Week8 backend

build.gradle

@@ -34,6 +34,8 @@ subprojects {
         implementation 'org.springframework.boot:spring-boot-starter-actuator'
         implementation 'io.micrometer:micrometer-registry-prometheus:1.15.1'
 
+        implementation("net.logstash.logback:logstash-logback-encoder:8.1")
+
         developmentOnly 'org.springframework.boot:spring-boot-devtools'
         annotationProcessor 'org.springframework.boot:spring-boot-configuration-processor'
 

helm/aihr/charts/service-application/templates/hpa.yaml

@@ -0,0 +1,22 @@
+{{- if .Values.autoscaling.enabled }}
+apiVersion: autoscaling/v2
+kind: HorizontalPodAutoscaler
+metadata:
+  name: {{ include "service-application.fullname" . }}
+  labels:
+    app: {{ include "service-application.fullname" . }}
+spec:
+  scaleTargetRef:
+    apiVersion: apps/v1
+    kind: Deployment
+    name: {{ include "service-application.fullname" . }}
+  minReplicas: {{ .Values.autoscaling.minReplicas }}
+  maxReplicas: {{ .Values.autoscaling.maxReplicas }}
+  metrics:
+    - type: Resource
+      resource:
+        name: cpu
+        target:
+          type: Utilization
+          averageUtilization: {{ .Values.autoscaling.targetCPUUtilizationPercentage }}
+{{- end }}

helm/aihr/charts/service-application/values.yaml

@@ -1,5 +1,11 @@
 replicaCount: 1
 
+autoscaling:
+  enabled: true
+  minReplicas: 1
+  maxReplicas: 3
+  targetCPUUtilizationPercentage: 70
+
 image:
   # 默认拼接：ghcr.io/<user>/<repo>-service-application:<tag>
   repository: ""

helm/aihr/charts/service-auth/templates/hpa.yaml

@@ -0,0 +1,22 @@
+{{- if .Values.autoscaling.enabled }}
+apiVersion: autoscaling/v2
+kind: HorizontalPodAutoscaler
+metadata:
+  name: {{ include "service-auth.fullname" . }}
+  labels:
+    app: {{ include "service-auth.fullname" . }}
+spec:
+  scaleTargetRef:
+    apiVersion: apps/v1
+    kind: Deployment
+    name: {{ include "service-auth.fullname" . }}
+  minReplicas: {{ .Values.autoscaling.minReplicas }}
+  maxReplicas: {{ .Values.autoscaling.maxReplicas }}
+  metrics:
+    - type: Resource
+      resource:
+        name: cpu
+        target:
+          type: Utilization
+          averageUtilization: {{ .Values.autoscaling.targetCPUUtilizationPercentage }}
+{{- end }}

helm/aihr/charts/service-auth/values.yaml

@@ -1,5 +1,11 @@
 replicaCount: 1
 
+autoscaling:
+  enabled: true
+  minReplicas: 1
+  maxReplicas: 3
+  targetCPUUtilizationPercentage: 70
+
 image:
   # 默认拼接：ghcr.io/<user>/<repo>-service-auth:<tag>
   repository: ""

helm/aihr/charts/service-genai/templates/hpa.yaml

@@ -0,0 +1,22 @@
+{{- if .Values.autoscaling.enabled }}
+apiVersion: autoscaling/v2
+kind: HorizontalPodAutoscaler
+metadata:
+  name: {{ include "service-genai.fullname" . }}
+  labels:
+    app: {{ include "service-genai.fullname" . }}
+spec:
+  scaleTargetRef:
+    apiVersion: apps/v1
+    kind: Deployment
+    name: {{ include "service-genai.fullname" . }}
+  minReplicas: {{ .Values.autoscaling.minReplicas }}
+  maxReplicas: {{ .Values.autoscaling.maxReplicas }}
+  metrics:
+    - type: Resource
+      resource:
+        name: cpu
+        target:
+          type: Utilization
+          averageUtilization: {{ .Values.autoscaling.targetCPUUtilizationPercentage }}
+{{- end }}

helm/aihr/charts/service-genai/values.yaml

@@ -1,5 +1,11 @@
 replicaCount: 1
 
+autoscaling:
+  enabled: true
+  minReplicas: 1
+  maxReplicas: 3
+  targetCPUUtilizationPercentage: 70
+
 image:
   # 默认拼接：ghcr.io/<user>/<repo>-service-genai:<tag>
   repository: ""

helm/aihr/charts/service-job/templates/hpa.yaml

@@ -0,0 +1,22 @@
+{{- if .Values.autoscaling.enabled }}
+apiVersion: autoscaling/v2
+kind: HorizontalPodAutoscaler
+metadata:
+  name: {{ include "service-job.fullname" . }}
+  labels:
+    app: {{ include "service-job.fullname" . }}
+spec:
+  scaleTargetRef:
+    apiVersion: apps/v1
+    kind: Deployment
+    name: {{ include "service-job.fullname" . }}
+  minReplicas: {{ .Values.autoscaling.minReplicas }}
+  maxReplicas: {{ .Values.autoscaling.maxReplicas }}
+  metrics:
+    - type: Resource
+      resource:
+        name: cpu
+        target:
+          type: Utilization
+          averageUtilization: {{ .Values.autoscaling.targetCPUUtilizationPercentage }}
+{{- end }}

helm/aihr/charts/service-job/values.yaml

@@ -1,5 +1,11 @@
 replicaCount: 1
 
+autoscaling:
+  enabled: true
+  minReplicas: 1
+  maxReplicas: 3
+  targetCPUUtilizationPercentage: 70
+
 image:
   # 默认拼接：ghcr.io/<user>/<repo>-service-job:<tag>
   repository: ""

helm/aihr/values-dev-promtail.yaml

@@ -2,6 +2,7 @@ promtail:
   # 日志采集与推送配置
   config:
     logLevel: debug
+    logFormat: json
     clients:
       - url: http://ai-hr-dev-loki-gateway/loki/api/v1/push
         tenant_id: "promtail"

helm/aihr/values-prod-promtail.yaml

@@ -2,6 +2,7 @@ promtail:
   # 日志采集与推送配置
   config:
     logLevel: debug
+    logFormat: json
     clients:
       - url: http://ai-hr-prod-loki-gateway/loki/api/v1/push
         tenant_id: "promtail"

k8s-install.sh

@@ -5,8 +5,8 @@ OLLAMA_MODEL=""
 OLLAMA_API_KEY=""
 
 # paste key as one line
-private_key=""
-public_key=""
+echo "JWT_PRIV_KEY" > priv.pem
+echo "JWT_PUB_KEY"  > pub.pem
 
 DISCORD_WEBHOOK=""
 
@@ -35,8 +35,8 @@ helm upgrade --install ai-hr-dev ./helm/aihr \
   --set global.ghcrUser=aet-devops25 \
   --set global.ghcrRepo=team-1 \
   --set global.imageTag="$(git rev-parse --short HEAD)" \
-  --set-file global.jwt.privateKey="${private_key}" \
-  --set-file global.jwt.publicKey="${public_key}" \
+  --set-file global.jwt.privateKey=priv.pem \
+  --set-file global.jwt.publicKey=pub.pem \
   --set global.ollama.ollamaBaseUrl="${OLLAMA_BASE_URL}" \
   --set global.ollama.ollamaModel="${OLLAMA_MODEL}" \
   --set global.ollama.ollamaApiKey="${OLLAMA_API_KEY}" \
@@ -59,8 +59,8 @@ helm upgrade --install ai-hr-prod ./helm/aihr \
   --set global.ghcrUser=aet-devops25 \
   --set global.ghcrRepo=team-1 \
   --set global.imageTag="$(git rev-parse --short HEAD)" \
-  --set-file global.jwt.privateKey="${private_key}" \
-  --set-file global.jwt.publicKey="${public_key}" \
+  --set-file global.jwt.privateKey=priv.pem \
+  --set-file global.jwt.publicKey=pub.pem \
   --set global.ollama.ollamaBaseUrl="${OLLAMA_BASE_URL}" \
   --set global.ollama.ollamaModel="${OLLAMA_MODEL}" \
   --set global.ollama.ollamaApiKey="${OLLAMA_API_KEY}" \

proto/ai.proto

@@ -31,6 +31,12 @@ message ChatReplyResponse {
   string ai_message = 1;
 }
 
+// --------------------------- QA ---------------------------
+message NormalQARequest {
+  string question = 1;
+  bool is_open_rag = 2;
+}
+
 // --------------------------- ScoreResume ---------------------------
 message ScoreResumeRequest {
   string job_title = 1;
@@ -71,6 +77,9 @@ service AIService {
   // Streamed chat with AI assistant. Server streams incremental ai_message tokens.
   rpc ChatReply(ChatReplyRequest) returns (stream ChatReplyResponse);
 
+  // Streamed chat with AI, normal QA
+  rpc NormalQA(NormalQARequest) returns (stream ChatReplyResponse);
+
   // Scores a resume against job requirements.
   rpc ScoreResume(ScoreResumeRequest) returns (ScoreResumeResponse);
 

proto/cp2service.sh

@@ -1,2 +1,2 @@
-cp proto/ai.proto service-genai/app/proto/ai.proto
+cp proto/ai.proto service-genai/app/proto/ai.proto
 cp proto/ai.proto service-application/src/main/proto/ai.proto