feat(deepdata): 引入修改密码、文件预览组件与清洗算子增强,deepflow 改名为 deep-flow

本次同步 09-12 至 09-28 的代码变更,主要内容:

新增功能
- 修改密码:后端新增 ChangePasswordRequest DTO 与UserController/UserService
  对应接口,前端新增 ChangePasswordDialog 并在 Header 接入入口
- 文件预览组件重构:file-preview 目录拆分出 VideoPreview(支持 blobUrl 直传)、
  ImagePreview、AudioPreview,index.tsx 统一调度各类型预览器
- 新增 my_ops 算子模块:markitdown_parser、mineru_pdf_parser、text_quality_evaluator
- 新增 tools/minio-file-server MinIO 文件服务

功能增强
- 数据清洗:cleaning_task_service/scheduler/routes 重构,
  data_juicer_executor 与 wrapper 增强,OperatorTable/LogsTable/TaskDetail 同步调整
- 数据标注:annotation sync.py、project.py 接口与schema 更新
- 数据采集、算子市场、首页与菜单路由相关页面调整
- DataJuicer 算子接入(useOperatorOperations、dj_ops_schema)

结构调整
- deepflow/ 更名为 deep-flow/(419 个文件重命名)
- 新增 helm 部署编排、GitHub Actions 之外的自建镜像构建脚本

未纳入本次提交
- scripts-backup/、runtime/python-executor-backup/、components_backup/(备份目录)
- *.backup*、__pycache__ 产物
- zh_core_web_sm-3.8.0-py3-none-any.whl(46MB 构建产物)
- DataX/(内嵌独立仓库,远程亦未收录其源码)
This commit is contained in:
沃巴蒂
2026-10-03 22:44:56 +08:00
parent cbb1048e18
commit ff22ed3a8b
1156 changed files with 129912 additions and 21716 deletions
+1 -1
View File
@@ -1,4 +1,4 @@
# DeepData Environment Variables Template
# deepdata Environment Variables Template
# Copy this file to .env and fill in the values
# cp .env.example .env
# IMPORTANT: Never commit .env to git! It is already in .gitignore.
+14 -34
View File
@@ -44,7 +44,7 @@ services:
- PGSQL_HOST=deepdata-database
- PGSQL_PORT=5432
- pgsql_password=${DB_PASSWORD:?DB_PASSWORD is required. Set in .env file}
- deepdata_jwt_enable=${DEEPDATA_JWT_ENABLE:-false}
- DEEPDATA_jwt_enable=${DEEPDATA_jwt_enable_JWT_ENABLE:-false}
- milvus_uri=${MILVUS_URI:-http://milvus:19530}
- LABEL_STUDIO_USERNAME=${LABEL_STUDIO_USERNAME:-admin@demo.com}
- LABEL_STUDIO_USER_TOKEN=${LABEL_STUDIO_USER_TOKEN:-}
@@ -69,23 +69,7 @@ services:
- '8080:8080'
environment:
- JWT_SECRET=${JWT_SECRET:-}
- DB_PASSWORD=${DB_PASSWORD:?DB_PASSWORD is required. Set in .env file}
- deepdata.jwt.enable=${DEEPDATA_JWT_ENABLE:-false}
# ---- Casdoor SSO(M1/M2):空值保持 Spring 默认;生产经 .env 注入 ----
- DEEPDATA_CASDOOR_ENABLED=${DEEPDATA_CASDOOR_ENABLED:-false}
- DEEPDATA_CASDOOR_ISSUER=${DEEPDATA_CASDOOR_ISSUER:-}
- DEEPDATA_CASDOOR_AUTHORIZEURI=${DEEPDATA_CASDOOR_AUTHORIZE_URI:-}
- DEEPDATA_CASDOOR_TOKENURI=${DEEPDATA_CASDOOR_TOKEN_URI:-}
- DEEPDATA_CASDOOR_JWKSURI=${DEEPDATA_CASDOOR_JWKS_URI:-}
- DEEPDATA_CASDOOR_CLIENTID=${DEEPDATA_CASDOOR_CLIENT_ID:-}
- DEEPDATA_CASDOOR_CLIENTSECRET=${DEEPDATA_CASDOOR_CLIENT_SECRET:-}
- DEEPDATA_CASDOOR_REDIRECTURI=${DEEPDATA_CASDOOR_REDIRECT_URI:-}
# ---- M3: Casdoor 账号唯一数据源 ----
- DEEPDATA_CASDOOR_ACCOUNTONLY=${DEEPDATA_CASDOOR_ACCOUNTONLY:-false}
- DEEPDATA_CASDOOR_SYNC_API_TOKEN=${DEEPDATA_CASDOOR_SYNC_API_TOKEN:-}
- DEEPDATA_CASDOOR_SYNC_USERNAME=${DEEPDATA_CASDOOR_SYNC_USERNAME:-}
- DEEPDATA_CASDOOR_SYNC_PASSWORD=${DEEPDATA_CASDOOR_SYNC_PASSWORD:-}
- DEEPDATA_CASDOOR_SYNC_INTERVAL_MINUTES=${DEEPDATA_CASDOOR_SYNC_INTERVAL_MINUTES:-5}
- LOG_ROTATION_MAX_SIZE=${LOG_ROTATION_MAX_SIZE:-100MB}
- LOG_ROTATION_BACKUP_COUNT=${LOG_ROTATION_BACKUP_COUNT:-30}
volumes:
@@ -214,38 +198,34 @@ services:
# ==============================
# Optional: Deer Flow (profile: deepflow)
# Optional: Deer Flow (profile: deep-flow)
# ==============================
deepflow-backend:
image: ${REGISTRY:-}deepflow-backend
container_name: deepflow-backend
deep-flow-backend:
image: ${REGISTRY:-}deep-flow-backend
container_name: deep-flow-backend
env_file:
- .env
ports:
- "8000:8000"
volumes:
- ./conf.yaml:/app/conf.yaml:ro
- deepflow-log-volume:/var/log/deepflow
- deep-flow-log-volume:/var/log/deep-flow
restart: on-failure
networks:
- deepdata
profiles:
- deepflow
- deep-flow
deepflow-frontend:
image: ${REGISTRY:-}deepflow-frontend
container_name: deepflow-frontend
deep-flow-frontend:
image: ${REGISTRY:-}deep-flow-frontend
container_name: deep-flow-frontend
env_file:
- .env
ports:
- "3001:3000"
depends_on:
- deepflow-backend
- deep-flow-backend
restart: on-failure
networks:
- deepdata
profiles:
- deepflow
- deep-flow
# ==============================
# Optional: Label Studio (profile: label-studio)
@@ -412,8 +392,8 @@ volumes:
name: deepdata-graph-data-volume
# Deer Flow
deepflow-log-volume:
name: deepflow-log-volume
deep-flow-log-volume:
name: deep-flow-log-volume
# Label Studio
label-studio-data:
@@ -1,5 +1,5 @@
apiVersion: v2
name: deepflow
name: deep-flow
description: A Helm chart for Kubernetes
# A chart can be either an 'application' or a 'library' chart.
@@ -7,7 +7,7 @@ replicaCount: 1
# This sets the container image more information can be found here: https://kubernetes.io/docs/concepts/containers/images/
image:
repository: "deepflow-backend"
repository: "deep-flow-backend"
# This sets the pull policy for images.
pullPolicy: "IfNotPresent"
# Overrides the image tag whose default is the chart appVersion.
@@ -16,8 +16,8 @@ image:
# This is for the secrets for pulling an image from a private repository more information can be found here: https://kubernetes.io/docs/tasks/configure-pod-container/pull-image-private-registry/
imagePullSecrets: []
# This is to override the chart name.
nameOverride: "deepflow-backend"
fullnameOverride: "deepflow-backend"
nameOverride: "deep-flow-backend"
fullnameOverride: "deep-flow-backend"
envFrom: []
env: []
@@ -7,7 +7,7 @@ replicaCount: 1
# This sets the container image more information can be found here: https://kubernetes.io/docs/concepts/containers/images/
image:
repository: "deepflow-frontend"
repository: "deep-flow-frontend"
# This sets the pull policy for images.
pullPolicy: "IfNotPresent"
# Overrides the image tag whose default is the chart appVersion.
@@ -16,8 +16,8 @@ image:
# This is for the secrets for pulling an image from a private repository more information can be found here: https://kubernetes.io/docs/tasks/configure-pod-container/pull-image-private-registry/
imagePullSecrets: []
# This is to override the chart name.
nameOverride: "deepflow-frontend"
fullnameOverride: "deepflow-frontend"
nameOverride: "deep-flow-frontend"
fullnameOverride: "deep-flow-frontend"
envFrom: []
env: []
@@ -1,7 +1,7 @@
apiVersion: v1
kind: Secret
metadata:
name: deepflow-env
name: deep-flow-env
stringData:
{{- range .Files.Lines ".env" }}
{{- $line := trim . }}
@@ -17,6 +17,6 @@ stringData:
apiVersion: v1
kind: Secret
metadata:
name: deepflow-conf
name: deep-flow-conf
stringData:
{{ (.Files.Glob "conf.yaml").AsConfig | indent 2 }}
@@ -1,40 +1,40 @@
# Default values for deepflow.
# This is a YAML-formatted file.
# Declare variables to be passed into your templates.
global:
image:
repository: ""
pullPolicy: "IfNotPresent"
backend:
name: "deepflow-backend"
tag: "latest"
frontend:
name: "deepflow-frontend"
tag: "latest"
envFrom: &envFrom
secretRef:
name: deepflow-env
backend:
envFrom:
- *envFrom
volumes:
- name: deepflow-conf
secret:
secretName: deepflow-conf
- name: log-volume
persistentVolumeClaim:
claimName: deepdata-log-pvc
volumeMounts:
- name: deepflow-conf
mountPath: /app/conf.yaml
subPath: conf.yaml
- name: log-volume
mountPath: /var/log/deepflow
subPath: deepflow
frontend:
envFrom:
- *envFrom
# Default values for deep-flow.
# This is a YAML-formatted file.
# Declare variables to be passed into your templates.
global:
image:
repository: "ghcr.io/modelengine-group/"
pullPolicy: "IfNotPresent"
backend:
name: "deep-flow-backend"
tag: "latest"
frontend:
name: "deep-flow-frontend"
tag: "latest"
envFrom: &envFrom
secretRef:
name: deep-flow-env
backend:
envFrom:
- *envFrom
volumes:
- name: deep-flow-conf
secret:
secretName: deep-flow-conf
- name: log-volume
persistentVolumeClaim:
claimName: deepdata-log-pvc
volumeMounts:
- name: deep-flow-conf
mountPath: /app/conf.yaml
subPath: conf.yaml
- name: log-volume
mountPath: /var/log/deep-flow
subPath: deep-flow
frontend:
envFrom:
- *envFrom
File diff suppressed because it is too large Load Diff