Merge branch 'main' into dev-manager-api-local

.dockerignore

@@ -0,0 +1,7 @@
+.git
+__pycache__
+*.pyc
+.env
+Dockerfile
+tmp/
+data/

.github/workflows/docker-image.yml

@@ -7,30 +7,31 @@ on:
 
 jobs:
   release:
-    name: Release Docker image
+    name: Release Docker images
     runs-on: ubuntu-latest
     permissions:
       packages: write
       contents: write
       id-token: write
       issues: write
-
     steps:
       - name: Check Disk Space
         run: |
           df -h
           docker system df
+
       - name: Clean up Docker resources
         run: |
           docker system prune -af
           docker builder prune -af
-      - name: Check out the repo
+
+      - name: Checkout code
         uses: actions/checkout@v4
 
       - name: Set up Docker Buildx
         uses: docker/setup-buildx-action@v3
 
-      - name: Log in to the GitHub Container Registry
+      - name: Login to GitHub Container Registry
         uses: docker/login-action@v3
         with:
           registry: ghcr.io
@@ -42,13 +43,26 @@ jobs:
         run: |
           echo "VERSION=${GITHUB_REF#refs/tags/}" >> $GITHUB_ENV
 
-      - name: Build and push Docker image
+      # 构建 xiaozhi-server 镜像
-        id: build_push
+      - name: Build and push xiaozhi-server
         uses: docker/build-push-action@v6
         with:
           context: .
+          file: Dockerfile-server
           push: true
           tags: |
-            ghcr.io/${{ github.repository }}:${{ env.VERSION }}
+            ghcr.io/${{ github.repository }}:server_${{ env.VERSION }}
-            ghcr.io/${{ github.repository }}:latest
+            ghcr.io/${{ github.repository }}:server_latest
+          platforms: linux/amd64,linux/arm64
+
+      # 构建 manager-api 镜像
+      - name: Build and push manager-web
+        uses: docker/build-push-action@v6
+        with:
+          context: .
+          file: Dockerfile-web
+          push: true
+          tags: |
+            ghcr.io/${{ github.repository }}:web_${{ env.VERSION }}
+            ghcr.io/${{ github.repository }}:web_latest
           platforms: linux/amd64,linux/arm64

Dockerfile-server

@@ -23,7 +23,7 @@ RUN apt-get update && \
 COPY --from=builder /usr/local/lib/python3.10/site-packages /usr/local/lib/python3.10/site-packages
 
 # 复制应用代码
-COPY main/xiaozhi-server/ .
+COPY main/xiaozhi-server .
 
 # 启动应用
 CMD ["python", "app.py"]

Dockerfile-web

@@ -0,0 +1,40 @@
+# 第一阶段：构建Vue前端
+FROM node:18 as web-builder
+WORKDIR /app
+COPY main/manager-web/package*.json ./
+RUN npm install
+COPY main/manager-web .
+RUN npm run build
+
+# 第二阶段：构建Java后端
+FROM maven:3-eclipse-temurin-21-alpine as api-builder
+WORKDIR /app
+COPY main/manager-api/pom.xml .
+COPY main/manager-api/src ./src
+RUN mvn clean package -Dmaven.test.skip=true
+
+# 第三阶段：构建最终镜像
+FROM eclipse-temurin:21-jdk-jammy
+
+# 安装Nginx并清理缓存
+RUN apt-get update && \
+    apt-get install -y nginx && \
+    apt-get clean && \
+    rm -rf /var/lib/apt/lists/*
+
+# 配置Nginx
+COPY docs/docker/nginx.conf /etc/nginx/conf.d/default.conf
+
+# 复制前端构建产物
+COPY --from=web-builder /app/dist /usr/share/nginx/html
+
+# 复制Java后端JAR包
+COPY --from=api-builder /app/target/xiaozhi-esp32-api.jar /app/xiaozhi-esp32-api.jar
+
+# 暴露端口
+EXPOSE 8002
+
+# 启动脚本
+COPY docs/docker/start.sh /start.sh
+RUN chmod +x /start.sh
+CMD ["/start.sh"]

docs/docker/nginx.conf

@@ -0,0 +1,26 @@
+server {
+    listen 8002;
+    server_name localhost;
+
+    # 静态资源服务（Vue项目）
+    location / {
+        root /usr/share/nginx/html;
+        try_files $uri $uri/ /index.html;
+    }
+
+    # API反向代理（Java项目）
+    location /xiaozhi-esp32-api/ {
+        proxy_pass http://127.0.0.1:8003;
+        proxy_set_header   Host   $host;
+        proxy_cookie_path /api/ /;
+        proxy_set_header   Referer $http_referer;
+        proxy_set_header   Cookie $http_cookie;
+
+        proxy_connect_timeout 10;
+        proxy_send_timeout 10;
+        proxy_read_timeout 10;
+
+        proxy_set_header   X-Real-IP  $remote_addr;
+        proxy_set_header   X-Forwarded-For $proxy_add_x_forwarded_for;
+    }
+}

docs/docker/start.sh

@@ -0,0 +1,12 @@
+#!/bin/bash
+# 启动Java后端（docker内监听8003端口）
+java -jar /app/xiaozhi-esp32-api.jar \
+  --server.port=8003 \
+  --spring.datasource.druid.url=${SPRING_DATASOURCE_DRUID_URL} \
+  --spring.datasource.druid.username=${SPRING_DATASOURCE_DRUID_USERNAME} \
+  --spring.datasource.druid.password=${SPRING_DATASOURCE_DRUID_PASSWORD} \
+  --spring.data.redis.host=${SPRING_DATA_REDIS_HOST} \
+  --spring.data.redis.port=${SPRING_DATA_REDIS_PORT} &
+
+# 启动Nginx（前台运行保持容器存活）
+nginx -g 'daemon off;'

main/manager-api/src/main/java/xiaozhi/common/exception/ErrorCode.java

@@ -36,7 +36,7 @@ public interface ErrorCode {
     int JOB_ERROR = 10028;
     int INVALID_SYMBOL = 10029;
     
-
+    // 密码相关错误码
     int PASSWORD_LENGTH_ERROR = 10030;
     int PASSWORD_WEAK_ERROR = 10031;
     int DEL_MYSELF_ERROR = 10032;

main/xiaozhi-server/.dockerignore

@@ -1,13 +0,0 @@
-.git
-__pycache__
-*.pyc
-.env
-Dockerfile
-../docs/
-tmp/
-data/
-LICENSE
-README.md
-README_en.md
-manager/static
-manager/static/webui/

main/xiaozhi-server/Dockerfile

@@ -1,16 +0,0 @@
-# 第一阶段：构建 Python 依赖
-FROM kalicyh/poetry:v3.10_xiaozhi AS builder
-
-WORKDIR /opt/xiaozhi-esp32-server
-
-# 同时拷贝本地环境.venv
-COPY . .
-# 检查是否有缺失
-RUN poetry install --no-root
-
-# 设置虚拟环境路径
-ENV PATH="/app/.venv/bin:$PATH"
-
-# 启动应用
-ENTRYPOINT ["poetry", "run", "python"]
-CMD ["app.py"]

main/xiaozhi-server/config.yaml

@@ -37,7 +37,8 @@ log:
   data_dir: data
 iot:
   Speaker:
-    volume: 100
+    # 设置esp32的音量，范围0-100
+    volume: 80
 xiaozhi:
   type: hello
   version: 1
@@ -258,6 +259,21 @@ TTS:
     parallel_infer: true
     repetition_penalty: 1.35
     aux_ref_audio_paths: []
+  GPT_SOVITS_V3:
+    type: gpt_sovits_v3
+    url: "http://127.0.0.1:9880/tts"
+    output_file: tmp/
+    text_lang: "auto"
+    ref_audio_path: "caixukun.wav"
+    prompt_lang: "zh"
+    prompt_text: ""
+    top_k: 5
+    top_p: 1
+    temperature: 1
+    sample_steps: 16
+    media_type: "wav"
+    streaming_mode: false
+    threshold: 30
   MinimaxTTS:
     # Minimax语音合成服务，需要先在minimax平台创建账户充值，并获取登录信息
     # 平台地址：https://platform.minimaxi.com/

main/xiaozhi-server/core/handle/iotHandle.py

@@ -109,7 +109,48 @@ async def handleIotDescriptors(conn, descriptors):
         default_iot_volume = conn.config["iot"]["Speaker"]["volume"]
     logger.bind(tag=TAG).info(f"服务端设置音量为{default_iot_volume}")
     await send_iot_conn(conn, "Speaker", "SetVolume", {"volume": default_iot_volume})
+async def handleIotStatus(conn, states):
+    """
+    处理物联网状态
+    示例: [{
+        "name":"Speaker",
+        "state":{
+            "volume":100
+        }
+    }]
+    states: 状态列表
+    """
+    for state in states:
+        for key, value in conn.iot_descriptors.items():
+            if key == state["name"]:
+                for property_item in value.properties:
+                    # properties为字典列表, 记录各种属性
+                    for k, v in state["state"].items():
+                        # state为字典, 记录各种属性的值, 是需要记录的信息
+                        if property_item["name"] == k:
+                            # 检查一下属性是不是相同的
+                            if type(v) != type(property_item["value"]):
+                                logger.bind(tag=TAG).error(f"属性{property_item['name']}的值类型不匹配")
+                                break
+                            else:
+                                property_item["value"] = v
+                                logger.bind(tag=TAG).info(f"物联网状态更新: {key} , {property_item['name']} = {v}")
+                            break
+                break
 
+async def get_iot_status(conn, name, property_name):
+    """
+    获取物联网状态
+    name: 设备名称 "Speaker"
+    property_name: 属性名称 "volume"
+    返回值: 属性值, 实际的属性有int, bool和str三种类型
+    """
+    for key, value in conn.iot_descriptors.items():
+        if key == name:
+            for property_item in value.properties:
+                if property_item["name"] == property_name:
+                    return property_item["value"]
+    return None
 
 async def send_iot_conn(conn, name, method_name, parameters):
     """

main/xiaozhi-server/core/handle/textHandle.py

@@ -3,7 +3,7 @@ import json
 from core.handle.abortHandle import handleAbortMessage
 from core.handle.helloHandle import handleHelloMessage
 from core.handle.receiveAudioHandle import startToChat
-from core.handle.iotHandle import handleIotDescriptors
+from core.handle.iotHandle import handleIotDescriptors, handleIotStatus
 
 TAG = __name__
 logger = setup_logging()
@@ -40,5 +40,7 @@ async def handleTextMessage(conn, message):
         elif msg_json["type"] == "iot":
             if "descriptors" in msg_json:
                 await handleIotDescriptors(conn, msg_json["descriptors"])
+            if "states" in msg_json:
+                await handleIotStatus(conn, msg_json["states"])  
     except json.JSONDecodeError:
         await conn.websocket.send(message)

main/xiaozhi-server/core/providers/tts/gpt_sovits_v3.py

@@ -0,0 +1,52 @@
+import os
+import uuid
+import requests
+from config.logger import setup_logging
+from datetime import datetime
+from core.providers.tts.base import TTSProviderBase
+
+TAG = __name__
+logger = setup_logging()
+
+class TTSProvider(TTSProviderBase):
+    def __init__(self, config, delete_audio_file):
+        super().__init__(config, delete_audio_file)
+        self.url = config.get("url")
+        self.text_lang = config.get("text_lang", "audo")
+        self.ref_audio_path = config.get("ref_audio_path")
+        self.prompt_lang = config.get("prompt_lang")
+        self.prompt_text = config.get("prompt_text")
+        self.top_k = config.get("top_k", 5)
+        self.top_p = config.get("top_p", 1)
+        self.temperature = config.get("temperature", 1)
+        self.sample_steps = config.get("sample_steps", 16)
+        self.media_type = config.get("media_type", "wav")
+        self.streaming_mode = config.get("streaming_mode", False)
+        self.threshold = config.get("threshold", 30)
+
+
+    def generate_filename(self, extension=".wav"):
+        return os.path.join(self.output_file, f"tts-{datetime.now().date()}@{uuid.uuid4().hex}{extension}")
+
+    async def text_to_speak(self, text, output_file):
+        request_params = {
+            "text": text,
+            "text_lang": self.text_lang,
+            "ref_audio_path": self.ref_audio_path,
+            "prompt_lang": self.prompt_lang,
+            "prompt_text": self.prompt_text,
+            "top_k": self.top_k,
+            "top_p": self.top_p,
+            "temperature": self.temperature,
+            "sample_steps": self.sample_steps,
+            "media_type": self.media_type,
+            "streaming_mode": self.streaming_mode,
+            "threshold": self.threshold,
+        }
+
+        resp = requests.get(self.url, params=request_params)
+        if resp.status_code == 200:
+            with open(output_file, "wb") as file:
+                file.write(resp.content)
+        else:
+            logger.bind(tag=TAG).error(f"GPT_SoVITS_V3 TTS请求失败: {resp.status_code} - {resp.text}")

main/xiaozhi-server/core/utils/util.py

@@ -75,7 +75,7 @@ def get_string_no_punctuation_or_emoji(s):
 def remove_punctuation_and_length(text):
     # 全角符号和半角符号的Unicode范围
     full_width_punctuations = '！＂＃＄％＆＇（）＊＋，－。／：；＜＝＞？＠［＼］＾＿｀｛｜｝～'
-    half_width_punctuations = '!"#$%&\'()*+,-./:;<=>?@[\]^_`{|}~'
+    half_width_punctuations = r'!"#$%&\'()*+,-./:;<=>?@[\]^_`{|}~'
     space = ' '  # 半角空格
     full_width_space = '　'  # 全角空格
 

main/xiaozhi-server/docker-compose.yml

@@ -1,7 +1,12 @@
+# 如果本机已经安装了MySQL，可以直接在数据库中创建名为`xiaozhi_esp32_server`的数据库。
+# 如果还没有MySQL，你可以通过docker安装mysql,执行以下一句话
+# docker run --name xiaozhi-esp32-server-db -e MYSQL_ROOT_PASSWORD=123456 -p 3306:3306 -e MYSQL_DATABASE=xiaozhi_esp32_server -e MYSQL_INITDB_ARGS="--character-set-server=utf8mb4 --collation-server=utf8mb4_unicode_ci" -d mysql:latest
+# 如果你的mysql账号和密码有修改过，记得修改下方数据库的账号和密码
+# 记得修改下方数据库的IP，ip不能写127.0.0.1或localhost，否则容器无法访问，要写你电脑局域网ip
 version: '3'
 services:
   xiaozhi-esp32-server:
-    image: ghcr.nju.edu.cn/xinnan-tech/xiaozhi-esp32-server:latest
+    image: ghcr.nju.edu.cn/xinnan-tech/xiaozhi-esp32-server:server_latest
     container_name: xiaozhi-esp32-server
     restart: always
     security_opt:
@@ -11,10 +16,23 @@ services:
     ports:
       # ws服务端
       - "8000:8000"
-      # 管理后台
-      - "8002:8002"
     volumes:
       # 配置文件目录
       - ./data:/opt/xiaozhi-esp32-server/data
       # 模型文件挂接，很重要
       - ./models/SenseVoiceSmall/model.pt:/opt/xiaozhi-esp32-server/models/SenseVoiceSmall/model.pt
+#  #智控台还没开发好，还不能完全使用，会报很多错误，如果是非技术人员，请不要启用智控台服务
+#  xiaozhi-esp32-server-web:
+#    image: ghcr.nju.edu.cn/xinnan-tech/xiaozhi-esp32-server:web_latest
+#    container_name: xiaozhi-esp32-server-web
+#    restart: always
+#    ports:
+#      - "8002:8002"
+#    environment:
+#      - TZ=Asia/Shanghai
+#      ##记得改mysql和redis IP 密码
+#      - SPRING_DATASOURCE_DRUID_URL=jdbc:mysql://192.168.1.20:3306/xiaozhi_esp32_server?useUnicode=true&characterEncoding=UTF-8&serverTimezone=Asia/Shanghai
+#      - SPRING_DATASOURCE_DRUID_USERNAME=root
+#      - SPRING_DATASOURCE_DRUID_PASSWORD=123456
+#      - SPRING_DATA_REDIS_HOST=192.168.1.20
+#      - SPRING_DATA_REDIS_PORT=6379

main/xiaozhi-server/pyproject.toml

@@ -1,42 +0,0 @@
-[tool.poetry]
-name = "xiaozhi-esp32-server"
-version = "0.1.0"
-description = ""
-authors = ["kalicyh <34980061+kaliCYH@users.noreply.github.com>"]
-readme = "README.md"
-
-[tool.poetry.dependencies]
-python = "^3.10"
-pyyml = "0.0.2"
-torch = "2.2.2"
-silero-vad = "5.1.2"
-websockets = "14.2"
-numpy = "1.26.4"
-pydub = "0.25.1"
-funasr = "1.2.3"
-torchaudio = "2.2.2"
-openai = "1.61.0"
-google-generativeai = "0.8.4"
-edge-tts = "7.0.0"
-httpx = "0.27.2"
-aiohttp = "3.9.3"
-aiohttp-cors = "0.7.0"
-ormsgpack = "1.7.0"
-ruamel-yaml = "0.18.10"
-setuptools = "^75.8.0"
-loguru = "^0.7.3"
-opuslib-next = "^1.1.2"
-fastapi = {extras = ["all"], version = "^0.115.8"}
-uvicorn = "^0.34.0"
-pyjwt = "^2.10.1"
-python-jose = {extras = ["cryptography"], version = "^3.3.0"}
-bcrypt = "^4.2.1"
-sqlalchemy = "^2.0.38"
-pymysql = "^1.1.1"
-asyncpg = "^0.30.0"
-onnxruntime = "1.19.2"
-
-
-[build-system]
-requires = ["poetry-core"]
-build-backend = "poetry.core.masonry.api"