Develop hsc (#58)

feature: 优化镜像构建/部署

.github/workflows/docker-image-backend-python.yml

@@ -0,0 +1,27 @@
+name: Python Backend Docker Image CI
+
+on:
+  push:
+    branches: [ "main" ]
+    paths:
+      - 'backend/**'
+      - 'scripts/images/datamate-python/**'
+      - '.github/workflows/docker-image-backend-python.yml'
+  pull_request:
+    branches: [ "main" ]
+    paths:
+      - 'backend/**'
+      - 'scripts/images/datamate-python/**'
+      - '.github/workflows/docker-image-backend-python.yml'
+  workflow_dispatch:
+
+jobs:
+  call-docker-build:
+    name: Build and Push Backend Python Docker Image
+    uses: ./.github/workflows/docker-images-reusable.yml
+    permissions:
+      contents: read
+      packages: write
+    with:
+      service_name: backend-python
+      build_dir: .

Makefile

@@ -3,6 +3,7 @@ MAKEFLAGS += --no-print-directory
 WITH_MINERU ?= false  # 默认不构建mineru
 VERSION ?= latest
 NAMESPACE ?= datamate
+REGISTRY ?= "ghcr.io/modelengine-group/"
 
 ifdef COMSPEC
     # Windows 环境
@@ -17,7 +18,7 @@ build-%:
 	$(MAKE) $*-docker-build
 
 .PHONY: build
-build: backend-docker-build frontend-docker-build runtime-docker-build $(if $(WITH_MINERU),mineru-docker-build)
+build: backend-docker-build frontend-docker-build runtime-docker-build
 
 .PHONY: create-namespace
 create-namespace:
@@ -42,7 +43,24 @@ else
 endif
 
 .PHONY: install
-install: install-datamate
+install:
+ifeq ($(origin INSTALLER), undefined)
+	@echo "Choose a deployment method:"
+	@echo "1. Docker/Docker-Compose"
+	@echo "2. Kubernetes/Helm"
+	@echo -n "Enter choice: "
+	@read choice; \
+	case $$choice in \
+		1) INSTALLER=docker ;; \
+		2) INSTALLER=k8s ;; \
+		*) echo "Invalid choice" && exit 1 ;; \
+	esac; \
+	$(MAKE) datamate-$$INSTALLER-install; \
+	$(MAKE) milvus-$$INSTALLER-install
+else
+	$(MAKE) datamate-$(INSTALLER)-install; \
+	$(MAKE) milvus-$(INSTALLER)-install
+endif
 
 .PHONY: uninstall-%
 uninstall-%:
@@ -63,7 +81,24 @@ else
 endif
 
 .PHONY: uninstall
-uninstall: uninstall-datamate
+uninstall:
+ifeq ($(origin INSTALLER), undefined)
+	@echo "Choose a deployment method:"
+	@echo "1. Docker/Docker-Compose"
+	@echo "2. Kubernetes/Helm"
+	@echo -n "Enter choice: "
+	@read choice; \
+	case $$choice in \
+		1) INSTALLER=docker ;; \
+		2) INSTALLER=k8s ;; \
+		*) echo "Invalid choice" && exit 1 ;; \
+	esac; \
+    $(MAKE) milvus-$$INSTALLER-uninstall; \
+	$(MAKE) datamate-$$INSTALLER-uninstall
+else
+	$(MAKE) milvus-$(INSTALLER)-uninstall; \
+	$(MAKE) datamate-$(INSTALLER)-uninstall
+endif
 
 # build
 .PHONY: backend-docker-build
@@ -92,6 +127,11 @@ deer-flow-docker-build:
 .PHONY: mineru-docker-build
 mineru-docker-build:
 	docker build -t datamate-mineru:$(VERSION) . -f scripts/images/mineru/Dockerfile
+
+.PHONY: backend-python-docker-build
+backend-python-docker-build:
+	docker build -t datamate-backend-python:$(VERSION) . -f scripts/images/datamate-python/Dockerfile
+
 .PHONY: backend-docker-install
 backend-docker-install:
 	cd deployment/docker/datamate && docker compose up -d backend
@@ -118,7 +158,7 @@ runtime-docker-uninstall:
 
 .PHONY: mineru-docker-install
 mineru-docker-install:
-	cd deployment/docker/datamate && cp .env.example .env && docker compose up -d datamate-mineru
+	cd deployment/docker/datamate && export REGISTRY=$(REGISTRY) && docker compose up -d datamate-mineru
 
 .PHONY: mineru-docker-uninstall
 mineru-docker-uninstall:
@@ -134,31 +174,40 @@ mineru-k8s-uninstall:
 
 .PHONY: datamate-docker-install
 datamate-docker-install:
-	cd deployment/docker/datamate && cp .env.example .env && docker compose -f docker-compose.yml up -d
+	cd deployment/docker/datamate && export REGISTRY=$(REGISTRY) && docker compose -f docker-compose.yml up -d
 
 .PHONY: datamate-docker-uninstall
 datamate-docker-uninstall:
-	cd deployment/docker/datamate && docker compose -f docker-compose.yml down -v
+	cd deployment/docker/datamate && docker compose -f docker-compose.yml --profile mineru down -v
 
 .PHONY: deer-flow-docker-install
 deer-flow-docker-install:
-	cd deployment/docker/datamate && cp .env.deer-flow.example .env && docker compose -f docker-compose.yml up -d
+	cd deployment/docker/datamate && export NGINX_CONF="./backend-with-deer-flow.conf" && export REGISTRY=$(REGISTRY) && docker compose -f docker-compose.yml up -d
 	cp -n runtime/deer-flow/.env.example runtime/deer-flow/.env
 	cp -n runtime/deer-flow/conf.yaml.example runtime/deer-flow/conf.yaml
-	cp runtime/deer-flow/.env deployment/docker/deer-flow/.env && cp runtime/deer-flow/conf.yaml deployment/docker/deer-flow/conf.yaml
+	cp runtime/deer-flow/.env deployment/docker/deer-flow/.env
-	cd deployment/docker/deer-flow && docker compose -f docker-compose.yml up -d
+	cp runtime/deer-flow/conf.yaml deployment/docker/deer-flow/conf.yaml
+	cd deployment/docker/deer-flow && export REGISTRY=$(REGISTRY) && docker compose -f docker-compose.yml up -d
 
 .PHONY: deer-flow-docker-uninstall
 deer-flow-docker-uninstall:
 	@if docker compose ls --filter name=datamate | grep -q datamate; then \
-		cd deployment/docker/datamate && docker compose -f docker-compose.yml up -d; \
+		cd deployment/docker/datamate && export REGISTRY=$(REGISTRY) && docker compose -f docker-compose.yml up -d; \
 	fi
 	cd deployment/docker/deer-flow && docker compose -f docker-compose.yml down
 
+.PHONY: milvus-docker-install
+milvus-docker-install:
+	cd deployment/docker/milvus && docker compose -f docker-compose.yml up -d
+
+.PHONY: milvus-docker-uninstall
+milvus-docker-uninstall:
+	cd deployment/docker/milvus && docker compose -f docker-compose.yml down
+
 .PHONY: datamate-k8s-install
 datamate-k8s-install: create-namespace
 	kubectl create configmap datamate-init-sql --from-file=scripts/db/ --dry-run=client -o yaml | kubectl apply -f - -n $(NAMESPACE)
-	helm upgrade datamate deployment/helm/datamate/ -n $(NAMESPACE) --install
+	helm upgrade datamate deployment/helm/datamate/ -n $(NAMESPACE) --install --set global.image.repository=$(REPOSITORY)
 
 .PHONY: datamate-k8s-uninstall
 datamate-k8s-uninstall:
@@ -167,14 +216,17 @@ datamate-k8s-uninstall:
 
 .PHONY: deer-flow-k8s-install
 deer-flow-k8s-install:
-	helm upgrade datamate deployment/helm/datamate/ -n $(NAMESPACE) --install --set global.deerFlow.enable=true
+	helm upgrade datamate deployment/helm/datamate/ -n $(NAMESPACE) --install --set global.deerFlow.enable=true --set global.image.repository=$(REPOSITORY)
 	cp runtime/deer-flow/.env deployment/helm/deer-flow/charts/public/.env
 	cp runtime/deer-flow/conf.yaml deployment/helm/deer-flow/charts/public/conf.yaml
-	helm upgrade deer-flow deployment/helm/deer-flow -n $(NAMESPACE) --install
+	helm upgrade deer-flow deployment/helm/deer-flow -n $(NAMESPACE) --install --set global.image.repository=$(REPOSITORY)
 
 .PHONY: deer-flow-k8s-uninstall
 deer-flow-k8s-uninstall:
 	helm uninstall deer-flow -n $(NAMESPACE) --ignore-not-found
+	@if helm ls -n $(NAMESPACE) --filter datamate | grep -q datamate; then \
+		helm upgrade datamate deployment/helm/datamate/ -n $(NAMESPACE) --set global.deerFlow.enable=false; \
+	fi
 
 .PHONY: milvus-k8s-install
 milvus-k8s-install:

deployment/docker/datamate/.env.deer-flow.example

@@ -1 +0,0 @@
-NGINX_CONF=./backend-with-deer-flow.conf

deployment/docker/datamate/.env.example

@@ -1 +0,0 @@
-NGINX_CONF=./backend.conf

deployment/docker/datamate/backend-with-deer-flow.conf

@@ -9,6 +9,20 @@ server {
 
     add_header Set-Cookie "NEXT_LOCALE=zh";
 
+    location /api/synthesis/ {
+        proxy_pass http://datamate-backend-python:18000/api/synthesis/;
+        proxy_set_header Host $host;
+        proxy_set_header X-Real-IP $remote_addr;
+        proxy_set_header X-Forwarded-For $proxy_add_x_forwarded_for;
+    }
+
+    location /api/annotation/ {
+        proxy_pass http://datamate-backend-python:18000/api/annotation/;
+        proxy_set_header Host $host;
+        proxy_set_header X-Real-IP $remote_addr;
+        proxy_set_header X-Forwarded-For $proxy_add_x_forwarded_for;
+    }
+
     location /api/ {
         proxy_pass http://datamate-backend:8080/api/;
         proxy_set_header Host $host;

deployment/docker/datamate/docker-compose.yml

@@ -2,7 +2,7 @@ services:
   # 1) backend
   datamate-backend:
     container_name: datamate-backend
-    image: datamate-backend
+    image: ${REGISTRY:-}datamate-backend
     restart: on-failure
     privileged: true
     volumes:
@@ -18,7 +18,7 @@ services:
   # 1) backend (Python)
   datamate-backend-python:
     container_name: datamate-backend-python
-    image: datamate-backend-python
+    image: ${REGISTRY:-}datamate-backend-python
     restart: on-failure
     privileged: true
     environment:
@@ -34,13 +34,13 @@ services:
   # 2) frontend（NodePort 30000）
   datamate-frontend:
     container_name: datamate-frontend
-    image: datamate-frontend
+    image: ${REGISTRY:-}datamate-frontend
     restart: on-failure
     ports:
       - "30000:80"            # nodePort → hostPort
     volumes:
       - frontend_log_volume:/var/log/datamate/frontend
-      - $NGINX_CONF:/etc/nginx/conf.d/backend.conf
+      - ${NGINX_CONF:-./backend.conf}:/etc/nginx/conf.d/backend.conf
     networks: [ datamate ]
     depends_on:
       - datamate-backend
@@ -71,7 +71,7 @@ services:
   # 3) runtime
   datamate-runtime:
     container_name: datamate-runtime
-    image: datamate-runtime
+    image: ${REGISTRY:-}datamate-runtime
     restart: on-failure
     environment:
       RAY_DEDUP_LOGS: "0"
@@ -81,7 +81,6 @@ services:
       MYSQL_USER: "root"
       MYSQL_PASSWORD: "password"
       MYSQL_DATABASE: "datamate"
-      PDF_FORMATTER_BASE_URL: "http://datamate-mineru:9001"
     command:
       - python
       - /opt/runtime/datamate/operator_runtime.py
@@ -135,6 +134,8 @@ volumes:
     name: datamate-operator-upload-volume
   operator-runtime-volume:
     name: datamate-operator-runtime-volume
+  mineru_log_volume:
+    name: datamate-mineru_log_volume
 
 networks:
   datamate:

deployment/docker/deer-flow/docker-compose.yml

@@ -1,6 +1,6 @@
 services:
   deer-flow-backend:
-    image: deer-flow-backend
+    image: ${REGISTRY:-}deer-flow-backend
     container_name: deer-flow-backend
     env_file:
       - .env
@@ -11,7 +11,7 @@ services:
       - datamate
 
   deer-flow-frontend:
-    image: deer-flow-frontend
+    image: ${REGISTRY:-}deer-flow-frontend
     container_name: deer-flow-frontend
     env_file:
       - .env

deployment/docker/milvus/docker-compose.yml

@@ -1,5 +1,3 @@
-version: '3.5'
-
 services:
   etcd:
     container_name: milvus-etcd

deployment/helm/datamate/charts/backend-python/.helmignore

@@ -0,0 +1,23 @@
+# Patterns to ignore when building packages.
+# This supports shell glob matching, relative path matching, and
+# negation (prefixed with !). Only one pattern per line.
+.DS_Store
+# Common VCS dirs
+.git/
+.gitignore
+.bzr/
+.bzrignore
+.hg/
+.hgignore
+.svn/
+# Common backup files
+*.swp
+*.bak
+*.tmp
+*.orig
+*~
+# Various IDEs
+.project
+.idea/
+*.tmproj
+.vscode/

deployment/helm/datamate/charts/backend-python/Chart.yaml

@@ -0,0 +1,29 @@
+apiVersion: v2
+name: backend-python
+description: A Helm chart for Kubernetes
+
+# A chart can be either an 'application' or a 'library' chart.
+#
+# Application charts are a collection of templates that can be packaged into versioned archives
+# to be deployed.
+#
+# Library charts provide useful utilities or functions for the chart developer. They're included as
+# a dependency of application charts to inject those utilities and functions into the rendering
+# pipeline. Library charts do not define any templates and therefore cannot be deployed.
+type: application
+
+# This is the chart version. This version number should be incremented each time you make changes
+# to the chart and its templates, including the app version.
+# Versions are expected to follow Semantic Versioning (https://semver.org/)
+version: 0.0.1
+
+# This is the version number of the application being deployed. This version number should be
+# incremented each time you make changes to the application. Versions are not expected to
+# follow Semantic Versioning. They should reflect the version the application is using.
+# It is recommended to use it with quotes.
+appVersion: "0.0.1"
+
+dependencies:
+  - name: database
+    repository: file://../database
+    version: 0.0.1

deployment/helm/datamate/charts/backend-python/templates/_helpers.tpl

@@ -0,0 +1,75 @@
+{{/*
+Expand the name of the chart.
+*/}}
+{{- define "backend-python.name" -}}
+{{- default .Chart.Name .Values.nameOverride | trunc 63 | trimSuffix "-" -}}
+{{- end }}
+
+{{/*
+Create a default fully qualified app name.
+We truncate at 63 chars because some Kubernetes name fields are limited to this (by the DNS naming spec).
+If release name contains chart name it will be used as a full name.
+*/}}
+{{- define "backend-python.fullname" -}}
+{{- if .Values.fullnameOverride }}
+{{- .Values.fullnameOverride | trunc 63 | trimSuffix "-" -}}
+{{- else }}
+{{- $name := default .Chart.Name .Values.nameOverride }}
+{{- if contains $name .Release.Name }}
+{{- .Release.Name | trunc 63 | trimSuffix "-" -}}
+{{- else }}
+{{- printf "%s-%s" .Release.Name $name | trunc 63 | trimSuffix "-" -}}
+{{- end }}
+{{- end }}
+{{- end }}
+
+{{/*
+Create chart name and version as used by the chart label.
+*/}}
+{{- define "backend-python.chart" -}}
+{{- printf "%s-%s" .Chart.Name .Chart.Version | replace "+" "_" | trunc 63 | trimSuffix "-" -}}
+{{- end }}
+
+{{/*
+Common labels
+*/}}
+{{- define "backend-python.labels" -}}
+helm.sh/chart: {{ include "backend-python.chart" . }}
+{{ include "backend-python.selectorLabels" . }}
+{{- if .Chart.AppVersion }}
+app.kubernetes.io/version: {{ .Chart.AppVersion | quote }}
+{{- end }}
+app.kubernetes.io/managed-by: {{ .Release.Service }}
+{{- end }}
+
+{{/*
+Selector labels
+*/}}
+{{- define "backend-python.selectorLabels" -}}
+app.kubernetes.io/name: {{ include "backend-python.name" . }}
+app.kubernetes.io/instance: {{ .Release.Name }}
+{{- end }}
+
+{{/*
+Create the name of the service account to use
+*/}}
+{{- define "backend-python.serviceAccountName" -}}
+{{- if .Values.serviceAccount.create }}
+{{- default (include "backend-python.fullname" .) .Values.serviceAccount.name -}}
+{{- else }}
+{{- default "default" .Values.serviceAccount.name -}}
+{{- end }}
+{{- end }}
+
+{{/*
+Name of image
+*/}}
+{{- define "backend-python.image" -}}
+{{- $name := default .Values.image.repository .Values.global.image.backendPython.name }}
+{{- $tag := default .Values.image.tag .Values.global.image.backendPython.tag }}
+{{- if .Values.global.image.repository }}
+{{- .Values.global.image.repository | trimSuffix "/" }}/{{ $name }}:{{ $tag }}
+{{- else }}
+{{- $name }}:{{ $tag }}
+{{- end }}
+{{- end }}

deployment/helm/datamate/charts/backend-python/templates/deployment.yaml

@@ -0,0 +1,82 @@
+apiVersion: apps/v1
+kind: Deployment
+metadata:
+  name: {{ include "backend-python.fullname" . }}
+  labels:
+    {{- include "backend-python.labels" . | nindent 4 }}
+spec:
+  {{- if not .Values.autoscaling.enabled }}
+  replicas: {{ .Values.replicaCount }}
+  {{- end }}
+  selector:
+    matchLabels:
+      {{- include "backend-python.selectorLabels" . | nindent 6 }}
+  template:
+    metadata:
+      {{- with .Values.podAnnotations }}
+      annotations:
+        {{- toYaml . | nindent 8 }}
+      {{- end }}
+      labels:
+        {{- include "backend-python.labels" . | nindent 8 }}
+        {{- with .Values.podLabels }}
+        {{- toYaml . | nindent 8 }}
+        {{- end }}
+    spec:
+      {{- with .Values.imagePullSecrets }}
+      imagePullSecrets:
+        {{- toYaml . | nindent 8 }}
+      {{- end }}
+      serviceAccountName: {{ include "backend-python.serviceAccountName" . }}
+      {{- with .Values.podSecurityContext }}
+      securityContext:
+        {{- toYaml . | nindent 8 }}
+      {{- end }}
+      containers:
+        - name: {{ .Chart.Name }}
+          {{- with .Values.securityContext }}
+          securityContext:
+            {{- toYaml . | nindent 12 }}
+          {{- end }}
+          image: "{{ include "backend-python.image" . }}"
+          imagePullPolicy: {{ default .Values.image.pullPolicy .Values.global.image.pullPolicy }}
+          ports:
+            - name: http
+              containerPort: {{ .Values.service.port }}
+              protocol: TCP
+          {{- with .Values.livenessProbe }}
+          livenessProbe:
+            {{- toYaml . | nindent 12 }}
+          {{- end }}
+          {{- with .Values.readinessProbe }}
+          readinessProbe:
+            {{- toYaml . | nindent 12 }}
+          {{- end }}
+          {{- with .Values.resources }}
+          resources:
+            {{- toYaml . | nindent 12 }}
+          {{- end }}
+          {{- with .Values.env }}
+          env:
+            {{- toYaml . | nindent 12 }}
+          {{- end }}
+          {{- with .Values.volumeMounts }}
+          volumeMounts:
+            {{- toYaml . | nindent 12 }}
+          {{- end }}
+      {{- with .Values.volumes }}
+      volumes:
+        {{- toYaml . | nindent 8 }}
+      {{- end }}
+      {{- with .Values.nodeSelector }}
+      nodeSelector:
+        {{- toYaml . | nindent 8 }}
+      {{- end }}
+      {{- with .Values.affinity }}
+      affinity:
+        {{- toYaml . | nindent 8 }}
+      {{- end }}
+      {{- with .Values.tolerations }}
+      tolerations:
+        {{- toYaml . | nindent 8 }}
+      {{- end }}

deployment/helm/datamate/charts/backend-python/templates/service.yaml

@@ -0,0 +1,15 @@
+apiVersion: v1
+kind: Service
+metadata:
+  name: {{ include "backend-python.fullname" . }}
+  labels:
+    {{- include "backend-python.labels" . | nindent 4 }}
+spec:
+  type: {{ .Values.service.type }}
+  ports:
+    - port: {{ .Values.service.port }}
+      targetPort: {{ .Values.service.port }}
+      protocol: TCP
+      name: {{ .Chart.Name }}
+  selector:
+    {{- include "backend.selectorLabels" . | nindent 4 }}

deployment/helm/datamate/charts/backend-python/templates/serviceaccount.yaml

@@ -0,0 +1,13 @@
+{{- if .Values.serviceAccount.create -}}
+apiVersion: v1
+kind: ServiceAccount
+metadata:
+  name: {{ include "backend-python.serviceAccountName" . }}
+  labels:
+    {{- include "backend-python.labels" . | nindent 4 }}
+  {{- with .Values.serviceAccount.annotations }}
+  annotations:
+    {{- toYaml . | nindent 4 }}
+  {{- end }}
+automountServiceAccountToken: {{ .Values.serviceAccount.automount }}
+{{- end }}

deployment/helm/datamate/charts/backend-python/values.yaml

@@ -0,0 +1,108 @@
+# Default values for datamate.
+# This is a YAML-formatted file.
+# Declare variables to be passed into your templates.
+
+# This will set the replicaset count more information can be found here: https://kubernetes.io/docs/concepts/workloads/controllers/replicaset/
+replicaCount: 1
+
+# This sets the container image more information can be found here: https://kubernetes.io/docs/concepts/containers/images/
+image:
+  repository: "datamate-backend-python"
+  # This sets the pull policy for images.
+  pullPolicy: "IfNotPresent"
+  # Overrides the image tag whose default is the chart appVersion.
+  tag: "latest"
+
+# 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: "datamate-backend-python"
+fullnameOverride: "datamate-backend-python"
+
+env: []
+
+# This section builds out the service account more information can be found here: https://kubernetes.io/docs/concepts/security/service-accounts/
+serviceAccount:
+  # Specifies whether a service account should be created
+  create: true
+  # Automatically mount a ServiceAccount's API credentials?
+  automount: true
+  # Annotations to add to the service account
+  annotations: {}
+  # The name of the service account to use.
+  # If not set and create is true, a name is generated using the fullname template
+  name: ""
+
+# This is for setting Kubernetes Annotations to a Pod.
+# For more information checkout: https://kubernetes.io/docs/concepts/overview/working-with-objects/annotations/
+podAnnotations: {}
+# This is for setting Kubernetes Labels to a Pod.
+# For more information checkout: https://kubernetes.io/docs/concepts/overview/working-with-objects/labels/
+podLabels: {}
+
+podSecurityContext: {}
+  # fsGroup: 2000
+
+securityContext: {}
+  # capabilities:
+  #   drop:
+  #   - ALL
+  # readOnlyRootFilesystem: true
+  # runAsNonRoot: true
+  # runAsUser: 1000
+
+# This is for setting up a service more information can be found here: https://kubernetes.io/docs/concepts/services-networking/service/
+service:
+  # This sets the service type more information can be found here: https://kubernetes.io/docs/concepts/services-networking/service/#publishing-services-service-types
+  type: ClusterIP
+  # This sets the ports more information can be found here: https://kubernetes.io/docs/concepts/services-networking/service/#field-spec-ports
+  port: 18000
+
+resources: {}
+  # We usually recommend not to specify default resources and to leave this as a conscious
+  # choice for the user. This also increases chances charts run on environments with little
+  # resources, such as Minikube. If you do want to specify resources, uncomment the following
+  # lines, adjust them as necessary, and remove the curly braces after 'resources:'.
+  # limits:
+  #   cpu: 100m
+  #   memory: 128Mi
+  # requests:
+  #   cpu: 100m
+  #   memory: 128Mi
+
+# This is to setup the liveness and readiness probes more information can be found here: https://kubernetes.io/docs/tasks/configure-pod-container/configure-liveness-readiness-startup-probes/
+# livenessProbe:
+#   httpGet:
+#     path: /
+#     port: http
+# readinessProbe:
+#   httpGet:
+#     path: /
+#     port: http
+
+# This section is for setting up autoscaling more information can be found here: https://kubernetes.io/docs/concepts/workloads/autoscaling/
+autoscaling:
+  enabled: false
+  minReplicas: 1
+  maxReplicas: 100
+  targetCPUUtilizationPercentage: 80
+  # targetMemoryUtilizationPercentage: 80
+
+# Additional volumes on the output Deployment definition.
+volumes: []
+# - name: foo
+#   secret:
+#     secretName: mysecret
+#     optional: false
+
+# Additional volumeMounts on the output Deployment definition.
+volumeMounts: []
+# - name: foo
+#   mountPath: "/etc/foo"
+#   readOnly: true
+
+nodeSelector: {}
+
+tolerations: []
+
+affinity: {}

deployment/helm/datamate/charts/frontend/templates/configmap.yaml

@@ -16,6 +16,20 @@ data:
 
         add_header Set-Cookie "NEXT_LOCALE=zh";
 
+        location /api/synthesis/ {
+            proxy_pass http://datamate-backend-python:18000/api/synthesis/;
+            proxy_set_header Host $host;
+            proxy_set_header X-Real-IP $remote_addr;
+            proxy_set_header X-Forwarded-For $proxy_add_x_forwarded_for;
+        }
+
+        location /api/annotation/ {
+            proxy_pass http://datamate-backend-python:18000/api/annotation/;
+            proxy_set_header Host $host;
+            proxy_set_header X-Real-IP $remote_addr;
+            proxy_set_header X-Forwarded-For $proxy_add_x_forwarded_for;
+        }
+
         location /api/ {
             proxy_pass http://datamate-backend:8080/api/;
             proxy_set_header Host $host;
@@ -70,6 +84,20 @@ data:
 
         client_max_body_size 1024M;
 
+        location /api/synthesis/ {
+            proxy_pass http://datamate-backend-python:18000/api/synthesis/;
+            proxy_set_header Host $host;
+            proxy_set_header X-Real-IP $remote_addr;
+            proxy_set_header X-Forwarded-For $proxy_add_x_forwarded_for;
+        }
+
+        location /api/annotation/ {
+            proxy_pass http://datamate-backend-python:18000/api/annotation/;
+            proxy_set_header Host $host;
+            proxy_set_header X-Real-IP $remote_addr;
+            proxy_set_header X-Forwarded-For $proxy_add_x_forwarded_for;
+        }
+
         location /api/ {
             proxy_pass http://datamate-backend:8080/api/;
             proxy_set_header Host $host;

deployment/helm/datamate/charts/ray-cluster/templates/_helpers.tpl

@@ -52,4 +52,29 @@ Create the name of the service account to use
 {{- else -}}
     {{ default "default" .Values.serviceAccount.name }}
 {{- end -}}
-{{- end -}}
+{{- end -}}
+
+{{/*
+Name of image
+*/}}
+{{- define "ray-cluster.image" -}}
+{{- $name := default .Values.image.repository .Values.global.image.runtime.name }}
+{{- $tag := default .Values.image.tag .Values.global.image.runtime.tag }}
+{{- if .Values.global.image.repository }}
+{{- .Values.global.image.repository | trimSuffix "/" }}/{{ $name }}:{{ $tag }}
+{{- else }}
+{{- $name }}:{{ $tag }}
+{{- end }}
+{{- end }}
+
+{{/*
+Name of sidecar image
+*/}}
+{{- define "ray-cluster-sidecar.image" -}}
+{{- $name := default (printf "%s:%s" .Values.image.repository .Values.image.tag) .Values.head.sidecarContainers.image }}
+{{- if .Values.global.image.repository }}
+{{- .Values.global.image.repository | trimSuffix "/" }}/{{ $name }}
+{{- else }}
+{{- $name }}
+{{- end }}
+{{- end }}

deployment/helm/datamate/charts/ray-cluster/templates/raycluster-cluster.yaml

@@ -58,13 +58,8 @@ spec:
         {{- end }}
         containers:
         - name: ray-head
-          {{- if .Values.head.image }}
+          image: {{ include "ray-cluster.image" . }}
-          image: {{ .Values.head.image.repository }}:{{ .Values.head.image.tag }}
+          imagePullPolicy: {{ default .Values.image.pullPolicy .Values.global.image.pullPolicy }}
-          imagePullPolicy: {{ .Values.head.image.pullPolicy }}
-          {{- else }}
-          image: {{ .Values.image.repository }}:{{ .Values.image.tag }}
-          imagePullPolicy: {{ .Values.image.pullPolicy }}
-          {{- end }}
           {{- with .Values.head.command }}
           command:
           {{- toYaml . | nindent 10 }}
@@ -101,8 +96,16 @@ spec:
           securityContext:
             {{- toYaml . | nindent 12 }}
           {{- end }}
+        {{- $defult := printf "%s:%s" .Values.image.repository .Values.image.tag }}
         {{- with .Values.head.sidecarContainers }}
-        {{- toYaml . | nindent 8 }}
+        {{- range $index, $container := . }}
+        {{- $image := default $defult $container.image -}}
+        {{- with $.Values.global.image.repository -}}
+        {{- $image = printf "%s/%s" (trimSuffix "/" .) (default $defult $container.image) -}}
+        {{- end -}}
+        {{- $mergedObj := mergeOverwrite $container (dict "image" $image) }}
+        - {{- toYaml $mergedObj | nindent 10 }}
+        {{- end }}
         {{- end }}
         {{- with .Values.imagePullSecrets }}
         imagePullSecrets:
@@ -185,13 +188,8 @@ spec:
         {{- end }}
         containers:
         - name: ray-worker
-          {{- if .Values.worker.image }}
+          image: {{ include "ray-cluster.image" . }}
-          image: {{ .Values.worker.image.repository }}:{{ .Values.worker.image.tag }}
+          imagePullPolicy: {{ default .Values.image.pullPolicy .Values.global.image.pullPolicy }}
-          imagePullPolicy: {{ .Values.worker.image.pullPolicy }}
-          {{- else }}
-          image: {{ .Values.image.repository }}:{{ .Values.image.tag }}
-          imagePullPolicy: {{ .Values.image.pullPolicy }}
-          {{- end }}
           {{- with .Values.worker.command }}
           command:
           {{- toYaml . | nindent 10 }}

deployment/helm/datamate/charts/ray-cluster/values.yaml

@@ -77,8 +77,6 @@ head:
       value: "password"
     - name: MYSQL_DATABASE
       value: "datamate"
-    - name: PDF_FORMATTER_BASE_URL
-      value: "http://datamate-mineru:9001"
   # - name: EXAMPLE_ENV
   #   value: "1"
   envFrom: []
@@ -173,8 +171,6 @@ worker:
       value: "password"
     - name: MYSQL_DATABASE
       value: "datamate"
-    - name: PDF_FORMATTER_BASE_URL
-      value: "http://datamate-mineru:9001"
   # - name: EXAMPLE_ENV
   #   value: "1"
   envFrom: []

deployment/helm/datamate/values.yaml

@@ -6,14 +6,20 @@ global:
   deerFlow:
     enable: false
   image:
-    repository: ""
+    repository: "ghcr.io/modelengine-group/"
     pullPolicy: "IfNotPresent"
     backend:
       name: "datamate-backend"
       tag: "latest"
+    backendPython:
+      name: "datamate-backend-python"
+      tag: "latest"
     frontend:
       name: "datamate-frontend"
       tag: "latest"
+    runtime:
+      name: "datamate-runtime"
+      tag: "latest"
     database:
       name: "mysql"
       tag: "8"
@@ -136,8 +142,6 @@ ray-cluster:
             value: "password"
           - name: MYSQL_DATABASE
             value: "datamate"
-          - name: PDF_FORMATTER_BASE_URL
-            value: "http://datamate-mineru:9001"
         ports:
           - containerPort: 8081
         volumeMounts:

deployment/helm/deer-flow/values.yaml

@@ -4,7 +4,7 @@
 
 global:
   image:
-    repository: ""
+    repository: "ghcr.io/modelengine-group/"
     pullPolicy: "IfNotPresent"
     backend:
       name: "deer-flow-backend"

deployment/kubernetes/backend/deploy.yaml

@@ -1,86 +0,0 @@
-
-
----
-apiVersion: v1
-kind: ServiceAccount
-metadata:
-  labels:
-    app: datamate
-    tier: backend
-  name: datamate-backend
-
----
-
-
----
-apiVersion: apps/v1
-kind: Deployment
-metadata:
-  name: datamate-backend
-  labels:
-    app: datamate
-    tier: backend
-spec:
-  replicas: 1
-  selector:
-    matchLabels:
-      app: datamate
-      tier: backend
-  template:
-    metadata:
-      labels:
-        app: datamate
-        tier: backend
-    spec:
-      serviceAccountName: datamate-backend
-      containers:
-        - name: backend
-          image: datamate-backend
-          imagePullPolicy: IfNotPresent
-          env:
-            - name: namespace
-              valueFrom:
-                fieldRef:
-                  fieldPath: metadata.namespace
-            - name: SPRING_CONFIG_LOCATION
-              value: file:/opt/backend/application.yml
-          ports:
-            - containerPort: 8080
-          volumeMounts:
-            - name: dataset-volume
-              mountPath: /dataset
-            - name: flow-volume
-              mountPath: /flow
-            - name: log-volume
-              mountPath: /var/log/datamate
-      volumes:
-        - name: dataset-volume
-          hostPath:
-            path: /opt/datamate/data/dataset
-            type: DirectoryOrCreate
-        - name: flow-volume
-          hostPath:
-            path: /opt/datamate/data/flow
-            type: DirectoryOrCreate
-        - name: log-volume
-          hostPath:
-            path: /opt/datamate/data/log
-            type: DirectoryOrCreate
-
----
-apiVersion: v1
-kind: Service
-metadata:
-  name: datamate-backend
-  labels:
-    app: datamate
-    tier: backend
-spec:
-  type: ClusterIP
-  ports:
-    - port: 8080
-      targetPort: 8080
-      protocol: TCP
-  selector:
-    app: datamate
-    tier: backend

deployment/kubernetes/frontend/deploy.yaml

@@ -1,52 +0,0 @@
-apiVersion: apps/v1
-kind: Deployment
-metadata:
-  name: datamate-frontend
-  labels:
-    app: datamate
-    tier: frontend
-spec:
-  replicas: 1
-  selector:
-    matchLabels:
-      app: datamate
-      tier: frontend
-  template:
-    metadata:
-      labels:
-        app: datamate
-        tier: frontend
-    spec:
-      containers:
-        - name: frontend
-          image: datamate-frontend
-          imagePullPolicy: IfNotPresent
-          ports:
-            - containerPort: 80
-          volumeMounts:
-            - name: log-volume
-              mountPath: /var/log/datamate/frontend
-              subPath: frontend
-      volumes:
-        - name: log-volume
-          hostPath:
-            path: /opt/datamate/data/log
-            type: DirectoryOrCreate
----
-apiVersion: v1
-kind: Service
-metadata:
-  name: datamate-frontend
-  labels:
-    app: datamate
-    tier: frontend
-spec:
-  type: NodePort
-  ports:
-    - port: 80
-      targetPort: 80
-      nodePort: 30000
-      protocol: TCP
-  selector:
-    app: datamate
-    tier: frontend

deployment/kubernetes/mysql/configmap.yaml

@@ -1,22 +0,0 @@
-apiVersion: v1
-kind: ConfigMap
-metadata:
-  name: datamate-mysql-utf8-config
-data:
-  utf8.cnf: |
-    [mysqld]
-    # 设置服务器默认字符集为 utf8mb4 (推荐，支持完整的 UTF-8，包括 emoji)
-    character-set-server = utf8mb4
-    # 设置默认排序规则
-    collation-server = utf8mb4_unicode_ci
-    # 或者使用 utf8_general_ci (性能稍好，但排序规则稍宽松)
-    default-time-zone = 'Asia/Shanghai'
-    log_error=/var/log/datamate/database/error.log
-
-    [client]
-    # 设置客户端连接默认字符集
-    default-character-set = utf8mb4
-
-    [mysql]
-    # 设置 mysql 命令行客户端默认字符集
-    default-character-set = utf8mb4

deployment/kubernetes/mysql/deploy.yaml

@@ -1,88 +0,0 @@
-apiVersion: apps/v1
-kind: Deployment
-metadata:
-  name: datamate-database
-  labels:
-    app: datamate
-    tier: database
-spec:
-  replicas: 1
-  selector:
-    matchLabels:
-      app: datamate
-      tier: database
-  strategy:
-    type: Recreate
-  template:
-    metadata:
-      labels:
-        app: datamate
-        tier: database
-    spec:
-      initContainers:
-        - name: init-log
-          image: mysql:8
-          imagePullPolicy: IfNotPresent
-          command:
-            - sh
-            - -c
-          args:
-            - |
-              chown mysql:mysql /var/log/datamate/database
-              chmod 755 /var/log/datamate/database
-          volumeMounts:
-            - name: log-volume
-              mountPath: /var/log/datamate/database
-              subPath: database
-      containers:
-        - name: mysql
-          image: mysql:8
-          imagePullPolicy: IfNotPresent
-          env:
-            - name: MYSQL_ROOT_PASSWORD
-              value: "password"
-          ports:
-            - containerPort: 3306
-          volumeMounts:
-            - name: data-volume
-              mountPath: /var/lib/mysql
-            - name: log-volume
-              mountPath: /var/log/datamate/database
-              subPath: database
-            - name: init-sql
-              mountPath: /docker-entrypoint-initdb.d
-            - name: mysql-utf8-config
-              mountPath: /etc/mysql/conf.d
-      volumes:
-        - name: data-volume
-          hostPath:
-            path: /opt/datamate/data/mysql
-            type: DirectoryOrCreate
-        - name: log-volume
-          hostPath:
-            path: /opt/datamate/data/log
-            type: DirectoryOrCreate
-        - name: init-sql
-          configMap:
-            name: datamate-init-sql
-        - name: mysql-utf8-config
-          configMap:
-            name: datamate-mysql-utf8-config
-
----
-apiVersion: v1
-kind: Service
-metadata:
-  name: datamate-database
-  labels:
-    app: datamate
-    tier: database
-spec:
-  type: ClusterIP
-  ports:
-    - port: 3306
-      targetPort: 3306
-      protocol: TCP
-  selector:
-    app: datamate
-    tier: database

runtime/deer-flow/.env.example

@@ -53,18 +53,17 @@ TAVILY_API_KEY=tvly-xxx
 # MOI_RETRIEVAL_SIZE=10
 # MOI_LIST_LIMIT=10
 
-
 # RAG_PROVIDER: milvus  (using free milvus instance on zilliz cloud: https://docs.zilliz.com/docs/quick-start )
 # RAG_PROVIDER=milvus
-# MILVUS_URI=<endpoint_of_self_hosted_milvus_or_zilliz_cloud>
+MILVUS_URI=http://milvus-standalone:19530
-# MILVUS_USER=<username_of_self_hosted_milvus_or_zilliz_cloud>
+MILVUS_USER=root
-# MILVUS_PASSWORD=<password_of_self_hosted_milvus_or_zilliz_cloud>
+MILVUS_PASSWORD=Milvus
+MILVUS_AUTO_LOAD_EXAMPLES=false
 # MILVUS_COLLECTION=documents
 # MILVUS_EMBEDDING_PROVIDER=openai # support openai,dashscope
 # MILVUS_EMBEDDING_BASE_URL=
 # MILVUS_EMBEDDING_MODEL=
 # MILVUS_EMBEDDING_API_KEY=
-# MILVUS_AUTO_LOAD_EXAMPLES=true
 
 # RAG_PROVIDER: milvus  (using milvus lite on Mac or Linux)
 # RAG_PROVIDER=milvus

runtime/ops/formatter/mineru_formatter/process.py

@@ -6,7 +6,6 @@ Description: MinerU PDF文本抽取
 Create: 2025/10/29 17:24
 """
 import json
-import os
 import time
 from loguru import logger
 from typing import Dict, Any
@@ -20,7 +19,7 @@ class MineruFormatter(Mapper):
 
     def __init__(self, *args, **kwargs):
         super(MineruFormatter, self).__init__(*args, **kwargs)
-        self.base_url = os.getenv("EXTERNAL_PDF_BASE_URL", "http://datamate-mineru:9001")
+        self.base_url = "http://datamate-mineru:9001"
         self.pdf_extract_url = f"{self.base_url}/api/pdf-extract"
 
     def execute(self, sample: Dict[str, Any]) -> Dict[str, Any]: