref_no, action, cast(update_date as varchar(4096)) as update_date FROM dwd_ai.apbo_eta_ful WHERE is_passdue = '1' AND is_dummy = '0' AND data_flag = 'Newest' ORDER BY soid, eta DESC",
|
||||
"field_selection_reason": "查询逾期订单的详细信息，按默认展示字段顺序显示"
|
||||
"region_info_query": {
|
||||
"user": "region = ANZ 的信息",
|
||||
"sql": "SELECT region, service_order_id, soid, cast(service_order_creation_date as varchar(4096)) as service_order_creation_date, ship_to_country, part_number, topmost_pn, commodity_code, category, cast(eta as varchar(4096)) as eta, cast(so_eta as varchar(4096)) as so_eta, key_lenovo_ref_no, order_type, stm_planner, dc_plant, mtm, machine_sn, whether_premier, service_type, warranty, parts_sales, customer, life_cycle, model, aging_range, lenovo_ref_no, action, cast(update_date as varchar(4096)) as update_date FROM dwd_ai.apbo_eta_ful WHERE data_flag = 'Newest' AND region = 'ANZ' ORDER BY soid, eta DESC",
|
||||
"field_selection_reason": "按区域查询，按默认展示字段顺序显示"
|
||||
},
|
||||
"sub_rule_query": {
|
||||
"user": "查询sub rule的订单",
|
||||
"sql": "SELECT action, service_order_id, soid, cast(service_order_creation_date as varchar(4096)) as service_order_creation_date, ship_to_country, part_number, topmost_pn, commodity_code, category, cast(eta as varchar(4096)) as eta, cast(so_eta as varchar(4096)) as so_eta, key_lenovo_ref_no, order_type, stm_planner, region, dc_plant, mtm, machine_sn, whether_premier, service_type, warranty, parts_sales, customer, life_cycle, model, aging_range, lenovo_ref_no, cast(update_date as varchar(4096)) as update_date FROM dwd_ai.apbo_eta_ful WHERE action = 'Not accept sub' AND data_flag = 'Newest' ORDER BY soid, eta DESC",
|
||||
"field_selection_reason": "用户提到'sub rule'，触发sub_rule_keyword_rule，在WHERE中添加 action = 'Not accept sub' 进行精确过滤"
|
||||
},
|
||||
"sub_rule_with_country_query": {
|
||||
"user": "查询country为VN的sub rule订单信息",
|
||||
"sql": "SELECT action, ship_to_country, service_order_id, soid, cast(service_order_creation_date as varchar(4096)) as service_order_creation_date, part_number, topmost_pn, commodity_code, category, cast(eta as varchar(4096)) as eta, cast(so_eta as varchar(4096)) as so_eta, key_lenovo_ref_no, order_type, stm_planner, region, dc_plant, mtm, machine_sn, whether_premier, service_type, warranty, parts_sales, customer, life_cycle, model, aging_range, lenovo_ref_no, cast(update_date as varchar(4096)) as update_date FROM dwd_ai.apbo_eta_ful WHERE action = 'Not accept sub' AND ship_to_country = 'VN' AND data_flag = 'Newest' ORDER BY soid, eta DESC",
|
||||
"field_selection_reason": "用户提到'sub rule'且指定country=VN，WHERE中同时包含 action = 'Not accept sub' 和 ship_to_country = 'VN'"
|
||||
},
|
||||
"passdue_query": {
|
||||
"user": "查询passdue的订单",
|
||||
"sql": "SELECT service_order_id, soid, cast(service_order_creation_date as varchar(4096)) as service_order_creation_date, ship_to_country, part_number, topmost_pn, commodity_code, category, cast(eta as varchar(4096)) as eta, cast(so_eta as varchar(4096)) as so_eta, key_lenovo_ref_no, order_type, stm_planner, region, dc_plant, mtm, machine_sn, whether_premier, service_type, warranty, parts_sales, customer, life_cycle, model, aging_range, lenovo_ref_no, action, cast(update_date as varchar(4096)) as update_date FROM dwd_ai.apbo_eta_ful WHERE cast(update_date as date) - cast(eta as date) > 0 AND data_flag = 'Newest' ORDER BY soid, eta DESC",
|
||||
"field_selection_reason": "用户提到'passdue'，触发passdue_keyword_rule，在WHERE中添加 cast(update_date as date) - cast(eta as date) > 0 过滤逾期订单"
|
||||
},
|
||||
"passdue_with_country_query": {
|
||||
"user": "查询country为AU的passdue订单",
|
||||
"sql": "SELECT ship_to_country, service_order_id, soid, cast(service_order_creation_date as varchar(4096)) as service_order_creation_date, part_number, topmost_pn, commodity_code, category, cast(eta as varchar(4096)) as eta, cast(so_eta as varchar(4096)) as so_eta, key_lenovo_ref_no, order_type, stm_planner, region, dc_plant, mtm, machine_sn, whether_premier, service_type, warranty, parts_sales, customer, life_cycle, model, aging_range, lenovo_ref_no, action, cast(update_date as varchar(4096)) as update_date FROM dwd_ai.apbo_eta_ful WHERE ship_to_country = 'AU' AND cast(update_date as date) - cast(eta as date) > 0 AND data_flag = 'Newest' ORDER BY soid, eta DESC",
|
||||
"field_selection_reason": "用户提到'passdue'且指定country=AU，WHERE中同时包含 ship_to_country = 'AU' 和 cast(update_date as date) - cast(eta as date) > 0"
|
||||
}
|
||||
}
|
||||
}
|
||||
+15
-13
@@ -5,13 +5,14 @@
|
||||
"description": "此模型用于查询订单在物流运输全链路中的关键节点(milestone)信息，追踪从订单创建、提货、运输到签收的完整状态流。每个订单可对应多个节点记录以反映运输进度。"
|
||||
},
|
||||
"data_model_specification": {
|
||||
"data_source": "dwd_ai.apbo_milestone_info",
|
||||
"fields_list": ["service_order_id", "soid", "part_number", "PO", "po_creation_date", "prid", "DN", "dn_date", "gi_date", "BOL", "hawb", "pickup_time", "etd", "atd", "eta", "ata", "pod", "gr_date", "status", "status_date", "service_order_creation_date", "so_eta", "topmost_pn", "commodity_code", "ship_to_country", "region", "dc_plant", "mtm", "machine_sn","machine_type", "whether_premier", "stm_planner", "category", "lenovo_ref_no"],
|
||||
"data_source": "dwd_ai.apbo_eta_milestone",
|
||||
"fields_list": ["service_order_id", "soid", "part_number", "PO", "po_creation_date", "prid", "DN", "dn_date", "gi_date", "BOL", "hawb", "pickup_time", "flight_etd", "flight_atd", "flight_eta", "flight_ata", "eta", "pod", "gr_date", "status", "status_date", "service_order_creation_date", "so_eta", "topmost_pn", "commodity_code", "ship_to_country", "region", "dc_plant", "mtm", "machine_sn","machine_type", "whether_premier", "stm_planner", "category", "lenovo_ref_no"],
|
||||
"mandatory_display_fields": {
|
||||
"rule1": "字段默认全部展示。日期字段需格式化为指定字符串格式。",
|
||||
"rule2": "select时，所有NULL值使用空字符串''代替",
|
||||
"rule3": "部分字段select时的顺序如下:po,po_creation_date,prid,dn,dn_date,gi_date,bol,hawb,pickup_time,etd,atd,eta,ata,pod,gr_date",
|
||||
"rule4": "禁止使用limit"
|
||||
"rule3": "部分字段select时的顺序如下:po,po_creation_date,prid,dn,dn_date,gi_date,bol,hawb,pickup_time,flight_etd,flight_atd,flight_eta,flight_ata,eta,pod,gr_date",
|
||||
"rule4": "禁止使用limit",
|
||||
"rule5": "status和category字段必须固定在最前面两列展示，且每次查询都必须包含这两个字段"
|
||||
},
|
||||
|
||||
"optional_fields": {
|
||||
@@ -54,14 +55,15 @@
|
||||
"dn_date": {"type": "date", "desc": "发货单创建日期", "format": "YYYY-MM-DD HH:MM:SS", "query_format": "CAST(field_name AS VARCHAR(2048)) AS field_name 作为字符串展示", "alias": ["发货单日期", "DN日期", "发货时间", "Delivery Note Date"]},
|
||||
"gi_date": {"type": "date", "desc": "货物发出日期(Goods Issue)", "format": "YYYY-MM-DD HH:MM:SS", "query_format": "CAST(field_name AS VARCHAR(2048)) AS field_name 作为字符串展示", "alias": ["货物发出时间", "发货日期", "出库时间", "Goods Issue Date", "出库日期"]},
|
||||
"pickup_time": {"type": "datetime", "desc": "提货时间", "format": "YYYY-MM-DD HH:MM:SS", "query_format": "CAST(field_name AS VARCHAR(2048)) AS field_name 作为字符串展示", "alias": ["提货日期", "取货时间", "提货时间点", "Pickup Time", "提取时间"]},
|
||||
"etd": {"type": "date", "desc": "预计出发时间(Estimated Time of Departure)", "format": "YYYY-MM-DD HH:MM:SS", "query_format": "CAST(field_name AS VARCHAR(2048)) AS field_name 作为字符串展示", "alias": ["预计出发", "计划出发时间", "ETD", "预计离港时间"]},
|
||||
"atd": {"type": "date", "desc": "实际出发时间(Actual Time of Departure)", "format": "YYYY-MM-DD HH:MM:SS", "query_format": "CAST(field_name AS VARCHAR(2048)) AS field_name 作为字符串展示", "alias": ["实际出发", "实际离港时间", "ATD", "实际出发时间"]},
|
||||
"eta": {"type": "date", "desc": "预计到达时间(Estimated Time of Arrival)", "format": "YYYY-MM-DD HH:MM:SS", "query_format": "CAST(field_name AS VARCHAR(2048)) AS field_name 作为字符串展示", "alias": ["预计到达", "计划到达时间", "ETA", "预计到港时间"]},
|
||||
"ata": {"type": "date", "desc": "实际到达时间(Actual Time of Arrival)", "format": "YYYY-MM-DD HH:MM:SS", "query_format": "CAST(field_name AS VARCHAR(2048)) AS field_name 作为字符串展示", "alias": ["实际到达", "实际到港时间", "ATA", "实际到达时间"]},
|
||||
"flight_etd": {"type": "date", "desc": "预计出发时间(Estimated Time of Departure)", "format": "YYYY-MM-DD HH:MM:SS", "query_format": "CAST(field_name AS VARCHAR(2048)) AS field_name 作为字符串展示", "alias": ["预计出发", "计划出发时间", "flight_etd", "预计离港时间"]},
|
||||
"flight_atd": {"type": "date", "desc": "实际出发时间(Actual Time of Departure)", "format": "YYYY-MM-DD HH:MM:SS", "query_format": "CAST(field_name AS VARCHAR(2048)) AS field_name 作为字符串展示", "alias": ["实际出发", "实际离港时间", "flight_atd", "实际出发时间"]},
|
||||
"flight_eta": {"type": "date", "desc": "航班预计到达时间(Flight Estimated Time of Arrival)", "format": "YYYY-MM-DD HH:MM:SS", "query_format": "CAST(field_name AS VARCHAR(2048)) AS field_name 作为字符串展示", "alias": ["航班预计到达", "航班计划到达时间", "flight_eta", "航班预计到港时间"]},
|
||||
"flight_ata": {"type": "date", "desc": "实际到达时间(Actual Time of Arrival)", "format": "YYYY-MM-DD HH:MM:SS", "query_format": "CAST(field_name AS VARCHAR(2048)) AS field_name 作为字符串展示", "alias": ["实际到达", "实际到港时间", "flight_ata", "实际到达时间"]},
|
||||
"eta": {"type": "date", "desc": "预计到达时间(Estimated Time of Arrival)", "format": "YYYY-MM-DD HH:MM:SS", "query_format": "CAST(field_name AS VARCHAR(2048)) AS field_name 作为字符串展示", "alias": ["预计到达", "计划到达时间", "eta", "预计到港时间"]},
|
||||
"pod": {"type": "date", "desc": "签收单收到日期(Proof of Delivery)", "format": "YYYY-MM-DD HH:MM:SS", "query_format": "CAST(field_name AS VARCHAR(2048)) AS field_name 作为字符串展示", "alias": ["签收时间", "POD时间", "签收日期", "Proof of Delivery", "签收证明时间"]},
|
||||
"gr_date": {"type": "date", "desc": "收货日期(Goods Receipt)", "format": "YYYY-MM-DD HH:MM:SS", "query_format": "CAST(field_name AS VARCHAR(2048)) AS field_name 作为字符串展示", "alias": ["收货时间", "入库时间", "GR时间", "Goods Receipt Date", "收货日期"]},
|
||||
"status_date": {"type": "date", "desc": "状态最后更新时间", "format": "YYYY-MM-DD HH:MM:SS", "query_format": "CAST(field_name AS VARCHAR(2048)) AS field_name 作为字符串展示", "alias": ["状态更新时间", "最后更新", "状态日期", "Status Update Date"]},
|
||||
"so_eta": {"type": "date", "desc": "订单预计到达时间(SO ETA)", "format": "YYYY-MM-DD HH:MM:SS", "query_format": "CAST(field_name AS VARCHAR(2048)) AS field_name 作为字符串展示", "alias": ["订单最终到达时间", "订单ETA", "服务订单预计到达", "Service Order ETA"]}
|
||||
"so_eta": {"type": "date", "desc": "订单预计到达时间(SO ata)", "format": "YYYY-MM-DD HH:MM:SS", "query_format": "CAST(field_name AS VARCHAR(2048)) AS field_name 作为字符串展示", "alias": ["订单最终到达时间", "订单ETA", "服务订单预计到达", "Service Order ata"]}
|
||||
},
|
||||
|
||||
"additional_fields": {
|
||||
@@ -85,13 +87,13 @@
|
||||
"examples": {
|
||||
"基础查询": {
|
||||
"user": "查询订单的物流节点信息",
|
||||
"sql": "SELECT service_order_id, soid, part_number, bol, dn, po, hawb, prid, CAST(service_order_creation_date AS VARCHAR(2048)) as service_order_creation_date, CAST(po_creation_date AS VARCHAR(2048)) as po_creation_date, CAST(dn_date AS VARCHAR(2048)) as dn_date, CAST(gi_date AS VARCHAR(2048)) as gi_date, CAST(pickup_time AS VARCHAR(2048)) as pickup_time, CAST(etd AS VARCHAR(2048)) as etd, CAST(atd AS VARCHAR(2048)) as atd, CAST(eta AS VARCHAR(2048)) as eta, CAST(ata AS VARCHAR(2048)) as ata, CAST(pod AS VARCHAR(2048)) as pod, CAST(gr_date AS VARCHAR(2048)) as gr_date, CAST(status_date AS VARCHAR(2048)) as status_date, CAST(so_eta AS VARCHAR(2048)) as so_eta FROM dwd_ai.apbo_milestone_info ORDER BY status_date DESC, service_order_creation_date DESC",
|
||||
"field_selection_reason": "基础查询显示所有必填的milestone字段,包括新增的service_order_creation_date, so_eta,日期字段已格式化为指定字符串格式"
|
||||
"sql": "SELECT status, category, service_order_id, soid, part_number, bol, dn, po, hawb, prid, CAST(service_order_creation_date AS VARCHAR(2048)) as service_order_creation_date, CAST(po_creation_date AS VARCHAR(2048)) as po_creation_date, CAST(dn_date AS VARCHAR(2048)) as dn_date, CAST(gi_date AS VARCHAR(2048)) as gi_date, CAST(pickup_time AS VARCHAR(2048)) as pickup_time, CAST(flight_etd AS VARCHAR(2048)) as flight_etd, CAST(flight_atd AS VARCHAR(2048)) as flight_atd, CAST(flight_eta AS VARCHAR(2048)) as flight_eta, CAST(flight_ata AS VARCHAR(2048)) as flight_ata, CAST(eta AS VARCHAR(2048)) as eta, CAST(pod AS VARCHAR(2048)) as pod, CAST(gr_date AS VARCHAR(2048)) as gr_date, CAST(status_date AS VARCHAR(2048)) as status_date, CAST(so_eta AS VARCHAR(2048)) as so_eta FROM dwd_ai.apbo_eta_milestone ORDER BY status_date DESC, service_order_creation_date DESC",
|
||||
"field_selection_reason": "基础查询显示所有必填的milestone字段,包括新增的service_order_creation_date, so_eta,日期字段已格式化为指定字符串格式,status和category固定在最前面两列"
|
||||
},
|
||||
"按主订单号查询": {
|
||||
"user": "SO为4019630464的milestone信息",
|
||||
"sql": "SELECT service_order_id, soid, part_number, bol, dn, po, hawb, prid, CAST(service_order_creation_date AS VARCHAR(2048)) as service_order_creation_date, CAST(po_creation_date AS VARCHAR(2048)) as po_creation_date, CAST(dn_date AS VARCHAR(2048)) as dn_date, CAST(gi_date AS VARCHAR(2048)) as gi_date, CAST(pickup_time AS VARCHAR(2048)) as pickup_time, CAST(etd AS VARCHAR(2048)) as etd, CAST(atd AS VARCHAR(2048)) as atd, CAST(eta AS VARCHAR(2048)) as eta, CAST(ata AS VARCHAR(2048)) as ata, CAST(pod AS VARCHAR(2048)) as pod, CAST(gr_date AS VARCHAR(2048)) as gr_date, CAST(status_date AS VARCHAR(2048)) as status_date, CAST(so_eta AS VARCHAR(2048)) as so_eta FROM dwd_ai.apbo_milestone_info WHERE service_order_id = '4019630464' ORDER BY status_date DESC, service_order_creation_date DESC",
|
||||
"field_selection_reason": "用户提到'SO',根据映射规则应查询service_order_id字段,包含所有必填字段,日期字段已格式化为字符串"
|
||||
"sql": "SELECT status, category, service_order_id, soid, part_number, bol, dn, po, hawb, prid, CAST(service_order_creation_date AS VARCHAR(2048)) as service_order_creation_date, CAST(po_creation_date AS VARCHAR(2048)) as po_creation_date, CAST(dn_date AS VARCHAR(2048)) as dn_date, CAST(gi_date AS VARCHAR(2048)) as gi_date, CAST(pickup_time AS VARCHAR(2048)) as pickup_time, CAST(flight_etd AS VARCHAR(2048)) as flight_etd, CAST(flight_atd AS VARCHAR(2048)) as flight_atd, CAST(flight_eta AS VARCHAR(2048)) as flight_eta, CAST(flight_ata AS VARCHAR(2048)) as flight_ata, CAST(eta AS VARCHAR(2048)) as eta, CAST(pod AS VARCHAR(2048)) as pod, CAST(gr_date AS VARCHAR(2048)) as gr_date, CAST(status_date AS VARCHAR(2048)) as status_date, CAST(so_eta AS VARCHAR(2048)) as so_eta FROM dwd_ai.apbo_eta_milestone WHERE service_order_id = '4019630464' ORDER BY status_date DESC, service_order_creation_date DESC",
|
||||
"field_selection_reason": "用户提到'SO',根据映射规则应查询service_order_id字段,包含所有必填字段,日期字段已格式化为字符串,status和category固定在最前面两列"
|
||||
}
|
||||
}
|
||||
}
|
||||
@@ -0,0 +1,243 @@
|
||||
{
|
||||
"meta": {
|
||||
"domain": "TP物料多重影响聚合分析",
|
||||
"keywords": [
|
||||
"multiple impact",
|
||||
"tp物料",
|
||||
"topmost_pn",
|
||||
"part_number",
|
||||
"region",
|
||||
"warranty",
|
||||
"ADW",
|
||||
"CLW",
|
||||
"DOA",
|
||||
"FOC",
|
||||
"MDOA",
|
||||
"OBL",
|
||||
"OOW",
|
||||
"OPT",
|
||||
"multipal_impact"
|
||||
],
|
||||
"description": "此模型用于查询 TP 物料多重影响聚合结果。数据已经按 topmost_pn、part_number、region 聚合，并补充各 warranty 类型计数以及总多重影响数 multipal_impact。支持明细展示、汇总统计、TopN 排名等查询方式。",
|
||||
"data_source": "dwd_ai.apbo_eta_multiple_impact"
|
||||
},
|
||||
"data_model_specification": {
|
||||
"fields_list": [
|
||||
"topmost_pn",
|
||||
"part_number",
|
||||
"region",
|
||||
"qty",
|
||||
"ADW",
|
||||
"CLW",
|
||||
"DOA",
|
||||
"FOC",
|
||||
"MDOA",
|
||||
"OBL",
|
||||
"OOW",
|
||||
"OPT",
|
||||
"multipal_impact"
|
||||
],
|
||||
"mandatory_display_fields": {
|
||||
"default_fields": "topmost_pn, part_number, region, qty, ADW, CLW, DOA, FOC, MDOA, OBL, OOW, OPT, multipal_impact",
|
||||
"rule1": "默认展示全部业务字段。",
|
||||
"rule2": "用户明确指定字段时，优先按用户提及顺序展示这些字段。",
|
||||
"rule3": "明细模式默认保留 topmost_pn, part_number, region, qty, multipal_impact 以及相关 warranty 字段。",
|
||||
"rule4": "聚合/TopN 模式仅保留分组维度字段与聚合结果字段。"
|
||||
},
|
||||
"optional_fields": {
|
||||
"identifier_fields": ["topmost_pn", "part_number"],
|
||||
"dimension_fields": ["region"],
|
||||
"metric_fields": ["qty", "multipal_impact", "ADW", "CLW", "DOA", "FOC", "MDOA", "OBL", "OOW", "OPT"],
|
||||
"warranty_metric_fields": ["ADW", "CLW", "DOA", "FOC", "MDOA", "OBL", "OOW", "OPT"]
|
||||
}
|
||||
},
|
||||
"business_logic_rules": {
|
||||
"query_recognition_rules": {
|
||||
"detail_mode_keywords": ["有哪些", "查看", "列出", "显示", "查询", "明细", "详情", "具体"],
|
||||
"aggregate_mode_keywords": ["统计", "汇总", "总数", "有多少", "数量", "count", "计数", "分组", "分布", "sum", "合计"],
|
||||
"topn_mode_keywords": ["top", "前", "排名", "最高", "最大", "最多"],
|
||||
"multiple_impact_keywords": ["multiple impact", "多重影响", "影响数", "multipal impact", "multipal_impact"],
|
||||
"warranty_keywords": ["ADW", "CLW", "DOA", "FOC", "MDOA", "OBL", "OOW", "OPT", "warranty"]
|
||||
},
|
||||
"default_behavior": {
|
||||
"detail_sorting": "multipal_impact DESC, qty DESC, topmost_pn, part_number, region",
|
||||
"aggregate_sorting": "qty DESC",
|
||||
"limit": "用户未要求时默认不加 LIMIT"
|
||||
},
|
||||
"aggregate_rules": {
|
||||
"metric_definitions": {
|
||||
"qty": "SUM(qty)",
|
||||
"multipal_impact": "SUM(multipal_impact)",
|
||||
"ADW": "SUM(ADW)",
|
||||
"CLW": "SUM(CLW)",
|
||||
"DOA": "SUM(DOA)",
|
||||
"FOC": "SUM(FOC)",
|
||||
"MDOA": "SUM(MDOA)",
|
||||
"OBL": "SUM(OBL)",
|
||||
"OOW": "SUM(OOW)",
|
||||
"OPT": "SUM(OPT)"
|
||||
},
|
||||
"group_by_rule": "所有非聚合字段必须出现在 GROUP BY 中。",
|
||||
"default_metric": "SUM(qty) AS qty"
|
||||
},
|
||||
"top_n_rules": {
|
||||
"recognition_triggers": ["top", "前", "排名", "最高", "最大", "最多"],
|
||||
"require_limit": "识别为 TopN 查询时必须使用 LIMIT N。",
|
||||
"default_limit": "用户未明确 N 时默认 LIMIT 10。",
|
||||
"default_order_by": "默认按 qty DESC 或 multipal_impact DESC 排序。"
|
||||
},
|
||||
"alias_usage": "允许用户使用字段别名或业务词汇，生成 SQL 时应映射到真实字段。",
|
||||
"where_field_must_select": "WHERE 中出现的业务字段默认也应出现在 SELECT 中；TopN 聚合查询除外，仅保留维度字段和聚合指标。",
|
||||
"warranty_metric_rule": "ADW、CLW、DOA、FOC、MDOA、OBL、OOW、OPT 均为已聚合的 warranty 计数字段，查询时直接使用，不需要再根据 warranty 字段二次统计。",
|
||||
"multiple_impact_rule": "multipal_impact 为表中现成字段；当用户表达 multiple impact 总量时，优先使用该字段。",
|
||||
"no_legacy_field_rule": "禁止再使用 pal_2h、service_order_id、soid 等旧表结构字段。"
|
||||
},
|
||||
"field_mapping_reference": {
|
||||
"critical_note": "该表已经是聚合结果表，不存在 pal_2h、service_order_id、soid 等旧明细字段。请仅基于 topmost_pn、part_number、region、qty、各 warranty 聚合字段以及 multipal_impact 生成 SQL。",
|
||||
"key_identifiers": {
|
||||
"topmost_pn": {
|
||||
"type": "varchar",
|
||||
"desc": "TP 物料编号",
|
||||
"example": "02HK965",
|
||||
"alias": ["tp", "物料", "物料号", "零件号", "TP物料", "topmost", "topmost pn", "topmost_pn"]
|
||||
},
|
||||
"part_number": {
|
||||
"type": "varchar",
|
||||
"desc": "料号",
|
||||
"example": "5D11J74767",
|
||||
"alias": ["pn", "part number", "part_number", "料号", "零件料号", "部件号"]
|
||||
},
|
||||
"region": {
|
||||
"type": "varchar",
|
||||
"desc": "区域",
|
||||
"example": "ANZ",
|
||||
"alias": ["region", "区域", "大区", "地区"]
|
||||
}
|
||||
},
|
||||
"metric_fields": {
|
||||
"qty": {
|
||||
"type": "bigint",
|
||||
"desc": "当前 topmost_pn + part_number + region 粒度下的订单数量",
|
||||
"alias": ["qty", "数量", "订单数", "记录数", "count"]
|
||||
},
|
||||
"multipal_impact": {
|
||||
"type": "bigint",
|
||||
"desc": "多重影响总数，字段名以表结构为准保留 multipal_impact 拼写",
|
||||
"alias": ["multiple impact", "multiple_impact", "multipal impact", "multipal_impact", "多重影响", "影响数", "总影响数"]
|
||||
},
|
||||
"ADW": {
|
||||
"type": "bigint",
|
||||
"desc": "warranty=ADW 的计数",
|
||||
"alias": ["ADW", "adw"]
|
||||
},
|
||||
"CLW": {
|
||||
"type": "bigint",
|
||||
"desc": "warranty=CLW 的计数",
|
||||
"alias": ["CLW", "clw"]
|
||||
},
|
||||
"DOA": {
|
||||
"type": "bigint",
|
||||
"desc": "warranty=DOA 的计数",
|
||||
"alias": ["DOA", "doa"]
|
||||
},
|
||||
"FOC": {
|
||||
"type": "bigint",
|
||||
"desc": "warranty=FOC 的计数",
|
||||
"alias": ["FOC", "foc"]
|
||||
},
|
||||
"MDOA": {
|
||||
"type": "bigint",
|
||||
"desc": "warranty=MDOA 的计数",
|
||||
"alias": ["MDOA", "mdoa"]
|
||||
},
|
||||
"OBL": {
|
||||
"type": "bigint",
|
||||
"desc": "warranty=OBL 的计数",
|
||||
"alias": ["OBL", "obl"]
|
||||
},
|
||||
"OOW": {
|
||||
"type": "bigint",
|
||||
"desc": "warranty=OOW 的计数",
|
||||
"alias": ["OOW", "oow"]
|
||||
},
|
||||
"OPT": {
|
||||
"type": "bigint",
|
||||
"desc": "warranty=OPT 的计数",
|
||||
"alias": ["OPT", "opt"]
|
||||
}
|
||||
},
|
||||
"condition_mapping": {
|
||||
"有multiple impact": "multipal_impact > 0",
|
||||
"有多重影响": "multipal_impact > 0",
|
||||
"有qty": "qty > 0",
|
||||
"有ADW": "ADW > 0",
|
||||
"有CLW": "CLW > 0",
|
||||
"有DOA": "DOA > 0",
|
||||
"有FOC": "FOC > 0",
|
||||
"有MDOA": "MDOA > 0",
|
||||
"有OBL": "OBL > 0",
|
||||
"有OOW": "OOW > 0",
|
||||
"有OPT": "OPT > 0"
|
||||
}
|
||||
},
|
||||
"examples": {
|
||||
"detail_mode_examples": {
|
||||
"example1": {
|
||||
"user": "列出 topmost_pn 为 02HK965 的 multiple impact 明细",
|
||||
"mode": "detail_mode",
|
||||
"sql": "SELECT topmost_pn, part_number, region, qty, ADW, CLW, DOA, FOC, MDOA, OBL, OOW, OPT, multipal_impact FROM dwd_ai.apbo_eta_multiple_impact WHERE topmost_pn = '02HK965' ORDER BY multipal_impact DESC, qty DESC, topmost_pn, part_number, region"
|
||||
},
|
||||
"example2": {
|
||||
"user": "查看 region 为 ANZ 且 ADW 有值的记录",
|
||||
"mode": "detail_mode",
|
||||
"sql": "SELECT region, ADW, topmost_pn, part_number, qty, CLW, DOA, FOC, MDOA, OBL, OOW, OPT, multipal_impact FROM dwd_ai.apbo_eta_multiple_impact WHERE region = 'ANZ' AND ADW > 0 ORDER BY multipal_impact DESC, qty DESC, topmost_pn, part_number, region"
|
||||
},
|
||||
"example3": {
|
||||
"user": "查询 pn 为 5D11J74767 的 TP 物料影响",
|
||||
"mode": "detail_mode",
|
||||
"sql": "SELECT part_number, topmost_pn, region, qty, ADW, CLW, DOA, FOC, MDOA, OBL, OOW, OPT, multipal_impact FROM dwd_ai.apbo_eta_multiple_impact WHERE part_number = '5D11J74767' ORDER BY multipal_impact DESC, qty DESC, topmost_pn, part_number, region"
|
||||
}
|
||||
},
|
||||
"aggregate_mode_examples": {
|
||||
"example1": {
|
||||
"user": "按 region 统计 multiple impact 数量",
|
||||
"mode": "aggregate_mode",
|
||||
"sql": "SELECT region, SUM(multipal_impact) AS multipal_impact, SUM(qty) AS qty FROM dwd_ai.apbo_eta_multiple_impact GROUP BY region ORDER BY multipal_impact DESC, qty DESC"
|
||||
},
|
||||
"example2": {
|
||||
"user": "按 topmost_pn 汇总 ADW 和 DOA 数量",
|
||||
"mode": "aggregate_mode",
|
||||
"sql": "SELECT topmost_pn, SUM(ADW) AS ADW, SUM(DOA) AS DOA, SUM(multipal_impact) AS multipal_impact FROM dwd_ai.apbo_eta_multiple_impact GROUP BY topmost_pn ORDER BY multipal_impact DESC, ADW DESC, DOA DESC"
|
||||
},
|
||||
"example3": {
|
||||
"user": "统计 ANZ 区域各 part number 的 qty",
|
||||
"mode": "aggregate_mode",
|
||||
"sql": "SELECT part_number, SUM(qty) AS qty FROM dwd_ai.apbo_eta_multiple_impact WHERE region = 'ANZ' GROUP BY part_number ORDER BY qty DESC"
|
||||
}
|
||||
},
|
||||
"topn_examples": {
|
||||
"example1": {
|
||||
"user": "按 topmost_pn 查询 top 10 multiple impact",
|
||||
"mode": "topn_mode",
|
||||
"sql": "SELECT topmost_pn, SUM(multipal_impact) AS multipal_impact FROM dwd_ai.apbo_eta_multiple_impact GROUP BY topmost_pn ORDER BY multipal_impact DESC LIMIT 10"
|
||||
},
|
||||
"example2": {
|
||||
"user": "by region top 5 qty",
|
||||
"mode": "topn_mode",
|
||||
"sql": "SELECT region, SUM(qty) AS qty FROM dwd_ai.apbo_eta_multiple_impact GROUP BY region ORDER BY qty DESC LIMIT 5"
|
||||
}
|
||||
},
|
||||
"edge_cases": {
|
||||
"example1": {
|
||||
"user": "有多少个 region 有 OOW 影响",
|
||||
"mode": "aggregate_mode",
|
||||
"sql": "SELECT region, SUM(OOW) AS OOW FROM dwd_ai.apbo_eta_multiple_impact WHERE OOW > 0 GROUP BY region ORDER BY OOW DESC"
|
||||
},
|
||||
"example2": {
|
||||
"user": "查看所有 warranty 字段的记录详情",
|
||||
"mode": "detail_mode",
|
||||
"sql": "SELECT topmost_pn, part_number, region, ADW, CLW, DOA, FOC, MDOA, OBL, OOW, OPT, qty, multipal_impact FROM dwd_ai.apbo_eta_multiple_impact ORDER BY multipal_impact DESC, qty DESC, topmost_pn, part_number, region"
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
@@ -0,0 +1,263 @@
|
||||
{
|
||||
"meta": {
|
||||
"domain": "亚太区物料库存与用量分析",
|
||||
"keywords": ["库存", "用量", "物料分析", "亚太区", "国家用量", "历史使用量", "近期用量", "premier", "qty", "数量"],
|
||||
"description": "此模型用于分析亚太地区各物料在不同区域、配送中心的国家用量统计。国家字段(AU, VN, JP等)是数值型用量字段，表示该物料在该国家的历史用量，不是国家代码。",
|
||||
"data_source": "dwd_ai.apbo_eta_region_report"
|
||||
},
|
||||
"data_model_specification": {
|
||||
"fields_list": [
|
||||
"topmost_pn", "region", "commodity_code", "dc_plant", "premier", "qty",
|
||||
"AU", "NZ", "LK", "VN", "JP", "HK", "SG", "TH", "PH", "IN", "BN", "NP", "BD", "KR", "ID", "FJ", "MY", "TW",
|
||||
"etl_time"
|
||||
],
|
||||
|
||||
"core_country_fields": {
|
||||
"list": ["AU", "NZ", "LK", "VN", "JP", "HK", "SG", "TH", "PH", "IN", "BN", "NP", "BD", "KR", "ID", "FJ", "MY", "TW"],
|
||||
"meaning": "各国家的总使用量计数，字段类型为BIGINT。这些字段表示该物料在该国家的历史用量值。",
|
||||
"critical_notes": "这些字段是数值型用量字段，不是国家代码。例如：VN字段表示物料在越南的历史使用量数值，不是字符串'VN'。"
|
||||
},
|
||||
|
||||
"mandatory_display_fields": {
|
||||
"rule1": "默认查询所有字段（SELECT *）",
|
||||
"rule2": "当用户明确指定某些字段时，只查询这些字段，并保持用户提到的顺序",
|
||||
"rule3": "WHERE条件中使用的所有字段（除了国家字段的数值比较外），必须在SELECT子句中展示",
|
||||
"rule4": "国家字段是数值型，直接展示数值，不需要特殊处理",
|
||||
"rule5": "select的所有字段必须用``包裹，如select `IN`，防止与SQL关键字冲突",
|
||||
"actual_fields_order": [
|
||||
"topmost_pn", "region", "commodity_code", "dc_plant", "premier", "qty",
|
||||
"AU", "NZ", "LK", "VN", "JP", "HK", "SG", "TH", "PH", "IN", "BN", "NP", "BD", "KR", "ID", "FJ", "MY", "TW",
|
||||
"etl_time"
|
||||
]
|
||||
}
|
||||
},
|
||||
"business_logic_rules": {
|
||||
"query_recognition_rules": {
|
||||
"material_keywords": ["物料", "topmost_pn", "物料号", "零件号", "Part Number", "PN", "topmost"],
|
||||
"region_keywords": ["region", "区域", "大区", "地区", "Region Code", "CAP", "ANZ", "JP"],
|
||||
"commodity_keywords": ["commodity_code", "商品代码", "编码", "物料分类", "Commodity Code", "CC"],
|
||||
"premier_keywords": ["premier", "优质", "优先", "Premier服务"],
|
||||
"qty_keywords": ["qty", "数量", "总量", "计数", "count"]
|
||||
},
|
||||
|
||||
"default_filters": {
|
||||
"rule": "默认不添加任何WHERE条件，除非用户明确要求",
|
||||
"examples": [
|
||||
"不要添加WHERE region = 'CAP'（除非用户明确要求）",
|
||||
"不要添加WHERE qty > 0（除非用户明确要求）"
|
||||
]
|
||||
},
|
||||
|
||||
"country_field_handling": {
|
||||
"important_note": "国家字段(AU, VN, JP等)是数值型BIGINT，表示该物料在该国家的使用量计数",
|
||||
"critical_warning": "绝对不要将这些字段作为字符串处理，不要使用单引号，不要使用LIKE操作符",
|
||||
"correct_usage": {
|
||||
"pattern": "国家用量大于{值} → {国家字段} > {value}",
|
||||
"examples": [
|
||||
"VN用量超过100 → VN > 100",
|
||||
"有澳大利亚用量 → AU > 0",
|
||||
"没有日本用量 → JP = 0"
|
||||
]
|
||||
},
|
||||
"incorrect_usage": {
|
||||
"pattern": "错误用法示例",
|
||||
"examples": [
|
||||
"WHERE VN = 'VN' (错误：VN是数值，不是字符串)",
|
||||
"WHERE JP LIKE '%JP%' (错误：JP是数值，不支持LIKE)",
|
||||
"WHERE AU IN ('AU', 'NZ') (错误：AU是数值，不是枚举)"
|
||||
]
|
||||
}
|
||||
},
|
||||
|
||||
"sorting": {
|
||||
"default": "ORDER BY qty DESC",
|
||||
"alternatives": {
|
||||
"by_premier": "ORDER BY premier DESC",
|
||||
"by_country_usage": "ORDER BY {country_field} DESC (如 ORDER BY VN DESC)"
|
||||
}
|
||||
},
|
||||
|
||||
"limit_rule": {
|
||||
"rule": "禁止使用LIMIT",
|
||||
"exception": "除非用户明确要求Top N"
|
||||
}
|
||||
},
|
||||
"field_mapping_reference": {
|
||||
"critical_note": "此表包含亚太地区各物料的国家用量统计数据。国家字段(AU, VN, JP等)是数值型BIGINT，表示使用量计数，不是国家代码。",
|
||||
|
||||
"material_identifier_fields": {
|
||||
"topmost_pn": {
|
||||
"type": "string",
|
||||
"desc": "顶级物料号，物料的唯一标识",
|
||||
"example": "5CB1L57599",
|
||||
"alias": ["物料号", "零件号", "Part Number", "PN", "topmost", "物料编码"]
|
||||
},
|
||||
"commodity_code": {
|
||||
"type": "string",
|
||||
"desc": "商品代码，物料分类标识",
|
||||
"example": "LF",
|
||||
"alias": ["商品编码", "物料分类", "Commodity Code", "CC", "编码", "商品类别"]
|
||||
}
|
||||
},
|
||||
|
||||
"geographic_dimension_fields": {
|
||||
"region": {
|
||||
"type": "string",
|
||||
"desc": "区域划分：CAP(亚太区)、ANZ(澳新)、JP(日本)",
|
||||
"example": "CAP",
|
||||
"values": ["CAP", "ANZ", "JP"],
|
||||
"alias": ["区域", "大区", "Region", "地区", "地理区域"]
|
||||
},
|
||||
"dc_plant": {
|
||||
"type": "string",
|
||||
"desc": "配送中心/工厂代码",
|
||||
"example": "HKGDC",
|
||||
"alias": ["工厂", "配送中心", "plant", "DC", "发货中心", "Distribution Center"]
|
||||
}
|
||||
},
|
||||
|
||||
"metrics_fields": {
|
||||
"premier": {
|
||||
"type": "bigint",
|
||||
"desc": "Premier服务的订单数量",
|
||||
"alias": ["优质服务", "优先服务", "Premier数量", "Premier订单"]
|
||||
},
|
||||
"qty": {
|
||||
"type": "bigint",
|
||||
"desc": "总数量/总计数",
|
||||
"alias": ["数量", "总量", "计数", "count", "总数"]
|
||||
}
|
||||
},
|
||||
|
||||
"country_usage_fields": {
|
||||
"important_note": "以下所有字段都是数值型(BIGINT)，表示该物料在该国家的历史使用量计数，不是国家代码。这些字段支持数值比较操作(>, <, >=, <=, =, !=)。",
|
||||
"critical_warning": "绝对不要将这些字段作为字符串处理，不要使用单引号，不要使用LIKE操作符。",
|
||||
|
||||
"AU": {
|
||||
"type": "bigint",
|
||||
"desc": "澳大利亚的使用量计数",
|
||||
"alias": ["澳大利亚", "澳洲", "AU用量", "Australia用量"]
|
||||
},
|
||||
"NZ": {
|
||||
"type": "bigint",
|
||||
"desc": "新西兰的使用量计数",
|
||||
"alias": ["新西兰", "NZ用量", "New Zealand用量"]
|
||||
},
|
||||
"LK": {
|
||||
"type": "bigint",
|
||||
"desc": "斯里兰卡的使用量计数",
|
||||
"alias": ["斯里兰卡", "LK用量", "Sri Lanka用量"]
|
||||
},
|
||||
"VN": {
|
||||
"type": "bigint",
|
||||
"desc": "越南的使用量计数",
|
||||
"alias": ["越南", "VN用量", "Vietnam用量"]
|
||||
},
|
||||
"JP": {
|
||||
"type": "bigint",
|
||||
"desc": "日本的使用量计数",
|
||||
"alias": ["日本", "JP用量", "Japan用量"]
|
||||
},
|
||||
"HK": {
|
||||
"type": "bigint",
|
||||
"desc": "香港的使用量计数",
|
||||
"alias": ["香港", "HK用量", "Hong Kong用量"]
|
||||
},
|
||||
"SG": {
|
||||
"type": "bigint",
|
||||
"desc": "新加坡的使用量计数",
|
||||
"alias": ["新加坡", "SG用量", "Singapore用量"]
|
||||
},
|
||||
"TH": {
|
||||
"type": "bigint",
|
||||
"desc": "泰国的使用量计数",
|
||||
"alias": ["泰国", "TH用量", "Thailand用量"]
|
||||
},
|
||||
"PH": {
|
||||
"type": "bigint",
|
||||
"desc": "菲律宾的使用量计数",
|
||||
"alias": ["菲律宾", "PH用量", "Philippines用量"]
|
||||
},
|
||||
"IN": {
|
||||
"type": "bigint",
|
||||
"desc": "印度的使用量计数",
|
||||
"alias": ["印度", "IN用量", "India用量"]
|
||||
},
|
||||
"BN": {
|
||||
"type": "bigint",
|
||||
"desc": "文莱的使用量计数",
|
||||
"alias": ["文莱", "BN用量", "Brunei用量"]
|
||||
},
|
||||
"NP": {
|
||||
"type": "bigint",
|
||||
"desc": "尼泊尔的使用量计数",
|
||||
"alias": ["尼泊尔", "NP用量", "Nepal用量"]
|
||||
},
|
||||
"BD": {
|
||||
"type": "bigint",
|
||||
"desc": "孟加拉国的使用量计数",
|
||||
"alias": ["孟加拉国", "BD用量", "Bangladesh用量"]
|
||||
},
|
||||
"KR": {
|
||||
"type": "bigint",
|
||||
"desc": "韩国的使用量计数",
|
||||
"alias": ["韩国", "KR用量", "Korea用量"]
|
||||
},
|
||||
"ID": {
|
||||
"type": "bigint",
|
||||
"desc": "印度尼西亚的使用量计数",
|
||||
"alias": ["印度尼西亚", "印尼", "ID用量", "Indonesia用量"]
|
||||
},
|
||||
"FJ": {
|
||||
"type": "bigint",
|
||||
"desc": "斐济的使用量计数",
|
||||
"alias": ["斐济", "FJ用量", "Fiji用量"]
|
||||
},
|
||||
"MY": {
|
||||
"type": "bigint",
|
||||
"desc": "马来西亚的使用量计数",
|
||||
"alias": ["马来西亚", "MY用量", "Malaysia用量"]
|
||||
},
|
||||
"TW": {
|
||||
"type": "bigint",
|
||||
"desc": "台湾的使用量计数",
|
||||
"alias": ["台湾", "TW用量", "Taiwan用量"]
|
||||
}
|
||||
},
|
||||
|
||||
"system_field": {
|
||||
"etl_time": {
|
||||
"type": "timestamp",
|
||||
"desc": "ETL更新时间",
|
||||
"alias": ["更新时间", "ETL时间", "数据更新时间"]
|
||||
}
|
||||
}
|
||||
},
|
||||
"query_examples": {
|
||||
"simple_query": {
|
||||
"user": "region为CAP的物料",
|
||||
"sql": "SELECT * FROM dwd_ai.apbo_eta_region_report WHERE region = 'CAP' ORDER BY qty DESC",
|
||||
"field_selection_reason": "用户没有指定字段，默认查询所有字段。WHERE条件包含region过滤。"
|
||||
},
|
||||
"country_usage_query": {
|
||||
"user": "VN用量超过100的物料",
|
||||
"sql": "SELECT * FROM dwd_ai.apbo_eta_region_report WHERE VN > 100 ORDER BY qty DESC",
|
||||
"field_selection_reason": "用户没有指定字段，默认查询所有字段。WHERE条件包含VN数值过滤。"
|
||||
},
|
||||
"premier_query": {
|
||||
"user": "有Premier服务的物料",
|
||||
"sql": "SELECT * FROM dwd_ai.apbo_eta_region_report WHERE premier > 0 ORDER BY premier DESC",
|
||||
"field_selection_reason": "用户没有指定字段，默认查询所有字段。WHERE条件包含premier数值过滤。"
|
||||
},
|
||||
"multi_country_query": {
|
||||
"user": "有VN和AU用量的物料",
|
||||
"sql": "SELECT topmost_pn, VN, AU FROM dwd_ai.apbo_eta_region_report WHERE VN > 0 AND AU > 0 ORDER BY qty DESC",
|
||||
"field_selection_reason": "用户指定了topmost_pn、VN、AU字段，只查询这些字段。WHERE条件包含VN和AU数值过滤。"
|
||||
},
|
||||
"zero_usage_query": {
|
||||
"user": "没有VN用量的物料",
|
||||
"sql": "SELECT * FROM dwd_ai.apbo_eta_region_report WHERE VN = 0 ORDER BY qty DESC",
|
||||
"field_selection_reason": "用户明确要求'没有VN用量的'，所以添加VN = 0条件。默认查询所有字段。"
|
||||
}
|
||||
}
|
||||
}
|
||||
@@ -0,0 +1,170 @@
|
||||
{
|
||||
"meta": {
|
||||
"domain": "亚太区物料用量与库存(按国家)分析",
|
||||
"keywords": ["库存", "用量", "物料分析", "亚太区", "国家", "IB", "库存数量", "usage", "ship_to_country"],
|
||||
"description": "此模型用于分析亚太地区各物料在不同区域、配送中心及目的地国家的库存与用量信息。表已在SQL层完成聚合与关联，包含国家维度(ship_to_country)及分组用量/库存字段。",
|
||||
"data_source": "dwd_ai.apbo_eta_usage_ib_report"
|
||||
},
|
||||
"data_model_specification": {
|
||||
"fields_list": [
|
||||
"topmost_pn", "region", "commodity_code", "dc_plant", "ship_to_country",
|
||||
"location_name", "usage_qty_8_week_by_group", "usage_qty_52_week_by_group",
|
||||
"total_history_usage_by_group", "group_current_ib"
|
||||
],
|
||||
"mandatory_display_fields": {
|
||||
"required_fields": "topmost_pn, region, commodity_code, dc_plant, ship_to_country, location_name",
|
||||
"rule1": "默认查询所有字段（SELECT *）",
|
||||
"rule2": "当用户明确指定某些字段时，只查询这些字段，但必须始终包含required_fields，并保持用户提到的顺序",
|
||||
"rule3": "WHERE条件中使用的所有字段，必须在SELECT子句中展示",
|
||||
"rule4": "select的所有字段必须用``包裹，避免关键字冲突"
|
||||
}
|
||||
},
|
||||
"business_logic_rules": {
|
||||
"query_recognition_rules": {
|
||||
"material_keywords": ["物料", "topmost_pn", "物料号", "零件号", "Part Number", "PN"],
|
||||
"region_keywords": ["region", "区域", "大区", "地区", "Region Code", "CAP", "EMEA", "AMER"],
|
||||
"commodity_keywords": ["commodity_code", "商品代码", "编码", "物料分类", "Commodity Code", "CC"],
|
||||
"inventory_keywords": ["库存", "ib", "库存数量", "库存量", "Inventory Balance"],
|
||||
"usage_keywords": ["用量", "使用量", "历史用量", "近期用量", "usage", "使用数量"],
|
||||
"location_keywords": ["dc_plant", "plant", "配送中心", "工厂", "location", "地点"],
|
||||
"country_keywords": ["country", "国家", "ship_to_country", "收货国", "目的地国家"]
|
||||
},
|
||||
"field_selection_logic": {
|
||||
"priority_order": [
|
||||
{
|
||||
"level": 1,
|
||||
"name": "用户明确指定的字段",
|
||||
"rule": "精确添加用户提到的字段，按用户问题中出现的顺序排列；无论用户是否提及，都必须包含required_fields"
|
||||
},
|
||||
{
|
||||
"level": 2,
|
||||
"name": "默认字段选择",
|
||||
"rule": "如果用户没有明确指定字段，默认查询所有字段（SELECT *）"
|
||||
}
|
||||
],
|
||||
"where_condition_fields_must_in_select": {
|
||||
"rule": "WHERE条件中使用的所有字段必须在SELECT子句中展示",
|
||||
"purpose": "确保查询结果的完整性，用户能看到过滤依据"
|
||||
}
|
||||
},
|
||||
"where_condition_generation": {
|
||||
"strict_rule": "只生成用户明确要求的过滤条件，不添加任何默认或假设的条件",
|
||||
"condition_types": {
|
||||
"exact_match": {
|
||||
"pattern": "{字段}为{值}",
|
||||
"sql": "{field} = '{value}'"
|
||||
},
|
||||
"range_filter": {
|
||||
"pattern": ["大于{值}", "超过{值}", "少于{值}", "小于{值}", "不低于{值}", "不超过{值}"],
|
||||
"sql_mapping": {
|
||||
"大于{值}": "{field} > {value}",
|
||||
"超过{值}": "{field} >= {value}",
|
||||
"少于{值}": "{field} < {value}",
|
||||
"小于{值}": "{field} < {value}",
|
||||
"不低于{值}": "{field} >= {value}",
|
||||
"不超过{值}": "{field} <= {value}"
|
||||
}
|
||||
},
|
||||
"multiple_conditions": {
|
||||
"pattern": ["且", "并且", "和", "同时", ","],
|
||||
"sql": "AND"
|
||||
}
|
||||
},
|
||||
"no_default_conditions": {
|
||||
"rule": "绝对不添加任何用户没有明确要求的WHERE条件"
|
||||
}
|
||||
},
|
||||
"default_behavior": {
|
||||
"sorting": "默认按group_current_ib(库存数量)降序排列：ORDER BY group_current_ib DESC",
|
||||
"limit": "禁止使用limit",
|
||||
"select_all": "默认查询所有字段：SELECT *",
|
||||
"field_order": "required_fields始终置前，其次按用户提到的顺序排列字段"
|
||||
}
|
||||
},
|
||||
"field_mapping_reference": {
|
||||
"critical_note": "此表为按国家维度的用量与库存报表，ship_to_country为国家代码维度字段，不是数值字段。用量与库存字段为数值型，支持比较运算。",
|
||||
"dimension_fields": {
|
||||
"topmost_pn": {
|
||||
"type": "string",
|
||||
"desc": "顶级物料号，物料唯一标识",
|
||||
"alias": ["物料号", "零件号", "Part Number", "PN", "topmost"]
|
||||
},
|
||||
"region": {
|
||||
"type": "string",
|
||||
"desc": "区域划分",
|
||||
"alias": ["区域", "大区", "Region", "地区"]
|
||||
},
|
||||
"commodity_code": {
|
||||
"type": "string",
|
||||
"desc": "商品代码",
|
||||
"alias": ["商品编码", "物料分类", "Commodity Code", "CC"]
|
||||
},
|
||||
"dc_plant": {
|
||||
"type": "string",
|
||||
"desc": "配送中心/工厂代码",
|
||||
"alias": ["工厂", "配送中心", "plant", "DC"]
|
||||
},
|
||||
"ship_to_country": {
|
||||
"type": "string",
|
||||
"desc": "目的地国家代码",
|
||||
"alias": ["country", "国家", "收货国", "目的地国家"]
|
||||
},
|
||||
"location_name": {
|
||||
"type": "string",
|
||||
"desc": "地点名称",
|
||||
"alias": ["地点名称", "location", "地点"]
|
||||
}
|
||||
},
|
||||
"metric_fields": {
|
||||
"usage_qty_8_week_by_group": {
|
||||
"type": "bigint",
|
||||
"desc": "近8周用量"
|
||||
},
|
||||
"usage_qty_52_week_by_group": {
|
||||
"type": "bigint",
|
||||
"desc": "近52周用量"
|
||||
},
|
||||
"total_history_usage_by_group": {
|
||||
"type": "bigint",
|
||||
"desc": "历史总用量"
|
||||
},
|
||||
"group_current_ib": {
|
||||
"type": "bigint",
|
||||
"desc": "当前库存数量"
|
||||
}
|
||||
},
|
||||
"time_fields": {}
|
||||
},
|
||||
"examples": {
|
||||
"simple_query_all_fields": {
|
||||
"user": "region为CAP的数据",
|
||||
"sql": "SELECT * FROM dwd_ai.apbo_eta_usage_ib_report WHERE region = 'CAP' ORDER BY group_current_ib DESC",
|
||||
"field_selection_reason": "用户没有指定字段，默认查询所有字段。"
|
||||
},
|
||||
"query_by_country": {
|
||||
"user": "country为VN的用量和库存",
|
||||
"sql": "SELECT `ship_to_country`, `usage_qty_8_week_by_group`, `usage_qty_52_week_by_group`, `total_history_usage_by_group`, `group_current_ib` FROM dwd_ai.apbo_eta_usage_ib_report WHERE ship_to_country = 'VN' ORDER BY group_current_ib DESC",
|
||||
"field_selection_reason": "用户指定国家维度与用量/库存字段，按用户顺序输出"
|
||||
},
|
||||
"query_specific_fields": {
|
||||
"user": "查看物料号、库存和近8周用量",
|
||||
"sql": "SELECT `topmost_pn`, `group_current_ib`, `usage_qty_8_week_by_group` FROM dwd_ai.apbo_eta_usage_ib_report ORDER BY group_current_ib DESC",
|
||||
"field_selection_reason": "用户明确指定字段，仅输出这些字段"
|
||||
},
|
||||
"query_usage_and_ib_with_required_fields": {
|
||||
"user": "查看usage和ib",
|
||||
"sql": "SELECT `topmost_pn`, `region`, `commodity_code`, `dc_plant`, `ship_to_country`, `location_name`, `usage_qty_8_week_by_group`, `usage_qty_52_week_by_group`, `total_history_usage_by_group`, `group_current_ib` FROM dwd_ai.apbo_eta_usage_ib_report ORDER BY group_current_ib DESC",
|
||||
"field_selection_reason": "用户仅提到usage和ib，但必须始终包含required_fields"
|
||||
},
|
||||
"query_with_multiple_conditions": {
|
||||
"user": "region为CAP且commodity_code为LF，库存大于500",
|
||||
"sql": "SELECT * FROM dwd_ai.apbo_eta_usage_ib_report WHERE region = 'CAP' AND commodity_code = 'LF' AND group_current_ib > 500 ORDER BY group_current_ib DESC",
|
||||
"field_selection_reason": "用户没有指定字段，默认查询所有字段，包含多条件过滤"
|
||||
},
|
||||
"query_with_etl_time": {
|
||||
"user": "查看CAP库存",
|
||||
"sql": "SELECT `region`, `group_current_ib` FROM dwd_ai.apbo_eta_usage_ib_report WHERE region = 'CAP' ORDER BY group_current_ib DESC",
|
||||
"field_selection_reason": "不展示系统时间字段，仅展示业务字段"
|
||||
}
|
||||
}
|
||||
}
|
||||
@@ -1,431 +0,0 @@
|
||||
{
|
||||
"meta": {
|
||||
"domain": "亚太区物料库存与用量分析",
|
||||
"keywords": ["库存", "用量", "物料分析", "亚太区", "国家用量", "历史使用量", "近期用量", "IB", "库存数量"],
|
||||
"description": "此模型用于分析亚太地区各物料在不同区域,配送中心及目的地国家的库存情况,近期用量及历史使用量。特别注意：国家字段(AU, VN, JP等)是数值型用量字段，表示该物料在该国家的历史用量，不是国家代码。",
|
||||
"data_source": "dwd_ai.apbo_region_usage_ib_report"
|
||||
},
|
||||
"data_model_specification": {
|
||||
"fields_list": ["topmost_pn", "region", "commodity_code", "dc_plant", "country_total_cnt", "AU", "NZ", "LK", "VN", "JP", "HK", "SG", "TH", "PH", "IN", "BN", "NP", "BD", "KR", "ID", "FJ", "MY", "TW", "location_name", "ib", "usage_qty_8_week", "usage_qty_52_week", "total_history_usage"],
|
||||
|
||||
"core_country_fields": {
|
||||
"list": ["AU", "NZ", "LK", "VN", "JP", "HK", "SG", "TH", "PH", "IN", "BN", "NP", "BD", "KR", "ID", "FJ", "MY", "TW"],
|
||||
"meaning": "各国家过去某几周的总使用量,字段类型为BIGINT.这些字段表示该物料在该国家的历史用量值.",
|
||||
"critical_notes": "这些字段是数值型用量字段，不是国家代码。例如：VN字段表示物料在越南的历史使用量数值，不是字符串'VN'。"
|
||||
},
|
||||
|
||||
"mandatory_display_fields": {
|
||||
"rule1": "默认查询所有字段（SELECT *）",
|
||||
"rule2": "当用户明确指定某些字段时，只查询这些字段，并保持用户提到的顺序",
|
||||
"rule3": "WHERE条件中使用的所有字段（除了国家字段的数值比较外），必须在SELECT子句中展示",
|
||||
"rule4": "国家字段是数值型，直接展示数值，不需要特殊处理",
|
||||
"rule5": "select的所有字段必须用``包裹，如select `IN`，防止与SQL关键字冲突",
|
||||
"actual_fields_order": ["topmost_pn", "region", "commodity_code", "dc_plant", "country_total_cnt", "AU", "NZ", "LK", "VN", "JP", "HK", "SG", "TH", "PH", "IN", "BN", "NP", "BD", "KR", "ID", "FJ", "MY", "TW", "location_name", "ib", "usage_qty_8_week", "usage_qty_52_week", "total_history_usage"]
|
||||
}
|
||||
},
|
||||
"business_logic_rules": {
|
||||
"query_recognition_rules": {
|
||||
"material_keywords": ["物料", "topmost_pn", "物料号", "零件号", "Part Number", "PN"],
|
||||
"region_keywords": ["region", "区域", "大区", "地区", "Region Code", "CAP", "EMEA", "AMER"],
|
||||
"commodity_keywords": ["commodity_code", "商品代码", "编码", "物料分类", "Commodity Code", "CC"],
|
||||
"inventory_keywords": ["库存", "ib", "库存数量", "库存量", "Inventory Balance"],
|
||||
"usage_keywords": ["用量", "使用量", "历史用量", "近期用量", "usage", "使用数量"],
|
||||
"location_keywords": ["dc_plant", "plant", "配送中心", "工厂", "location", "地点"],
|
||||
"country_usage_keywords": ["国家用量", "国家使用量", "country usage", "国家用量分析"],
|
||||
"specific_country_keywords": {
|
||||
"AU": ["澳大利亚", "澳洲", "AU", "Australia"],
|
||||
"VN": ["越南", "VN", "Vietnam"],
|
||||
"JP": ["日本", "JP", "Japan"],
|
||||
"HK": ["香港", "HK", "Hong Kong"],
|
||||
"SG": ["新加坡", "SG", "Singapore"],
|
||||
"TH": ["泰国", "TH", "Thailand"],
|
||||
"IN": ["印度", "IN", "India"],
|
||||
"KR": ["韩国", "KR", "Korea"],
|
||||
"ID": ["印度尼西亚", "印尼", "ID", "Indonesia"],
|
||||
"MY": ["马来西亚", "MY", "Malaysia"],
|
||||
"TW": ["台湾", "TW", "Taiwan"],
|
||||
"NZ": ["新西兰", "NZ", "New Zealand"],
|
||||
"PH": ["菲律宾", "PH", "Philippines"]
|
||||
}
|
||||
},
|
||||
|
||||
"country_field_interpretation": {
|
||||
"fundamental_rule": "国家字段(AU, VN, JP等)是数值型用量字段(BIGINT)，表示该物料在该国家的历史用量，不是国家代码",
|
||||
"correct_usage": {
|
||||
"in_select": "直接展示数值，如：SELECT AU, VN, JP",
|
||||
"in_where": "不需要添加任何默认过滤条件，除非用户明确要求",
|
||||
"as_numeric": "作为数值字段处理，支持比较运算符：>, <, >=, <=, ="
|
||||
},
|
||||
"incorrect_usage": [
|
||||
"WHERE VN = 'VN' (错误：VN是数值字段，不是字符串)",
|
||||
"WHERE VN LIKE '%VN%' (错误：VN是数值字段，不支持LIKE)",
|
||||
"WHERE VN IN ('VN', 'AU') (错误：VN是数值字段，不是枚举值)"
|
||||
],
|
||||
"user_intent_interpretation": {
|
||||
"当用户说'country为VN'": "用户只是提到VN字段，但不一定要求VN>0，不需要添加过滤条件",
|
||||
"当用户说'VN国家'": "用户指的是VN字段，按字段处理",
|
||||
"当用户说'有VN用量的物料'": "需要添加WHERE VN > 0",
|
||||
"当用户说'VN用量超过100'": "需要添加WHERE VN >= 100",
|
||||
"当用户说'VN用量为0'": "需要添加WHERE VN = 0",
|
||||
"当用户说'没有VN用量的'": "需要添加WHERE VN = 0"
|
||||
}
|
||||
},
|
||||
|
||||
"field_selection_logic": {
|
||||
"priority_order": [
|
||||
{
|
||||
"level": 1,
|
||||
"name": "用户明确指定的字段",
|
||||
"rule": "精确添加用户提到的字段，按用户问题中出现的顺序排列，不添加未提及的字段"
|
||||
},
|
||||
{
|
||||
"level": 2,
|
||||
"name": "默认字段选择",
|
||||
"rule": "如果用户没有明确指定字段，默认查询所有字段（SELECT *）"
|
||||
}
|
||||
],
|
||||
|
||||
"where_condition_fields_must_in_select": {
|
||||
"rule": "WHERE条件中使用的所有字段（除了国家字段的数值比较外），必须在SELECT子句中展示",
|
||||
"purpose": "确保查询结果的完整性，用户能看到过滤依据",
|
||||
"examples": [
|
||||
"用户说'region为CAP的数据' → SELECT * ... WHERE region = 'CAP'",
|
||||
"用户说'ib大于500的物料号' → SELECT topmost_pn, ib ... WHERE ib > 500",
|
||||
"用户说'region为CAP且commodity_code为LF的物料号' → SELECT topmost_pn, region, commodity_code ... WHERE region = 'CAP' AND commodity_code = 'LF'"
|
||||
]
|
||||
}
|
||||
},
|
||||
|
||||
"where_condition_generation": {
|
||||
"strict_rule": "只生成用户明确要求的过滤条件，不添加任何默认或假设的条件",
|
||||
"condition_types": {
|
||||
"exact_match": {
|
||||
"pattern": "{字段}为{值}",
|
||||
"sql": "{field} = '{value}'",
|
||||
"examples": ["region为CAP → region = 'CAP'", "commodity_code为LF → commodity_code = 'LF'", "dc_plant为HKGDC → dc_plant = 'HKGDC'"]
|
||||
},
|
||||
"country_field_handling": {
|
||||
"important_note": "当用户提到'country为VN'时，不需要在WHERE中添加VN > 0，除非用户明确要求过滤用量",
|
||||
"correct_interpretation": "用户只是提到VN字段，但没有要求过滤VN的值",
|
||||
"only_add_filter_when": [
|
||||
"用户明确说'有VN用量的' → WHERE VN > 0",
|
||||
"用户明确说'VN用量大于0的' → WHERE VN > 0",
|
||||
"用户明确说'VN超过100的' → WHERE VN >= 100",
|
||||
"用户明确说'VN用量为0的' → WHERE VN = 0",
|
||||
"用户明确说'没有VN用量的' → WHERE VN = 0"
|
||||
],
|
||||
"incorrect_interpretation": [
|
||||
"用户说'country为VN' → 错误：添加WHERE VN > 0",
|
||||
"用户说'VN国家' → 错误：添加WHERE VN > 0",
|
||||
"用户说'查看VN' → 错误：添加WHERE VN > 0"
|
||||
]
|
||||
},
|
||||
"range_filter": {
|
||||
"pattern": ["大于{值}", "超过{值}", "少于{值}", "小于{值}", "不低于{值}", "不超过{值}"],
|
||||
"sql_mapping": {
|
||||
"大于{值}": "{field} > {value}",
|
||||
"超过{值}": "{field} >= {value}",
|
||||
"少于{值}": "{field} < {value}",
|
||||
"小于{值}": "{field} < {value}",
|
||||
"不低于{值}": "{field} >= {value}",
|
||||
"不超过{值}": "{field} <= {value}"
|
||||
},
|
||||
"examples": [
|
||||
"库存大于500 → ib > 500",
|
||||
"VN用量超过100 → VN >= 100",
|
||||
"近期用量少于50 → usage_qty_8_week < 50"
|
||||
]
|
||||
},
|
||||
"multiple_conditions": {
|
||||
"pattern": ["且", "并且", "和", "同时", ","],
|
||||
"sql": "AND",
|
||||
"examples": [
|
||||
"region为CAP且commodity_code为LF → region = 'CAP' AND commodity_code = 'LF'",
|
||||
"库存大于500且有VN用量 → ib > 500 AND VN > 0"
|
||||
]
|
||||
}
|
||||
},
|
||||
|
||||
"no_default_conditions": {
|
||||
"rule": "绝对不添加任何用户没有明确要求的WHERE条件",
|
||||
"examples_of_what_not_to_add": [
|
||||
"不要添加WHERE region = 'CAP'（除非用户明确要求）",
|
||||
"不要添加WHERE ib > 0（除非用户明确要求）",
|
||||
"不要添加WHERE commodity_code IS NOT NULL（除非用户明确要求）",
|
||||
"不要添加任何假设性的过滤条件"
|
||||
]
|
||||
}
|
||||
},
|
||||
|
||||
"default_behavior": {
|
||||
"sorting": "默认按ib(库存数量)降序排列：ORDER BY ib DESC",
|
||||
"limit": "禁止使用limit",
|
||||
"select_all": "默认查询所有字段：SELECT *",
|
||||
"field_order": "当用户指定字段时，按用户提到的顺序排列字段",
|
||||
"date_handling": "本表无日期字段，不需要日期转换"
|
||||
}
|
||||
},
|
||||
"field_mapping_reference": {
|
||||
"critical_note": "此表包含亚太地区各物料的库存、近期用量及历史使用量的详细数据。特别注意：国家字段(AU, VN, JP等)是数值型用量字段，表示该物料在该国家的历史用量，不是国家代码。这些字段是BIGINT类型，支持数值比较操作。",
|
||||
|
||||
"material_identifier_fields": {
|
||||
"topmost_pn": {
|
||||
"type": "string",
|
||||
"desc": "顶级物料号，物料的唯一标识",
|
||||
"example": "5CB1L57599",
|
||||
"query_pattern": "物料为{值} → topmost_pn = '{value}'",
|
||||
"alias": ["物料号", "零件号", "Part Number", "PN", "topmost", "物料编码"]
|
||||
},
|
||||
"commodity_code": {
|
||||
"type": "string",
|
||||
"desc": "商品代码，物料分类标识",
|
||||
"example": "LF",
|
||||
"query_pattern": "commodity_code为{值} → commodity_code = '{value}'",
|
||||
"alias": ["商品编码", "物料分类", "Commodity Code", "CC", "编码", "商品类别"]
|
||||
}
|
||||
},
|
||||
|
||||
"geographic_dimension_fields": {
|
||||
"region": {
|
||||
"type": "string",
|
||||
"desc": "区域划分，如CAP（亚太区）、EMEA（欧洲中东非洲）等",
|
||||
"example": "CAP",
|
||||
"values": ["CAP", "EMEA", "AMER"],
|
||||
"query_pattern": "region为{值} → region = '{value}'",
|
||||
"alias": ["区域", "大区", "Region", "地区", "地理区域"]
|
||||
},
|
||||
"dc_plant": {
|
||||
"type": "string",
|
||||
"desc": "配送中心/工厂代码",
|
||||
"example": "HKGDC",
|
||||
"query_pattern": "dc_plant为{值} → dc_plant = '{value}'",
|
||||
"alias": ["工厂", "配送中心", "plant", "DC", "发货中心", "Distribution Center"]
|
||||
},
|
||||
"location_name": {
|
||||
"type": "string",
|
||||
"desc": "地点名称",
|
||||
"example": "Hong Kong Distribution Center",
|
||||
"alias": ["地点名称", "位置名称", "location", "地点", "场所名称"]
|
||||
}
|
||||
},
|
||||
|
||||
"country_usage_fields_section": {
|
||||
"important_note": "以下所有字段都是数值型(BIGINT)，表示该物料在该国家的历史使用量，不是国家代码。这些字段支持数值比较操作(>, <, >=, <=, =, !=)。",
|
||||
"critical_warning": "绝对不要将这些字段作为字符串处理，不要使用单引号，不要使用LIKE操作符。",
|
||||
|
||||
"country_total_cnt": {
|
||||
"type": "bigint",
|
||||
"desc": "所有国家的总使用量计数",
|
||||
"calculation_note": "可能是各国家字段的汇总或其他计算逻辑",
|
||||
"alias": ["国家总计数", "总使用量", "country total", "总计"]
|
||||
},
|
||||
|
||||
"country_usage_fields": {
|
||||
"AU": {
|
||||
"type": "bigint",
|
||||
"desc": "澳大利亚的历史使用量",
|
||||
"alias": ["澳大利亚", "澳洲", "AU用量", "Australia用量"]
|
||||
},
|
||||
"NZ": {
|
||||
"type": "bigint",
|
||||
"desc": "新西兰的历史使用量",
|
||||
"alias": ["新西兰", "NZ用量", "New Zealand用量"]
|
||||
},
|
||||
"LK": {
|
||||
"type": "bigint",
|
||||
"desc": "斯里兰卡的历史使用量",
|
||||
"alias": ["斯里兰卡", "LK用量", "Sri Lanka用量"]
|
||||
},
|
||||
"VN": {
|
||||
"type": "bigint",
|
||||
"desc": "越南的历史使用量",
|
||||
"alias": ["越南", "VN用量", "Vietnam用量"]
|
||||
},
|
||||
"JP": {
|
||||
"type": "bigint",
|
||||
"desc": "日本的历史使用量",
|
||||
"alias": ["日本", "JP用量", "Japan用量"]
|
||||
},
|
||||
"HK": {
|
||||
"type": "bigint",
|
||||
"desc": "香港的历史使用量",
|
||||
"alias": ["香港", "HK用量", "Hong Kong用量"]
|
||||
},
|
||||
"SG": {
|
||||
"type": "bigint",
|
||||
"desc": "新加坡的历史使用量",
|
||||
"alias": ["新加坡", "SG用量", "Singapore用量"]
|
||||
},
|
||||
"TH": {
|
||||
"type": "bigint",
|
||||
"desc": "泰国的历史使用量",
|
||||
"alias": ["泰国", "TH用量", "Thailand用量"]
|
||||
},
|
||||
"PH": {
|
||||
"type": "bigint",
|
||||
"desc": "菲律宾的历史使用量",
|
||||
"alias": ["菲律宾", "PH用量", "Philippines用量"]
|
||||
},
|
||||
"IN": {
|
||||
"type": "bigint",
|
||||
"desc": "印度的历史使用量",
|
||||
"alias": ["印度", "IN用量", "India用量"]
|
||||
},
|
||||
"BN": {
|
||||
"type": "bigint",
|
||||
"desc": "文莱的历史使用量",
|
||||
"alias": ["文莱", "BN用量", "Brunei用量"]
|
||||
},
|
||||
"NP": {
|
||||
"type": "bigint",
|
||||
"desc": "尼泊尔的历史使用量",
|
||||
"alias": ["尼泊尔", "NP用量", "Nepal用量"]
|
||||
},
|
||||
"BD": {
|
||||
"type": "bigint",
|
||||
"desc": "孟加拉国的历史使用量",
|
||||
"alias": ["孟加拉国", "BD用量", "Bangladesh用量"]
|
||||
},
|
||||
"KR": {
|
||||
"type": "bigint",
|
||||
"desc": "韩国的历史使用量",
|
||||
"alias": ["韩国", "KR用量", "Korea用量"]
|
||||
},
|
||||
"ID": {
|
||||
"type": "bigint",
|
||||
"desc": "印度尼西亚的历史使用量",
|
||||
"alias": ["印度尼西亚", "印尼", "ID用量", "Indonesia用量"]
|
||||
},
|
||||
"FJ": {
|
||||
"type": "bigint",
|
||||
"desc": "斐济的历史使用量",
|
||||
"alias": ["斐济", "FJ用量", "Fiji用量"]
|
||||
},
|
||||
"MY": {
|
||||
"type": "bigint",
|
||||
"desc": "马来西亚的历史使用量",
|
||||
"alias": ["马来西亚", "MY用量", "Malaysia用量"]
|
||||
},
|
||||
"TW": {
|
||||
"type": "bigint",
|
||||
"desc": "台湾的历史使用量",
|
||||
"alias": ["台湾", "TW用量", "Taiwan用量"]
|
||||
}
|
||||
},
|
||||
|
||||
"query_examples": {
|
||||
"correct": [
|
||||
"WHERE VN > 0 (查询有越南用量的物料)",
|
||||
"WHERE JP >= 100 (查询日本用量超过100的物料)",
|
||||
"WHERE AU = 0 (查询没有澳大利亚用量的物料)",
|
||||
"WHERE SG < 50 (查询新加坡用量少于50的物料)"
|
||||
],
|
||||
"incorrect": [
|
||||
"WHERE VN = 'VN' (错误：VN是数值，不是字符串)",
|
||||
"WHERE JP LIKE '%JP%' (错误：JP是数值，不支持LIKE)",
|
||||
"WHERE AU IN ('AU', 'VN') (错误：AU是数值，不是枚举)"
|
||||
]
|
||||
}
|
||||
},
|
||||
|
||||
"inventory_metrics": {
|
||||
"ib": {
|
||||
"type": "bigint",
|
||||
"desc": "库存数量(Inventory Balance)",
|
||||
"query_pattern": "库存超过{值} → ib > {value}, 库存大于{值} → ib > {value}, 库存少于{值} → ib < {value}",
|
||||
"alias": ["库存", "库存量", "库存数量", "Inventory", "库存余额", "IB"]
|
||||
}
|
||||
},
|
||||
|
||||
"usage_time_series_fields": {
|
||||
"usage_qty_8_week": {
|
||||
"type": "bigint",
|
||||
"desc": "近8周的使用量",
|
||||
"alias": ["近8周用量", "近期用量", "短期用量", "8周用量", "近期使用量"]
|
||||
},
|
||||
"usage_qty_52_week": {
|
||||
"type": "bigint",
|
||||
"desc": "近52周的使用量",
|
||||
"alias": ["近52周用量", "年度用量", "长期用量", "52周用量", "年度使用量"]
|
||||
},
|
||||
"total_history_usage": {
|
||||
"type": "bigint",
|
||||
"desc": "历史总使用量",
|
||||
"alias": ["历史总用量", "总使用量", "累计用量", "历史累计", "total usage"]
|
||||
}
|
||||
}
|
||||
},
|
||||
"examples": {
|
||||
"简单查询-全部字段": {
|
||||
"user": "region为CAP的数据",
|
||||
"sql": "SELECT * FROM dwd_ai.apbo_region_usage_ib_report WHERE region = 'CAP' ORDER BY ib DESC",
|
||||
"field_selection_reason": "用户没有指定字段，默认查询所有字段。WHERE条件中使用了region字段。"
|
||||
},
|
||||
|
||||
"简单查询-基础过滤": {
|
||||
"user": "region为CAP，commodity_code为LF的数据",
|
||||
"sql": "SELECT * FROM dwd_ai.apbo_region_usage_ib_report WHERE region = 'CAP' AND commodity_code = 'LF' ORDER BY ib DESC",
|
||||
"field_selection_reason": "用户没有指定字段，默认查询所有字段。WHERE条件中使用了region和commodity_code字段。"
|
||||
},
|
||||
|
||||
"简单查询-带国家字段但不过滤": {
|
||||
"user": "region为CAP，commodity_code为LF的，country为VN的数据",
|
||||
"sql": "SELECT * FROM dwd_ai.apbo_region_usage_ib_report WHERE region = 'CAP' AND commodity_code = 'LF' ORDER BY ib DESC",
|
||||
"field_selection_reason": "用户提到'country为VN'但没有要求过滤VN用量，所以不添加VN > 0条件。默认查询所有字段。"
|
||||
},
|
||||
|
||||
"简单查询-带国家用量过滤": {
|
||||
"user": "region为CAP，commodity_code为LF的，有VN用量的数据",
|
||||
"sql": "SELECT * FROM dwd_ai.apbo_region_usage_ib_report WHERE region = 'CAP' AND commodity_code = 'LF' AND VN > 0 ORDER BY ib DESC",
|
||||
"field_selection_reason": "用户明确要求'有VN用量的'，所以添加VN > 0条件。默认查询所有字段。"
|
||||
},
|
||||
|
||||
"简单查询-指定字段": {
|
||||
"user": "查看物料号和库存数量",
|
||||
"sql": "SELECT topmost_pn, ib FROM dwd_ai.apbo_region_usage_ib_report ORDER BY ib DESC",
|
||||
"field_selection_reason": "用户明确指定了topmost_pn和ib字段，只查询这两个字段，按用户提到的顺序排列。"
|
||||
},
|
||||
|
||||
"简单查询-多条件组合": {
|
||||
"user": "region为CAP，commodity_code为LF，库存大于500，有VN用量的数据",
|
||||
"sql": "SELECT * FROM dwd_ai.apbo_region_usage_ib_report WHERE region = 'CAP' AND commodity_code = 'LF' AND ib > 500 AND VN > 0 ORDER BY ib DESC",
|
||||
"field_selection_reason": "用户没有指定字段，默认查询所有字段。WHERE条件包含region、commodity_code、ib和VN字段的过滤。"
|
||||
},
|
||||
|
||||
"指定字段且包含WHERE字段": {
|
||||
"user": "region为CAP的物料号和库存",
|
||||
"sql": "SELECT topmost_pn, ib, region FROM dwd_ai.apbo_region_usage_ib_report WHERE region = 'CAP' ORDER BY ib DESC",
|
||||
"field_selection_reason": "用户指定了topmost_pn和ib字段，但WHERE条件中使用了region字段，所以必须包含region字段在SELECT中。"
|
||||
},
|
||||
|
||||
"国家用量范围查询": {
|
||||
"user": "VN用量超过100且库存大于200的物料",
|
||||
"sql": "SELECT * FROM dwd_ai.apbo_region_usage_ib_report WHERE VN >= 100 AND ib > 200 ORDER BY ib DESC",
|
||||
"field_selection_reason": "用户没有指定字段，默认查询所有字段。WHERE条件包含VN和ib字段的数值范围过滤。"
|
||||
},
|
||||
|
||||
"多国家用量查询": {
|
||||
"user": "有VN用量且有AU用量的物料号",
|
||||
"sql": "SELECT topmost_pn, VN, AU FROM dwd_ai.apbo_region_usage_ib_report WHERE VN > 0 AND AU > 0 ORDER BY ib DESC",
|
||||
"field_selection_reason": "用户指定了topmost_pn字段，并提到了VN和AU用量，所以包含这些字段。WHERE条件包含VN>0和AU>0。"
|
||||
},
|
||||
|
||||
"混合条件复杂查询": {
|
||||
"user": "region为CAP，commodity_code为LF，库存大于500，有VN用量且超过50，近期用量少于100的物料信息",
|
||||
"sql": "SELECT * FROM dwd_ai.apbo_region_usage_ib_report WHERE region = 'CAP' AND commodity_code = 'LF' AND ib > 500 AND VN > 50 AND usage_qty_8_week < 100 ORDER BY ib DESC",
|
||||
"field_selection_reason": "用户没有指定字段，默认查询所有字段。WHERE条件包含多个字段的复杂过滤。"
|
||||
},
|
||||
|
||||
"国家用量为零查询": {
|
||||
"user": "没有VN用量的物料",
|
||||
"sql": "SELECT * FROM dwd_ai.apbo_region_usage_ib_report WHERE VN = 0 ORDER BY ib DESC",
|
||||
"field_selection_reason": "用户明确要求'没有VN用量的'，所以添加VN = 0条件。默认查询所有字段。"
|
||||
},
|
||||
|
||||
"仅查看特定国家用量": {
|
||||
"user": "查看VN和JP的用量",
|
||||
"sql": "SELECT VN, JP FROM dwd_ai.apbo_region_usage_ib_report ORDER BY ib DESC",
|
||||
"field_selection_reason": "用户明确指定了VN和JP字段，只查询这两个字段。没有WHERE条件。"
|
||||
}
|
||||
}
|
||||
}
|
||||
@@ -1,182 +0,0 @@
|
||||
{
|
||||
"meta": {
|
||||
"domain": "TP物料多重影响分析",
|
||||
"keywords": ["multiple impact", "tp物料", "物料影响", "pal_2h", "达标状态", "不达标状态", "物料分析", "TP分析", "影响分析"],
|
||||
"description": "此模型用于分析TP物料基于pal_2h状态的详细记录和统计信息。pal_2h='N'表示不达标，pal_2h='Y'表示达标。支持明细查询和统计分析两种模式，根据不同查询意图自动切换模式。",
|
||||
"data_source": "dwd_ai.apbo_tp_multiple_impact"
|
||||
},
|
||||
|
||||
"data_model_specification": {
|
||||
"fields_list": ["topmost_pn", "service_order_id", "soid", "pal_2h"],
|
||||
"mandatory_display_fields": {
|
||||
"rule1": "所有核心字段必须出现在SELECT子句中，除非用户明确指定排除。",
|
||||
"rule2": "pal_2h字段在两种模式下都必须显示",
|
||||
"rule3": "SELECT子句中字段顺序建议为：pal_2h, topmost_pn, service_order_id, soid",
|
||||
"action": "detail_mode下显示所有字段，statistical_mode下显示分组字段和统计结果"
|
||||
},
|
||||
|
||||
"optional_fields": {
|
||||
"key_fields": ["topmost_pn", "service_order_id", "soid"],
|
||||
"status_fields": ["pal_2h"],
|
||||
"grouping_fields": ["topmost_pn", "pal_2h"]
|
||||
}
|
||||
},
|
||||
|
||||
"business_logic_rules": {
|
||||
"query_recognition_rules": {
|
||||
"detail_mode_keywords": ["有哪些", "查看", "列出", "显示", "查询", "搜索", "找出", "记录", "明细", "详情", "具体"],
|
||||
"statistical_mode_keywords": ["统计", "汇总", "总数", "有多少", "数量", "count", "条数", "计数", "分组", "分布", "占比", "比例"],
|
||||
"tp_material_keywords": ["tp", "物料", "topmost_pn", "零件", "零件号", "物料号", "TP物料"],
|
||||
"order_keywords": ["订单", "so", "service_order_id", "SOID", "soid"],
|
||||
"status_keywords": ["状态", "pal_2h", "达标", "不达标", "Y", "N", "status"]
|
||||
},
|
||||
|
||||
"default_behavior": {
|
||||
"detail_mode": {
|
||||
"sorting": "默认按topmost_pn, service_order_id排序",
|
||||
"pal_2h_display": "pal_2h字段必须显示在SELECT结果中",
|
||||
"pal_2h_filter": "用户未指定状态条件时，禁止使用pal_2h过滤"
|
||||
},
|
||||
"statistical_mode": {
|
||||
"sorting": "COUNT(*) DESC",
|
||||
"limit": "禁止使用limit",
|
||||
"pal_2h_filter": "用户未指定状态条件时，禁止使用pal_2h过滤"
|
||||
},
|
||||
"alias_handling": "将用户提到的别名转换为完整字段名后再生成SQL"
|
||||
}
|
||||
},
|
||||
|
||||
"field_mapping_reference": {
|
||||
"critical_note": "注意区分detail_mode（明细查询）和statistical_mode（统计分析）两种模式，根据用户query中的关键词自动判断模式。detail_mode禁止使用聚合函数，statistical_mode必须使用聚合函数。",
|
||||
|
||||
"key_identifiers": {
|
||||
"topmost_pn": {
|
||||
"type": "varchar",
|
||||
"desc": "TP物料编号",
|
||||
"example": "02HK965",
|
||||
"required": true,
|
||||
"alias": ["tp", "物料", "物料号", "零件号", "TP物料", "零件编号", "物料编码"]
|
||||
},
|
||||
"service_order_id": {
|
||||
"type": "varchar",
|
||||
"desc": "服务订单ID",
|
||||
"example": "4020438779",
|
||||
"required": true,
|
||||
"alias": ["so", "订单", "订单号", "service_order", "订单ID", "SO", "服务订单"]
|
||||
},
|
||||
"soid": {
|
||||
"type": "varchar",
|
||||
"desc": "SOID（服务订单明细ID）",
|
||||
"example": "402043877920",
|
||||
"required": true,
|
||||
"alias": ["SOID", "子单号", "明细ID", "订单明细", "服务订单明细"]
|
||||
}
|
||||
},
|
||||
|
||||
"status_fields": {
|
||||
"pal_2h": {
|
||||
"type": "varchar(1)",
|
||||
"desc": "状态字段：'Y'表示达标，'N'表示不达标",
|
||||
"values": {
|
||||
"Y": "达标",
|
||||
"N": "不达标",
|
||||
"NULL": "无状态"
|
||||
},
|
||||
"business_rule": "用户未指定状态条件时，默认查询不达标记录（pal_2h = 'N'）",
|
||||
"alias": ["状态", "达标状态", "不达标状态", "pal_2h状态", "status", "达标标识"]
|
||||
}
|
||||
},
|
||||
|
||||
"condition_mapping": {
|
||||
"达标": "pal_2h = 'Y'",
|
||||
"不达标": "pal_2h = 'N'",
|
||||
"无状态": "pal_2h IS NULL",
|
||||
"所有状态": "pal_2h IN ('Y', 'N')",
|
||||
"有状态的": "pal_2h IN ('Y', 'N')",
|
||||
"状态完整": "pal_2h IN ('Y', 'N')"
|
||||
}
|
||||
},
|
||||
|
||||
"examples": {
|
||||
"detail_mode_examples": {
|
||||
"example1": {
|
||||
"user": "tp为02HK965的multiple impact有哪些",
|
||||
"mode": "detail_mode",
|
||||
"reason": "包含'有哪些'关键词，表示查看具体记录；未指定状态，默认查不达标",
|
||||
"sql": "SELECT pal_2h, topmost_pn, service_order_id, soid FROM dwd_ai.apbo_tp_multiple_impact WHERE topmost_pn = '02HK965' ORDER BY topmost_pn, service_order_id"
|
||||
},
|
||||
"example2": {
|
||||
"user": "查看达标的记录",
|
||||
"mode": "detail_mode",
|
||||
"reason": "包含'查看'关键词，表示查看具体记录；指定了达标状态",
|
||||
"sql": "SELECT pal_2h, topmost_pn, service_order_id, soid FROM dwd_ai.apbo_tp_multiple_impact WHERE ORDER BY topmost_pn, service_order_id"
|
||||
},
|
||||
"example3": {
|
||||
"user": "列出topmost_pn为02HK965的记录",
|
||||
"mode": "detail_mode",
|
||||
"reason": "包含'列出'关键词，表示查看具体记录；未指定状态，默认查不达标",
|
||||
"sql": "SELECT pal_2h, topmost_pn, service_order_id, soid FROM dwd_ai.apbo_tp_multiple_impact WHERE topmost_pn = '02HK965' ORDER BY topmost_pn, service_order_id"
|
||||
},
|
||||
"example4": {
|
||||
"user": "查询订单4020438779的TP物料影响",
|
||||
"mode": "detail_mode",
|
||||
"reason": "包含'查询'关键词，表示查看具体记录；未指定状态，默认查不达标",
|
||||
"sql": "SELECT pal_2h, topmost_pn, service_order_id, soid FROM dwd_ai.apbo_tp_multiple_impact WHERE service_order_id = '4020438779' ORDER BY topmost_pn, soid"
|
||||
}
|
||||
},
|
||||
|
||||
"statistical_mode_examples": {
|
||||
"example1": {
|
||||
"user": "统计不同状态的物料数量",
|
||||
"mode": "statistical_mode",
|
||||
"reason": "包含'统计'关键词，表示统计数量；统计不同状态，需要显示所有状态",
|
||||
"sql": "SELECT pal_2h, COUNT(topmost_pn) AS topmost_pn_count FROM dwd_ai.apbo_tp_multiple_impact GROUP BY pal_2h ORDER BY topmost_pn_count DESC"
|
||||
},
|
||||
"example2": {
|
||||
"user": "按topmost_pn分组统计每个物料的记录数",
|
||||
"mode": "statistical_mode",
|
||||
"reason": "包含'统计'和'分组'关键词；未指定状态，默认只统计不达标",
|
||||
"sql": "SELECT topmost_pn, pal_2h, COUNT(*) AS count FROM dwd_ai.apbo_tp_multiple_impact GROUP BY topmost_pn, pal_2h ORDER BY count DESC"
|
||||
},
|
||||
"example3": {
|
||||
"user": "汇总各TP物料的影响分布",
|
||||
"mode": "statistical_mode",
|
||||
"reason": "包含'汇总'关键词，表示统计分布；未指定状态，默认只统计不达标",
|
||||
"sql": "SELECT topmost_pn, COUNT(*) AS record_count FROM dwd_ai.apbo_tp_multiple_impact GROUP BY topmost_pn ORDER BY record_count DESC"
|
||||
}
|
||||
},
|
||||
|
||||
"edge_cases": {
|
||||
"example1": {
|
||||
"user": "有多少条tp为02HK965的记录",
|
||||
"mode": "statistical_mode",
|
||||
"reason": "包含'有多少'关键词，虽然指定了具体物料，但目的是获取数量；未指定状态，默认只统计不达标",
|
||||
"sql": "SELECT COUNT(*) AS count FROM dwd_ai.apbo_tp_multiple_impact WHERE topmost_pn = '02HK965'"
|
||||
},
|
||||
"example2": {
|
||||
"user": "显示所有状态为达标和不达标的记录",
|
||||
"mode": "detail_mode",
|
||||
"reason": "包含'显示'关键词，表示查看具体记录；明确要求查看两种状态，不使用默认值",
|
||||
"sql": "SELECT pal_2h, topmost_pn, service_order_id, soid FROM dwd_ai.apbo_tp_multiple_impact ORDER BY topmost_pn, service_order_id"
|
||||
},
|
||||
"example3": {
|
||||
"user": "统计状态为NULL的记录数量",
|
||||
"mode": "statistical_mode",
|
||||
"reason": "包含'统计'关键词，表示统计数量；明确指定NULL状态，不使用默认值",
|
||||
"sql": "SELECT COUNT(*) AS count FROM dwd_ai.apbo_tp_multiple_impact WHERE pal_2h IS NULL"
|
||||
},
|
||||
"example4": {
|
||||
"user": "查看所有状态的记录详情",
|
||||
"mode": "detail_mode",
|
||||
"reason": "包含'查看'和'详情'关键词，表示查看具体记录；要求所有状态，不使用默认值",
|
||||
"sql": "SELECT pal_2h, topmost_pn, service_order_id, soid FROM dwd_ai.apbo_tp_multiple_impact OR pal_2h IS NULL ORDER BY pal_2h, topmost_pn, service_order_id"
|
||||
},
|
||||
"example5": {
|
||||
"user": "统计每个TP物料的不同状态数量",
|
||||
"mode": "statistical_mode",
|
||||
"reason": "包含'统计'关键词，表示统计分析；统计每个物料的各状态分布",
|
||||
"sql": "SELECT topmost_pn, pal_2h, COUNT(*) AS count FROM dwd_ai.apbo_tp_multiple_impact GROUP BY topmost_pn, pal_2h ORDER BY topmost_pn, pal_2h"
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
@@ -1,4 +0,0 @@
|
||||
本目录存放用于 RAGFlow 匹配的表名检索提示词（JSON）。
|
||||
|
||||
约定：使用单一 JSON 文件维护多个表名及其模板列表。
|
||||
示例文件：tables.json。
|
||||
@@ -1,5 +1,6 @@
|
||||
{
|
||||
"apbo_eta_ful": [
|
||||
"backlog order",
|
||||
"SO ETA INFO",
|
||||
"BO list",
|
||||
"CC",
|
||||
@@ -17,9 +18,14 @@
|
||||
"recovery ETA",
|
||||
"history order",
|
||||
"Warranty type",
|
||||
"category"
|
||||
"category",
|
||||
"eta",
|
||||
"eta信息",
|
||||
"passdue",
|
||||
"逾期"
|
||||
],
|
||||
"apbo_milestone_info": [
|
||||
"apbo_eta_milestone": [
|
||||
"soid milestone",
|
||||
"GR or POD",
|
||||
"POD",
|
||||
"GR",
|
||||
@@ -30,17 +36,23 @@
|
||||
"里程碑",
|
||||
"节点明细"
|
||||
],
|
||||
"apbo_hic_ssoc_consumption": [
|
||||
"consumption消耗记录",
|
||||
"consumption order"
|
||||
],
|
||||
"apbo_tp_multiple_impact": [
|
||||
"multiple impact orders",
|
||||
"apbo_eta_multiple_impact": [
|
||||
"multiple impact",
|
||||
"不达标的multiple impact",
|
||||
"multiple impact status"
|
||||
],
|
||||
"apbo_region_usage_ib_report": [
|
||||
"ib",
|
||||
"usage"
|
||||
"apbo_eta_region_report": [
|
||||
"region report",
|
||||
"regional report"
|
||||
],
|
||||
"apbo_eta_usage_ib_report":[
|
||||
|
||||
],
|
||||
"apbo_hic_ssoc_consumption": [
|
||||
"consumption消耗记录",
|
||||
"consumption order",
|
||||
"consumption record",
|
||||
"SSOC consumption",
|
||||
"consumption"
|
||||
]
|
||||
}
|
||||
@@ -1,52 +0,0 @@
|
||||
"""
|
||||
核心模块 - 提供扩展性基础设施
|
||||
|
||||
包含:
|
||||
- Registry: 注册机制
|
||||
- State: 增强的状态管理
|
||||
- Provider: LLM Provider 抽象
|
||||
- Response: 统一响应格式
|
||||
"""
|
||||
|
||||
from .registry import (
|
||||
BaseRegistry,
|
||||
NodeRegistry,
|
||||
ToolRegistry,
|
||||
WorkflowRegistry,
|
||||
ProviderRegistry,
|
||||
RegistryEntry,
|
||||
ToolMetadata,
|
||||
WorkflowMetadata,
|
||||
ProviderMetadata,
|
||||
register_tool,
|
||||
register_workflow,
|
||||
register_provider,
|
||||
)
|
||||
from .state import AgentState, StateContext
|
||||
from .providers import LLMProvider, LLMFactory
|
||||
from .response import ApiResponse, StreamEvent
|
||||
|
||||
__all__ = [
|
||||
# Registry
|
||||
"BaseRegistry",
|
||||
"NodeRegistry",
|
||||
"ToolRegistry",
|
||||
"WorkflowRegistry",
|
||||
"ProviderRegistry",
|
||||
"RegistryEntry",
|
||||
"ToolMetadata",
|
||||
"WorkflowMetadata",
|
||||
"ProviderMetadata",
|
||||
"register_tool",
|
||||
"register_workflow",
|
||||
"register_provider",
|
||||
# State
|
||||
"AgentState",
|
||||
"StateContext",
|
||||
# Provider
|
||||
"LLMProvider",
|
||||
"LLMFactory",
|
||||
# Response
|
||||
"ApiResponse",
|
||||
"StreamEvent",
|
||||
]
|
||||
@@ -1,218 +0,0 @@
|
||||
"""
|
||||
LLM Provider 抽象层
|
||||
|
||||
支持多种 LLM 提供商的统一接口
|
||||
"""
|
||||
|
||||
from typing import Any, Dict, List, Optional, Protocol, Type, runtime_checkable
|
||||
from abc import ABC, abstractmethod
|
||||
import logging
|
||||
|
||||
from langchain_core.language_models import BaseChatModel
|
||||
|
||||
from config import Config
|
||||
from .registry import ProviderRegistry, register_provider
|
||||
|
||||
logger = logging.getLogger(__name__)
|
||||
|
||||
|
||||
@runtime_checkable
|
||||
class LLMProvider(Protocol):
|
||||
"""
|
||||
LLM Provider 协议
|
||||
|
||||
定义所有 LLM 提供商必须实现的接口
|
||||
"""
|
||||
|
||||
@property
|
||||
def name(self) -> str:
|
||||
"""Provider 名称"""
|
||||
...
|
||||
|
||||
@property
|
||||
def supported_models(self) -> List[str]:
|
||||
"""支持的模型列表"""
|
||||
...
|
||||
|
||||
def create_model(self, config: Dict[str, Any]) -> BaseChatModel:
|
||||
"""
|
||||
创建 LLM 模型实例
|
||||
|
||||
Args:
|
||||
config: 模型配置
|
||||
|
||||
Returns:
|
||||
BaseChatModel 实例
|
||||
"""
|
||||
...
|
||||
|
||||
|
||||
class BaseLLMProvider(ABC):
|
||||
"""LLM Provider 基类"""
|
||||
|
||||
def __init__(self, name: str, supported_models: List[str]):
|
||||
self._name = name
|
||||
self._supported_models = supported_models
|
||||
|
||||
@property
|
||||
def name(self) -> str:
|
||||
return self._name
|
||||
|
||||
@property
|
||||
def supported_models(self) -> List[str]:
|
||||
return self._supported_models
|
||||
|
||||
@abstractmethod
|
||||
def create_model(self, config: Dict[str, Any]) -> BaseChatModel:
|
||||
"""子类实现具体的模型创建逻辑"""
|
||||
pass
|
||||
|
||||
|
||||
class OpenAICompatibleProvider(BaseLLMProvider):
|
||||
"""
|
||||
OpenAI 兼容的 Provider
|
||||
|
||||
支持所有兼容 OpenAI API 的服务：
|
||||
- OpenAI
|
||||
- Azure OpenAI
|
||||
- 本地部署的兼容服务
|
||||
- 国产大模型（通义千问、文心一言等）
|
||||
"""
|
||||
|
||||
def __init__(self, name: str = "openai_compatible", supported_models: Optional[List[str]] = None):
|
||||
super().__init__(name, supported_models or [])
|
||||
|
||||
def create_model(self, config: Dict[str, Any]) -> BaseChatModel:
|
||||
from langchain_openai import ChatOpenAI
|
||||
|
||||
return ChatOpenAI(
|
||||
model=config.get("model_name") or config.get("MODEL_NAME"),
|
||||
openai_api_key=config.get("api_key") or config.get("OPENAI_API_KEY"),
|
||||
openai_api_base=config.get("base_url") or config.get("URL"),
|
||||
temperature=config.get("temperature", 0.7),
|
||||
max_tokens=config.get("max_tokens"),
|
||||
timeout=config.get("timeout", 30),
|
||||
max_retries=config.get("max_retries", 3),
|
||||
)
|
||||
|
||||
|
||||
class AzureOpenAIProvider(BaseLLMProvider):
|
||||
"""Azure OpenAI Provider"""
|
||||
|
||||
def __init__(self):
|
||||
super().__init__("azure", ["gpt-4", "gpt-35-turbo"])
|
||||
|
||||
def create_model(self, config: Dict[str, Any]) -> BaseChatModel:
|
||||
from langchain_openai import AzureChatOpenAI
|
||||
|
||||
return AzureChatOpenAI(
|
||||
azure_deployment=config.get("deployment_name"),
|
||||
openai_api_version=config.get("api_version", "2024-02-15-preview"),
|
||||
azure_endpoint=config.get("endpoint"),
|
||||
openai_api_key=config.get("api_key"),
|
||||
temperature=config.get("temperature", 0.7),
|
||||
)
|
||||
|
||||
|
||||
class LLMFactory:
|
||||
"""
|
||||
LLM 工厂类
|
||||
|
||||
统一管理 LLM 实例的创建，支持：
|
||||
- 多种 Provider
|
||||
- 配置驱动
|
||||
- 单例缓存
|
||||
"""
|
||||
|
||||
_instances: Dict[str, BaseChatModel] = {}
|
||||
_default_provider: str = "openai_compatible"
|
||||
|
||||
@classmethod
|
||||
def register_provider(cls, name: str, provider: LLMProvider) -> None:
|
||||
"""注册 Provider"""
|
||||
ProviderRegistry._entries[name] = type(
|
||||
"RegistryEntry",
|
||||
(),
|
||||
{"instance": provider, "metadata": {}}
|
||||
)()
|
||||
logger.info(f"Registered LLM provider: {name}")
|
||||
|
||||
@classmethod
|
||||
def get_provider(cls, name: str) -> Optional[LLMProvider]:
|
||||
"""获取 Provider"""
|
||||
entry = ProviderRegistry.get_entry(name)
|
||||
if entry:
|
||||
return entry.instance
|
||||
return None
|
||||
|
||||
@classmethod
|
||||
def create(
|
||||
cls,
|
||||
provider: Optional[str] = None,
|
||||
config: Optional[Dict[str, Any]] = None,
|
||||
model_section: Optional[str] = None,
|
||||
use_cache: bool = True,
|
||||
) -> BaseChatModel:
|
||||
"""
|
||||
创建 LLM 实例
|
||||
|
||||
Args:
|
||||
provider: Provider 名称，默认使用 openai_compatible
|
||||
config: 模型配置
|
||||
model_section: 配置文件中的模型段名
|
||||
use_cache: 是否使用缓存
|
||||
|
||||
Returns:
|
||||
BaseChatModel 实例
|
||||
"""
|
||||
provider_name = provider or cls._default_provider
|
||||
|
||||
if model_section:
|
||||
config = Config.get_section(model_section)
|
||||
cache_key = f"{provider_name}:{model_section}"
|
||||
else:
|
||||
config = config or {}
|
||||
cache_key = f"{provider_name}:{hash(frozenset(config.items()))}"
|
||||
|
||||
if use_cache and cache_key in cls._instances:
|
||||
return cls._instances[cache_key]
|
||||
|
||||
provider_instance = cls.get_provider(provider_name)
|
||||
|
||||
if provider_instance is None:
|
||||
provider_instance = OpenAICompatibleProvider()
|
||||
|
||||
model = provider_instance.create_model(config)
|
||||
|
||||
if use_cache:
|
||||
cls._instances[cache_key] = model
|
||||
|
||||
return model
|
||||
|
||||
@classmethod
|
||||
def clear_cache(cls) -> None:
|
||||
"""清空缓存"""
|
||||
cls._instances.clear()
|
||||
|
||||
@classmethod
|
||||
def list_providers(cls) -> List[str]:
|
||||
"""列出所有注册的 Provider"""
|
||||
return ProviderRegistry.list_names()
|
||||
|
||||
|
||||
OpenAICompatibleProvider()
|
||||
ProviderRegistry._entries["openai_compatible"] = type(
|
||||
"RegistryEntry",
|
||||
(),
|
||||
{"instance": OpenAICompatibleProvider(), "metadata": {}}
|
||||
)()
|
||||
|
||||
|
||||
def create_chat_model(model_section: Optional[str] = None) -> BaseChatModel:
|
||||
"""
|
||||
创建聊天模型（兼容现有代码）
|
||||
|
||||
这是现有 llm_factory.create_chat_model 的替代实现，
|
||||
使用新的 Provider 架构但保持接口兼容
|
||||
"""
|
||||
return LLMFactory.create(model_section=model_section)
|
||||
@@ -1,222 +0,0 @@
|
||||
"""
|
||||
核心注册机制模块
|
||||
|
||||
提供统一的注册器模式，支持动态扩展：
|
||||
- NodeRegistry: 节点注册器
|
||||
- ToolRegistry: 工具注册器
|
||||
- WorkflowRegistry: 工作流注册器
|
||||
- ProviderRegistry: LLM Provider 注册器
|
||||
"""
|
||||
|
||||
from typing import Any, Callable, Dict, List, Optional, Type, TypeVar, Protocol, runtime_checkable
|
||||
from dataclasses import dataclass, field
|
||||
from enum import Enum
|
||||
import time
|
||||
|
||||
|
||||
T = TypeVar("T")
|
||||
|
||||
|
||||
@runtime_checkable
|
||||
class Registerable(Protocol[T]):
|
||||
"""可注册对象的协议"""
|
||||
name: str
|
||||
description: str = ""
|
||||
|
||||
|
||||
@dataclass
|
||||
class RegistryEntry:
|
||||
"""注册条目"""
|
||||
name: str
|
||||
instance: Any
|
||||
metadata: Dict[str, Any] = field(default_factory=dict)
|
||||
registered_at: float = field(default_factory=time.time)
|
||||
|
||||
|
||||
class BaseRegistry:
|
||||
"""基础注册器"""
|
||||
|
||||
_entries: Dict[str, RegistryEntry] = {}
|
||||
|
||||
@classmethod
|
||||
def register(cls, name: str, metadata: Optional[Dict[str, Any]] = None):
|
||||
"""
|
||||
注册装饰器
|
||||
|
||||
Usage:
|
||||
@NodeRegistry.register("my_node", metadata={"category": "processing"})
|
||||
def my_node(state: AgentState) -> AgentState:
|
||||
...
|
||||
"""
|
||||
def decorator(obj: T) -> T:
|
||||
entry = RegistryEntry(
|
||||
name=name,
|
||||
instance=obj,
|
||||
metadata=metadata or {},
|
||||
)
|
||||
cls._entries[name] = entry
|
||||
return obj
|
||||
return decorator
|
||||
|
||||
@classmethod
|
||||
def get(cls, name: str) -> Optional[Any]:
|
||||
"""获取注册的对象"""
|
||||
entry = cls._entries.get(name)
|
||||
return entry.instance if entry else None
|
||||
|
||||
@classmethod
|
||||
def get_entry(cls, name: str) -> Optional[RegistryEntry]:
|
||||
"""获取注册条目（包含元数据）"""
|
||||
return cls._entries.get(name)
|
||||
|
||||
@classmethod
|
||||
def list_names(cls) -> List[str]:
|
||||
"""列出所有注册名称"""
|
||||
return list(cls._entries.keys())
|
||||
|
||||
@classmethod
|
||||
def list_entries(cls) -> List[RegistryEntry]:
|
||||
"""列出所有注册条目"""
|
||||
return list(cls._entries.values())
|
||||
|
||||
@classmethod
|
||||
def unregister(cls, name: str) -> bool:
|
||||
"""注销注册"""
|
||||
if name in cls._entries:
|
||||
del cls._entries[name]
|
||||
return True
|
||||
return False
|
||||
|
||||
@classmethod
|
||||
def clear(cls):
|
||||
"""清空注册表"""
|
||||
cls._entries.clear()
|
||||
|
||||
|
||||
class NodeRegistry(BaseRegistry):
|
||||
"""节点注册器 - 用于注册 Agent 工作流节点"""
|
||||
_entries: Dict[str, RegistryEntry] = {}
|
||||
|
||||
|
||||
class ToolRegistry(BaseRegistry):
|
||||
"""工具注册器 - 用于注册工具"""
|
||||
_entries: Dict[str, RegistryEntry] = {}
|
||||
|
||||
|
||||
class WorkflowRegistry(BaseRegistry):
|
||||
"""工作流注册器 - 用于注册工作流类型"""
|
||||
_entries: Dict[str, RegistryEntry] = {}
|
||||
|
||||
|
||||
class ProviderRegistry(BaseRegistry):
|
||||
"""LLM Provider 注册器"""
|
||||
_entries: Dict[str, RegistryEntry] = {}
|
||||
|
||||
|
||||
@dataclass
|
||||
class ToolMetadata:
|
||||
"""工具元数据"""
|
||||
name: str
|
||||
description: str
|
||||
version: str = "1.0.0"
|
||||
timeout: int = 30
|
||||
retry: int = 0
|
||||
parameters_schema: Optional[Dict[str, Any]] = None
|
||||
requires_auth: bool = False
|
||||
tags: List[str] = field(default_factory=list)
|
||||
|
||||
|
||||
@dataclass
|
||||
class WorkflowMetadata:
|
||||
"""工作流元数据"""
|
||||
name: str
|
||||
description: str
|
||||
version: str = "1.0.0"
|
||||
agent_class: Optional[Type] = None
|
||||
default_model: Optional[str] = None
|
||||
supported_features: List[str] = field(default_factory=list)
|
||||
|
||||
|
||||
@dataclass
|
||||
class ProviderMetadata:
|
||||
"""LLM Provider 元数据"""
|
||||
name: str
|
||||
description: str
|
||||
provider_type: str
|
||||
supported_models: List[str] = field(default_factory=list)
|
||||
config_schema: Optional[Dict[str, Any]] = None
|
||||
|
||||
|
||||
def register_tool(
|
||||
name: str,
|
||||
description: str = "",
|
||||
version: str = "1.0.0",
|
||||
timeout: int = 30,
|
||||
retry: int = 0,
|
||||
tags: Optional[List[str]] = None,
|
||||
):
|
||||
"""
|
||||
工具注册装饰器
|
||||
|
||||
Usage:
|
||||
@register_tool("calculator", "数学计算", timeout=10)
|
||||
class CalculatorTool(BaseTool):
|
||||
...
|
||||
"""
|
||||
metadata = ToolMetadata(
|
||||
name=name,
|
||||
description=description,
|
||||
version=version,
|
||||
timeout=timeout,
|
||||
retry=retry,
|
||||
tags=tags or [],
|
||||
)
|
||||
return ToolRegistry.register(name, {"tool_metadata": metadata})
|
||||
|
||||
|
||||
def register_workflow(
|
||||
name: str,
|
||||
description: str = "",
|
||||
version: str = "1.0.0",
|
||||
default_model: Optional[str] = None,
|
||||
supported_features: Optional[List[str]] = None,
|
||||
):
|
||||
"""
|
||||
工作流注册装饰器
|
||||
|
||||
Usage:
|
||||
@register_workflow("data_query", "数据查询工作流")
|
||||
class DataQueryAgent(BaseAgent):
|
||||
...
|
||||
"""
|
||||
metadata = WorkflowMetadata(
|
||||
name=name,
|
||||
description=description,
|
||||
version=version,
|
||||
default_model=default_model,
|
||||
supported_features=supported_features or [],
|
||||
)
|
||||
return WorkflowRegistry.register(name, {"workflow_metadata": metadata})
|
||||
|
||||
|
||||
def register_provider(
|
||||
name: str,
|
||||
provider_type: str,
|
||||
description: str = "",
|
||||
supported_models: Optional[List[str]] = None,
|
||||
):
|
||||
"""
|
||||
LLM Provider 注册装饰器
|
||||
|
||||
Usage:
|
||||
@register_provider("openai", "openai", supported_models=["gpt-4", "gpt-3.5"])
|
||||
class OpenAIProvider:
|
||||
...
|
||||
"""
|
||||
metadata = ProviderMetadata(
|
||||
name=name,
|
||||
description=description,
|
||||
provider_type=provider_type,
|
||||
supported_models=supported_models or [],
|
||||
)
|
||||
return ProviderRegistry.register(name, {"provider_metadata": metadata})
|
||||
@@ -1,248 +0,0 @@
|
||||
"""
|
||||
统一响应格式模块
|
||||
|
||||
提供标准化的 API 响应和流式事件格式
|
||||
"""
|
||||
|
||||
from typing import Any, Dict, Generic, List, Optional, TypeVar, Literal
|
||||
from pydantic import BaseModel, Field
|
||||
import time
|
||||
import uuid
|
||||
|
||||
|
||||
T = TypeVar("T")
|
||||
|
||||
|
||||
class ApiResponse(BaseModel, Generic[T]):
|
||||
"""
|
||||
统一 API 响应格式
|
||||
|
||||
所有 API 响应都使用这个格式，提供一致的响应结构
|
||||
|
||||
Usage:
|
||||
@router.get("/users/{user_id}")
|
||||
async def get_user(user_id: str) -> ApiResponse[User]:
|
||||
user = await user_service.get(user_id)
|
||||
return ApiResponse.success(data=user)
|
||||
"""
|
||||
|
||||
code: str = Field(default="success", description="响应代码")
|
||||
message: str = Field(default="", description="响应消息")
|
||||
data: Optional[T] = Field(default=None, description="响应数据")
|
||||
trace_id: Optional[str] = Field(default=None, description="追踪ID")
|
||||
timestamp: int = Field(
|
||||
default_factory=lambda: int(time.time() * 1000),
|
||||
description="时间戳(毫秒)"
|
||||
)
|
||||
|
||||
@classmethod
|
||||
def success(cls, data: T = None, message: str = "", trace_id: Optional[str] = None) -> "ApiResponse[T]":
|
||||
"""创建成功响应"""
|
||||
return cls(
|
||||
code="success",
|
||||
message=message,
|
||||
data=data,
|
||||
trace_id=trace_id or uuid.uuid4().hex,
|
||||
)
|
||||
|
||||
@classmethod
|
||||
def error(
|
||||
cls,
|
||||
code: str = "error",
|
||||
message: str = "",
|
||||
data: T = None,
|
||||
trace_id: Optional[str] = None,
|
||||
) -> "ApiResponse[T]":
|
||||
"""创建错误响应"""
|
||||
return cls(
|
||||
code=code,
|
||||
message=message,
|
||||
data=data,
|
||||
trace_id=trace_id or uuid.uuid4().hex,
|
||||
)
|
||||
|
||||
@classmethod
|
||||
def from_exception(cls, exc: Exception, trace_id: Optional[str] = None) -> "ApiResponse[None]":
|
||||
"""从异常创建错误响应"""
|
||||
return cls.error(
|
||||
code="internal_error",
|
||||
message=str(exc),
|
||||
trace_id=trace_id,
|
||||
)
|
||||
|
||||
def is_success(self) -> bool:
|
||||
"""判断是否成功"""
|
||||
return self.code == "success"
|
||||
|
||||
|
||||
class PagedResponse(BaseModel, Generic[T]):
|
||||
"""
|
||||
分页响应格式
|
||||
|
||||
用于返回分页数据
|
||||
"""
|
||||
|
||||
items: List[T] = Field(default_factory=list, description="数据列表")
|
||||
total: int = Field(default=0, description="总数")
|
||||
page: int = Field(default=1, description="当前页")
|
||||
page_size: int = Field(default=20, description="每页大小")
|
||||
total_pages: int = Field(default=0, description="总页数")
|
||||
|
||||
@classmethod
|
||||
def create(
|
||||
cls,
|
||||
items: List[T],
|
||||
total: int,
|
||||
page: int = 1,
|
||||
page_size: int = 20,
|
||||
) -> "PagedResponse[T]":
|
||||
"""创建分页响应"""
|
||||
total_pages = (total + page_size - 1) // page_size if page_size > 0 else 0
|
||||
return cls(
|
||||
items=items,
|
||||
total=total,
|
||||
page=page,
|
||||
page_size=page_size,
|
||||
total_pages=total_pages,
|
||||
)
|
||||
|
||||
|
||||
class StreamEvent(BaseModel):
|
||||
"""
|
||||
流式响应事件
|
||||
|
||||
用于 SSE (Server-Sent Events) 流式响应
|
||||
|
||||
Usage:
|
||||
async def event_stream():
|
||||
yield StreamEvent(event="start", data="Processing started")
|
||||
# ... 处理逻辑
|
||||
yield StreamEvent(event="result", data=json.dumps(result))
|
||||
yield StreamEvent(event="done", data="")
|
||||
"""
|
||||
|
||||
event: str = Field(..., description="事件类型")
|
||||
data: str = Field(default="", description="事件数据")
|
||||
event_id: Optional[str] = Field(default=None, description="事件ID")
|
||||
retry: Optional[int] = Field(default=None, description="重试间隔(毫秒)")
|
||||
|
||||
def to_sse(self) -> str:
|
||||
"""转换为 SSE 格式字符串"""
|
||||
lines = [f"event: {self.event}"]
|
||||
if self.event_id:
|
||||
lines.append(f"id: {self.event_id}")
|
||||
if self.retry:
|
||||
lines.append(f"retry: {self.retry}")
|
||||
lines.append(f"data: {self.data}")
|
||||
lines.append("")
|
||||
lines.append("")
|
||||
return "\n".join(lines)
|
||||
|
||||
@classmethod
|
||||
def message(cls, data: str, event_id: Optional[str] = None) -> "StreamEvent":
|
||||
"""创建消息事件"""
|
||||
return cls(event="message", data=data, event_id=event_id)
|
||||
|
||||
@classmethod
|
||||
def done(cls) -> "StreamEvent":
|
||||
"""创建完成事件"""
|
||||
return cls(event="done", data="[DONE]")
|
||||
|
||||
@classmethod
|
||||
def error(cls, message: str) -> "StreamEvent":
|
||||
"""创建错误事件"""
|
||||
return cls(event="error", data=message)
|
||||
|
||||
|
||||
class WorkflowEvent(BaseModel):
|
||||
"""
|
||||
工作流事件
|
||||
|
||||
用于工作流执行过程中的状态通知
|
||||
"""
|
||||
|
||||
workflow_id: str = Field(..., description="工作流ID")
|
||||
event_type: Literal[
|
||||
"started",
|
||||
"node_started",
|
||||
"node_completed",
|
||||
"node_failed",
|
||||
"completed",
|
||||
"failed",
|
||||
] = Field(..., description="事件类型")
|
||||
node_name: Optional[str] = Field(None, description="节点名称")
|
||||
data: Optional[Dict[str, Any]] = Field(None, description="事件数据")
|
||||
error: Optional[str] = Field(None, description="错误信息")
|
||||
timestamp: int = Field(
|
||||
default_factory=lambda: int(time.time() * 1000),
|
||||
description="时间戳"
|
||||
)
|
||||
|
||||
@classmethod
|
||||
def started(cls, workflow_id: str) -> "WorkflowEvent":
|
||||
"""创建开始事件"""
|
||||
return cls(workflow_id=workflow_id, event_type="started")
|
||||
|
||||
@classmethod
|
||||
def node_started(cls, workflow_id: str, node_name: str) -> "WorkflowEvent":
|
||||
"""创建节点开始事件"""
|
||||
return cls(
|
||||
workflow_id=workflow_id,
|
||||
event_type="node_started",
|
||||
node_name=node_name,
|
||||
)
|
||||
|
||||
@classmethod
|
||||
def node_completed(
|
||||
cls,
|
||||
workflow_id: str,
|
||||
node_name: str,
|
||||
data: Optional[Dict[str, Any]] = None,
|
||||
) -> "WorkflowEvent":
|
||||
"""创建节点完成事件"""
|
||||
return cls(
|
||||
workflow_id=workflow_id,
|
||||
event_type="node_completed",
|
||||
node_name=node_name,
|
||||
data=data,
|
||||
)
|
||||
|
||||
@classmethod
|
||||
def completed(
|
||||
cls,
|
||||
workflow_id: str,
|
||||
data: Optional[Dict[str, Any]] = None,
|
||||
) -> "WorkflowEvent":
|
||||
"""创建完成事件"""
|
||||
return cls(workflow_id=workflow_id, event_type="completed", data=data)
|
||||
|
||||
@classmethod
|
||||
def failed(
|
||||
cls,
|
||||
workflow_id: str,
|
||||
error: str,
|
||||
node_name: Optional[str] = None,
|
||||
) -> "WorkflowEvent":
|
||||
"""创建失败事件"""
|
||||
return cls(
|
||||
workflow_id=workflow_id,
|
||||
event_type="failed",
|
||||
node_name=node_name,
|
||||
error=error,
|
||||
)
|
||||
|
||||
|
||||
class ErrorCode:
|
||||
"""错误代码常量"""
|
||||
|
||||
SUCCESS = "success"
|
||||
UNKNOWN_ERROR = "unknown_error"
|
||||
INVALID_REQUEST = "invalid_request"
|
||||
INVALID_WORKFLOW_TYPE = "invalid_workflow_type"
|
||||
SQL_GENERATION_FAILED = "sql_generation_failed"
|
||||
TOOL_NOT_FOUND = "tool_not_found"
|
||||
TOOL_EXECUTION_FAILED = "tool_execution_failed"
|
||||
INTERNAL_ERROR = "internal_error"
|
||||
TIMEOUT = "timeout"
|
||||
RATE_LIMITED = "rate_limited"
|
||||
UNAUTHORIZED = "unauthorized"
|
||||
-199
@@ -1,199 +0,0 @@
|
||||
"""
|
||||
增强的状态管理模块
|
||||
|
||||
使用 Pydantic 提供类型安全和验证
|
||||
"""
|
||||
|
||||
from typing import Any, Dict, List, Optional, Literal
|
||||
from pydantic import BaseModel, Field, field_validator
|
||||
from langchain_core.messages import BaseMessage, HumanMessage, AIMessage, SystemMessage
|
||||
|
||||
|
||||
class StateContext(BaseModel):
|
||||
"""状态上下文 - 存储工作流执行过程中的数据"""
|
||||
|
||||
original_input: Optional[str] = Field(None, description="用户原始输入")
|
||||
normalized_input: Optional[str] = Field(None, description="规范化后的输入")
|
||||
intent: Optional[str] = Field(None, description="识别的意图")
|
||||
table_match: Optional[Dict[str, Any]] = Field(None, description="表名匹配结果")
|
||||
final_sql: Optional[str] = Field(None, description="生成的 SQL")
|
||||
sr_api_result: Optional[Any] = Field(None, description="API 执行结果")
|
||||
|
||||
class Config:
|
||||
extra = "allow"
|
||||
|
||||
def get(self, key: str, default: Any = None) -> Any:
|
||||
"""获取上下文值"""
|
||||
return getattr(self, key, default)
|
||||
|
||||
def set(self, key: str, value: Any) -> None:
|
||||
"""设置上下文值"""
|
||||
setattr(self, key, value)
|
||||
|
||||
def to_dict(self) -> Dict[str, Any]:
|
||||
"""转换为字典"""
|
||||
return self.model_dump(exclude_none=True)
|
||||
|
||||
|
||||
class AgentState(BaseModel):
|
||||
"""
|
||||
Agent 工作流状态定义
|
||||
|
||||
使用 Pydantic 提供类型安全和验证
|
||||
"""
|
||||
|
||||
messages: List[BaseMessage] = Field(default_factory=list, description="消息历史")
|
||||
current_step: str = Field(default="start", description="当前步骤")
|
||||
context: StateContext = Field(default_factory=StateContext, description="上下文数据")
|
||||
|
||||
model_config = {
|
||||
"arbitrary_types_allowed": True,
|
||||
"extra": "forbid",
|
||||
}
|
||||
|
||||
@field_validator("messages", mode="before")
|
||||
@classmethod
|
||||
def validate_messages(cls, v):
|
||||
"""验证并转换消息列表"""
|
||||
if not isinstance(v, list):
|
||||
return []
|
||||
|
||||
result = []
|
||||
for msg in v:
|
||||
if isinstance(msg, BaseMessage):
|
||||
result.append(msg)
|
||||
elif isinstance(msg, dict):
|
||||
msg_type = msg.get("type", "human")
|
||||
content = msg.get("content", "")
|
||||
if msg_type == "human":
|
||||
result.append(HumanMessage(content=content))
|
||||
elif msg_type == "ai":
|
||||
result.append(AIMessage(content=content))
|
||||
elif msg_type == "system":
|
||||
result.append(SystemMessage(content=content))
|
||||
return result
|
||||
|
||||
def add_message(self, message: BaseMessage) -> "AgentState":
|
||||
"""添加消息并返回新状态"""
|
||||
return AgentState(
|
||||
messages=[*self.messages, message],
|
||||
current_step=self.current_step,
|
||||
context=self.context,
|
||||
)
|
||||
|
||||
def add_human_message(self, content: str) -> "AgentState":
|
||||
"""添加用户消息"""
|
||||
return self.add_message(HumanMessage(content=content))
|
||||
|
||||
def add_ai_message(self, content: str) -> "AgentState":
|
||||
"""添加 AI 消息"""
|
||||
return self.add_message(AIMessage(content=content))
|
||||
|
||||
def update_step(self, step: str) -> "AgentState":
|
||||
"""更新当前步骤"""
|
||||
return AgentState(
|
||||
messages=self.messages,
|
||||
current_step=step,
|
||||
context=self.context,
|
||||
)
|
||||
|
||||
def update_context(self, **kwargs) -> "AgentState":
|
||||
"""更新上下文"""
|
||||
new_context = self.context.model_copy()
|
||||
for key, value in kwargs.items():
|
||||
new_context.set(key, value)
|
||||
return AgentState(
|
||||
messages=self.messages,
|
||||
current_step=self.current_step,
|
||||
context=new_context,
|
||||
)
|
||||
|
||||
def get_last_message(self) -> Optional[BaseMessage]:
|
||||
"""获取最后一条消息"""
|
||||
return self.messages[-1] if self.messages else None
|
||||
|
||||
def get_context(self, key: str, default: Any = None) -> Any:
|
||||
"""获取上下文值"""
|
||||
return self.context.get(key, default)
|
||||
|
||||
def to_legacy_format(self) -> Dict[str, Any]:
|
||||
"""
|
||||
转换为旧格式（兼容现有代码）
|
||||
|
||||
现有代码期望 state 是一个可修改的对象，
|
||||
这个方法返回一个兼容的字典格式
|
||||
"""
|
||||
return {
|
||||
"messages": self.messages,
|
||||
"current_step": self.current_step,
|
||||
"context": self.context.to_dict(),
|
||||
}
|
||||
|
||||
@classmethod
|
||||
def from_legacy_format(cls, data: Dict[str, Any]) -> "AgentState":
|
||||
"""从旧格式创建"""
|
||||
context_data = data.get("context", {})
|
||||
if isinstance(context_data, StateContext):
|
||||
context = context_data
|
||||
else:
|
||||
context = StateContext(**context_data) if context_data else StateContext()
|
||||
|
||||
return cls(
|
||||
messages=data.get("messages", []),
|
||||
current_step=data.get("current_step", "start"),
|
||||
context=context,
|
||||
)
|
||||
|
||||
|
||||
class MutableAgentState:
|
||||
"""
|
||||
可变的 Agent 状态包装器
|
||||
|
||||
用于兼容现有代码中直接修改 state 的模式
|
||||
"""
|
||||
|
||||
def __init__(self, state: Optional[AgentState] = None):
|
||||
self._state = state or AgentState()
|
||||
self._context_overrides: Dict[str, Any] = {}
|
||||
|
||||
@property
|
||||
def messages(self) -> List[BaseMessage]:
|
||||
return self._state.messages
|
||||
|
||||
@messages.setter
|
||||
def messages(self, value: List[BaseMessage]):
|
||||
self._state = AgentState(
|
||||
messages=value,
|
||||
current_step=self._state.current_step,
|
||||
context=self._state.context,
|
||||
)
|
||||
|
||||
@property
|
||||
def current_step(self) -> str:
|
||||
return self._state.current_step
|
||||
|
||||
@current_step.setter
|
||||
def current_step(self, value: str):
|
||||
self._state = AgentState(
|
||||
messages=self._state.messages,
|
||||
current_step=value,
|
||||
context=self._state.context,
|
||||
)
|
||||
|
||||
@property
|
||||
def context(self) -> Dict[str, Any]:
|
||||
"""返回可修改的上下文字典"""
|
||||
result = self._state.context.to_dict()
|
||||
result.update(self._context_overrides)
|
||||
return result
|
||||
|
||||
def to_immutable(self) -> AgentState:
|
||||
"""转换为不可变状态"""
|
||||
context = self._state.context.model_copy()
|
||||
for key, value in self._context_overrides.items():
|
||||
context.set(key, value)
|
||||
return AgentState(
|
||||
messages=self._state.messages,
|
||||
current_step=self._state.current_step,
|
||||
context=context,
|
||||
)
|
||||
Vendored
+111
@@ -0,0 +1,111 @@
|
||||
// apbo-boat-agent/deploy/dev/Jenkinsfile
|
||||
pipeline {
|
||||
agent any
|
||||
|
||||
tools {
|
||||
jdk 'jdk21'
|
||||
maven 'apache-maven-3.9.12' // 与 Global Tool Configuration 中配置的 Name 保持一致
|
||||
}
|
||||
|
||||
environment {
|
||||
ENVIRONMENT = 'dev'
|
||||
DOCKER_REGISTRY = '10.122.172.43:9080' // 私有镜像仓库地址
|
||||
DOCKER_CREDENTIALS_ID = 'harbor-credentials-id' // Jenkins 中 Docker 凭证 ID
|
||||
DOCKER_PROJECT = 'apbo' // Jenkins 中 Docker 凭证 ID
|
||||
KUBECONFIG_CREDENTIALS_ID = 'k3s-cluster1-config' // Jenkins 中 kubeconfig 凭证 ID
|
||||
PROJECT_MODULE = 'apbo-boat-agent'
|
||||
|
||||
NAMESPACE = 'apbo-${ENVIRONMENT}' // 与 deployment.yaml 中的 namespace 一致
|
||||
IMAGE_TAG = "${ENVIRONMENT}-${BUILD_NUMBER}"
|
||||
IMAGE_NAME = "${DOCKER_REGISTRY}/${DOCKER_PROJECT}/${PROJECT_MODULE}:${IMAGE_TAG}"
|
||||
}
|
||||
|
||||
stages {
|
||||
|
||||
stage('Checkout') {
|
||||
steps {
|
||||
checkout scm
|
||||
}
|
||||
}
|
||||
|
||||
stage('Check Code Changes') {
|
||||
steps {
|
||||
script {
|
||||
def prev = env.GIT_PREVIOUS_SUCCESSFUL_COMMIT ?: ''
|
||||
if (!prev?.trim()) {
|
||||
echo "未找到上次成功构建提交，默认执行构建"
|
||||
env.SKIP_BUILD = 'false'
|
||||
} else {
|
||||
int rc = sh(
|
||||
script: "git diff --quiet ${prev} HEAD -- apbo-boat-agent",
|
||||
returnStatus: true
|
||||
)
|
||||
env.SKIP_BUILD = (rc == 0) ? 'true' : 'false'
|
||||
}
|
||||
|
||||
echo "代码变更检查结果: SKIP_BUILD=${env.SKIP_BUILD}"
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
|
||||
stage('Build & Push Docker Image') {
|
||||
when {
|
||||
expression { env.SKIP_BUILD != 'true' }
|
||||
}
|
||||
steps {
|
||||
script {
|
||||
docker.withRegistry("http://${DOCKER_REGISTRY}", DOCKER_CREDENTIALS_ID) {
|
||||
dir('.') {
|
||||
def image = docker.build(
|
||||
"${IMAGE_NAME}",
|
||||
"-f apbo-boat-agent/deploy/${ENVIRONMENT}/Dockerfile --build-arg PIP_OPTIONS=\"--no-hash-check\" ./apbo-boat-agent"
|
||||
)
|
||||
image.push()
|
||||
image.push("${ENVIRONMENT}-latest")
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
stage('Deploy to K3s') {
|
||||
steps {
|
||||
script {
|
||||
// 使用 withCredentials 绑定 kubeconfig 文件
|
||||
withCredentials([file(credentialsId: KUBECONFIG_CREDENTIALS_ID, variable: 'KUBECONFIG')]) {
|
||||
// 设置 KUBECONFIG 环境变量
|
||||
withEnv(["KUBECONFIG=${env.KUBECONFIG}"]) {
|
||||
// 先 apply 整个 deployment.yaml（确保资源存在）
|
||||
sh "kubectl apply -f ${PROJECT_MODULE}/deploy/${ENVIRONMENT}/deployment.yaml -n ${NAMESPACE}"
|
||||
|
||||
// 滚动更新镜像
|
||||
sh "kubectl set image deployment/apbo-boat-agent-${ENVIRONMENT} apbo-boat-agent=${IMAGE_NAME} -n ${NAMESPACE} --record"
|
||||
|
||||
// 等待 rollout 完成
|
||||
sh "kubectl rollout status deployment/apbo-boat-agent-${ENVIRONMENT} -n ${NAMESPACE}"
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
post {
|
||||
success {
|
||||
script {
|
||||
echo '清理本次构建的 Docker 镜像以释放磁盘空间...'
|
||||
// 注意：此操作需要在 Jenkins 节点上安装并配置好 Docker 客户端，且能访问私有仓库
|
||||
sh """
|
||||
docker rmi ${IMAGE_NAME} || true
|
||||
"""
|
||||
// 清理所有悬空镜像，解决 <none> 问题
|
||||
sh 'docker image prune -f'
|
||||
echo '镜像清理完成。'
|
||||
}
|
||||
}
|
||||
failure {
|
||||
echo '部署失败，请检查日志'
|
||||
}
|
||||
}
|
||||
}
|
||||
@@ -0,0 +1,9 @@
|
||||
# K8s 模块
|
||||
|
||||
## 作用
|
||||
|
||||
存放 Kubernetes 部署清单，用于服务容器化部署。
|
||||
|
||||
## 文件
|
||||
|
||||
- `deployment.yaml`：应用部署配置
|
||||
@@ -0,0 +1,59 @@
|
||||
# apbo-boat-agent/deploy/dev/deployment.yaml
|
||||
apiVersion: apps/v1
|
||||
kind: Deployment
|
||||
metadata:
|
||||
name: apbo-boat-agent-dev
|
||||
namespace: apbo-dev # 替换为实际 namespace
|
||||
spec:
|
||||
strategy:
|
||||
type: Recreate # 防止出现之前的服务还没有下掉，端口占用，导致新的服务起不来
|
||||
replicas: 1
|
||||
selector:
|
||||
matchLabels:
|
||||
app: apbo-boat-agent-dev
|
||||
template:
|
||||
metadata:
|
||||
labels:
|
||||
app: apbo-boat-agent-dev
|
||||
spec:
|
||||
hostNetwork: true # 关键：使用宿主机网络
|
||||
containers:
|
||||
- name: apbo-boat-agent
|
||||
image: 10.122.172.43:9080/apbo-boat-agent:dev-latest # 占位镜像，Jenkins 会覆盖
|
||||
ports:
|
||||
- containerPort: 26004
|
||||
# 由于 hostNetwork，containerPort 直接占用宿主机 8080 端口
|
||||
env:
|
||||
- name: SPRING_PROFILES_ACTIVE
|
||||
value: "dev"
|
||||
- name: NACOS_SERVER_ADDR
|
||||
value: "10.122.132.204:8848" # 根据实际 Nacos 地址调整
|
||||
- name: NACOS_NAMESPACE
|
||||
value: "apbo_dev"
|
||||
- name: NACOS_GROUP
|
||||
value: "apbo"
|
||||
- name: NACOS_USERNAME
|
||||
value: "nacos"
|
||||
- name: NACOS_PASSWORD
|
||||
value: "bgs20250901"
|
||||
# 如有其他配置，通过环境变量传递
|
||||
resources:
|
||||
requests:
|
||||
memory: "1Gi"
|
||||
cpu: "1000m"
|
||||
limits:
|
||||
memory: "2Gi"
|
||||
cpu: "2000m"
|
||||
---
|
||||
apiVersion: v1
|
||||
kind: Service
|
||||
metadata:
|
||||
name: apbo-boat-agent-dev
|
||||
namespace: apbo-dev
|
||||
spec:
|
||||
selector:
|
||||
app: apbo-boat-agent-dev
|
||||
ports:
|
||||
- port: 8000
|
||||
targetPort: 26004
|
||||
type: ClusterIP # 该 Service 仅用于集群内 DNS 发现，实际访问通过宿主机 IP + 8080
|
||||
@@ -0,0 +1,24 @@
|
||||
# Docs 模块
|
||||
|
||||
## 核心流程图
|
||||
|
||||
```mermaid
|
||||
flowchart TD
|
||||
A[用户请求] --> B[API: endpoints]
|
||||
B --> C[WorkflowManager]
|
||||
C --> D[ConversationAgent]
|
||||
|
||||
D --> E[analyze_intent]
|
||||
E --> F[process_input]
|
||||
F --> G[normalize_input]
|
||||
G --> H[classify_query_mode]
|
||||
H --> I[match_table]
|
||||
I --> J[load_sql_prompt]
|
||||
J --> K[build_sql_plan]
|
||||
K --> L[generate_sql]
|
||||
L --> M[execute_sql]
|
||||
M --> N[generate_response]
|
||||
N --> O[update_context]
|
||||
|
||||
O --> P[返回结果]
|
||||
```
|
||||
@@ -0,0 +1,9 @@
|
||||
# Examples 模块
|
||||
|
||||
## 作用
|
||||
|
||||
提供最小可运行示例，帮助快速理解项目调用方式。
|
||||
|
||||
## 文件
|
||||
|
||||
- `basic_usage.py`：工作流管理器基础调用示例
|
||||
@@ -1,33 +0,0 @@
|
||||
apiVersion: apps/v1
|
||||
kind: Deployment
|
||||
metadata:
|
||||
name: more-dots
|
||||
namespace: more-dots
|
||||
spec:
|
||||
replicas: 2
|
||||
selector:
|
||||
matchLabels:
|
||||
app: more-dots
|
||||
template:
|
||||
metadata:
|
||||
labels:
|
||||
app: more-dots
|
||||
spec:
|
||||
containers:
|
||||
- name: more-dots
|
||||
image: 10.128.62.130:8843/more_dots:latest
|
||||
ports:
|
||||
- containerPort: 8000
|
||||
---
|
||||
apiVersion: v1
|
||||
kind: Service
|
||||
metadata:
|
||||
name: more-dots-service
|
||||
namespace: more-dots
|
||||
spec:
|
||||
selector:
|
||||
app: more-dots
|
||||
ports:
|
||||
- port: 80
|
||||
targetPort: 8000
|
||||
type: ClusterIP
|
||||
@@ -0,0 +1,30 @@
|
||||
# 开发依赖
|
||||
# 使用方式：pip install -r requirements-dev.txt
|
||||
|
||||
# 包含所有生产依赖
|
||||
-r requirements.txt
|
||||
|
||||
# 测试框架
|
||||
pytest>=7.4.0
|
||||
pytest-cov>=4.1.0
|
||||
pytest-asyncio>=0.21.0
|
||||
pytest-mock>=3.11.0
|
||||
|
||||
# 代码质量
|
||||
flake8>=6.1.0
|
||||
black>=23.7.0
|
||||
isort>=5.12.0
|
||||
mypy>=1.5.0
|
||||
pylint>=2.17.0
|
||||
|
||||
# 类型检查
|
||||
types-PyYAML>=6.0.0
|
||||
types-redis>=4.6.0
|
||||
|
||||
# 开发工具
|
||||
pre-commit>=3.4.0
|
||||
ipython>=8.15.0
|
||||
|
||||
# 文档（可选）
|
||||
mkdocs>=1.5.0
|
||||
mkdocs-material>=9.4.0
|
||||
@@ -8,3 +8,5 @@ uvicorn>=0.30.0
|
||||
nacos-sdk-python==2.0.9
|
||||
httpx>=0.27.0
|
||||
pyyaml>=6.0.1
|
||||
redis>=5.0.0
|
||||
pymysql>=1.1.1
|
||||
|
||||
@@ -0,0 +1,12 @@
|
||||
# Schemas 模块
|
||||
|
||||
## 作用
|
||||
|
||||
定义 API 与工作流的数据模型，统一请求与响应结构。
|
||||
|
||||
## 文件
|
||||
|
||||
- `agent_input.py` / `agent_output.py`：Agent 入参与出参模型
|
||||
- `tool_input.py` / `tool_output.py`：工具调用模型
|
||||
- `chat_message_request.py` / `chat_message_response.py`：聊天接口模型，其中 `ChatMessageRequestDTO` 对齐前端 `query / inputs / response_mode / user / conversation_id / files` DTO
|
||||
- `stream_input.py`：流式接口输入模型
|
||||
@@ -0,0 +1,22 @@
|
||||
"""数据模型层"""
|
||||
|
||||
from .agent_input import AgentInput
|
||||
from .agent_output import AgentOutput
|
||||
from .tool_input import ToolInput
|
||||
from .tool_output import ToolOutput
|
||||
from .chat_message_request import ChatMessageRequestDTO, ChatMessageFileDTO
|
||||
from .chat_message_response import ChatMessageResponseDTO
|
||||
from .message_feedback_request import MessageFeedbackRequestDTO
|
||||
from .messages import MessagesDTO
|
||||
|
||||
__all__ = [
|
||||
"AgentInput",
|
||||
"AgentOutput",
|
||||
"ToolInput",
|
||||
"ToolOutput",
|
||||
"ChatMessageRequestDTO",
|
||||
"ChatMessageFileDTO",
|
||||
"ChatMessageResponseDTO",
|
||||
"MessageFeedbackRequestDTO",
|
||||
"MessagesDTO",
|
||||
]
|
||||
+4
-12
@@ -1,16 +1,8 @@
|
||||
from typing import Any, Dict, Optional
|
||||
|
||||
from pydantic import BaseModel, ConfigDict, Field
|
||||
from schemas.chat_message_request import ChatMessageRequestDTO
|
||||
|
||||
|
||||
class AgentInput(BaseModel):
|
||||
"""统一工作流输入模型（新版本 DTO）"""
|
||||
class AgentInput(ChatMessageRequestDTO):
|
||||
"""兼容旧名称，实际与 ChatMessageRequestDTO 使用同一套前端请求模型。"""
|
||||
|
||||
|
||||
model_config = ConfigDict(extra="forbid")
|
||||
|
||||
query: str
|
||||
conversation_id: Optional[str] = None
|
||||
workflow_type: str = "conversation"
|
||||
response_mode: str = "blocking"
|
||||
user: Optional[str] = None
|
||||
inputs: Dict[str, Any] = Field(default_factory=dict)
|
||||
|
||||
@@ -1,22 +1,23 @@
|
||||
from typing import Any, Dict, List, Optional
|
||||
from typing import Any, List, Optional
|
||||
|
||||
from pydantic import BaseModel, ConfigDict, Field
|
||||
|
||||
|
||||
class ChatMessageFileDTO(BaseModel):
|
||||
"""文件输入模型（预留）"""
|
||||
"""文件输入模型（保持与前端 DTO 兼容，允许附带任意文件元数据）。"""
|
||||
|
||||
model_config = ConfigDict(extra="allow")
|
||||
|
||||
|
||||
class ChatMessageRequestDTO(BaseModel):
|
||||
"""/api/workflows/stream 请求模型（对齐标准 chat message 请求）"""
|
||||
"""/api/workflows/stream 请求模型（对齐前端 ChatMessageRequestDTO）。"""
|
||||
|
||||
model_config = ConfigDict(extra="forbid")
|
||||
|
||||
query: str
|
||||
inputs: Dict[str, Any] = Field(default_factory=dict)
|
||||
response_mode: str = "streaming"
|
||||
user: Optional[str] = None
|
||||
conversation_id: Optional[str] = None
|
||||
files: List[ChatMessageFileDTO] = Field(default_factory=list)
|
||||
query: Optional[str] = Field(default=None, description="用户输入/提问内容。")
|
||||
inputs: Any = Field(default_factory=dict, description="App 定义的变量值，默认 {}。")
|
||||
response_mode: Optional[str] = Field(default=None, description="streaming 或 blocking。")
|
||||
user: Optional[str] = Field(default=None, description="用户唯一标识。")
|
||||
conversation_id: Optional[str] = Field(default=None, description="可选会话 ID。")
|
||||
files: List[ChatMessageFileDTO] = Field(default_factory=list, description="可选文件列表。")
|
||||
auto_generate_name: Optional[bool] = Field(default=None, description="兼容旧前端字段，当前后端忽略。")
|
||||
|
||||
@@ -0,0 +1,18 @@
|
||||
from typing import Literal, Optional
|
||||
|
||||
from pydantic import BaseModel, Field, model_validator
|
||||
|
||||
|
||||
class MessageFeedbackRequestDTO(BaseModel):
|
||||
"""消息反馈请求模型"""
|
||||
|
||||
message_id: str = Field(..., description="消息 ID")
|
||||
feedback: Literal["like", "dislike"] = Field(..., description="反馈类型: like/dislike")
|
||||
feedback_content: Optional[str] = Field(default=None, description="点踩反馈内容")
|
||||
|
||||
@model_validator(mode="after")
|
||||
def validate_feedback_content(self):
|
||||
if self.feedback == "dislike" and not (self.feedback_content or "").strip():
|
||||
raise ValueError("feedback_content is required when feedback=dislike")
|
||||
return self
|
||||
|
||||
@@ -0,0 +1,19 @@
|
||||
from typing import Any, Dict, Optional
|
||||
|
||||
from pydantic import BaseModel, Field
|
||||
|
||||
|
||||
class MessagesDTO(BaseModel):
|
||||
"""messages 表字段契约，对齐 Java Messages 实体。"""
|
||||
|
||||
message_id: str = Field(..., description="消息 ID")
|
||||
conversation_id: str = Field(..., description="会话 ID")
|
||||
user: Optional[str] = Field(default=None, description="用户")
|
||||
query: str = Field(..., description="用户输入 / 提问内容")
|
||||
answer: Optional[str] = Field(default=None, description="回答消息内容")
|
||||
feedback: Optional[str] = Field(default=None, description="点赞 like / 点踩 dislike")
|
||||
feedback_content: Optional[str] = Field(default=None, description="点踩内容")
|
||||
created_at: int = Field(..., description="创建时间(毫秒时间戳)")
|
||||
updated_at: int = Field(..., description="更新时间(毫秒时间戳)")
|
||||
log: Dict[str, Any] = Field(default_factory=dict, description="当前对话日志(JSON)")
|
||||
|
||||
@@ -1,7 +1,5 @@
|
||||
from schemas.agent_input import AgentInput
|
||||
from schemas.chat_message_request import ChatMessageRequestDTO
|
||||
|
||||
|
||||
class StreamInputDTO(AgentInput):
|
||||
"""流式输入 DTO（与统一 AgentInput 保持一致）"""
|
||||
|
||||
response_mode: str = "streaming"
|
||||
class StreamInputDTO(ChatMessageRequestDTO):
|
||||
"""流式输入 DTO（与统一 ChatMessageRequestDTO 保持一致）。"""
|
||||
|
||||
@@ -1,37 +0,0 @@
|
||||
from typing import Any, Dict, Optional
|
||||
|
||||
from pydantic import BaseModel, ConfigDict, Field
|
||||
|
||||
|
||||
class SuperAgentRequest(BaseModel):
|
||||
"""Super Agent 请求模型"""
|
||||
|
||||
model_config = ConfigDict(extra="forbid")
|
||||
|
||||
query: str = Field(..., desc ription="用户查询")
|
||||
conversation_id: Optional[str] = Field(None, description="会话ID")
|
||||
user_id: Optional[str] = Field(None, description="用户ID")
|
||||
workflow_type: str = Field(default="conversation", description="工作流类型")
|
||||
context: Dict[str, str] = Field(default_factory=dict, description="上下文信息")
|
||||
timeout_seconds: int = Field(default=30, description="超时时间(秒)")
|
||||
|
||||
|
||||
class SuperAgentResponse(BaseModel):
|
||||
"""Super Agent 响应模型"""
|
||||
|
||||
conversation_id: str = Field(..., description="会话ID")
|
||||
workflow_type: str = Field(..., description="工作流类型")
|
||||
status: str = Field(default="success", description="状态: success/error")
|
||||
sql: Optional[str] = Field(None, description="生成的SQL")
|
||||
result: Optional[str] = Field(None, description="查询结果")
|
||||
error: Optional[str] = Field(None, description="错误信息")
|
||||
metadata: Dict[str, str] = Field(default_factory=dict, description="元数据")
|
||||
|
||||
|
||||
class SuperAgentStreamEvent(BaseModel):
|
||||
"""Super Agent 流式响应事件"""
|
||||
|
||||
conversation_id: str = Field(..., description="会话ID")
|
||||
event: str = Field(..., description="事件类型: sql_generated/sql_executing/result/error/done")
|
||||
data: str = Field(..., description="事件数据")
|
||||
timestamp: int = Field(..., description="时间戳(毫秒)")
|
||||
@@ -0,0 +1,21 @@
|
||||
# Scripts 模块
|
||||
|
||||
## 目录说明
|
||||
|
||||
`scripts` 提供本地调试与数据同步脚本。
|
||||
|
||||
## 文件清单
|
||||
|
||||
- `console_chat.py`：命令行多轮问答调试
|
||||
- `demo_chat.py`：示例交互脚本
|
||||
- `sync_ragflow_templates.py`：同步表检索模板到 RAGFlow
|
||||
- `sync_sql_gen_prompts.py`：同步 SQL 提示词到 RAGFlow
|
||||
|
||||
## 常用命令
|
||||
|
||||
```powershell
|
||||
python scripts\console_chat.py --skip-sr-api --show-sql
|
||||
python scripts\sync_ragflow_templates.py
|
||||
python scripts\sync_sql_gen_prompts.py
|
||||
```
|
||||
|
||||
@@ -0,0 +1,336 @@
|
||||
#!/usr/bin/env python3
|
||||
"""控制台问数脚本：支持交互式多轮问答和单次执行。"""
|
||||
|
||||
from __future__ import annotations
|
||||
|
||||
import argparse
|
||||
import json
|
||||
import sys
|
||||
import traceback
|
||||
import uuid
|
||||
from pathlib import Path
|
||||
from typing import Any, Dict, Iterable, Optional, Sequence
|
||||
|
||||
# 允许直接使用 `python scripts/console_chat.py` 运行
|
||||
PROJECT_ROOT = Path(__file__).resolve().parent.parent
|
||||
if str(PROJECT_ROOT) not in sys.path:
|
||||
sys.path.insert(0, str(PROJECT_ROOT))
|
||||
|
||||
from agent.agents.conversation import ConversationAgent
|
||||
from config import Config
|
||||
|
||||
|
||||
def build_parser() -> argparse.ArgumentParser:
|
||||
parser = argparse.ArgumentParser(
|
||||
description="在控制台中直接输入自然语言问题，调用 ConversationAgent 进行问数。"
|
||||
)
|
||||
parser.add_argument("--model-section", default=None, help="可选：指定 config.ini 中的模型配置段")
|
||||
parser.add_argument("--conversation-id", default=None, help="可选：会话 ID，仅用于展示和上下文标识")
|
||||
parser.add_argument("--user", default="console-user", help="可选：用户标识")
|
||||
parser.add_argument("--query", "-q", default=None, help="单次执行模式：直接执行一条问题后退出")
|
||||
parser.add_argument("--skip-sr-api", action="store_true", help="仅生成 SQL，不执行 SR API")
|
||||
parser.add_argument("--show-sql", action="store_true", help="额外打印生成的 SQL")
|
||||
parser.add_argument("--show-context", action="store_true", help="额外打印完整上下文 JSON")
|
||||
parser.add_argument("--show-plan", action="store_true", help="额外打印 SQL 规划 JSON")
|
||||
parser.add_argument("--no-banner", action="store_true", help="不显示启动横幅")
|
||||
return parser
|
||||
|
||||
|
||||
def print_banner(model_section: Optional[str], conversation_id: str, skip_sr_api: bool) -> None:
|
||||
print("=" * 72)
|
||||
print("APBO Console Chat")
|
||||
print(f"Model Section : {model_section or 'default'}")
|
||||
print(f"Conversation : {conversation_id}")
|
||||
print(f"Execution : {'SQL only' if skip_sr_api else 'SQL + SR API'}")
|
||||
print("Commands : /quit /exit /sql /context /plan /exec")
|
||||
print("=" * 72)
|
||||
|
||||
|
||||
def _safe_json(data: Any) -> str:
|
||||
try:
|
||||
return json.dumps(data, ensure_ascii=False, indent=2, default=str)
|
||||
except Exception:
|
||||
return str(data)
|
||||
|
||||
|
||||
def _looks_like_json(text: str) -> bool:
|
||||
stripped = (text or "").strip()
|
||||
return stripped.startswith("{") or stripped.startswith("[")
|
||||
|
||||
|
||||
def _try_json_loads(value: Any) -> Any:
|
||||
if isinstance(value, (dict, list)):
|
||||
return value
|
||||
if isinstance(value, str) and _looks_like_json(value):
|
||||
try:
|
||||
return json.loads(value)
|
||||
except Exception:
|
||||
return value
|
||||
return value
|
||||
|
||||
|
||||
def parse_sr_api_result(raw_result: Any) -> Any:
|
||||
"""解析 SR API 返回值，兼容外层 envelope 和内层 text JSON。"""
|
||||
parsed = _try_json_loads(raw_result)
|
||||
if isinstance(parsed, dict) and "text" in parsed:
|
||||
text_payload = _try_json_loads(parsed.get("text"))
|
||||
parsed = {**parsed, "text": text_payload}
|
||||
return parsed
|
||||
|
||||
|
||||
def _find_table_candidate(value: Any) -> Any:
|
||||
if isinstance(value, list):
|
||||
return value
|
||||
if isinstance(value, dict):
|
||||
if "columns" in value and any(key in value for key in ("rows", "data", "values")):
|
||||
return value
|
||||
for key in ("data", "rows", "records", "record", "items", "list", "result", "text"):
|
||||
nested = value.get(key)
|
||||
if isinstance(nested, (list, dict)):
|
||||
found = _find_table_candidate(nested)
|
||||
if found is not None:
|
||||
return found
|
||||
return None
|
||||
|
||||
|
||||
def extract_table_rows(parsed_result: Any) -> tuple[list[str], list[list[str]]]:
|
||||
"""从常见查询结果结构中提取表头和二维行数据。"""
|
||||
candidate = _find_table_candidate(parsed_result)
|
||||
if candidate is None:
|
||||
return [], []
|
||||
|
||||
if isinstance(candidate, dict) and isinstance(candidate.get("columns"), list):
|
||||
headers = [str(col) for col in candidate.get("columns") or []]
|
||||
raw_rows = candidate.get("rows") or candidate.get("data") or candidate.get("values") or []
|
||||
if raw_rows and all(isinstance(row, dict) for row in raw_rows):
|
||||
return headers or list(raw_rows[0].keys()), [
|
||||
[str((row or {}).get(header, "")) for header in (headers or list(raw_rows[0].keys()))]
|
||||
for row in raw_rows
|
||||
]
|
||||
return headers, [[str(cell) for cell in row] for row in raw_rows if isinstance(row, (list, tuple))]
|
||||
|
||||
if isinstance(candidate, list) and candidate:
|
||||
if all(isinstance(row, dict) for row in candidate):
|
||||
headers: list[str] = []
|
||||
for row in candidate:
|
||||
for key in row.keys():
|
||||
if key not in headers:
|
||||
headers.append(str(key))
|
||||
return headers, [[str((row or {}).get(header, "")) for header in headers] for row in candidate]
|
||||
if all(isinstance(row, (list, tuple)) for row in candidate):
|
||||
width = max(len(row) for row in candidate)
|
||||
headers = [f"col_{idx + 1}" for idx in range(width)]
|
||||
return headers, [[str(row[idx]) if idx < len(row) else "" for idx in range(width)] for row in candidate]
|
||||
|
||||
return [], []
|
||||
|
||||
|
||||
def render_text_table(headers: Sequence[str], rows: Sequence[Sequence[str]], *, max_width: int = 28, max_rows: int = 20) -> str:
|
||||
"""将二维数据渲染成纯文本表格。"""
|
||||
if not headers or not rows:
|
||||
return "<empty table>"
|
||||
|
||||
def clip(value: Any) -> str:
|
||||
text = str(value).replace("\r", " ").replace("\n", " ")
|
||||
return text if len(text) <= max_width else text[: max_width - 3] + "..."
|
||||
|
||||
display_rows = list(rows[:max_rows])
|
||||
str_rows = [[clip(cell) for cell in row] for row in display_rows]
|
||||
clipped_headers = [clip(header) for header in headers]
|
||||
|
||||
widths = []
|
||||
for idx, header in enumerate(clipped_headers):
|
||||
col_values = [row[idx] if idx < len(row) else "" for row in str_rows]
|
||||
widths.append(max(len(header), *(len(value) for value in col_values)) if col_values else len(header))
|
||||
|
||||
def render_row(values: Sequence[str]) -> str:
|
||||
padded = []
|
||||
for idx, width in enumerate(widths):
|
||||
value = values[idx] if idx < len(values) else ""
|
||||
padded.append(value.ljust(width))
|
||||
return "| " + " | ".join(padded) + " |"
|
||||
|
||||
separator = "+-" + "-+-".join("-" * width for width in widths) + "-+"
|
||||
lines = [separator, render_row(clipped_headers), separator]
|
||||
lines.extend(render_row(row) for row in str_rows)
|
||||
lines.append(separator)
|
||||
if len(rows) > max_rows:
|
||||
lines.append(f"... showing first {max_rows} of {len(rows)} rows")
|
||||
return "\n".join(lines)
|
||||
|
||||
|
||||
def _format_sr_api_table(sr_api_result: Any) -> Optional[str]:
|
||||
parsed = parse_sr_api_result(sr_api_result)
|
||||
headers, rows = extract_table_rows(parsed)
|
||||
if not headers or not rows:
|
||||
return None
|
||||
|
||||
summary = f"Query Result: {len(rows)} row(s)"
|
||||
if isinstance(parsed, dict) and parsed.get("status_code") is not None:
|
||||
summary += f" | status={parsed.get('status_code')}"
|
||||
return summary + "\n" + render_text_table(headers, rows)
|
||||
|
||||
|
||||
def format_result(
|
||||
result: Dict[str, Any],
|
||||
*,
|
||||
show_sql: bool = False,
|
||||
show_context: bool = False,
|
||||
show_plan: bool = False,
|
||||
) -> str:
|
||||
context = (result or {}).get("context") or {}
|
||||
messages = (result or {}).get("messages") or []
|
||||
sr_api_result = context.get("sr_api_result")
|
||||
|
||||
answer = ""
|
||||
if messages:
|
||||
last = messages[-1]
|
||||
answer = getattr(last, "content", "") or str(last)
|
||||
if not answer:
|
||||
answer = str(sr_api_result or context.get("final_sql") or "<empty response>")
|
||||
|
||||
table_block = _format_sr_api_table(sr_api_result) if sr_api_result else None
|
||||
if table_block and (_looks_like_json(answer) or answer.strip().lower() in {"ok", "success"}):
|
||||
answer = "查询成功，结果已按二维表格展示如下。"
|
||||
|
||||
blocks = [f"Answer:\n{answer}"]
|
||||
|
||||
if table_block:
|
||||
blocks.append(table_block)
|
||||
|
||||
if show_sql and context.get("final_sql"):
|
||||
blocks.append(f"SQL:\n{context['final_sql']}")
|
||||
|
||||
if show_plan and context.get("sql_plan"):
|
||||
blocks.append(f"SQL Plan:\n{_safe_json(context['sql_plan'])}")
|
||||
|
||||
if show_context:
|
||||
blocks.append(f"Context:\n{_safe_json(context)}")
|
||||
|
||||
return "\n\n".join(blocks)
|
||||
|
||||
|
||||
def run_turn(
|
||||
agent: ConversationAgent,
|
||||
query: str,
|
||||
*,
|
||||
user: str,
|
||||
conversation_id: str,
|
||||
skip_sr_api: bool,
|
||||
show_sql: bool,
|
||||
show_context: bool,
|
||||
show_plan: bool,
|
||||
) -> Dict[str, Any]:
|
||||
result = agent.run(
|
||||
query,
|
||||
user=user,
|
||||
conversation_id=conversation_id,
|
||||
skip_sr_api=skip_sr_api,
|
||||
debug_node_trace=True,
|
||||
)
|
||||
print(format_result(result, show_sql=show_sql, show_context=show_context, show_plan=show_plan))
|
||||
return result
|
||||
|
||||
|
||||
def interactive_loop(args: argparse.Namespace) -> int:
|
||||
conversation_id = args.conversation_id or f"console_{uuid.uuid4().hex[:8]}"
|
||||
agent = ConversationAgent(model_section=args.model_section)
|
||||
|
||||
show_sql = bool(args.show_sql)
|
||||
show_context = bool(args.show_context)
|
||||
show_plan = bool(args.show_plan)
|
||||
skip_sr_api = bool(args.skip_sr_api)
|
||||
|
||||
if not args.no_banner:
|
||||
print_banner(args.model_section, conversation_id, skip_sr_api)
|
||||
|
||||
while True:
|
||||
try:
|
||||
user_input = input("\n问数> ").strip()
|
||||
except (EOFError, KeyboardInterrupt):
|
||||
print("\nBye.")
|
||||
return 0
|
||||
|
||||
if not user_input:
|
||||
continue
|
||||
|
||||
lowered = user_input.lower()
|
||||
if lowered in {"/quit", "/exit", "quit", "exit"}:
|
||||
print("Bye.")
|
||||
return 0
|
||||
if lowered == "/sql":
|
||||
show_sql = not show_sql
|
||||
print(f"show_sql = {show_sql}")
|
||||
continue
|
||||
if lowered == "/context":
|
||||
show_context = not show_context
|
||||
print(f"show_context = {show_context}")
|
||||
continue
|
||||
if lowered == "/plan":
|
||||
show_plan = not show_plan
|
||||
print(f"show_plan = {show_plan}")
|
||||
continue
|
||||
if lowered == "/exec":
|
||||
skip_sr_api = not skip_sr_api
|
||||
print(f"skip_sr_api = {skip_sr_api}")
|
||||
continue
|
||||
|
||||
try:
|
||||
run_turn(
|
||||
agent,
|
||||
user_input,
|
||||
user=args.user,
|
||||
conversation_id=conversation_id,
|
||||
skip_sr_api=skip_sr_api,
|
||||
show_sql=show_sql,
|
||||
show_context=show_context,
|
||||
show_plan=show_plan,
|
||||
)
|
||||
except Exception as exc:
|
||||
print(f"\n[ERROR] {exc}")
|
||||
traceback.print_exc()
|
||||
|
||||
return 0
|
||||
|
||||
|
||||
def one_shot(args: argparse.Namespace) -> int:
|
||||
conversation_id = args.conversation_id or f"console_{uuid.uuid4().hex[:8]}"
|
||||
agent = ConversationAgent(model_section=args.model_section)
|
||||
try:
|
||||
run_turn(
|
||||
agent,
|
||||
args.query,
|
||||
user=args.user,
|
||||
conversation_id=conversation_id,
|
||||
skip_sr_api=bool(args.skip_sr_api),
|
||||
show_sql=bool(args.show_sql),
|
||||
show_context=bool(args.show_context),
|
||||
show_plan=bool(args.show_plan),
|
||||
)
|
||||
return 0
|
||||
except Exception as exc:
|
||||
print(f"[ERROR] {exc}", file=sys.stderr)
|
||||
traceback.print_exc()
|
||||
return 1
|
||||
|
||||
|
||||
def main(argv: Optional[Iterable[str]] = None) -> int:
|
||||
parser = build_parser()
|
||||
args = parser.parse_args(list(argv) if argv is not None else None)
|
||||
|
||||
try:
|
||||
Config.validate_config()
|
||||
except Exception as exc:
|
||||
print(f"Configuration error: {exc}", file=sys.stderr)
|
||||
print("Please check `config/config.ini` and your model/API settings.", file=sys.stderr)
|
||||
return 1
|
||||
|
||||
if args.query:
|
||||
return one_shot(args)
|
||||
return interactive_loop(args)
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
raise SystemExit(main())
|
||||
|
||||
|
||||
@@ -0,0 +1,167 @@
|
||||
#!/usr/bin/env python3
|
||||
"""简洁演示问数脚本：只保留问题输入与结果输出。"""
|
||||
|
||||
from __future__ import annotations
|
||||
|
||||
import argparse
|
||||
import sys
|
||||
import time
|
||||
import traceback
|
||||
import uuid
|
||||
from pathlib import Path
|
||||
from typing import Any, Dict, Iterable, Optional
|
||||
|
||||
# 允许直接使用 `python scripts/demo_chat.py` 运行
|
||||
PROJECT_ROOT = Path(__file__).resolve().parent.parent
|
||||
if str(PROJECT_ROOT) not in sys.path:
|
||||
sys.path.insert(0, str(PROJECT_ROOT))
|
||||
|
||||
from agent.agents.conversation import ConversationAgent
|
||||
from config import Config
|
||||
from scripts.console_chat import extract_table_rows, parse_sr_api_result, render_text_table
|
||||
|
||||
|
||||
def build_parser() -> argparse.ArgumentParser:
|
||||
parser = argparse.ArgumentParser(
|
||||
description="演示版控制台问数：仅展示耗时、SQL、结果表和数据行数。"
|
||||
)
|
||||
parser.add_argument("--model-section", default=None, help="可选：指定 config.ini 中的模型配置段")
|
||||
parser.add_argument("--conversation-id", default=None, help="可选：会话 ID")
|
||||
parser.add_argument("--user", default="demo-user", help="可选：用户标识")
|
||||
parser.add_argument("--query", "-q", default=None, help="单次执行模式：直接执行一条问题后退出")
|
||||
return parser
|
||||
|
||||
|
||||
def _last_answer_text(result: Dict[str, Any]) -> str:
|
||||
messages = (result or {}).get("messages") or []
|
||||
if not messages:
|
||||
return ""
|
||||
last = messages[-1]
|
||||
return getattr(last, "content", "") or str(last)
|
||||
|
||||
|
||||
def format_demo_result(result: Dict[str, Any], elapsed_seconds: float) -> str:
|
||||
context = (result or {}).get("context") or {}
|
||||
final_sql = str(context.get("final_sql") or "")
|
||||
parsed_result = parse_sr_api_result(context.get("sr_api_result"))
|
||||
headers, rows = extract_table_rows(parsed_result)
|
||||
row_count = len(rows)
|
||||
has_structured_result = context.get("sr_api_result") is not None and isinstance(parsed_result, (dict, list))
|
||||
is_empty_result = bool(context.get("is_empty_result"))
|
||||
response_source = str(context.get("response_source") or "")
|
||||
answer = _last_answer_text(result)
|
||||
|
||||
blocks = [f"耗时: {elapsed_seconds:.2f}s"]
|
||||
|
||||
if final_sql:
|
||||
blocks.append(f"SQL:\n{final_sql}")
|
||||
else:
|
||||
blocks.append("SQL:\n<未生成 SQL>")
|
||||
|
||||
blocks.append(f"数据行数: {row_count}")
|
||||
|
||||
if is_empty_result and response_source in {"model_empty_result_fallback", "empty_result_fixed_fallback"}:
|
||||
blocks.append(f"结果说明:\n{answer or '未查询到符合条件的数据，请尝试调整筛选条件后再查询。'}")
|
||||
elif has_structured_result:
|
||||
table_text = render_text_table(headers or ['result'], rows)
|
||||
blocks.append(f"SQL执行结果表:\n{table_text}")
|
||||
else:
|
||||
blocks.append(f"SQL执行结果:\n{answer or str(parsed_result or '<无结果>')}")
|
||||
|
||||
return "\n\n".join(blocks)
|
||||
|
||||
|
||||
def run_turn(
|
||||
agent: ConversationAgent,
|
||||
query: str,
|
||||
*,
|
||||
user: str,
|
||||
conversation_id: str,
|
||||
) -> Dict[str, Any]:
|
||||
started_at = time.perf_counter()
|
||||
result = agent.run(
|
||||
query,
|
||||
user=user,
|
||||
conversation_id=conversation_id,
|
||||
skip_sr_api=False,
|
||||
debug_node_trace=False,
|
||||
)
|
||||
elapsed_seconds = time.perf_counter() - started_at
|
||||
print(format_demo_result(result, elapsed_seconds))
|
||||
return result
|
||||
|
||||
|
||||
def interactive_loop(args: argparse.Namespace) -> int:
|
||||
conversation_id = args.conversation_id or f"demo_{uuid.uuid4().hex[:8]}"
|
||||
agent = ConversationAgent(model_section=args.model_section)
|
||||
|
||||
while True:
|
||||
try:
|
||||
user_input = input("\n问题> ").strip()
|
||||
except (EOFError, KeyboardInterrupt):
|
||||
print("\nBye.")
|
||||
return 0
|
||||
|
||||
if not user_input:
|
||||
continue
|
||||
|
||||
if user_input.lower() in {"/quit", "/exit", "quit", "exit"}:
|
||||
print("Bye.")
|
||||
return 0
|
||||
|
||||
try:
|
||||
run_turn(
|
||||
agent,
|
||||
user_input,
|
||||
user=args.user,
|
||||
conversation_id=conversation_id,
|
||||
)
|
||||
except Exception as exc:
|
||||
print(f"\n[ERROR] {exc}")
|
||||
traceback.print_exc()
|
||||
|
||||
return 0
|
||||
|
||||
|
||||
def one_shot(args: argparse.Namespace) -> int:
|
||||
conversation_id = args.conversation_id or f"demo_{uuid.uuid4().hex[:8]}"
|
||||
agent = ConversationAgent(model_section=args.model_section)
|
||||
query = str(args.query or "")
|
||||
try:
|
||||
run_turn(
|
||||
agent,
|
||||
query,
|
||||
user=args.user,
|
||||
conversation_id=conversation_id,
|
||||
)
|
||||
return 0
|
||||
except Exception as exc:
|
||||
print(f"[ERROR] {exc}", file=sys.stderr)
|
||||
traceback.print_exc()
|
||||
return 1
|
||||
|
||||
|
||||
def main(argv: Optional[Iterable[str]] = None) -> int:
|
||||
parser = build_parser()
|
||||
args = parser.parse_args(list(argv) if argv is not None else None)
|
||||
|
||||
try:
|
||||
Config.validate_config()
|
||||
except Exception as exc:
|
||||
print(f"Configuration error: {exc}", file=sys.stderr)
|
||||
print("Please check `config/config.ini` and your model/API settings.", file=sys.stderr)
|
||||
return 1
|
||||
|
||||
if args.query:
|
||||
return one_shot(args)
|
||||
return interactive_loop(args)
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
raise SystemExit(main())
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
@@ -1,8 +1,18 @@
|
||||
from pathlib import Path
|
||||
import sys
|
||||
|
||||
|
||||
PROJECT_ROOT = Path(__file__).resolve().parent.parent
|
||||
if str(PROJECT_ROOT) not in sys.path:
|
||||
sys.path.insert(0, str(PROJECT_ROOT))
|
||||
|
||||
|
||||
def main():
|
||||
from services.ragflow_sync import RagflowSync
|
||||
from services.integrations.ragflow_sync import RagflowSync
|
||||
syncer = RagflowSync()
|
||||
syncer.sync_table_retrieval()
|
||||
result = syncer.sync_table_retrieval()
|
||||
print("表名检索模板同步完成")
|
||||
print(result)
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
|
||||
@@ -1,10 +1,19 @@
|
||||
from services.ragflow_sync import RagflowSync
|
||||
from pathlib import Path
|
||||
import sys
|
||||
|
||||
|
||||
PROJECT_ROOT = Path(__file__).resolve().parent.parent
|
||||
if str(PROJECT_ROOT) not in sys.path:
|
||||
sys.path.insert(0, str(PROJECT_ROOT))
|
||||
|
||||
from services.integrations.ragflow_sync import RagflowSync
|
||||
|
||||
|
||||
def main():
|
||||
syncer = RagflowSync()
|
||||
syncer.sync_sql_gen_prompts()
|
||||
result = syncer.sync_sql_gen_prompts()
|
||||
print("SQL 生成提示词同步完成")
|
||||
print(result)
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
|
||||
@@ -0,0 +1,188 @@
|
||||
#!/usr/bin/env python3
|
||||
"""
|
||||
SQL 提示词 Redis 热更新脚本
|
||||
|
||||
用法:
|
||||
python scripts/update_sql_prompts.py # 同步所有本地文件到 Redis
|
||||
python scripts/update_sql_prompts.py --tables apbo_eta_ful apbo_eta_milestone # 同步指定表
|
||||
python scripts/update_sql_prompts.py --list # 列出 Redis 中的所有表
|
||||
python scripts/update_sql_prompts.py --delete apbo_eta_ful # 删除指定表
|
||||
python scripts/update_sql_prompts.py --from-file path/to/file.json --table apbo_eta_ful # 从指定文件更新
|
||||
"""
|
||||
|
||||
import argparse
|
||||
import json
|
||||
import sys
|
||||
from pathlib import Path
|
||||
|
||||
PROJECT_ROOT = Path(__file__).resolve().parent.parent
|
||||
if str(PROJECT_ROOT) not in sys.path:
|
||||
sys.path.insert(0, str(PROJECT_ROOT))
|
||||
|
||||
from config import Config
|
||||
from services.storage.cache import RedisCache
|
||||
|
||||
|
||||
def _first_line(value) -> str:
|
||||
if value is None:
|
||||
return ""
|
||||
text = str(value)
|
||||
return text.splitlines()[0].strip() if text else ""
|
||||
|
||||
|
||||
def _to_bool(value, default: bool = False) -> bool:
|
||||
text = _first_line(value).lower()
|
||||
if not text:
|
||||
return default
|
||||
return text in ("1", "true", "yes", "y", "on")
|
||||
|
||||
|
||||
def _to_int(value, default: int = 0) -> int:
|
||||
text = _first_line(value)
|
||||
if not text:
|
||||
return default
|
||||
try:
|
||||
return int(text)
|
||||
except Exception:
|
||||
return default
|
||||
|
||||
|
||||
def get_redis_cache() -> RedisCache:
|
||||
redis_cfg = Config.get_section("redis")
|
||||
enabled = _to_bool(redis_cfg.get("enabled", "false"))
|
||||
if not enabled:
|
||||
raise RuntimeError("Redis 未启用，请检查配置 redis.enabled")
|
||||
|
||||
url = _first_line(redis_cfg.get("url"))
|
||||
db = _to_int(redis_cfg.get("db", redis_cfg.get("database", 0)), default=0)
|
||||
if not url:
|
||||
host = _first_line(redis_cfg.get("host"))
|
||||
port = _first_line(redis_cfg.get("port", "6379")) or "6379"
|
||||
password = _first_line(redis_cfg.get("password", ""))
|
||||
username = _first_line(redis_cfg.get("username", ""))
|
||||
database = _first_line(redis_cfg.get("database", str(db))) or str(db)
|
||||
if host:
|
||||
from urllib.parse import quote_plus
|
||||
if username and password:
|
||||
auth = f"{quote_plus(username)}:{quote_plus(password)}@"
|
||||
elif password:
|
||||
auth = f":{quote_plus(password)}@"
|
||||
else:
|
||||
auth = ""
|
||||
url = f"redis://{auth}{host}:{port}/{database}"
|
||||
|
||||
if not url:
|
||||
raise RuntimeError("Redis 配置不完整，请检查 redis.url 或 redis.host")
|
||||
|
||||
return RedisCache(url=url, db=db)
|
||||
|
||||
|
||||
def get_ttl() -> int:
|
||||
redis_cfg = Config.get_section("redis")
|
||||
return _to_int(redis_cfg.get("sql_prompt_ttl", 0), default=0)
|
||||
|
||||
|
||||
def sync_from_local_files(cache: RedisCache, tables: list = None, ttl: int = None):
|
||||
prompts_dir = PROJECT_ROOT / "config" / "sql_gen_prompts"
|
||||
|
||||
if tables:
|
||||
files = [prompts_dir / f"{t}.json" for t in tables]
|
||||
else:
|
||||
files = list(prompts_dir.glob("*.json"))
|
||||
|
||||
results = {}
|
||||
for file_path in files:
|
||||
if not file_path.exists():
|
||||
print(f"[跳过] 文件不存在: {file_path}")
|
||||
continue
|
||||
|
||||
table_name = file_path.stem
|
||||
try:
|
||||
with open(file_path, "r", encoding="utf-8") as f:
|
||||
prompt = json.load(f)
|
||||
|
||||
key = f"sql_prompt:{table_name}"
|
||||
cache.set(key, json.dumps(prompt, ensure_ascii=False), ttl)
|
||||
results[table_name] = "success"
|
||||
print(f"[成功] {table_name}")
|
||||
except Exception as e:
|
||||
results[table_name] = f"failed: {e}"
|
||||
print(f"[失败] {table_name}: {e}")
|
||||
|
||||
return results
|
||||
|
||||
|
||||
def update_from_file(cache: RedisCache, file_path: str, table_name: str, ttl: int = None):
|
||||
path = Path(file_path)
|
||||
if not path.exists():
|
||||
print(f"[错误] 文件不存在: {file_path}")
|
||||
return False
|
||||
|
||||
try:
|
||||
with open(path, "r", encoding="utf-8") as f:
|
||||
prompt = json.load(f)
|
||||
|
||||
key = f"sql_prompt:{table_name}"
|
||||
cache.set(key, json.dumps(prompt, ensure_ascii=False), ttl)
|
||||
print(f"[成功] 已更新 {table_name}")
|
||||
return True
|
||||
except Exception as e:
|
||||
print(f"[失败] {table_name}: {e}")
|
||||
return False
|
||||
|
||||
|
||||
def list_tables(cache: RedisCache):
|
||||
keys = cache.keys("sql_prompt:*")
|
||||
tables = []
|
||||
for key in keys:
|
||||
parts = key.split(":", 1)
|
||||
if len(parts) == 2 and parts[1] != "table_list":
|
||||
tables.append(parts[1])
|
||||
|
||||
if tables:
|
||||
print("Redis 中的 SQL 提示词表:")
|
||||
for t in sorted(tables):
|
||||
print(f" - {t}")
|
||||
else:
|
||||
print("Redis 中没有 SQL 提示词")
|
||||
return tables
|
||||
|
||||
|
||||
def delete_table(cache: RedisCache, table_name: str):
|
||||
key = f"sql_prompt:{table_name}"
|
||||
cache.delete(key)
|
||||
print(f"[成功] 已删除 {table_name}")
|
||||
|
||||
|
||||
def main():
|
||||
parser = argparse.ArgumentParser(description="SQL 提示词 Redis 热更新工具")
|
||||
parser.add_argument("--tables", nargs="*", help="指定要同步的表名列表")
|
||||
parser.add_argument("--list", action="store_true", help="列出 Redis 中的所有表")
|
||||
parser.add_argument("--delete", type=str, help="删除指定表")
|
||||
parser.add_argument("--from-file", type=str, help="从指定文件更新")
|
||||
parser.add_argument("--table", type=str, help="目标表名（与 --from-file 配合使用）")
|
||||
|
||||
args = parser.parse_args()
|
||||
|
||||
try:
|
||||
cache = get_redis_cache()
|
||||
ttl = get_ttl()
|
||||
except Exception as e:
|
||||
print(f"[错误] {e}")
|
||||
sys.exit(1)
|
||||
|
||||
if args.list:
|
||||
list_tables(cache)
|
||||
elif args.delete:
|
||||
delete_table(cache, args.delete)
|
||||
elif args.from_file:
|
||||
if not args.table:
|
||||
print("[错误] 使用 --from-file 时必须指定 --table")
|
||||
sys.exit(1)
|
||||
update_from_file(cache, args.from_file, args.table, ttl)
|
||||
else:
|
||||
sync_from_local_files(cache, args.tables, ttl)
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
main()
|
||||
@@ -1,19 +1,83 @@
|
||||
import errno
|
||||
import logging
|
||||
import socket
|
||||
from contextlib import asynccontextmanager
|
||||
|
||||
import uvicorn
|
||||
from fastapi import FastAPI
|
||||
|
||||
try:
|
||||
import psutil
|
||||
except Exception: # pragma: no cover - optional runtime dependency for richer diagnostics
|
||||
psutil = None
|
||||
|
||||
from config import Config
|
||||
from workflows.workflow_manager import WorkflowManager
|
||||
from services.nacos_service import load_nacos_config, load_service_config, NacosManager
|
||||
from services.tool_router import ToolRouter
|
||||
from services.prompt_manager import get_prompt_manager
|
||||
from services.integrations.nacos_service import load_nacos_config, load_service_config, NacosManager
|
||||
from services.tools.tool_router import ToolRouter
|
||||
from services.core.prompt_manager import get_prompt_manager
|
||||
from api import endpoints
|
||||
|
||||
logger = logging.getLogger(__name__)
|
||||
|
||||
|
||||
def _find_listening_process_on_port(port: int) -> dict | None:
|
||||
if psutil is None:
|
||||
return None
|
||||
|
||||
try:
|
||||
for conn in psutil.net_connections(kind="tcp"):
|
||||
local_port = getattr(getattr(conn, "laddr", None), "port", None)
|
||||
if local_port != port or conn.status != psutil.CONN_LISTEN:
|
||||
continue
|
||||
|
||||
pid = conn.pid
|
||||
if pid is None:
|
||||
return {"pid": None, "process_name": None, "cmdline": None}
|
||||
|
||||
try:
|
||||
proc = psutil.Process(pid)
|
||||
return {
|
||||
"pid": pid,
|
||||
"process_name": proc.name(),
|
||||
"cmdline": " ".join(proc.cmdline()),
|
||||
}
|
||||
except Exception:
|
||||
return {"pid": pid, "process_name": None, "cmdline": None}
|
||||
except Exception:
|
||||
return None
|
||||
return None
|
||||
|
||||
|
||||
def _ensure_port_available(host: str, port: int) -> None:
|
||||
probe = socket.socket(socket.AF_INET, socket.SOCK_STREAM)
|
||||
try:
|
||||
probe.bind((host, port))
|
||||
except OSError as exc:
|
||||
if exc.errno == errno.EADDRINUSE or getattr(exc, "winerror", None) == 10048:
|
||||
process_info = _find_listening_process_on_port(port) or {}
|
||||
owner_bits = []
|
||||
if process_info.get("pid") is not None:
|
||||
owner_bits.append(f"pid={process_info['pid']}")
|
||||
if process_info.get("process_name"):
|
||||
owner_bits.append(f"name={process_info['process_name']}")
|
||||
if process_info.get("cmdline"):
|
||||
owner_bits.append(f"cmdline={process_info['cmdline']}")
|
||||
|
||||
logger.error(
|
||||
"端口占用，服务无法启动: host=%s port=%s config=%s%s",
|
||||
host,
|
||||
port,
|
||||
Config._get_config_path(),
|
||||
f" owner=({' | '.join(owner_bits)})" if owner_bits else "",
|
||||
)
|
||||
logger.error("请先停止占用该端口的进程，或修改 `config/config.ini` 中 `[app].port`。")
|
||||
raise SystemExit(1) from exc
|
||||
raise
|
||||
finally:
|
||||
probe.close()
|
||||
|
||||
|
||||
def create_app() -> FastAPI:
|
||||
"""创建 FastAPI 应用"""
|
||||
service_config = load_service_config()
|
||||
@@ -59,6 +123,7 @@ app = create_app()
|
||||
|
||||
if __name__ == "__main__":
|
||||
service_config = load_service_config()
|
||||
_ensure_port_available(service_config.host, service_config.port)
|
||||
uvicorn.run(
|
||||
"server:app",
|
||||
host=service_config.host,
|
||||
|
||||
@@ -0,0 +1,29 @@
|
||||
# Services 模块
|
||||
|
||||
## 目录说明
|
||||
|
||||
`services` 负责底层能力封装，包括模型、检索、存储、工具路由和异常体系。
|
||||
|
||||
```
|
||||
services/
|
||||
├── core/ # LLM / Prompt / 表匹配 / SQL Prompt 管理
|
||||
├── integrations/ # RAGFlow / Nacos 等外部集成
|
||||
├── storage/ # 消息存储、日志、缓存
|
||||
├── tools/ # 工具路由
|
||||
├── common/ # 通用错误定义
|
||||
└── README.md
|
||||
```
|
||||
|
||||
## 核心职责
|
||||
|
||||
- 为 Agent 提供可复用的基础服务
|
||||
- 屏蔽外部系统交互细节
|
||||
- 提供统一的数据持久化与缓存能力
|
||||
|
||||
## 文件
|
||||
|
||||
- `core/`：模型构建、提示词加载、表匹配、SQL Prompt 管理
|
||||
- `integrations/`：RAGFlow 与 Nacos 外部接入
|
||||
- `storage/`：缓存、消息存储、结构化日志
|
||||
- `tools/`：工具路由
|
||||
- `common/`：错误码与应用异常
|
||||
@@ -0,0 +1,74 @@
|
||||
"""服务层模块 - 核心与扩展分离架构"""
|
||||
|
||||
# 核心服务
|
||||
from services.core import (
|
||||
create_chat_model,
|
||||
get_prompt_manager,
|
||||
get_sql_prompt_manager,
|
||||
get_template_matcher,
|
||||
)
|
||||
|
||||
# 外部集成
|
||||
from services.integrations import (
|
||||
RagflowClient,
|
||||
extract_table_name,
|
||||
RagflowSync,
|
||||
)
|
||||
|
||||
# 可选的 Nacos 导入
|
||||
try:
|
||||
from services.integrations import (
|
||||
NacosManager,
|
||||
NacosConfig,
|
||||
ServiceConfig,
|
||||
load_nacos_config,
|
||||
load_service_config,
|
||||
)
|
||||
except ImportError:
|
||||
pass
|
||||
|
||||
# 数据存储
|
||||
from services.storage import (
|
||||
get_message_storage,
|
||||
MessageStorage,
|
||||
get_structured_logger,
|
||||
CacheBase,
|
||||
NoopCache,
|
||||
RedisCache,
|
||||
)
|
||||
|
||||
# 工具服务
|
||||
from services.tools import ToolRouter
|
||||
|
||||
# 基础设施
|
||||
from services.common import AppError, ErrorCode
|
||||
|
||||
__all__ = [
|
||||
# 核心服务
|
||||
"create_chat_model",
|
||||
"get_prompt_manager",
|
||||
"get_sql_prompt_manager",
|
||||
"get_template_matcher",
|
||||
# 外部集成
|
||||
"RagflowClient",
|
||||
"extract_table_name",
|
||||
"RagflowSync",
|
||||
# Nacos (可选)
|
||||
"NacosManager",
|
||||
"NacosConfig",
|
||||
"ServiceConfig",
|
||||
"load_nacos_config",
|
||||
"load_service_config",
|
||||
# 数据存储
|
||||
"get_message_storage",
|
||||
"MessageStorage",
|
||||
"get_structured_logger",
|
||||
"CacheBase",
|
||||
"NoopCache",
|
||||
"RedisCache",
|
||||
# 工具服务
|
||||
"ToolRouter",
|
||||
# 基础设施
|
||||
"AppError",
|
||||
"ErrorCode",
|
||||
]
|
||||
@@ -1,23 +0,0 @@
|
||||
from __future__ import annotations
|
||||
|
||||
from typing import Optional
|
||||
|
||||
|
||||
class CacheBase:
|
||||
"""缓存接口"""
|
||||
|
||||
def get(self, key: str) -> Optional[str]:
|
||||
raise NotImplementedError
|
||||
|
||||
def set(self, key: str, value: str, ttl: int) -> None:
|
||||
raise NotImplementedError
|
||||
|
||||
|
||||
class NoopCache(CacheBase):
|
||||
"""空实现缓存"""
|
||||
|
||||
def get(self, key: str) -> Optional[str]:
|
||||
return None
|
||||
|
||||
def set(self, key: str, value: str, ttl: int) -> None:
|
||||
return None
|
||||
@@ -0,0 +1,6 @@
|
||||
"""基础设施模块"""
|
||||
|
||||
from .app_errors import AppError, ErrorCode
|
||||
from .datetime_utils import DateTimeBundle, DateTimeGenerator
|
||||
|
||||
__all__ = ["AppError", "ErrorCode", "DateTimeBundle", "DateTimeGenerator"]
|
||||
@@ -6,11 +6,17 @@ from typing import Any, Dict, Optional
|
||||
|
||||
|
||||
class ErrorCode(str, Enum):
|
||||
INVALID_REQUEST = "INVALID_REQUEST"
|
||||
INVALID_WORKFLOW_TYPE = "INVALID_WORKFLOW_TYPE"
|
||||
INVALID_RESPONSE_MODE = "INVALID_RESPONSE_MODE"
|
||||
SQL_GENERATION_FAILED = "SQL_GENERATION_FAILED"
|
||||
TABLE_MATCH_FAILED = "TABLE_MATCH_FAILED"
|
||||
SQL_EXECUTION_FAILED = "SQL_EXECUTION_FAILED"
|
||||
RAGFLOW_RETRIEVE_FAILED = "RAGFLOW_RETRIEVE_FAILED"
|
||||
CONVERSATION_NOT_FOUND = "CONVERSATION_NOT_FOUND"
|
||||
CONVERSATION_CREATE_FAILED = "CONVERSATION_CREATE_FAILED"
|
||||
CONVERSATION_UPDATE_FAILED = "CONVERSATION_UPDATE_FAILED"
|
||||
MESSAGE_SAVE_FAILED = "MESSAGE_SAVE_FAILED"
|
||||
CONFIG_INVALID = "CONFIG_INVALID"
|
||||
INTERNAL_ERROR = "INTERNAL_ERROR"
|
||||
|
||||
@@ -0,0 +1,152 @@
|
||||
from __future__ import annotations
|
||||
|
||||
from dataclasses import dataclass
|
||||
from datetime import date, datetime, time as dt_time
|
||||
from typing import Any
|
||||
from zoneinfo import ZoneInfo
|
||||
|
||||
|
||||
@dataclass(frozen=True)
|
||||
class DateTimeBundle:
|
||||
"""Unified datetime payload for storage and API usage."""
|
||||
|
||||
dt: datetime
|
||||
db_datetime: datetime
|
||||
epoch_seconds: int
|
||||
epoch_millis: int
|
||||
yyyymmdd: str
|
||||
date_str: str
|
||||
datetime_str: str
|
||||
iso_str: str
|
||||
|
||||
|
||||
class DateTimeGenerator:
|
||||
"""Parse and generate datetime values in multiple common formats."""
|
||||
|
||||
DEFAULT_TZ = ZoneInfo("Asia/Shanghai")
|
||||
SUPPORTED_FORMATS = (
|
||||
"%Y%m%d",
|
||||
"%Y%m%d%H%M%S",
|
||||
"%Y-%m-%d",
|
||||
"%Y/%m/%d",
|
||||
"%Y-%m-%d %H:%M",
|
||||
"%Y/%m/%d %H:%M",
|
||||
"%Y-%m-%d %H:%M:%S",
|
||||
"%Y/%m/%d %H:%M:%S",
|
||||
"%Y-%m-%d %H:%M:%S.%f",
|
||||
"%Y/%m/%d %H:%M:%S.%f",
|
||||
)
|
||||
|
||||
@classmethod
|
||||
def now(cls) -> DateTimeBundle:
|
||||
return cls.bundle()
|
||||
|
||||
@classmethod
|
||||
def bundle(cls, value: Any = None, *, default_to_now: bool = True) -> DateTimeBundle:
|
||||
dt = cls.parse(value, default_to_now=default_to_now)
|
||||
epoch_seconds = int(dt.timestamp())
|
||||
epoch_millis = int(dt.timestamp() * 1000)
|
||||
return DateTimeBundle(
|
||||
dt=dt,
|
||||
db_datetime=dt.replace(tzinfo=None),
|
||||
epoch_seconds=epoch_seconds,
|
||||
epoch_millis=epoch_millis,
|
||||
yyyymmdd=dt.strftime("%Y%m%d"),
|
||||
date_str=dt.strftime("%Y-%m-%d"),
|
||||
datetime_str=dt.strftime("%Y-%m-%d %H:%M:%S"),
|
||||
iso_str=dt.isoformat(),
|
||||
)
|
||||
|
||||
@classmethod
|
||||
def pair(cls, created_value: Any = None, updated_value: Any = None) -> tuple[DateTimeBundle, DateTimeBundle]:
|
||||
created = cls.bundle(created_value, default_to_now=True)
|
||||
updated = cls.bundle(updated_value if updated_value is not None else created.epoch_millis, default_to_now=True)
|
||||
return created, updated
|
||||
|
||||
@classmethod
|
||||
def parse(cls, value: Any = None, *, default_to_now: bool = True) -> datetime:
|
||||
if value is None:
|
||||
if default_to_now:
|
||||
return datetime.now(cls.DEFAULT_TZ)
|
||||
raise ValueError("datetime value is None")
|
||||
|
||||
if isinstance(value, datetime):
|
||||
return cls._normalize_datetime(value)
|
||||
|
||||
if isinstance(value, date):
|
||||
return datetime.combine(value, dt_time.min).replace(tzinfo=cls.DEFAULT_TZ)
|
||||
|
||||
if isinstance(value, (int, float)):
|
||||
return cls._parse_numeric(str(int(value)), default_to_now=default_to_now)
|
||||
|
||||
if isinstance(value, str):
|
||||
text = value.strip()
|
||||
if not text:
|
||||
if default_to_now:
|
||||
return datetime.now(cls.DEFAULT_TZ)
|
||||
raise ValueError("datetime value is blank")
|
||||
|
||||
if text.isdigit():
|
||||
return cls._parse_numeric(text, default_to_now=default_to_now)
|
||||
|
||||
iso_candidate = text.replace("Z", "+00:00")
|
||||
try:
|
||||
return cls._normalize_datetime(datetime.fromisoformat(iso_candidate))
|
||||
except Exception:
|
||||
pass
|
||||
|
||||
for fmt in cls.SUPPORTED_FORMATS:
|
||||
try:
|
||||
parsed = datetime.strptime(text, fmt)
|
||||
return parsed.replace(tzinfo=cls.DEFAULT_TZ)
|
||||
except Exception:
|
||||
continue
|
||||
|
||||
if default_to_now:
|
||||
return datetime.now(cls.DEFAULT_TZ)
|
||||
raise ValueError(f"unsupported datetime value: {value!r}")
|
||||
|
||||
@classmethod
|
||||
def _parse_numeric(cls, text: str, *, default_to_now: bool) -> datetime:
|
||||
if len(text) == 8:
|
||||
try:
|
||||
return datetime.strptime(text, "%Y%m%d").replace(tzinfo=cls.DEFAULT_TZ)
|
||||
except Exception:
|
||||
if default_to_now:
|
||||
return datetime.now(cls.DEFAULT_TZ)
|
||||
raise
|
||||
|
||||
if len(text) == 14:
|
||||
try:
|
||||
return datetime.strptime(text, "%Y%m%d%H%M%S").replace(tzinfo=cls.DEFAULT_TZ)
|
||||
except Exception:
|
||||
if default_to_now:
|
||||
return datetime.now(cls.DEFAULT_TZ)
|
||||
raise
|
||||
|
||||
if len(text) == 10:
|
||||
try:
|
||||
return datetime.fromtimestamp(int(text), tz=cls.DEFAULT_TZ)
|
||||
except Exception:
|
||||
if default_to_now:
|
||||
return datetime.now(cls.DEFAULT_TZ)
|
||||
raise
|
||||
|
||||
if len(text) == 13:
|
||||
try:
|
||||
return datetime.fromtimestamp(int(text) / 1000, tz=cls.DEFAULT_TZ)
|
||||
except Exception:
|
||||
if default_to_now:
|
||||
return datetime.now(cls.DEFAULT_TZ)
|
||||
raise
|
||||
|
||||
if default_to_now:
|
||||
return datetime.now(cls.DEFAULT_TZ)
|
||||
raise ValueError(f"unsupported numeric datetime value: {text!r}")
|
||||
|
||||
@classmethod
|
||||
def _normalize_datetime(cls, value: datetime) -> datetime:
|
||||
if value.tzinfo is None:
|
||||
return value.replace(tzinfo=cls.DEFAULT_TZ)
|
||||
return value.astimezone(cls.DEFAULT_TZ)
|
||||
|
||||
@@ -0,0 +1,13 @@
|
||||
"""核心服务模块"""
|
||||
|
||||
from .llm_factory import create_chat_model
|
||||
from .prompt_manager import get_prompt_manager
|
||||
from .sql_prompt_manager import get_sql_prompt_manager
|
||||
from .template_matcher import get_template_matcher
|
||||
|
||||
__all__ = [
|
||||
"create_chat_model",
|
||||
"get_prompt_manager",
|
||||
"get_sql_prompt_manager",
|
||||
"get_template_matcher",
|
||||
]
|
||||
@@ -1,6 +1,6 @@
|
||||
from typing import Optional
|
||||
from langchain_openai import ChatOpenAI
|
||||
from config import Config
|
||||
from config import Config, MAX_RETRIES, TIMEOUT
|
||||
|
||||
|
||||
def create_chat_model(model_section: Optional[str] = None) -> ChatOpenAI:
|
||||
@@ -11,6 +11,6 @@ def create_chat_model(model_section: Optional[str] = None) -> ChatOpenAI:
|
||||
api_key=model_config['api_key'],
|
||||
base_url=model_config.get('base_url'),
|
||||
temperature=0.1,
|
||||
max_retries=Config.MAX_RETRIES,
|
||||
timeout=Config.TIMEOUT
|
||||
max_retries=MAX_RETRIES,
|
||||
timeout=TIMEOUT
|
||||
)
|
||||
@@ -8,7 +8,7 @@ class PromptManager:
|
||||
"""提示词配置管理器"""
|
||||
|
||||
def __init__(self, config_path: Optional[str] = None):
|
||||
root_dir = os.path.dirname(os.path.dirname(__file__))
|
||||
root_dir = os.path.dirname(os.path.dirname(os.path.dirname(__file__)))
|
||||
self._config_path = config_path or os.path.join(root_dir, "config", "prompts.yaml")
|
||||
self._data: Dict[str, Any] = {}
|
||||
self.reload()
|
||||
@@ -0,0 +1,238 @@
|
||||
import json
|
||||
import os
|
||||
from typing import Any, Dict, List, Optional
|
||||
|
||||
from config import Config
|
||||
from services.storage.cache import CacheBase, NoopCache, RedisCache
|
||||
|
||||
|
||||
class SqlPromptManager:
|
||||
"""按表名读取 SQL 提示词，Redis 主存储 + 本地文件回退"""
|
||||
|
||||
KEY_PREFIX = "sql_prompt"
|
||||
TABLE_LIST_KEY = "sql_prompt:table_list"
|
||||
SOURCE_REDIS = "redis"
|
||||
SOURCE_FILE = "file"
|
||||
|
||||
def __init__(self, base_dir: Optional[str] = None):
|
||||
root_dir = os.path.dirname(os.path.dirname(os.path.dirname(__file__)))
|
||||
self._fallback_dir = base_dir or os.path.join(root_dir, "config", "sql_gen_prompts")
|
||||
self._cache = self._init_cache()
|
||||
self._cache_ttl = self._get_cache_ttl()
|
||||
self._use_redis_primary = self._get_use_redis_primary()
|
||||
|
||||
@staticmethod
|
||||
def _first_line(value: Any) -> str:
|
||||
if value is None:
|
||||
return ""
|
||||
text = str(value)
|
||||
return text.splitlines()[0].strip() if text else ""
|
||||
|
||||
@classmethod
|
||||
def _to_bool(cls, value: Any, default: bool = False) -> bool:
|
||||
text = cls._first_line(value).lower()
|
||||
if not text:
|
||||
return default
|
||||
return text in ("1", "true", "yes", "y", "on")
|
||||
|
||||
@classmethod
|
||||
def _to_int(cls, value: Any, default: int = 0) -> int:
|
||||
text = cls._first_line(value)
|
||||
if not text:
|
||||
return default
|
||||
try:
|
||||
return int(text)
|
||||
except Exception:
|
||||
return default
|
||||
|
||||
@classmethod
|
||||
def _extract_key_from_multiline_values(cls, redis_cfg: Dict[str, Any], target_key: str) -> str:
|
||||
token = f"{target_key}="
|
||||
for raw in redis_cfg.values():
|
||||
text = str(raw or "")
|
||||
for line in text.splitlines()[1:]:
|
||||
cleaned = line.strip()
|
||||
normalized = cleaned.replace(" ", "")
|
||||
if normalized.lower().startswith(token.lower()):
|
||||
return cleaned.split("=", 1)[1].strip()
|
||||
return ""
|
||||
|
||||
@classmethod
|
||||
def _get_cfg_value(cls, redis_cfg: Dict[str, Any], key: str, default: Any = "") -> Any:
|
||||
if key in redis_cfg:
|
||||
return redis_cfg.get(key, default)
|
||||
recovered = cls._extract_key_from_multiline_values(redis_cfg, key)
|
||||
return recovered if recovered else default
|
||||
|
||||
@classmethod
|
||||
def _get_cache_ttl(cls) -> Optional[int]:
|
||||
redis_cfg = Config.get_section("redis")
|
||||
ttl = cls._to_int(cls._get_cfg_value(redis_cfg, "sql_prompt_ttl", 0), default=0)
|
||||
if ttl:
|
||||
return ttl
|
||||
return None
|
||||
|
||||
@classmethod
|
||||
def _get_use_redis_primary(cls) -> bool:
|
||||
redis_cfg = Config.get_section("redis")
|
||||
enabled = cls._to_bool(cls._get_cfg_value(redis_cfg, "enabled", "false"), default=False)
|
||||
primary = cls._to_bool(cls._get_cfg_value(redis_cfg, "sql_prompt_redis_primary", "false"), default=False)
|
||||
return enabled and primary
|
||||
|
||||
@classmethod
|
||||
def _init_cache(cls):
|
||||
redis_cfg = Config.get_section("redis")
|
||||
enabled = cls._to_bool(cls._get_cfg_value(redis_cfg, "enabled", "false"), default=False)
|
||||
if not enabled:
|
||||
return NoopCache()
|
||||
|
||||
url = cls._first_line(cls._get_cfg_value(redis_cfg, "url"))
|
||||
db = cls._to_int(cls._get_cfg_value(redis_cfg, "db", cls._get_cfg_value(redis_cfg, "database", 0)), default=0)
|
||||
if not url:
|
||||
host = cls._first_line(cls._get_cfg_value(redis_cfg, "host"))
|
||||
port = cls._first_line(cls._get_cfg_value(redis_cfg, "port", "6379")) or "6379"
|
||||
password = cls._first_line(cls._get_cfg_value(redis_cfg, "password", ""))
|
||||
username = cls._first_line(cls._get_cfg_value(redis_cfg, "username", ""))
|
||||
database = cls._first_line(cls._get_cfg_value(redis_cfg, "database", str(db))) or str(db)
|
||||
if host:
|
||||
from urllib.parse import quote_plus
|
||||
if username and password:
|
||||
auth = f"{quote_plus(username)}:{quote_plus(password)}@"
|
||||
elif password:
|
||||
auth = f":{quote_plus(password)}@"
|
||||
else:
|
||||
auth = ""
|
||||
url = f"redis://{auth}{host}:{port}/{database}"
|
||||
|
||||
if not url:
|
||||
return NoopCache()
|
||||
try:
|
||||
return RedisCache(url=url, db=db)
|
||||
except Exception:
|
||||
return NoopCache()
|
||||
|
||||
@staticmethod
|
||||
def _safe_filename(name: str) -> str:
|
||||
return name.replace("..", "").replace("/", "_").replace("\\", "_")
|
||||
|
||||
def _redis_key(self, table_name: str) -> str:
|
||||
return f"{self.KEY_PREFIX}:{table_name}"
|
||||
|
||||
def get_prompt(self, table_name: str) -> Optional[Dict[str, Any]]:
|
||||
"""读取指定表的提示词，优先 Redis，回退本地文件"""
|
||||
if not table_name:
|
||||
return None
|
||||
|
||||
if self._use_redis_primary:
|
||||
prompt = self._get_from_redis(table_name)
|
||||
if prompt:
|
||||
return prompt
|
||||
|
||||
prompt = self._get_from_file(table_name)
|
||||
return prompt
|
||||
|
||||
def get_prompt_with_source(self, table_name: str) -> tuple[Optional[Dict[str, Any]], str]:
|
||||
"""读取指定表的提示词，返回 (prompt, source) 元组"""
|
||||
if not table_name:
|
||||
return None, self.SOURCE_FILE
|
||||
|
||||
if self._use_redis_primary:
|
||||
prompt = self._get_from_redis(table_name)
|
||||
if prompt:
|
||||
return prompt, self.SOURCE_REDIS
|
||||
|
||||
prompt = self._get_from_file(table_name)
|
||||
source = self.SOURCE_FILE if prompt else self.SOURCE_FILE
|
||||
return prompt, source
|
||||
|
||||
def _get_from_redis(self, table_name: str) -> Optional[Dict[str, Any]]:
|
||||
key = self._redis_key(table_name)
|
||||
try:
|
||||
data = self._cache.get(key)
|
||||
if data:
|
||||
try:
|
||||
return json.loads(data)
|
||||
except Exception:
|
||||
pass
|
||||
except Exception:
|
||||
pass
|
||||
return None
|
||||
|
||||
def _get_from_file(self, table_name: str) -> Optional[Dict[str, Any]]:
|
||||
safe_name = self._safe_filename(table_name)
|
||||
filename = safe_name + ".json"
|
||||
path = os.path.join(self._fallback_dir, filename)
|
||||
if not os.path.exists(path):
|
||||
return None
|
||||
|
||||
with open(path, "r", encoding="utf-8") as f:
|
||||
prompt = json.load(f)
|
||||
return prompt
|
||||
|
||||
def save_prompt(self, table_name: str, prompt: Dict[str, Any]) -> bool:
|
||||
"""保存提示词到 Redis"""
|
||||
if not table_name or not prompt:
|
||||
return False
|
||||
|
||||
key = self._redis_key(table_name)
|
||||
try:
|
||||
self._cache.set(key, json.dumps(prompt, ensure_ascii=False), self._cache_ttl)
|
||||
return True
|
||||
except Exception:
|
||||
return False
|
||||
|
||||
def delete_prompt(self, table_name: str) -> bool:
|
||||
"""从 Redis 删除提示词"""
|
||||
if not table_name:
|
||||
return False
|
||||
|
||||
key = self._redis_key(table_name)
|
||||
try:
|
||||
self._cache.delete(key)
|
||||
return True
|
||||
except Exception:
|
||||
return False
|
||||
|
||||
def list_tables(self) -> List[str]:
|
||||
"""列出 Redis 中所有表名"""
|
||||
pattern = f"{self.KEY_PREFIX}:*"
|
||||
keys = self._cache.keys(pattern)
|
||||
tables = []
|
||||
for key in keys:
|
||||
if key == self.TABLE_LIST_KEY:
|
||||
continue
|
||||
parts = key.split(":", 1)
|
||||
if len(parts) == 2:
|
||||
tables.append(parts[1])
|
||||
return tables
|
||||
|
||||
def sync_from_files(self, tables: Optional[List[str]] = None) -> Dict[str, bool]:
|
||||
"""从本地文件同步到 Redis"""
|
||||
results: Dict[str, bool] = {}
|
||||
|
||||
if tables:
|
||||
files_to_sync = [f"{self._safe_filename(t)}.json" for t in tables]
|
||||
else:
|
||||
try:
|
||||
files_to_sync = [f for f in os.listdir(self._fallback_dir) if f.endswith(".json")]
|
||||
except Exception:
|
||||
return results
|
||||
|
||||
for filename in files_to_sync:
|
||||
table_name = filename[:-5]
|
||||
prompt = self._get_from_file(table_name)
|
||||
if prompt:
|
||||
results[table_name] = self.save_prompt(table_name, prompt)
|
||||
|
||||
return results
|
||||
|
||||
|
||||
_GLOBAL_SQL_PROMPT_MANAGER: Optional[SqlPromptManager] = None
|
||||
|
||||
|
||||
def get_sql_prompt_manager(base_dir: Optional[str] = None) -> SqlPromptManager:
|
||||
"""获取全局 SqlPromptManager（单例）"""
|
||||
global _GLOBAL_SQL_PROMPT_MANAGER
|
||||
if _GLOBAL_SQL_PROMPT_MANAGER is None:
|
||||
_GLOBAL_SQL_PROMPT_MANAGER = SqlPromptManager(base_dir=base_dir)
|
||||
return _GLOBAL_SQL_PROMPT_MANAGER
|
||||
@@ -0,0 +1,201 @@
|
||||
import json
|
||||
import re
|
||||
from pathlib import Path
|
||||
from typing import Any, Dict, Optional, Set
|
||||
|
||||
from config import Config
|
||||
from services.core.sql_prompt_manager import get_sql_prompt_manager
|
||||
from services.integrations.ragflow_client import RagflowClient, extract_table_name
|
||||
|
||||
|
||||
IDENTIFIER_RE = re.compile(r"[a-zA-Z_][a-zA-Z0-9_]*")
|
||||
EXPLICIT_FILTER_FIELD_RE = re.compile(r"([a-zA-Z_][a-zA-Z0-9_]*)\s*=")
|
||||
|
||||
|
||||
def _normalize_term(term: str) -> str:
|
||||
return str(term or "").strip().lower()
|
||||
|
||||
|
||||
class TemplateMatcher:
|
||||
"""模板匹配器：RAGFlow 检索"""
|
||||
|
||||
KEYWORD_MATCH_BONUS = 50
|
||||
|
||||
def __init__(self):
|
||||
self._ragflow = RagflowClient()
|
||||
self._sql_prompt_manager = get_sql_prompt_manager()
|
||||
cfg = Config.get_section("ragflow")
|
||||
self._dataset_id = (cfg.get("table_retrieval_dataset_id") or "").strip()
|
||||
self._top_k = int(cfg.get("retrieval_top_k", 3))
|
||||
self._non_empty_tables, self._table_keywords = self._load_table_config()
|
||||
self._table_terms_cache: Dict[str, Set[str]] = {}
|
||||
|
||||
def _load_table_config(self) -> tuple[Optional[Set[str]], Dict[str, Set[str]]]:
|
||||
"""从本地 tables.json 读取非空模板表集合和关键词映射。"""
|
||||
try:
|
||||
tables_path = Path(__file__).resolve().parents[2] / "config" / "table_retrieval_prompts" / "tables.json"
|
||||
with open(tables_path, "r", encoding="utf-8") as f:
|
||||
data = json.load(f)
|
||||
|
||||
if not isinstance(data, dict):
|
||||
return None, {}
|
||||
|
||||
non_empty: Set[str] = set()
|
||||
keywords_map: Dict[str, Set[str]] = {}
|
||||
|
||||
for table_name, templates in data.items():
|
||||
if not isinstance(table_name, str):
|
||||
continue
|
||||
if isinstance(templates, list) and len(templates) > 0:
|
||||
non_empty.add(table_name)
|
||||
keywords_map[table_name] = {_normalize_term(kw) for kw in templates if isinstance(kw, str)}
|
||||
|
||||
return non_empty, keywords_map
|
||||
except Exception:
|
||||
return None, {}
|
||||
|
||||
def _validate(self) -> None:
|
||||
if not self._dataset_id:
|
||||
raise RuntimeError("未配置 ragflow.table_retrieval_dataset_id，无法进行表名检索")
|
||||
|
||||
@staticmethod
|
||||
def _extract_query_terms(normalized_text: str) -> Set[str]:
|
||||
return {
|
||||
_normalize_term(match.group(0))
|
||||
for match in IDENTIFIER_RE.finditer(normalized_text or "")
|
||||
}
|
||||
|
||||
@staticmethod
|
||||
def _extract_explicit_filter_fields(normalized_text: str) -> Set[str]:
|
||||
return {
|
||||
_normalize_term(match.group(1))
|
||||
for match in EXPLICIT_FILTER_FIELD_RE.finditer(normalized_text or "")
|
||||
}
|
||||
|
||||
def _load_table_terms(self, table_name: str) -> Set[str]:
|
||||
cached = self._table_terms_cache.get(table_name)
|
||||
if cached is not None:
|
||||
return cached
|
||||
|
||||
prompt = self._sql_prompt_manager.get_prompt(table_name) or {}
|
||||
terms: Set[str] = set()
|
||||
|
||||
for field in (prompt.get("data_model_specification") or {}).get("fields_list") or []:
|
||||
if isinstance(field, str):
|
||||
terms.add(_normalize_term(field))
|
||||
|
||||
field_ref = prompt.get("field_mapping_reference") or {}
|
||||
self._collect_mapping_terms(field_ref, terms)
|
||||
|
||||
self._table_terms_cache[table_name] = terms
|
||||
return terms
|
||||
|
||||
def _collect_mapping_terms(self, node: Any, terms: Set[str]) -> None:
|
||||
if isinstance(node, dict):
|
||||
for key, value in node.items():
|
||||
if key == "alias" and isinstance(value, list):
|
||||
for alias in value:
|
||||
if isinstance(alias, str):
|
||||
terms.add(_normalize_term(alias))
|
||||
continue
|
||||
|
||||
if isinstance(value, dict):
|
||||
if "alias" in value or "type" in value:
|
||||
terms.add(_normalize_term(key))
|
||||
self._collect_mapping_terms(value, terms)
|
||||
elif isinstance(value, list):
|
||||
# 对字段列表直接入词，增强字段覆盖匹配
|
||||
if key.endswith("_fields") or key in {"fields_list", "list"}:
|
||||
for item in value:
|
||||
if isinstance(item, str):
|
||||
terms.add(_normalize_term(item))
|
||||
self._collect_mapping_terms(value, terms)
|
||||
elif isinstance(node, list):
|
||||
for item in node:
|
||||
self._collect_mapping_terms(item, terms)
|
||||
|
||||
def _rank_candidates(self, normalized_text: str, candidates: list[Dict[str, Any]]) -> list[Dict[str, Any]]:
|
||||
query_terms = self._extract_query_terms(normalized_text)
|
||||
explicit_fields = self._extract_explicit_filter_fields(normalized_text)
|
||||
|
||||
if not query_terms or not candidates:
|
||||
return candidates
|
||||
|
||||
ranked: list[Dict[str, Any]] = []
|
||||
for index, candidate in enumerate(candidates):
|
||||
table_name = candidate.get("table_name")
|
||||
if not table_name:
|
||||
continue
|
||||
|
||||
table_terms = self._load_table_terms(table_name)
|
||||
overlap = len(query_terms & table_terms)
|
||||
|
||||
missing_explicit_fields = len([field for field in explicit_fields if field not in table_terms])
|
||||
|
||||
keyword_bonus = 0
|
||||
table_keywords = self._table_keywords.get(table_name, set())
|
||||
if table_keywords:
|
||||
matched_keywords = query_terms & table_keywords
|
||||
keyword_bonus = len(matched_keywords) * self.KEYWORD_MATCH_BONUS
|
||||
|
||||
rank_score = overlap + keyword_bonus - (missing_explicit_fields * 5)
|
||||
|
||||
ranked.append({
|
||||
**candidate,
|
||||
"rank_score": rank_score,
|
||||
"rank_overlap": overlap,
|
||||
"rank_keyword_bonus": keyword_bonus,
|
||||
"rank_missing_explicit_fields": missing_explicit_fields,
|
||||
"rank_index": index,
|
||||
})
|
||||
|
||||
ranked.sort(key=lambda item: (item["rank_score"], item["rank_overlap"], -item["rank_index"]), reverse=True)
|
||||
return ranked
|
||||
|
||||
def match(self, normalized_text: str) -> Dict[str, Any]:
|
||||
"""返回匹配的表名与原始响应"""
|
||||
self._validate()
|
||||
try:
|
||||
response = self._ragflow.retrieve(normalized_text, top_k=self._top_k, dataset_id=self._dataset_id)
|
||||
except Exception as e:
|
||||
return {"table_name": None, "candidates": [], "raw": {"error": str(e)}}
|
||||
|
||||
candidates = []
|
||||
seen = set()
|
||||
data = response.get("data") if isinstance(response, dict) else None
|
||||
records = []
|
||||
if isinstance(data, list):
|
||||
records = data
|
||||
elif isinstance(data, dict):
|
||||
chunks = data.get("chunks")
|
||||
if isinstance(chunks, list):
|
||||
records = chunks
|
||||
|
||||
for item in records:
|
||||
table_name = extract_table_name(item)
|
||||
if self._non_empty_tables is not None and table_name not in self._non_empty_tables:
|
||||
continue
|
||||
if table_name and table_name not in seen:
|
||||
seen.add(table_name)
|
||||
candidates.append(
|
||||
{
|
||||
"table_name": table_name,
|
||||
"metadata": item.get("metadata") or {},
|
||||
"content": item.get("content") or item.get("text") or "",
|
||||
}
|
||||
)
|
||||
|
||||
candidates = self._rank_candidates(normalized_text, candidates)
|
||||
matched = candidates[0]["table_name"] if candidates else None
|
||||
return {"table_name": matched, "candidates": candidates, "raw": response}
|
||||
|
||||
|
||||
_GLOBAL_TEMPLATE_MATCHER: TemplateMatcher | None = None
|
||||
|
||||
|
||||
def get_template_matcher() -> TemplateMatcher:
|
||||
"""获取全局 TemplateMatcher（单例）"""
|
||||
global _GLOBAL_TEMPLATE_MATCHER
|
||||
if _GLOBAL_TEMPLATE_MATCHER is None:
|
||||
_GLOBAL_TEMPLATE_MATCHER = TemplateMatcher()
|
||||
return _GLOBAL_TEMPLATE_MATCHER
|
||||
@@ -0,0 +1,24 @@
|
||||
"""外部集成模块"""
|
||||
|
||||
from .ragflow_client import RagflowClient, extract_table_name
|
||||
from .ragflow_sync import RagflowSync
|
||||
|
||||
# 延迟导入 nacos（可选依赖）
|
||||
try:
|
||||
from .nacos_service import NacosManager, NacosConfig, ServiceConfig, load_nacos_config, load_service_config
|
||||
__all__ = [
|
||||
"RagflowClient",
|
||||
"extract_table_name",
|
||||
"RagflowSync",
|
||||
"NacosManager",
|
||||
"NacosConfig",
|
||||
"ServiceConfig",
|
||||
"load_nacos_config",
|
||||
"load_service_config",
|
||||
]
|
||||
except ImportError:
|
||||
__all__ = [
|
||||
"RagflowClient",
|
||||
"extract_table_name",
|
||||
"RagflowSync",
|
||||
]
|
||||
@@ -1,9 +1,15 @@
|
||||
import asyncio
|
||||
import logging
|
||||
import os
|
||||
import socket
|
||||
from dataclasses import dataclass
|
||||
from typing import Any, Dict, Optional
|
||||
import nacos
|
||||
|
||||
try:
|
||||
import nacos # type: ignore
|
||||
except ImportError:
|
||||
nacos = None
|
||||
|
||||
from config import Config
|
||||
|
||||
logger = logging.getLogger(__name__)
|
||||
@@ -22,6 +28,7 @@ class NacosConfig:
|
||||
heartbeat_interval: int
|
||||
weight: float
|
||||
ephemeral: bool
|
||||
register_port: Optional[int]
|
||||
|
||||
|
||||
@dataclass
|
||||
@@ -36,21 +43,34 @@ class ServiceConfig:
|
||||
|
||||
def _get_local_ip() -> str:
|
||||
"""获取本地 IP 地址"""
|
||||
for env_name in ("POD_IP", "HOST_IP"):
|
||||
env_ip = os.getenv(env_name)
|
||||
if env_ip:
|
||||
return env_ip
|
||||
|
||||
try:
|
||||
s = socket.socket(socket.AF_INET, socket.SOCK_DGRAM)
|
||||
s.connect(("8.8.8.8", 80))
|
||||
ip = s.getsockname()[0]
|
||||
s.close()
|
||||
return ip
|
||||
except Exception as e:
|
||||
logger.warning(f"获取本地 IP 失败，使用 127.0.0.1: {e}")
|
||||
return "127.0.0.1"
|
||||
except Exception:
|
||||
try:
|
||||
host_ip = socket.gethostbyname(socket.gethostname())
|
||||
if host_ip and host_ip != "127.0.0.1":
|
||||
return host_ip
|
||||
except Exception:
|
||||
pass
|
||||
|
||||
logger.warning("获取本地 IP 失败，使用 127.0.0.1")
|
||||
return "127.0.0.1"
|
||||
|
||||
|
||||
def load_nacos_config() -> NacosConfig:
|
||||
"""从 config.ini 读取 Nacos 配置"""
|
||||
section = "nacos"
|
||||
enabled = Config._config.getboolean(section, "enabled", fallback=False)
|
||||
register_port = Config._config.getint(section, "register_port", fallback=0)
|
||||
return NacosConfig(
|
||||
enabled=enabled,
|
||||
server_addresses=Config._config.get(section, "server", fallback="localhost:8848"),
|
||||
@@ -62,22 +82,23 @@ def load_nacos_config() -> NacosConfig:
|
||||
heartbeat_interval=Config._config.getint(section, "heartbeat_interval", fallback=5),
|
||||
weight=Config._config.getfloat(section, "weight", fallback=1.0),
|
||||
ephemeral=Config._config.getboolean(section, "ephemeral", fallback=True),
|
||||
register_port=register_port if register_port > 0 else None,
|
||||
)
|
||||
|
||||
|
||||
def load_service_config() -> ServiceConfig:
|
||||
"""从 config.ini 读取服务配置"""
|
||||
section = "app"
|
||||
service_name = Config._config.get(section, "service_name", fallback="more-dots-api")
|
||||
service_name = Config._config.get(section, "service_name", fallback="apbo-boat-agent")
|
||||
host = Config._config.get(section, "host", fallback="0.0.0.0")
|
||||
port = Config._config.getint(section, "port", fallback=8000)
|
||||
ip = host if host != "0.0.0.0" else _get_local_ip()
|
||||
ip = host if host not in ("0.0.0.0", "::") else _get_local_ip()
|
||||
|
||||
metadata = {
|
||||
"version": Config._config.get(section, "version", fallback="1.0.0"),
|
||||
"service_type": "fastapi",
|
||||
"api_paths": "/health,/api/workflows,/api/workflows/stream,/nacos/status",
|
||||
"streaming": "false",
|
||||
"streaming": "true",
|
||||
"model_section": Config._config.get(section, "model_section", fallback=Config.DEFAULT_MODEL_SECTION),
|
||||
}
|
||||
|
||||
@@ -105,6 +126,10 @@ class NacosManager:
|
||||
self._stop_event = asyncio.Event()
|
||||
self.is_registered = False
|
||||
|
||||
def _registration_port(self) -> int:
|
||||
"""Nacos 注册端口：优先使用 nacos.register_port，未配置时回退 app.port。"""
|
||||
return int(self.nacos_config.register_port or self.service_config.port)
|
||||
|
||||
def _init_client(self) -> bool:
|
||||
"""初始化 Nacos 客户端"""
|
||||
if nacos is None:
|
||||
@@ -132,7 +157,7 @@ class NacosManager:
|
||||
self.client.add_naming_instance(
|
||||
service_name=self.service_config.service_name,
|
||||
ip=self.service_config.ip,
|
||||
port=self.service_config.port,
|
||||
port=self._registration_port(),
|
||||
cluster_name=self.nacos_config.cluster_name,
|
||||
group_name=self.nacos_config.group_name,
|
||||
weight=self.nacos_config.weight,
|
||||
@@ -144,7 +169,7 @@ class NacosManager:
|
||||
"✅ 服务注册成功: %s (%s:%s)",
|
||||
self.service_config.service_name,
|
||||
self.service_config.ip,
|
||||
self.service_config.port,
|
||||
self._registration_port(),
|
||||
)
|
||||
return True
|
||||
except Exception as e:
|
||||
@@ -161,7 +186,7 @@ class NacosManager:
|
||||
self.client.remove_naming_instance(
|
||||
service_name=self.service_config.service_name,
|
||||
ip=self.service_config.ip,
|
||||
port=self.service_config.port,
|
||||
port=self._registration_port(),
|
||||
cluster_name=self.nacos_config.cluster_name,
|
||||
group_name=self.nacos_config.group_name,
|
||||
)
|
||||
@@ -180,7 +205,7 @@ class NacosManager:
|
||||
self.client.send_heartbeat(
|
||||
service_name=self.service_config.service_name,
|
||||
ip=self.service_config.ip,
|
||||
port=self.service_config.port,
|
||||
port=self._registration_port(),
|
||||
cluster_name=self.nacos_config.cluster_name,
|
||||
group_name=self.nacos_config.group_name,
|
||||
)
|
||||
@@ -192,8 +217,14 @@ class NacosManager:
|
||||
|
||||
while not self._stop_event.is_set():
|
||||
try:
|
||||
self._send_heartbeat()
|
||||
logger.debug("心跳发送成功: %s", self.service_config.service_name)
|
||||
if not self.is_registered:
|
||||
if self.register_service():
|
||||
logger.info("✅ Nacos 重试注册成功: %s", self.service_config.service_name)
|
||||
else:
|
||||
logger.warning("⚠️ Nacos 注册重试失败: %s", self.service_config.service_name)
|
||||
else:
|
||||
self._send_heartbeat()
|
||||
logger.debug("心跳发送成功: %s", self.service_config.service_name)
|
||||
except Exception as e:
|
||||
logger.warning(f"心跳发送失败: {e}")
|
||||
# 尝试重新注册
|
||||
@@ -213,12 +244,13 @@ class NacosManager:
|
||||
logger.info("Nacos 未启用，跳过注册")
|
||||
return
|
||||
|
||||
if self.register_service():
|
||||
self._heartbeat_task = asyncio.create_task(self._heartbeat_loop())
|
||||
logger.info("✅ Nacos 心跳任务已启动")
|
||||
else:
|
||||
if not self.register_service():
|
||||
logger.warning("⚠️ Nacos 注册失败，服务继续运行")
|
||||
|
||||
# 无论首次注册是否成功，都启动循环以便持续重试注册
|
||||
self._heartbeat_task = asyncio.create_task(self._heartbeat_loop())
|
||||
logger.info("✅ Nacos 心跳任务已启动")
|
||||
|
||||
async def stop(self) -> None:
|
||||
"""停止心跳并注销"""
|
||||
self._stop_event.set()
|
||||
@@ -238,6 +270,7 @@ class NacosManager:
|
||||
"service_name": self.service_config.service_name,
|
||||
"ip": self.service_config.ip,
|
||||
"port": self.service_config.port,
|
||||
"register_port": self._registration_port(),
|
||||
"namespace": self.nacos_config.namespace,
|
||||
"group": self.nacos_config.group_name,
|
||||
"cluster": self.nacos_config.cluster_name,
|
||||
@@ -6,6 +6,11 @@ import httpx
|
||||
from config import Config
|
||||
|
||||
|
||||
TABLE_NAME_ALIASES = {
|
||||
"apbo_tp_multiple_impact": "apbo_eta_multiple_impact",
|
||||
}
|
||||
|
||||
|
||||
class RagflowClient:
|
||||
"""RAGFlow 客户端（仅检索）"""
|
||||
|
||||
@@ -55,17 +60,23 @@ class RagflowClient:
|
||||
|
||||
def extract_table_name(record: Dict[str, Any]) -> Optional[str]:
|
||||
"""从检索结果中提取表名"""
|
||||
def _canonicalize(table_name: Any) -> Optional[str]:
|
||||
normalized = str(table_name or "").strip()
|
||||
if not normalized:
|
||||
return None
|
||||
return TABLE_NAME_ALIASES.get(normalized, normalized)
|
||||
|
||||
if not record:
|
||||
return None
|
||||
|
||||
metadata = record.get("metadata") or {}
|
||||
for key in ("table", "table_name"):
|
||||
if key in metadata:
|
||||
return metadata.get(key)
|
||||
return _canonicalize(metadata.get(key))
|
||||
|
||||
for key in ("table", "table_name"):
|
||||
if key in record:
|
||||
return record.get(key)
|
||||
return _canonicalize(record.get(key))
|
||||
|
||||
content = record.get("content") or record.get("text") or ""
|
||||
|
||||
@@ -75,12 +86,12 @@ def extract_table_name(record: Dict[str, Any]) -> Optional[str]:
|
||||
if isinstance(parsed, dict):
|
||||
for key in ("table", "table_name"):
|
||||
if parsed.get(key):
|
||||
return str(parsed.get(key))
|
||||
return _canonicalize(parsed.get(key))
|
||||
except Exception:
|
||||
pass
|
||||
|
||||
for line in str(content).splitlines():
|
||||
if line.lower().startswith("table:"):
|
||||
return line.split(":", 1)[1].strip()
|
||||
return _canonicalize(line.split(":", 1)[1].strip())
|
||||
|
||||
return None
|
||||
@@ -1,6 +1,7 @@
|
||||
import json
|
||||
import os
|
||||
from typing import Any, Dict, List
|
||||
from pathlib import Path
|
||||
|
||||
import httpx
|
||||
|
||||
@@ -31,6 +32,38 @@ class RagflowSync:
|
||||
self._table_retrieval_dataset_id = (cfg.get("table_retrieval_dataset_id") or "").strip()
|
||||
self._sql_gen_dataset_id = (cfg.get("sql_gen_dataset_id") or "").strip()
|
||||
|
||||
@staticmethod
|
||||
def _project_root() -> Path:
|
||||
"""返回项目根目录。"""
|
||||
return Path(__file__).resolve().parents[2]
|
||||
|
||||
def _collect_sql_gen_documents(self) -> tuple[List[Dict[str, Any]], List[Dict[str, str]]]:
|
||||
"""收集 SQL 生成文档，并跳过空文件/非法 JSON。"""
|
||||
prompts_dir = self._project_root() / "config" / "sql_gen_prompts"
|
||||
documents: List[Dict[str, Any]] = []
|
||||
warnings: List[Dict[str, str]] = []
|
||||
|
||||
for name in os.listdir(prompts_dir):
|
||||
if not name.endswith(".json"):
|
||||
continue
|
||||
|
||||
path = prompts_dir / name
|
||||
raw_text = path.read_text(encoding="utf-8")
|
||||
if not raw_text.strip():
|
||||
warnings.append({"file": name, "reason": "empty_file"})
|
||||
continue
|
||||
|
||||
try:
|
||||
prompt = json.loads(raw_text)
|
||||
except json.JSONDecodeError as exc:
|
||||
warnings.append({"file": name, "reason": f"invalid_json:{exc}"})
|
||||
continue
|
||||
|
||||
table = prompt.get("table") or path.stem
|
||||
documents.append({"filename": f"{table}.txt", "content": _dump_json_content(prompt)})
|
||||
|
||||
return documents, warnings
|
||||
|
||||
def upload_documents(self, dataset_id: str, documents: List[Dict[str, Any]]) -> Dict[str, Any]:
|
||||
"""上传文档到指定知识库（每个文档单独上传）"""
|
||||
if not self._base_url:
|
||||
@@ -262,8 +295,7 @@ class RagflowSync:
|
||||
if not self._table_retrieval_dataset_id:
|
||||
raise RuntimeError("未配置 ragflow.table_retrieval_dataset_id，无法更新表名检索文档")
|
||||
|
||||
root = os.path.dirname(os.path.dirname(__file__))
|
||||
tables_file = os.path.join(root, "config", "table_retrieval_prompts", "tables.json")
|
||||
tables_file = self._project_root() / "config" / "table_retrieval_prompts" / "tables.json"
|
||||
with open(tables_file, "r", encoding="utf-8") as f:
|
||||
data = json.load(f)
|
||||
|
||||
@@ -277,34 +309,35 @@ class RagflowSync:
|
||||
]
|
||||
return self.replace_documents(self._table_retrieval_dataset_id, documents)
|
||||
|
||||
def sync_table_retrieval(self) -> Dict[str, Any]:
|
||||
"""兼容旧脚本：同步表名检索文档，采用覆盖更新避免旧表残留。"""
|
||||
return self.update_table_retrieval_documents()
|
||||
|
||||
def update_sql_gen_documents(self) -> Dict[str, Any]:
|
||||
"""更新 SQL 生成文档（仅文档内容）"""
|
||||
if not self._sql_gen_dataset_id:
|
||||
raise RuntimeError("未配置 ragflow.sql_gen_dataset_id，无法更新 SQL 生成文档")
|
||||
|
||||
root = os.path.dirname(os.path.dirname(__file__))
|
||||
prompts_dir = os.path.join(root, "config", "sql_gen_prompts")
|
||||
documents: List[Dict[str, Any]] = []
|
||||
documents, warnings = self._collect_sql_gen_documents()
|
||||
if not documents:
|
||||
raise RuntimeError(f"SQL 生成提示词目录中没有可同步的有效 JSON 文档，warnings={warnings}")
|
||||
|
||||
for name in os.listdir(prompts_dir):
|
||||
if not name.endswith(".json"):
|
||||
continue
|
||||
path = os.path.join(prompts_dir, name)
|
||||
with open(path, "r", encoding="utf-8") as f:
|
||||
prompt = json.load(f)
|
||||
table = prompt.get("table") or os.path.splitext(name)[0]
|
||||
documents.append({"filename": f"{table}.txt", "content": _dump_json_content(prompt)})
|
||||
result = self.replace_documents(self._sql_gen_dataset_id, documents)
|
||||
result["warnings"] = warnings
|
||||
result["valid_document_count"] = len(documents)
|
||||
return result
|
||||
|
||||
return self.replace_documents(self._sql_gen_dataset_id, documents)
|
||||
def sync_sql_gen_prompts(self) -> Dict[str, Any]:
|
||||
"""兼容旧脚本：同步 SQL 生成提示词文档，采用覆盖更新避免旧 prompt 残留。"""
|
||||
return self.update_sql_gen_documents()
|
||||
|
||||
def upload_table_retrieval(self) -> Dict[str, Any]:
|
||||
"""上传表名检索模板文档 - 直接上传整个 JSON 文件"""
|
||||
if not self._table_retrieval_dataset_id:
|
||||
raise RuntimeError("未配置 ragflow.table_retrieval_dataset_id，无法上传表名检索模板")
|
||||
|
||||
root = os.path.dirname(os.path.dirname(__file__))
|
||||
tables_file = os.path.join(root, "config", "table_retrieval_prompts", "tables.json")
|
||||
|
||||
tables_file = self._project_root() / "config" / "table_retrieval_prompts" / "tables.json"
|
||||
|
||||
if not os.path.exists(tables_file):
|
||||
raise RuntimeError(f"表名检索模板文件不存在: {tables_file}")
|
||||
|
||||
@@ -328,22 +361,16 @@ class RagflowSync:
|
||||
if not self._sql_gen_dataset_id:
|
||||
raise RuntimeError("未配置 ragflow.sql_gen_dataset_id，无法上传 SQL 生成提示词")
|
||||
|
||||
root = os.path.dirname(os.path.dirname(__file__))
|
||||
prompts_dir = os.path.join(root, "config", "sql_gen_prompts")
|
||||
|
||||
prompts_dir = self._project_root() / "config" / "sql_gen_prompts"
|
||||
|
||||
if not os.path.exists(prompts_dir):
|
||||
raise RuntimeError(f"SQL 生成提示词目录不存在: {prompts_dir}")
|
||||
|
||||
documents = []
|
||||
|
||||
for name in os.listdir(prompts_dir):
|
||||
if not name.endswith(".json"):
|
||||
continue
|
||||
path = os.path.join(prompts_dir, name)
|
||||
with open(path, "r", encoding="utf-8") as f:
|
||||
prompt = json.load(f)
|
||||
table = prompt.get("table") or os.path.splitext(name)[0]
|
||||
json_content = _dump_json_content(prompt)
|
||||
documents.append({"filename": f"{table}.txt", "content": json_content})
|
||||
documents, warnings = self._collect_sql_gen_documents()
|
||||
if not documents:
|
||||
raise RuntimeError(f"SQL 生成提示词目录中没有可上传的有效 JSON 文档，warnings={warnings}")
|
||||
|
||||
return self.upload_documents(self._sql_gen_dataset_id, documents)
|
||||
result = self.upload_documents(self._sql_gen_dataset_id, documents)
|
||||
result["warnings"] = warnings
|
||||
result["valid_document_count"] = len(documents)
|
||||
return result
|
||||
@@ -1,41 +0,0 @@
|
||||
import json
|
||||
import os
|
||||
from typing import Any, Dict, Optional
|
||||
|
||||
|
||||
class SqlPromptManager:
|
||||
"""按表名读取 SQL 提示词"""
|
||||
|
||||
def __init__(self, base_dir: Optional[str] = None):
|
||||
root_dir = os.path.dirname(os.path.dirname(__file__))
|
||||
self._base_dir = base_dir or os.path.join(root_dir, "config", "sql_gen_prompts")
|
||||
|
||||
@staticmethod
|
||||
def _safe_filename(name: str) -> str:
|
||||
return name.replace("..", "").replace("/", "_").replace("\\", "_")
|
||||
|
||||
def get_prompt(self, table_name: str) -> Optional[Dict[str, Any]]:
|
||||
"""读取指定表的提示词 JSON"""
|
||||
if not table_name:
|
||||
return None
|
||||
safe_name = self._safe_filename(table_name)
|
||||
filename = safe_name + ".json"
|
||||
path = os.path.join(self._base_dir, filename)
|
||||
if not os.path.exists(path):
|
||||
return None
|
||||
|
||||
with open(path, "r", encoding="utf-8") as f:
|
||||
prompt = json.load(f)
|
||||
|
||||
return prompt
|
||||
|
||||
|
||||
_GLOBAL_SQL_PROMPT_MANAGER: Optional[SqlPromptManager] = None
|
||||
|
||||
|
||||
def get_sql_prompt_manager(base_dir: Optional[str] = None) -> SqlPromptManager:
|
||||
"""获取全局 SqlPromptManager（单例）"""
|
||||
global _GLOBAL_SQL_PROMPT_MANAGER
|
||||
if _GLOBAL_SQL_PROMPT_MANAGER is None:
|
||||
_GLOBAL_SQL_PROMPT_MANAGER = SqlPromptManager(base_dir=base_dir)
|
||||
return _GLOBAL_SQL_PROMPT_MANAGER
|
||||
@@ -0,0 +1,14 @@
|
||||
"""数据存储模块"""
|
||||
|
||||
from .message_storage import get_message_storage, MessageStorage
|
||||
from .structured_logger import get_structured_logger
|
||||
from .cache import CacheBase, NoopCache, RedisCache
|
||||
|
||||
__all__ = [
|
||||
"get_message_storage",
|
||||
"MessageStorage",
|
||||
"get_structured_logger",
|
||||
"CacheBase",
|
||||
"NoopCache",
|
||||
"RedisCache",
|
||||
]
|
||||
@@ -0,0 +1,64 @@
|
||||
from __future__ import annotations
|
||||
|
||||
from typing import List, Optional
|
||||
|
||||
try:
|
||||
import redis
|
||||
except Exception:
|
||||
redis = None
|
||||
|
||||
|
||||
class CacheBase:
|
||||
"""缓存接口"""
|
||||
|
||||
def get(self, key: str) -> Optional[str]:
|
||||
raise NotImplementedError
|
||||
|
||||
def set(self, key: str, value: str, ttl: int = None) -> None:
|
||||
raise NotImplementedError
|
||||
|
||||
def delete(self, key: str) -> None:
|
||||
raise NotImplementedError
|
||||
|
||||
def keys(self, pattern: str) -> List[str]:
|
||||
raise NotImplementedError
|
||||
|
||||
|
||||
class NoopCache(CacheBase):
|
||||
"""空实现缓存"""
|
||||
|
||||
def get(self, key: str) -> Optional[str]:
|
||||
return None
|
||||
|
||||
def set(self, key: str, value: str, ttl: int = None) -> None:
|
||||
return None
|
||||
|
||||
def delete(self, key: str) -> None:
|
||||
return None
|
||||
|
||||
def keys(self, pattern: str) -> List[str]:
|
||||
return []
|
||||
|
||||
|
||||
class RedisCache(CacheBase):
|
||||
"""Redis 缓存实现"""
|
||||
|
||||
def __init__(self, url: str, db: int = 0):
|
||||
if redis is None:
|
||||
raise ImportError("未安装 redis 依赖")
|
||||
self._client = redis.Redis.from_url(url, db=db, decode_responses=True)
|
||||
|
||||
def get(self, key: str) -> Optional[str]:
|
||||
return self._client.get(key)
|
||||
|
||||
def set(self, key: str, value: str, ttl: int = None) -> None:
|
||||
if ttl:
|
||||
self._client.set(key, value, ex=ttl)
|
||||
else:
|
||||
self._client.set(key, value)
|
||||
|
||||
def delete(self, key: str) -> None:
|
||||
self._client.delete(key)
|
||||
|
||||
def keys(self, pattern: str) -> List[str]:
|
||||
return self._client.keys(pattern)
|
||||
@@ -0,0 +1,885 @@
|
||||
"""
|
||||
消息存储服务 - 将每次查询的消息记录存储到 MySQL
|
||||
"""
|
||||
|
||||
from __future__ import annotations
|
||||
|
||||
import json
|
||||
from typing import Any, Dict, List, Optional
|
||||
|
||||
import pymysql
|
||||
|
||||
from config import Config
|
||||
from services.common.datetime_utils import DateTimeGenerator
|
||||
from schemas.messages import MessagesDTO
|
||||
|
||||
|
||||
class MessageStorage:
|
||||
"""消息存储服务"""
|
||||
|
||||
def __init__(self):
|
||||
cfg = Config.get_section("logging_mysql")
|
||||
self.enabled = str(cfg.get("enabled", "false")).lower() in ("1", "true", "yes")
|
||||
self.entity_debug_enabled = str(cfg.get("entity_debug_enabled", "false")).lower() in ("1", "true", "yes")
|
||||
self.host = cfg.get("host", "127.0.0.1")
|
||||
self.port = int(cfg.get("port", 3306))
|
||||
self.user = cfg.get("user", "root")
|
||||
self.password = cfg.get("password", "")
|
||||
self.database = cfg.get("database", "more_dots")
|
||||
# 消息落库与结构化日志分表，避免误用 logging_mysql.table=structured_logs
|
||||
self.table = cfg.get("messages_table", "ipc_apbo.messages")
|
||||
self.conversation_table = cfg.get("conversation_table", "ipc_apbo.conversations")
|
||||
self.connect_timeout = int(cfg.get("connect_timeout", 5))
|
||||
self._inited = False
|
||||
self._conversation_schema_checked = False
|
||||
|
||||
def _get_conn(self):
|
||||
"""获取数据库连接"""
|
||||
return pymysql.connect(
|
||||
host=self.host,
|
||||
port=self.port,
|
||||
user=self.user,
|
||||
password=self.password,
|
||||
database=self.database,
|
||||
charset="utf8mb4",
|
||||
autocommit=True,
|
||||
connect_timeout=self.connect_timeout,
|
||||
)
|
||||
|
||||
@staticmethod
|
||||
def _log_local(event: str, payload: Optional[Dict[str, Any]] = None) -> None:
|
||||
print(json.dumps({
|
||||
"level": "ERROR",
|
||||
"event": event,
|
||||
"payload": payload or {},
|
||||
"created_at": DateTimeGenerator.now().epoch_millis,
|
||||
}, ensure_ascii=False))
|
||||
|
||||
def _log_entity_debug(self, event: str, payload: Optional[Dict[str, Any]] = None) -> None:
|
||||
if not self.entity_debug_enabled:
|
||||
return
|
||||
print(json.dumps({
|
||||
"level": "DEBUG",
|
||||
"event": event,
|
||||
"payload": payload or {},
|
||||
"created_at": DateTimeGenerator.now().epoch_millis,
|
||||
}, ensure_ascii=False))
|
||||
|
||||
@staticmethod
|
||||
def _now_ms() -> int:
|
||||
return DateTimeGenerator.now().epoch_millis
|
||||
|
||||
@staticmethod
|
||||
def _build_audit_fields(
|
||||
*,
|
||||
random_code: str,
|
||||
user: Optional[str],
|
||||
created_value: Any = None,
|
||||
updated_value: Any = None,
|
||||
) -> Dict[str, Any]:
|
||||
created_ms = MessageStorage._resolve_epoch_millis(created_value)
|
||||
updated_ms = MessageStorage._resolve_epoch_millis(updated_value, fallback=created_ms)
|
||||
created_bundle = DateTimeGenerator.bundle(created_ms, default_to_now=True)
|
||||
updated_bundle = DateTimeGenerator.bundle(updated_ms, default_to_now=True)
|
||||
operator = (user or "system").strip() if isinstance(user, str) else "system"
|
||||
return {
|
||||
"random_code": random_code,
|
||||
"create_user": operator,
|
||||
"create_date": created_bundle.db_datetime,
|
||||
"update_user": operator,
|
||||
"update_date": updated_bundle.db_datetime,
|
||||
"create_user_name": operator,
|
||||
"update_user_name": operator,
|
||||
"created_at": created_ms,
|
||||
"updated_at": updated_ms,
|
||||
}
|
||||
|
||||
@staticmethod
|
||||
def _resolve_epoch_millis(value: Any, fallback: Optional[int] = None) -> int:
|
||||
if value is None:
|
||||
return fallback if fallback is not None else DateTimeGenerator.now().epoch_millis
|
||||
|
||||
if isinstance(value, (int, float)):
|
||||
raw = int(value)
|
||||
digits = len(str(abs(raw)))
|
||||
if digits == 10:
|
||||
return raw * 1000
|
||||
return raw
|
||||
|
||||
if isinstance(value, str):
|
||||
text = value.strip()
|
||||
if text.isdigit():
|
||||
raw = int(text)
|
||||
digits = len(text)
|
||||
if digits == 10:
|
||||
return raw * 1000
|
||||
if digits == 13:
|
||||
return raw
|
||||
|
||||
parsed = DateTimeGenerator.bundle(value, default_to_now=True)
|
||||
return parsed.epoch_millis
|
||||
|
||||
parsed = DateTimeGenerator.bundle(value, default_to_now=True)
|
||||
return parsed.epoch_millis
|
||||
|
||||
def _log_entity_stage(self, entity: str, action: str, stage: str, started_at: int, payload: Optional[Dict[str, Any]] = None) -> None:
|
||||
debug_payload = dict(payload or {})
|
||||
debug_payload.update({
|
||||
"entity": entity,
|
||||
"action": action,
|
||||
"stage": stage,
|
||||
"elapsed_ms": max(0, self._now_ms() - started_at),
|
||||
})
|
||||
self._log_entity_debug(f"message_storage.{entity}.{action}.{stage}", debug_payload)
|
||||
|
||||
@staticmethod
|
||||
def _split_table_reference(table_name: str, default_schema: str) -> tuple[str, str]:
|
||||
cleaned = str(table_name or "").strip()
|
||||
if "." in cleaned:
|
||||
schema_name, physical_table_name = cleaned.split(".", 1)
|
||||
else:
|
||||
schema_name, physical_table_name = default_schema, cleaned
|
||||
return schema_name.strip().strip("`"), physical_table_name.strip().strip("`")
|
||||
|
||||
def _ensure_conversation_schema(self, conn) -> None:
|
||||
if self._conversation_schema_checked or not self.enabled:
|
||||
return
|
||||
|
||||
started_at = self._now_ms()
|
||||
self._log_entity_stage(
|
||||
"conversations",
|
||||
"ensure_schema",
|
||||
"start",
|
||||
started_at,
|
||||
{"conversation_table": self.conversation_table},
|
||||
)
|
||||
|
||||
schema_name, table_name = self._split_table_reference(self.conversation_table, self.database)
|
||||
probe_sql = """
|
||||
SELECT 1
|
||||
FROM information_schema.columns
|
||||
WHERE table_schema = %s AND table_name = %s AND column_name = %s
|
||||
LIMIT 1
|
||||
"""
|
||||
|
||||
with conn.cursor() as cur:
|
||||
cur.execute(probe_sql, (schema_name, table_name, "name"))
|
||||
if cur.fetchone() is None:
|
||||
self._log_entity_stage(
|
||||
"conversations",
|
||||
"ensure_schema",
|
||||
"alter_needed",
|
||||
started_at,
|
||||
{"conversation_table": self.conversation_table, "missing_column": "name"},
|
||||
)
|
||||
alter_sql = f"""
|
||||
ALTER TABLE {self.conversation_table}
|
||||
ADD COLUMN name VARCHAR(255) NULL COMMENT '会话名称' AFTER user
|
||||
"""
|
||||
cur.execute(alter_sql)
|
||||
|
||||
self._conversation_schema_checked = True
|
||||
self._log_entity_stage(
|
||||
"conversations",
|
||||
"ensure_schema",
|
||||
"success",
|
||||
started_at,
|
||||
{"conversation_table": self.conversation_table, "schema_checked": True},
|
||||
)
|
||||
|
||||
def _ensure_table(self) -> None:
|
||||
"""确保消息表存在"""
|
||||
if self._inited or not self.enabled:
|
||||
return
|
||||
|
||||
started_at = self._now_ms()
|
||||
self._log_entity_stage(
|
||||
"storage",
|
||||
"ensure_table",
|
||||
"start",
|
||||
started_at,
|
||||
{"messages_table": self.table, "conversation_table": self.conversation_table},
|
||||
)
|
||||
|
||||
message_sql = f"""
|
||||
CREATE TABLE IF NOT EXISTS {self.table} (
|
||||
id BIGINT PRIMARY KEY AUTO_INCREMENT,
|
||||
random_code VARCHAR(100) NULL COMMENT '业务主键',
|
||||
create_user VARCHAR(100) NULL COMMENT '创建人',
|
||||
create_date DATETIME NULL COMMENT '创建时间',
|
||||
update_user VARCHAR(100) NULL COMMENT '修改人',
|
||||
update_date DATETIME NULL COMMENT '修改时间',
|
||||
create_user_name VARCHAR(255) NULL COMMENT '创建人姓名',
|
||||
update_user_name VARCHAR(255) NULL COMMENT '修改人姓名',
|
||||
message_id VARCHAR(255) NULL COMMENT '消息 ID',
|
||||
conversation_id VARCHAR(255) NULL COMMENT '会话 ID',
|
||||
user VARCHAR(255) NULL COMMENT '用户标识',
|
||||
query LONGTEXT NULL COMMENT '用户查询',
|
||||
answer LONGTEXT NULL COMMENT '回答消息内容',
|
||||
feedback VARCHAR(255) NULL COMMENT '点赞 like / 点踩 dislike',
|
||||
feedback_content TEXT NULL COMMENT '点踩内容',
|
||||
created_at BIGINT NULL COMMENT '创建时间(毫秒时间戳)',
|
||||
updated_at BIGINT NULL COMMENT '更新时间(毫秒时间戳)',
|
||||
`log` JSON NULL COMMENT '当前对话日志(JSON字符串)',
|
||||
UNIQUE KEY uk_random_code (random_code),
|
||||
UNIQUE KEY uk_message_id (message_id),
|
||||
INDEX idx_conversation_id (conversation_id),
|
||||
INDEX idx_created_at (created_at)
|
||||
) ENGINE=InnoDB DEFAULT CHARSET=utf8mb4 COMMENT='消息记录表';
|
||||
"""
|
||||
|
||||
conversation_sql = f"""
|
||||
CREATE TABLE IF NOT EXISTS {self.conversation_table} (
|
||||
id BIGINT PRIMARY KEY AUTO_INCREMENT,
|
||||
random_code VARCHAR(100) NULL COMMENT '业务主键',
|
||||
create_user VARCHAR(100) NULL COMMENT '创建人',
|
||||
create_date DATETIME NULL COMMENT '创建时间',
|
||||
update_user VARCHAR(100) NULL COMMENT '修改人',
|
||||
update_date DATETIME NULL COMMENT '修改时间',
|
||||
create_user_name VARCHAR(255) NULL COMMENT '创建人姓名',
|
||||
update_user_name VARCHAR(255) NULL COMMENT '修改人姓名',
|
||||
conversation_id VARCHAR(255) NULL COMMENT '会话 ID',
|
||||
user VARCHAR(255) NULL COMMENT '用户',
|
||||
name VARCHAR(512) NULL COMMENT '会话名称',
|
||||
status VARCHAR(255) NULL COMMENT '状态',
|
||||
introduction VARCHAR(255) NULL COMMENT '开场白',
|
||||
created_at BIGINT NULL COMMENT '创建时间(毫秒时间戳)',
|
||||
updated_at BIGINT NULL COMMENT '更新时间(毫秒时间戳)',
|
||||
UNIQUE KEY uk_conversation_random_code (random_code),
|
||||
UNIQUE KEY uk_conversation_id (conversation_id),
|
||||
INDEX idx_conversation_updated_at (updated_at)
|
||||
) ENGINE=InnoDB DEFAULT CHARSET=utf8mb4 COMMENT='会话记录表';
|
||||
"""
|
||||
|
||||
try:
|
||||
with self._get_conn() as conn:
|
||||
with conn.cursor() as cur:
|
||||
cur.execute(message_sql)
|
||||
cur.execute(conversation_sql)
|
||||
self._ensure_conversation_schema(conn)
|
||||
self._inited = True
|
||||
self._log_entity_stage(
|
||||
"storage",
|
||||
"ensure_table",
|
||||
"success",
|
||||
started_at,
|
||||
{"messages_table": self.table, "conversation_table": self.conversation_table},
|
||||
)
|
||||
except Exception as exc:
|
||||
self._log_entity_stage(
|
||||
"storage",
|
||||
"ensure_table",
|
||||
"failed",
|
||||
started_at,
|
||||
{"messages_table": self.table, "conversation_table": self.conversation_table, "error": str(exc)},
|
||||
)
|
||||
self._log_local("message_storage.ensure_table_failed", {
|
||||
"error": str(exc),
|
||||
"messages_table": self.table,
|
||||
"conversation_table": self.conversation_table,
|
||||
})
|
||||
# 开发阶段容错，避免初始化失败影响主流程
|
||||
self.enabled = False
|
||||
|
||||
def create_conversation(
|
||||
self,
|
||||
conversation_id: str,
|
||||
user: Optional[str],
|
||||
name: Optional[str],
|
||||
status: str,
|
||||
introduction: Optional[str],
|
||||
created_at: int,
|
||||
updated_at: int,
|
||||
) -> bool:
|
||||
started_at = self._now_ms()
|
||||
self._log_entity_stage(
|
||||
"conversations",
|
||||
"create",
|
||||
"start",
|
||||
started_at,
|
||||
{
|
||||
"conversation_id": conversation_id,
|
||||
"user": user,
|
||||
"name_len": len(name or ""),
|
||||
"status": status,
|
||||
},
|
||||
)
|
||||
if not self.enabled:
|
||||
self._log_entity_stage(
|
||||
"conversations",
|
||||
"create",
|
||||
"skipped",
|
||||
started_at,
|
||||
{"conversation_id": conversation_id, "reason": "storage_disabled"},
|
||||
)
|
||||
return False
|
||||
|
||||
self._ensure_table()
|
||||
if not self.enabled:
|
||||
self._log_entity_stage(
|
||||
"conversations",
|
||||
"create",
|
||||
"skipped",
|
||||
started_at,
|
||||
{"conversation_id": conversation_id, "reason": "storage_disabled_after_init"},
|
||||
)
|
||||
return False
|
||||
|
||||
insert_sql = f"""
|
||||
INSERT INTO {self.conversation_table}(
|
||||
random_code, create_user, create_date, update_user, update_date,
|
||||
create_user_name, update_user_name,
|
||||
conversation_id, user, name, status, introduction, created_at, updated_at
|
||||
) VALUES(%s, %s, %s, %s, %s, %s, %s, %s, %s, %s, %s, %s, %s, %s)
|
||||
"""
|
||||
try:
|
||||
audit = self._build_audit_fields(
|
||||
random_code=conversation_id,
|
||||
user=user,
|
||||
created_value=created_at,
|
||||
updated_value=updated_at,
|
||||
)
|
||||
with self._get_conn() as conn:
|
||||
self._ensure_conversation_schema(conn)
|
||||
with conn.cursor() as cur:
|
||||
self._log_entity_stage(
|
||||
"conversations",
|
||||
"create",
|
||||
"sql_execute",
|
||||
started_at,
|
||||
{"conversation_id": conversation_id, "table": self.conversation_table},
|
||||
)
|
||||
cur.execute(
|
||||
insert_sql,
|
||||
(
|
||||
audit["random_code"],
|
||||
audit["create_user"],
|
||||
audit["create_date"],
|
||||
audit["update_user"],
|
||||
audit["update_date"],
|
||||
audit["create_user_name"],
|
||||
audit["update_user_name"],
|
||||
conversation_id,
|
||||
user,
|
||||
name,
|
||||
status,
|
||||
introduction,
|
||||
audit["created_at"],
|
||||
audit["updated_at"],
|
||||
),
|
||||
)
|
||||
self._log_entity_stage(
|
||||
"conversations",
|
||||
"create",
|
||||
"success",
|
||||
started_at,
|
||||
{"conversation_id": conversation_id, "table": self.conversation_table},
|
||||
)
|
||||
return True
|
||||
except Exception as exc:
|
||||
self._log_entity_stage(
|
||||
"conversations",
|
||||
"create",
|
||||
"failed",
|
||||
started_at,
|
||||
{"conversation_id": conversation_id, "table": self.conversation_table, "error": str(exc)},
|
||||
)
|
||||
self._log_local("message_storage.create_conversation_failed", {
|
||||
"error": str(exc),
|
||||
"conversation_table": self.conversation_table,
|
||||
"conversation_id": conversation_id,
|
||||
})
|
||||
return False
|
||||
|
||||
def get_conversation_by_id(self, conversation_id: str) -> Optional[Dict[str, Any]]:
|
||||
started_at = self._now_ms()
|
||||
self._log_entity_stage(
|
||||
"conversations",
|
||||
"get_by_id",
|
||||
"start",
|
||||
started_at,
|
||||
{"conversation_id": conversation_id},
|
||||
)
|
||||
if not self.enabled:
|
||||
self._log_entity_stage(
|
||||
"conversations",
|
||||
"get_by_id",
|
||||
"skipped",
|
||||
started_at,
|
||||
{"conversation_id": conversation_id, "reason": "storage_disabled"},
|
||||
)
|
||||
return None
|
||||
|
||||
self._ensure_table()
|
||||
if not self.enabled:
|
||||
self._log_entity_stage(
|
||||
"conversations",
|
||||
"get_by_id",
|
||||
"skipped",
|
||||
started_at,
|
||||
{"conversation_id": conversation_id, "reason": "storage_disabled_after_init"},
|
||||
)
|
||||
return None
|
||||
|
||||
select_sql = f"""
|
||||
SELECT conversation_id, user, name, status, introduction, created_at, updated_at
|
||||
FROM {self.conversation_table}
|
||||
WHERE conversation_id = %s
|
||||
LIMIT 1
|
||||
"""
|
||||
try:
|
||||
with self._get_conn() as conn:
|
||||
self._ensure_conversation_schema(conn)
|
||||
with conn.cursor(pymysql.cursors.DictCursor) as cur:
|
||||
self._log_entity_stage(
|
||||
"conversations",
|
||||
"get_by_id",
|
||||
"sql_execute",
|
||||
started_at,
|
||||
{"conversation_id": conversation_id, "table": self.conversation_table},
|
||||
)
|
||||
cur.execute(select_sql, (conversation_id,))
|
||||
result = cur.fetchone()
|
||||
self._log_entity_stage(
|
||||
"conversations",
|
||||
"get_by_id",
|
||||
"success",
|
||||
started_at,
|
||||
{
|
||||
"conversation_id": conversation_id,
|
||||
"table": self.conversation_table,
|
||||
"found": bool(result),
|
||||
},
|
||||
)
|
||||
return dict(result) if result else None
|
||||
except Exception as exc:
|
||||
self._log_entity_stage(
|
||||
"conversations",
|
||||
"get_by_id",
|
||||
"failed",
|
||||
started_at,
|
||||
{"conversation_id": conversation_id, "table": self.conversation_table, "error": str(exc)},
|
||||
)
|
||||
self._log_local("message_storage.get_conversation_failed", {
|
||||
"error": str(exc),
|
||||
"conversation_table": self.conversation_table,
|
||||
"conversation_id": conversation_id,
|
||||
})
|
||||
return None
|
||||
|
||||
def update_conversation_updated_at(self, conversation_id: str, updated_at: int) -> bool:
|
||||
started_at = self._now_ms()
|
||||
self._log_entity_stage(
|
||||
"conversations",
|
||||
"update_updated_at",
|
||||
"start",
|
||||
started_at,
|
||||
{"conversation_id": conversation_id, "updated_at": updated_at},
|
||||
)
|
||||
if not self.enabled:
|
||||
self._log_entity_stage(
|
||||
"conversations",
|
||||
"update_updated_at",
|
||||
"skipped",
|
||||
started_at,
|
||||
{"conversation_id": conversation_id, "reason": "storage_disabled"},
|
||||
)
|
||||
return False
|
||||
|
||||
self._ensure_table()
|
||||
if not self.enabled:
|
||||
self._log_entity_stage(
|
||||
"conversations",
|
||||
"update_updated_at",
|
||||
"skipped",
|
||||
started_at,
|
||||
{"conversation_id": conversation_id, "reason": "storage_disabled_after_init"},
|
||||
)
|
||||
return False
|
||||
|
||||
update_sql = f"""
|
||||
UPDATE {self.conversation_table}
|
||||
SET updated_at = %s,
|
||||
update_date = %s
|
||||
WHERE conversation_id = %s
|
||||
"""
|
||||
try:
|
||||
update_ms = self._resolve_epoch_millis(updated_at)
|
||||
update_bundle = DateTimeGenerator.bundle(update_ms, default_to_now=True)
|
||||
with self._get_conn() as conn:
|
||||
self._ensure_conversation_schema(conn)
|
||||
with conn.cursor() as cur:
|
||||
self._log_entity_stage(
|
||||
"conversations",
|
||||
"update_updated_at",
|
||||
"sql_execute",
|
||||
started_at,
|
||||
{"conversation_id": conversation_id, "table": self.conversation_table},
|
||||
)
|
||||
affected_rows = cur.execute(
|
||||
update_sql,
|
||||
(update_ms, update_bundle.db_datetime, conversation_id),
|
||||
)
|
||||
self._log_entity_stage(
|
||||
"conversations",
|
||||
"update_updated_at",
|
||||
"success",
|
||||
started_at,
|
||||
{"conversation_id": conversation_id, "affected_rows": int(affected_rows or 0)},
|
||||
)
|
||||
return bool(affected_rows)
|
||||
except Exception as exc:
|
||||
self._log_entity_stage(
|
||||
"conversations",
|
||||
"update_updated_at",
|
||||
"failed",
|
||||
started_at,
|
||||
{"conversation_id": conversation_id, "table": self.conversation_table, "error": str(exc)},
|
||||
)
|
||||
self._log_local("message_storage.update_conversation_failed", {
|
||||
"error": str(exc),
|
||||
"conversation_table": self.conversation_table,
|
||||
"conversation_id": conversation_id,
|
||||
})
|
||||
return False
|
||||
|
||||
def save_message(
|
||||
self,
|
||||
conversation_id: str,
|
||||
message_id: str,
|
||||
query: str,
|
||||
answer: Optional[str] = None,
|
||||
workflow_type: Optional[str] = None,
|
||||
user: Optional[str] = None,
|
||||
sql_query: Optional[str] = None,
|
||||
execution_result: Optional[Dict[str, Any]] = None,
|
||||
metadata: Optional[Dict[str, Any]] = None,
|
||||
created_at: Optional[int] = None,
|
||||
updated_at: Optional[int] = None,
|
||||
logs: Optional[List[str]] = None,
|
||||
) -> bool:
|
||||
started_at = self._now_ms()
|
||||
self._log_entity_stage(
|
||||
"messages",
|
||||
"create",
|
||||
"start",
|
||||
started_at,
|
||||
{
|
||||
"conversation_id": conversation_id,
|
||||
"message_id": message_id,
|
||||
"query_len": len(query or ""),
|
||||
"answer_len": len(answer or ""),
|
||||
"workflow_type": workflow_type,
|
||||
},
|
||||
)
|
||||
"""
|
||||
保存消息记录
|
||||
|
||||
Args:
|
||||
conversation_id: 会话 ID
|
||||
message_id: 消息 ID
|
||||
query: 用户查询
|
||||
answer: AI 回复
|
||||
workflow_type: 工作流类型 (conversation/tool_using)
|
||||
user: 用户标识
|
||||
sql_query: 生成的 SQL
|
||||
execution_result: SQL 执行结果
|
||||
metadata: 其他元数据
|
||||
logs: 过程日志（兼容 Java saveMessageToDB）
|
||||
|
||||
Returns:
|
||||
bool: 是否保存成功
|
||||
"""
|
||||
if not self.enabled:
|
||||
self._log_entity_stage(
|
||||
"messages",
|
||||
"create",
|
||||
"skipped",
|
||||
started_at,
|
||||
{"conversation_id": conversation_id, "message_id": message_id, "reason": "storage_disabled"},
|
||||
)
|
||||
return False
|
||||
|
||||
self._ensure_table()
|
||||
if not self.enabled:
|
||||
self._log_entity_stage(
|
||||
"messages",
|
||||
"create",
|
||||
"skipped",
|
||||
started_at,
|
||||
{"conversation_id": conversation_id, "message_id": message_id, "reason": "storage_disabled_after_init"},
|
||||
)
|
||||
return False
|
||||
|
||||
audit = self._build_audit_fields(
|
||||
random_code=message_id,
|
||||
user=user,
|
||||
created_value=created_at,
|
||||
updated_value=updated_at,
|
||||
)
|
||||
log_payload = {
|
||||
"workflow_type": workflow_type,
|
||||
"sql_query": sql_query,
|
||||
"execution_result": execution_result or {},
|
||||
"metadata": metadata or {},
|
||||
}
|
||||
normalized_logs = [str(item) for item in (logs or []) if str(item).strip()]
|
||||
if normalized_logs:
|
||||
log_payload["data"] = "\n".join(normalized_logs)
|
||||
message_record = MessagesDTO(
|
||||
message_id=message_id,
|
||||
conversation_id=conversation_id,
|
||||
user=user,
|
||||
query=query,
|
||||
answer=answer,
|
||||
feedback=None,
|
||||
feedback_content=None,
|
||||
created_at=audit["created_at"],
|
||||
updated_at=audit["updated_at"],
|
||||
log=log_payload,
|
||||
)
|
||||
|
||||
insert_sql = f"""
|
||||
INSERT INTO {self.table}(
|
||||
random_code, create_user, create_date, update_user, update_date,
|
||||
create_user_name, update_user_name,
|
||||
message_id, conversation_id, user, query, answer,
|
||||
feedback, feedback_content, created_at, updated_at, `log`
|
||||
) VALUES(%s, %s, %s, %s, %s, %s, %s, %s, %s, %s, %s, %s, %s, %s, %s, %s, %s)
|
||||
"""
|
||||
|
||||
try:
|
||||
with self._get_conn() as conn:
|
||||
with conn.cursor() as cur:
|
||||
self._log_entity_stage(
|
||||
"messages",
|
||||
"create",
|
||||
"sql_execute",
|
||||
started_at,
|
||||
{"conversation_id": conversation_id, "message_id": message_id, "table": self.table},
|
||||
)
|
||||
cur.execute(
|
||||
insert_sql,
|
||||
(
|
||||
audit["random_code"],
|
||||
audit["create_user"],
|
||||
audit["create_date"],
|
||||
audit["update_user"],
|
||||
audit["update_date"],
|
||||
audit["create_user_name"],
|
||||
audit["update_user_name"],
|
||||
message_record.message_id,
|
||||
message_record.conversation_id,
|
||||
message_record.user,
|
||||
message_record.query,
|
||||
message_record.answer,
|
||||
message_record.feedback,
|
||||
message_record.feedback_content,
|
||||
message_record.created_at,
|
||||
message_record.updated_at,
|
||||
json.dumps(message_record.log, ensure_ascii=False),
|
||||
),
|
||||
)
|
||||
self._log_entity_stage(
|
||||
"messages",
|
||||
"create",
|
||||
"success",
|
||||
started_at,
|
||||
{"conversation_id": conversation_id, "message_id": message_id, "table": self.table},
|
||||
)
|
||||
return True
|
||||
except Exception as exc:
|
||||
self._log_entity_stage(
|
||||
"messages",
|
||||
"create",
|
||||
"failed",
|
||||
started_at,
|
||||
{"conversation_id": conversation_id, "message_id": message_id, "table": self.table, "error": str(exc)},
|
||||
)
|
||||
self._log_local("message_storage.save_failed", {
|
||||
"error": str(exc),
|
||||
"messages_table": self.table,
|
||||
"message_id": message_id,
|
||||
"conversation_id": conversation_id,
|
||||
})
|
||||
# 开发阶段容错，避免日志失败影响主流程
|
||||
return False
|
||||
|
||||
def get_conversation_history(
|
||||
self,
|
||||
conversation_id: str,
|
||||
limit: int = 20
|
||||
) -> List[Dict[str, Any]]:
|
||||
"""
|
||||
获取会话历史消息
|
||||
|
||||
Args:
|
||||
conversation_id: 会话 ID
|
||||
limit: 返回消息数量
|
||||
|
||||
Returns:
|
||||
List[Dict[str, Any]]: 消息列表
|
||||
"""
|
||||
started_at = self._now_ms()
|
||||
self._log_entity_stage(
|
||||
"messages",
|
||||
"get_history",
|
||||
"start",
|
||||
started_at,
|
||||
{"conversation_id": conversation_id, "limit": limit},
|
||||
)
|
||||
if not self.enabled:
|
||||
self._log_entity_stage(
|
||||
"messages",
|
||||
"get_history",
|
||||
"skipped",
|
||||
started_at,
|
||||
{"conversation_id": conversation_id, "reason": "storage_disabled"},
|
||||
)
|
||||
return []
|
||||
|
||||
self._ensure_table()
|
||||
if not self.enabled:
|
||||
self._log_entity_stage(
|
||||
"messages",
|
||||
"get_history",
|
||||
"skipped",
|
||||
started_at,
|
||||
{"conversation_id": conversation_id, "reason": "storage_disabled_after_init"},
|
||||
)
|
||||
return []
|
||||
|
||||
select_sql = f"""
|
||||
SELECT * FROM {self.table}
|
||||
WHERE conversation_id = %s
|
||||
ORDER BY created_at DESC
|
||||
LIMIT %s
|
||||
"""
|
||||
|
||||
try:
|
||||
with self._get_conn() as conn:
|
||||
with conn.cursor(pymysql.cursors.DictCursor) as cur:
|
||||
self._log_entity_stage(
|
||||
"messages",
|
||||
"get_history",
|
||||
"sql_execute",
|
||||
started_at,
|
||||
{"conversation_id": conversation_id, "limit": limit, "table": self.table},
|
||||
)
|
||||
cur.execute(select_sql, (conversation_id, limit))
|
||||
results = cur.fetchall()
|
||||
self._log_entity_stage(
|
||||
"messages",
|
||||
"get_history",
|
||||
"success",
|
||||
started_at,
|
||||
{"conversation_id": conversation_id, "count": len(results or [])},
|
||||
)
|
||||
return list(results)
|
||||
except Exception as exc:
|
||||
self._log_entity_stage(
|
||||
"messages",
|
||||
"get_history",
|
||||
"failed",
|
||||
started_at,
|
||||
{"conversation_id": conversation_id, "error": str(exc)},
|
||||
)
|
||||
return []
|
||||
|
||||
def update_feedback_by_message_id(
|
||||
self,
|
||||
message_id: str,
|
||||
feedback: str,
|
||||
feedback_content: Optional[str] = None,
|
||||
) -> bool:
|
||||
"""按 message_id 回写点赞/点踩反馈。"""
|
||||
started_at = self._now_ms()
|
||||
self._log_entity_stage(
|
||||
"messages",
|
||||
"update_feedback",
|
||||
"start",
|
||||
started_at,
|
||||
{"message_id": message_id, "feedback": feedback},
|
||||
)
|
||||
if not self.enabled:
|
||||
self._log_entity_stage(
|
||||
"messages",
|
||||
"update_feedback",
|
||||
"skipped",
|
||||
started_at,
|
||||
{"message_id": message_id, "reason": "storage_disabled"},
|
||||
)
|
||||
return False
|
||||
|
||||
self._ensure_table()
|
||||
if not self.enabled:
|
||||
self._log_entity_stage(
|
||||
"messages",
|
||||
"update_feedback",
|
||||
"skipped",
|
||||
started_at,
|
||||
{"message_id": message_id, "reason": "storage_disabled_after_init"},
|
||||
)
|
||||
return False
|
||||
|
||||
update_sql = f"""
|
||||
UPDATE {self.table}
|
||||
SET feedback = %s,
|
||||
feedback_content = %s,
|
||||
updated_at = %s,
|
||||
update_date = %s
|
||||
WHERE message_id = %s
|
||||
"""
|
||||
|
||||
normalized_feedback_content = (feedback_content or "").strip() or None
|
||||
now_bundle = DateTimeGenerator.now()
|
||||
try:
|
||||
with self._get_conn() as conn:
|
||||
with conn.cursor() as cur:
|
||||
self._log_entity_stage(
|
||||
"messages",
|
||||
"update_feedback",
|
||||
"sql_execute",
|
||||
started_at,
|
||||
{"message_id": message_id, "table": self.table},
|
||||
)
|
||||
affected_rows = cur.execute(
|
||||
update_sql,
|
||||
(
|
||||
feedback,
|
||||
normalized_feedback_content,
|
||||
now_bundle.epoch_millis,
|
||||
now_bundle.db_datetime,
|
||||
message_id,
|
||||
),
|
||||
)
|
||||
self._log_entity_stage(
|
||||
"messages",
|
||||
"update_feedback",
|
||||
"success",
|
||||
started_at,
|
||||
{"message_id": message_id, "affected_rows": int(affected_rows or 0)},
|
||||
)
|
||||
return bool(affected_rows)
|
||||
except Exception as exc:
|
||||
self._log_entity_stage(
|
||||
"messages",
|
||||
"update_feedback",
|
||||
"failed",
|
||||
started_at,
|
||||
{"message_id": message_id, "error": str(exc)},
|
||||
)
|
||||
# 开发阶段容错，避免日志失败影响主流程
|
||||
return False
|
||||
|
||||
|
||||
# 全局单例
|
||||
_GLOBAL_MESSAGE_STORAGE: Optional[MessageStorage] = None
|
||||
|
||||
|
||||
def get_message_storage() -> MessageStorage:
|
||||
"""获取消息存储服务实例"""
|
||||
global _GLOBAL_MESSAGE_STORAGE
|
||||
if _GLOBAL_MESSAGE_STORAGE is None:
|
||||
_GLOBAL_MESSAGE_STORAGE = MessageStorage()
|
||||
return _GLOBAL_MESSAGE_STORAGE
|
||||
@@ -0,0 +1,104 @@
|
||||
from __future__ import annotations
|
||||
|
||||
import json
|
||||
from typing import Any, Dict, Optional
|
||||
|
||||
import pymysql
|
||||
|
||||
from config import Config
|
||||
from services.common.datetime_utils import DateTimeGenerator
|
||||
|
||||
|
||||
class StructuredLogger:
|
||||
def __init__(self):
|
||||
cfg = Config.get_section("logging_mysql")
|
||||
self.enabled = str(cfg.get("enabled", "false")).lower() in ("1", "true", "yes")
|
||||
self.host = cfg.get("host", "127.0.0.1")
|
||||
self.port = int(cfg.get("port", 3306))
|
||||
self.user = cfg.get("user", "root")
|
||||
self.password = cfg.get("password", "")
|
||||
self.database = cfg.get("database", "more_dots")
|
||||
self.table = cfg.get("table", "structured_logs")
|
||||
self.connect_timeout = int(cfg.get("connect_timeout", 5))
|
||||
self._inited = False
|
||||
|
||||
def _get_conn(self):
|
||||
return pymysql.connect(
|
||||
host=self.host,
|
||||
port=self.port,
|
||||
user=self.user,
|
||||
password=self.password,
|
||||
database=self.database,
|
||||
charset="utf8mb4",
|
||||
autocommit=True,
|
||||
connect_timeout=self.connect_timeout,
|
||||
)
|
||||
|
||||
def _ensure_table(self) -> None:
|
||||
if self._inited or not self.enabled:
|
||||
return
|
||||
sql = f"""
|
||||
CREATE TABLE IF NOT EXISTS {self.table} (
|
||||
id BIGINT PRIMARY KEY AUTO_INCREMENT,
|
||||
trace_id VARCHAR(64) NOT NULL,
|
||||
level VARCHAR(16) NOT NULL,
|
||||
event VARCHAR(128) NOT NULL,
|
||||
error_code VARCHAR(64) NULL,
|
||||
payload JSON NULL,
|
||||
created_at DATETIME NOT NULL
|
||||
) ENGINE=InnoDB DEFAULT CHARSET=utf8mb4;
|
||||
"""
|
||||
try:
|
||||
with self._get_conn() as conn:
|
||||
with conn.cursor() as cur:
|
||||
cur.execute(sql)
|
||||
self._inited = True
|
||||
except Exception:
|
||||
# 开发阶段容错，避免日志失败影响主流程
|
||||
self.enabled = False
|
||||
|
||||
def log(self, level: str, event: str, trace_id: str, payload: Optional[Dict[str, Any]] = None, error_code: Optional[str] = None) -> None:
|
||||
print(json.dumps({
|
||||
"trace_id": trace_id,
|
||||
"level": level,
|
||||
"event": event,
|
||||
"error_code": error_code,
|
||||
"payload": payload or {},
|
||||
"created_at": DateTimeGenerator.now().iso_str,
|
||||
}, ensure_ascii=False))
|
||||
|
||||
if not self.enabled:
|
||||
return
|
||||
|
||||
self._ensure_table()
|
||||
if not self.enabled:
|
||||
return
|
||||
|
||||
insert_sql = f"INSERT INTO {self.table}(trace_id, level, event, error_code, payload, created_at) VALUES(%s,%s,%s,%s,%s,%s)"
|
||||
try:
|
||||
with self._get_conn() as conn:
|
||||
with conn.cursor() as cur:
|
||||
cur.execute(
|
||||
insert_sql,
|
||||
(
|
||||
trace_id,
|
||||
level,
|
||||
event,
|
||||
error_code,
|
||||
json.dumps(payload or {}, ensure_ascii=False),
|
||||
DateTimeGenerator.now().db_datetime,
|
||||
),
|
||||
)
|
||||
except Exception:
|
||||
# 开发阶段容错，避免日志失败影响主流程
|
||||
return
|
||||
|
||||
|
||||
_GLOBAL_STRUCTURED_LOGGER: Optional[StructuredLogger] = None
|
||||
|
||||
|
||||
def get_structured_logger() -> StructuredLogger:
|
||||
global _GLOBAL_STRUCTURED_LOGGER
|
||||
if _GLOBAL_STRUCTURED_LOGGER is None:
|
||||
_GLOBAL_STRUCTURED_LOGGER = StructuredLogger()
|
||||
return _GLOBAL_STRUCTURED_LOGGER
|
||||
@@ -1,30 +0,0 @@
|
||||
from __future__ import annotations
|
||||
|
||||
import json
|
||||
from datetime import datetime
|
||||
from typing import Any, Dict, Optional
|
||||
|
||||
|
||||
class StructuredLogger:
|
||||
def __init__(self):
|
||||
pass
|
||||
|
||||
def log(self, level: str, event: str, trace_id: str, payload: Optional[Dict[str, Any]] = None, error_code: Optional[str] = None) -> None:
|
||||
print(json.dumps({
|
||||
"trace_id": trace_id,
|
||||
"level": level,
|
||||
"event": event,
|
||||
"error_code": error_code,
|
||||
"payload": payload or {},
|
||||
"created_at": datetime.now().isoformat(),
|
||||
}, ensure_ascii=False))
|
||||
|
||||
|
||||
_GLOBAL_STRUCTURED_LOGGER: Optional[StructuredLogger] = None
|
||||
|
||||
|
||||
def get_structured_logger() -> StructuredLogger:
|
||||
global _GLOBAL_STRUCTURED_LOGGER
|
||||
if _GLOBAL_STRUCTURED_LOGGER is None:
|
||||
_GLOBAL_STRUCTURED_LOGGER = StructuredLogger()
|
||||
return _GLOBAL_STRUCTURED_LOGGER
|
||||
@@ -1,55 +0,0 @@
|
||||
from typing import Any, Dict
|
||||
|
||||
from config import Config
|
||||
from services.ragflow_client import RagflowClient, extract_table_name
|
||||
|
||||
|
||||
class TemplateMatcher:
|
||||
"""模板匹配器：RAGFlow 检索"""
|
||||
|
||||
def __init__(self):
|
||||
self._ragflow = RagflowClient()
|
||||
cfg = Config.get_section("ragflow")
|
||||
self._dataset_id = (cfg.get("table_retrieval_dataset_id") or "").strip()
|
||||
self._top_k = int(cfg.get("retrieval_top_k", 3))
|
||||
|
||||
def _validate(self) -> None:
|
||||
if not self._dataset_id:
|
||||
raise RuntimeError("未配置 ragflow.table_retrieval_dataset_id，无法进行表名检索")
|
||||
|
||||
def match(self, normalized_text: str) -> Dict[str, Any]:
|
||||
"""返回匹配的表名与原始响应"""
|
||||
self._validate()
|
||||
try:
|
||||
response = self._ragflow.retrieve(normalized_text, top_k=self._top_k, dataset_id=self._dataset_id)
|
||||
except Exception as e:
|
||||
return {"table_name": None, "raw": {"error": str(e)}}
|
||||
|
||||
candidates = []
|
||||
data = response.get("data") if isinstance(response, dict) else None
|
||||
records = []
|
||||
if isinstance(data, list):
|
||||
records = data
|
||||
elif isinstance(data, dict):
|
||||
chunks = data.get("chunks")
|
||||
if isinstance(chunks, list):
|
||||
records = chunks
|
||||
|
||||
for item in records:
|
||||
table_name = extract_table_name(item)
|
||||
if table_name:
|
||||
candidates.append(table_name)
|
||||
|
||||
matched = candidates[0] if candidates else None
|
||||
return {"table_name": matched, "raw": response}
|
||||
|
||||
|
||||
_GLOBAL_TEMPLATE_MATCHER: TemplateMatcher | None = None
|
||||
|
||||
|
||||
def get_template_matcher() -> TemplateMatcher:
|
||||
"""获取全局 TemplateMatcher（单例）"""
|
||||
global _GLOBAL_TEMPLATE_MATCHER
|
||||
if _GLOBAL_TEMPLATE_MATCHER is None:
|
||||
_GLOBAL_TEMPLATE_MATCHER = TemplateMatcher()
|
||||
return _GLOBAL_TEMPLATE_MATCHER
|
||||
@@ -1,272 +0,0 @@
|
||||
"""
|
||||
工具路由器模块
|
||||
|
||||
支持动态注册和管理工具
|
||||
"""
|
||||
|
||||
import json
|
||||
import logging
|
||||
import time
|
||||
from typing import Any, Callable, Dict, List, Optional, Type
|
||||
|
||||
from langchain_core.tools import BaseTool
|
||||
|
||||
from tools.calculator import CalculatorTool
|
||||
from tools.web_search import WebSearchTool
|
||||
from tools.rest_api_tool import RestApiTool
|
||||
from tools.sr_api_tool import SrApiQueryTool
|
||||
from core.registry import ToolRegistry, ToolMetadata
|
||||
|
||||
logger = logging.getLogger(__name__)
|
||||
|
||||
|
||||
class ToolRouter:
|
||||
"""
|
||||
工具路由器：统一调用入口
|
||||
|
||||
支持特性：
|
||||
- 动态注册工具
|
||||
- 工具元数据管理
|
||||
- 执行监控
|
||||
"""
|
||||
|
||||
def __init__(self, tools: Optional[List[BaseTool]] = None):
|
||||
self._tools: Dict[str, BaseTool] = {}
|
||||
self._tool_metadata: Dict[str, ToolMetadata] = {}
|
||||
self._execution_stats: Dict[str, Dict[str, Any]] = {}
|
||||
|
||||
if tools is not None:
|
||||
for tool in tools:
|
||||
self.register_tool(tool)
|
||||
else:
|
||||
self._register_default_tools()
|
||||
|
||||
def _register_default_tools(self) -> None:
|
||||
"""注册默认工具"""
|
||||
default_tools = [
|
||||
CalculatorTool(),
|
||||
WebSearchTool(),
|
||||
RestApiTool(),
|
||||
SrApiQueryTool(),
|
||||
]
|
||||
for tool in default_tools:
|
||||
self.register_tool(tool)
|
||||
|
||||
def register_tool(
|
||||
self,
|
||||
tool: BaseTool,
|
||||
description: str = "",
|
||||
version: str = "1.0.0",
|
||||
timeout: int = 30,
|
||||
retry: int = 0,
|
||||
tags: Optional[List[str]] = None,
|
||||
) -> None:
|
||||
"""
|
||||
注册工具
|
||||
|
||||
Args:
|
||||
tool: 工具实例
|
||||
description: 描述（默认使用 tool.description）
|
||||
version: 版本
|
||||
timeout: 超时时间
|
||||
retry: 重试次数
|
||||
tags: 标签
|
||||
"""
|
||||
name = tool.name
|
||||
metadata = ToolMetadata(
|
||||
name=name,
|
||||
description=description or tool.description,
|
||||
version=version,
|
||||
timeout=timeout,
|
||||
retry=retry,
|
||||
tags=tags or [],
|
||||
)
|
||||
|
||||
self._tools[name] = tool
|
||||
self._tool_metadata[name] = metadata
|
||||
self._execution_stats[name] = {
|
||||
"total_calls": 0,
|
||||
"success_calls": 0,
|
||||
"failed_calls": 0,
|
||||
"total_time_ms": 0,
|
||||
}
|
||||
|
||||
ToolRegistry._entries[name] = type(
|
||||
"RegistryEntry",
|
||||
(),
|
||||
{"instance": tool, "metadata": {"tool_metadata": metadata}}
|
||||
)()
|
||||
|
||||
logger.info(f"Registered tool: {name} (v{version})")
|
||||
|
||||
def unregister_tool(self, name: str) -> bool:
|
||||
"""
|
||||
注销工具
|
||||
|
||||
Args:
|
||||
name: 工具名称
|
||||
|
||||
Returns:
|
||||
是否成功注销
|
||||
"""
|
||||
if name in self._tools:
|
||||
del self._tools[name]
|
||||
del self._tool_metadata[name]
|
||||
del self._execution_stats[name]
|
||||
ToolRegistry.unregister(name)
|
||||
logger.info(f"Unregistered tool: {name}")
|
||||
return True
|
||||
return False
|
||||
|
||||
def get_tool(self, name: str) -> Optional[BaseTool]:
|
||||
"""获取工具实例"""
|
||||
return self._tools.get(name)
|
||||
|
||||
def get_tool_metadata(self, name: str) -> Optional[ToolMetadata]:
|
||||
"""获取工具元数据"""
|
||||
return self._tool_metadata.get(name)
|
||||
|
||||
def list_tools(self) -> List[str]:
|
||||
"""列出可用工具名称"""
|
||||
return list(self._tools.keys())
|
||||
|
||||
def get_tool_info(self, name: str) -> Optional[Dict[str, Any]]:
|
||||
"""获取工具详细信息"""
|
||||
if name not in self._tools:
|
||||
return None
|
||||
|
||||
tool = self._tools[name]
|
||||
metadata = self._tool_metadata.get(name)
|
||||
stats = self._execution_stats.get(name, {})
|
||||
|
||||
return {
|
||||
"name": name,
|
||||
"description": metadata.description if metadata else tool.description,
|
||||
"version": metadata.version if metadata else "unknown",
|
||||
"timeout": metadata.timeout if metadata else 30,
|
||||
"tags": metadata.tags if metadata else [],
|
||||
"stats": {
|
||||
"total_calls": stats.get("total_calls", 0),
|
||||
"success_rate": self._calculate_success_rate(name),
|
||||
},
|
||||
}
|
||||
|
||||
def call(self, tool_name: str, payload: Any) -> Dict[str, Any]:
|
||||
"""
|
||||
调用工具并返回标准化结果
|
||||
|
||||
Args:
|
||||
tool_name: 工具名称
|
||||
payload: 输入参数
|
||||
|
||||
Returns:
|
||||
标准化结果 {ok, data, error}
|
||||
"""
|
||||
tool = self._tools.get(tool_name)
|
||||
if not tool:
|
||||
return {"ok": False, "data": None, "error": f"工具不存在: {tool_name}"}
|
||||
|
||||
start_time = time.time()
|
||||
|
||||
try:
|
||||
if isinstance(payload, (dict, list)):
|
||||
input_value = json.dumps(payload, ensure_ascii=False)
|
||||
elif payload is None:
|
||||
input_value = ""
|
||||
else:
|
||||
input_value = str(payload)
|
||||
|
||||
result = tool.run(input_value)
|
||||
|
||||
self._record_success(tool_name, time.time() - start_time)
|
||||
|
||||
return {"ok": True, "data": result, "error": None}
|
||||
|
||||
except Exception as e:
|
||||
self._record_failure(tool_name, time.time() - start_time)
|
||||
return {"ok": False, "data": None, "error": str(e)}
|
||||
|
||||
def call_with_metadata(
|
||||
self,
|
||||
tool_name: str,
|
||||
payload: Any,
|
||||
) -> Dict[str, Any]:
|
||||
"""
|
||||
调用工具并返回包含元数据的结果
|
||||
|
||||
Args:
|
||||
tool_name: 工具名称
|
||||
payload: 输入参数
|
||||
|
||||
Returns:
|
||||
包含元数据的结果
|
||||
"""
|
||||
result = self.call(tool_name, payload)
|
||||
metadata = self.get_tool_metadata(tool_name)
|
||||
|
||||
return {
|
||||
**result,
|
||||
"tool_name": tool_name,
|
||||
"tool_version": metadata.version if metadata else "unknown",
|
||||
"execution_time_ms": self._execution_stats.get(tool_name, {}).get("last_time_ms", 0),
|
||||
}
|
||||
|
||||
def _record_success(self, tool_name: str, elapsed: float) -> None:
|
||||
"""记录成功执行"""
|
||||
if tool_name in self._execution_stats:
|
||||
stats = self._execution_stats[tool_name]
|
||||
stats["total_calls"] += 1
|
||||
stats["success_calls"] += 1
|
||||
stats["total_time_ms"] += elapsed * 1000
|
||||
stats["last_time_ms"] = elapsed * 1000
|
||||
|
||||
def _record_failure(self, tool_name: str, elapsed: float) -> None:
|
||||
"""记录失败执行"""
|
||||
if tool_name in self._execution_stats:
|
||||
stats = self._execution_stats[tool_name]
|
||||
stats["total_calls"] += 1
|
||||
stats["failed_calls"] += 1
|
||||
stats["total_time_ms"] += elapsed * 1000
|
||||
stats["last_time_ms"] = elapsed * 1000
|
||||
|
||||
def _calculate_success_rate(self, tool_name: str) -> float:
|
||||
"""计算成功率"""
|
||||
stats = self._execution_stats.get(tool_name)
|
||||
if not stats or stats["total_calls"] == 0:
|
||||
return 0.0
|
||||
return stats["success_calls"] / stats["total_calls"]
|
||||
|
||||
def get_all_stats(self) -> Dict[str, Dict[str, Any]]:
|
||||
"""获取所有工具的执行统计"""
|
||||
result = {}
|
||||
for name in self._tools:
|
||||
result[name] = {
|
||||
**self._execution_stats.get(name, {}),
|
||||
"success_rate": self._calculate_success_rate(name),
|
||||
}
|
||||
return result
|
||||
|
||||
def register_function(
|
||||
self,
|
||||
name: str,
|
||||
func: Callable,
|
||||
description: str = "",
|
||||
timeout: int = 30,
|
||||
) -> None:
|
||||
"""
|
||||
将普通函数注册为工具
|
||||
|
||||
Args:
|
||||
name: 工具名称
|
||||
func: 函数
|
||||
description: 描述
|
||||
timeout: 超时时间
|
||||
"""
|
||||
from langchain_core.tools import Tool
|
||||
|
||||
tool = Tool(
|
||||
name=name,
|
||||
description=description,
|
||||
func=func,
|
||||
)
|
||||
self.register_tool(tool, description=description, timeout=timeout)
|
||||
@@ -0,0 +1,5 @@
|
||||
"""工具服务模块"""
|
||||
|
||||
from .tool_router import ToolRouter
|
||||
|
||||
__all__ = ["ToolRouter"]
|
||||
@@ -0,0 +1,41 @@
|
||||
import json
|
||||
from typing import Any, Dict, Optional
|
||||
|
||||
from langchain_core.tools import BaseTool
|
||||
|
||||
from tools.calculator import CalculatorTool
|
||||
from tools.web_search import WebSearchTool
|
||||
from tools.rest_api_tool import RestApiTool
|
||||
from tools.sr_api_tool import SrApiQueryTool
|
||||
|
||||
|
||||
class ToolRouter:
|
||||
"""工具路由器：统一调用入口"""
|
||||
|
||||
def __init__(self, tools: Optional[list[BaseTool]] = None):
|
||||
if tools is None:
|
||||
tools = [CalculatorTool(), WebSearchTool(), RestApiTool(), SrApiQueryTool()]
|
||||
self._tools: Dict[str, BaseTool] = {tool.name: tool for tool in tools}
|
||||
|
||||
def list_tools(self) -> list[str]:
|
||||
"""列出可用工具名称"""
|
||||
return list(self._tools.keys())
|
||||
|
||||
def call(self, tool_name: str, payload: Any) -> Dict[str, Any]:
|
||||
"""调用工具并返回标准化结果"""
|
||||
tool = self._tools.get(tool_name)
|
||||
if not tool:
|
||||
return {"ok": False, "data": None, "error": f"工具不存在: {tool_name}"}
|
||||
|
||||
try:
|
||||
if isinstance(payload, (dict, list)):
|
||||
input_value = json.dumps(payload, ensure_ascii=False)
|
||||
elif payload is None:
|
||||
input_value = ""
|
||||
else:
|
||||
input_value = str(payload)
|
||||
|
||||
result = tool.run(input_value)
|
||||
return {"ok": True, "data": result, "error": None}
|
||||
except Exception as e:
|
||||
return {"ok": False, "data": None, "error": str(e)}
|
||||
@@ -0,0 +1,12 @@
|
||||
# Tests 模块
|
||||
|
||||
## 作用
|
||||
|
||||
维护项目自动化测试，覆盖工作流、API 与脚本行为。
|
||||
|
||||
## 文件
|
||||
|
||||
- `test_basic.py`：基础可用性测试
|
||||
- `test_endpoints.py`：接口行为测试
|
||||
- `test_sql_workflow_refactor.py`：SQL 流程关键逻辑测试
|
||||
- `test_console_chat.py` / `test_demo_chat.py`：脚本相关测试
|
||||
@@ -0,0 +1 @@
|
||||
"""测试模块"""
|
||||
@@ -0,0 +1,51 @@
|
||||
"""
|
||||
pytest 配置文件
|
||||
|
||||
提供全局的 fixtures 和配置
|
||||
"""
|
||||
|
||||
import os
|
||||
import sys
|
||||
from pathlib import Path
|
||||
|
||||
import pytest
|
||||
|
||||
# 添加项目根目录到 Python 路径
|
||||
project_root = Path(__file__).parent.parent
|
||||
sys.path.insert(0, str(project_root))
|
||||
|
||||
|
||||
@pytest.fixture(scope="session")
|
||||
def project_dir() -> Path:
|
||||
"""获取项目根目录"""
|
||||
return project_root
|
||||
|
||||
|
||||
@pytest.fixture(scope="session")
|
||||
def config_dir() -> Path:
|
||||
"""获取配置目录"""
|
||||
return project_root / "config"
|
||||
|
||||
|
||||
@pytest.fixture
|
||||
def sample_user_input() -> str:
|
||||
"""示例用户输入"""
|
||||
return "你好，帮我查询订单信息"
|
||||
|
||||
|
||||
@pytest.fixture
|
||||
def sample_sql() -> str:
|
||||
"""示例 SQL 语句"""
|
||||
return "SELECT * FROM orders LIMIT 10"
|
||||
|
||||
|
||||
# 自动使用的 fixture（可选）
|
||||
@pytest.fixture(autouse=True)
|
||||
def setup_environment():
|
||||
"""为所有测试设置环境变量"""
|
||||
# 可以在这里设置测试环境变量
|
||||
os.environ.setdefault("TESTING", "true")
|
||||
yield
|
||||
# 清理（如果需要）
|
||||
if "TESTING" in os.environ:
|
||||
del os.environ["TESTING"]
|
||||
+118
-2
@@ -6,6 +6,9 @@ LangChain + LangGraph 脚手架基础测试
|
||||
import unittest
|
||||
import sys
|
||||
import os
|
||||
from unittest.mock import patch
|
||||
from typing import cast
|
||||
from langchain_core.messages import AIMessage
|
||||
sys.path.append(os.path.dirname(os.path.dirname(os.path.abspath(__file__))))
|
||||
|
||||
config_path = os.path.join(os.path.dirname(__file__), '..', 'config', 'config.ini')
|
||||
@@ -27,6 +30,23 @@ OPENAI_API_KEY = your_openai_api_key_here
|
||||
""")
|
||||
|
||||
from workflows.workflow_manager import WorkflowManager, WorkflowType
|
||||
from services.common.app_errors import AppError, ErrorCode
|
||||
|
||||
|
||||
class FakeModel:
|
||||
def invoke(self, messages):
|
||||
if len(messages) == 2 and getattr(messages[0], 'content', '').startswith('You are a translation and normalization assistant'):
|
||||
return AIMessage(content=messages[1].content)
|
||||
return AIMessage(content='fallback')
|
||||
|
||||
|
||||
class EmptyTemplateMatcher:
|
||||
def match(self, normalized_text: str):
|
||||
return {
|
||||
'table_name': None,
|
||||
'candidates': [],
|
||||
'raw': {'query': normalized_text},
|
||||
}
|
||||
|
||||
|
||||
class TestWorkflowManager(unittest.TestCase):
|
||||
@@ -34,8 +54,16 @@ class TestWorkflowManager(unittest.TestCase):
|
||||
|
||||
def setUp(self):
|
||||
"""设置测试夹具"""
|
||||
self.manager = WorkflowManager()
|
||||
|
||||
self.model_patcher = patch("agent.core.base_agent.create_chat_model", lambda model_section=None: FakeModel())
|
||||
self.matcher_patcher = patch("agent.core.nodes.get_template_matcher", lambda: EmptyTemplateMatcher())
|
||||
self.model_patcher.start()
|
||||
self.matcher_patcher.start()
|
||||
self.manager = WorkflowManager(enable_multi_turn=False)
|
||||
|
||||
def tearDown(self):
|
||||
self.matcher_patcher.stop()
|
||||
self.model_patcher.stop()
|
||||
|
||||
def test_get_available_workflows(self):
|
||||
"""测试可用工作流返回"""
|
||||
workflows = self.manager.get_available_workflows()
|
||||
@@ -68,6 +96,94 @@ class TestWorkflowManager(unittest.TestCase):
|
||||
self.assertIsNotNone(session_info)
|
||||
self.assertEqual(session_info["workflow_type"], WorkflowType.CONVERSATION)
|
||||
|
||||
def test_conversation_session_is_temporarily_stateless(self):
|
||||
"""测试关闭多轮后，同一 session_id 也不会自动累积对话历史"""
|
||||
first = self.manager.execute_workflow(
|
||||
WorkflowType.CONVERSATION,
|
||||
"Hello, first turn",
|
||||
session_id="session-1",
|
||||
)
|
||||
second = self.manager.execute_workflow(
|
||||
WorkflowType.CONVERSATION,
|
||||
"Hello, second turn",
|
||||
session_id="session-1",
|
||||
)
|
||||
other = self.manager.execute_workflow(
|
||||
WorkflowType.CONVERSATION,
|
||||
"Hello, other session",
|
||||
session_id="session-2",
|
||||
)
|
||||
|
||||
session_one = self.manager.get_session_info("session-1")
|
||||
session_two = self.manager.get_session_info("session-2")
|
||||
|
||||
self.assertEqual(first["session_id"], "session-1")
|
||||
self.assertEqual(second["session_id"], "session-1")
|
||||
self.assertEqual(other["session_id"], "session-2")
|
||||
self.assertNotIn("conversation_history", session_one)
|
||||
self.assertNotIn("last_context", session_one)
|
||||
self.assertNotIn("conversation_history", session_two)
|
||||
self.assertNotIn("last_context", session_two)
|
||||
self.assertEqual(len(first["result"].get("conversation_history") or []), 2)
|
||||
self.assertEqual(len(second["result"].get("conversation_history") or []), 2)
|
||||
self.assertEqual(len(other["result"].get("conversation_history") or []), 2)
|
||||
|
||||
def test_conversation_session_memory_can_be_enabled(self):
|
||||
"""测试开启多轮后，同一 session_id 会保存并复用会话级历史"""
|
||||
manager = WorkflowManager(enable_multi_turn=True)
|
||||
|
||||
first = manager.execute_workflow(
|
||||
WorkflowType.CONVERSATION,
|
||||
"Hello, first turn",
|
||||
session_id="session-enabled",
|
||||
)
|
||||
second = manager.execute_workflow(
|
||||
WorkflowType.CONVERSATION,
|
||||
"Hello, second turn",
|
||||
session_id="session-enabled",
|
||||
)
|
||||
|
||||
session_info = manager.get_session_info("session-enabled")
|
||||
|
||||
self.assertIn("conversation_history", session_info)
|
||||
self.assertIn("last_context", session_info)
|
||||
self.assertGreaterEqual(len(session_info["conversation_history"]), 4)
|
||||
self.assertEqual(len(first["result"].get("conversation_history") or []), 2)
|
||||
self.assertGreaterEqual(len(second["result"].get("conversation_history") or []), 4)
|
||||
|
||||
def test_reusing_session_id_with_different_workflow_raises(self):
|
||||
"""测试同一个 session_id 不能绑定到不同工作流"""
|
||||
self.manager.execute_workflow(
|
||||
WorkflowType.CONVERSATION,
|
||||
"Hello, test session",
|
||||
session_id="shared-session",
|
||||
)
|
||||
|
||||
with self.assertRaises(ValueError):
|
||||
self.manager.execute_workflow(
|
||||
WorkflowType.TOOL_USING,
|
||||
"2 + 2",
|
||||
session_id="shared-session",
|
||||
)
|
||||
|
||||
def test_execute_workflow_rejects_none_user_input(self):
|
||||
"""测试空 query 会在进入 Agent 之前被拒绝"""
|
||||
with self.assertRaises(AppError) as ctx:
|
||||
self.manager.execute_workflow(WorkflowType.CONVERSATION, cast(str, None))
|
||||
|
||||
self.assertEqual(ctx.exception.code, ErrorCode.INVALID_REQUEST)
|
||||
self.assertEqual(ctx.exception.status_code, 400)
|
||||
self.assertEqual(ctx.exception.detail, {"field": "user_input", "reason": "missing_or_blank"})
|
||||
|
||||
def test_execute_workflow_rejects_blank_user_input(self):
|
||||
"""测试全空白 query 会在进入 Agent 之前被拒绝"""
|
||||
with self.assertRaises(AppError) as ctx:
|
||||
self.manager.execute_workflow(WorkflowType.CONVERSATION, " ")
|
||||
|
||||
self.assertEqual(ctx.exception.code, ErrorCode.INVALID_REQUEST)
|
||||
self.assertEqual(ctx.exception.status_code, 400)
|
||||
self.assertEqual(ctx.exception.detail, {"field": "user_input", "reason": "missing_or_blank"})
|
||||
|
||||
|
||||
class TestConfiguration(unittest.TestCase):
|
||||
"""测试配置校验"""
|
||||
|
||||
@@ -0,0 +1,99 @@
|
||||
from schemas.agent_input import AgentInput
|
||||
from schemas.chat_message_request import ChatMessageRequestDTO
|
||||
from schemas.stream_input import StreamInputDTO
|
||||
|
||||
|
||||
def test_chat_message_request_accepts_frontend_dto_shape():
|
||||
payload = ChatMessageRequestDTO(
|
||||
query="查询 SO 4020438779 的 eta 信息",
|
||||
inputs={"region": "ANZ", "filters": ["top10"]},
|
||||
response_mode="streaming",
|
||||
user="tester-001",
|
||||
conversation_id="cid-123",
|
||||
files=[{"type": "image", "transfer_method": "remote_url", "url": "https://example.com/a.png"}],
|
||||
)
|
||||
|
||||
assert payload.query == "查询 SO 4020438779 的 eta 信息"
|
||||
assert payload.inputs == {"region": "ANZ", "filters": ["top10"]}
|
||||
assert payload.response_mode == "streaming"
|
||||
assert payload.user == "tester-001"
|
||||
assert payload.conversation_id == "cid-123"
|
||||
assert payload.files[0].model_dump()["type"] == "image"
|
||||
|
||||
|
||||
|
||||
def test_chat_message_request_defaults_inputs_and_files():
|
||||
payload = ChatMessageRequestDTO(
|
||||
query="hello",
|
||||
response_mode="blocking",
|
||||
user="tester-002",
|
||||
)
|
||||
|
||||
assert payload.inputs == {}
|
||||
assert payload.files == []
|
||||
assert payload.conversation_id is None
|
||||
|
||||
|
||||
|
||||
def test_chat_message_request_accepts_non_dict_inputs_object():
|
||||
payload = ChatMessageRequestDTO(
|
||||
query="hello",
|
||||
inputs=[{"name": "foo"}],
|
||||
response_mode="streaming",
|
||||
user="tester-003",
|
||||
)
|
||||
|
||||
assert payload.inputs == [{"name": "foo"}]
|
||||
|
||||
|
||||
|
||||
def test_chat_message_request_allows_nullable_java_dto_fields():
|
||||
payload = ChatMessageRequestDTO()
|
||||
|
||||
assert payload.query is None
|
||||
assert payload.response_mode is None
|
||||
assert payload.user is None
|
||||
assert payload.conversation_id is None
|
||||
assert payload.inputs == {}
|
||||
assert payload.files == []
|
||||
|
||||
|
||||
def test_chat_message_request_accepts_legacy_auto_generate_name_field():
|
||||
payload = ChatMessageRequestDTO(
|
||||
query="hello",
|
||||
response_mode="streaming",
|
||||
user="tester-legacy",
|
||||
auto_generate_name=True,
|
||||
)
|
||||
|
||||
assert payload.auto_generate_name is True
|
||||
assert payload.query == "hello"
|
||||
|
||||
|
||||
def test_agent_input_uses_same_schema_as_chat_message_request():
|
||||
payload = AgentInput(
|
||||
query="hello",
|
||||
response_mode="blocking",
|
||||
user="tester-004",
|
||||
inputs={"k": "v"},
|
||||
files=[{"type": "text"}],
|
||||
)
|
||||
|
||||
assert isinstance(payload, ChatMessageRequestDTO)
|
||||
assert payload.inputs == {"k": "v"}
|
||||
assert payload.files[0].model_dump()["type"] == "text"
|
||||
|
||||
|
||||
def test_stream_input_uses_same_schema_as_chat_message_request():
|
||||
payload = StreamInputDTO(
|
||||
query="hello",
|
||||
response_mode="streaming",
|
||||
user="tester-005",
|
||||
inputs={"region": "ANZ"},
|
||||
)
|
||||
|
||||
assert isinstance(payload, ChatMessageRequestDTO)
|
||||
assert payload.response_mode == "streaming"
|
||||
assert payload.user == "tester-005"
|
||||
|
||||
|
||||
@@ -0,0 +1,30 @@
|
||||
from schemas.chat_message_response import ChatMessageResponseDTO
|
||||
|
||||
|
||||
EXPECTED_KEYS = [
|
||||
"id",
|
||||
"event",
|
||||
"task_id",
|
||||
"message_id",
|
||||
"conversation_id",
|
||||
"answer",
|
||||
"created_at",
|
||||
]
|
||||
|
||||
|
||||
def test_chat_message_response_matches_java_dto_shape():
|
||||
dto = ChatMessageResponseDTO(
|
||||
id="id-1",
|
||||
task_id="task-1",
|
||||
message_id="msg-1",
|
||||
conversation_id="cid-1",
|
||||
answer="hello",
|
||||
created_at=1705395332,
|
||||
)
|
||||
|
||||
dumped = dto.model_dump()
|
||||
|
||||
assert list(dumped.keys()) == EXPECTED_KEYS
|
||||
assert dumped["event"] == "message"
|
||||
assert isinstance(dumped["created_at"], int)
|
||||
|
||||
@@ -0,0 +1,158 @@
|
||||
import json
|
||||
from unittest.mock import patch
|
||||
|
||||
from scripts.console_chat import format_result, main, run_turn
|
||||
|
||||
|
||||
class FakeMessage:
|
||||
def __init__(self, content: str):
|
||||
self.content = content
|
||||
|
||||
|
||||
class FakeAgent:
|
||||
def __init__(self, model_section=None):
|
||||
self.model_section = model_section
|
||||
self.calls = []
|
||||
|
||||
def run(self, query, **kwargs):
|
||||
self.calls.append((query, kwargs))
|
||||
return {
|
||||
"messages": [FakeMessage("mock answer")],
|
||||
"context": {
|
||||
"table_name": "apbo_eta_ful",
|
||||
"query_mode": "detail",
|
||||
"final_sql": "SELECT service_order_id FROM dwd_ai.apbo_eta_ful",
|
||||
"sql_plan": {"selected_table": "apbo_eta_ful", "query_mode": "detail"},
|
||||
},
|
||||
"final_step": "response_generated",
|
||||
}
|
||||
|
||||
|
||||
def test_format_result_includes_optional_blocks():
|
||||
result = {
|
||||
"messages": [FakeMessage("hello")],
|
||||
"context": {
|
||||
"final_sql": "SELECT 1",
|
||||
"sql_plan": {"mode": "detail"},
|
||||
"foo": "bar",
|
||||
},
|
||||
}
|
||||
|
||||
text = format_result(result, show_sql=True, show_context=True, show_plan=True)
|
||||
assert "Answer:" in text
|
||||
assert "SQL:" in text
|
||||
assert "SQL Plan:" in text
|
||||
assert "Context:" in text
|
||||
|
||||
|
||||
def test_format_result_renders_table_from_wrapped_sr_api_result():
|
||||
wrapped = json.dumps(
|
||||
{
|
||||
"status_code": 200,
|
||||
"text": json.dumps(
|
||||
{
|
||||
"data": [
|
||||
{"service_order_id": "4020438779", "ship_to_country": "VN"},
|
||||
{"service_order_id": "4020438780", "ship_to_country": "PH"},
|
||||
]
|
||||
},
|
||||
ensure_ascii=False,
|
||||
),
|
||||
},
|
||||
ensure_ascii=False,
|
||||
)
|
||||
result = {
|
||||
"messages": [FakeMessage('{"status_code": 200, "text": "..."}')],
|
||||
"context": {
|
||||
"sr_api_result": wrapped,
|
||||
"final_sql": "SELECT service_order_id, ship_to_country FROM dwd_ai.apbo_eta_ful",
|
||||
},
|
||||
}
|
||||
|
||||
text = format_result(result)
|
||||
assert "Query Result: 2 row(s)" in text
|
||||
assert "status=200" in text
|
||||
assert "service_order_id" in text
|
||||
assert "ship_to_country" in text
|
||||
assert "4020438779" in text
|
||||
assert "VN" in text
|
||||
|
||||
|
||||
def test_format_result_renders_columns_and_rows_payload():
|
||||
result = {
|
||||
"messages": [FakeMessage("ok")],
|
||||
"context": {
|
||||
"sr_api_result": {
|
||||
"status_code": 200,
|
||||
"text": {
|
||||
"columns": ["region", "qty"],
|
||||
"rows": [["ANZ", 12], ["CAP", 8]],
|
||||
},
|
||||
}
|
||||
},
|
||||
}
|
||||
|
||||
text = format_result(result)
|
||||
assert "Query Result: 2 row(s)" in text
|
||||
assert "status=200" in text
|
||||
assert "region" in text
|
||||
assert "qty" in text
|
||||
assert "ANZ" in text
|
||||
assert "12" in text
|
||||
|
||||
|
||||
def test_format_result_falls_back_for_non_tabular_error():
|
||||
result = {
|
||||
"messages": [FakeMessage("请求失败: timeout")],
|
||||
"context": {"sr_api_result": "请求失败: timeout"},
|
||||
}
|
||||
|
||||
text = format_result(result)
|
||||
assert "Answer:" in text
|
||||
assert "请求失败: timeout" in text
|
||||
assert "Query Result:" not in text
|
||||
|
||||
|
||||
def test_main_one_shot_success(capsys):
|
||||
with patch("scripts.console_chat.Config.validate_config", return_value=None), \
|
||||
patch("scripts.console_chat.ConversationAgent", FakeAgent):
|
||||
exit_code = main([
|
||||
"--query",
|
||||
"查询 SO 4020438779 的 eta 信息",
|
||||
"--skip-sr-api",
|
||||
"--show-sql",
|
||||
])
|
||||
|
||||
captured = capsys.readouterr()
|
||||
assert exit_code == 0
|
||||
assert "mock answer" in captured.out
|
||||
assert "SELECT service_order_id FROM dwd_ai.apbo_eta_ful" in captured.out
|
||||
|
||||
|
||||
def test_run_turn_enables_debug_node_trace(capsys):
|
||||
agent = FakeAgent()
|
||||
|
||||
run_turn(
|
||||
agent,
|
||||
"查询 SO 4020438779 的 eta 信息",
|
||||
user="tester",
|
||||
conversation_id="cid-1",
|
||||
skip_sr_api=True,
|
||||
show_sql=False,
|
||||
show_context=False,
|
||||
show_plan=False,
|
||||
)
|
||||
|
||||
_, kwargs = agent.calls[-1]
|
||||
assert kwargs["debug_node_trace"] is True
|
||||
|
||||
|
||||
def test_main_config_error(capsys):
|
||||
with patch("scripts.console_chat.Config.validate_config", side_effect=ValueError("bad config")):
|
||||
exit_code = main(["--query", "hello"])
|
||||
|
||||
captured = capsys.readouterr()
|
||||
assert exit_code == 1
|
||||
assert "Configuration error" in captured.err
|
||||
|
||||
|
||||
Some files were not shown because too many files have changed in this diff Show More
Reference in New Issue
Block a user