k8s dev

.env

@@ -1,11 +1,15 @@
 # LLM API Configuration
-LLM_API_URL=http://tianchat.zenithsafe.com:5001/v1
-LLM_API_KEY=app-k9WhnUvAPCVcSoPDEYVUxXgC
+LLM_API_URL=http://101.133.149.116:8777/v1
+LLM_API_KEY=app-7mh1IAGueaBodwdMflz8Omqv
+
+LLMOurApiUrl=https://ark.cn-beijing.volces.com/api/v3/bots/chat/completions
+LLMOurApiKey=e999a241-6bf3-4ee0-99a8-e4de9b617f28
+
 MiniMaxApiKey=eyJhbGciOiJSUzI1NiIsInR5cCI6IkpXVCJ9.eyJHcm91cE5hbWUiOiLkuIrmtbfpopzpgJTnp5HmioDmnInpmZDlhazlj7giLCJVc2VyTmFtZSI6IuadqOmqpSIsIkFjY291bnQiOiIiLCJTdWJqZWN0SUQiOiIxNzI4NzEyMzI0OTc5NjI2ODM5IiwiUGhvbmUiOiIxMzM4MTU1OTYxOCIsIkdyb3VwSUQiOiIxNzI4NzEyMzI0OTcxMjM4MjMxIiwiUGFnZU5hbWUiOiIiLCJNYWlsIjoiIiwiQ3JlYXRlVGltZSI6IjIwMjUtMDYtMTYgMTY6Mjk6NTkiLCJUb2tlblR5cGUiOjEsImlzcyI6Im1pbmltYXgifQ.D_JF0-nO89NdMZCYq4ocEyqxtZ9SeEdtMvbeSkZTWspt0XfX2QpPAVh-DI3MCPZTeSmjNWLf4fA_Th2zpVrj4UxWMbGKBeLZWLulNpwAHGMUTdqenuih3daCDPCzs0duhlFyQnZgGcEOGQ476HL72N2klujP8BUy_vfAh_Zv0po-aujQa5RxardDSOsbs49NTPEw0SQEXwaJ5bVmiZ5s-ysJ9pZWSEiyJ6SX9z3JeZHKj9DxHdOw5roZR8izo54e4IoqyLlzEfhOMW7P15-ffDH3M6HGiEmeBaGRYGAIciELjZS19ONNMKsTj-wXNGWtKG-sjAB1uuqkkT5Ul9Dunw
 MiniMaxApiURL=https://api.minimaxi.com/v1/t2a_v2
-APP_ID=1364994890450210816
-APP_KEY=b4839cb2-cb81-4472-a2c1-2abf31e4bb27
+APP_ID=1364966010532270080
+APP_KEY=a72c98fa-cbe3-449e-b004-36523437bc5d
 SIG_EXP=3600
-FILE_URL=http://172.17.0.1:6200/
+FILE_URL=http://14.103.114.237/gongzheng-backend/audio/
 # Server Configuration
-PORT=8080
+PORT=80

.gitea/charts/Chart.yaml

@@ -0,0 +1,24 @@
+apiVersion: v2
+name: homeland
+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: 0.1.0
+
+# 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: "1.16.0"

.gitea/charts/templates/NOTES.txt

@@ -0,0 +1,22 @@
+1. Get the application URL by running these commands:
+{{- if .Values.ingress.enabled }}
+{{- range $host := .Values.ingress.hosts }}
+  {{- range .paths }}
+  http{{ if $.Values.ingress.tls }}s{{ end }}://{{ $host.host }}{{ .path }}
+  {{- end }}
+{{- end }}
+{{- else if contains "NodePort" .Values.service.type }}
+  export NODE_PORT=$(kubectl get --namespace {{ .Release.Namespace }} -o jsonpath="{.spec.ports[0].nodePort}" services {{ include "homeland.fullname" . }})
+  export NODE_IP=$(kubectl get nodes --namespace {{ .Release.Namespace }} -o jsonpath="{.items[0].status.addresses[0].address}")
+  echo http://$NODE_IP:$NODE_PORT
+{{- else if contains "LoadBalancer" .Values.service.type }}
+     NOTE: It may take a few minutes for the LoadBalancer IP to be available.
+           You can watch the status of by running 'kubectl get --namespace {{ .Release.Namespace }} svc -w {{ include "homeland.fullname" . }}'
+  export SERVICE_IP=$(kubectl get svc --namespace {{ .Release.Namespace }} {{ include "homeland.fullname" . }} --template "{{"{{ range (index .status.loadBalancer.ingress 0) }}{{.}}{{ end }}"}}")
+  echo http://$SERVICE_IP:{{ .Values.service.port }}
+{{- else if contains "ClusterIP" .Values.service.type }}
+  export POD_NAME=$(kubectl get pods --namespace {{ .Release.Namespace }} -l "app.kubernetes.io/name={{ include "homeland.name" . }},app.kubernetes.io/instance={{ .Release.Name }}" -o jsonpath="{.items[0].metadata.name}")
+  export CONTAINER_PORT=$(kubectl get pod --namespace {{ .Release.Namespace }} $POD_NAME -o jsonpath="{.spec.containers[0].ports[0].containerPort}")
+  echo "Visit http://127.0.0.1:8080 to use your application"
+  kubectl --namespace {{ .Release.Namespace }} port-forward $POD_NAME 8080:$CONTAINER_PORT
+{{- end }}

.gitea/charts/templates/_helpers.tpl

@@ -0,0 +1,62 @@
+{{/*
+Expand the name of the chart.
+*/}}
+{{- define "homeland.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 "homeland.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 "homeland.chart" -}}
+{{- printf "%s-%s" .Chart.Name .Chart.Version | replace "+" "_" | trunc 63 | trimSuffix "-" }}
+{{- end }}
+
+{{/*
+Common labels
+*/}}
+{{- define "homeland.labels" -}}
+helm.sh/chart: {{ include "homeland.chart" . }}
+{{ include "homeland.selectorLabels" . }}
+{{- if .Chart.AppVersion }}
+app.kubernetes.io/version: {{ .Chart.AppVersion | quote }}
+{{- end }}
+app.kubernetes.io/managed-by: {{ .Release.Service }}
+{{- end }}
+
+{{/*
+Selector labels
+*/}}
+{{- define "homeland.selectorLabels" -}}
+app.kubernetes.io/name: {{ include "homeland.name" . }}
+app.kubernetes.io/instance: {{ .Release.Name }}
+{{- end }}
+
+{{/*
+Create the name of the service account to use
+*/}}
+{{- define "homeland.serviceAccountName" -}}
+{{- if .Values.serviceAccount.create }}
+{{- default (include "homeland.fullname" .) .Values.serviceAccount.name }}
+{{- else }}
+{{- default "default" .Values.serviceAccount.name }}
+{{- end }}
+{{- end }}

.gitea/charts/templates/deployment.yaml

@@ -0,0 +1,61 @@
+apiVersion: apps/v1
+kind: Deployment
+metadata:
+  name: {{ include "homeland.fullname" . }}
+  labels:
+    {{- include "homeland.labels" . | nindent 4 }}
+spec:
+  {{- if not .Values.autoscaling.enabled }}
+  replicas: {{ .Values.replicaCount }}
+  {{- end }}
+  selector:
+    matchLabels:
+      {{- include "homeland.selectorLabels" . | nindent 6 }}
+  template:
+    metadata:
+      {{- with .Values.podAnnotations }}
+      annotations:
+        {{- toYaml . | nindent 8 }}
+      {{- end }}
+      labels:
+        {{- include "homeland.selectorLabels" . | nindent 8 }}
+    spec:
+      {{- with .Values.imagePullSecrets }}
+      imagePullSecrets:
+        {{- toYaml . | nindent 8 }}
+      {{- end }}
+      serviceAccountName: {{ include "homeland.serviceAccountName" . }}
+      securityContext:
+        {{- toYaml .Values.podSecurityContext | nindent 8 }}
+      containers:
+        - name: {{ .Chart.Name }}
+          securityContext:
+            {{- toYaml .Values.securityContext | nindent 12 }}
+          image: "{{ .Values.image.repository }}:{{ .Values.image.tag | default .Chart.AppVersion }}"
+          imagePullPolicy: {{ .Values.image.pullPolicy }}
+          ports:
+            - name: http
+              containerPort: {{ .Values.service.port }}
+              protocol: TCP
+          livenessProbe:
+            httpGet:
+              path: /
+              port: http
+          readinessProbe:
+            httpGet:
+              path: /
+              port: http
+          resources:
+            {{- toYaml .Values.resources | nindent 12 }}
+      {{- with .Values.nodeSelector }}
+      nodeSelector:
+        {{- toYaml . | nindent 8 }}
+      {{- end }}
+      {{- with .Values.affinity }}
+      affinity:
+        {{- toYaml . | nindent 8 }}
+      {{- end }}
+      {{- with .Values.tolerations }}
+      tolerations:
+        {{- toYaml . | nindent 8 }}
+      {{- end }}

.gitea/charts/templates/hpa.yaml

@@ -0,0 +1,32 @@
+{{- if .Values.autoscaling.enabled }}
+apiVersion: autoscaling/v2
+kind: HorizontalPodAutoscaler
+metadata:
+  name: {{ include "homeland.fullname" . }}
+  labels:
+    {{- include "homeland.labels" . | nindent 4 }}
+spec:
+  scaleTargetRef:
+    apiVersion: apps/v1
+    kind: Deployment
+    name: {{ include "homeland.fullname" . }}
+  minReplicas: {{ .Values.autoscaling.minReplicas }}
+  maxReplicas: {{ .Values.autoscaling.maxReplicas }}
+  metrics:
+    {{- if .Values.autoscaling.targetCPUUtilizationPercentage }}
+    - type: Resource
+      resource:
+        name: cpu
+        target:
+          type: Utilization
+          averageUtilization: {{ .Values.autoscaling.targetCPUUtilizationPercentage }}
+    {{- end }}
+    {{- if .Values.autoscaling.targetMemoryUtilizationPercentage }}
+    - type: Resource
+      resource:
+        name: memory
+        target:
+          type: Utilization
+          averageUtilization: {{ .Values.autoscaling.targetMemoryUtilizationPercentage }}
+    {{- end }}
+{{- end }}

.gitea/charts/templates/ingress.yaml

@@ -0,0 +1,61 @@
+{{- if .Values.ingress.enabled -}}
+{{- $fullName := include "homeland.fullname" . -}}
+{{- $svcPort := .Values.service.port -}}
+{{- if and .Values.ingress.className (not (semverCompare ">=1.18-0" .Capabilities.KubeVersion.GitVersion)) }}
+  {{- if not (hasKey .Values.ingress.annotations "kubernetes.io/ingress.class") }}
+  {{- $_ := set .Values.ingress.annotations "kubernetes.io/ingress.class" .Values.ingress.className}}
+  {{- end }}
+{{- end }}
+{{- if semverCompare ">=1.19-0" .Capabilities.KubeVersion.GitVersion -}}
+apiVersion: networking.k8s.io/v1
+{{- else if semverCompare ">=1.14-0" .Capabilities.KubeVersion.GitVersion -}}
+apiVersion: networking.k8s.io/v1beta1
+{{- else -}}
+apiVersion: extensions/v1beta1
+{{- end }}
+kind: Ingress
+metadata:
+  name: {{ $fullName }}
+  labels:
+    {{- include "homeland.labels" . | nindent 4 }}
+  {{- with .Values.ingress.annotations }}
+  annotations:
+    {{- toYaml . | nindent 4 }}
+  {{- end }}
+spec:
+  {{- if and .Values.ingress.className (semverCompare ">=1.18-0" .Capabilities.KubeVersion.GitVersion) }}
+  ingressClassName: {{ .Values.ingress.className }}
+  {{- end }}
+  {{- if .Values.ingress.tls }}
+  tls:
+    {{- range .Values.ingress.tls }}
+    - hosts:
+        {{- range .hosts }}
+        - {{ . | quote }}
+        {{- end }}
+      secretName: {{ .secretName }}
+    {{- end }}
+  {{- end }}
+  rules:
+    {{- range .Values.ingress.hosts }}
+    - host: {{ .host | quote }}
+      http:
+        paths:
+          {{- range .paths }}
+          - path: {{ .path }}
+            {{- if and .pathType (semverCompare ">=1.18-0" $.Capabilities.KubeVersion.GitVersion) }}
+            pathType: {{ .pathType }}
+            {{- end }}
+            backend:
+              {{- if semverCompare ">=1.19-0" $.Capabilities.KubeVersion.GitVersion }}
+              service:
+                name: {{ $fullName }}
+                port:
+                  number: {{ $svcPort }}
+              {{- else }}
+              serviceName: {{ $fullName }}
+              servicePort: {{ $svcPort }}
+              {{- end }}
+          {{- end }}
+    {{- end }}
+{{- end }}

.gitea/charts/templates/service.yaml

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

.gitea/charts/templates/serviceaccount.yaml

@@ -0,0 +1,12 @@
+{{- if .Values.serviceAccount.create -}}
+apiVersion: v1
+kind: ServiceAccount
+metadata:
+  name: {{ include "homeland.serviceAccountName" . }}
+  labels:
+    {{- include "homeland.labels" . | nindent 4 }}
+  {{- with .Values.serviceAccount.annotations }}
+  annotations:
+    {{- toYaml . | nindent 4 }}
+  {{- end }}
+{{- end }}

.gitea/charts/templates/tests/test-connection.yaml

@@ -0,0 +1,15 @@
+apiVersion: v1
+kind: Pod
+metadata:
+  name: "{{ include "homeland.fullname" . }}-test-connection"
+  labels:
+    {{- include "homeland.labels" . | nindent 4 }}
+  annotations:
+    "helm.sh/hook": test
+spec:
+  containers:
+    - name: wget
+      image: busybox
+      command: ['wget']
+      args: ['{{ include "homeland.fullname" . }}:{{ .Values.service.port }}']
+  restartPolicy: Never

.gitea/charts/values.yaml

@@ -0,0 +1,84 @@
+# Default values for homeland.
+# This is a YAML-formatted file.
+# Declare variables to be passed into your templates.
+
+replicaCount: 1
+
+image:
+  repository: 172.16.54.94:5000/homeland
+  pullPolicy: IfNotPresent
+  # Overrides the image tag whose default is the chart appVersion.
+  tag: "29"
+
+imagePullSecrets: []
+nameOverride: ""
+fullnameOverride: ""
+
+serviceAccount:
+  # Specifies whether a service account should be created
+  create: 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: ""
+
+podAnnotations: {}
+
+podSecurityContext: {}
+  # fsGroup: 2000
+
+securityContext: {}
+  # capabilities:
+  #   drop:
+  #   - ALL
+  # readOnlyRootFilesystem: true
+  # runAsNonRoot: true
+  # runAsUser: 1000
+
+service:
+  type: ClusterIP
+  port: 80
+
+ingress:
+  enabled: false
+  className: ""
+  annotations: {}
+    # kubernetes.io/ingress.class: nginx
+    # kubernetes.io/tls-acme: "true"
+  hosts:
+    - host: homeland.local
+      paths:
+        - path: /
+          pathType: ImplementationSpecific
+  tls: []
+  #  - secretName: chart-example-tls
+  #    hosts:
+  #      - chart-example.local
+
+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
+
+autoscaling:
+  enabled: false
+  minReplicas: 1
+  maxReplicas: 100
+  targetCPUUtilizationPercentage: 80
+  # targetMemoryUtilizationPercentage: 80
+
+nodeSelector: {
+  kubernetes.io/hostname: devsvr1
+}
+
+tolerations: []
+
+affinity: {}

.gitea/workflows/deploy.yaml

@@ -3,7 +3,7 @@ run-name: ${{ gitea.actor }} is testing out Gitea Actions 🚀
 on:
   push:
     branches:
-      - 'prod'
+      - 'prod-yantu'
 
 env:
   BUILD: staging
@@ -11,7 +11,7 @@ env:
 
 jobs:
   Explore-Gitea-Actions:
-    runs-on: stream9
+    runs-on: yantoo-ci
     steps:
       - run: echo "🎉 The job was automatically triggered by a ${{ gitea.event_name }} event."
       - run: echo "🐧 This job is now running on a ${{ runner.os }} server hosted by Gitea!"
@@ -29,18 +29,13 @@ jobs:
       - name: Build and push
         uses: https://gitea.yantootech.com/neil/build-push-action@v6
         with:
-          push: false
-          tags: gong-zheng-api:${{ gitea.run_id }}
-      - name: Run docker
+          push: true
+          tags: 14.103.114.237:30005/gongzheng-backend:${{ gitea.run_id }}
+      - name: Install
         run: |
-          pwd
-          if [ "$(docker ps -q -f name=^gong-zheng-api$)" ]; then
-            docker stop gong-zheng-api
-          fi
-          docker run -d --rm --name gong-zheng-api \
-            -v /usr/share/fonts/opentype/noto:/usr/share/fonts \
-            -v $(pwd)/audio:/app/audio \
-            -p 6211:8080 \
-            -p 6212:8000 \
-            gong-zheng-api:${{ gitea.run_id }}
+          helm upgrade --install gongzheng-backend ./.gitea/charts \
+            --namespace gongzhengb \
+            --create-namespace \
+            --set image.repository=14.103.114.237:30005/gongzheng-backend \
+            --set image.tag=${{ gitea.run_id }}
       - run: echo "🍏 This job's status is ${{ job.status }}."

Dockerfile

@@ -1,56 +1,31 @@
 # 构建 Go 服务
 FROM golang:1.21-alpine AS go-builder
 
-WORKDIR /app
+WORKDIR /usr/src/app
 
 # 安装必要的构建工具
 RUN apk add --no-cache gcc musl-dev
 
+# 设置 GOPROXY 环境变量
+ENV GOPROXY=https://goproxy.cn,direct
+
 # 复制 Go 项目文件
 COPY . .
 
 # 构建 Go 服务
 RUN go build -o main ./main.go
 
-# 构建 Python 服务
-FROM python:3.11-slim
+# 运行阶段
+FROM alpine:latest
 
-WORKDIR /app
+WORKDIR /usr/src/app
 
-# 安装必要的系统依赖
-RUN apt-get update && apt-get install -y \
-    ca-certificates \
-    && rm -rf /var/lib/apt/lists/*
+# 从构建阶段复制编译好的二进制文件和配置文件
+COPY --from=go-builder /usr/src/app/main .
+COPY --from=go-builder /usr/src/app/.env .
 
-# 创建音频目录
-RUN mkdir -p /app/audio
+# 暴露端口（根据你的 API 服务端口修改）
+EXPOSE 8080
 
-# 复制 Python 文件服务器
-COPY file_server.py .
-
-# 从 go-builder 阶段复制编译好的 Go 服务
-COPY --from=go-builder /app/main .
-
-# 复制配置文件（如果有的话）
-COPY --from=go-builder /app/config.yaml .
-
-# 设置环境变量
-ENV PORT=8000
-ENV GO_PORT=8080
-
-# 创建启动脚本
-RUN echo '#!/bin/bash\n\
-# 启动 Go 服务\n\
-./main &\n\
-# 启动 Python 文件服务器\n\
-python file_server.py -p $PORT\n\
-' > /app/start.sh && chmod +x /app/start.sh
-
-# 暴露端口
-EXPOSE 8000 8080
-
-# 设置工作目录
-WORKDIR /app
-
-# 启动服务
-CMD ["/app/start.sh"] 
+# 运行服务
+CMD ["./main"]

docker-compose.yml

@@ -4,11 +4,9 @@ services:
   app:
     build: .
     ports:
-      - "8000:8000"  # Python 文件服务器端口
       - "8080:8080"  # Go 服务端口
     volumes:
       - ./audio:/app/audio  # 挂载音频目录
     environment:
-      - PORT=8000
       - GO_PORT=8080
     restart: unless-stopped 

file_server.py

@@ -62,7 +62,6 @@ class FileHandler(http.server.SimpleHTTPRequestHandler):
             with open(file_path, 'rb') as f:
                 self.send_response(200)
                 self.send_header('Content-type', content_type)
-                self.send_header('Content-Disposition', f'attachment; filename="{os.path.basename(file_path)}"')
                 self.end_headers()
                 self.wfile.write(f.read())
         except Exception as e:

main.go

@@ -1,6 +1,7 @@
 package main
 
 import (
+	"fmt"
 	"log"
 	"os"
 	"strconv"
@@ -25,8 +26,12 @@ func main() {
 		MiniMaxApiKey: os.Getenv("MiniMaxApiKey"),
 		MiniMaxApiURL: os.Getenv("MiniMaxApiURL"),
 		FILE_URL:      os.Getenv("FILE_URL"),
+		LLMOurApiUrl:  os.Getenv("LLMOurApiUrl"),
+		LLMOurApiKey:  os.Getenv("LLMOurApiKey"),
 	})
 
+	fmt.Println("config: ", llmService)
+
 	// Get token configuration from environment variables
 	sigExp, err := strconv.Atoi(os.Getenv("SIG_EXP"))
 	if err != nil {
@@ -69,9 +74,24 @@ func main() {
 	router.POST("/speech/synthesize", llmHandler.SynthesizeSpeech)
 	router.GET("/stream-text", llmHandler.StreamText)
 	router.POST("/token", tokenHandler.GenerateToken)
+	// Define routes
+	router.GET("/", func(c *gin.Context) {
+		c.JSON(200, gin.H{
+			"status":  "ok",
+			"message": "Service is healthy",
+		})
+	})
+	// Define routes
+	router.GET("/health", func(c *gin.Context) {
+		c.JSON(200, gin.H{
+			"status":  "ok",
+			"message": "Service is healthy",
+		})
+	})
 
 	// Serve static files
 	router.Static("/static", "./static")
+	router.Static("/audio", "./audio") // 添加音频文件访问服务
 
 	// Get host and port from environment variables
 	host := os.Getenv("HOST")
@@ -80,7 +100,7 @@ func main() {
 	}
 	port := os.Getenv("PORT")
 	if port == "" {
-		port = "8080"
+		port = "80"
 	}
 
 	// Start server

service/llm_service.go

@@ -24,6 +24,8 @@ type Config struct {
 	MiniMaxApiKey string
 	MiniMaxApiURL string
 	FILE_URL      string
+	LLMOurApiUrl  string
+	LLMOurApiKey  string
 }
 
 // LLMService handles communication with the LLM API
@@ -51,6 +53,7 @@ type RequestPayload struct {
 	ConversationID string                 `json:"conversation_id"`
 	Files          []interface{}          `json:"files"`
 	Audio          string                 `json:"audio"`
+	LlmType        string                 `json:"llm_type"`
 }
 
 // VoiceSetting represents voice configuration
@@ -112,6 +115,18 @@ type SpeechResponse struct {
 	BaseResp  BaseResponse `json:"base_resp"`
 }
 
+type LLMOurMessage struct {
+	Role    string `json:"role"`
+	Content string `json:"content"`
+}
+
+type LLMOurRequestPayload struct {
+	Model         string                 `json:"model"`
+	Stream        bool                   `json:"stream"`
+	StreamOptions map[string]interface{} `json:"stream_options"`
+	Messages      []LLMOurMessage        `json:"messages"`
+}
+
 // NewLLMService creates a new instance of LLMService
 func NewLLMService(config Config) *LLMService {
 	return &LLMService{
@@ -130,6 +145,7 @@ func (s *LLMService) CallLLMAPI(data map[string]interface{}) (interface{}, error
 		ConversationID: getString(data, "conversation_id"),
 		Files:          make([]interface{}, 0),
 		Audio:          getString(data, "audio"),
+		LlmType:        getString(data, "llm_type"),
 	}
 
 	fmt.Printf("前端传来的数据：%+v\n", payload)
@@ -138,12 +154,51 @@ func (s *LLMService) CallLLMAPI(data map[string]interface{}) (interface{}, error
 		return nil, fmt.Errorf("error marshaling payload: %v", err)
 	}
 
-	req, err := http.NewRequest("POST", s.config.LLMApiURL+"/chat-messages", bytes.NewBuffer(jsonData))
-	// req, err := http.NewRequest("GET", "http://localhost:8080/stream-text", nil)
+	currentUrl := s.config.LLMApiURL + "/chat-messages"
+	fmt.Println(currentUrl)
+	req := &http.Request{}
+	if payload.LlmType == "ours" {
+		// 动态构造 messages
+		var messages []LLMOurMessage
+		if msgs, ok := data["messages"]; ok {
+			if arr, ok := msgs.([]interface{}); ok {
+				for _, m := range arr {
+					if mMap, ok := m.(map[string]interface{}); ok {
+						role, _ := mMap["role"].(string)
+						content, _ := mMap["content"].(string)
+						messages = append(messages, LLMOurMessage{Role: role, Content: content})
+					}
+				}
+			}
+		}
+		// fallback: 如果没有 messages，则用 query 作为 user 消息
+		if len(messages) == 0 && payload.Query != "" {
+			messages = append(messages, LLMOurMessage{Role: "user", Content: payload.Query})
+		}
+		ourPayload := LLMOurRequestPayload{
+			Model:         "bot-20250522162100-44785", // 可根据 data 或配置传入
+			Stream:        true,
+			StreamOptions: map[string]interface{}{"include_usage": true},
+			Messages:      messages,
+		}
+		jsonData, err = json.Marshal(ourPayload)
+		if err != nil {
+			return nil, fmt.Errorf("error marshaling ourPayload: %v", err)
+		}
+		currentUrl = s.config.LLMOurApiUrl
+		req, err = http.NewRequest("POST", currentUrl, bytes.NewBuffer(jsonData))
+		if err != nil {
+			return nil, fmt.Errorf("error creating request: %v", err)
+		}
+		req.Header.Set("Authorization", "Bearer "+s.config.LLMOurApiKey)
+		req.Header.Set("Content-Type", "application/json")
+		return s.handleStreamingResponseV2(req, data, payload.Audio)
+	}
+
+	req, err = http.NewRequest("POST", currentUrl, bytes.NewBuffer(jsonData))
 	if err != nil {
 		return nil, fmt.Errorf("error creating request: %v", err)
 	}
-
 	req.Header.Set("Authorization", "Bearer "+s.config.LLMApiKey)
 	req.Header.Set("Content-Type", "application/json")
 
@@ -155,6 +210,135 @@ func (s *LLMService) CallLLMAPI(data map[string]interface{}) (interface{}, error
 	return s.handleNonStreamingResponse(req)
 }
 
+// processStreamSegment 处理流式文本分段、语音合成等逻辑，返回 new_message、audio、是否需要发送
+func (s *LLMService) processStreamSegment(initialSessage *string, all_message *string, answer string, audio_type string) (string, string, bool) {
+	// 定义标点符号map
+	punctuations := map[string]bool{
+		",": true, "，": true, // 逗号
+		".": true, "。": true, // 句号
+		"!": true, "！": true, // 感叹号
+		"?": true, "？": true, // 问号
+		";": true, "；": true, // 分号
+		":": true, "：": true, // 冒号
+		"、": true,
+	}
+
+	// 删除字符串前后的标点符号
+	trimPunctuation := func(s string) string {
+		if len(s) > 0 {
+			lastRune, size := utf8.DecodeLastRuneInString(s)
+			if punctuations[string(lastRune)] {
+				s = s[:len(s)-size]
+			}
+		}
+		return s
+	}
+
+	// 判断字符串是否包含标点符号
+	containsPunctuation := func(s string) bool {
+		for _, char := range s {
+			if punctuations[string(char)] {
+				return true
+			}
+		}
+		return false
+	}
+
+	// 按标点符号分割文本
+	splitByPunctuation := func(s string) []string {
+		var result []string
+		var current string
+		for _, char := range s {
+			if punctuations[string(char)] {
+				if current != "" {
+					result = append(result, current+string(char))
+					current = ""
+				}
+			} else {
+				current += string(char)
+			}
+		}
+		if current != "" {
+			result = append(result, current)
+		}
+		return result
+	}
+
+	*initialSessage += answer
+	*all_message += answer
+	new_message := ""
+	if containsPunctuation(*initialSessage) {
+		segments := splitByPunctuation(*initialSessage)
+		if len(segments) > 1 {
+			format_message := strings.Join(segments[:len(segments)-1], "")
+			if utf8.RuneCountInString(format_message) > 10 {
+				*initialSessage = segments[len(segments)-1]
+				new_message = strings.Join(segments[:len(segments)-1], "")
+			} else {
+				return "", "", false
+			}
+		} else {
+			if utf8.RuneCountInString(*initialSessage) > 10 {
+				new_message = *initialSessage
+				*initialSessage = ""
+			} else if utf8.RuneCountInString(*initialSessage) <= 10 && strings.HasSuffix(*initialSessage, "。") {
+				new_message = *initialSessage
+				*initialSessage = ""
+			} else {
+				return "", "", false
+			}
+		}
+	}
+
+	if new_message == "" {
+		return "", "", false
+	}
+	s_msg := strings.TrimSpace(new_message)
+	new_message = trimPunctuation(s_msg)
+
+	audio := ""
+	for i := 0; i < 1; i++ {
+		speechResp, err := s.SynthesizeSpeech(new_message, audio_type)
+		if err != nil {
+			fmt.Printf("Error synthesizing speech: %v\n", err)
+			break
+		}
+		fmt.Println("触发音频", speechResp)
+		audio = speechResp.Data.Audio
+		if audio != "" {
+			resp, err := http.Get(audio)
+			if err != nil {
+				fmt.Printf("Error downloading audio: %v\n", err)
+			} else {
+				defer resp.Body.Close()
+				audioBytes, err := io.ReadAll(resp.Body)
+				if err != nil {
+					fmt.Printf("Error reading audio data: %v\n", err)
+				} else {
+					originalPath := fmt.Sprintf("audio/original_%d.wav", time.Now().UnixNano())
+					if err := os.WriteFile(originalPath, audioBytes, 0644); err != nil {
+						fmt.Printf("Error saving original audio: %v\n", err)
+					}
+					audioBase64 := base64.StdEncoding.EncodeToString(audioBytes)
+					trimmedAudio, err := s.TrimAudioSilence(audioBase64)
+					if err != nil {
+						fmt.Printf("Error trimming audio silence: %v\n", err)
+					} else {
+						audio_path := fmt.Sprintf("trimmed_%d.wav", time.Now().UnixNano())
+						outputPath := "audio/" + audio_path
+						if err := s.SaveBase64AsWAV(trimmedAudio, outputPath); err != nil {
+							fmt.Printf("Error saving trimmed WAV file: %v\n", err)
+						}
+						audio = s.config.FILE_URL + audio_path
+					}
+				}
+			}
+			break
+		}
+	}
+	return s_msg, audio, true
+}
+
 // handleStreamingResponse processes streaming responses
 func (s *LLMService) handleStreamingResponse(req *http.Request, data map[string]interface{}, audio_type string) (chan Message, error) {
 	resp, err := s.client.Do(req)
@@ -167,6 +351,7 @@ func (s *LLMService) handleStreamingResponse(req *http.Request, data map[string]
 	}
 
 	messageChan := make(chan Message, 100) // Buffered channel for better performance
+	all_message := ""
 	initialSessage := ""
 	go func() {
 		defer resp.Body.Close()
@@ -200,6 +385,7 @@ func (s *LLMService) handleStreamingResponse(req *http.Request, data map[string]
 			switch event {
 			case "message":
 				answer := getString(jsonData, "answer")
+				fmt.Println("源文本：", answer)
 				var audio string
 
 				// 定义标点符号map
@@ -209,7 +395,7 @@ func (s *LLMService) handleStreamingResponse(req *http.Request, data map[string]
 					"!": true, "！": true, // 感叹号
 					"?": true, "？": true, // 问号
 					";": true, "；": true, // 分号
-					":": true, "：": true, // 冒号
+					"：": true, // 冒号
 					"、": true,
 				}
 
@@ -256,6 +442,7 @@ func (s *LLMService) handleStreamingResponse(req *http.Request, data map[string]
 				}
 				new_message := ""
 				initialSessage += answer
+				all_message += answer
 				if containsPunctuation(initialSessage) {
 					segments := splitByPunctuation(initialSessage)
 					// fmt.Printf("原始文本: %s\n", initialSessage)
@@ -264,11 +451,32 @@ func (s *LLMService) handleStreamingResponse(req *http.Request, data map[string]
 					// 	fmt.Printf("片段 %d: %s\n", i+1, segment)
 					// }
 					if len(segments) > 1 {
-						initialSessage = segments[len(segments)-1]
-						new_message = strings.Join(segments[:len(segments)-1], "")
+
+						format_message := strings.Join(segments[:len(segments)-1], "")
+						// 检查initialSessage的字符长度是否超过15个
+						if utf8.RuneCountInString(format_message) > 15 {
+							initialSessage = segments[len(segments)-1]
+							// 如果超过10个字符，将其添加到new_message中并清空initialSessage
+							new_message = strings.Join(segments[:len(segments)-1], "")
+							// initialSessage = ""
+						} else {
+							if containsPunctuation(format_message) && utf8.RuneCountInString(format_message) > 10 {
+
+								initialSessage = segments[len(segments)-1]
+								new_message = strings.Join(segments[:len(segments)-1], "")
+							} else {
+								continue
+							}
+						}
 					} else {
-						new_message = initialSessage
-						initialSessage = ""
+
+						if utf8.RuneCountInString(initialSessage) > 15 {
+							new_message = initialSessage
+							initialSessage = ""
+						} else {
+							continue
+						}
+
 					}
 					// fmt.Printf("新消息: %s\n", new_message)
 					// fmt.Printf("剩余文本: %s\n", initialSessage)
@@ -280,8 +488,8 @@ func (s *LLMService) handleStreamingResponse(req *http.Request, data map[string]
 				s_msg := strings.TrimSpace(new_message)
 				// Trim punctuation from the message
 				new_message = trimPunctuation(s_msg)
-				// fmt.Println("new_message", new_message)
-
+				fmt.Println("new_message", new_message)
+				// println(new_message)
 				// 最多重试一次
 				for i := 0; i < 1; i++ {
 					speechResp, err := s.SynthesizeSpeech(new_message, audio_type)
@@ -303,7 +511,7 @@ func (s *LLMService) handleStreamingResponse(req *http.Request, data map[string]
 								fmt.Printf("Error reading audio data: %v\n", err)
 							} else {
 								// Save original audio first
-								originalPath := fmt.Sprintf("audio/original_%d.wav", time.Now().Unix())
+								originalPath := fmt.Sprintf("audio/original_%d.wav", time.Now().UnixNano())
 								if err := os.WriteFile(originalPath, audioBytes, 0644); err != nil {
 									fmt.Printf("Error saving original audio: %v\n", err)
 								}
@@ -315,7 +523,7 @@ func (s *LLMService) handleStreamingResponse(req *http.Request, data map[string]
 									fmt.Printf("Error trimming audio silence: %v\n", err)
 								} else {
 									// Save the trimmed audio as WAV file
-									audio_path := fmt.Sprintf("trimmed_%d.wav", time.Now().Unix())
+									audio_path := fmt.Sprintf("trimmed_%d.wav", time.Now().UnixNano())
 									outputPath := "audio/" + audio_path
 									if err := s.SaveBase64AsWAV(trimmedAudio, outputPath); err != nil {
 										fmt.Printf("Error saving trimmed WAV file: %v\n", err)
@@ -326,12 +534,12 @@ func (s *LLMService) handleStreamingResponse(req *http.Request, data map[string]
 						}
 						break // 获取到音频就退出
 					}
-					fmt.Println("audio is empty, retry", speechResp)
+					// fmt.Println("audio is empty, retry", speechResp)
 					// time.Sleep(1 * time.Second)
 				}
-
+				fmt.Println("所有消息：", all_message)
 				messageChan <- Message{
-					Answer:         new_message,
+					Answer:         s_msg,
 					IsEnd:          false,
 					ConversationID: getString(jsonData, "conversation_id"),
 					TaskID:         getString(jsonData, "task_id"),
@@ -339,6 +547,96 @@ func (s *LLMService) handleStreamingResponse(req *http.Request, data map[string]
 					AudioData:      audio, // Update to use the correct path to audio data
 				}
 			case "message_end":
+				// 在流结束前，处理剩余的文本生成音频
+				if initialSessage != "" {
+					// 不管文本长度，直接生成音频
+					s_msg := strings.TrimSpace(initialSessage)
+					// 定义标点符号map
+					punctuations := map[string]bool{
+						",": true, "，": true, // 逗号
+						".": true, "。": true, // 句号
+						"!": true, "！": true, // 感叹号
+						"?": true, "？": true, // 问号
+						";": true, "；": true, // 分号
+						":": true, "：": true, // 冒号
+						"、": true,
+					}
+
+					// 删除字符串前后的标点符号
+					trimPunctuation := func(s string) string {
+						if len(s) > 0 {
+							lastRune, size := utf8.DecodeLastRuneInString(s)
+							if punctuations[string(lastRune)] {
+								s = s[:len(s)-size]
+							}
+						}
+						return s
+					}
+
+					new_message := trimPunctuation(s_msg)
+					fmt.Println("最后一段文本生成音频:", new_message)
+
+					// 生成语音
+					var audio string
+					for i := 0; i < 1; i++ {
+						speechResp, err := s.SynthesizeSpeech(new_message, audio_type)
+						if err != nil {
+							fmt.Printf("Error synthesizing speech: %v\n", err)
+							break
+						}
+						fmt.Println("语音：", speechResp)
+						audio = speechResp.Data.Audio
+						if audio != "" {
+							// 下载并处理音频
+							resp, err := http.Get(audio)
+							if err != nil {
+								fmt.Printf("Error downloading audio: %v\n", err)
+							} else {
+								defer resp.Body.Close()
+								audioBytes, err := io.ReadAll(resp.Body)
+								if err != nil {
+									fmt.Printf("Error reading audio data: %v\n", err)
+								} else {
+									// 保存原始音频
+									originalPath := fmt.Sprintf("audio/original_%d.wav", time.Now().UnixNano())
+									if err := os.WriteFile(originalPath, audioBytes, 0644); err != nil {
+										fmt.Printf("Error saving original audio: %v\n", err)
+									}
+
+									// 静音裁剪
+									audioBase64 := base64.StdEncoding.EncodeToString(audioBytes)
+									trimmedAudio, err := s.TrimAudioSilence(audioBase64)
+									if err != nil {
+										fmt.Printf("Error trimming audio silence: %v\n", err)
+									} else {
+										audio_path := fmt.Sprintf("trimmed_%d.wav", time.Now().UnixNano())
+										outputPath := "audio/" + audio_path
+										if err := s.SaveBase64AsWAV(trimmedAudio, outputPath); err != nil {
+											fmt.Printf("Error saving trimmed WAV file: %v\n", err)
+										}
+										audio = s.config.FILE_URL + audio_path
+									}
+								}
+							}
+							break
+						}
+					}
+
+					// 发送最后一段文本的消息
+					messageChan <- Message{
+						Answer:         s_msg,
+						IsEnd:          false,
+						ConversationID: getString(jsonData, "conversation_id"),
+						TaskID:         getString(jsonData, "task_id"),
+						ClientID:       getString(data, "conversation_id"),
+						AudioData:      audio,
+					}
+
+					// 清空剩余文本
+					initialSessage = ""
+				}
+
+				// 发送结束消息
 				messageChan <- Message{
 					Answer:         "",
 					IsEnd:          true,
@@ -353,6 +651,95 @@ func (s *LLMService) handleStreamingResponse(req *http.Request, data map[string]
 	return messageChan, nil
 }
 
+// handleStreamingResponseV2 适配新流式返回格式
+func (s *LLMService) handleStreamingResponseV2(req *http.Request, data map[string]interface{}, audio_type string) (chan Message, error) {
+	resp, err := s.client.Do(req)
+	if err != nil {
+		return nil, fmt.Errorf("error making request: %v", err)
+	}
+
+	if resp.StatusCode != http.StatusOK {
+		return nil, fmt.Errorf("unexpected status code: %d", resp.StatusCode)
+	}
+
+	messageChan := make(chan Message, 100)
+	all_message := ""
+	initialSessage := ""
+	go func() {
+		defer resp.Body.Close()
+		defer close(messageChan)
+		reader := bufio.NewReader(resp.Body)
+		for {
+			line, err := reader.ReadString('\n')
+			if err != nil {
+				if err == io.EOF {
+					break
+				}
+				fmt.Printf("Error reading line: %v\n", err)
+				continue
+			}
+
+			line = strings.TrimSpace(line)
+			if line == "" {
+				continue
+			}
+
+			// line = strings.TrimSpace(line)
+			if strings.HasPrefix(line, "data:") {
+				line = strings.TrimSpace(strings.TrimPrefix(line, "data:"))
+			}
+
+			// fmt.Println("line: ", line)
+
+			if line == "[DONE]" {
+				messageChan <- Message{
+					Answer:         "",
+					IsEnd:          true,
+					ConversationID: getString(data, "conversation_id"),
+					TaskID:         getString(data, "task_id"),
+				}
+				return
+			}
+
+			var jsonData map[string]interface{}
+			if err := json.Unmarshal([]byte(line), &jsonData); err != nil {
+				fmt.Printf("Error unmarshaling JSON: %v\n", err)
+				continue
+			}
+			choices, ok := jsonData["choices"].([]interface{})
+			if !ok || len(choices) == 0 {
+				continue
+			}
+			choice, ok := choices[0].(map[string]interface{})
+			if !ok {
+				continue
+			}
+			delta, ok := choice["delta"].(map[string]interface{})
+			if !ok {
+				continue
+			}
+			content, _ := delta["content"].(string)
+			if content == "" {
+				continue
+			}
+
+			new_message, audio, needSend := s.processStreamSegment(&initialSessage, &all_message, content, audio_type)
+			if !needSend {
+				continue
+			}
+			messageChan <- Message{
+				Answer:         new_message,
+				IsEnd:          false,
+				ConversationID: getString(data, "conversation_id"),
+				TaskID:         getString(data, "task_id"),
+				ClientID:       getString(data, "conversation_id"),
+				AudioData:      audio,
+			}
+		}
+	}()
+	return messageChan, nil
+}
+
 // handleNonStreamingResponse processes non-streaming responses
 func (s *LLMService) handleNonStreamingResponse(req *http.Request) (map[string]interface{}, error) {
 	resp, err := s.client.Do(req)
@@ -424,7 +811,7 @@ func (s *LLMService) DeleteConversation(conversationID, user string) (map[string
 // SynthesizeSpeech converts text to speech
 func (s *LLMService) SynthesizeSpeech(text string, audio string) (*SpeechResponse, error) {
 	payload := SpeechRequest{
-		Model:         "speech-02-turbo",
+		Model:         "speech-02-hd",
 		Text:          text,
 		Stream:        false,
 		LanguageBoost: "auto",
@@ -433,8 +820,8 @@ func (s *LLMService) SynthesizeSpeech(text string, audio string) (*SpeechRespons
 			VoiceID: audio,
 			Speed:   1,
 			Vol:     1,
-			Pitch:   0,
-			Emotion: "happy",
+			Pitch:   -1,
+			Emotion: "neutral",
 		},
 		AudioSetting: AudioSetting{
 			SampleRate: 32000,