mirror of
https://github.com/xinnan-tech/xiaozhi-esp32-server.git
synced 2026-07-23 15:43:54 +08:00
Compare commits
1
Commits
| Author | SHA1 | Date | |
|---|---|---|---|
  dependabot[bot]andGitHub
|
4f7665d92d |
+1
-10
@@ -112,17 +112,12 @@ celerybeat.pid
|
||||
# Environments
|
||||
.env
|
||||
.venv
|
||||
/.venv-*/
|
||||
env/
|
||||
venv/
|
||||
ENV/
|
||||
env.bak/
|
||||
venv.bak/
|
||||
|
||||
# Repository-local runtimes and package-manager caches
|
||||
/.runtime/
|
||||
/main/manager-web/.npm-cache/
|
||||
|
||||
# Spyder project settings
|
||||
.spyderproject
|
||||
.spyproject
|
||||
@@ -192,8 +187,4 @@ uploadfile
|
||||
!main/manager-mobile/**/env/
|
||||
!main/manager-mobile/**/.env*
|
||||
!main/manager-mobile/**/*.json
|
||||
!main/xiaozhi-server/**/*.json
|
||||
!main/digital-human/**/*.json
|
||||
main/digital-human/wakeword_runtime/models
|
||||
main/digital-human/wakeword_runtime/sherpa-onnx-kws-zipformer-wenetspeech-3.3M-2024-01-01
|
||||
sherpa-onnx-kws-zipformer-wenetspeech-3.3M-2024-01-01.tar.bz2
|
||||
!main/xiaozhi-server/**/*.json
|
||||
@@ -18,10 +18,10 @@
|
||||
|
||||
<p align="center">
|
||||
<a href="./README.md"><img alt="简体中文版自述文件" src="https://img.shields.io/badge/简体中文-DBEDFA"></a>
|
||||
<a href="./docs/readme/README_en.md"><img alt="README in English" src="https://img.shields.io/badge/English-DFE0E5"></a>
|
||||
<a href="./docs/readme/README_vi.md"><img alt="Tiếng Việt" src="https://img.shields.io/badge/Tiếng Việt-DFE0E5"></a>
|
||||
<a href="./docs/readme/README_de.md"><img alt="Deutsch" src="https://img.shields.io/badge/Deutsch-DFE0E5"></a>
|
||||
<a href="./docs/readme/README_pt_BR.md"><img alt="Português (Brasil)" src="https://img.shields.io/badge/Português (Brasil)-DFE0E5"></a>
|
||||
<a href="./README_en.md"><img alt="README in English" src="https://img.shields.io/badge/English-DFE0E5"></a>
|
||||
<a href="./README_vi.md"><img alt="Tiếng Việt" src="https://img.shields.io/badge/Tiếng Việt-DFE0E5"></a>
|
||||
<a href="./README_de.md"><img alt="Deutsch" src="https://img.shields.io/badge/Deutsch-DFE0E5"></a>
|
||||
<a href="./README_pt_BR.md"><img alt="Português (Brasil)" src="https://img.shields.io/badge/Português (Brasil)-DFE0E5"></a>
|
||||
<a href="https://github.com/xinnan-tech/xiaozhi-esp32-server/releases">
|
||||
<img alt="GitHub Contributors" src="https://img.shields.io/github/v/release/xinnan-tech/xiaozhi-esp32-server?logo=docker" />
|
||||
</a>
|
||||
@@ -53,98 +53,113 @@ Spearheaded by Professor Siyuan Liu's Team (South China University of Technology
|
||||
<table>
|
||||
<tr>
|
||||
<td>
|
||||
<a href="https://www.bilibili.com/video/BV1FMFyejExX" target="_blank">
|
||||
<picture>
|
||||
<img alt="响应速度感受" src="docs/images/demo9.png" /></picture>
|
||||
</a>
|
||||
<a href="https://www.bilibili.com/video/BV1FMFyejExX" target="_blank">
|
||||
<picture>
|
||||
<img alt="响应速度感受" src="docs/images/demo9.png" />
|
||||
</picture>
|
||||
</a>
|
||||
</td>
|
||||
<td>
|
||||
<a href="https://www.bilibili.com/video/BV1vchQzaEse" target="_blank">
|
||||
<picture>
|
||||
<img alt="速度优化秘诀" src="docs/images/demo6.png" /></picture>
|
||||
</a>
|
||||
<a href="https://www.bilibili.com/video/BV1vchQzaEse" target="_blank">
|
||||
<picture>
|
||||
<img alt="速度优化秘诀" src="docs/images/demo6.png" />
|
||||
</picture>
|
||||
</a>
|
||||
</td>
|
||||
<td>
|
||||
<a href="https://www.bilibili.com/video/BV1WEcxzFEAT" target="_blank">
|
||||
<picture>
|
||||
<img alt="小智数字人 支持语音唤醒" src="docs/images/demo8.png" /></picture>
|
||||
</a>
|
||||
<a href="https://www.bilibili.com/video/BV1C1tCzUEZh" target="_blank">
|
||||
<picture>
|
||||
<img alt="复杂医疗场景" src="docs/images/demo1.png" />
|
||||
</picture>
|
||||
</a>
|
||||
</td>
|
||||
<td>
|
||||
<a href="https://www.bilibili.com/video/BV1CKVz6UEuB" target="_blank">
|
||||
<picture>
|
||||
<img alt="设备呼叫设备，打电话" src="docs/images/demo0.png" /></picture>
|
||||
</a>
|
||||
<a href="https://www.bilibili.com/video/BV1zUW5zJEkq" target="_blank">
|
||||
<picture>
|
||||
<img alt="MQTT指令下发" src="docs/images/demo4.png" />
|
||||
</picture>
|
||||
</a>
|
||||
</td>
|
||||
<td>
|
||||
<a href="https://www.bilibili.com/video/BV1C1tCzUEZh" target="_blank">
|
||||
<picture>
|
||||
<img alt="复杂医疗场景" src="docs/images/demo1.png" /></picture>
|
||||
</a>
|
||||
<a href="https://www.bilibili.com/video/BV1Exu3zqEDe" target="_blank">
|
||||
<picture>
|
||||
<img alt="声纹识别" src="docs/images/demo14.png" />
|
||||
</picture>
|
||||
</a>
|
||||
</td>
|
||||
</tr>
|
||||
<tr>
|
||||
<td>
|
||||
<a href="https://www.bilibili.com/video/BV1VC96Y5EMH" target="_blank">
|
||||
<picture>
|
||||
<img alt="播放音乐查询天气播报新闻" src="docs/images/demo7.png" /></picture>
|
||||
</a>
|
||||
<a href="https://www.bilibili.com/video/BV1pNXWYGEx1" target="_blank">
|
||||
<picture>
|
||||
<img alt="控制家电开关" src="docs/images/demo5.png" />
|
||||
</picture>
|
||||
</a>
|
||||
</td>
|
||||
<td>
|
||||
<a href="https://www.bilibili.com/video/BV12J7WzBEaH" target="_blank">
|
||||
<picture>
|
||||
<img alt="实时打断" src="docs/images/demo10.png" /></picture>
|
||||
</a>
|
||||
</td>
|
||||
<td>
|
||||
<a href="https://www.bilibili.com/video/BV1Co76z7EvK" target="_blank">
|
||||
<picture>
|
||||
<img alt="拍照识物品" src="docs/images/demo12.png" /></picture>
|
||||
</a>
|
||||
</td>
|
||||
<td>
|
||||
<a href="https://www.bilibili.com/video/BV1pNXWYGEx1" target="_blank">
|
||||
<picture>
|
||||
<img alt="控制家电开关" src="docs/images/demo5.png" /></picture>
|
||||
</a>
|
||||
<a href="https://www.bilibili.com/video/BV1ZQKUzYExM" target="_blank">
|
||||
<picture>
|
||||
<img alt="MCP接入点" src="docs/images/demo13.png" />
|
||||
</picture>
|
||||
</a>
|
||||
</td>
|
||||
<td>
|
||||
<a href="https://www.bilibili.com/video/BV1TJ7WzzEo6" target="_blank">
|
||||
<picture>
|
||||
<img alt="多指令任务" src="docs/images/demo11.png" /></picture>
|
||||
</a>
|
||||
<picture>
|
||||
<img alt="多指令任务" src="docs/images/demo11.png" />
|
||||
</picture>
|
||||
</a>
|
||||
</td>
|
||||
<td>
|
||||
<a href="https://www.bilibili.com/video/BV1VC96Y5EMH" target="_blank">
|
||||
<picture>
|
||||
<img alt="播放音乐" src="docs/images/demo7.png" />
|
||||
</picture>
|
||||
</a>
|
||||
</td>
|
||||
<td>
|
||||
<a href="https://www.bilibili.com/video/BV1Z8XuYZEAS" target="_blank">
|
||||
<picture>
|
||||
<img alt="天气插件" src="docs/images/demo8.png" />
|
||||
</picture>
|
||||
</a>
|
||||
</td>
|
||||
</tr>
|
||||
<tr>
|
||||
<td>
|
||||
<a href="https://www.bilibili.com/video/BV1ZQKUzYExM" target="_blank">
|
||||
<picture>
|
||||
<img alt="MCP接入点" src="docs/images/demo13.png" /></picture>
|
||||
</a>
|
||||
<a href="https://www.bilibili.com/video/BV12J7WzBEaH" target="_blank">
|
||||
<picture>
|
||||
<img alt="实时打断" src="docs/images/demo10.png" />
|
||||
</picture>
|
||||
</a>
|
||||
</td>
|
||||
<td>
|
||||
<a href="https://www.bilibili.com/video/BV1zUW5zJEkq" target="_blank">
|
||||
<picture>
|
||||
<img alt="MQTT指令下发" src="docs/images/demo4.png" /></picture>
|
||||
</a>
|
||||
<a href="https://www.bilibili.com/video/BV1Co76z7EvK" target="_blank">
|
||||
<picture>
|
||||
<img alt="拍照识物品" src="docs/images/demo12.png" />
|
||||
</picture>
|
||||
</a>
|
||||
</td>
|
||||
<td>
|
||||
<a href="https://www.bilibili.com/video/BV1Exu3zqEDe" target="_blank">
|
||||
<picture>
|
||||
<img alt="声纹识别" src="docs/images/demo14.png" /></picture>
|
||||
</a>
|
||||
<a href="https://www.bilibili.com/video/BV1CDKWemEU6" target="_blank">
|
||||
<picture>
|
||||
<img alt="自定义音色" src="docs/images/demo2.png" />
|
||||
</picture>
|
||||
</a>
|
||||
</td>
|
||||
<td>
|
||||
<a href="https://www.bilibili.com/video/BV1CDKWemEU6" target="_blank">
|
||||
<picture>
|
||||
<img alt="自定义音色" src="docs/images/demo2.png" /></picture>
|
||||
</a>
|
||||
<a href="https://www.bilibili.com/video/BV12yA2egEaC" target="_blank">
|
||||
<picture>
|
||||
<img alt="使用粤语交流" src="docs/images/demo3.png" />
|
||||
</picture>
|
||||
</a>
|
||||
</td>
|
||||
<td>
|
||||
<a href="https://www.bilibili.com/video/BV12yA2egEaC" target="_blank">
|
||||
<picture>
|
||||
<img alt="使用粤语交流" src="docs/images/demo3.png" /></picture>
|
||||
</a>
|
||||
<a href="https://www.bilibili.com/video/BV17LXWYvENb" target="_blank">
|
||||
<picture>
|
||||
<img alt="播报新闻" src="docs/images/demo0.png" />
|
||||
</picture>
|
||||
</a>
|
||||
</td>
|
||||
</tr>
|
||||
</table>
|
||||
@@ -211,7 +226,7 @@ Websocket接口地址: wss://2662r3426b.vicp.fun/xiaozhi/v1/
|
||||
|
||||
| 工具名称 | 位置 | 使用方法 | 功能说明 |
|
||||
|:---:|:---|:---:|:---:|
|
||||
| 音频交互测试工具 | main》digital-human》index.html | 在 `main/digital-human` 执行 `python start.py` 后访问 `http://127.0.0.1:8006/index.html` | 测试音频播放和接收功能，验证Python端音频处理是否正常 |
|
||||
| 音频交互测试工具 | main》xiaozhi-server》test》test_page.html | 使用谷歌浏览器直接打开 | 测试音频播放和接收功能，验证Python端音频处理是否正常 |
|
||||
| 模型响应测试工具 | main》xiaozhi-server》performance_tester.py | 执行 `python performance_tester.py` | 测试ASR(语音识别)、LLM(大模型)、VLLM(视觉模型)、TTS(语音合成)三个核心模块的响应速度 |
|
||||
|
||||
> 💡 提示：测试模型速度时，只会测试配置了密钥的模型。
|
||||
|
||||
@@ -1,4 +1,4 @@
|
||||
[](https://github.com/xinnan-tech/xiaozhi-esp32-server)
|
||||
[](https://github.com/xinnan-tech/xiaozhi-esp32-server)
|
||||
|
||||
<h1 align="center">Xiaozhi Backend-Service xiaozhi-esp32-server</h1>
|
||||
|
||||
@@ -10,14 +10,14 @@ Unterstützt MQTT+UDP-Protokoll, Websocket-Protokoll, MCP-Endpunkte und Stimmabd
|
||||
</p>
|
||||
|
||||
<p align="center">
|
||||
<a href="../FAQ.md">Häufige Fragen</a>
|
||||
<a href="./docs/FAQ.md">Häufige Fragen</a>
|
||||
· <a href="https://github.com/xinnan-tech/xiaozhi-esp32-server/issues">Probleme melden</a>
|
||||
· <a href="../../README.md#%E9%83%A8%E7%BD%B2%E6%96%87%E6%A1%A3">Deployment-Dokumentation</a>
|
||||
· <a href="./README.md#%E9%83%A8%E7%BD%B2%E6%96%87%E6%A1%A3">Deployment-Dokumentation</a>
|
||||
· <a href="https://github.com/xinnan-tech/xiaozhi-esp32-server/releases">Release-Hinweise</a>
|
||||
</p>
|
||||
|
||||
<p align="center">
|
||||
<a href="../../README.md"><img alt="简体中文版自述文件" src="https://img.shields.io/badge/简体中文-DFE0E5"></a>
|
||||
<a href="./README.md"><img alt="简体中文版自述文件" src="https://img.shields.io/badge/简体中文-DFE0E5"></a>
|
||||
<a href="./README_en.md"><img alt="README in English" src="https://img.shields.io/badge/English-DFE0E5"></a>
|
||||
<a href="./README_vi.md"><img alt="Tiếng Việt" src="https://img.shields.io/badge/Tiếng Việt-DFE0E5"></a>
|
||||
<a href="./README_de.md"><img alt="Deutsch" src="https://img.shields.io/badge/Deutsch-DBEDFA"></a>
|
||||
@@ -38,7 +38,7 @@ Geleitet vom Team von Professor Siyuan Liu (South China University of Technology
|
||||
</br>
|
||||
刘思源教授团队主导研发(华南理工大学)
|
||||
</br>
|
||||
<img src="../images/hnlg.jpg" alt="South China University of Technology" width="50%">
|
||||
<img src="./docs/images/hnlg.jpg" alt="South China University of Technology" width="50%">
|
||||
</p>
|
||||
|
||||
---
|
||||
@@ -52,98 +52,113 @@ Möchten Sie die Nutzungseffekte sehen? Klicken Sie auf die Videos unten 🎥
|
||||
<table>
|
||||
<tr>
|
||||
<td>
|
||||
<a href="https://www.bilibili.com/video/BV1FMFyejExX" target="_blank">
|
||||
<picture>
|
||||
<img alt="响应速度感受" src="docs/images/demo9.png" /></picture>
|
||||
</a>
|
||||
<a href="https://www.bilibili.com/video/BV1FMFyejExX" target="_blank">
|
||||
<picture>
|
||||
<img alt="响应速度感受" src="docs/images/demo9.png" />
|
||||
</picture>
|
||||
</a>
|
||||
</td>
|
||||
<td>
|
||||
<a href="https://www.bilibili.com/video/BV1vchQzaEse" target="_blank">
|
||||
<picture>
|
||||
<img alt="速度优化秘诀" src="docs/images/demo6.png" /></picture>
|
||||
</a>
|
||||
<a href="https://www.bilibili.com/video/BV1vchQzaEse" target="_blank">
|
||||
<picture>
|
||||
<img alt="速度优化秘诀" src="docs/images/demo6.png" />
|
||||
</picture>
|
||||
</a>
|
||||
</td>
|
||||
<td>
|
||||
<a href="https://www.bilibili.com/video/BV1WEcxzFEAT" target="_blank">
|
||||
<picture>
|
||||
<img alt="小智数字人 支持语音唤醒" src="docs/images/demo8.png" /></picture>
|
||||
</a>
|
||||
<a href="https://www.bilibili.com/video/BV1C1tCzUEZh" target="_blank">
|
||||
<picture>
|
||||
<img alt="复杂医疗场景" src="docs/images/demo1.png" />
|
||||
</picture>
|
||||
</a>
|
||||
</td>
|
||||
<td>
|
||||
<a href="https://www.bilibili.com/video/BV1CKVz6UEuB" target="_blank">
|
||||
<picture>
|
||||
<img alt="设备呼叫设备，打电话" src="docs/images/demo0.png" /></picture>
|
||||
</a>
|
||||
<a href="https://www.bilibili.com/video/BV1zUW5zJEkq" target="_blank">
|
||||
<picture>
|
||||
<img alt="MQTT指令下发" src="docs/images/demo4.png" />
|
||||
</picture>
|
||||
</a>
|
||||
</td>
|
||||
<td>
|
||||
<a href="https://www.bilibili.com/video/BV1C1tCzUEZh" target="_blank">
|
||||
<picture>
|
||||
<img alt="复杂医疗场景" src="docs/images/demo1.png" /></picture>
|
||||
</a>
|
||||
<a href="https://www.bilibili.com/video/BV1Exu3zqEDe" target="_blank">
|
||||
<picture>
|
||||
<img alt="声纹识别" src="docs/images/demo14.png" />
|
||||
</picture>
|
||||
</a>
|
||||
</td>
|
||||
</tr>
|
||||
<tr>
|
||||
<td>
|
||||
<a href="https://www.bilibili.com/video/BV1VC96Y5EMH" target="_blank">
|
||||
<picture>
|
||||
<img alt="播放音乐查询天气播报新闻" src="docs/images/demo7.png" /></picture>
|
||||
</a>
|
||||
<a href="https://www.bilibili.com/video/BV1pNXWYGEx1" target="_blank">
|
||||
<picture>
|
||||
<img alt="控制家电开关" src="docs/images/demo5.png" />
|
||||
</picture>
|
||||
</a>
|
||||
</td>
|
||||
<td>
|
||||
<a href="https://www.bilibili.com/video/BV12J7WzBEaH" target="_blank">
|
||||
<picture>
|
||||
<img alt="实时打断" src="docs/images/demo10.png" /></picture>
|
||||
</a>
|
||||
</td>
|
||||
<td>
|
||||
<a href="https://www.bilibili.com/video/BV1Co76z7EvK" target="_blank">
|
||||
<picture>
|
||||
<img alt="拍照识物品" src="docs/images/demo12.png" /></picture>
|
||||
</a>
|
||||
</td>
|
||||
<td>
|
||||
<a href="https://www.bilibili.com/video/BV1pNXWYGEx1" target="_blank">
|
||||
<picture>
|
||||
<img alt="控制家电开关" src="docs/images/demo5.png" /></picture>
|
||||
</a>
|
||||
<a href="https://www.bilibili.com/video/BV1ZQKUzYExM" target="_blank">
|
||||
<picture>
|
||||
<img alt="MCP接入点" src="docs/images/demo13.png" />
|
||||
</picture>
|
||||
</a>
|
||||
</td>
|
||||
<td>
|
||||
<a href="https://www.bilibili.com/video/BV1TJ7WzzEo6" target="_blank">
|
||||
<picture>
|
||||
<img alt="多指令任务" src="docs/images/demo11.png" /></picture>
|
||||
</a>
|
||||
<picture>
|
||||
<img alt="多指令任务" src="docs/images/demo11.png" />
|
||||
</picture>
|
||||
</a>
|
||||
</td>
|
||||
<td>
|
||||
<a href="https://www.bilibili.com/video/BV1VC96Y5EMH" target="_blank">
|
||||
<picture>
|
||||
<img alt="播放音乐" src="docs/images/demo7.png" />
|
||||
</picture>
|
||||
</a>
|
||||
</td>
|
||||
<td>
|
||||
<a href="https://www.bilibili.com/video/BV1Z8XuYZEAS" target="_blank">
|
||||
<picture>
|
||||
<img alt="天气插件" src="docs/images/demo8.png" />
|
||||
</picture>
|
||||
</a>
|
||||
</td>
|
||||
</tr>
|
||||
<tr>
|
||||
<td>
|
||||
<a href="https://www.bilibili.com/video/BV1ZQKUzYExM" target="_blank">
|
||||
<picture>
|
||||
<img alt="MCP接入点" src="docs/images/demo13.png" /></picture>
|
||||
</a>
|
||||
<a href="https://www.bilibili.com/video/BV12J7WzBEaH" target="_blank">
|
||||
<picture>
|
||||
<img alt="实时打断" src="docs/images/demo10.png" />
|
||||
</picture>
|
||||
</a>
|
||||
</td>
|
||||
<td>
|
||||
<a href="https://www.bilibili.com/video/BV1zUW5zJEkq" target="_blank">
|
||||
<picture>
|
||||
<img alt="MQTT指令下发" src="docs/images/demo4.png" /></picture>
|
||||
</a>
|
||||
<a href="https://www.bilibili.com/video/BV1Co76z7EvK" target="_blank">
|
||||
<picture>
|
||||
<img alt="拍照识物品" src="docs/images/demo12.png" />
|
||||
</picture>
|
||||
</a>
|
||||
</td>
|
||||
<td>
|
||||
<a href="https://www.bilibili.com/video/BV1Exu3zqEDe" target="_blank">
|
||||
<picture>
|
||||
<img alt="声纹识别" src="docs/images/demo14.png" /></picture>
|
||||
</a>
|
||||
<a href="https://www.bilibili.com/video/BV1CDKWemEU6" target="_blank">
|
||||
<picture>
|
||||
<img alt="自定义音色" src="docs/images/demo2.png" />
|
||||
</picture>
|
||||
</a>
|
||||
</td>
|
||||
<td>
|
||||
<a href="https://www.bilibili.com/video/BV1CDKWemEU6" target="_blank">
|
||||
<picture>
|
||||
<img alt="自定义音色" src="docs/images/demo2.png" /></picture>
|
||||
</a>
|
||||
<a href="https://www.bilibili.com/video/BV12yA2egEaC" target="_blank">
|
||||
<picture>
|
||||
<img alt="使用粤语交流" src="docs/images/demo3.png" />
|
||||
</picture>
|
||||
</a>
|
||||
</td>
|
||||
<td>
|
||||
<a href="https://www.bilibili.com/video/BV12yA2egEaC" target="_blank">
|
||||
<picture>
|
||||
<img alt="使用粤语交流" src="docs/images/demo3.png" /></picture>
|
||||
</a>
|
||||
<a href="https://www.bilibili.com/video/BV17LXWYvENb" target="_blank">
|
||||
<picture>
|
||||
<img alt="播报新闻" src="docs/images/demo0.png" />
|
||||
</picture>
|
||||
</a>
|
||||
</td>
|
||||
</tr>
|
||||
</table>
|
||||
@@ -160,17 +175,17 @@ Möchten Sie die Nutzungseffekte sehen? Klicken Sie auf die Videos unten 🎥
|
||||
|
||||
## Deployment-Dokumentation
|
||||
|
||||
|
||||
|
||||
|
||||
Dieses Projekt bietet zwei Bereitstellungsmethoden. Bitte wählen Sie basierend auf Ihren spezifischen Anforderungen:
|
||||
|
||||
#### 🚀 Auswahl der Bereitstellungsmethode
|
||||
| Bereitstellungsmethode | Funktionen | Anwendungsszenarien | Deployment-Dokumente | Konfigurationsanforderungen | Video-Tutorials |
|
||||
|---------|------|---------|---------|---------|---------|
|
||||
| **Vereinfachte Installation** | Intelligenter Dialog, Einzel-Agenten-Verwaltung | Umgebungen mit geringer Konfiguration, Daten in Konfigurationsdateien gespeichert, keine Datenbank erforderlich | [①Docker-Version](../Deployment.md#%E6%96%B9%E5%BC%8F%E4%B8%80docker%E5%8F%AA%E8%BF%90%E8%A1%8Cserver) / [②Quellcode-Deployment](../Deployment.md#%E6%96%B9%E5%BC%8F%E4%BA%8C%E6%9C%AC%E5%9C%B0%E6%BA%90%E7%A0%81%E5%8F%AA%E8%BF%90%E8%A1%8Cserver)| 2 Kerne 4GB bei Verwendung von `FunASR`, 2 Kerne 2GB bei allen APIs | - |
|
||||
| **Vollständige Modulinstallation** | Intelligenter Dialog, Mehrbenutzerverwaltung, Mehr-Agenten-Verwaltung, Intelligente Steuerkonsole-Bedienung | Vollständige Funktionserfahrung, Daten in Datenbank gespeichert |[①Docker-Version](../Deployment_all.md#%E6%96%B9%E5%BC%8F%E4%B8%80docker%E8%BF%90%E8%A1%8C%E5%85%A8%E6%A8%A1%E5%9D%97) / [②Quellcode-Deployment](../Deployment_all.md#%E6%96%B9%E5%BC%8F%E4%BA%8C%E6%9C%AC%E5%9C%B0%E6%BA%90%E7%A0%81%E8%BF%90%E8%A1%8C%E5%85%A8%E6%A8%A1%E5%9D%97) / [③Quellcode-Deployment Auto-Update-Tutorial](../dev-ops-integration.md) | 4 Kerne 8GB bei Verwendung von `FunASR`, 2 Kerne 4GB bei allen APIs| [Video-Tutorial für lokalen Quellcode-Start](https://www.bilibili.com/video/BV1wBJhz4Ewe) |
|
||||
| **Vereinfachte Installation** | Intelligenter Dialog, Einzel-Agenten-Verwaltung | Umgebungen mit geringer Konfiguration, Daten in Konfigurationsdateien gespeichert, keine Datenbank erforderlich | [①Docker-Version](./docs/Deployment.md#%E6%96%B9%E5%BC%8F%E4%B8%80docker%E5%8F%AA%E8%BF%90%E8%A1%8Cserver) / [②Quellcode-Deployment](./docs/Deployment.md#%E6%96%B9%E5%BC%8F%E4%BA%8C%E6%9C%AC%E5%9C%B0%E6%BA%90%E7%A0%81%E5%8F%AA%E8%BF%90%E8%A1%8Cserver)| 2 Kerne 4GB bei Verwendung von `FunASR`, 2 Kerne 2GB bei allen APIs | - |
|
||||
| **Vollständige Modulinstallation** | Intelligenter Dialog, Mehrbenutzerverwaltung, Mehr-Agenten-Verwaltung, Intelligente Steuerkonsole-Bedienung | Vollständige Funktionserfahrung, Daten in Datenbank gespeichert |[①Docker-Version](./docs/Deployment_all.md#%E6%96%B9%E5%BC%8F%E4%B8%80docker%E8%BF%90%E8%A1%8C%E5%85%A8%E6%A8%A1%E5%9D%97) / [②Quellcode-Deployment](./docs/Deployment_all.md#%E6%96%B9%E5%BC%8F%E4%BA%8C%E6%9C%AC%E5%9C%B0%E6%BA%90%E7%A0%81%E8%BF%90%E8%A1%8C%E5%85%A8%E6%A8%A1%E5%9D%97) / [③Quellcode-Deployment Auto-Update-Tutorial](./docs/dev-ops-integration.md) | 4 Kerne 8GB bei Verwendung von `FunASR`, 2 Kerne 4GB bei allen APIs| [Video-Tutorial für lokalen Quellcode-Start](https://www.bilibili.com/video/BV1wBJhz4Ewe) |
|
||||
|
||||
Häufige Fragen und entsprechende Tutorials finden Sie unter [diesem Link](../FAQ.md)
|
||||
Häufige Fragen und entsprechende Tutorials finden Sie unter [diesem Link](./docs/FAQ.md)
|
||||
|
||||
> 💡 Hinweis: Unten ist eine Testplattform, die mit dem neuesten Code bereitgestellt wurde. Sie können bei Bedarf brennen und testen. Gleichzeitige Benutzer: 6, Daten werden täglich gelöscht.
|
||||
|
||||
@@ -209,7 +224,7 @@ Dieses Projekt bietet die folgenden Testwerkzeuge, um Ihnen bei der Überprüfun
|
||||
|
||||
| Werkzeugname | Standort | Verwendungsmethode | Funktionsbeschreibung |
|
||||
|:---:|:---|:---:|:---:|
|
||||
| Audio-Interaktionstesttool | main》digital-human》index.html | In `main/digital-human` `python start.py` ausführen und dann `http://127.0.0.1:8006/index.html` öffnen | Testet Audio-Wiedergabe- und Empfangsfunktionen, überprüft, ob die Python-seitige Audioverarbeitung normal ist |
|
||||
| Audio-Interaktionstesttool | main》xiaozhi-server》test》test_page.html | Direkt mit Google Chrome öffnen | Testet Audio-Wiedergabe- und Empfangsfunktionen, überprüft, ob die Python-seitige Audioverarbeitung normal ist |
|
||||
| Modell-Reaktionstesttool | main》xiaozhi-server》performance_tester.py | Ausführen `python performance_tester.py` | Testet die Reaktionsgeschwindigkeit von ASR (Spracherkennung), LLM (großes Modell), VLLM (Vision-Modell), TTS (Sprachsynthese) drei Kernmodulen |
|
||||
|
||||
> 💡 Hinweis: Beim Testen der Modellgeschwindigkeit werden nur Modelle mit konfigurierten Schlüsseln getestet.
|
||||
@@ -217,7 +232,7 @@ Dieses Projekt bietet die folgenden Testwerkzeuge, um Ihnen bei der Überprüfun
|
||||
---
|
||||
## Funktionsliste ✨
|
||||
### Implementiert ✅
|
||||
|
||||
|
||||
| Funktionsmodul | Beschreibung |
|
||||
|:---:|:---|
|
||||
| Kernarchitektur | Basierend auf [MQTT+UDP-Gateway](https://github.com/xinnan-tech/xiaozhi-esp32-server/blob/main/docs/mqtt-gateway-integration.md), WebSocket und HTTP-Servern, bietet vollständiges Konsolenverwaltungs- und Authentifizierungssystem |
|
||||
@@ -237,9 +252,9 @@ Dieses Projekt bietet die folgenden Testwerkzeuge, um Ihnen bei der Überprüfun
|
||||
|
||||
### In Entwicklung 🚧
|
||||
|
||||
Um über spezifische Entwicklungsplanfortschritte zu erfahren, [klicken Sie hier](https://github.com/users/xinnan-tech/projects/3). Häufige Fragen und entsprechende Tutorials finden Sie unter [diesem Link](../FAQ.md)
|
||||
Um über spezifische Entwicklungsplanfortschritte zu erfahren, [klicken Sie hier](https://github.com/users/xinnan-tech/projects/3). Häufige Fragen und entsprechende Tutorials finden Sie unter [diesem Link](./docs/FAQ.md)
|
||||
|
||||
Wenn Sie ein Softwareentwickler sind, finden Sie hier einen [Offenen Brief an Entwickler](../contributor_open_letter.md). Willkommen beim Beitritt!
|
||||
Wenn Sie ein Softwareentwickler sind, finden Sie hier einen [Offenen Brief an Entwickler](docs/contributor_open_letter.md). Willkommen beim Beitritt!
|
||||
|
||||
---
|
||||
|
||||
@@ -314,7 +329,7 @@ Tatsächlich kann jedes VLLM, das OpenAI-Schnittstellenaufrufe unterstützt, int
|
||||
| Typ | Plattformname | Verwendungsmethode | Preismodell | Hinweise |
|
||||
|:------:|:---------------:|:----:|:---------:|:--:|
|
||||
| Memory | mem0ai | Schnittstellenaufrufe | 1000 Mal/Monat Kontingent | |
|
||||
| Memory | [powermem](../powermem-integration.md) | Lokale Zusammenfassung | Abhängig von LLM und DB | OceanBase Open Source, unterstützt intelligente Abfrage |
|
||||
| Memory | [powermem](./docs/powermem-integration.md) | Lokale Zusammenfassung | Abhängig von LLM und DB | OceanBase Open Source, unterstützt intelligente Abfrage |
|
||||
| Memory | mem_local_short | Lokale Zusammenfassung | Kostenlos | |
|
||||
| Memory | nomem | Kein Gedächtnismodus | Kostenlos | |
|
||||
|
||||
@@ -342,13 +357,13 @@ Tatsächlich kann jedes VLLM, das OpenAI-Schnittstellenaufrufe unterstützt, int
|
||||
|
||||
| Logo | Projekt/Unternehmen | Beschreibung |
|
||||
|:---:|:---:|:---|
|
||||
| <img src="../images/logo_bailing.png" width="160"> | [Bailing Voice Dialogue Robot](https://github.com/wwbin2017/bailing) | Dieses Projekt wurde von [Bailing Voice Dialogue Robot](https://github.com/wwbin2017/bailing) inspiriert und auf dessen Basis implementiert |
|
||||
| <img src="../images/logo_tenclass.png" width="160"> | [Tenclass](https://www.tenclass.com/) | Dank an [Tenclass](https://www.tenclass.com/) für die Formulierung von Standardkommunikationsprotokollen, Multi-Geräte-Kompatibilitätslösungen und High-Concurrency-Szenario-Praxisdemonstrationen für das Xiaozhi-Ökosystem; für die Bereitstellung vollständiger technischer Dokumentationsunterstützung für dieses Projekt |
|
||||
| <img src="../images/logo_xuanfeng.png" width="160"> | [Xuanfeng Technology](https://github.com/Eric0308) | Dank an [Xuanfeng Technology](https://github.com/Eric0308) für den Beitrag des Funktionsaufruf-Frameworks, des MCP-Kommunikationsprotokolls und der plugin-basierten Aufrufmechanismus-Implementierungscode. Durch standardisiertes Befehlsplanungssystem und dynamische Erweiterungsfähigkeiten wird die Interaktionseffizienz und funktionale Erweiterbarkeit von Frontend-Geräten (IoT) erheblich verbessert |
|
||||
| <img src="../images/logo_junsen.png" width="160"> | [huangjunsen](https://github.com/huangjunsen0406) | Dank an [huangjunsen](https://github.com/huangjunsen0406) für den Beitrag des `Smart Control Console Mobile`-Moduls, das eine effiziente Steuerung und Echtzeit-Interaktion über mobile Geräte ermöglicht und die Betriebsbequemlichkeit und Verwaltungseffizienz des Systems in mobilen Szenarien erheblich verbessert |
|
||||
| <img src="../images/logo_huiyuan.png" width="160"> | [Huiyuan Design](http://ui.kwd988.net/) | Dank an [Huiyuan Design](http://ui.kwd988.net/) für die Bereitstellung professioneller visueller Lösungen für dieses Projekt, unter Verwendung ihrer Design-Praxiserfahrung im Dienst von über tausend Unternehmen, um die Produktbenutzererfahrung dieses Projekts zu stärken |
|
||||
| <img src="../images/logo_qinren.png" width="160"> | [Xi'an Qinren Information Technology](https://www.029app.com/) | Dank an [Xi'an Qinren Information Technology](https://www.029app.com/) für die Vertiefung des visuellen Systems dieses Projekts und die Sicherstellung der Konsistenz und Erweiterbarkeit des Gesamtdesignstils in Multi-Szenario-Anwendungen |
|
||||
| <img src="../images/logo_contributors.png" width="160"> | [Code-Mitwirkende](https://github.com/xinnan-tech/xiaozhi-esp32-server/graphs/contributors) | Dank an [alle Code-Mitwirkenden](https://github.com/xinnan-tech/xiaozhi-esp32-server/graphs/contributors), Ihre Bemühungen haben das Projekt robuster und leistungsfähiger gemacht. |
|
||||
| <img src="./docs/images/logo_bailing.png" width="160"> | [Bailing Voice Dialogue Robot](https://github.com/wwbin2017/bailing) | Dieses Projekt wurde von [Bailing Voice Dialogue Robot](https://github.com/wwbin2017/bailing) inspiriert und auf dessen Basis implementiert |
|
||||
| <img src="./docs/images/logo_tenclass.png" width="160"> | [Tenclass](https://www.tenclass.com/) | Dank an [Tenclass](https://www.tenclass.com/) für die Formulierung von Standardkommunikationsprotokollen, Multi-Geräte-Kompatibilitätslösungen und High-Concurrency-Szenario-Praxisdemonstrationen für das Xiaozhi-Ökosystem; für die Bereitstellung vollständiger technischer Dokumentationsunterstützung für dieses Projekt |
|
||||
| <img src="./docs/images/logo_xuanfeng.png" width="160"> | [Xuanfeng Technology](https://github.com/Eric0308) | Dank an [Xuanfeng Technology](https://github.com/Eric0308) für den Beitrag des Funktionsaufruf-Frameworks, des MCP-Kommunikationsprotokolls und der plugin-basierten Aufrufmechanismus-Implementierungscode. Durch standardisiertes Befehlsplanungssystem und dynamische Erweiterungsfähigkeiten wird die Interaktionseffizienz und funktionale Erweiterbarkeit von Frontend-Geräten (IoT) erheblich verbessert |
|
||||
| <img src="./docs/images/logo_junsen.png" width="160"> | [huangjunsen](https://github.com/huangjunsen0406) | Dank an [huangjunsen](https://github.com/huangjunsen0406) für den Beitrag des `Smart Control Console Mobile`-Moduls, das eine effiziente Steuerung und Echtzeit-Interaktion über mobile Geräte ermöglicht und die Betriebsbequemlichkeit und Verwaltungseffizienz des Systems in mobilen Szenarien erheblich verbessert |
|
||||
| <img src="./docs/images/logo_huiyuan.png" width="160"> | [Huiyuan Design](http://ui.kwd988.net/) | Dank an [Huiyuan Design](http://ui.kwd988.net/) für die Bereitstellung professioneller visueller Lösungen für dieses Projekt, unter Verwendung ihrer Design-Praxiserfahrung im Dienst von über tausend Unternehmen, um die Produktbenutzererfahrung dieses Projekts zu stärken |
|
||||
| <img src="./docs/images/logo_qinren.png" width="160"> | [Xi'an Qinren Information Technology](https://www.029app.com/) | Dank an [Xi'an Qinren Information Technology](https://www.029app.com/) für die Vertiefung des visuellen Systems dieses Projekts und die Sicherstellung der Konsistenz und Erweiterbarkeit des Gesamtdesignstils in Multi-Szenario-Anwendungen |
|
||||
| <img src="./docs/images/logo_contributors.png" width="160"> | [Code-Mitwirkende](https://github.com/xinnan-tech/xiaozhi-esp32-server/graphs/contributors) | Dank an [alle Code-Mitwirkenden](https://github.com/xinnan-tech/xiaozhi-esp32-server/graphs/contributors), Ihre Bemühungen haben das Projekt robuster und leistungsfähiger gemacht. |
|
||||
|
||||
|
||||
<a href="https://star-history.com/#xinnan-tech/xiaozhi-esp32-server&Date">
|
||||
@@ -1,4 +1,4 @@
|
||||
[](https://github.com/xinnan-tech/xiaozhi-esp32-server)
|
||||
[](https://github.com/xinnan-tech/xiaozhi-esp32-server)
|
||||
|
||||
<h1 align="center">Xiaozhi Backend Service xiaozhi-esp32-server</h1>
|
||||
|
||||
@@ -10,14 +10,14 @@ Support for MQTT+UDP protocol, Websocket protocol, MCP access point, voiceprint
|
||||
</p>
|
||||
|
||||
<p align="center">
|
||||
<a href="../FAQ.md">FAQ</a>
|
||||
<a href="./docs/FAQ.md">FAQ</a>
|
||||
· <a href="https://github.com/xinnan-tech/xiaozhi-esp32-server/issues">Report Issues</a>
|
||||
· <a href="../../README.md#%E9%83%A8%E7%BD%B2%E6%96%87%E6%A1%A3">Deployment Docs</a>
|
||||
· <a href="./README.md#%E9%83%A8%E7%BD%B2%E6%96%87%E6%A1%A3">Deployment Docs</a>
|
||||
· <a href="https://github.com/xinnan-tech/xiaozhi-esp32-server/releases">Release Notes</a>
|
||||
</p>
|
||||
|
||||
<p align="center">
|
||||
<a href="../../README.md"><img alt="简体中文版自述文件" src="https://img.shields.io/badge/简体中文-DFE0E5"></a>
|
||||
<a href="./README.md"><img alt="简体中文版自述文件" src="https://img.shields.io/badge/简体中文-DFE0E5"></a>
|
||||
<a href="./README_en.md"><img alt="README in English" src="https://img.shields.io/badge/English-DBEDFA"></a>
|
||||
<a href="./README_vi.md"><img alt="Tiếng Việt" src="https://img.shields.io/badge/Tiếng Việt-DFE0E5"></a>
|
||||
<a href="./README_de.md"><img alt="Deutsch" src="https://img.shields.io/badge/Deutsch-DFE0E5"></a>
|
||||
@@ -38,7 +38,7 @@ Spearheaded by Professor Siyuan Liu's Team (South China University of Technology
|
||||
</br>
|
||||
刘思源教授团队主导研发（华南理工大学）
|
||||
</br>
|
||||
<img src="../images/hnlg.jpg" alt="South China University of Technology" width="50%">
|
||||
<img src="./docs/images/hnlg.jpg" alt="South China University of Technology" width="50%">
|
||||
</p>
|
||||
|
||||
---
|
||||
@@ -52,98 +52,113 @@ Want to see the usage effects? Click the videos below 🎥
|
||||
<table>
|
||||
<tr>
|
||||
<td>
|
||||
<a href="https://www.bilibili.com/video/BV1FMFyejExX" target="_blank">
|
||||
<picture>
|
||||
<img alt="响应速度感受" src="docs/images/demo9.png" /></picture>
|
||||
</a>
|
||||
<a href="https://www.bilibili.com/video/BV1FMFyejExX" target="_blank">
|
||||
<picture>
|
||||
<img alt="响应速度感受" src="docs/images/demo9.png" />
|
||||
</picture>
|
||||
</a>
|
||||
</td>
|
||||
<td>
|
||||
<a href="https://www.bilibili.com/video/BV1vchQzaEse" target="_blank">
|
||||
<picture>
|
||||
<img alt="速度优化秘诀" src="docs/images/demo6.png" /></picture>
|
||||
</a>
|
||||
<a href="https://www.bilibili.com/video/BV1vchQzaEse" target="_blank">
|
||||
<picture>
|
||||
<img alt="速度优化秘诀" src="docs/images/demo6.png" />
|
||||
</picture>
|
||||
</a>
|
||||
</td>
|
||||
<td>
|
||||
<a href="https://www.bilibili.com/video/BV1WEcxzFEAT" target="_blank">
|
||||
<picture>
|
||||
<img alt="小智数字人 支持语音唤醒" src="docs/images/demo8.png" /></picture>
|
||||
</a>
|
||||
<a href="https://www.bilibili.com/video/BV1C1tCzUEZh" target="_blank">
|
||||
<picture>
|
||||
<img alt="复杂医疗场景" src="docs/images/demo1.png" />
|
||||
</picture>
|
||||
</a>
|
||||
</td>
|
||||
<td>
|
||||
<a href="https://www.bilibili.com/video/BV1CKVz6UEuB" target="_blank">
|
||||
<picture>
|
||||
<img alt="设备呼叫设备，打电话" src="docs/images/demo0.png" /></picture>
|
||||
</a>
|
||||
<a href="https://www.bilibili.com/video/BV1zUW5zJEkq" target="_blank">
|
||||
<picture>
|
||||
<img alt="MQTT指令下发" src="docs/images/demo4.png" />
|
||||
</picture>
|
||||
</a>
|
||||
</td>
|
||||
<td>
|
||||
<a href="https://www.bilibili.com/video/BV1C1tCzUEZh" target="_blank">
|
||||
<picture>
|
||||
<img alt="复杂医疗场景" src="docs/images/demo1.png" /></picture>
|
||||
</a>
|
||||
<a href="https://www.bilibili.com/video/BV1Exu3zqEDe" target="_blank">
|
||||
<picture>
|
||||
<img alt="声纹识别" src="docs/images/demo14.png" />
|
||||
</picture>
|
||||
</a>
|
||||
</td>
|
||||
</tr>
|
||||
<tr>
|
||||
<td>
|
||||
<a href="https://www.bilibili.com/video/BV1VC96Y5EMH" target="_blank">
|
||||
<picture>
|
||||
<img alt="播放音乐查询天气播报新闻" src="docs/images/demo7.png" /></picture>
|
||||
</a>
|
||||
<a href="https://www.bilibili.com/video/BV1pNXWYGEx1" target="_blank">
|
||||
<picture>
|
||||
<img alt="控制家电开关" src="docs/images/demo5.png" />
|
||||
</picture>
|
||||
</a>
|
||||
</td>
|
||||
<td>
|
||||
<a href="https://www.bilibili.com/video/BV12J7WzBEaH" target="_blank">
|
||||
<picture>
|
||||
<img alt="实时打断" src="docs/images/demo10.png" /></picture>
|
||||
</a>
|
||||
</td>
|
||||
<td>
|
||||
<a href="https://www.bilibili.com/video/BV1Co76z7EvK" target="_blank">
|
||||
<picture>
|
||||
<img alt="拍照识物品" src="docs/images/demo12.png" /></picture>
|
||||
</a>
|
||||
</td>
|
||||
<td>
|
||||
<a href="https://www.bilibili.com/video/BV1pNXWYGEx1" target="_blank">
|
||||
<picture>
|
||||
<img alt="控制家电开关" src="docs/images/demo5.png" /></picture>
|
||||
</a>
|
||||
<a href="https://www.bilibili.com/video/BV1ZQKUzYExM" target="_blank">
|
||||
<picture>
|
||||
<img alt="MCP接入点" src="docs/images/demo13.png" />
|
||||
</picture>
|
||||
</a>
|
||||
</td>
|
||||
<td>
|
||||
<a href="https://www.bilibili.com/video/BV1TJ7WzzEo6" target="_blank">
|
||||
<picture>
|
||||
<img alt="多指令任务" src="docs/images/demo11.png" /></picture>
|
||||
</a>
|
||||
<picture>
|
||||
<img alt="多指令任务" src="docs/images/demo11.png" />
|
||||
</picture>
|
||||
</a>
|
||||
</td>
|
||||
<td>
|
||||
<a href="https://www.bilibili.com/video/BV1VC96Y5EMH" target="_blank">
|
||||
<picture>
|
||||
<img alt="播放音乐" src="docs/images/demo7.png" />
|
||||
</picture>
|
||||
</a>
|
||||
</td>
|
||||
<td>
|
||||
<a href="https://www.bilibili.com/video/BV1Z8XuYZEAS" target="_blank">
|
||||
<picture>
|
||||
<img alt="天气插件" src="docs/images/demo8.png" />
|
||||
</picture>
|
||||
</a>
|
||||
</td>
|
||||
</tr>
|
||||
<tr>
|
||||
<td>
|
||||
<a href="https://www.bilibili.com/video/BV1ZQKUzYExM" target="_blank">
|
||||
<picture>
|
||||
<img alt="MCP接入点" src="docs/images/demo13.png" /></picture>
|
||||
</a>
|
||||
<a href="https://www.bilibili.com/video/BV12J7WzBEaH" target="_blank">
|
||||
<picture>
|
||||
<img alt="实时打断" src="docs/images/demo10.png" />
|
||||
</picture>
|
||||
</a>
|
||||
</td>
|
||||
<td>
|
||||
<a href="https://www.bilibili.com/video/BV1zUW5zJEkq" target="_blank">
|
||||
<picture>
|
||||
<img alt="MQTT指令下发" src="docs/images/demo4.png" /></picture>
|
||||
</a>
|
||||
<a href="https://www.bilibili.com/video/BV1Co76z7EvK" target="_blank">
|
||||
<picture>
|
||||
<img alt="拍照识物品" src="docs/images/demo12.png" />
|
||||
</picture>
|
||||
</a>
|
||||
</td>
|
||||
<td>
|
||||
<a href="https://www.bilibili.com/video/BV1Exu3zqEDe" target="_blank">
|
||||
<picture>
|
||||
<img alt="声纹识别" src="docs/images/demo14.png" /></picture>
|
||||
</a>
|
||||
<a href="https://www.bilibili.com/video/BV1CDKWemEU6" target="_blank">
|
||||
<picture>
|
||||
<img alt="自定义音色" src="docs/images/demo2.png" />
|
||||
</picture>
|
||||
</a>
|
||||
</td>
|
||||
<td>
|
||||
<a href="https://www.bilibili.com/video/BV1CDKWemEU6" target="_blank">
|
||||
<picture>
|
||||
<img alt="自定义音色" src="docs/images/demo2.png" /></picture>
|
||||
</a>
|
||||
<a href="https://www.bilibili.com/video/BV12yA2egEaC" target="_blank">
|
||||
<picture>
|
||||
<img alt="使用粤语交流" src="docs/images/demo3.png" />
|
||||
</picture>
|
||||
</a>
|
||||
</td>
|
||||
<td>
|
||||
<a href="https://www.bilibili.com/video/BV12yA2egEaC" target="_blank">
|
||||
<picture>
|
||||
<img alt="使用粤语交流" src="docs/images/demo3.png" /></picture>
|
||||
</a>
|
||||
<a href="https://www.bilibili.com/video/BV17LXWYvENb" target="_blank">
|
||||
<picture>
|
||||
<img alt="播报新闻" src="docs/images/demo0.png" />
|
||||
</picture>
|
||||
</a>
|
||||
</td>
|
||||
</tr>
|
||||
</table>
|
||||
@@ -160,17 +175,17 @@ Want to see the usage effects? Click the videos below 🎥
|
||||
|
||||
## Deployment Documentation
|
||||
|
||||
|
||||
|
||||
|
||||
This project provides two deployment methods. Please choose based on your specific needs:
|
||||
|
||||
#### 🚀 Deployment Method Selection
|
||||
| Deployment Method | Features | Applicable Scenarios | Deployment Docs | Configuration Requirements | Video Tutorials |
|
||||
|---------|------|---------|---------|---------|---------|
|
||||
| **Simplified Installation** | Intelligent dialogue, single agent management | Low-configuration environments, data stored in config files, no database required | [①Docker Version](../Deployment.md#%E6%96%B9%E5%BC%8F%E4%B8%80docker%E5%8F%AA%E8%BF%90%E8%A1%8Cserver) / [②Source Code Deployment](../Deployment.md#%E6%96%B9%E5%BC%8F%E4%BA%8C%E6%9C%AC%E5%9C%B0%E6%BA%90%E7%A0%81%E5%8F%AA%E8%BF%90%E8%A1%8Cserver)| 2 cores 4GB if using `FunASR`, 2 cores 2GB if all APIs | - |
|
||||
| **Full Module Installation** | Intelligent dialogue, multi-user management, multi-agent management, intelligent console interface operation | Complete functionality experience, data stored in database |[①Docker Version](../Deployment_all.md#%E6%96%B9%E5%BC%8F%E4%B8%80docker%E8%BF%90%E8%A1%8C%E5%85%A8%E6%A8%A1%E5%9D%97) / [②Source Code Deployment](../Deployment_all.md#%E6%96%B9%E5%BC%8F%E4%BA%8C%E6%9C%AC%E5%9C%B0%E6%BA%90%E7%A0%81%E8%BF%90%E8%A1%8C%E5%85%A8%E6%A8%A1%E5%9D%97) / [③Source Code Deployment Auto-Update Tutorial](../dev-ops-integration.md) | 4 cores 8GB if using `FunASR`, 2 cores 4GB if all APIs| [Local Source Code Startup Video Tutorial](https://www.bilibili.com/video/BV1wBJhz4Ewe) |
|
||||
| **Simplified Installation** | Intelligent dialogue, single agent management | Low-configuration environments, data stored in config files, no database required | [①Docker Version](./docs/Deployment.md#%E6%96%B9%E5%BC%8F%E4%B8%80docker%E5%8F%AA%E8%BF%90%E8%A1%8Cserver) / [②Source Code Deployment](./docs/Deployment.md#%E6%96%B9%E5%BC%8F%E4%BA%8C%E6%9C%AC%E5%9C%B0%E6%BA%90%E7%A0%81%E5%8F%AA%E8%BF%90%E8%A1%8Cserver)| 2 cores 4GB if using `FunASR`, 2 cores 2GB if all APIs | - |
|
||||
| **Full Module Installation** | Intelligent dialogue, multi-user management, multi-agent management, intelligent console interface operation | Complete functionality experience, data stored in database |[①Docker Version](./docs/Deployment_all.md#%E6%96%B9%E5%BC%8F%E4%B8%80docker%E8%BF%90%E8%A1%8C%E5%85%A8%E6%A8%A1%E5%9D%97) / [②Source Code Deployment](./docs/Deployment_all.md#%E6%96%B9%E5%BC%8F%E4%BA%8C%E6%9C%AC%E5%9C%B0%E6%BA%90%E7%A0%81%E8%BF%90%E8%A1%8C%E5%85%A8%E6%A8%A1%E5%9D%97) / [③Source Code Deployment Auto-Update Tutorial](./docs/dev-ops-integration.md) | 4 cores 8GB if using `FunASR`, 2 cores 4GB if all APIs| [Local Source Code Startup Video Tutorial](https://www.bilibili.com/video/BV1wBJhz4Ewe) |
|
||||
|
||||
For frequently asked questions and related tutorials, please refer to [this link](../FAQ.md)
|
||||
For frequently asked questions and related tutorials, please refer to [this link](./docs/FAQ.md)
|
||||
|
||||
> 💡 Note: Below is a test platform deployed with the latest code. You can burn and test if needed. Concurrent users: 6, data will be cleared daily.
|
||||
|
||||
@@ -209,7 +224,7 @@ This project provides the following testing tools to help you verify the system
|
||||
|
||||
| Tool Name | Location | Usage Method | Function Description |
|
||||
|:---:|:---|:---:|:---:|
|
||||
| Audio Interaction Test Tool | main》digital-human》index.html | Run `python start.py` in `main/digital-human`, then open `http://127.0.0.1:8006/index.html` | Tests audio playback and reception functions, verifies if Python-side audio processing is normal |
|
||||
| Audio Interaction Test Tool | main》xiaozhi-server》test》test_page.html | Open directly with Google Chrome | Tests audio playback and reception functions, verifies if Python-side audio processing is normal |
|
||||
| Model Response Test Tool | main》xiaozhi-server》performance_tester.py | Execute `python performance_tester.py` | Tests response speed of three core modules: ASR(speech recognition), LLM(large model), VLLM(vision model), TTS(speech synthesis) |
|
||||
|
||||
> 💡 Note: When testing model speed, only models with configured keys will be tested.
|
||||
@@ -217,7 +232,7 @@ This project provides the following testing tools to help you verify the system
|
||||
---
|
||||
## Feature List ✨
|
||||
### Implemented ✅
|
||||
|
||||
|
||||
| Feature Module | Description |
|
||||
|:---:|:---|
|
||||
| Core Architecture | Based on [MQTT+UDP gateway](https://github.com/xinnan-tech/xiaozhi-esp32-server/blob/main/docs/mqtt-gateway-integration.md), WebSocket and HTTP servers, provides complete console management and authentication system |
|
||||
@@ -237,9 +252,9 @@ This project provides the following testing tools to help you verify the system
|
||||
|
||||
### Under Development 🚧
|
||||
|
||||
To learn about specific development plan progress, [click here](https://github.com/users/xinnan-tech/projects/3). For frequently asked questions and related tutorials, please refer to [this link](../FAQ.md)
|
||||
To learn about specific development plan progress, [click here](https://github.com/users/xinnan-tech/projects/3). For frequently asked questions and related tutorials, please refer to [this link](./docs/FAQ.md)
|
||||
|
||||
If you are a software developer, here is an [Open Letter to Developers](../contributor_open_letter.md). Welcome to join!
|
||||
If you are a software developer, here is an [Open Letter to Developers](docs/contributor_open_letter.md). Welcome to join!
|
||||
|
||||
---
|
||||
|
||||
@@ -314,7 +329,7 @@ In fact, any VLLM that supports OpenAI interface calls can be integrated and use
|
||||
| Type | Platform Name | Usage Method | Pricing Model | Notes |
|
||||
|:------:|:---------------:|:----:|:---------:|:--:|
|
||||
| Memory | mem0ai | Interface calls | 1000 times/month quota | |
|
||||
| Memory | [powermem](../powermem-integration.md) | Local summarization | Depends on LLM and DB | OceanBase open source, supports intelligent retrieval |
|
||||
| Memory | [powermem](./docs/powermem-integration.md) | Local summarization | Depends on LLM and DB | OceanBase open source, supports intelligent retrieval |
|
||||
| Memory | mem_local_short | Local summarization | Free | |
|
||||
| Memory | nomem | No memory mode | Free | |
|
||||
|
||||
@@ -342,13 +357,13 @@ In fact, any VLLM that supports OpenAI interface calls can be integrated and use
|
||||
|
||||
| Logo | Project/Company | Description |
|
||||
|:---:|:---:|:---|
|
||||
| <img src="../images/logo_bailing.png" width="160"> | [Bailing Voice Dialogue Robot](https://github.com/wwbin2017/bailing) | This project is inspired by [Bailing Voice Dialogue Robot](https://github.com/wwbin2017/bailing) and implemented on its basis |
|
||||
| <img src="../images/logo_tenclass.png" width="160"> | [Tenclass](https://www.tenclass.com/) | Thanks to [Tenclass](https://www.tenclass.com/) for formulating standard communication protocols, multi-device compatibility solutions, and high-concurrency scenario practice demonstrations for the Xiaozhi ecosystem; providing full-link technical documentation support for this project |
|
||||
| <img src="../images/logo_xuanfeng.png" width="160"> | [Xuanfeng Technology](https://github.com/Eric0308) | Thanks to [Xuanfeng Technology](https://github.com/Eric0308) for contributing function calling framework, MCP communication protocol, and plugin-based calling mechanism implementation code. Through standardized instruction scheduling system and dynamic expansion capabilities, it significantly improves the interaction efficiency and functional extensibility of frontend devices (IoT) |
|
||||
| <img src="../images/logo_junsen.png" width="160"> | [huangjunsen](https://github.com/huangjunsen0406) | Thanks to [huangjunsen](https://github.com/huangjunsen0406) for contributing the `Smart Control Console Mobile` module, which enables efficient control and real-time interaction across mobile devices, significantly enhancing the system's operational convenience and management efficiency in mobile scenarios. |
|
||||
| <img src="../images/logo_huiyuan.png" width="160"> | [Huiyuan Design](http://ui.kwd988.net/) | Thanks to [Huiyuan Design](http://ui.kwd988.net/) for providing professional visual solutions for this project, using their design practical experience serving over a thousand enterprises to empower this project's product user experience |
|
||||
| <img src="../images/logo_qinren.png" width="160"> | [Xi'an Qinren Information Technology](https://www.029app.com/) | Thanks to [Xi'an Qinren Information Technology](https://www.029app.com/) for deepening this project's visual system, ensuring consistency and extensibility of overall design style in multi-scenario applications |
|
||||
| <img src="../images/logo_contributors.png" width="160"> | [Code Contributors](https://github.com/xinnan-tech/xiaozhi-esp32-server/graphs/contributors) | Thanks to [all code contributors](https://github.com/xinnan-tech/xiaozhi-esp32-server/graphs/contributors), your efforts have made the project more robust and powerful. |
|
||||
| <img src="./docs/images/logo_bailing.png" width="160"> | [Bailing Voice Dialogue Robot](https://github.com/wwbin2017/bailing) | This project is inspired by [Bailing Voice Dialogue Robot](https://github.com/wwbin2017/bailing) and implemented on its basis |
|
||||
| <img src="./docs/images/logo_tenclass.png" width="160"> | [Tenclass](https://www.tenclass.com/) | Thanks to [Tenclass](https://www.tenclass.com/) for formulating standard communication protocols, multi-device compatibility solutions, and high-concurrency scenario practice demonstrations for the Xiaozhi ecosystem; providing full-link technical documentation support for this project |
|
||||
| <img src="./docs/images/logo_xuanfeng.png" width="160"> | [Xuanfeng Technology](https://github.com/Eric0308) | Thanks to [Xuanfeng Technology](https://github.com/Eric0308) for contributing function calling framework, MCP communication protocol, and plugin-based calling mechanism implementation code. Through standardized instruction scheduling system and dynamic expansion capabilities, it significantly improves the interaction efficiency and functional extensibility of frontend devices (IoT) |
|
||||
| <img src="./docs/images/logo_junsen.png" width="160"> | [huangjunsen](https://github.com/huangjunsen0406) | Thanks to [huangjunsen](https://github.com/huangjunsen0406) for contributing the `Smart Control Console Mobile` module, which enables efficient control and real-time interaction across mobile devices, significantly enhancing the system's operational convenience and management efficiency in mobile scenarios. |
|
||||
| <img src="./docs/images/logo_huiyuan.png" width="160"> | [Huiyuan Design](http://ui.kwd988.net/) | Thanks to [Huiyuan Design](http://ui.kwd988.net/) for providing professional visual solutions for this project, using their design practical experience serving over a thousand enterprises to empower this project's product user experience |
|
||||
| <img src="./docs/images/logo_qinren.png" width="160"> | [Xi'an Qinren Information Technology](https://www.029app.com/) | Thanks to [Xi'an Qinren Information Technology](https://www.029app.com/) for deepening this project's visual system, ensuring consistency and extensibility of overall design style in multi-scenario applications |
|
||||
| <img src="./docs/images/logo_contributors.png" width="160"> | [Code Contributors](https://github.com/xinnan-tech/xiaozhi-esp32-server/graphs/contributors) | Thanks to [all code contributors](https://github.com/xinnan-tech/xiaozhi-esp32-server/graphs/contributors), your efforts have made the project more robust and powerful. |
|
||||
|
||||
|
||||
<a href="https://star-history.com/#xinnan-tech/xiaozhi-esp32-server&Date">
|
||||
@@ -1,4 +1,4 @@
|
||||
[](https://github.com/xinnan-tech/xiaozhi-esp32-server)
|
||||
[](https://github.com/xinnan-tech/xiaozhi-esp32-server)
|
||||
|
||||
<h1 align="center">Serviço Backend Xiaozhi xiaozhi-esp32-server</h1>
|
||||
|
||||
@@ -10,14 +10,14 @@ Suporte ao protocolo MQTT+UDP, protocolo WebSocket, ponto de acesso MCP, reconhe
|
||||
</p>
|
||||
|
||||
<p align="center">
|
||||
<a href="../FAQ.md">Perguntas Frequentes</a>
|
||||
<a href="./docs/FAQ.md">Perguntas Frequentes</a>
|
||||
· <a href="https://github.com/xinnan-tech/xiaozhi-esp32-server/issues">Reportar Problemas</a>
|
||||
· <a href="../../README.md#%E9%83%A8%E7%BD%B2%E6%96%87%E6%A1%A3">Documentação de Implantação</a>
|
||||
· <a href="./README.md#%E9%83%A8%E7%BD%B2%E6%96%87%E6%A1%A3">Documentação de Implantação</a>
|
||||
· <a href="https://github.com/xinnan-tech/xiaozhi-esp32-server/releases">Notas de Lançamento</a>
|
||||
</p>
|
||||
|
||||
<p align="center">
|
||||
<a href="../../README.md"><img alt="简体中文版自述文件" src="https://img.shields.io/badge/简体中文-DFE0E5"></a>
|
||||
<a href="./README.md"><img alt="简体中文版自述文件" src="https://img.shields.io/badge/简体中文-DFE0E5"></a>
|
||||
<a href="./README_en.md"><img alt="README in English" src="https://img.shields.io/badge/English-DFE0E5"></a>
|
||||
<a href="./README_vi.md"><img alt="Tiếng Việt" src="https://img.shields.io/badge/Tiếng Việt-DFE0E5"></a>
|
||||
<a href="./README_de.md"><img alt="Deutsch" src="https://img.shields.io/badge/Deutsch-DFE0E5"></a>
|
||||
@@ -38,7 +38,7 @@ Liderado pela Equipe do Professor Siyuan Liu (Universidade de Tecnologia do Sul
|
||||
</br>
|
||||
刘思源教授团队主导研发（华南理工大学）
|
||||
</br>
|
||||
<img src="../images/hnlg.jpg" alt="Universidade de Tecnologia do Sul da China (华南理工大学)" width="50%">
|
||||
<img src="./docs/images/hnlg.jpg" alt="Universidade de Tecnologia do Sul da China (华南理工大学)" width="50%">
|
||||
</p>
|
||||
|
||||
---
|
||||
@@ -52,98 +52,113 @@ Quer ver os efeitos de uso? Clique nos vídeos abaixo 🎥
|
||||
<table>
|
||||
<tr>
|
||||
<td>
|
||||
<a href="https://www.bilibili.com/video/BV1FMFyejExX" target="_blank">
|
||||
<picture>
|
||||
<img alt="响应速度感受" src="docs/images/demo9.png" /></picture>
|
||||
</a>
|
||||
<a href="https://www.bilibili.com/video/BV1FMFyejExX" target="_blank">
|
||||
<picture>
|
||||
<img alt="Experiência de velocidade de resposta" src="docs/images/demo9.png" />
|
||||
</picture>
|
||||
</a>
|
||||
</td>
|
||||
<td>
|
||||
<a href="https://www.bilibili.com/video/BV1vchQzaEse" target="_blank">
|
||||
<picture>
|
||||
<img alt="速度优化秘诀" src="docs/images/demo6.png" /></picture>
|
||||
</a>
|
||||
<a href="https://www.bilibili.com/video/BV1vchQzaEse" target="_blank">
|
||||
<picture>
|
||||
<img alt="Segredo da otimização de velocidade" src="docs/images/demo6.png" />
|
||||
</picture>
|
||||
</a>
|
||||
</td>
|
||||
<td>
|
||||
<a href="https://www.bilibili.com/video/BV1WEcxzFEAT" target="_blank">
|
||||
<picture>
|
||||
<img alt="小智数字人 支持语音唤醒" src="docs/images/demo8.png" /></picture>
|
||||
</a>
|
||||
<a href="https://www.bilibili.com/video/BV1C1tCzUEZh" target="_blank">
|
||||
<picture>
|
||||
<img alt="Cenário médico complexo" src="docs/images/demo1.png" />
|
||||
</picture>
|
||||
</a>
|
||||
</td>
|
||||
<td>
|
||||
<a href="https://www.bilibili.com/video/BV1CKVz6UEuB" target="_blank">
|
||||
<picture>
|
||||
<img alt="设备呼叫设备，打电话" src="docs/images/demo0.png" /></picture>
|
||||
</a>
|
||||
<a href="https://www.bilibili.com/video/BV1zUW5zJEkq" target="_blank">
|
||||
<picture>
|
||||
<img alt="Envio de comandos MQTT" src="docs/images/demo4.png" />
|
||||
</picture>
|
||||
</a>
|
||||
</td>
|
||||
<td>
|
||||
<a href="https://www.bilibili.com/video/BV1C1tCzUEZh" target="_blank">
|
||||
<picture>
|
||||
<img alt="复杂医疗场景" src="docs/images/demo1.png" /></picture>
|
||||
</a>
|
||||
<a href="https://www.bilibili.com/video/BV1Exu3zqEDe" target="_blank">
|
||||
<picture>
|
||||
<img alt="Reconhecimento de impressão vocal" src="docs/images/demo14.png" />
|
||||
</picture>
|
||||
</a>
|
||||
</td>
|
||||
</tr>
|
||||
<tr>
|
||||
<td>
|
||||
<a href="https://www.bilibili.com/video/BV1VC96Y5EMH" target="_blank">
|
||||
<picture>
|
||||
<img alt="播放音乐查询天气播报新闻" src="docs/images/demo7.png" /></picture>
|
||||
</a>
|
||||
<a href="https://www.bilibili.com/video/BV1pNXWYGEx1" target="_blank">
|
||||
<picture>
|
||||
<img alt="Controle de interruptores de eletrodomésticos" src="docs/images/demo5.png" />
|
||||
</picture>
|
||||
</a>
|
||||
</td>
|
||||
<td>
|
||||
<a href="https://www.bilibili.com/video/BV12J7WzBEaH" target="_blank">
|
||||
<picture>
|
||||
<img alt="实时打断" src="docs/images/demo10.png" /></picture>
|
||||
</a>
|
||||
</td>
|
||||
<td>
|
||||
<a href="https://www.bilibili.com/video/BV1Co76z7EvK" target="_blank">
|
||||
<picture>
|
||||
<img alt="拍照识物品" src="docs/images/demo12.png" /></picture>
|
||||
</a>
|
||||
</td>
|
||||
<td>
|
||||
<a href="https://www.bilibili.com/video/BV1pNXWYGEx1" target="_blank">
|
||||
<picture>
|
||||
<img alt="控制家电开关" src="docs/images/demo5.png" /></picture>
|
||||
</a>
|
||||
<a href="https://www.bilibili.com/video/BV1ZQKUzYExM" target="_blank">
|
||||
<picture>
|
||||
<img alt="Ponto de acesso MCP" src="docs/images/demo13.png" />
|
||||
</picture>
|
||||
</a>
|
||||
</td>
|
||||
<td>
|
||||
<a href="https://www.bilibili.com/video/BV1TJ7WzzEo6" target="_blank">
|
||||
<picture>
|
||||
<img alt="多指令任务" src="docs/images/demo11.png" /></picture>
|
||||
</a>
|
||||
<picture>
|
||||
<img alt="Tarefas com múltiplos comandos" src="docs/images/demo11.png" />
|
||||
</picture>
|
||||
</a>
|
||||
</td>
|
||||
<td>
|
||||
<a href="https://www.bilibili.com/video/BV1VC96Y5EMH" target="_blank">
|
||||
<picture>
|
||||
<img alt="Reproduzir música" src="docs/images/demo7.png" />
|
||||
</picture>
|
||||
</a>
|
||||
</td>
|
||||
<td>
|
||||
<a href="https://www.bilibili.com/video/BV1Z8XuYZEAS" target="_blank">
|
||||
<picture>
|
||||
<img alt="Plugin de clima" src="docs/images/demo8.png" />
|
||||
</picture>
|
||||
</a>
|
||||
</td>
|
||||
</tr>
|
||||
<tr>
|
||||
<td>
|
||||
<a href="https://www.bilibili.com/video/BV1ZQKUzYExM" target="_blank">
|
||||
<picture>
|
||||
<img alt="MCP接入点" src="docs/images/demo13.png" /></picture>
|
||||
</a>
|
||||
<a href="https://www.bilibili.com/video/BV12J7WzBEaH" target="_blank">
|
||||
<picture>
|
||||
<img alt="Interrupção em tempo real" src="docs/images/demo10.png" />
|
||||
</picture>
|
||||
</a>
|
||||
</td>
|
||||
<td>
|
||||
<a href="https://www.bilibili.com/video/BV1zUW5zJEkq" target="_blank">
|
||||
<picture>
|
||||
<img alt="MQTT指令下发" src="docs/images/demo4.png" /></picture>
|
||||
</a>
|
||||
<a href="https://www.bilibili.com/video/BV1Co76z7EvK" target="_blank">
|
||||
<picture>
|
||||
<img alt="Fotografar e identificar objetos" src="docs/images/demo12.png" />
|
||||
</picture>
|
||||
</a>
|
||||
</td>
|
||||
<td>
|
||||
<a href="https://www.bilibili.com/video/BV1Exu3zqEDe" target="_blank">
|
||||
<picture>
|
||||
<img alt="声纹识别" src="docs/images/demo14.png" /></picture>
|
||||
</a>
|
||||
<a href="https://www.bilibili.com/video/BV1CDKWemEU6" target="_blank">
|
||||
<picture>
|
||||
<img alt="Timbre de voz personalizado" src="docs/images/demo2.png" />
|
||||
</picture>
|
||||
</a>
|
||||
</td>
|
||||
<td>
|
||||
<a href="https://www.bilibili.com/video/BV1CDKWemEU6" target="_blank">
|
||||
<picture>
|
||||
<img alt="自定义音色" src="docs/images/demo2.png" /></picture>
|
||||
</a>
|
||||
<a href="https://www.bilibili.com/video/BV12yA2egEaC" target="_blank">
|
||||
<picture>
|
||||
<img alt="Comunicação em cantonês" src="docs/images/demo3.png" />
|
||||
</picture>
|
||||
</a>
|
||||
</td>
|
||||
<td>
|
||||
<a href="https://www.bilibili.com/video/BV12yA2egEaC" target="_blank">
|
||||
<picture>
|
||||
<img alt="使用粤语交流" src="docs/images/demo3.png" /></picture>
|
||||
</a>
|
||||
<a href="https://www.bilibili.com/video/BV17LXWYvENb" target="_blank">
|
||||
<picture>
|
||||
<img alt="Transmissão de notícias" src="docs/images/demo0.png" />
|
||||
</picture>
|
||||
</a>
|
||||
</td>
|
||||
</tr>
|
||||
</table>
|
||||
@@ -160,17 +175,17 @@ Quer ver os efeitos de uso? Clique nos vídeos abaixo 🎥
|
||||
|
||||
## Documentação de Implantação
|
||||
|
||||
|
||||
|
||||
|
||||
Este projeto oferece dois métodos de implantação. Por favor, escolha de acordo com suas necessidades específicas:
|
||||
|
||||
#### 🚀 Seleção do Método de Implantação
|
||||
| Método de Implantação | Funcionalidades | Cenários Aplicáveis | Documentação de Implantação | Requisitos de Configuração | Tutoriais em Vídeo |
|
||||
|---------|------|---------|---------|---------|---------|
|
||||
| **Instalação Simplificada** | Diálogo inteligente, gerenciamento de agente único | Ambientes de baixa configuração, dados armazenados em arquivos de configuração, sem necessidade de banco de dados | [①Versão Docker](../Deployment.md#%E6%96%B9%E5%BC%8F%E4%B8%80docker%E5%8F%AA%E8%BF%90%E8%A1%8Cserver) / [②Implantação via Código-Fonte](../Deployment.md#%E6%96%B9%E5%BC%8F%E4%BA%8C%E6%9C%AC%E5%9C%B0%E6%BA%90%E7%A0%81%E5%8F%AA%E8%BF%90%E8%A1%8Cserver)| 2 núcleos 4GB se usar `FunASR`, 2 núcleos 2GB se todas APIs | - |
|
||||
| **Instalação de Módulo Completo** | Diálogo inteligente, gerenciamento multiusuário, gerenciamento de múltiplos agentes, operação de interface do console inteligente | Experiência com funcionalidade completa, dados armazenados em banco de dados |[①Versão Docker](../Deployment_all.md#%E6%96%B9%E5%BC%8F%E4%B8%80docker%E8%BF%90%E8%A1%8C%E5%85%A8%E6%A8%A1%E5%9D%97) / [②Implantação via Código-Fonte](../Deployment_all.md#%E6%96%B9%E5%BC%8F%E4%BA%8C%E6%9C%AC%E5%9C%B0%E6%BA%90%E7%A0%81%E8%BF%90%E8%A1%8C%E5%85%A8%E6%A8%A1%E5%9D%97) / [③Tutorial de Atualização Automática via Código-Fonte](../dev-ops-integration.md) | 4 núcleos 8GB se usar `FunASR`, 2 núcleos 4GB se todas APIs| [Tutorial em Vídeo de Inicialização via Código-Fonte Local](https://www.bilibili.com/video/BV1wBJhz4Ewe) |
|
||||
| **Instalação Simplificada** | Diálogo inteligente, gerenciamento de agente único | Ambientes de baixa configuração, dados armazenados em arquivos de configuração, sem necessidade de banco de dados | [①Versão Docker](./docs/Deployment.md#%E6%96%B9%E5%BC%8F%E4%B8%80docker%E5%8F%AA%E8%BF%90%E8%A1%8Cserver) / [②Implantação via Código-Fonte](./docs/Deployment.md#%E6%96%B9%E5%BC%8F%E4%BA%8C%E6%9C%AC%E5%9C%B0%E6%BA%90%E7%A0%81%E5%8F%AA%E8%BF%90%E8%A1%8Cserver)| 2 núcleos 4GB se usar `FunASR`, 2 núcleos 2GB se todas APIs | - |
|
||||
| **Instalação de Módulo Completo** | Diálogo inteligente, gerenciamento multiusuário, gerenciamento de múltiplos agentes, operação de interface do console inteligente | Experiência com funcionalidade completa, dados armazenados em banco de dados |[①Versão Docker](./docs/Deployment_all.md#%E6%96%B9%E5%BC%8F%E4%B8%80docker%E8%BF%90%E8%A1%8C%E5%85%A8%E6%A8%A1%E5%9D%97) / [②Implantação via Código-Fonte](./docs/Deployment_all.md#%E6%96%B9%E5%BC%8F%E4%BA%8C%E6%9C%AC%E5%9C%B0%E6%BA%90%E7%A0%81%E8%BF%90%E8%A1%8C%E5%85%A8%E6%A8%A1%E5%9D%97) / [③Tutorial de Atualização Automática via Código-Fonte](./docs/dev-ops-integration.md) | 4 núcleos 8GB se usar `FunASR`, 2 núcleos 4GB se todas APIs| [Tutorial em Vídeo de Inicialização via Código-Fonte Local](https://www.bilibili.com/video/BV1wBJhz4Ewe) |
|
||||
|
||||
Perguntas frequentes e tutoriais relacionados podem ser consultados [neste link](../FAQ.md)
|
||||
Perguntas frequentes e tutoriais relacionados podem ser consultados [neste link](./docs/FAQ.md)
|
||||
|
||||
> 💡 Nota: Abaixo está uma plataforma de teste implantada com o código mais recente. Você pode gravar e testar se necessário. Usuários simultâneos: 6, os dados serão limpos diariamente.
|
||||
|
||||
@@ -209,7 +224,7 @@ Este projeto fornece as seguintes ferramentas de teste para ajudá-lo a verifica
|
||||
|
||||
| Nome da Ferramenta | Localização | Método de Uso | Descrição da Função |
|
||||
|:---:|:---|:---:|:---:|
|
||||
| Ferramenta de Teste de Interação por Áudio | main》digital-human》index.html | Execute `python start.py` em `main/digital-human` e depois abra `http://127.0.0.1:8006/index.html` | Testa as funções de reprodução e recepção de áudio, verifica se o processamento de áudio no lado Python está normal |
|
||||
| Ferramenta de Teste de Interação por Áudio | main》xiaozhi-server》test》test_page.html | Abrir diretamente com Google Chrome | Testa as funções de reprodução e recepção de áudio, verifica se o processamento de áudio no lado Python está normal |
|
||||
| Ferramenta de Teste de Resposta de Modelo | main》xiaozhi-server》performance_tester.py | Execute `python performance_tester.py` | Testa a velocidade de resposta dos três módulos principais: ASR(reconhecimento de fala), LLM(modelo de linguagem), VLLM(modelo de visão), TTS(síntese de voz) |
|
||||
|
||||
> 💡 Nota: Ao testar a velocidade dos modelos, apenas os modelos com chaves configuradas serão testados.
|
||||
@@ -217,7 +232,7 @@ Este projeto fornece as seguintes ferramentas de teste para ajudá-lo a verifica
|
||||
---
|
||||
## Lista de Funcionalidades ✨
|
||||
### Implementado ✅
|
||||
|
||||
|
||||
| Módulo de Funcionalidade | Descrição |
|
||||
|:---:|:---|
|
||||
| Arquitetura Principal | Baseado em [gateway MQTT+UDP](https://github.com/xinnan-tech/xiaozhi-esp32-server/blob/main/docs/mqtt-gateway-integration.md), servidores WebSocket e HTTP, fornece sistema completo de gerenciamento de console e autenticação |
|
||||
@@ -237,9 +252,9 @@ Este projeto fornece as seguintes ferramentas de teste para ajudá-lo a verifica
|
||||
|
||||
### Em Desenvolvimento 🚧
|
||||
|
||||
Para conhecer o progresso específico do plano de desenvolvimento, [clique aqui](https://github.com/users/xinnan-tech/projects/3). Perguntas frequentes e tutoriais relacionados podem ser consultados [neste link](../FAQ.md)
|
||||
Para conhecer o progresso específico do plano de desenvolvimento, [clique aqui](https://github.com/users/xinnan-tech/projects/3). Perguntas frequentes e tutoriais relacionados podem ser consultados [neste link](./docs/FAQ.md)
|
||||
|
||||
Se você é um desenvolvedor de software, aqui está uma [Carta Aberta aos Desenvolvedores](../contributor_open_letter.md). Seja bem-vindo a participar!
|
||||
Se você é um desenvolvedor de software, aqui está uma [Carta Aberta aos Desenvolvedores](docs/contributor_open_letter.md). Seja bem-vindo a participar!
|
||||
|
||||
---
|
||||
|
||||
@@ -314,7 +329,7 @@ Na verdade, qualquer VLLM que suporte chamadas via interface OpenAI pode ser int
|
||||
| Tipo | Nome da Plataforma | Método de Uso | Modelo de Preço | Observações |
|
||||
|:------:|:---------------:|:----:|:---------:|:--:|
|
||||
| Memória | mem0ai | Chamadas via interface | Cota de 1000 vezes/mês | |
|
||||
| Memória | [powermem](../powermem-integration.md) | Resumo local | Depende do LLM e BD | OceanBase de código aberto, suporta busca inteligente |
|
||||
| Memória | [powermem](./docs/powermem-integration.md) | Resumo local | Depende do LLM e BD | OceanBase de código aberto, suporta busca inteligente |
|
||||
| Memória | mem_local_short | Resumo local | Gratuito | |
|
||||
| Memória | nomem | Modo sem memória | Gratuito | |
|
||||
|
||||
@@ -342,13 +357,13 @@ Na verdade, qualquer VLLM que suporte chamadas via interface OpenAI pode ser int
|
||||
|
||||
| Logo | Projeto/Empresa | Descrição |
|
||||
|:---:|:---:|:---|
|
||||
| <img src="../images/logo_bailing.png" width="160"> | [Robô de Diálogo por Voz Bailing](https://github.com/wwbin2017/bailing) | Este projeto foi inspirado pelo [Robô de Diálogo por Voz Bailing](https://github.com/wwbin2017/bailing) e implementado com base nele |
|
||||
| <img src="../images/logo_tenclass.png" width="160"> | [Tenclass](https://www.tenclass.com/) | Agradecimentos à [Tenclass](https://www.tenclass.com/) por formular protocolos de comunicação padrão, soluções de compatibilidade multidispositivo e demonstrações práticas de cenários de alta concorrência para o ecossistema Xiaozhi; fornecendo suporte completo de documentação técnica para este projeto |
|
||||
| <img src="../images/logo_xuanfeng.png" width="160"> | [Xuanfeng Technology (玄凤科技)](https://github.com/Eric0308) | Agradecimentos à [Xuanfeng Technology](https://github.com/Eric0308) por contribuir com o framework de chamada de função, protocolo de comunicação MCP e implementação do mecanismo de chamada baseado em plugins. Através de um sistema padronizado de agendamento de instruções e capacidades de expansão dinâmica, melhora significativamente a eficiência de interação e extensibilidade funcional dos dispositivos de frontend (IoT) |
|
||||
| <img src="../images/logo_junsen.png" width="160"> | [huangjunsen](https://github.com/huangjunsen0406) | Agradecimentos a [huangjunsen](https://github.com/huangjunsen0406) por contribuir com o módulo `Console de Controle Inteligente Mobile`, que permite controle eficiente e interação em tempo real em dispositivos móveis, melhorando significativamente a conveniência operacional e a eficiência de gerenciamento do sistema em cenários móveis. |
|
||||
| <img src="../images/logo_huiyuan.png" width="160"> | [Huiyuan Design (汇远设计)](http://ui.kwd988.net/) | Agradecimentos à [Huiyuan Design](http://ui.kwd988.net/) por fornecer soluções visuais profissionais para este projeto, utilizando sua experiência prática de design atendendo mais de mil empresas para potencializar a experiência do usuário deste produto |
|
||||
| <img src="../images/logo_qinren.png" width="160"> | [Xi'an Qinren Information Technology (西安勤人信息科技)](https://www.029app.com/) | Agradecimentos à [Xi'an Qinren Information Technology](https://www.029app.com/) por aprofundar o sistema visual deste projeto, garantindo consistência e extensibilidade do estilo de design geral em aplicações de múltiplos cenários |
|
||||
| <img src="../images/logo_contributors.png" width="160"> | [Contribuidores de Código](https://github.com/xinnan-tech/xiaozhi-esp32-server/graphs/contributors) | Agradecimentos a [todos os contribuidores de código](https://github.com/xinnan-tech/xiaozhi-esp32-server/graphs/contributors), seus esforços tornaram o projeto mais robusto e poderoso. |
|
||||
| <img src="./docs/images/logo_bailing.png" width="160"> | [Robô de Diálogo por Voz Bailing](https://github.com/wwbin2017/bailing) | Este projeto foi inspirado pelo [Robô de Diálogo por Voz Bailing](https://github.com/wwbin2017/bailing) e implementado com base nele |
|
||||
| <img src="./docs/images/logo_tenclass.png" width="160"> | [Tenclass](https://www.tenclass.com/) | Agradecimentos à [Tenclass](https://www.tenclass.com/) por formular protocolos de comunicação padrão, soluções de compatibilidade multidispositivo e demonstrações práticas de cenários de alta concorrência para o ecossistema Xiaozhi; fornecendo suporte completo de documentação técnica para este projeto |
|
||||
| <img src="./docs/images/logo_xuanfeng.png" width="160"> | [Xuanfeng Technology (玄凤科技)](https://github.com/Eric0308) | Agradecimentos à [Xuanfeng Technology](https://github.com/Eric0308) por contribuir com o framework de chamada de função, protocolo de comunicação MCP e implementação do mecanismo de chamada baseado em plugins. Através de um sistema padronizado de agendamento de instruções e capacidades de expansão dinâmica, melhora significativamente a eficiência de interação e extensibilidade funcional dos dispositivos de frontend (IoT) |
|
||||
| <img src="./docs/images/logo_junsen.png" width="160"> | [huangjunsen](https://github.com/huangjunsen0406) | Agradecimentos a [huangjunsen](https://github.com/huangjunsen0406) por contribuir com o módulo `Console de Controle Inteligente Mobile`, que permite controle eficiente e interação em tempo real em dispositivos móveis, melhorando significativamente a conveniência operacional e a eficiência de gerenciamento do sistema em cenários móveis. |
|
||||
| <img src="./docs/images/logo_huiyuan.png" width="160"> | [Huiyuan Design (汇远设计)](http://ui.kwd988.net/) | Agradecimentos à [Huiyuan Design](http://ui.kwd988.net/) por fornecer soluções visuais profissionais para este projeto, utilizando sua experiência prática de design atendendo mais de mil empresas para potencializar a experiência do usuário deste produto |
|
||||
| <img src="./docs/images/logo_qinren.png" width="160"> | [Xi'an Qinren Information Technology (西安勤人信息科技)](https://www.029app.com/) | Agradecimentos à [Xi'an Qinren Information Technology](https://www.029app.com/) por aprofundar o sistema visual deste projeto, garantindo consistência e extensibilidade do estilo de design geral em aplicações de múltiplos cenários |
|
||||
| <img src="./docs/images/logo_contributors.png" width="160"> | [Contribuidores de Código](https://github.com/xinnan-tech/xiaozhi-esp32-server/graphs/contributors) | Agradecimentos a [todos os contribuidores de código](https://github.com/xinnan-tech/xiaozhi-esp32-server/graphs/contributors), seus esforços tornaram o projeto mais robusto e poderoso. |
|
||||
|
||||
|
||||
<a href="https://star-history.com/#xinnan-tech/xiaozhi-esp32-server&Date">
|
||||
@@ -1,4 +1,4 @@
|
||||
[](https://github.com/xinnan-tech/xiaozhi-esp32-server)
|
||||
[](https://github.com/xinnan-tech/xiaozhi-esp32-server)
|
||||
|
||||
<h1 align="center">Dịch vụ Backend Xiaozhi xiaozhi-esp32-server</h1>
|
||||
|
||||
@@ -10,14 +10,14 @@ Hỗ trợ giao thức MQTT+UDP, giao thức Websocket, điểm truy cập MCP,
|
||||
</p>
|
||||
|
||||
<p align="center">
|
||||
<a href="../FAQ.md">Câu hỏi thường gặp</a>
|
||||
<a href="./docs/FAQ.md">Câu hỏi thường gặp</a>
|
||||
· <a href="https://github.com/xinnan-tech/xiaozhi-esp32-server/issues">Báo cáo vấn đề</a>
|
||||
· <a href="../../README.md#%E9%83%A8%E7%BD%B2%E6%96%87%E6%A1%A3">Tài liệu triển khai</a>
|
||||
· <a href="./README.md#%E9%83%A8%E7%BD%B2%E6%96%87%E6%A1%A3">Tài liệu triển khai</a>
|
||||
· <a href="https://github.com/xinnan-tech/xiaozhi-esp32-server/releases">Nhật ký cập nhật</a>
|
||||
</p>
|
||||
|
||||
<p align="center">
|
||||
<a href="../../README.md"><img alt="简体中文版自述文件" src="https://img.shields.io/badge/简体中文-DFE0E5"></a>
|
||||
<a href="./README.md"><img alt="简体中文版自述文件" src="https://img.shields.io/badge/简体中文-DFE0E5"></a>
|
||||
<a href="./README_en.md"><img alt="README in English" src="https://img.shields.io/badge/English-DFE0E5"></a>
|
||||
<a href="./README_vi.md"><img alt="Tiếng Việt" src="https://img.shields.io/badge/Tiếng Việt-DBEDFA"></a>
|
||||
<a href="./README_de.md"><img alt="Deutsch" src="https://img.shields.io/badge/Deutsch-DFE0E5"></a>
|
||||
@@ -38,7 +38,7 @@ Spearheaded by Professor Siyuan Liu's Team (South China University of Technology
|
||||
</br>
|
||||
Được dẫn dắt bởi nhóm Giáo sư Lưu Tư Nguyên (Đại học Bách khoa Nam Trung Quốc)
|
||||
</br>
|
||||
<img src="../images/hnlg.jpg" alt="华南理工大学" width="50%">
|
||||
<img src="./docs/images/hnlg.jpg" alt="华南理工大学" width="50%">
|
||||
</p>
|
||||
|
||||
---
|
||||
@@ -52,98 +52,113 @@ Muốn xem hiệu quả sử dụng? Hãy xem video 🎥
|
||||
<table>
|
||||
<tr>
|
||||
<td>
|
||||
<a href="https://www.bilibili.com/video/BV1FMFyejExX" target="_blank">
|
||||
<picture>
|
||||
<img alt="响应速度感受" src="docs/images/demo9.png" /></picture>
|
||||
</a>
|
||||
<a href="https://www.bilibili.com/video/BV1FMFyejExX" target="_blank">
|
||||
<picture>
|
||||
<img alt="响应速度感受" src="docs/images/demo9.png" />
|
||||
</picture>
|
||||
</a>
|
||||
</td>
|
||||
<td>
|
||||
<a href="https://www.bilibili.com/video/BV1vchQzaEse" target="_blank">
|
||||
<picture>
|
||||
<img alt="速度优化秘诀" src="docs/images/demo6.png" /></picture>
|
||||
</a>
|
||||
<a href="https://www.bilibili.com/video/BV1vchQzaEse" target="_blank">
|
||||
<picture>
|
||||
<img alt="速度优化秘诀" src="docs/images/demo6.png" />
|
||||
</picture>
|
||||
</a>
|
||||
</td>
|
||||
<td>
|
||||
<a href="https://www.bilibili.com/video/BV1WEcxzFEAT" target="_blank">
|
||||
<picture>
|
||||
<img alt="小智数字人 支持语音唤醒" src="docs/images/demo8.png" /></picture>
|
||||
</a>
|
||||
<a href="https://www.bilibili.com/video/BV1C1tCzUEZh" target="_blank">
|
||||
<picture>
|
||||
<img alt="复杂医疗场景" src="docs/images/demo1.png" />
|
||||
</picture>
|
||||
</a>
|
||||
</td>
|
||||
<td>
|
||||
<a href="https://www.bilibili.com/video/BV1CKVz6UEuB" target="_blank">
|
||||
<picture>
|
||||
<img alt="设备呼叫设备，打电话" src="docs/images/demo0.png" /></picture>
|
||||
</a>
|
||||
<a href="https://www.bilibili.com/video/BV1zUW5zJEkq" target="_blank">
|
||||
<picture>
|
||||
<img alt="MQTT指令下发" src="docs/images/demo4.png" />
|
||||
</picture>
|
||||
</a>
|
||||
</td>
|
||||
<td>
|
||||
<a href="https://www.bilibili.com/video/BV1C1tCzUEZh" target="_blank">
|
||||
<picture>
|
||||
<img alt="复杂医疗场景" src="docs/images/demo1.png" /></picture>
|
||||
</a>
|
||||
<a href="https://www.bilibili.com/video/BV1Exu3zqEDe" target="_blank">
|
||||
<picture>
|
||||
<img alt="声纹识别" src="docs/images/demo14.png" />
|
||||
</picture>
|
||||
</a>
|
||||
</td>
|
||||
</tr>
|
||||
<tr>
|
||||
<td>
|
||||
<a href="https://www.bilibili.com/video/BV1VC96Y5EMH" target="_blank">
|
||||
<picture>
|
||||
<img alt="播放音乐查询天气播报新闻" src="docs/images/demo7.png" /></picture>
|
||||
</a>
|
||||
<a href="https://www.bilibili.com/video/BV1pNXWYGEx1" target="_blank">
|
||||
<picture>
|
||||
<img alt="控制家电开关" src="docs/images/demo5.png" />
|
||||
</picture>
|
||||
</a>
|
||||
</td>
|
||||
<td>
|
||||
<a href="https://www.bilibili.com/video/BV12J7WzBEaH" target="_blank">
|
||||
<picture>
|
||||
<img alt="实时打断" src="docs/images/demo10.png" /></picture>
|
||||
</a>
|
||||
</td>
|
||||
<td>
|
||||
<a href="https://www.bilibili.com/video/BV1Co76z7EvK" target="_blank">
|
||||
<picture>
|
||||
<img alt="拍照识物品" src="docs/images/demo12.png" /></picture>
|
||||
</a>
|
||||
</td>
|
||||
<td>
|
||||
<a href="https://www.bilibili.com/video/BV1pNXWYGEx1" target="_blank">
|
||||
<picture>
|
||||
<img alt="控制家电开关" src="docs/images/demo5.png" /></picture>
|
||||
</a>
|
||||
<a href="https://www.bilibili.com/video/BV1ZQKUzYExM" target="_blank">
|
||||
<picture>
|
||||
<img alt="MCP接入点" src="docs/images/demo13.png" />
|
||||
</picture>
|
||||
</a>
|
||||
</td>
|
||||
<td>
|
||||
<a href="https://www.bilibili.com/video/BV1TJ7WzzEo6" target="_blank">
|
||||
<picture>
|
||||
<img alt="多指令任务" src="docs/images/demo11.png" /></picture>
|
||||
</a>
|
||||
<picture>
|
||||
<img alt="多指令任务" src="docs/images/demo11.png" />
|
||||
</picture>
|
||||
</a>
|
||||
</td>
|
||||
<td>
|
||||
<a href="https://www.bilibili.com/video/BV1VC96Y5EMH" target="_blank">
|
||||
<picture>
|
||||
<img alt="播放音乐" src="docs/images/demo7.png" />
|
||||
</picture>
|
||||
</a>
|
||||
</td>
|
||||
<td>
|
||||
<a href="https://www.bilibili.com/video/BV1Z8XuYZEAS" target="_blank">
|
||||
<picture>
|
||||
<img alt="天气插件" src="docs/images/demo8.png" />
|
||||
</picture>
|
||||
</a>
|
||||
</td>
|
||||
</tr>
|
||||
<tr>
|
||||
<td>
|
||||
<a href="https://www.bilibili.com/video/BV1ZQKUzYExM" target="_blank">
|
||||
<picture>
|
||||
<img alt="MCP接入点" src="docs/images/demo13.png" /></picture>
|
||||
</a>
|
||||
<a href="https://www.bilibili.com/video/BV12J7WzBEaH" target="_blank">
|
||||
<picture>
|
||||
<img alt="实时打断" src="docs/images/demo10.png" />
|
||||
</picture>
|
||||
</a>
|
||||
</td>
|
||||
<td>
|
||||
<a href="https://www.bilibili.com/video/BV1zUW5zJEkq" target="_blank">
|
||||
<picture>
|
||||
<img alt="MQTT指令下发" src="docs/images/demo4.png" /></picture>
|
||||
</a>
|
||||
<a href="https://www.bilibili.com/video/BV1Co76z7EvK" target="_blank">
|
||||
<picture>
|
||||
<img alt="拍照识物品" src="docs/images/demo12.png" />
|
||||
</picture>
|
||||
</a>
|
||||
</td>
|
||||
<td>
|
||||
<a href="https://www.bilibili.com/video/BV1Exu3zqEDe" target="_blank">
|
||||
<picture>
|
||||
<img alt="声纹识别" src="docs/images/demo14.png" /></picture>
|
||||
</a>
|
||||
<a href="https://www.bilibili.com/video/BV1CDKWemEU6" target="_blank">
|
||||
<picture>
|
||||
<img alt="自定义音色" src="docs/images/demo2.png" />
|
||||
</picture>
|
||||
</a>
|
||||
</td>
|
||||
<td>
|
||||
<a href="https://www.bilibili.com/video/BV1CDKWemEU6" target="_blank">
|
||||
<picture>
|
||||
<img alt="自定义音色" src="docs/images/demo2.png" /></picture>
|
||||
</a>
|
||||
<a href="https://www.bilibili.com/video/BV12yA2egEaC" target="_blank">
|
||||
<picture>
|
||||
<img alt="使用粤语交流" src="docs/images/demo3.png" />
|
||||
</picture>
|
||||
</a>
|
||||
</td>
|
||||
<td>
|
||||
<a href="https://www.bilibili.com/video/BV12yA2egEaC" target="_blank">
|
||||
<picture>
|
||||
<img alt="使用粤语交流" src="docs/images/demo3.png" /></picture>
|
||||
</a>
|
||||
<a href="https://www.bilibili.com/video/BV17LXWYvENb" target="_blank">
|
||||
<picture>
|
||||
<img alt="播报新闻" src="docs/images/demo0.png" />
|
||||
</picture>
|
||||
</a>
|
||||
</td>
|
||||
</tr>
|
||||
</table>
|
||||
@@ -161,17 +176,17 @@ Khuyến nghị người dùng ưu tiên lựa chọn nhà cung cấp dịch v
|
||||
|
||||
## Tài liệu triển khai
|
||||
|
||||
|
||||
|
||||
|
||||
Dự án này cung cấp hai phương pháp triển khai, vui lòng chọn theo nhu cầu cụ thể của bạn:
|
||||
|
||||
#### 🚀 Lựa chọn phương pháp triển khai
|
||||
| Phương pháp triển khai | Đặc điểm | Tình huống áp dụng | Tài liệu triển khai | Yêu cầu cấu hình | Video hướng dẫn |
|
||||
|---------|------|---------|---------|---------|---------|
|
||||
| **Cài đặt tối giản** | Đối thoại thông minh, quản lý đơn tác nhân | Môi trường cấu hình thấp, dữ liệu lưu trong tệp cấu hình, không cần cơ sở dữ liệu | [①Phiên bản Docker](../Deployment.md#%E6%96%B9%E5%BC%8F%E4%B8%80docker%E5%8F%AA%E8%BF%90%E8%A1%8Cserver) / [②Triển khai mã nguồn](../Deployment.md#%E6%96%B9%E5%BC%8F%E4%BA%8C%E6%9C%AC%E5%9C%B0%E6%BA%90%E7%A0%81%E5%8F%AA%E8%BF%90%E8%A1%8Cserver)| 2 nhân 4GB nếu dùng `FunASR`, 2 nhân 2GB nếu toàn API | - |
|
||||
| **Cài đặt toàn bộ module** | Đối thoại thông minh, quản lý đa người dùng, quản lý đa tác nhân, bảng điều khiển thông minh | Trải nghiệm đầy đủ tính năng, dữ liệu lưu trong cơ sở dữ liệu |[①Phiên bản Docker](../Deployment_all.md#%E6%96%B9%E5%BC%8F%E4%B8%80docker%E8%BF%90%E8%A1%8C%E5%85%A8%E6%A8%A1%E5%9D%97) / [②Triển khai mã nguồn](../Deployment_all.md#%E6%96%B9%E5%BC%8F%E4%BA%8C%E6%9C%AC%E5%9C%B0%E6%BA%90%E7%A0%81%E8%BF%90%E8%A1%8C%E5%85%A8%E6%A8%A1%E5%9D%97) / [③Hướng dẫn tự động cập nhật triển khai mã nguồn](../dev-ops-integration.md) | 4 nhân 8GB nếu dùng `FunASR`, 2 nhân 4GB nếu toàn API| [Video hướng dẫn khởi động mã nguồn cục bộ](https://www.bilibili.com/video/BV1wBJhz4Ewe) |
|
||||
| **Cài đặt tối giản** | Đối thoại thông minh, quản lý đơn tác nhân | Môi trường cấu hình thấp, dữ liệu lưu trong tệp cấu hình, không cần cơ sở dữ liệu | [①Phiên bản Docker](./docs/Deployment.md#%E6%96%B9%E5%BC%8F%E4%B8%80docker%E5%8F%AA%E8%BF%90%E8%A1%8Cserver) / [②Triển khai mã nguồn](./docs/Deployment.md#%E6%96%B9%E5%BC%8F%E4%BA%8C%E6%9C%AC%E5%9C%B0%E6%BA%90%E7%A0%81%E5%8F%AA%E8%BF%90%E8%A1%8Cserver)| 2 nhân 4GB nếu dùng `FunASR`, 2 nhân 2GB nếu toàn API | - |
|
||||
| **Cài đặt toàn bộ module** | Đối thoại thông minh, quản lý đa người dùng, quản lý đa tác nhân, bảng điều khiển thông minh | Trải nghiệm đầy đủ tính năng, dữ liệu lưu trong cơ sở dữ liệu |[①Phiên bản Docker](./docs/Deployment_all.md#%E6%96%B9%E5%BC%8F%E4%B8%80docker%E8%BF%90%E8%A1%8C%E5%85%A8%E6%A8%A1%E5%9D%97) / [②Triển khai mã nguồn](./docs/Deployment_all.md#%E6%96%B9%E5%BC%8F%E4%BA%8C%E6%9C%AC%E5%9C%B0%E6%BA%90%E7%A0%81%E8%BF%90%E8%A1%8C%E5%85%A8%E6%A8%A1%E5%9D%97) / [③Hướng dẫn tự động cập nhật triển khai mã nguồn](./docs/dev-ops-integration.md) | 4 nhân 8GB nếu dùng `FunASR`, 2 nhân 4GB nếu toàn API| [Video hướng dẫn khởi động mã nguồn cục bộ](https://www.bilibili.com/video/BV1wBJhz4Ewe) |
|
||||
|
||||
Câu hỏi thường gặp và hướng dẫn liên quan, vui lòng tham khảo [liên kết này](../FAQ.md)
|
||||
Câu hỏi thường gặp và hướng dẫn liên quan, vui lòng tham khảo [liên kết này](./docs/FAQ.md)
|
||||
|
||||
> 💡 Gợi ý: Dưới đây là nền tảng thử nghiệm được triển khai theo mã mới nhất, có thể flash để thử nghiệm nếu cần, đồng thời là 6, dữ liệu sẽ được xóa mỗi ngày,
|
||||
|
||||
@@ -210,7 +225,7 @@ Dự án này cung cấp các công cụ kiểm tra sau để giúp bạn xác m
|
||||
|
||||
| Tên công cụ | Vị trí | Phương pháp sử dụng | Mô tả chức năng |
|
||||
|:---:|:---|:---:|:---:|
|
||||
| Công cụ kiểm tra tương tác âm thanh | main》digital-human》index.html | Chạy `python start.py` trong `main/digital-human`, sau đó mở `http://127.0.0.1:8006/index.html` | Kiểm tra chức năng phát và nhận âm thanh, xác minh xử lý âm thanh phía Python có bình thường không |
|
||||
| Công cụ kiểm tra tương tác âm thanh | main》xiaozhi-server》test》test_page.html | Mở trực tiếp bằng trình duyệt Google Chrome | Kiểm tra chức năng phát và nhận âm thanh, xác minh xử lý âm thanh phía Python có bình thường không |
|
||||
| Công cụ kiểm tra phản hồi mô hình | main》xiaozhi-server》performance_tester.py | Thực hiện `python performance_tester.py` | Kiểm tra tốc độ phản hồi của ba module cốt lõi ASR(Nhận dạng giọng nói), LLM(Mô hình lớn), VLLM(Mô hình thị giác), TTS(Tổng hợp giọng nói) |
|
||||
|
||||
> 💡 Gợi ý: Khi kiểm tra tốc độ mô hình, chỉ kiểm tra các mô hình đã cấu hình khóa.
|
||||
@@ -218,7 +233,7 @@ Dự án này cung cấp các công cụ kiểm tra sau để giúp bạn xác m
|
||||
---
|
||||
## Danh sách tính năng ✨
|
||||
### Đã thực hiện ✅
|
||||
|
||||
|
||||
| Module chức năng | Mô tả |
|
||||
|:---:|:---|
|
||||
| Kiến trúc cốt lõi | Dựa trên [cổng MQTT+UDP](https://github.com/xinnan-tech/xiaozhi-esp32-server/blob/main/docs/mqtt-gateway-integration.md), WebSocket, máy chủ HTTP, cung cấp hệ thống quản lý bảng điều khiển và xác thực hoàn chỉnh |
|
||||
@@ -238,9 +253,9 @@ Dự án này cung cấp các công cụ kiểm tra sau để giúp bạn xác m
|
||||
|
||||
### Đang phát triển 🚧
|
||||
|
||||
Muốn hiểu tiến độ kế hoạch phát triển cụ thể, [vui lòng nhấp vào đây](https://github.com/users/xinnan-tech/projects/3). Câu hỏi thường gặp và hướng dẫn liên quan, vui lòng tham khảo [liên kết này](../FAQ.md)
|
||||
Muốn hiểu tiến độ kế hoạch phát triển cụ thể, [vui lòng nhấp vào đây](https://github.com/users/xinnan-tech/projects/3). Câu hỏi thường gặp và hướng dẫn liên quan, vui lòng tham khảo [liên kết này](./docs/FAQ.md)
|
||||
|
||||
Nếu bạn là một nhà phát triển phần mềm, đây có một [Lá thư mở gửi các nhà phát triển](../contributor_open_letter.md), chào mừng tham gia!
|
||||
Nếu bạn là một nhà phát triển phần mềm, đây có một [Lá thư mở gửi các nhà phát triển](docs/contributor_open_letter.md), chào mừng tham gia!
|
||||
|
||||
---
|
||||
|
||||
@@ -315,7 +330,7 @@ Trên thực tế, bất kỳ VLLM nào hỗ trợ gọi giao diện openai đ
|
||||
| Loại | Tên nền tảng | Phương pháp sử dụng | Mô hình thu phí | Ghi chú |
|
||||
|:------:|:---------------:|:----:|:---------:|:--:|
|
||||
| Memory | mem0ai | Gọi giao diện | Hạn mức 1000 lần/tháng | |
|
||||
| Memory | [powermem](../powermem-integration.md) | Tóm tắt cục bộ | Phụ thuộc vào LLM và DB | OceanBase mã nguồn mở, hỗ trợ tìm kiếm thông minh |
|
||||
| Memory | [powermem](./docs/powermem-integration.md) | Tóm tắt cục bộ | Phụ thuộc vào LLM và DB | OceanBase mã nguồn mở, hỗ trợ tìm kiếm thông minh |
|
||||
| Memory | mem_local_short | Tóm tắt cục bộ | Miễn phí | |
|
||||
| Memory | nomem | Chế độ không có bộ nhớ | Miễn phí | |
|
||||
|
||||
@@ -343,13 +358,13 @@ Trên thực tế, bất kỳ VLLM nào hỗ trợ gọi giao diện openai đ
|
||||
|
||||
| Logo | Dự án/Công ty | Mô tả |
|
||||
|:---:|:---:|:---|
|
||||
| <img src="../images/logo_bailing.png" width="160"> | [Robot đối thoại giọng nói Bailing](https://github.com/wwbin2017/bailing) | Dự án này được lấy cảm hứng từ [Robot đối thoại giọng nói Bailing](https://github.com/wwbin2017/bailing) và được triển khai trên cơ sở đó |
|
||||
| <img src="../images/logo_tenclass.png" width="160"> | [Shifang Ronghai](https://www.tenclass.com/) | Cảm ơn [Shifang Ronghai](https://www.tenclass.com/) đã xây dựng giao thức truyền thông tiêu chuẩn, phương án tương thích đa thiết bị và mô phạm thực hành tình huống đồng thời cao cho hệ sinh thái Xiaozhi; cung cấp tài liệu hỗ trợ kỹ thuật toàn diện cho dự án này |
|
||||
| <img src="../images/logo_xuanfeng.png" width="160"> | [Xuanfeng Technology](https://github.com/Eric0308) | Cảm ơn [Xuanfeng Technology](https://github.com/Eric0308) đã đóng góp khung gọi hàm, giao thức truyền thông MCP và mã triển khai cơ chế gọi dạng plugin, thông qua hệ thống điều phối lệnh tiêu chuẩn hóa và khả năng mở rộng động, đã cải thiện đáng kể hiệu suất tương tác và khả năng mở rộng chức năng của thiết bị front-end(IoT) |
|
||||
| <img src="../images/logo_junsen.png" width="160"> | [huangjunsen](https://github.com/huangjunsen0406) | Cảm ơn [huangjunsen](https://github.com/huangjunsen0406) đã đóng góp module `Bảng điều khiển thông minh di động`, thực hiện điều khiển hiệu quả và tương tác thời gian thực trên thiết bị di động đa nền tảng, cải thiện đáng kể sự tiện lợi vận hành và hiệu quả quản lý của hệ thống trong tình huống di động |
|
||||
| <img src="../images/logo_huiyuan.png" width="160"> | [Huiyuan Design](http://ui.kwd988.net/) | Cảm ơn [Huiyuan Design](http://ui.kwd988.net/) đã cung cấp giải pháp thị giác chuyên nghiệp cho dự án này, sử dụng kinh nghiệm thực tế thiết kế phục vụ hơn nghìn doanh nghiệp, trao quyền cho trải nghiệm người dùng sản phẩm của dự án này |
|
||||
| <img src="../images/logo_qinren.png" width="160"> | [Xi'an Qinren Information Technology](https://www.029app.com/) | Cảm ơn [Xi'an Qinren Information Technology](https://www.029app.com/) đã làm sâu sắc hệ thống thị giác của dự án này, đảm bảo tính nhất quán và khả năng mở rộng của phong cách thiết kế tổng thể trong ứng dụng đa tình huống |
|
||||
| <img src="../images/logo_contributors.png" width="160"> | [Người đóng góp mã](https://github.com/xinnan-tech/xiaozhi-esp32-server/graphs/contributors) | Cảm ơn [tất cả người đóng góp mã](https://github.com/xinnan-tech/xiaozhi-esp32-server/graphs/contributors), sự cống hiến của bạn khiến dự án mạnh mẽ và vững chắc hơn. |
|
||||
| <img src="./docs/images/logo_bailing.png" width="160"> | [Robot đối thoại giọng nói Bailing](https://github.com/wwbin2017/bailing) | Dự án này được lấy cảm hứng từ [Robot đối thoại giọng nói Bailing](https://github.com/wwbin2017/bailing) và được triển khai trên cơ sở đó |
|
||||
| <img src="./docs/images/logo_tenclass.png" width="160"> | [Shifang Ronghai](https://www.tenclass.com/) | Cảm ơn [Shifang Ronghai](https://www.tenclass.com/) đã xây dựng giao thức truyền thông tiêu chuẩn, phương án tương thích đa thiết bị và mô phạm thực hành tình huống đồng thời cao cho hệ sinh thái Xiaozhi; cung cấp tài liệu hỗ trợ kỹ thuật toàn diện cho dự án này |
|
||||
| <img src="./docs/images/logo_xuanfeng.png" width="160"> | [Xuanfeng Technology](https://github.com/Eric0308) | Cảm ơn [Xuanfeng Technology](https://github.com/Eric0308) đã đóng góp khung gọi hàm, giao thức truyền thông MCP và mã triển khai cơ chế gọi dạng plugin, thông qua hệ thống điều phối lệnh tiêu chuẩn hóa và khả năng mở rộng động, đã cải thiện đáng kể hiệu suất tương tác và khả năng mở rộng chức năng của thiết bị front-end(IoT) |
|
||||
| <img src="./docs/images/logo_junsen.png" width="160"> | [huangjunsen](https://github.com/huangjunsen0406) | Cảm ơn [huangjunsen](https://github.com/huangjunsen0406) đã đóng góp module `Bảng điều khiển thông minh di động`, thực hiện điều khiển hiệu quả và tương tác thời gian thực trên thiết bị di động đa nền tảng, cải thiện đáng kể sự tiện lợi vận hành và hiệu quả quản lý của hệ thống trong tình huống di động |
|
||||
| <img src="./docs/images/logo_huiyuan.png" width="160"> | [Huiyuan Design](http://ui.kwd988.net/) | Cảm ơn [Huiyuan Design](http://ui.kwd988.net/) đã cung cấp giải pháp thị giác chuyên nghiệp cho dự án này, sử dụng kinh nghiệm thực tế thiết kế phục vụ hơn nghìn doanh nghiệp, trao quyền cho trải nghiệm người dùng sản phẩm của dự án này |
|
||||
| <img src="./docs/images/logo_qinren.png" width="160"> | [Xi'an Qinren Information Technology](https://www.029app.com/) | Cảm ơn [Xi'an Qinren Information Technology](https://www.029app.com/) đã làm sâu sắc hệ thống thị giác của dự án này, đảm bảo tính nhất quán và khả năng mở rộng của phong cách thiết kế tổng thể trong ứng dụng đa tình huống |
|
||||
| <img src="./docs/images/logo_contributors.png" width="160"> | [Người đóng góp mã](https://github.com/xinnan-tech/xiaozhi-esp32-server/graphs/contributors) | Cảm ơn [tất cả người đóng góp mã](https://github.com/xinnan-tech/xiaozhi-esp32-server/graphs/contributors), sự cống hiến của bạn khiến dự án mạnh mẽ và vững chắc hơn. |
|
||||
|
||||
|
||||
<a href="https://star-history.com/#xinnan-tech/xiaozhi-esp32-server&Date">
|
||||
+1
-1
@@ -241,7 +241,7 @@ LLM:
|
||||
250427 13:04:20[0.3.11_SiFuChTTnofu][__main__]-INFO-OTA接口是 http://192.168.4.123:8003/xiaozhi/ota/
|
||||
250427 13:04:20[0.3.11_SiFuChTTnofu][__main__]-INFO-Websocket地址是 ws://192.168.4.123:8000/xiaozhi/v1/
|
||||
250427 13:04:20[0.3.11_SiFuChTTnofu][__main__]-INFO-=======上面的地址是websocket协议地址，请勿用浏览器访问=======
|
||||
250427 13:04:20[0.3.11_SiFuChTTnofu][__main__]-INFO-如想测试websocket请启动digital-human模块，打开浏览器交互测试
|
||||
250427 13:04:20[0.3.11_SiFuChTTnofu][__main__]-INFO-如想测试websocket请用谷歌浏览器打开test目录下的test_page.html
|
||||
250427 13:04:20[0.3.11_SiFuChTTnofu][__main__]-INFO-=======================================================
|
||||
```
|
||||
|
||||
|
||||
@@ -198,7 +198,7 @@ docker logs -f xiaozhi-esp32-server
|
||||
```
|
||||
25-02-23 12:01:09[core.websocket_server] - INFO - Websocket地址是 ws://xxx.xx.xx.xx:8000/xiaozhi/v1/
|
||||
25-02-23 12:01:09[core.websocket_server] - INFO - =======上面的地址是websocket协议地址，请勿用浏览器访问=======
|
||||
25-02-23 12:01:09[core.websocket_server] - INFO - 如想测试websocket请启动digital-human模块，打开浏览器交互测试
|
||||
25-02-23 12:01:09[core.websocket_server] - INFO - 如想测试websocket请用谷歌浏览器打开test目录下的test_page.html
|
||||
25-02-23 12:01:09[core.websocket_server] - INFO - =======================================================
|
||||
```
|
||||
|
||||
@@ -431,7 +431,7 @@ python app.py
|
||||
```
|
||||
25-02-23 12:01:09[core.websocket_server] - INFO - Server is running at ws://xxx.xx.xx.xx:8000/xiaozhi/v1/
|
||||
25-02-23 12:01:09[core.websocket_server] - INFO - =======上面的地址是websocket协议地址，请勿用浏览器访问=======
|
||||
25-02-23 12:01:09[core.websocket_server] - INFO - 如想测试websocket请启动digital-human模块，打开浏览器交互测试
|
||||
25-02-23 12:01:09[core.websocket_server] - INFO - 如想测试websocket请用谷歌浏览器打开test目录下的test_page.html
|
||||
25-02-23 12:01:09[core.websocket_server] - INFO - =======================================================
|
||||
```
|
||||
|
||||
|
||||
+2
-9
@@ -65,14 +65,13 @@ VAD:
|
||||
3、[如何部署MQTT网关开启MQTT+UDP协议](./mqtt-gateway-integration.md)<br/>
|
||||
4、[如何自动拉取本项目最新代码自动编译和启动](./dev-ops-integration.md)<br/>
|
||||
5、[如何与Nginx集成](https://github.com/xinnan-tech/xiaozhi-esp32-server/issues/791)<br/>
|
||||
6、[修改代码后怎么编译自己的Docker镜像](./docker-build.md)<br/>
|
||||
|
||||
### 8、编译固件相关教程
|
||||
### 9、编译固件相关教程
|
||||
1、[如何自己编译小智固件](./firmware-build.md)<br/>
|
||||
2、[如何基于虾哥编译好的固件修改OTA地址](./firmware-setting.md)<br/>
|
||||
3、[单模块部署如何配置固件OTA自动升级](./ota-upgrade-guide.md)<br/>
|
||||
|
||||
### 9、拓展相关教程
|
||||
### 10、拓展相关教程
|
||||
1、[如何开启手机号码注册智控台](./ali-sms-integration.md)<br/>
|
||||
2、[如何集成HomeAssistant实现智能家居控制](./homeassistant-integration.md)<br/>
|
||||
3、[如何开启视觉模型实现拍照识物](./mcp-vision-integration.md)<br/>
|
||||
@@ -85,12 +84,6 @@ VAD:
|
||||
10、[如何部署上下文源](./context-provider-integration.md)<br/>
|
||||
11、[如何集成PowerMem智能记忆](./powermem-integration.md)<br/>
|
||||
12、[如何配置天气插件查询天气](./weather-integration.md)<br/>
|
||||
13、[如何开启设备呼叫插件](./device-call-guide.md)<br/>
|
||||
14、[如何开启联网搜索功能](./web-search-integration.md)<br/>
|
||||
|
||||
### 10、数字人相关教程
|
||||
1、[数字人digital-human启动方法](./digital-human-wakeword.md)<br/>
|
||||
2、[如何在N100迷你主机上部署数字人digital-human](./all-in-one-digital-human-setup.md)<br/>
|
||||
|
||||
### 11、语音克隆、本地语音部署相关教程
|
||||
1、[如何在智控台克隆音色](./huoshan-streamTTS-voice-cloning.md)<br/>
|
||||
|
||||
@@ -1,442 +0,0 @@
|
||||
# 一体机数字人配置指南
|
||||
|
||||
本项目用于在 x86 架构设备（如迷你主机、工控机、普通电脑等）上部署一套完整的数字人展示系统，实现以下功能：
|
||||
- 开机自动进入 Kiosk 全屏浏览器，展示指定网页
|
||||
- 后台运行唤醒词检测服务，支持语音交互
|
||||
|
||||
> **说明**：本文档以 **Intel N100 迷你主机（天虹 QN10-100B4）** 为例进行部署演示，其他 x86 设备可参考调整（注意网络配置和声卡设备差异）。
|
||||
|
||||
## 适用环境
|
||||
|
||||
| 项目 | 说明 |
|
||||
|------|------|
|
||||
| 示例硬件 | 天虹 QN10-100B4（Intel N100） |
|
||||
| 操作系统 | Ubuntu 24.04 LTS (Noble Numbat) |
|
||||
| 示例用户 | xz（请根据实际情况替换） |
|
||||
| 网络 | Wi-Fi 连接，固定 IP（可按需改为有线） |
|
||||
|
||||
## 部署流程
|
||||
|
||||
1. 系统初始化（换源、连网）
|
||||
2. 安装图形组件与 Kiosk 浏览器
|
||||
3. 配置自动登录与图形界面
|
||||
4. 部署唤醒词服务（Python 环境 + 麦克风）
|
||||
5. 优化开机速度与隐藏启动信息
|
||||
|
||||
---
|
||||
|
||||
|
||||
### 系统初始化（换源、连网）
|
||||
|
||||
```
|
||||
sudo cp /etc/apt/sources.list /etc/apt/sources.list.bak
|
||||
|
||||
sudo tee /etc/apt/sources.list > /dev/null <<EOF
|
||||
deb http://mirrors.aliyun.com/ubuntu/ noble main restricted universe multiverse
|
||||
# deb-src http://mirrors.aliyun.com/ubuntu/ noble main restricted universe multiverse
|
||||
|
||||
deb http://mirrors.aliyun.com/ubuntu/ noble-security main restricted universe multiverse
|
||||
# deb-src http://mirrors.aliyun.com/ubuntu/ noble-security main restricted universe multiverse
|
||||
|
||||
deb http://mirrors.aliyun.com/ubuntu/ noble-updates main restricted universe multiverse
|
||||
# deb-src http://mirrors.aliyun.com/ubuntu/ noble-updates main restricted universe multiverse
|
||||
|
||||
deb http://mirrors.aliyun.com/ubuntu/ noble-proposed main restricted universe multiverse
|
||||
# deb-src http://mirrors.aliyun.com/ubuntu/ noble-proposed main restricted universe multiverse
|
||||
|
||||
deb http://mirrors.aliyun.com/ubuntu/ noble-backports main restricted universe multiverse
|
||||
# deb-src http://mirrors.aliyun.com/ubuntu/ noble-backports main restricted universe multiverse
|
||||
EOF
|
||||
|
||||
echo 'Acquire::ForceIPv4 "true";' | sudo tee /etc/apt/apt.conf.d/99force-ipv4
|
||||
```
|
||||
|
||||
|
||||
安装网络管理工具（若已存在可忽略）
|
||||
|
||||
Bash
|
||||
|
||||
```
|
||||
sudo apt update
|
||||
sudo apt install network-manager -y
|
||||
sudo systemctl start NetworkManager
|
||||
sudo systemctl enable NetworkManager
|
||||
```
|
||||
|
||||
|
||||
设置wifi密码，固定ip
|
||||
|
||||
> **提醒**：以下命令中的 Wi-Fi 名称、密码、IP 地址均为示例，请务必替换为你自己的实际信息。
|
||||
|
||||
Bash
|
||||
|
||||
```
|
||||
sudo nmcli device wifi connect "MERCURY_1812" password "12345678"
|
||||
|
||||
sudo nmcli connection modify "MERCURY_1812" ipv4.addresses "192.168.0.86/24" ipv4.gateway "192.168.0.1" ipv4.dns "8.8.8.8,114.114.114.114" ipv4.method "manual"
|
||||
|
||||
sudo nmcli connection up "MERCURY_1812"
|
||||
```
|
||||
|
||||
|
||||
### 第一步：安装核心图形组件与浏览器
|
||||
|
||||
这里我们坚持“极简主义”，坚决不装多余的桌面环境（如 GNOME/KDE），只装底层驱动、最轻量的窗口管理器（Openbox）、隐藏鼠标工具以及 Chromium 浏览器。
|
||||
|
||||
Bash
|
||||
|
||||
```
|
||||
sudo timedatectl set-timezone Asia/Shanghai
|
||||
|
||||
|
||||
sudo apt install net-tools vim fonts-wqy-microhei fonts-wqy-zenhei alsa-utils pulseaudio -y
|
||||
sudo apt install --no-install-recommends xserver-xorg x11-xserver-utils xinit openbox unclutter -y
|
||||
|
||||
wget https://dl.google.com/linux/direct/google-chrome-stable_current_amd64.deb
|
||||
sudo apt install ./google-chrome-stable_current_amd64.deb -y
|
||||
rm google-chrome-stable_current_amd64.deb
|
||||
|
||||
sudo apt purge snapd -y
|
||||
|
||||
```
|
||||
|
||||
### 第二步：配置 TTY1 开机免密自动登录
|
||||
|
||||
为了避免手动输入账号密码的尴尬，我们通过修改 systemd 服务，让系统一开机就自动以 `xz` 的身份登录。这里使用一键写入命令，彻底避开由于 `nano` 或 `vi` 操作不当导致的保存失败问题。
|
||||
|
||||
**1. 创建配置目录：**
|
||||
|
||||
Bash
|
||||
|
||||
```
|
||||
sudo mkdir -p /etc/systemd/system/getty@tty1.service.d/
|
||||
```
|
||||
|
||||
**2. 写入自动登录规则：**
|
||||
|
||||
Bash
|
||||
|
||||
```
|
||||
echo -e "[Service]\nExecStart=\nExecStart=-/sbin/agetty --autologin xz --noclear %I \$TERM" | sudo tee /etc/systemd/system/getty@tty1.service.d/override.conf
|
||||
```
|
||||
|
||||
**3. 重载服务并设置默认启动目标：**
|
||||
|
||||
Bash
|
||||
|
||||
```
|
||||
sudo systemctl daemon-reload
|
||||
sudo systemctl set-default multi-user.target
|
||||
```
|
||||
|
||||
### 第三步：配置登录后自动启动图形界面
|
||||
|
||||
系统自动登录后默认停留在黑底白字的命令行，我们需要配置脚本，让它一旦登录立马启动 X11 图形环境。
|
||||
|
||||
**1. 触发 `startx` 的启动逻辑：**
|
||||
|
||||
直接将触发代码追加写入你的个人环境配置文件中：
|
||||
|
||||
Bash
|
||||
|
||||
```
|
||||
cat << 'EOF' >> ~/.bash_profile
|
||||
if [ -z "$DISPLAY" ] && [ "$(fgconsole)" -eq 1 ]; then
|
||||
exec startx
|
||||
fi
|
||||
EOF
|
||||
```
|
||||
|
||||
**2. 告诉 `startx` 去启动 Openbox：**
|
||||
|
||||
Bash
|
||||
|
||||
```
|
||||
echo "exec openbox-session" > ~/.xinitrc
|
||||
```
|
||||
|
||||
### 第四步：配置“铜墙铁壁”的 Openbox 与浏览器
|
||||
|
||||
这是最核心的一步：关闭屏幕休眠、隐藏鼠标、全屏锁定浏览器，并写一个“死循环”保证浏览器被意外关闭后也能瞬间复活。
|
||||
|
||||
**1. 创建 Openbox 配置目录：**
|
||||
|
||||
Bash
|
||||
|
||||
```
|
||||
mkdir -p ~/.config/openbox
|
||||
```
|
||||
|
||||
**2. 写入自启动脚本 (`autostart`)：**
|
||||
|
||||
复制以下整段代码并回车（这会自动把所有保护规则写进文件里）：
|
||||
|
||||
Bash
|
||||
|
||||
```
|
||||
cat << 'EOF' > ~/.config/openbox/autostart
|
||||
# 关闭屏幕保护
|
||||
xset -dpms
|
||||
xset s noblank
|
||||
xset s off
|
||||
|
||||
# 隐藏鼠标
|
||||
unclutter -idle 0.1 -root &
|
||||
|
||||
# 死循环启动 Chromium（崩溃或被关也能秒重启）
|
||||
while true; do
|
||||
google-chrome \
|
||||
--kiosk \
|
||||
--no-first-run \
|
||||
--no-default-browser-check \
|
||||
--disable-infobars \
|
||||
--disable-session-crashed-bubble \
|
||||
--disable-translate \
|
||||
--disable-external-intent-requests \
|
||||
--autoplay-policy=no-user-gesture-required \
|
||||
--use-fake-ui-for-media-stream \
|
||||
"https://www.douyin.com"
|
||||
sleep 2
|
||||
done &
|
||||
EOF
|
||||
```
|
||||
|
||||
**3. 屏蔽 `Alt+F4` 退出快捷键：**
|
||||
|
||||
为了防止别人插上键盘强行关掉窗口，我们把 Openbox 默认的系统快捷键干掉。
|
||||
|
||||
Bash
|
||||
|
||||
```
|
||||
cp /etc/xdg/openbox/rc.xml ~/.config/openbox/
|
||||
sed -i '/<keybind key="A-F4">/,/<\/keybind>/d' ~/.config/openbox/rc.xml
|
||||
```
|
||||
|
||||
### 第五步：重启验收成果
|
||||
|
||||
如果拔掉网线或不需要等待所有网络上线，可禁用网络等待服务，避免开机卡顿
|
||||
|
||||
Bash
|
||||
|
||||
```
|
||||
sudo systemctl mask systemd-networkd-wait-online.service
|
||||
sudo systemctl mask NetworkManager-wait-online.service
|
||||
```
|
||||
|
||||
隐藏开机信息（GRUB）
|
||||
|
||||
Bash
|
||||
|
||||
```
|
||||
sudo sed -i 's/GRUB_CMDLINE_LINUX_DEFAULT=.*/GRUB_CMDLINE_LINUX_DEFAULT="quiet loglevel=3 systemd.show_status=false vt.global_cursor_default=0"/g' /etc/default/grub
|
||||
|
||||
echo 'GRUB_TIMEOUT_STYLE="hidden"' | sudo tee -a /etc/default/grub
|
||||
echo 'GRUB_RECORDFAIL_TIMEOUT=0' | sudo tee -a /etc/default/grub
|
||||
|
||||
sudo update-grub
|
||||
```
|
||||
|
||||
声音设置成100%，然后 重启：
|
||||
|
||||
Bash
|
||||
|
||||
```
|
||||
amixer -q sset Master 100% unmute
|
||||
sudo reboot
|
||||
```
|
||||
|
||||
### 部署唤醒词服务
|
||||
|
||||
在一体机上部署唤醒词检测服务，需要安装 Python 环境、上传项目文件、配置 Camera 麦克风和开机自启。
|
||||
|
||||
#### 1. 安装 Miniconda
|
||||
|
||||
```bash
|
||||
wget https://repo.anaconda.com/miniconda/Miniconda3-latest-Linux-x86_64.sh
|
||||
bash Miniconda3-latest-Linux-x86_64.sh -b -p $HOME/miniconda3
|
||||
~/miniconda3/bin/conda init bash
|
||||
source ~/.bashrc
|
||||
rm Miniconda3-latest-Linux-x86_64.sh
|
||||
```
|
||||
|
||||
|
||||
确保登录时自动进入conda环境
|
||||
|
||||
```bash
|
||||
if ! grep -q '.bashrc' ~/.bash_profile; then
|
||||
cat << 'EOF' >> ~/.bash_profile
|
||||
|
||||
if [ -f ~/.bashrc ]; then
|
||||
. ~/.bashrc
|
||||
fi
|
||||
EOF
|
||||
fi
|
||||
```
|
||||
|
||||
|
||||
#### 2. 创建 Python 虚拟环境
|
||||
|
||||
```bash
|
||||
conda create -n test python=3.10 -y
|
||||
conda activate test
|
||||
```
|
||||
|
||||
若出现 Terms of Service have not been accepted 错误，执行：
|
||||
|
||||
```bash
|
||||
conda tos accept --override-channels --channel https://repo.anaconda.com/pkgs/main
|
||||
conda tos accept --override-channels --channel https://repo.anaconda.com/pkgs/r
|
||||
```
|
||||
|
||||
#### 3. 上传项目文件
|
||||
|
||||
将开发机上的 `main/digital-human/` 整个目录上传到一体机的 `~/digital-human/` 目录：
|
||||
|
||||
```bash
|
||||
# 在开发机上执行（将 <一体机IP> 替换为实际 IP）
|
||||
scp -r main/digital-human/ xz@<一体机IP>:~/digital-human/
|
||||
```
|
||||
|
||||
#### 4. 安装系统依赖
|
||||
|
||||
唤醒词服务需要音频采集库和 ALSA PulseAudio 插件：
|
||||
|
||||
```bash
|
||||
sudo apt install libportaudio2 portaudio19-dev libasound2-plugins -y
|
||||
```
|
||||
|
||||
#### 5. 安装 Python 依赖
|
||||
|
||||
```bash
|
||||
cd ~/digital-human/wakeword_runtime
|
||||
pip install numpy
|
||||
pip install -r requirements.txt
|
||||
```
|
||||
|
||||
#### 6. 下载唤醒词模型
|
||||
|
||||
模型文件不包含在项目中，需要单独下载配置，详见 [docs/digital-human-wakeword.md](digital-human-wakeword.md) 中的“模型下载”章节。
|
||||
|
||||
#### 7. 修改 Openbox 自启动脚本
|
||||
|
||||
需要在 autostart 中加上 PulseAudio 和 Camera 麦克风配置，并将 Chrome 地址改为测试页面。
|
||||
|
||||
先确认 Camera 麦克风在 PulseAudio 中的设备名：
|
||||
|
||||
```bash
|
||||
pulseaudio --start
|
||||
pactl list sources short
|
||||
```
|
||||
|
||||
找到包含 `USB_Camera` 的那一行，记下完整名称，例如：
|
||||
|
||||
```
|
||||
alsa_input.usb-SN0002_2K_USB_Camera_46435000_P030D00_SN0002-02.mono-fallback
|
||||
```
|
||||
|
||||
然后用完整内容覆盖 autostart（将 `TARGET_MIC` 替换为你的实际设备名）：
|
||||
|
||||
```bash
|
||||
cat << 'EOF' > ~/.config/openbox/autostart
|
||||
# 1. 启动声音服务并稍作等待
|
||||
pulseaudio --start
|
||||
sleep 1
|
||||
|
||||
# 2. 锁定 Camera 的麦克风（请替换为你的实际设备名）
|
||||
TARGET_MIC="alsa_input.usb-SN0002_2K_USB_Camera_46435000_P030D00_SN0002-02.mono-fallback"
|
||||
|
||||
# 3. 设为系统默认麦克风
|
||||
pactl set-default-source "$TARGET_MIC"
|
||||
|
||||
# 4. 解除静音
|
||||
pactl set-source-mute "$TARGET_MIC" 0
|
||||
|
||||
# 5. 音量拉到 100%
|
||||
pactl set-source-volume "$TARGET_MIC" 100%
|
||||
|
||||
# --- 极简桌面与浏览器环境配置 ---
|
||||
|
||||
# 关闭屏幕保护
|
||||
xset -dpms
|
||||
xset s noblank
|
||||
xset s off
|
||||
|
||||
# 隐藏鼠标
|
||||
unclutter -idle 0.1 -root &
|
||||
|
||||
# 死循环启动浏览器（崩溃或被关也能秒重启）
|
||||
while true; do
|
||||
google-chrome \
|
||||
--kiosk \
|
||||
--no-first-run \
|
||||
--no-default-browser-check \
|
||||
--disable-infobars \
|
||||
--disable-session-crashed-bubble \
|
||||
--disable-translate \
|
||||
--disable-external-intent-requests \
|
||||
--autoplay-policy=no-user-gesture-required \
|
||||
--use-fake-ui-for-media-stream \
|
||||
"http://127.0.0.1:8006/index.html"
|
||||
sleep 2
|
||||
done &
|
||||
EOF
|
||||
```
|
||||
|
||||
#### 8. 配置唤醒词服务开机自启
|
||||
|
||||
创建 systemd 服务文件，让唤醒词服务开机自动运行。
|
||||
|
||||
先确认当前用户的 UID：
|
||||
|
||||
```bash
|
||||
id -u $(whoami)
|
||||
```
|
||||
|
||||
然后用查到的 UID 替换下面 `1000`（通常第一个用户就是 1000）：
|
||||
|
||||
```bash
|
||||
sudo tee /etc/systemd/system/digital-human.service << 'EOF'
|
||||
[Unit]
|
||||
Description=Digital Human Runtime
|
||||
After=network.target sound.target
|
||||
|
||||
[Service]
|
||||
Type=simple
|
||||
User=xz
|
||||
Environment=XDG_RUNTIME_DIR=/run/user/1000
|
||||
Environment=PULSE_SERVER=unix:/run/user/1000/pulse/native
|
||||
WorkingDirectory=/home/xz/digital-human
|
||||
ExecStartPre=/bin/sleep 10
|
||||
ExecStart=/home/xz/miniconda3/envs/test/bin/python start.py
|
||||
Restart=on-failure
|
||||
RestartSec=10
|
||||
|
||||
[Install]
|
||||
WantedBy=multi-user.target
|
||||
EOF
|
||||
```
|
||||
|
||||
> **重要说明**：
|
||||
> - `User=xz` — 替换为你的实际用户名
|
||||
> - `/run/user/1000` — 替换为你实际的 UID
|
||||
> - `WorkingDirectory` 和 `ExecStart` 中的路径 — 替换为你的实际部署路径
|
||||
> - `Environment` 中的 PulseAudio 环境变量**必须保留**，否则唤醒词服务和浏览器无法同时使用 Camera 麦克风
|
||||
|
||||
启用并启动服务：
|
||||
|
||||
```bash
|
||||
sudo systemctl daemon-reload
|
||||
sudo systemctl enable digital-human
|
||||
sudo systemctl start digital-human
|
||||
```
|
||||
|
||||
#### 9. 常用服务管理命令
|
||||
|
||||
```bash
|
||||
sudo systemctl start digital-human # 立即启动
|
||||
sudo systemctl stop digital-human # 停止
|
||||
sudo systemctl restart digital-human # 重启
|
||||
sudo systemctl status digital-human # 查看状态
|
||||
journalctl -u digital-human -f # 查看实时日志
|
||||
```
|
||||
|
||||
@@ -1,148 +0,0 @@
|
||||
# 设备间相互呼叫插件使用指南
|
||||
|
||||
## 概述
|
||||
|
||||
设备呼叫功能允许两个已配置设备之间通过语音/数据通道进行双向通信。设备A呼叫设备B时，系统通过以下流程实现：
|
||||
|
||||
```
|
||||
设备A → 授权校验 → MQTT网关 → 设备B远程唤醒 → 建立连接 → 通话建立
|
||||
```
|
||||
## 使用这个功能的前提条件
|
||||
1. 你必须要有至少两个设备，每个设备型号必须是`ESP32-S3`，因为只有`ESP32-S3`才支持远程唤醒功能。
|
||||
2. 你的设备必须要有`两个麦克风`。但是如果你的设备只有`单个麦克风`，你只是想体验一下这个功能，也是可以的，但是会有强烈的卡顿感。
|
||||
3. 你必须使用[全模块部署](Deployment_all.md)本项目，因为你需要`智控台`来管理设备的权限和通信。
|
||||
4. 你必须安装并配置好`2026年5月27日`以后的[MQTT网关服务](mqtt-gateway-integration.md)，如果你已经部署了MQTT网关服务，请确认代码的版本是`2026年5月27日`之后的版本。
|
||||
|
||||
以上是使用这个功能的硬性条件，接下来会详细介绍。
|
||||
|
||||
## 配置步骤
|
||||
|
||||
### 第一步：开启通讯录功能
|
||||
|
||||
1. 确认你的智控台版本是`0.9.4`或以上版本。
|
||||
2. 登录智控台后台
|
||||
3. 进入 **系统功能配置**
|
||||
4. 在左侧功能列表中勾选 **通讯录**
|
||||
5. 点击 **保存配置** 确认
|
||||
|
||||
### 第二步：配置设备间呼叫权限
|
||||
|
||||
1. 在智控台顶部菜单点击 **通讯录**
|
||||
2. 在左侧智能体下，设备列表中选择你的设备A（支持按 MAC地址 或 备注名 搜索）
|
||||
3. 在右侧详情面板中，找到目标设备B的称呼设置，例如 **"小王"**
|
||||
4. 勾选设备B的 **呼叫权限** 复选框
|
||||
5. 点击 **保存**
|
||||
|
||||
**双向授权说明：** 如需设备A和设备B互相通信，必须在两侧智控台分别配置对方权限。例如：
|
||||
|
||||
- 在设备A的配置中勾选设备B → 设备A可与设备B通信
|
||||
- 在设备B的配置中勾选设备A → 设备B可与设备A通信
|
||||
|
||||
### 第三步：在智能体配置添加呼叫工具
|
||||
|
||||
1. 在智控台顶部菜单点击 **智能体管理**
|
||||
2. 在刚刚配置设备联系人的相关智能体中点击 **编辑角色**
|
||||
3. 在右侧详情面板中，点击 **编辑功能**
|
||||
4. 勾选 **设备呼叫设备** 工具
|
||||
5. 点击 **保存配置** 确认
|
||||
6. 在外侧再次点击 **保存配置** ，随即重启设备
|
||||
|
||||
### 第四步：固件端添加远程唤醒工具
|
||||
|
||||
1. 在[xiaozhi-esp32](https://github.com/78/xiaozhi-esp32) 代码的基础上增加远程唤醒工具MCP，版本支持为2.1.0至2.2.6（2026年5月29日的版本）
|
||||
2. 在application.h文件中添加远程唤醒函数声明
|
||||
```cpp
|
||||
void RemoteWakeup(const std::string& reason);
|
||||
```
|
||||
3. 在application.cc文件中添加远程唤醒函数
|
||||
```cpp
|
||||
void Application::RemoteWakeup(const std::string& reason){
|
||||
if (!protocol_) {
|
||||
return;
|
||||
}
|
||||
|
||||
auto state = GetDeviceState();
|
||||
|
||||
if (state == kDeviceStateIdle) {
|
||||
audio_service_.EncodeWakeWord();
|
||||
|
||||
if (!protocol_->IsAudioChannelOpened()) {
|
||||
SetDeviceState(kDeviceStateConnecting);
|
||||
if (!protocol_->OpenAudioChannel()) {
|
||||
audio_service_.EnableWakeWordDetection(true);
|
||||
return;
|
||||
}
|
||||
}
|
||||
std::string wake_word = reason;
|
||||
#if CONFIG_USE_AFE_WAKE_WORD || CONFIG_USE_CUSTOM_WAKE_WORD
|
||||
// Encode and send the wake word data to the server
|
||||
while (auto packet = audio_service_.PopWakeWordPacket()) {
|
||||
protocol_->SendAudio(std::move(packet));
|
||||
}
|
||||
// Set the chat state to wake word detected
|
||||
protocol_->SendWakeWordDetected(wake_word);
|
||||
SetListeningMode(aec_mode_ == kAecOff ? kListeningModeAutoStop : kListeningModeRealtime);
|
||||
#else
|
||||
// Set flag to play popup sound after state changes to listening
|
||||
// (PlaySound here would be cleared by ResetDecoder in EnableVoiceProcessing)
|
||||
play_popup_on_listening_ = true;
|
||||
SetListeningMode(aec_mode_ == kAecOff ? kListeningModeAutoStop : kListeningModeRealtime);
|
||||
#endif
|
||||
} else if (state == kDeviceStateSpeaking) {
|
||||
AbortSpeaking(kAbortReasonWakeWordDetected);
|
||||
SetDeviceState(kDeviceStateIdle);
|
||||
} else if (state == kDeviceStateActivating) {
|
||||
SetDeviceState(kDeviceStateIdle);
|
||||
}
|
||||
}
|
||||
```
|
||||
4. 在mcp_server.cc文件中添加远程唤醒工具
|
||||
```cpp
|
||||
AddUserOnlyTool("self.remote_wakeup", "Remote wakeup function with configurable parameters",
|
||||
PropertyList({
|
||||
Property("reason", kPropertyTypeString, "Wakeup reason"),
|
||||
}),
|
||||
[this](const PropertyList& properties) -> ReturnValue {
|
||||
std::string reason = properties["reason"].value<std::string>();
|
||||
ESP_LOGI(TAG, "Wakeup reason=%s", reason.c_str());
|
||||
auto& app = Application::GetInstance();
|
||||
app.RemoteWakeup(reason);
|
||||
return true;
|
||||
```
|
||||
5. 按照 [固件编译烧录指南](firmware-build.md) 完成固件烧录
|
||||
6. 无论你的设备是单麦还是双麦，请在编译环节，勾选开启AEC功能!
|
||||
7. 无论你的设备是单麦还是双麦，请在编译环节，勾选开启AEC功能!
|
||||
8. 无论你的设备是单麦还是双麦，请在编译环节，勾选开启AEC功能!
|
||||
|
||||
### 第五步：配置MQTT网关服务
|
||||
|
||||
1. 部署MQTT网关服务，参考 [MQTT网关集成文档](mqtt-gateway-integration.md)
|
||||
2. 如果已经部署请确认代码的版本是2026年5月27日的版本
|
||||
|
||||
## 呼叫流程说明
|
||||
|
||||
准备两个设备，在智控台上面配置好通讯权限和在智能体中添加呼叫工具之后，在其中一个小智对话那里对他说：”呼叫XXX“，观察设备B是否响应。
|
||||
|
||||
## 常见问题
|
||||
|
||||
### Q: 设备B没有响应呼叫？
|
||||
|
||||
- 检查设备B是否在线（智控台设备状态）
|
||||
- 确认设备B的固件已正确集成远程唤醒工具
|
||||
- 检查MQTT网关连接是否正常
|
||||
- 验证双向权限配置是否完整
|
||||
|
||||
### Q: 提示"无呼叫权限"？
|
||||
|
||||
- 在智控台确认设备A已勾选设备B的呼叫权限
|
||||
- 确认配置已保存（非仅修改未保存）
|
||||
|
||||
### Q: 如何确认通讯录功能已开启？
|
||||
|
||||
- 智控台顶部菜单如显示"通讯录"入口，则表示已开启
|
||||
|
||||
### Q: 我叫他呼叫"张山"，但是他老是识别成"张三"，怎么办？
|
||||
- 可以查阅你使用的asr服务的文档，确认是否支持热词识别。
|
||||
- 如果你用的是`FunASRServer`,可以在容器里的`热词文件`里添加"张山"，然后重启容器。
|
||||
- 如果你用的是`火山引擎`的服务，可以在`火山引擎的控制台`里添加`热词文件`，然后回到智控台的`模型配置页面`，把`热词文件名称`配置在`火山引擎的tts`上去。
|
||||
|
||||
@@ -1,220 +0,0 @@
|
||||
# 数字人digital-human启动方法
|
||||
|
||||
## 概述
|
||||
|
||||
测试页面集成了基于 **Sherpa-ONNX** 的高精度语音唤醒功能，支持自定义唤醒词和实时检测。使用轻量级关键词检测模型，提供毫秒级响应速度。
|
||||
|
||||
## 唤醒词模型
|
||||
|
||||
### 模型下载（必需）
|
||||
|
||||
**重要说明**: 项目不包含模型文件，需要提前下载配置。
|
||||
|
||||
### 官方模型下载地址
|
||||
|
||||
- **官方模型列表**: <https://csukuangfj.github.io/sherpa/onnx/kws/pretrained_models/index.html>
|
||||
- **推荐模型**: `sherpa-onnx-kws-zipformer-wenetspeech-3.3M-2024-01-01`
|
||||
|
||||
### 下载和配置步骤
|
||||
|
||||
#### 1. 下载模型包
|
||||
|
||||
```bash
|
||||
# 方法1：直接下载（推荐）
|
||||
cd main/digital-human/wakeword_runtime/
|
||||
wget https://github.com/k2-fsa/sherpa-onnx/releases/download/kws-models/sherpa-onnx-kws-zipformer-wenetspeech-3.3M-2024-01-01.tar.bz2
|
||||
|
||||
# 解压
|
||||
tar xvf sherpa-onnx-kws-zipformer-wenetspeech-3.3M-2024-01-01.tar.bz2
|
||||
|
||||
# 方法2：使用ModelScope
|
||||
pip install modelscope
|
||||
python -c "
|
||||
from modelscope import snapshot_download
|
||||
snapshot_download('pkufool/sherpa-onnx-kws-zipformer-wenetspeech-3.3M-2024-01-01', cache_dir='./models')
|
||||
"
|
||||
```
|
||||
|
||||
#### 2. 配置模型文件
|
||||
|
||||
模型包下载后包含以下文件：
|
||||
|
||||
```
|
||||
sherpa-onnx-kws-zipformer-wenetspeech-3.3M-2024-01-01/
|
||||
├── encoder-epoch-12-avg-2-chunk-16-left-64.int8.onnx # 速度优先
|
||||
├── encoder-epoch-12-avg-2-chunk-16-left-64.onnx
|
||||
├── encoder-epoch-99-avg-1-chunk-16-left-64.int8.onnx # 速度优先
|
||||
├── encoder-epoch-99-avg-1-chunk-16-left-64.onnx # 精度优先
|
||||
├── decoder-epoch-12-avg-2-chunk-16-left-64.onnx
|
||||
├── decoder-epoch-99-avg-1-chunk-16-left-64.onnx # 精度优先
|
||||
├── joiner-epoch-12-avg-2-chunk-16-left-64.int8.onnx # 速度优先
|
||||
├── joiner-epoch-12-avg-2-chunk-16-left-64.onnx
|
||||
├── joiner-epoch-99-avg-1-chunk-16-left-64.int8.onnx # 速度优先
|
||||
├── joiner-epoch-99-avg-1-chunk-16-left-64.onnx # 精度优先
|
||||
├── tokens.txt # Token映射表（必需）
|
||||
├── keywords_raw.txt # 模型包里可能附带（可选，runtime 不依赖）
|
||||
├── keywords.txt # 现成的
|
||||
├── test_wavs/ # 测试音频（可选）
|
||||
├── configuration.json # 模型元信息（可选）
|
||||
└── README.md # 说明文档（可选）
|
||||
```
|
||||
|
||||
#### 3. 选择配置方案
|
||||
|
||||
**方案一：精度优先（推荐）**
|
||||
|
||||
```bash
|
||||
cd sherpa-onnx-kws-zipformer-wenetspeech-3.3M-2024-01-01
|
||||
|
||||
# 创建模型目录
|
||||
mkdir -p ../models
|
||||
|
||||
# 复制精度优先的epoch-99 fp32三件套
|
||||
cp encoder-epoch-99-avg-1-chunk-16-left-64.onnx ../models/encoder.onnx
|
||||
cp decoder-epoch-99-avg-1-chunk-16-left-64.onnx ../models/decoder.onnx
|
||||
cp joiner-epoch-99-avg-1-chunk-16-left-64.onnx ../models/joiner.onnx
|
||||
|
||||
# 复制配套文件
|
||||
cp tokens.txt ../models/tokens.txt
|
||||
# keywords_raw.txt 如果模型包里附带，可自行保留；runtime 不依赖它
|
||||
```
|
||||
|
||||
**方案二：速度优先**
|
||||
|
||||
```bash
|
||||
cd sherpa-onnx-kws-zipformer-wenetspeech-3.3M-2024-01-01
|
||||
|
||||
# 创建模型目录
|
||||
mkdir -p ../models
|
||||
|
||||
# 复制速度优先的epoch-99 int8三件套
|
||||
cp encoder-epoch-99-avg-1-chunk-16-left-64.int8.onnx ../models/encoder.onnx
|
||||
cp decoder-epoch-99-avg-1-chunk-16-left-64.onnx ../models/decoder.onnx
|
||||
cp joiner-epoch-99-avg-1-chunk-16-left-64.int8.onnx ../models/joiner.onnx
|
||||
|
||||
# 复制配套文件
|
||||
cp tokens.txt ../models/tokens.txt
|
||||
```
|
||||
|
||||
**注意事项**:
|
||||
|
||||
- **不要混用 fp32 与 int8**：三个模型文件必须保持一致的精度
|
||||
- **优先选择 epoch-99**：比 epoch-12 训练更充分，精度更高
|
||||
- **必需文件**：`encoder.onnx` + `decoder.onnx` + `joiner.onnx` + `tokens.txt` + `keywords.txt`
|
||||
|
||||
### 最终模型文件结构
|
||||
|
||||
配置完成后，模型文件应放在 `wakeword_runtime/models/` 目录下，完整路径为 `main/digital-human/wakeword_runtime/models/`：
|
||||
|
||||
```
|
||||
wakeword_runtime/models/
|
||||
├── encoder.onnx # 编码器模型（重命名后）
|
||||
├── decoder.onnx # 解码器模型（重命名后）
|
||||
├── joiner.onnx # 连接器模型（重命名后）
|
||||
├── tokens.txt # 拼音 Token 映射表（228行版本）
|
||||
├── keywords.txt # 关键词配置文件（首次启动自动生成）
|
||||
└── keywords_raw.txt # 可选，runtime 不依赖
|
||||
```
|
||||
|
||||
## 启动方式
|
||||
|
||||
在 `main/digital-human` 目录执行：
|
||||
|
||||
```bash
|
||||
pip install -r wakeword_runtime/requirements.txt
|
||||
python start.py
|
||||
```
|
||||
|
||||
启动后默认地址：
|
||||
|
||||
- 页面地址：`http://127.0.0.1:8006/index.html`
|
||||
- 事件桥地址：`ws://127.0.0.1:8006/wakeword-ws`
|
||||
- 健康检查：`http://127.0.0.1:8006/health`
|
||||
|
||||
停止方式：
|
||||
|
||||
- 在运行终端按 `Ctrl+C`
|
||||
- 会同时停止静态页面服务、事件桥和唤醒词检测流程
|
||||
|
||||
## 配置文件说明
|
||||
|
||||
配置文件位于 [main/digital-human/wakeword_runtime/config.json](../main/digital-human/wakeword_runtime/config.json)。
|
||||
|
||||
当前主要配置项：
|
||||
|
||||
```json
|
||||
{
|
||||
"wakeword": {
|
||||
"enabled": true
|
||||
},
|
||||
"model_dir": "models",
|
||||
"audio": {
|
||||
"input_device": null,
|
||||
"sample_rate": 16000,
|
||||
"channels": 1
|
||||
},
|
||||
"detector": {
|
||||
"num_threads": 4,
|
||||
"provider": "cpu",
|
||||
"max_active_paths": 2,
|
||||
"keywords_score": 1.8,
|
||||
"keywords_threshold": 0.1,
|
||||
"num_trailing_blanks": 1,
|
||||
"cooldown_seconds": 1.5
|
||||
},
|
||||
"logging": {
|
||||
"level": "INFO",
|
||||
"dir": "logs",
|
||||
"file": "wakeword-runtime.log"
|
||||
}
|
||||
}
|
||||
```
|
||||
|
||||
各字段含义：
|
||||
|
||||
| 参数 | 说明 |
|
||||
| --- | --- |
|
||||
| `wakeword.enabled` | 是否启用本地唤醒词检测 |
|
||||
| `model_dir` | 模型和词表所在目录 |
|
||||
| `audio.input_device` | 麦克风输入设备，默认使用系统默认设备 |
|
||||
| `audio.sample_rate` | 采样率，默认 `16000` |
|
||||
| `audio.channels` | 声道数，默认 `1` |
|
||||
| `detector.num_threads` | 检测器线程数 |
|
||||
| `detector.provider` | 推理 provider，当前通常为 `cpu` |
|
||||
| `detector.max_active_paths` | 搜索路径数 |
|
||||
| `detector.keywords_score` | 关键词增强分数 |
|
||||
| `detector.keywords_threshold` | 检测阈值 |
|
||||
| `detector.num_trailing_blanks` | 尾随空白数量 |
|
||||
| `detector.cooldown_seconds` | 连续触发冷却时间 |
|
||||
| `logging.level` | 日志等级 |
|
||||
| `logging.dir` | 日志目录 |
|
||||
| `logging.file` | 日志文件名 |
|
||||
|
||||
## 推荐使用流程
|
||||
|
||||
### 首次使用
|
||||
|
||||
1. 准备 `models/` 目录下的模型文件和 `tokens.txt`
|
||||
2. 确认 `models/keywords.txt` 存在
|
||||
3. 在 `digital-human` 目录运行 `python start.py`
|
||||
4. 浏览器打开 `http://127.0.0.1:8006/index.html`
|
||||
5. 进入设置页检查“唤醒词”配置
|
||||
|
||||
### 修改唤醒词
|
||||
|
||||
1. 打开数字人页面设置
|
||||
2. 切到“唤醒词”页签
|
||||
3. 修改启用状态或唤醒词列表
|
||||
4. 点击“应用唤醒词”
|
||||
5. 根据提示决定是否立即重启
|
||||
|
||||
### 禁用唤醒词
|
||||
|
||||
1. 将“启用本地唤醒词”改成禁用
|
||||
2. 点击“应用唤醒词”
|
||||
3. 建议立即重启一次
|
||||
|
||||
禁用后：
|
||||
|
||||
- 页面与事件桥仍然可用
|
||||
- 唤醒词检测不会继续运行
|
||||
+12
-65
@@ -1,74 +1,21 @@
|
||||
# 本地编译docker镜像方法
|
||||
|
||||
现在本项目已经使用`github`的`自动编译docker镜像`功能，如果您拉取的是项目发行的镜像，您没有自己编译镜像的需求，那就忽略本文档。
|
||||
现在本项目已经使用github自动编译docker功能，本文档是提供给有本地编译docker镜像需求的朋友准备的。
|
||||
|
||||
如果您修改了源码，然后想采用`docker`的方式部署运行，可以参照以下步骤操作：
|
||||
|
||||
## 1、环境准备
|
||||
|
||||
安装docker：
|
||||
```bash
|
||||
1、安装docker
|
||||
```
|
||||
sudo apt-get install docker-ce docker-ce-cli containerd.io docker-buildx-plugin docker-compose-plugin
|
||||
```
|
||||
|
||||
## 2、编译镜像
|
||||
|
||||
当你修改好代码后，需要编译新的镜像时，需要按照以下步骤操作：
|
||||
|
||||
准备好你的`你的用户名`和`新的版本号`。
|
||||
- 这个`你的用户名`是你在`docker hub`注册的用户名，例如`xiaozhi`。当然，如果你不需要推送到`docker hub`，你可以自由定义。
|
||||
- 这个`新的版本号`是你编译的镜像版本，例如`1.2.3`，你可以根据需要自定义或者使用日期格式（例如`20260609`）主要是方便和现在运行的版本号做区分，同时也方便下次回忆你是什么时候构建的，不要和现在你本机运行的版本号相同。
|
||||
|
||||
进入`xiaozhi-esp32-server`项目根目录，编译 server 和 web 两个镜像：
|
||||
|
||||
```bash
|
||||
cd 项目根目录
|
||||
|
||||
# 编译server镜像
|
||||
docker build -f Dockerfile-server -t 你的用户名/xiaozhi-esp32-server:新的版本号 .
|
||||
|
||||
# 编译web镜像
|
||||
docker build -f Dockerfile-web -t 你的用户名/xiaozhi-esp32-server-web:新的版本号 .
|
||||
|
||||
2、编译docker镜像
|
||||
```
|
||||
#进入项目根目录
|
||||
# 编译server
|
||||
docker build -t xiaozhi-esp32-server:server_latest -f ./Dockerfile-server .
|
||||
# 编译web
|
||||
docker build -t xiaozhi-esp32-server:web_latest -f ./Dockerfile-web .
|
||||
|
||||
## 3、修改docker-compose配置
|
||||
|
||||
```bash
|
||||
# 编译完成后，可以使用docker-compose启动项目
|
||||
# docker-compose.yml你需要修改成自己编译的镜像版本
|
||||
cd main/xiaozhi-server
|
||||
```
|
||||
|
||||
编辑 `docker-compose_all.yml` 文件，将镜像版本替换为你刚才编译的版本：
|
||||
|
||||
```yaml
|
||||
services:
|
||||
xiaozhi-esp32-server:
|
||||
image: 你的用户名/xiaozhi-esp32-server:新的版本号 # 修改为你的镜像地址
|
||||
...
|
||||
|
||||
xiaozhi-esp32-server-web:
|
||||
image: 你的用户名/xiaozhi-esp32-server-web:新的版本号 #修改为你的镜像地址
|
||||
...
|
||||
```
|
||||
|
||||
## 4、重启服务
|
||||
|
||||
```bash
|
||||
# 停止旧容器
|
||||
docker compose -f docker-compose_all.yml down
|
||||
|
||||
# 启动新容器
|
||||
docker compose -f docker-compose_all.yml up -d
|
||||
```
|
||||
|
||||
## 5、验证
|
||||
|
||||
查看日志确认服务启动正常：
|
||||
|
||||
```bash
|
||||
# 查看server日志
|
||||
docker logs -f -n 50 xiaozhi-esp32-server
|
||||
|
||||
# 查看web日志
|
||||
docker logs -f -n 50 xiaozhi-esp32-server-web
|
||||
docker compose up -d
|
||||
```
|
||||
|
||||
@@ -13,9 +13,9 @@ http://192.168.1.25:8003/xiaozhi/ota/
|
||||
```
|
||||
如果显示“OTA接口运行正常，向设备发送的websocket地址是：ws://xxx:8000/xiaozhi/v1/
|
||||
|
||||
你可以启动`digital-human`模块后打开`index.html`测试一下，是否能连上ota页面输出的websocket地址。
|
||||
你可以使用项目自带的`test_page.html`测试一下，是否能连上ota页面输出的websocket地址。
|
||||
|
||||
如果访问不到，你需要到配置文件`.config.yaml`里修改`server.websocket`的地址，重启后再重新测试，直到`index.html`能正常访问。
|
||||
如果访问不到，你需要到配置文件`.config.yaml`里修改`server.websocket`的地址，重启后再重新测试，直到`test_page.html`能正常访问。
|
||||
|
||||
成功后，请往下进行第2步
|
||||
|
||||
|
||||
Binary file not shown.
|
Before Width: | Height: | Size: 152 KiB After Width: | Height: | Size: 289 KiB |
Binary file not shown.
|
Before Width: | Height: | Size: 143 KiB After Width: | Height: | Size: 325 KiB |
Binary file not shown.
|
Before Width: | Height: | Size: 108 KiB After Width: | Height: | Size: 280 KiB |
@@ -118,7 +118,7 @@ mcp_endpoint: ws://192.168.1.25:8004/mcp_endpoint/mcp/?token=def
|
||||
250705[__main__]-INFO-mcp接入点是 ws://192.168.1.25:8004/mcp_endpoint/mcp/?token=abc
|
||||
250705[__main__]-INFO-Websocket地址是 ws://192.168.1.25:8000/xiaozhi/v1/
|
||||
250705[__main__]-INFO-=======上面的地址是websocket协议地址，请勿用浏览器访问=======
|
||||
250705[__main__]-INFO-如想测试websocket请启动digital-human模块，打开浏览器交互测试
|
||||
250705[__main__]-INFO-如想测试websocket请用谷歌浏览器打开test目录下的test_page.html
|
||||
250705[__main__]-INFO-=============================================================
|
||||
```
|
||||
|
||||
|
||||
@@ -23,7 +23,7 @@
|
||||
250705[__main__]-INFO-mcp接入点是 ws://192.168.1.25:8004/mcp_endpoint/mcp/?token=abc
|
||||
250705[__main__]-INFO-Websocket地址是 ws://192.168.1.25:8000/xiaozhi/v1/
|
||||
250705[__main__]-INFO-=======上面的地址是websocket协议地址，请勿用浏览器访问=======
|
||||
250705[__main__]-INFO-如想测试websocket请启动digital-human模块，打开浏览器交互测试
|
||||
250705[__main__]-INFO-如想测试websocket请用谷歌浏览器打开test目录下的test_page.html
|
||||
250705[__main__]-INFO-=============================================================
|
||||
```
|
||||
|
||||
|
||||
@@ -58,7 +58,7 @@ docker restart xiaozhi-esp32-server
|
||||
2025-06-01 **** - 视觉分析接口是 http://192.168.4.7:8003/mcp/vision/explain
|
||||
2025-06-01 **** - Websocket地址是 ws://192.168.4.7:8000/xiaozhi/v1/
|
||||
2025-06-01 **** - =======上面的地址是websocket协议地址，请勿用浏览器访问=======
|
||||
2025-06-01 **** - 如想测试websocket请启动digital-human模块，打开浏览器交互测试
|
||||
2025-06-01 **** - 如想测试websocket请用谷歌浏览器打开test目录下的test_page.html
|
||||
2025-06-01 **** - =============================================================
|
||||
```
|
||||
|
||||
@@ -133,7 +133,7 @@ docker restart xiaozhi-esp32-server
|
||||
2025-06-01 **** - 视觉分析接口是 http://192.168.4.7:8003/mcp/vision/explain
|
||||
2025-06-01 **** - Websocket地址是 ws://192.168.4.7:8000/xiaozhi/v1/
|
||||
2025-06-01 **** - =======上面的地址是websocket协议地址，请勿用浏览器访问=======
|
||||
2025-06-01 **** - 如想测试websocket请启动digital-human模块，打开浏览器交互测试
|
||||
2025-06-01 **** - 如想测试websocket请用谷歌浏览器打开test目录下的test_page.html
|
||||
2025-06-01 **** - =============================================================
|
||||
```
|
||||
|
||||
|
||||
@@ -91,7 +91,7 @@ TTS:
|
||||
```py
|
||||
python app.py
|
||||
```
|
||||
启动`main/digital-human`下的`python start.py`后，打开`http://127.0.0.1:8006/index.html`，测试连接和发送消息时paddlespeech端是否有输出日志
|
||||
打开test目录下的test_page.html，测试连接和发送消息时paddlespeech端是否有输出日志
|
||||
|
||||
输出日志参考：
|
||||
```
|
||||
|
||||
@@ -1,71 +0,0 @@
|
||||
# 联网搜索插件使用指南
|
||||
|
||||
## 功能简介
|
||||
|
||||
联网搜索插件 `web_search` 支持在对话过程中实时联网搜索信息并返回结果。插件支持两个搜索源：秘塔（Metaso）和Tavily，用户可根据需要选择其中一个。
|
||||
|
||||
## API Key申请指南
|
||||
|
||||
目前我们适配了`秘塔搜索`和`Tavily搜索`。
|
||||
- Tavily搜索：每个月1000次免费额度。
|
||||
- 秘塔搜索：拥有较为优质的国内数据源。
|
||||
|
||||
## API Key申请指南
|
||||
|
||||
### 方式一：使用秘塔搜索
|
||||
|
||||
- 访问 [秘塔搜索API](https://metaso.cn/search-api/api-keys)，注册并登录账号
|
||||
- 在API密钥管理页面，点击"创建新的Key"
|
||||
- 复制生成的API Key（以 `mk-` 为前缀），这是配置所需的关键信息
|
||||
|
||||
### 方式二：使用Tavily搜索
|
||||
|
||||
- 访问 [Tavily控制台](https://app.tavily.com/home)，注册并登录账号
|
||||
- 在控制台中创建API Key
|
||||
- 复制生成的API Key（以 `tvly-` 为前缀），这是配置所需的关键信息
|
||||
|
||||
## 配置方式
|
||||
|
||||
### 方式1. 使用智控台部署（推荐）
|
||||
|
||||
- 登录智控台
|
||||
- 进入"配置角色"页面，选择要配置的智能体
|
||||
- 点击"编辑功能"按钮，在右侧参数配置区域找到"联网搜索"插件
|
||||
- 勾选"联网搜索"
|
||||
- 填入搜索源（`metaso`或`tavily`），并将对应的`API Key`填入配置项
|
||||
- 保存配置，再保存智能体配置
|
||||
|
||||
### 方式2. 单模块xiaozhi-server部署
|
||||
|
||||
在 `data/.config.yaml` 中配置：
|
||||
|
||||
- 将搜索源填入 `provider`，可选值为 `metaso` 或 `tavily`
|
||||
- 将申请到的API Key填入 `api_key`
|
||||
|
||||
```yaml
|
||||
plugins:
|
||||
web_search:
|
||||
provider: "metaso"
|
||||
api_key: "你的API Key"
|
||||
```
|
||||
|
||||
如需自定义返回结果数量和工具描述，可额外配置 `max_results` 和 `description`：
|
||||
|
||||
```yaml
|
||||
plugins:
|
||||
web_search:
|
||||
provider: "metaso"
|
||||
description: "联网搜索工具。当用户明确需要联网搜索问题时使用此工具。"
|
||||
max_results: 5
|
||||
api_key: "你的API Key"
|
||||
```
|
||||
|
||||
同时在 `functions` 列表中确保已启用 `web_search`：
|
||||
|
||||
```yaml
|
||||
plugins:
|
||||
functions:
|
||||
- web_search
|
||||
```
|
||||
|
||||
配置完成后重启服务即可生效。
|
||||
+1
-52
@@ -9,7 +9,6 @@
|
||||
* [3.2. `manager-api` (管理后端 - Java Spring Boot实现)](#32-manager-api-管理后端---java-spring-boot实现)
|
||||
* [3.3. `manager-web` (Web管理前端 - Vue.js实现)](#33-manager-web-web管理前端---vuejs实现)
|
||||
* [3.4. `manager-mobile` (移动管理端 - uni-app+Vue3实现)](#34-manager-mobile-移动管理端---uni-appvue3实现)
|
||||
* [3.5. `digital-human` (数字人测试模块 - Python+Web实现)](#35-digital-human-数字人测试模块---pythonweb实现)
|
||||
4. [数据流与交互机制](#4-数据流与交互机制)
|
||||
5. [核心功能概要](#5-核心功能概要)
|
||||
6. [部署与配置概述](#6-部署与配置概述)
|
||||
@@ -68,13 +67,6 @@
|
||||
* 基于alova + @alova/adapter-uniapp实现网络请求，与manager-api无缝集成。
|
||||
* 使用pinia进行状态管理，确保数据一致性。
|
||||
|
||||
6. **`digital-human` (数字人测试模块 - Python+Web实现):**
|
||||
这是一个独立的数字人测试模块，提供本地测试页面、前端交互资源、唤醒词运行时与事件桥能力，用于联调整个数字人交互链路。其主要能力包括：
|
||||
* 提供浏览器端的数字人测试页面，用于验证音频播放、接收和交互流程。
|
||||
* 集成本地唤醒词运行时，支持基于Sherpa-ONNX的关键词检测。
|
||||
* 通过事件桥将页面状态与本地运行时打通，便于调试唤醒词触发与交互效果。
|
||||
* 作为独立模块与`xiaozhi-server`、`manager-web`、`manager-api`并列，便于单独开发和部署。
|
||||
|
||||
**高层交互流程概述:**
|
||||
|
||||
* **语音交互主线:** **ESP32设备**捕捉到用户语音后，通过**WebSocket**将音频数据实时传输给**`xiaozhi-server`**。`xiaozhi-server`完成一系列AI处理（VAD、ASR、LLM交互、TTS）后，再通过WebSocket将合成的语音回复发送回ESP32设备进行播放。所有与语音直接相关的实时交互均在此链路完成。
|
||||
@@ -88,8 +80,7 @@ xiaozhi-esp32-server
|
||||
├─ xiaozhi-server 8000 端口 Python语言开发 负责与esp32通信
|
||||
├─ manager-web 8001 端口 Node.js+Vue开发 负责提供控制台的web界面
|
||||
├─ manager-api 8002 端口 Java语言开发 负责提供控制台的api
|
||||
├─ manager-mobile 跨平台移动应用 uni-app+Vue3开发 负责提供移动版智控台管理
|
||||
└─ digital-human 数字人测试模块 Python+Web实现 负责本地测试页面、唤醒词运行时与事件桥
|
||||
└─ manager-mobile 跨平台移动应用 uni-app+Vue3开发 负责提供移动版智控台管理
|
||||
```
|
||||
|
||||
---
|
||||
@@ -375,48 +366,6 @@ xiaozhi-esp32-server
|
||||
|
||||
---
|
||||
|
||||
### 3.5. `digital-human` (数字人测试模块 - Python+Web实现)
|
||||
|
||||
`digital-human` 组件是一个独立的数字人测试模块，负责提供本地测试页面、页面资源、唤醒词运行时和事件桥能力。它主要用于联调整个数字人交互链路，帮助开发者验证页面交互、音频能力和本地唤醒词流程。
|
||||
|
||||
* **核心目标:**
|
||||
* 提供独立的本地测试页面，用于验证数字人交互效果。
|
||||
* 提供本地唤醒词运行时，支持关键词检测与事件上报。
|
||||
* 为前端页面和本地运行时提供事件桥，打通测试链路。
|
||||
* 以独立模块形式存在，便于单独开发、调试和部署。
|
||||
|
||||
* **核心技术栈:**
|
||||
* **Python 3:** 作为测试运行时的主要语言，负责启动本地服务、管理唤醒词运行时和事件桥。
|
||||
* **原生HTML/CSS/JavaScript:** 用于构建数字人测试页面与交互逻辑。
|
||||
* **Sherpa-ONNX:** 用于本地唤醒词检测。
|
||||
* **ThreadingHTTPServer / WebSocket桥接:** 用于承载测试页面、健康检查和本地事件通信。
|
||||
|
||||
* **关键实现细节:**
|
||||
|
||||
1. **模块入口与页面资源:**
|
||||
* `start.py` 是模块启动入口，负责初始化测试运行时。
|
||||
* `index.html` 是数字人测试页面入口。
|
||||
* `js/`、`css/`、`images/`、`resources/` 目录提供页面脚本、样式和资源文件。
|
||||
|
||||
2. **本地测试运行时:**
|
||||
* `wakeword_runtime/` 目录承载本地唤醒词运行时实现。
|
||||
* 运行时负责配置加载、日志初始化、音频采集、关键词检测和服务生命周期管理。
|
||||
* 模块默认通过本地HTTP服务暴露页面地址、事件桥地址和健康检查接口。
|
||||
|
||||
3. **唤醒词检测链路:**
|
||||
* 基于Sherpa-ONNX关键词检测模型，支持本地唤醒词触发。
|
||||
* 模型文件和关键词配置位于 `wakeword_runtime/models/` 及相应配置文件中。
|
||||
* 页面侧可结合事件桥观察唤醒词服务状态和触发结果。
|
||||
|
||||
4. **调试与联调定位:**
|
||||
* 启动后可通过浏览器访问本地页面，验证音频播放、接收和交互逻辑。
|
||||
* 通过事件桥可以将唤醒词状态同步到页面，便于排查本地链路问题。
|
||||
* 详细的模型下载、运行时配置和使用说明已整理在 `docs/digital-human-wakeword.md` 中。
|
||||
|
||||
`digital-human` 的存在使得数字人相关能力可以脱离主服务独立验证，降低了页面调试、唤醒词联调和本地环境搭建的复杂度。
|
||||
|
||||
---
|
||||
|
||||
## 4. 数据流与交互机制
|
||||
|
||||
`xiaozhi-esp32-server` 系统通过各组件间定义清晰的数据流和交互协议来协同工作。主要的通信方式依赖于针对实时交互优化的WebSocket协议和适用于客户端-服务器请求的RESTful API。
|
||||
|
||||
+1
-58
@@ -9,7 +9,6 @@
|
||||
* [3.2. `manager-api` (Management Backend - Java Spring Boot Implementation)](#32-manager-api-management-backend---java-spring-boot-implementation)
|
||||
* [3.3. `manager-web` (Web Management Frontend - Vue.js Implementation)](#33-manager-web-web-management-frontend---vuejs-implementation)
|
||||
* [3.4. `manager-mobile` (Mobile Management Console - uni-app Implementation)](#34-manager-mobile-mobile-management-console---uniapp-implementation)
|
||||
* [3.5. `digital-human` (Digital Human Test Module - Python+Web Implementation)](#35-digital-human-digital-human-test-module---pythonweb-implementation)
|
||||
4. [Data Flow and Interaction Mechanisms](#4-data-flow-and-interaction-mechanisms)
|
||||
5. [Key Features Summary](#5-key-features-summary)
|
||||
6. [Deployment and Configuration Overview](#6-deployment-and-configuration-overview)
|
||||
@@ -61,21 +60,6 @@ The `xiaozhi-esp32-server` system adopts a **distributed, multi-component collab
|
||||
* (Potential functionality) Monitoring system operation status, viewing logs, troubleshooting, etc.
|
||||
* Comprehensive interaction with all backend management functions provided by `manager-api`.
|
||||
|
||||
5. **`manager-mobile` (Mobile Management Console - uni-app Implementation):**
|
||||
This is a cross-platform mobile management application based on uni-app v3 + Vue 3 + Vite, supporting App (Android & iOS) and WeChat Mini Program. Its main capabilities include:
|
||||
* Providing a convenient management interface on mobile devices, similar in functionality to manager-web but optimized for mobile platforms.
|
||||
* Supporting core functions such as user login, device management, and AI service configuration.
|
||||
* Cross-platform adaptation, allowing a single codebase to run on iOS, Android, and WeChat Mini Programs.
|
||||
* Integrating with `manager-api` through alova + `@alova/adapter-uniapp`.
|
||||
* Using pinia for state management to ensure data consistency.
|
||||
|
||||
6. **`digital-human` (Digital Human Test Module - Python+Web Implementation):**
|
||||
This is an independent digital human test module that provides a local test page, frontend interaction resources, a wake word runtime, and an event bridge for end-to-end debugging of the digital human interaction flow. Its main capabilities include:
|
||||
* Providing a browser-based digital human test page for validating audio playback, audio reception, and interaction flow.
|
||||
* Integrating a local wake word runtime with keyword detection based on Sherpa-ONNX.
|
||||
* Bridging page state and the local runtime through an event bridge to simplify wake word debugging.
|
||||
* Existing as a standalone module alongside `xiaozhi-server`, `manager-web`, and `manager-api`, making independent development and deployment easier.
|
||||
|
||||
**High-Level Interaction Flow Overview:**
|
||||
|
||||
* **Voice Interaction Main Line:** After the **ESP32 device** captures user voice, it transmits audio data in real-time to **`xiaozhi-server`** through **WebSocket**. After `xiaozhi-server` completes a series of AI processing (VAD, ASR, LLM interaction, TTS), it sends the synthesized voice response back to the ESP32 device for playback through WebSocket. All real-time interactions directly related to voice are completed in this link.
|
||||
@@ -89,8 +73,7 @@ xiaozhi-esp32-server
|
||||
├─ xiaozhi-server Port 8000 Python development Responsible for ESP32 communication
|
||||
├─ manager-web Port 8001 Node.js+Vue development Responsible for providing web interface for console
|
||||
├─ manager-api Port 8002 Java development Responsible for providing console API
|
||||
├─ manager-mobile Cross-platform mobile application uni-app+Vue3 development Responsible for providing mobile console management
|
||||
└─ digital-human Digital human test module Python+Web implementation Responsible for local test page, wake word runtime, and event bridge
|
||||
└─ manager-mobile Cross-platform mobile application uni-app+Vue3 development Responsible for providing mobile console management
|
||||
```
|
||||
|
||||
---
|
||||
@@ -274,46 +257,6 @@ The `manager-mobile` component is a cross-platform mobile management application
|
||||
|
||||
`manager-mobile` provides users with a fully functional, smooth mobile management tool through the application of these technologies, allowing administrators to perform system management and configuration anytime, anywhere.
|
||||
|
||||
### 3.5. `digital-human` (Digital Human Test Module - Python+Web Implementation)
|
||||
|
||||
The `digital-human` component is an independent digital human test module responsible for providing a local test page, page resources, a wake word runtime, and an event bridge. It is primarily used to debug the complete digital human interaction flow and to validate frontend interaction, audio capability, and local wake word behavior.
|
||||
|
||||
* **Core Objectives:**
|
||||
* Provide an independent local test page for validating digital human interaction effects.
|
||||
* Provide a local wake word runtime for keyword detection and event reporting.
|
||||
* Provide an event bridge between the frontend page and the local runtime to connect the test flow.
|
||||
* Exist as a standalone module for easier independent development, debugging, and deployment.
|
||||
|
||||
* **Core Technologies:**
|
||||
* **Python 3:** Used for the local test runtime, service startup, wake word lifecycle management, and event bridge coordination.
|
||||
* **Native HTML/CSS/JavaScript:** Used to build the digital human test page and interaction logic.
|
||||
* **Sherpa-ONNX:** Used for local wake word keyword detection.
|
||||
* **ThreadingHTTPServer / WebSocket bridge:** Used to serve the local page, health check endpoint, and event communication.
|
||||
|
||||
* **Key Implementation Aspects:**
|
||||
|
||||
1. **Module Entry and Page Resources:**
|
||||
* `start.py` is the module entry point responsible for starting the local test runtime.
|
||||
* `index.html` is the entry page for digital human testing.
|
||||
* The `js/`, `css/`, `images/`, and `resources/` directories provide frontend scripts, styles, and static resources.
|
||||
|
||||
2. **Local Test Runtime:**
|
||||
* The `wakeword_runtime/` directory contains the local wake word runtime implementation.
|
||||
* The runtime is responsible for configuration loading, logging initialization, audio capture, keyword detection, and lifecycle management.
|
||||
* The module exposes a local page URL, event bridge URL, and health check endpoint through a local HTTP service.
|
||||
|
||||
3. **Wake Word Detection Flow:**
|
||||
* Uses Sherpa-ONNX keyword detection models to support local wake word triggering.
|
||||
* Model files and keyword configurations are stored in `wakeword_runtime/models/` and related configuration files.
|
||||
* The page can observe runtime state and trigger results through the event bridge.
|
||||
|
||||
4. **Debugging and Integration Positioning:**
|
||||
* After startup, developers can open the local page in a browser to validate playback, reception, and interaction logic.
|
||||
* The event bridge synchronizes wake word state to the page, which helps with local debugging.
|
||||
* Detailed model download, runtime configuration, and usage instructions are documented in `docs/digital-human-wakeword.md`.
|
||||
|
||||
The `digital-human` module allows digital human related capabilities to be validated independently from the main service, reducing the complexity of page debugging, wake word integration, and local environment setup.
|
||||
|
||||
---
|
||||
|
||||
## 4. Data Flow and Interaction Mechanisms
|
||||
|
||||
@@ -1,46 +0,0 @@
|
||||
本文档是开发类文档，如需部署小智服务端，[点击这里查看部署教程](../../README.md#%E9%83%A8%E7%BD%B2%E6%96%87%E6%A1%A3)
|
||||
|
||||
如需查看一体机数字人落地部署、Kiosk 全屏启动和系统环境配置，[点击这里查看一体机部署指南](../../docs/all-in-one-digital-human-setup.md)
|
||||
|
||||
如需查看唤醒词模型下载、运行时配置和详细使用说明，[点击这里查看唤醒词专题文档](../../docs/digital-human-wakeword.md)
|
||||
|
||||
# 项目介绍
|
||||
|
||||
digital-human 是独立的数字人测试模块，负责提供本地测试页面、前端交互资源、唤醒词运行时和事件桥能力，用于联调整个数字人交互链路。
|
||||
|
||||
# 快速启动
|
||||
|
||||
安装依赖：
|
||||
|
||||
```bash
|
||||
pip install -r wakeword_runtime/requirements.txt
|
||||
```
|
||||
|
||||
启动模块：
|
||||
|
||||
```bash
|
||||
python start.py
|
||||
```
|
||||
|
||||
# 访问地址
|
||||
|
||||
启动后可访问：
|
||||
|
||||
- 页面地址：http://127.0.0.1:8006/index.html
|
||||
- 事件桥地址：ws://127.0.0.1:8006/wakeword-ws
|
||||
- 健康检查：http://127.0.0.1:8006/health
|
||||
|
||||
# 目录说明
|
||||
|
||||
- `start.py`：模块启动入口
|
||||
- `index.html`：数字人测试页面入口
|
||||
- `wakeword_runtime`：本地唤醒词运行时与配置目录
|
||||
- `js`、`css`：页面前端脚本与样式
|
||||
- `images`、`resources`：页面资源文件
|
||||
|
||||
# 相关文档
|
||||
|
||||
- 一体机部署指南：适用于 x86 设备整机落地部署、Kiosk 展示和开机自启动配置
|
||||
[../../docs/all-in-one-digital-human-setup.md](../../docs/all-in-one-digital-human-setup.md)
|
||||
- 唤醒词专题文档：适用于唤醒词模型下载、运行时配置和本地调试说明
|
||||
[../../docs/digital-human-wakeword.md](../../docs/digital-human-wakeword.md)
|
||||
@@ -1,225 +0,0 @@
|
||||
import { uiController } from '../../ui/controller.js?v=0205';
|
||||
import { log } from '../../utils/logger.js?v=0205';
|
||||
|
||||
let wakewordSocket = null;
|
||||
let reconnectTimer = null;
|
||||
let reconnectAttempts = 0;
|
||||
let shouldReconnect = true;
|
||||
let wakewordRequestSeq = 0;
|
||||
let onNextBridgeConnectedCallback = null;
|
||||
|
||||
const pendingWakewordRequests = new Map();
|
||||
|
||||
export function startWakewordBridgeListener() {
|
||||
if (wakewordSocket) {
|
||||
return wakewordSocket;
|
||||
}
|
||||
|
||||
shouldReconnect = true;
|
||||
log('正在连接本地唤醒事件桥...', 'info');
|
||||
tryConnect();
|
||||
return wakewordSocket;
|
||||
}
|
||||
|
||||
function tryConnect() {
|
||||
const bridgeUrl = buildWakewordBridgeUrl();
|
||||
|
||||
try {
|
||||
wakewordSocket = new WebSocket(bridgeUrl);
|
||||
wakewordSocket.onopen = () => {
|
||||
reconnectAttempts = 0;
|
||||
log(`本地唤醒事件桥已连接: ${bridgeUrl}`, 'success');
|
||||
// 连接成功后自动保存地址，刷新后仍能记住
|
||||
localStorage.setItem('xz_tester_wakewordWsUrl', bridgeUrl);
|
||||
const urlInput = document.getElementById('wakewordWsUrl');
|
||||
if (urlInput) urlInput.value = bridgeUrl;
|
||||
};
|
||||
|
||||
wakewordSocket.onerror = () => {
|
||||
log(`本地唤醒事件桥连接失败: ${bridgeUrl}`, 'error');
|
||||
};
|
||||
|
||||
wakewordSocket.onmessage = async (event) => {
|
||||
try {
|
||||
const message = parseWakewordBridgeMessage(event.data);
|
||||
if (message.requestId && pendingWakewordRequests.has(message.requestId)) {
|
||||
settleWakewordRequest(message);
|
||||
return;
|
||||
}
|
||||
|
||||
if (message.success === false) {
|
||||
log(`本地唤醒事件桥返回错误: ${message.error || '未知错误'}`, 'error');
|
||||
return;
|
||||
}
|
||||
|
||||
if (message.type === 'bridge_connected') {
|
||||
log('本地唤醒监听已就绪', 'info');
|
||||
if (onNextBridgeConnectedCallback) {
|
||||
const cb = onNextBridgeConnectedCallback;
|
||||
onNextBridgeConnectedCallback = null;
|
||||
cb(message);
|
||||
}
|
||||
return;
|
||||
}
|
||||
|
||||
if (message.type === 'service_ready') {
|
||||
log('本地唤醒服务已启动', 'info');
|
||||
return;
|
||||
}
|
||||
|
||||
if (message.type === 'wakeword_config') {
|
||||
uiController.applyWakewordConfig(message.payload || {});
|
||||
log('已同步本地唤醒词配置', 'info');
|
||||
return;
|
||||
}
|
||||
|
||||
if (message.type === 'service_stopping') {
|
||||
log('本地唤醒服务正在停止', 'warning');
|
||||
return;
|
||||
}
|
||||
|
||||
if (message.type === 'wake_word_detected') {
|
||||
const wakeWord = message.payload?.wake_word || '唤醒词';
|
||||
log(`检测到本地唤醒事件: ${wakeWord}`, 'info');
|
||||
await uiController.triggerWakewordDial(wakeWord);
|
||||
}
|
||||
} catch (error) {
|
||||
log(`解析本地唤醒事件失败: ${error.message}`, 'error');
|
||||
}
|
||||
};
|
||||
|
||||
wakewordSocket.onclose = () => {
|
||||
if (wakewordSocket) {
|
||||
wakewordSocket = null;
|
||||
}
|
||||
|
||||
rejectAllWakewordRequests('本地唤醒事件桥已断开');
|
||||
|
||||
if (!shouldReconnect) {
|
||||
return;
|
||||
}
|
||||
|
||||
if (reconnectTimer) {
|
||||
return;
|
||||
}
|
||||
|
||||
reconnectAttempts += 1;
|
||||
const delay = Math.min(1000 * reconnectAttempts, 5000);
|
||||
log(`本地唤醒事件桥将在 ${delay}ms 后重连: ${bridgeUrl}`, 'warning');
|
||||
reconnectTimer = window.setTimeout(() => {
|
||||
reconnectTimer = null;
|
||||
tryConnect();
|
||||
}, delay);
|
||||
};
|
||||
|
||||
return wakewordSocket;
|
||||
} catch (error) {
|
||||
log(`启动本地唤醒监听失败: ${error.message}`, 'error');
|
||||
return null;
|
||||
}
|
||||
}
|
||||
|
||||
export function stopWakewordBridgeListener() {
|
||||
shouldReconnect = false;
|
||||
|
||||
if (reconnectTimer) {
|
||||
window.clearTimeout(reconnectTimer);
|
||||
reconnectTimer = null;
|
||||
}
|
||||
|
||||
if (!wakewordSocket) {
|
||||
return;
|
||||
}
|
||||
|
||||
wakewordSocket.onclose = null;
|
||||
wakewordSocket.close();
|
||||
wakewordSocket = null;
|
||||
}
|
||||
|
||||
export function sendWakewordBridgeMessage(type, payload = {}, requestId = null) {
|
||||
if (!wakewordSocket || wakewordSocket.readyState !== WebSocket.OPEN) {
|
||||
log('本地唤醒事件桥未连接，无法发送消息', 'warning');
|
||||
return false;
|
||||
}
|
||||
|
||||
wakewordSocket.send(JSON.stringify({
|
||||
type,
|
||||
requestId,
|
||||
payload,
|
||||
}));
|
||||
return true;
|
||||
}
|
||||
|
||||
export function requestWakewordBridge(type, payload = {}, timeout = 5000) {
|
||||
const requestId = `wakeword-${Date.now()}-${++wakewordRequestSeq}`;
|
||||
|
||||
return new Promise((resolve, reject) => {
|
||||
const timer = window.setTimeout(() => {
|
||||
pendingWakewordRequests.delete(requestId);
|
||||
reject(new Error('本地唤醒服务响应超时'));
|
||||
}, timeout);
|
||||
|
||||
pendingWakewordRequests.set(requestId, { resolve, reject, timer });
|
||||
|
||||
if (!sendWakewordBridgeMessage(type, payload, requestId)) {
|
||||
window.clearTimeout(timer);
|
||||
pendingWakewordRequests.delete(requestId);
|
||||
reject(new Error('本地唤醒事件桥未连接'));
|
||||
}
|
||||
});
|
||||
}
|
||||
|
||||
export function getWakewordBridgeUrl() {
|
||||
if (wakewordSocket && wakewordSocket.url) {
|
||||
return wakewordSocket.url;
|
||||
}
|
||||
return buildWakewordBridgeUrl();
|
||||
}
|
||||
|
||||
export function onNextBridgeConnected(callback) {
|
||||
onNextBridgeConnectedCallback = callback;
|
||||
}
|
||||
|
||||
function buildWakewordBridgeUrl() {
|
||||
const configured = localStorage.getItem('xz_tester_wakewordWsUrl');
|
||||
if (configured && configured.trim()) {
|
||||
return configured.trim();
|
||||
}
|
||||
return 'ws://127.0.0.1:8006/wakeword-ws';
|
||||
}
|
||||
|
||||
function parseWakewordBridgeMessage(rawData) {
|
||||
const message = JSON.parse(rawData);
|
||||
return {
|
||||
type: message.type || '',
|
||||
requestId: message.requestId || null,
|
||||
success: message.success !== false,
|
||||
payload: message.payload || {},
|
||||
error: message.error || null,
|
||||
};
|
||||
}
|
||||
|
||||
function settleWakewordRequest(message) {
|
||||
const pendingRequest = pendingWakewordRequests.get(message.requestId);
|
||||
if (!pendingRequest) {
|
||||
return;
|
||||
}
|
||||
|
||||
window.clearTimeout(pendingRequest.timer);
|
||||
pendingWakewordRequests.delete(message.requestId);
|
||||
|
||||
if (message.success === false) {
|
||||
pendingRequest.reject(new Error(message.error || '本地唤醒服务返回失败'));
|
||||
return;
|
||||
}
|
||||
|
||||
pendingRequest.resolve(message);
|
||||
}
|
||||
|
||||
function rejectAllWakewordRequests(errorMessage) {
|
||||
pendingWakewordRequests.forEach((pendingRequest) => {
|
||||
window.clearTimeout(pendingRequest.timer);
|
||||
pendingRequest.reject(new Error(errorMessage));
|
||||
});
|
||||
pendingWakewordRequests.clear();
|
||||
}
|
||||
@@ -1,55 +0,0 @@
|
||||
import threading
|
||||
from pathlib import Path
|
||||
|
||||
from wakeword_runtime.config import load_config, setup_logging
|
||||
from wakeword_runtime.runtime import TestRuntimeApplication, TestRuntimeHttpServer
|
||||
|
||||
|
||||
def main() -> int:
|
||||
test_root = Path(__file__).resolve().parent
|
||||
runtime_root = test_root / "wakeword_runtime"
|
||||
|
||||
config = load_config(runtime_root)
|
||||
setup_logging(config.log_file, config.log_level)
|
||||
http_server = TestRuntimeHttpServer(test_root)
|
||||
app_lock = threading.RLock()
|
||||
app = TestRuntimeApplication(config, http_server.event_bridge)
|
||||
|
||||
def restart_runtime() -> None:
|
||||
nonlocal app
|
||||
with app_lock:
|
||||
app.shutdown()
|
||||
next_config = load_config(runtime_root)
|
||||
setup_logging(next_config.log_file, next_config.log_level)
|
||||
next_app = TestRuntimeApplication(next_config, http_server.event_bridge)
|
||||
next_app.setup()
|
||||
next_app.start()
|
||||
app = next_app
|
||||
|
||||
http_server.set_restart_handler(restart_runtime)
|
||||
|
||||
print(f"test runtime started: {http_server.page_url}")
|
||||
print(f"wakeword bridge websocket: {http_server.bridge_url}")
|
||||
print(f"wakeword enabled: {config.wakeword_enabled}")
|
||||
print("press Ctrl+C to stop")
|
||||
|
||||
try:
|
||||
with app_lock:
|
||||
try:
|
||||
app.setup()
|
||||
app.start()
|
||||
except Exception as e:
|
||||
print(f"警告: 唤醒词服务启动失败({e})，测试页面仍可正常使用")
|
||||
http_server.serve_forever()
|
||||
except KeyboardInterrupt:
|
||||
print("test runtime stopped")
|
||||
finally:
|
||||
with app_lock:
|
||||
app.shutdown()
|
||||
http_server.shutdown()
|
||||
|
||||
return 0
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
raise SystemExit(main())
|
||||
@@ -1 +0,0 @@
|
||||
"""Test-side wakeword runtime package."""
|
||||
@@ -1 +0,0 @@
|
||||
from .event_bridge import WakewordEventBridge
|
||||
@@ -1,106 +0,0 @@
|
||||
import json
|
||||
import logging
|
||||
import queue
|
||||
import threading
|
||||
import time
|
||||
from typing import Any
|
||||
|
||||
logger = logging.getLogger(__name__)
|
||||
|
||||
|
||||
class WakewordEventBridge:
|
||||
def __init__(self) -> None:
|
||||
self._clients: list[queue.Queue[str]] = []
|
||||
self._clients_lock = threading.Lock()
|
||||
self._running = True
|
||||
|
||||
@property
|
||||
def is_running(self) -> bool:
|
||||
return self._running
|
||||
|
||||
def build_ready_message(self) -> str:
|
||||
return self.build_message(
|
||||
"bridge_connected",
|
||||
{"status": "ready"},
|
||||
)
|
||||
|
||||
def publish_detected(self, wake_word: str) -> None:
|
||||
self.publish(
|
||||
"wake_word_detected",
|
||||
{
|
||||
"wake_word": wake_word,
|
||||
"timestamp": time.time(),
|
||||
},
|
||||
)
|
||||
|
||||
def publish(self, event_type: str, payload: dict[str, Any] | None = None) -> None:
|
||||
if not self._running:
|
||||
return
|
||||
|
||||
message = self.build_message(event_type, payload or {})
|
||||
with self._clients_lock:
|
||||
clients = list(self._clients)
|
||||
|
||||
stale_clients: list[queue.Queue[str]] = []
|
||||
for client_queue in clients:
|
||||
try:
|
||||
client_queue.put_nowait(message)
|
||||
except queue.Full:
|
||||
stale_clients.append(client_queue)
|
||||
|
||||
if stale_clients:
|
||||
with self._clients_lock:
|
||||
for client_queue in stale_clients:
|
||||
if client_queue in self._clients:
|
||||
self._clients.remove(client_queue)
|
||||
|
||||
def add_client(self) -> queue.Queue[str]:
|
||||
client_queue: queue.Queue[str] = queue.Queue(maxsize=16)
|
||||
with self._clients_lock:
|
||||
self._clients.append(client_queue)
|
||||
return client_queue
|
||||
|
||||
def build_message(
|
||||
self,
|
||||
event_type: str,
|
||||
payload: dict[str, Any] | None = None,
|
||||
request_id: str | None = None,
|
||||
success: bool = True,
|
||||
error: str | None = None,
|
||||
) -> str:
|
||||
message: dict[str, Any] = {
|
||||
"type": event_type,
|
||||
"requestId": request_id,
|
||||
"success": success,
|
||||
"payload": payload or {},
|
||||
}
|
||||
if error:
|
||||
message["error"] = error
|
||||
return json.dumps(message, ensure_ascii=False)
|
||||
|
||||
def remove_client(self, client_queue: queue.Queue[str]) -> None:
|
||||
with self._clients_lock:
|
||||
if client_queue in self._clients:
|
||||
self._clients.remove(client_queue)
|
||||
|
||||
def publish_service_ready(self) -> None:
|
||||
self.publish("service_ready", {"status": "ready"})
|
||||
|
||||
def publish_service_stopping(self) -> None:
|
||||
self.publish("service_stopping", {"status": "stopping"})
|
||||
|
||||
def close(self) -> None:
|
||||
if not self._running:
|
||||
return
|
||||
|
||||
self.publish_service_stopping()
|
||||
self._running = False
|
||||
with self._clients_lock:
|
||||
clients = list(self._clients)
|
||||
self._clients.clear()
|
||||
|
||||
for client_queue in clients:
|
||||
try:
|
||||
client_queue.put_nowait("__bridge_closed__")
|
||||
except queue.Full:
|
||||
pass
|
||||
@@ -1,25 +0,0 @@
|
||||
{
|
||||
"wakeword": {
|
||||
"enabled": true
|
||||
},
|
||||
"model_dir": "models",
|
||||
"audio": {
|
||||
"input_device": null,
|
||||
"sample_rate": 16000,
|
||||
"channels": 1
|
||||
},
|
||||
"detector": {
|
||||
"num_threads": 4,
|
||||
"provider": "cpu",
|
||||
"max_active_paths": 2,
|
||||
"keywords_score": 1.8,
|
||||
"keywords_threshold": 0.1,
|
||||
"num_trailing_blanks": 1,
|
||||
"cooldown_seconds": 1.5
|
||||
},
|
||||
"logging": {
|
||||
"level": "INFO",
|
||||
"dir": "logs",
|
||||
"file": "wakeword-runtime.log"
|
||||
}
|
||||
}
|
||||
@@ -1,2 +0,0 @@
|
||||
from .config_loader import RuntimeConfig, load_config
|
||||
from .logging_setup import setup_logging
|
||||
@@ -1,153 +0,0 @@
|
||||
import json
|
||||
from dataclasses import dataclass
|
||||
from pathlib import Path
|
||||
|
||||
|
||||
@dataclass
|
||||
class WakewordSettings:
|
||||
enabled: bool = False
|
||||
|
||||
|
||||
@dataclass
|
||||
class AudioSettings:
|
||||
input_device: str | int | None = None
|
||||
sample_rate: int = 16000
|
||||
channels: int = 1
|
||||
|
||||
|
||||
@dataclass
|
||||
class DetectorSettings:
|
||||
num_threads: int = 4
|
||||
provider: str = "cpu"
|
||||
max_active_paths: int = 2
|
||||
keywords_score: float = 1.8
|
||||
keywords_threshold: float = 0.2
|
||||
num_trailing_blanks: int = 1
|
||||
cooldown_seconds: float = 1.5
|
||||
|
||||
|
||||
@dataclass
|
||||
class LoggingSettings:
|
||||
level: str = "INFO"
|
||||
directory: str = "logs"
|
||||
file_name: str = "wakeword-runtime.log"
|
||||
|
||||
|
||||
@dataclass
|
||||
class RuntimeConfig:
|
||||
runtime_root: Path
|
||||
wakeword: WakewordSettings
|
||||
wake_words: list[str]
|
||||
model_dir: Path
|
||||
audio: AudioSettings
|
||||
detector: DetectorSettings
|
||||
logging: LoggingSettings
|
||||
|
||||
def validate(self) -> None:
|
||||
if self.wakeword.enabled and not self.wake_words:
|
||||
raise ValueError("keywords.txt cannot be empty when wakeword is enabled")
|
||||
|
||||
if self.audio.sample_rate <= 0:
|
||||
raise ValueError("audio.sample_rate must be greater than 0")
|
||||
|
||||
if self.audio.channels <= 0:
|
||||
raise ValueError("audio.channels must be greater than 0")
|
||||
|
||||
if self.detector.num_threads <= 0:
|
||||
raise ValueError("detector.num_threads must be greater than 0")
|
||||
|
||||
if self.detector.cooldown_seconds < 0:
|
||||
raise ValueError("detector.cooldown_seconds cannot be negative")
|
||||
|
||||
if not self.logging.level:
|
||||
raise ValueError("logging.level cannot be empty")
|
||||
|
||||
@property
|
||||
def wakeword_enabled(self) -> bool:
|
||||
return self.wakeword.enabled
|
||||
|
||||
@property
|
||||
def log_dir(self) -> Path:
|
||||
return (self.runtime_root / self.logging.directory).resolve()
|
||||
|
||||
@property
|
||||
def log_file(self) -> Path:
|
||||
return self.log_dir / self.logging.file_name
|
||||
|
||||
@property
|
||||
def log_level(self) -> str:
|
||||
return self.logging.level.upper()
|
||||
|
||||
|
||||
def load_config(runtime_root: Path) -> RuntimeConfig:
|
||||
config_path = runtime_root / "config.json"
|
||||
raw = json.loads(config_path.read_text(encoding="utf-8"))
|
||||
wakeword_cfg = dict(raw.get("wakeword", {}))
|
||||
raw_model_dir = Path(str(raw.get("model_dir", "models")))
|
||||
model_dir = raw_model_dir.resolve() if raw_model_dir.is_absolute() else (runtime_root / raw_model_dir).resolve()
|
||||
wake_words = _load_wake_words_from_keywords_file(model_dir)
|
||||
|
||||
audio_cfg = dict(raw.get("audio", {}))
|
||||
detector_cfg = dict(raw.get("detector", {}))
|
||||
logging_cfg = dict(raw.get("logging", {}))
|
||||
|
||||
config = RuntimeConfig(
|
||||
runtime_root=runtime_root,
|
||||
wakeword=WakewordSettings(enabled=bool(wakeword_cfg.get("enabled", False))),
|
||||
wake_words=wake_words,
|
||||
model_dir=model_dir,
|
||||
audio=AudioSettings(
|
||||
input_device=audio_cfg.get("input_device"),
|
||||
sample_rate=int(audio_cfg.get("sample_rate", 16000)),
|
||||
channels=int(audio_cfg.get("channels", 1)),
|
||||
),
|
||||
detector=DetectorSettings(
|
||||
num_threads=int(detector_cfg.get("num_threads", 4)),
|
||||
provider=str(detector_cfg.get("provider", "cpu")),
|
||||
max_active_paths=int(detector_cfg.get("max_active_paths", 2)),
|
||||
keywords_score=float(detector_cfg.get("keywords_score", 1.8)),
|
||||
keywords_threshold=float(detector_cfg.get("keywords_threshold", 0.2)),
|
||||
num_trailing_blanks=int(detector_cfg.get("num_trailing_blanks", 1)),
|
||||
cooldown_seconds=float(detector_cfg.get("cooldown_seconds", 1.5)),
|
||||
),
|
||||
logging=LoggingSettings(
|
||||
level=str(logging_cfg.get("level", "INFO")).upper(),
|
||||
directory=str(logging_cfg.get("dir", "logs")),
|
||||
file_name=str(logging_cfg.get("file", "wakeword-runtime.log")),
|
||||
),
|
||||
)
|
||||
config.validate()
|
||||
return config
|
||||
|
||||
|
||||
DEFAULT_WAKE_WORDS = [
|
||||
"你好小智",
|
||||
"你好小志",
|
||||
"小爱同学",
|
||||
"你好小鑫",
|
||||
"你好小新",
|
||||
"小美同学",
|
||||
"小龙小龙",
|
||||
"喵喵同学",
|
||||
"小滨小滨",
|
||||
"小冰小冰",
|
||||
"嘿你好呀",
|
||||
]
|
||||
|
||||
|
||||
def _load_wake_words_from_keywords_file(model_dir: Path) -> list[str]:
|
||||
keywords_file = model_dir / "keywords.txt"
|
||||
if not keywords_file.exists():
|
||||
return DEFAULT_WAKE_WORDS.copy()
|
||||
|
||||
wake_words: list[str] = []
|
||||
for line in keywords_file.read_text(encoding="utf-8").splitlines():
|
||||
text = line.strip()
|
||||
if not text or text.startswith("#") or "@" not in text:
|
||||
continue
|
||||
|
||||
wake_word = text.split("@", 1)[1].strip()
|
||||
if wake_word:
|
||||
wake_words.append(wake_word)
|
||||
|
||||
return wake_words if wake_words else DEFAULT_WAKE_WORDS.copy()
|
||||
@@ -1,23 +0,0 @@
|
||||
import logging
|
||||
from pathlib import Path
|
||||
|
||||
|
||||
def setup_logging(log_file: Path, level: str = "INFO") -> None:
|
||||
log_file.parent.mkdir(parents=True, exist_ok=True)
|
||||
|
||||
logger = logging.getLogger()
|
||||
logger.setLevel(getattr(logging, level.upper(), logging.INFO))
|
||||
logger.handlers.clear()
|
||||
|
||||
formatter = logging.Formatter(
|
||||
"%(asctime)s [%(levelname)s] %(name)s - %(message)s"
|
||||
)
|
||||
|
||||
stream_handler = logging.StreamHandler()
|
||||
stream_handler.setFormatter(formatter)
|
||||
|
||||
file_handler = logging.FileHandler(log_file, encoding="utf-8")
|
||||
file_handler.setFormatter(formatter)
|
||||
|
||||
logger.addHandler(stream_handler)
|
||||
logger.addHandler(file_handler)
|
||||
@@ -1,3 +0,0 @@
|
||||
from .detector_assets import DetectorAssets, DetectorAssetsBuilder
|
||||
from .detector import WakewordDetector
|
||||
from .microphone import MicrophoneListener
|
||||
@@ -1,191 +0,0 @@
|
||||
import queue
|
||||
import threading
|
||||
import logging
|
||||
import time
|
||||
from typing import Any, Callable
|
||||
|
||||
import numpy as np
|
||||
|
||||
from ..config import RuntimeConfig
|
||||
from .detector_assets import DetectorAssetsBuilder
|
||||
|
||||
logger = logging.getLogger(__name__)
|
||||
|
||||
|
||||
class WakewordDetector:
|
||||
def __init__(self, config: RuntimeConfig) -> None:
|
||||
self.config = config
|
||||
self.enabled = config.wakeword_enabled
|
||||
self.assets_builder = DetectorAssetsBuilder(config)
|
||||
self.audio_source = None
|
||||
self.keyword_spotter: Any | None = None
|
||||
self.stream: Any | None = None
|
||||
self.is_running_flag = False
|
||||
self.paused = False
|
||||
self.on_detected_callback: Callable[[str, str], None] | None = None
|
||||
self.on_error: Callable[[Exception], None] | None = None
|
||||
self._audio_queue: queue.Queue[np.ndarray] = queue.Queue(maxsize=100)
|
||||
self._worker_thread: threading.Thread | None = None
|
||||
self.last_detection_time = 0.0
|
||||
self.detection_cooldown = self.config.detector.cooldown_seconds
|
||||
|
||||
def initialize(self) -> None:
|
||||
if not self.enabled:
|
||||
raise RuntimeError("wakeword detector is disabled")
|
||||
|
||||
try:
|
||||
import sherpa_onnx
|
||||
except ImportError as exc:
|
||||
raise RuntimeError(
|
||||
"Missing dependency: sherpa-onnx. Install runtime dependencies before initializing detector."
|
||||
) from exc
|
||||
|
||||
assets = self.assets_builder.prepare()
|
||||
detector_cfg = self.config.detector
|
||||
|
||||
self.keyword_spotter = sherpa_onnx.KeywordSpotter(
|
||||
tokens=str(assets.tokens_file),
|
||||
encoder=str(assets.encoder_file),
|
||||
decoder=str(assets.decoder_file),
|
||||
joiner=str(assets.joiner_file),
|
||||
keywords_file=str(assets.keywords_file),
|
||||
num_threads=detector_cfg.num_threads,
|
||||
sample_rate=self.config.audio.sample_rate,
|
||||
feature_dim=80,
|
||||
max_active_paths=detector_cfg.max_active_paths,
|
||||
keywords_score=detector_cfg.keywords_score,
|
||||
keywords_threshold=detector_cfg.keywords_threshold,
|
||||
num_trailing_blanks=detector_cfg.num_trailing_blanks,
|
||||
provider=detector_cfg.provider,
|
||||
)
|
||||
self.stream = self.keyword_spotter.create_stream()
|
||||
logger.info("detector initialized")
|
||||
logger.info("detector model root: %s", assets.model_root)
|
||||
logger.info("detector keywords file: %s", assets.keywords_file)
|
||||
|
||||
def on_detected(self, callback: Callable[[str, str], None]) -> None:
|
||||
self.on_detected_callback = callback
|
||||
|
||||
def on_audio_data(self, audio_data: np.ndarray) -> None:
|
||||
if not self.enabled or not self.is_running_flag or self.paused:
|
||||
return
|
||||
|
||||
try:
|
||||
self._audio_queue.put_nowait(audio_data.copy())
|
||||
except queue.Full:
|
||||
try:
|
||||
self._audio_queue.get_nowait()
|
||||
self._audio_queue.put_nowait(audio_data.copy())
|
||||
except queue.Empty:
|
||||
pass
|
||||
except Exception as exc:
|
||||
logger.debug("audio data enqueue failed: %s", exc)
|
||||
|
||||
def start(self, audio_source) -> None:
|
||||
if not self.enabled:
|
||||
logger.info("wakeword detector disabled")
|
||||
return
|
||||
|
||||
if self.keyword_spotter is None or self.stream is None:
|
||||
self.initialize()
|
||||
|
||||
if self.is_running_flag:
|
||||
return
|
||||
|
||||
self.audio_source = audio_source
|
||||
self.audio_source.add_audio_listener(self)
|
||||
self.is_running_flag = True
|
||||
self.paused = False
|
||||
self._worker_thread = threading.Thread(
|
||||
target=self._detection_loop,
|
||||
name="wakeword-detector",
|
||||
daemon=True,
|
||||
)
|
||||
self._worker_thread.start()
|
||||
logger.info("wakeword detector started")
|
||||
|
||||
def stop(self) -> None:
|
||||
if not self.is_running_flag and self.audio_source is None and self._worker_thread is None:
|
||||
return
|
||||
|
||||
self.is_running_flag = False
|
||||
|
||||
if self.audio_source is not None:
|
||||
self.audio_source.remove_audio_listener(self)
|
||||
self.audio_source = None
|
||||
|
||||
if self._worker_thread is not None:
|
||||
self._worker_thread.join(timeout=1.0)
|
||||
self._worker_thread = None
|
||||
|
||||
while not self._audio_queue.empty():
|
||||
try:
|
||||
self._audio_queue.get_nowait()
|
||||
except queue.Empty:
|
||||
break
|
||||
|
||||
logger.info("wakeword detector stopped")
|
||||
|
||||
def _detection_loop(self) -> None:
|
||||
error_count = 0
|
||||
max_errors = 5
|
||||
|
||||
while self.is_running_flag:
|
||||
try:
|
||||
if self.paused:
|
||||
time.sleep(0.1)
|
||||
continue
|
||||
|
||||
audio_data = self._audio_queue.get(timeout=0.1)
|
||||
result = self.process_audio_chunk(audio_data)
|
||||
if result and self.on_detected_callback is not None:
|
||||
self.on_detected_callback(result, result)
|
||||
error_count = 0
|
||||
except queue.Empty:
|
||||
continue
|
||||
except Exception as exc:
|
||||
error_count += 1
|
||||
logger.error("wakeword detection loop error(%s/%s): %s", error_count, max_errors, exc)
|
||||
if self.on_error is not None:
|
||||
try:
|
||||
self.on_error(exc)
|
||||
except Exception:
|
||||
logger.exception("wakeword error callback failed")
|
||||
if error_count >= max_errors:
|
||||
logger.critical("too many wakeword detection errors, stopping detector")
|
||||
break
|
||||
time.sleep(1)
|
||||
|
||||
self.is_running_flag = False
|
||||
|
||||
def process_audio_chunk(self, audio_data: np.ndarray) -> str | None:
|
||||
if self.keyword_spotter is None or self.stream is None:
|
||||
raise RuntimeError("detector is not initialized")
|
||||
|
||||
if audio_data is None or len(audio_data) == 0:
|
||||
return None
|
||||
|
||||
if audio_data.dtype == np.int16:
|
||||
samples = audio_data.astype(np.float32) / 32768.0
|
||||
else:
|
||||
samples = audio_data.astype(np.float32)
|
||||
|
||||
sample_rate = self.config.audio.sample_rate
|
||||
self.stream.accept_waveform(sample_rate=sample_rate, waveform=samples)
|
||||
|
||||
if not self.keyword_spotter.is_ready(self.stream):
|
||||
return None
|
||||
|
||||
self.keyword_spotter.decode_stream(self.stream)
|
||||
result = self.keyword_spotter.get_result(self.stream)
|
||||
if not result:
|
||||
return None
|
||||
|
||||
self.keyword_spotter.reset_stream(self.stream)
|
||||
|
||||
current_time = time.time()
|
||||
if current_time - self.last_detection_time < self.detection_cooldown:
|
||||
return None
|
||||
|
||||
self.last_detection_time = current_time
|
||||
return str(result)
|
||||
@@ -1,94 +0,0 @@
|
||||
from dataclasses import dataclass
|
||||
from pathlib import Path
|
||||
|
||||
from ..config import RuntimeConfig
|
||||
|
||||
REQUIRED_MODEL_FILES = (
|
||||
"encoder.onnx",
|
||||
"decoder.onnx",
|
||||
"joiner.onnx",
|
||||
"tokens.txt",
|
||||
)
|
||||
|
||||
|
||||
@dataclass
|
||||
class DetectorAssets:
|
||||
model_root: Path
|
||||
tokens_file: Path
|
||||
encoder_file: Path
|
||||
decoder_file: Path
|
||||
joiner_file: Path
|
||||
keywords_file: Path
|
||||
|
||||
|
||||
class DetectorAssetsBuilder:
|
||||
def __init__(self, config: RuntimeConfig) -> None:
|
||||
self.config = config
|
||||
|
||||
def prepare(self) -> DetectorAssets:
|
||||
model_root = self._resolve_model_root()
|
||||
keywords_file = self._write_keywords_file(model_root)
|
||||
return DetectorAssets(
|
||||
model_root=model_root,
|
||||
tokens_file=model_root / "tokens.txt",
|
||||
encoder_file=model_root / "encoder.onnx",
|
||||
decoder_file=model_root / "decoder.onnx",
|
||||
joiner_file=model_root / "joiner.onnx",
|
||||
keywords_file=keywords_file,
|
||||
)
|
||||
|
||||
def _resolve_model_root(self) -> Path:
|
||||
preferred = self.config.model_dir
|
||||
if self._has_required_files(preferred):
|
||||
return preferred
|
||||
|
||||
raise FileNotFoundError(
|
||||
"No valid model directory found. Expected configured model files to exist."
|
||||
)
|
||||
|
||||
def _write_keywords_file(self, model_root: Path) -> Path:
|
||||
try:
|
||||
from pypinyin import Style, pinyin
|
||||
except ImportError as exc:
|
||||
raise RuntimeError(
|
||||
"Missing dependency: pypinyin. Install runtime dependencies before generating keywords."
|
||||
) from exc
|
||||
|
||||
wake_words = self.config.wake_words
|
||||
if not wake_words:
|
||||
raise ValueError("keywords.txt cannot be empty")
|
||||
|
||||
keywords_path = model_root / "keywords.txt"
|
||||
lines: list[str] = []
|
||||
for keyword_text in wake_words:
|
||||
initials = pinyin(keyword_text, style=Style.INITIALS, strict=False)
|
||||
finals = pinyin(
|
||||
keyword_text,
|
||||
style=Style.FINALS_TONE,
|
||||
strict=False,
|
||||
neutral_tone_with_five=True,
|
||||
)
|
||||
|
||||
tokens: list[str] = []
|
||||
for initial_parts, final_parts in zip(initials, finals):
|
||||
initial = initial_parts[0].strip()
|
||||
final = final_parts[0].strip()
|
||||
if initial:
|
||||
tokens.append(initial)
|
||||
if final:
|
||||
tokens.append(final)
|
||||
|
||||
if not tokens:
|
||||
raise ValueError(
|
||||
f"failed to generate pinyin tokens for wake word: {keyword_text}"
|
||||
)
|
||||
|
||||
lines.append(f"{' '.join(tokens)} @{keyword_text}")
|
||||
|
||||
keywords_path.write_text("\n".join(lines) + "\n", encoding="utf-8")
|
||||
return keywords_path
|
||||
|
||||
def _has_required_files(self, directory: Path) -> bool:
|
||||
if not directory.exists():
|
||||
return False
|
||||
return all((directory / file_name).exists() for file_name in REQUIRED_MODEL_FILES)
|
||||
@@ -1,91 +0,0 @@
|
||||
import logging
|
||||
from typing import Protocol
|
||||
|
||||
import numpy as np
|
||||
|
||||
from ..config import RuntimeConfig
|
||||
|
||||
logger = logging.getLogger(__name__)
|
||||
|
||||
|
||||
class AudioListener(Protocol):
|
||||
def on_audio_data(self, audio_data: np.ndarray) -> None:
|
||||
...
|
||||
|
||||
|
||||
class MicrophoneListener:
|
||||
|
||||
def __init__(self, config: RuntimeConfig) -> None:
|
||||
self.config = config
|
||||
self._stream = None
|
||||
self._running = False
|
||||
self._listeners: list[AudioListener] = []
|
||||
self._sample_rate = self.config.audio.sample_rate
|
||||
self._channels = self.config.audio.channels
|
||||
self._device = self.config.audio.input_device
|
||||
self._block_duration_ms = 30
|
||||
self._block_size = int(self._sample_rate * (self._block_duration_ms / 1000))
|
||||
|
||||
def add_audio_listener(self, listener: AudioListener) -> None:
|
||||
if listener not in self._listeners:
|
||||
self._listeners.append(listener)
|
||||
|
||||
def remove_audio_listener(self, listener: AudioListener) -> None:
|
||||
if listener in self._listeners:
|
||||
self._listeners.remove(listener)
|
||||
|
||||
def start(self) -> None:
|
||||
try:
|
||||
import sounddevice as sd
|
||||
except ImportError as exc:
|
||||
raise RuntimeError(
|
||||
"Missing dependency: sounddevice. Install runtime dependencies before starting microphone listener."
|
||||
) from exc
|
||||
|
||||
self._stream = sd.InputStream(
|
||||
device=self._device,
|
||||
samplerate=self._sample_rate,
|
||||
channels=self._channels,
|
||||
dtype="int16",
|
||||
blocksize=self._block_size,
|
||||
callback=self._input_callback,
|
||||
latency="low",
|
||||
)
|
||||
self._stream.start()
|
||||
self._running = True
|
||||
|
||||
logger.info("microphone listener started")
|
||||
logger.info("microphone sample rate: %s", self._sample_rate)
|
||||
logger.info("microphone channels: %s", self._channels)
|
||||
logger.info("microphone device: %s", self._device if self._device is not None else "default")
|
||||
logger.info("microphone block size: %s", self._block_size)
|
||||
|
||||
def stop(self) -> None:
|
||||
if not self._running and self._stream is None:
|
||||
return
|
||||
|
||||
self._running = False
|
||||
if self._stream is not None:
|
||||
try:
|
||||
self._stream.stop()
|
||||
finally:
|
||||
self._stream.close()
|
||||
self._stream = None
|
||||
logger.info("microphone listener stopped")
|
||||
|
||||
def _input_callback(self, indata, frames, time_info, status) -> None:
|
||||
_ = frames, time_info
|
||||
if status and "overflow" not in str(status).lower():
|
||||
logger.warning("microphone status: %s", status)
|
||||
|
||||
audio = np.copy(indata)
|
||||
if audio.ndim > 1:
|
||||
audio = audio[:, 0]
|
||||
else:
|
||||
audio = audio.reshape(-1)
|
||||
|
||||
for listener in list(self._listeners):
|
||||
try:
|
||||
listener.on_audio_data(audio)
|
||||
except Exception:
|
||||
logger.exception("audio listener callback failed")
|
||||
@@ -1,4 +0,0 @@
|
||||
from .audio import AudioPlugin
|
||||
from .base import Plugin
|
||||
from .manager import PluginManager
|
||||
from .wake_word import WakeWordPlugin
|
||||
@@ -1,37 +0,0 @@
|
||||
import logging
|
||||
from typing import Any
|
||||
|
||||
from ..core import MicrophoneListener
|
||||
from .base import Plugin
|
||||
|
||||
logger = logging.getLogger(__name__)
|
||||
|
||||
|
||||
class AudioPlugin(Plugin):
|
||||
name = "audio"
|
||||
priority = 10
|
||||
|
||||
def __init__(self) -> None:
|
||||
self.app = None
|
||||
self.source: MicrophoneListener | None = None
|
||||
|
||||
def setup(self, app: Any) -> None:
|
||||
self.app = app
|
||||
self.source = MicrophoneListener(app.config)
|
||||
self.app.audio_source = self.source
|
||||
|
||||
def start(self) -> None:
|
||||
if self.source is None:
|
||||
logger.warning("audio source not initialized")
|
||||
return
|
||||
self.source.start()
|
||||
|
||||
def stop(self) -> None:
|
||||
if self.source is not None:
|
||||
self.source.stop()
|
||||
|
||||
def shutdown(self) -> None:
|
||||
if self.app is not None:
|
||||
self.app.audio_source = None
|
||||
self.source = None
|
||||
self.app = None
|
||||
@@ -1,18 +0,0 @@
|
||||
from typing import Any
|
||||
|
||||
|
||||
class Plugin:
|
||||
name: str = "plugin"
|
||||
priority: int = 50
|
||||
|
||||
def setup(self, app: Any) -> None:
|
||||
return None
|
||||
|
||||
def start(self) -> None:
|
||||
return None
|
||||
|
||||
def stop(self) -> None:
|
||||
return None
|
||||
|
||||
def shutdown(self) -> None:
|
||||
return None
|
||||
@@ -1,37 +0,0 @@
|
||||
from typing import Any
|
||||
|
||||
from .base import Plugin
|
||||
|
||||
|
||||
class PluginManager:
|
||||
def __init__(self) -> None:
|
||||
self._plugins: list[Plugin] = []
|
||||
self._by_name: dict[str, Plugin] = {}
|
||||
|
||||
def register(self, *plugins: Plugin) -> None:
|
||||
for plugin in sorted(plugins, key=lambda item: getattr(item, "priority", 50)):
|
||||
if plugin in self._plugins:
|
||||
continue
|
||||
self._plugins.append(plugin)
|
||||
name = getattr(plugin, "name", "")
|
||||
if isinstance(name, str) and name:
|
||||
self._by_name[name] = plugin
|
||||
|
||||
def get_plugin(self, name: str) -> Plugin | None:
|
||||
return self._by_name.get(name)
|
||||
|
||||
def setup_all(self, app: Any) -> None:
|
||||
for plugin in list(self._plugins):
|
||||
plugin.setup(app)
|
||||
|
||||
def start_all(self) -> None:
|
||||
for plugin in list(self._plugins):
|
||||
plugin.start()
|
||||
|
||||
def stop_all(self) -> None:
|
||||
for plugin in reversed(self._plugins):
|
||||
plugin.stop()
|
||||
|
||||
def shutdown_all(self) -> None:
|
||||
for plugin in reversed(self._plugins):
|
||||
plugin.shutdown()
|
||||
@@ -1,53 +0,0 @@
|
||||
import logging
|
||||
from typing import Any
|
||||
|
||||
from ..core import WakewordDetector
|
||||
from .base import Plugin
|
||||
|
||||
logger = logging.getLogger(__name__)
|
||||
|
||||
|
||||
class WakeWordPlugin(Plugin):
|
||||
name = "wake_word"
|
||||
priority = 30
|
||||
|
||||
def __init__(self) -> None:
|
||||
self.app = None
|
||||
self.detector: WakewordDetector | None = None
|
||||
|
||||
def setup(self, app: Any) -> None:
|
||||
self.app = app
|
||||
self.detector = WakewordDetector(app.config)
|
||||
if not self.detector.enabled:
|
||||
self.detector = None
|
||||
return
|
||||
self.detector.on_detected(self._on_detected)
|
||||
self.detector.on_error = self._on_error
|
||||
|
||||
def start(self) -> None:
|
||||
if self.detector is None:
|
||||
return
|
||||
|
||||
audio_plugin = self.app.plugins.get_plugin("audio") if self.app else None
|
||||
audio_source = getattr(audio_plugin, "source", None)
|
||||
if audio_source is None:
|
||||
logger.warning("audio source unavailable, wakeword plugin not started")
|
||||
return
|
||||
|
||||
self.detector.start(audio_source)
|
||||
|
||||
def stop(self) -> None:
|
||||
if self.detector is not None:
|
||||
self.detector.stop()
|
||||
|
||||
def shutdown(self) -> None:
|
||||
self.detector = None
|
||||
self.app = None
|
||||
|
||||
def _on_detected(self, wake_word: str, full_text: str) -> None:
|
||||
if self.app is None:
|
||||
return
|
||||
self.app.handle_wake_word_detected(wake_word, full_text)
|
||||
|
||||
def _on_error(self, error: Exception) -> None:
|
||||
logger.error("wakeword detection error: %s", error)
|
||||
@@ -1,3 +0,0 @@
|
||||
sherpa-onnx==1.12.29
|
||||
sounddevice>=0.4.4
|
||||
pypinyin==0.55.0
|
||||
@@ -1,2 +0,0 @@
|
||||
from .app import TestRuntimeApplication
|
||||
from .http_server import TestRuntimeHttpServer
|
||||
@@ -1,70 +0,0 @@
|
||||
import logging
|
||||
from typing import Protocol
|
||||
|
||||
from ..config import RuntimeConfig
|
||||
from ..plugins import AudioPlugin, PluginManager, WakeWordPlugin
|
||||
|
||||
logger = logging.getLogger(__name__)
|
||||
|
||||
|
||||
class EventPublisher(Protocol):
|
||||
def publish_service_ready(self) -> None:
|
||||
...
|
||||
|
||||
def publish_service_stopping(self) -> None:
|
||||
...
|
||||
|
||||
def publish_detected(self, wake_word: str) -> None:
|
||||
...
|
||||
|
||||
|
||||
class TestRuntimeApplication:
|
||||
def __init__(self, config: RuntimeConfig, event_publisher: EventPublisher) -> None:
|
||||
self.config = config
|
||||
self.event_bridge = event_publisher
|
||||
self.plugins = PluginManager()
|
||||
self.audio_source = None
|
||||
self._is_setup = False
|
||||
self._is_running = False
|
||||
|
||||
def setup(self) -> None:
|
||||
if self._is_setup:
|
||||
return
|
||||
|
||||
if self.config.wakeword_enabled:
|
||||
self.plugins.register(
|
||||
AudioPlugin(),
|
||||
WakeWordPlugin(),
|
||||
)
|
||||
self.plugins.setup_all(self)
|
||||
self._is_setup = True
|
||||
|
||||
def start(self) -> None:
|
||||
if self._is_running:
|
||||
return
|
||||
|
||||
self.setup()
|
||||
self.plugins.start_all()
|
||||
if self.config.wakeword_enabled:
|
||||
self.event_bridge.publish_service_ready()
|
||||
self._is_running = True
|
||||
logger.info("test runtime application started")
|
||||
|
||||
def stop(self) -> None:
|
||||
if not self._is_running:
|
||||
return
|
||||
|
||||
self.event_bridge.publish_service_stopping()
|
||||
self.plugins.stop_all()
|
||||
self._is_running = False
|
||||
logger.info("test runtime application stopped")
|
||||
|
||||
def shutdown(self) -> None:
|
||||
self.stop()
|
||||
if self._is_setup:
|
||||
self.plugins.shutdown_all()
|
||||
|
||||
def handle_wake_word_detected(self, wake_word: str, full_text: str) -> None:
|
||||
_ = full_text
|
||||
logger.info("wake word detected: %s", wake_word)
|
||||
self.event_bridge.publish_detected(wake_word)
|
||||
@@ -1,352 +0,0 @@
|
||||
import base64
|
||||
import hashlib
|
||||
import json
|
||||
import queue
|
||||
import socket
|
||||
import threading
|
||||
from http import HTTPStatus
|
||||
from http.server import SimpleHTTPRequestHandler, ThreadingHTTPServer
|
||||
from pathlib import Path
|
||||
from typing import Callable
|
||||
|
||||
from ..bridge import WakewordEventBridge
|
||||
from ..config.config_loader import load_config
|
||||
|
||||
|
||||
class TestRuntimeHttpServer:
|
||||
def __init__(self, test_root: Path, host: str = "0.0.0.0", port: int = 8006) -> None:
|
||||
self.test_root = test_root
|
||||
self.host = host
|
||||
self.port = port
|
||||
self.event_bridge = WakewordEventBridge()
|
||||
self._restart_handler: Callable[[], None] | None = None
|
||||
self._restart_lock = threading.Lock()
|
||||
self._server = self._build_server()
|
||||
|
||||
@property
|
||||
def page_url(self) -> str:
|
||||
return f"http://127.0.0.1:{self.port}/index.html"
|
||||
|
||||
@property
|
||||
def bridge_url(self) -> str:
|
||||
return f"ws://127.0.0.1:{self.port}/wakeword-ws"
|
||||
|
||||
def serve_forever(self) -> None:
|
||||
self._server.serve_forever()
|
||||
|
||||
def shutdown(self) -> None:
|
||||
self._server.shutdown()
|
||||
self.event_bridge.close()
|
||||
self._server.server_close()
|
||||
|
||||
def set_restart_handler(self, handler: Callable[[], None]) -> None:
|
||||
self._restart_handler = handler
|
||||
|
||||
def request_runtime_restart(self) -> None:
|
||||
with self._restart_lock:
|
||||
handler = self._restart_handler
|
||||
|
||||
if handler is None:
|
||||
raise RuntimeError("restart handler is not configured")
|
||||
|
||||
threading.Thread(
|
||||
target=self._run_restart_handler,
|
||||
name="test-runtime-restart",
|
||||
daemon=True,
|
||||
).start()
|
||||
|
||||
def _run_restart_handler(self) -> None:
|
||||
handler = self._restart_handler
|
||||
if handler is None:
|
||||
return
|
||||
handler()
|
||||
|
||||
def _build_server(self) -> ThreadingHTTPServer:
|
||||
test_root = self.test_root
|
||||
event_bridge = self.event_bridge
|
||||
schedule_restart = self.request_runtime_restart
|
||||
|
||||
class TestRuntimeHandler(SimpleHTTPRequestHandler):
|
||||
protocol_version = "HTTP/1.1"
|
||||
|
||||
def __init__(self, *args, **kwargs):
|
||||
super().__init__(*args, directory=str(test_root), **kwargs)
|
||||
|
||||
def handle(self) -> None:
|
||||
try:
|
||||
super().handle()
|
||||
except (BrokenPipeError, ConnectionResetError, ConnectionAbortedError):
|
||||
pass
|
||||
|
||||
def do_GET(self) -> None:
|
||||
if self.path == "/wakeword-ws":
|
||||
self._handle_websocket(event_bridge)
|
||||
return
|
||||
|
||||
if self.path == "/health":
|
||||
body = json.dumps({"status": "ok"}).encode("utf-8")
|
||||
self.send_response(HTTPStatus.OK)
|
||||
self.send_header("Content-Type", "application/json; charset=utf-8")
|
||||
self.send_header("Cache-Control", "no-cache")
|
||||
self.send_header("Content-Length", str(len(body)))
|
||||
self.end_headers()
|
||||
self.wfile.write(body)
|
||||
return
|
||||
|
||||
super().do_GET()
|
||||
|
||||
def log_message(self, format: str, *args) -> None:
|
||||
return
|
||||
|
||||
def _handle_websocket(self, bridge: WakewordEventBridge) -> None:
|
||||
if self.headers.get("Upgrade", "").lower() != "websocket":
|
||||
self.send_error(HTTPStatus.BAD_REQUEST, "expected websocket upgrade")
|
||||
return
|
||||
|
||||
websocket_key = self.headers.get("Sec-WebSocket-Key")
|
||||
if not websocket_key:
|
||||
self.send_error(HTTPStatus.BAD_REQUEST, "missing Sec-WebSocket-Key")
|
||||
return
|
||||
|
||||
accept_source = websocket_key + "258EAFA5-E914-47DA-95CA-C5AB0DC85B11"
|
||||
accept_value = base64.b64encode(
|
||||
hashlib.sha1(accept_source.encode("utf-8")).digest()
|
||||
).decode("ascii")
|
||||
|
||||
client_queue = bridge.add_client()
|
||||
self.send_response(HTTPStatus.SWITCHING_PROTOCOLS)
|
||||
self.send_header("Upgrade", "websocket")
|
||||
self.send_header("Connection", "Upgrade")
|
||||
self.send_header("Sec-WebSocket-Accept", accept_value)
|
||||
self.end_headers()
|
||||
|
||||
try:
|
||||
self.connection.settimeout(0.2)
|
||||
self._send_websocket_text(bridge.build_ready_message())
|
||||
self._send_websocket_text(self._build_wakeword_config_message(bridge))
|
||||
|
||||
while bridge.is_running:
|
||||
inbound_message = self._receive_websocket_message()
|
||||
if inbound_message is not None:
|
||||
response_message = self._handle_bridge_request(bridge, inbound_message)
|
||||
if response_message:
|
||||
self._send_websocket_text(response_message)
|
||||
|
||||
try:
|
||||
message = client_queue.get(timeout=0.2)
|
||||
if message == "__bridge_closed__":
|
||||
break
|
||||
self._send_websocket_text(message)
|
||||
except queue.Empty:
|
||||
if not bridge.is_running:
|
||||
break
|
||||
continue
|
||||
except socket.timeout:
|
||||
pass
|
||||
except (BrokenPipeError, ConnectionResetError, ConnectionAbortedError):
|
||||
pass
|
||||
finally:
|
||||
bridge.remove_client(client_queue)
|
||||
|
||||
def _build_wakeword_config_message(self, bridge: WakewordEventBridge) -> str:
|
||||
try:
|
||||
runtime_root = test_root / "wakeword_runtime"
|
||||
config = load_config(runtime_root)
|
||||
payload = {
|
||||
"enabled": config.wakeword_enabled,
|
||||
"wakeWords": config.wake_words,
|
||||
}
|
||||
return bridge.build_message("wakeword_config", payload)
|
||||
except Exception as exc:
|
||||
return bridge.build_message(
|
||||
"wakeword_config",
|
||||
{},
|
||||
success=False,
|
||||
error=f"读取唤醒词配置失败: {exc}",
|
||||
)
|
||||
|
||||
def _handle_bridge_request(self, bridge: WakewordEventBridge, raw_message: str) -> str | None:
|
||||
try:
|
||||
message = json.loads(raw_message)
|
||||
except json.JSONDecodeError:
|
||||
return None
|
||||
|
||||
message_type = str(message.get("type", "")).strip()
|
||||
request_id = message.get("requestId")
|
||||
payload = message.get("payload") or {}
|
||||
result_type = f"{message_type}_result" if message_type else "bridge_request_result"
|
||||
|
||||
if message_type == "set_wakeword_config":
|
||||
try:
|
||||
result_payload = self._save_wakeword_config(payload)
|
||||
bridge.publish("wakeword_config", result_payload)
|
||||
return bridge.build_message(
|
||||
"set_wakeword_config_result",
|
||||
result_payload,
|
||||
request_id=request_id,
|
||||
)
|
||||
except Exception as exc:
|
||||
return bridge.build_message(
|
||||
"set_wakeword_config_result",
|
||||
{},
|
||||
request_id=request_id,
|
||||
success=False,
|
||||
error=f"保存唤醒词配置失败: {exc}",
|
||||
)
|
||||
|
||||
if message_type == "restart_wakeword_service":
|
||||
schedule_restart()
|
||||
return bridge.build_message(
|
||||
"restart_wakeword_service_result",
|
||||
{"restarting": True},
|
||||
request_id=request_id,
|
||||
)
|
||||
|
||||
return bridge.build_message(
|
||||
result_type,
|
||||
{},
|
||||
request_id=request_id,
|
||||
success=False,
|
||||
error=f"unsupported message type: {message_type}",
|
||||
)
|
||||
|
||||
def _save_wakeword_config(self, payload: dict) -> dict:
|
||||
runtime_root = test_root / "wakeword_runtime"
|
||||
config_path = runtime_root / "config.json"
|
||||
model_root = runtime_root / "models"
|
||||
keywords_path = model_root / "keywords.txt"
|
||||
|
||||
enabled = bool(payload.get("enabled", True))
|
||||
wake_words = payload.get("wakeWords") or []
|
||||
normalized_wake_words = []
|
||||
for item in wake_words:
|
||||
if not isinstance(item, str):
|
||||
continue
|
||||
text = item.strip()
|
||||
if text and text not in normalized_wake_words:
|
||||
normalized_wake_words.append(text)
|
||||
|
||||
if enabled and not normalized_wake_words:
|
||||
raise ValueError("wakeWords cannot be empty when wakeword is enabled")
|
||||
|
||||
raw_config = json.loads(config_path.read_text(encoding="utf-8"))
|
||||
raw_config.setdefault("wakeword", {})["enabled"] = enabled
|
||||
config_path.write_text(
|
||||
json.dumps(raw_config, indent=2, ensure_ascii=False),
|
||||
encoding="utf-8",
|
||||
)
|
||||
|
||||
keywords_lines = [self._build_keyword_line(item) for item in normalized_wake_words]
|
||||
keywords_path.write_text(
|
||||
("\n".join(keywords_lines) + "\n") if keywords_lines else "",
|
||||
encoding="utf-8",
|
||||
)
|
||||
|
||||
return {
|
||||
"enabled": enabled,
|
||||
"wakeWords": normalized_wake_words,
|
||||
}
|
||||
|
||||
def _build_keyword_line(self, keyword_text: str) -> str:
|
||||
from pypinyin import Style, pinyin
|
||||
|
||||
initials = pinyin(keyword_text, style=Style.INITIALS, strict=False)
|
||||
finals = pinyin(
|
||||
keyword_text,
|
||||
style=Style.FINALS_TONE,
|
||||
strict=False,
|
||||
neutral_tone_with_five=True,
|
||||
)
|
||||
|
||||
tokens: list[str] = []
|
||||
for initial_parts, final_parts in zip(initials, finals):
|
||||
initial = initial_parts[0].strip()
|
||||
final = final_parts[0].strip()
|
||||
if initial:
|
||||
tokens.append(initial)
|
||||
if final:
|
||||
tokens.append(final)
|
||||
|
||||
if not tokens:
|
||||
raise ValueError(f"failed to generate pinyin tokens for wake word: {keyword_text}")
|
||||
|
||||
return f"{' '.join(tokens)} @{keyword_text}"
|
||||
|
||||
def _receive_websocket_message(self) -> str | None:
|
||||
try:
|
||||
header = self._read_exact(2)
|
||||
except socket.timeout:
|
||||
return None
|
||||
|
||||
if not header:
|
||||
return None
|
||||
|
||||
first_byte, second_byte = header[0], header[1]
|
||||
opcode = first_byte & 0x0F
|
||||
masked = (second_byte & 0x80) != 0
|
||||
payload_length = second_byte & 0x7F
|
||||
|
||||
if payload_length == 126:
|
||||
payload_length = int.from_bytes(self._read_exact(2), "big")
|
||||
elif payload_length == 127:
|
||||
payload_length = int.from_bytes(self._read_exact(8), "big")
|
||||
|
||||
masking_key = self._read_exact(4) if masked else b""
|
||||
payload = self._read_exact(payload_length) if payload_length else b""
|
||||
|
||||
if masked and payload:
|
||||
payload = bytes(
|
||||
byte ^ masking_key[index % 4]
|
||||
for index, byte in enumerate(payload)
|
||||
)
|
||||
|
||||
if opcode == 0x8:
|
||||
raise ConnectionAbortedError("websocket closed by client")
|
||||
|
||||
if opcode == 0x9:
|
||||
self._send_websocket_frame(0xA, payload)
|
||||
return None
|
||||
|
||||
if opcode == 0xA:
|
||||
return None
|
||||
|
||||
if opcode != 0x1:
|
||||
return None
|
||||
|
||||
return payload.decode("utf-8")
|
||||
|
||||
def _read_exact(self, size: int) -> bytes:
|
||||
if size <= 0:
|
||||
return b""
|
||||
|
||||
chunks = bytearray()
|
||||
while len(chunks) < size:
|
||||
chunk = self.connection.recv(size - len(chunks))
|
||||
if not chunk:
|
||||
raise ConnectionResetError("websocket connection closed")
|
||||
chunks.extend(chunk)
|
||||
return bytes(chunks)
|
||||
|
||||
def _send_websocket_text(self, message: str) -> None:
|
||||
self._send_websocket_frame(0x1, message.encode("utf-8"))
|
||||
|
||||
def _send_websocket_frame(self, opcode: int, payload: bytes) -> None:
|
||||
header = bytearray()
|
||||
header.append(0x80 | opcode)
|
||||
|
||||
payload_length = len(payload)
|
||||
if payload_length < 126:
|
||||
header.append(payload_length)
|
||||
elif payload_length < 65536:
|
||||
header.append(126)
|
||||
header.extend(payload_length.to_bytes(2, "big"))
|
||||
else:
|
||||
header.append(127)
|
||||
header.extend(payload_length.to_bytes(8, "big"))
|
||||
|
||||
self.wfile.write(bytes(header) + payload)
|
||||
self.wfile.flush()
|
||||
|
||||
server = ThreadingHTTPServer((self.host, self.port), TestRuntimeHandler)
|
||||
server.daemon_threads = True
|
||||
return server
|
||||
@@ -20,7 +20,7 @@
|
||||
<java.version>21</java.version>
|
||||
<junit.version>5.10.1</junit.version>
|
||||
<druid.version>1.2.20</druid.version>
|
||||
<mybatisplus.version>3.5.17</mybatisplus.version>
|
||||
<mybatisplus.version>3.5.5</mybatisplus.version>
|
||||
<hutool.version>5.8.24</hutool.version>
|
||||
<jsoup.version>1.19.1</jsoup.version>
|
||||
<knife4j.version>4.6.0</knife4j.version>
|
||||
@@ -32,8 +32,6 @@
|
||||
<liquibase-core.version>4.20.0</liquibase-core.version>
|
||||
<aliyun-sms-version>4.1.0</aliyun-sms-version>
|
||||
<okio-version>3.4.0</okio-version>
|
||||
<skipTests>true</skipTests>
|
||||
<argLine></argLine>
|
||||
</properties>
|
||||
|
||||
<dependencies>
|
||||
@@ -177,13 +175,13 @@
|
||||
</dependency>
|
||||
<dependency>
|
||||
<groupId>com.baomidou</groupId>
|
||||
<artifactId>mybatis-plus-spring-boot3-starter</artifactId>
|
||||
<artifactId>mybatis-plus-boot-starter</artifactId>
|
||||
<version>${mybatisplus.version}</version>
|
||||
</dependency>
|
||||
<dependency>
|
||||
<groupId>com.baomidou</groupId>
|
||||
<artifactId>mybatis-plus-jsqlparser-4.9</artifactId>
|
||||
<version>${mybatisplus.version}</version>
|
||||
<groupId>org.mybatis</groupId>
|
||||
<artifactId>mybatis-spring</artifactId>
|
||||
<version>3.0.3</version>
|
||||
</dependency>
|
||||
<dependency>
|
||||
<groupId>cn.hutool</groupId>
|
||||
@@ -273,22 +271,11 @@
|
||||
<groupId>org.springframework.boot</groupId>
|
||||
<artifactId>spring-boot-maven-plugin</artifactId>
|
||||
</plugin>
|
||||
<plugin>
|
||||
<groupId>org.apache.maven.plugins</groupId>
|
||||
<artifactId>maven-compiler-plugin</artifactId>
|
||||
<configuration>
|
||||
<proc>full</proc>
|
||||
<compilerArgs>
|
||||
<arg>-Xlint:deprecation,unchecked</arg>
|
||||
</compilerArgs>
|
||||
</configuration>
|
||||
</plugin>
|
||||
<plugin>
|
||||
<groupId>org.apache.maven.plugins</groupId>
|
||||
<artifactId>maven-surefire-plugin</artifactId>
|
||||
<configuration>
|
||||
<skipTests>${skipTests}</skipTests>
|
||||
<argLine>@{argLine} -Xshare:off -javaagent:"${settings.localRepository}/org/mockito/mockito-core/${mockito.version}/mockito-core-${mockito.version}.jar"</argLine>
|
||||
<skipTests>true</skipTests>
|
||||
</configuration>
|
||||
</plugin>
|
||||
</plugins>
|
||||
|
||||
@@ -146,11 +146,6 @@ public interface Constant {
|
||||
*/
|
||||
String SERVER_AUTH_ENABLED = "server.auth.enabled";
|
||||
|
||||
/**
|
||||
* 系统功能菜单配置
|
||||
*/
|
||||
String SYSTEM_WEB_MENU = "system-web.menu";
|
||||
|
||||
/**
|
||||
* 无记忆
|
||||
*/
|
||||
@@ -324,7 +319,7 @@ public interface Constant {
|
||||
/**
|
||||
* 版本号
|
||||
*/
|
||||
public static final String VERSION = "0.9.5";
|
||||
public static final String VERSION = "0.9.3";
|
||||
|
||||
/**
|
||||
* 无效固件URL
|
||||
|
||||
+2
-2
@@ -67,7 +67,7 @@ public class DataFilterInterceptor implements InnerInterceptor {
|
||||
private String getSelect(String buildSql, DataScope scope) {
|
||||
try {
|
||||
Select select = (Select) CCJSqlParserUtil.parse(buildSql);
|
||||
PlainSelect plainSelect = select.getPlainSelect();
|
||||
PlainSelect plainSelect = (PlainSelect) select.getSelectBody();
|
||||
|
||||
Expression expression = plainSelect.getWhere();
|
||||
if (expression == null) {
|
||||
@@ -82,4 +82,4 @@ public class DataFilterInterceptor implements InnerInterceptor {
|
||||
return buildSql;
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
@@ -188,11 +188,4 @@ public class RedisKeys {
|
||||
return "ota:upload:count:" + username;
|
||||
}
|
||||
|
||||
/**
|
||||
* 设备通讯录缓存Key
|
||||
*/
|
||||
public static String getAddressBookKey() {
|
||||
return "device:address_book:all";
|
||||
}
|
||||
|
||||
}
|
||||
|
||||
@@ -5,7 +5,7 @@ import java.util.ArrayList;
|
||||
import java.util.Collection;
|
||||
import java.util.List;
|
||||
import java.util.Map;
|
||||
import java.util.function.BiFunction;
|
||||
import java.util.function.BiConsumer;
|
||||
|
||||
import org.apache.ibatis.binding.MapperMethod;
|
||||
import org.apache.ibatis.logging.Log;
|
||||
@@ -81,8 +81,8 @@ public abstract class BaseServiceImpl<M extends BaseMapper<T>, T> implements Bas
|
||||
// 处理排序字段
|
||||
if (orderField instanceof String) {
|
||||
orderFields.add((String) orderField);
|
||||
} else if (orderField instanceof List<?> fields) {
|
||||
fields.forEach(field -> orderFields.add(String.class.cast(field)));
|
||||
} else if (orderField instanceof List) {
|
||||
orderFields.addAll((List<String>) orderField);
|
||||
}
|
||||
|
||||
// 有排序字段则排序
|
||||
@@ -142,12 +142,11 @@ public abstract class BaseServiceImpl<M extends BaseMapper<T>, T> implements Bas
|
||||
return SqlHelper.retBool(result);
|
||||
}
|
||||
|
||||
protected Class<?> currentMapperClass() {
|
||||
return ReflectionKit.getSuperClassGenericType(this.getClass(), BaseServiceImpl.class, 0);
|
||||
protected Class<M> currentMapperClass() {
|
||||
return (Class<M>) ReflectionKit.getSuperClassGenericType(this.getClass(), BaseServiceImpl.class, 0);
|
||||
}
|
||||
|
||||
@Override
|
||||
@SuppressWarnings("unchecked")
|
||||
public Class<T> currentModelClass() {
|
||||
return (Class<T>) ReflectionKit.getSuperClassGenericType(this.getClass(), BaseServiceImpl.class, 1);
|
||||
}
|
||||
@@ -182,9 +181,8 @@ public abstract class BaseServiceImpl<M extends BaseMapper<T>, T> implements Bas
|
||||
* 执行批量操作
|
||||
*/
|
||||
@SuppressWarnings("deprecation")
|
||||
protected <E> boolean executeBatch(Collection<E> list, int batchSize, BiFunction<SqlSession, E, Integer> operation) {
|
||||
return SqlHelper.executeBatch(SqlHelper.sqlSessionFactory(this.currentModelClass()), this.log, list, batchSize,
|
||||
operation);
|
||||
protected <E> boolean executeBatch(Collection<E> list, int batchSize, BiConsumer<SqlSession, E> consumer) {
|
||||
return SqlHelper.executeBatch(this.currentModelClass(), this.log, list, batchSize, consumer);
|
||||
}
|
||||
|
||||
@Override
|
||||
@@ -211,7 +209,7 @@ public abstract class BaseServiceImpl<M extends BaseMapper<T>, T> implements Bas
|
||||
return executeBatch(entityList, batchSize, (sqlSession, entity) -> {
|
||||
MapperMethod.ParamMap<T> param = new MapperMethod.ParamMap<>();
|
||||
param.put(Constants.ENTITY, entity);
|
||||
return sqlSession.update(sqlStatement, param);
|
||||
sqlSession.update(sqlStatement, param);
|
||||
});
|
||||
}
|
||||
|
||||
@@ -227,6 +225,6 @@ public abstract class BaseServiceImpl<M extends BaseMapper<T>, T> implements Bas
|
||||
|
||||
@Override
|
||||
public boolean deleteBatchIds(Collection<? extends Serializable> idList) {
|
||||
return SqlHelper.retBool(baseDao.deleteByIds(idList));
|
||||
return SqlHelper.retBool(baseDao.deleteBatchIds(idList));
|
||||
}
|
||||
}
|
||||
}
|
||||
@@ -24,7 +24,6 @@ import xiaozhi.common.utils.ConvertUtils;
|
||||
public abstract class CrudServiceImpl<M extends BaseMapper<T>, T, D> extends BaseServiceImpl<M, T>
|
||||
implements CrudService<T, D> {
|
||||
|
||||
@SuppressWarnings("unchecked")
|
||||
protected Class<D> currentDtoClass() {
|
||||
return (Class<D>) ReflectionKit.getSuperClassGenericType(getClass(), CrudServiceImpl.class, 2);
|
||||
}
|
||||
@@ -71,6 +70,6 @@ public abstract class CrudServiceImpl<M extends BaseMapper<T>, T, D> extends Bas
|
||||
|
||||
@Override
|
||||
public void delete(Serializable[] ids) {
|
||||
baseDao.deleteByIds(Arrays.asList(ids));
|
||||
baseDao.deleteBatchIds(Arrays.asList(ids));
|
||||
}
|
||||
}
|
||||
}
|
||||
@@ -1,9 +1,7 @@
|
||||
package xiaozhi.common.utils;
|
||||
|
||||
import java.util.ArrayList;
|
||||
import java.util.LinkedHashMap;
|
||||
import java.util.List;
|
||||
import java.util.Map;
|
||||
|
||||
import com.fasterxml.jackson.core.type.TypeReference;
|
||||
import com.fasterxml.jackson.databind.ObjectMapper;
|
||||
@@ -18,10 +16,6 @@ import cn.hutool.core.util.StrUtil;
|
||||
*/
|
||||
public class JsonUtils {
|
||||
private static final ObjectMapper objectMapper = new ObjectMapper();
|
||||
private static final TypeReference<Map<String, Object>> STRING_OBJECT_MAP = new TypeReference<>() {
|
||||
};
|
||||
private static final TypeReference<List<Map<String, Object>>> STRING_OBJECT_MAP_LIST = new TypeReference<>() {
|
||||
};
|
||||
|
||||
public static String toJsonString(Object object) {
|
||||
try {
|
||||
@@ -73,59 +67,4 @@ public class JsonUtils {
|
||||
}
|
||||
}
|
||||
|
||||
public static Map<String, Object> parseMap(String text) {
|
||||
if (StrUtil.isEmpty(text)) {
|
||||
return null;
|
||||
}
|
||||
return parseObject(text, STRING_OBJECT_MAP);
|
||||
}
|
||||
|
||||
public static List<Map<String, Object>> parseMapList(String text) {
|
||||
if (StrUtil.isEmpty(text)) {
|
||||
return null;
|
||||
}
|
||||
return parseObject(text, STRING_OBJECT_MAP_LIST);
|
||||
}
|
||||
|
||||
public static Map<String, Object> toStringObjectMap(Object value) {
|
||||
if (value == null) {
|
||||
return null;
|
||||
}
|
||||
if (!(value instanceof Map<?, ?> map)) {
|
||||
throw new ClassCastException("Expected Map but got " + value.getClass().getName());
|
||||
}
|
||||
|
||||
Map<String, Object> result = new LinkedHashMap<>(map.size());
|
||||
for (Map.Entry<?, ?> entry : map.entrySet()) {
|
||||
result.put(String.class.cast(entry.getKey()), entry.getValue());
|
||||
}
|
||||
return result;
|
||||
}
|
||||
|
||||
public static List<Map<String, Object>> toStringObjectMapList(Object value) {
|
||||
if (value == null) {
|
||||
return null;
|
||||
}
|
||||
|
||||
List<?> list = List.class.cast(value);
|
||||
List<Map<String, Object>> result = new ArrayList<>(list.size());
|
||||
for (Object item : list) {
|
||||
result.add(toStringObjectMap(item));
|
||||
}
|
||||
return result;
|
||||
}
|
||||
|
||||
public static <T> List<T> toList(Object value, Class<T> elementType) {
|
||||
if (value == null) {
|
||||
return null;
|
||||
}
|
||||
|
||||
List<?> list = List.class.cast(value);
|
||||
List<T> result = new ArrayList<>(list.size());
|
||||
for (Object item : list) {
|
||||
result.add(elementType.cast(item));
|
||||
}
|
||||
return result;
|
||||
}
|
||||
|
||||
}
|
||||
|
||||
@@ -75,11 +75,11 @@ public class SensitiveDataUtils {
|
||||
Object value = jsonObject.get(key);
|
||||
|
||||
if (SENSITIVE_FIELDS.contains(key.toLowerCase()) && value instanceof String) {
|
||||
result.set(key, maskMiddle((String) value));
|
||||
result.put(key, maskMiddle((String) value));
|
||||
} else if (value instanceof JSONObject) {
|
||||
result.set(key, maskSensitiveFields((JSONObject) value));
|
||||
result.put(key, maskSensitiveFields((JSONObject) value));
|
||||
} else {
|
||||
result.set(key, value);
|
||||
result.put(key, value);
|
||||
}
|
||||
}
|
||||
|
||||
@@ -162,4 +162,4 @@ public class SensitiveDataUtils {
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
@@ -22,10 +22,10 @@ public class SqlFilter {
|
||||
return null;
|
||||
}
|
||||
// 去掉'|"|;|\字符
|
||||
str = str.replace("'", "");
|
||||
str = str.replace("\"", "");
|
||||
str = str.replace(";", "");
|
||||
str = str.replace("\\", "");
|
||||
str = StringUtils.replace(str, "'", "");
|
||||
str = StringUtils.replace(str, "\"", "");
|
||||
str = StringUtils.replace(str, ";", "");
|
||||
str = StringUtils.replace(str, "\\", "");
|
||||
|
||||
// 转换成小写
|
||||
str = str.toLowerCase();
|
||||
|
||||
@@ -1,103 +0,0 @@
|
||||
package xiaozhi.modules.agent.Enums;
|
||||
|
||||
import java.util.Arrays;
|
||||
import java.util.List;
|
||||
import java.util.function.BiConsumer;
|
||||
import java.util.function.Function;
|
||||
|
||||
import lombok.Getter;
|
||||
import xiaozhi.modules.agent.dto.AgentSnapshotDataDTO;
|
||||
import xiaozhi.modules.agent.dto.AgentUpdateDTO;
|
||||
import xiaozhi.modules.agent.entity.AgentEntity;
|
||||
|
||||
@Getter
|
||||
public enum AgentSnapshotField {
|
||||
AGENT_CODE("agentCode", AgentSnapshotDataDTO::getAgentCode, AgentUpdateDTO::getAgentCode,
|
||||
(agent, data) -> agent.setAgentCode(data.getAgentCode())),
|
||||
AGENT_NAME("agentName", AgentSnapshotDataDTO::getAgentName, AgentUpdateDTO::getAgentName,
|
||||
(agent, data) -> agent.setAgentName(data.getAgentName())),
|
||||
ASR_MODEL_ID("asrModelId", AgentSnapshotDataDTO::getAsrModelId, AgentUpdateDTO::getAsrModelId,
|
||||
(agent, data) -> agent.setAsrModelId(data.getAsrModelId())),
|
||||
VAD_MODEL_ID("vadModelId", AgentSnapshotDataDTO::getVadModelId, AgentUpdateDTO::getVadModelId,
|
||||
(agent, data) -> agent.setVadModelId(data.getVadModelId())),
|
||||
LLM_MODEL_ID("llmModelId", AgentSnapshotDataDTO::getLlmModelId, AgentUpdateDTO::getLlmModelId,
|
||||
(agent, data) -> agent.setLlmModelId(data.getLlmModelId())),
|
||||
SLM_MODEL_ID("slmModelId", AgentSnapshotDataDTO::getSlmModelId, AgentUpdateDTO::getSlmModelId,
|
||||
(agent, data) -> agent.setSlmModelId(data.getSlmModelId())),
|
||||
VLLM_MODEL_ID("vllmModelId", AgentSnapshotDataDTO::getVllmModelId, AgentUpdateDTO::getVllmModelId,
|
||||
(agent, data) -> agent.setVllmModelId(data.getVllmModelId())),
|
||||
TTS_MODEL_ID("ttsModelId", AgentSnapshotDataDTO::getTtsModelId, AgentUpdateDTO::getTtsModelId,
|
||||
(agent, data) -> agent.setTtsModelId(data.getTtsModelId())),
|
||||
TTS_VOICE_ID("ttsVoiceId", AgentSnapshotDataDTO::getTtsVoiceId, AgentUpdateDTO::getTtsVoiceId,
|
||||
(agent, data) -> agent.setTtsVoiceId(data.getTtsVoiceId())),
|
||||
TTS_LANGUAGE("ttsLanguage", AgentSnapshotDataDTO::getTtsLanguage, AgentUpdateDTO::getTtsLanguage,
|
||||
(agent, data) -> agent.setTtsLanguage(data.getTtsLanguage())),
|
||||
TTS_VOLUME("ttsVolume", AgentSnapshotDataDTO::getTtsVolume, AgentUpdateDTO::getTtsVolume,
|
||||
(agent, data) -> agent.setTtsVolume(data.getTtsVolume())),
|
||||
TTS_RATE("ttsRate", AgentSnapshotDataDTO::getTtsRate, AgentUpdateDTO::getTtsRate,
|
||||
(agent, data) -> agent.setTtsRate(data.getTtsRate())),
|
||||
TTS_PITCH("ttsPitch", AgentSnapshotDataDTO::getTtsPitch, AgentUpdateDTO::getTtsPitch,
|
||||
(agent, data) -> agent.setTtsPitch(data.getTtsPitch())),
|
||||
MEM_MODEL_ID("memModelId", AgentSnapshotDataDTO::getMemModelId, AgentUpdateDTO::getMemModelId,
|
||||
(agent, data) -> agent.setMemModelId(data.getMemModelId())),
|
||||
INTENT_MODEL_ID("intentModelId", AgentSnapshotDataDTO::getIntentModelId, AgentUpdateDTO::getIntentModelId,
|
||||
(agent, data) -> agent.setIntentModelId(data.getIntentModelId())),
|
||||
CHAT_HISTORY_CONF("chatHistoryConf", AgentSnapshotDataDTO::getChatHistoryConf, AgentUpdateDTO::getChatHistoryConf,
|
||||
(agent, data) -> agent.setChatHistoryConf(data.getChatHistoryConf())),
|
||||
SYSTEM_PROMPT("systemPrompt", AgentSnapshotDataDTO::getSystemPrompt, AgentUpdateDTO::getSystemPrompt,
|
||||
(agent, data) -> agent.setSystemPrompt(data.getSystemPrompt())),
|
||||
SUMMARY_MEMORY("summaryMemory", AgentSnapshotDataDTO::getSummaryMemory, AgentUpdateDTO::getSummaryMemory,
|
||||
(agent, data) -> agent.setSummaryMemory(data.getSummaryMemory())),
|
||||
LANG_CODE("langCode", AgentSnapshotDataDTO::getLangCode, AgentUpdateDTO::getLangCode,
|
||||
(agent, data) -> agent.setLangCode(data.getLangCode())),
|
||||
LANGUAGE("language", AgentSnapshotDataDTO::getLanguage, AgentUpdateDTO::getLanguage,
|
||||
(agent, data) -> agent.setLanguage(data.getLanguage())),
|
||||
SORT("sort", AgentSnapshotDataDTO::getSort, AgentUpdateDTO::getSort,
|
||||
(agent, data) -> agent.setSort(data.getSort())),
|
||||
FUNCTIONS("functions", AgentSnapshotDataDTO::getFunctions, AgentUpdateDTO::getFunctions, null),
|
||||
CONTEXT_PROVIDERS("contextProviders", AgentSnapshotDataDTO::getContextProviders,
|
||||
AgentUpdateDTO::getContextProviders, null),
|
||||
CORRECT_WORD_FILE_IDS("correctWordFileIds", AgentSnapshotDataDTO::getCorrectWordFileIds,
|
||||
AgentUpdateDTO::getCorrectWordFileIds, null),
|
||||
TAG_NAMES("tagNames", AgentSnapshotDataDTO::getTagNames, AgentUpdateDTO::getTagNames, null);
|
||||
|
||||
private final String fieldName;
|
||||
private final Function<AgentSnapshotDataDTO, Object> snapshotGetter;
|
||||
private final Function<AgentUpdateDTO, Object> updateGetter;
|
||||
private final BiConsumer<AgentEntity, AgentSnapshotDataDTO> restoreApplier;
|
||||
|
||||
AgentSnapshotField(String fieldName, Function<AgentSnapshotDataDTO, Object> snapshotGetter,
|
||||
Function<AgentUpdateDTO, Object> updateGetter,
|
||||
BiConsumer<AgentEntity, AgentSnapshotDataDTO> restoreApplier) {
|
||||
this.fieldName = fieldName;
|
||||
this.snapshotGetter = snapshotGetter;
|
||||
this.updateGetter = updateGetter;
|
||||
this.restoreApplier = restoreApplier;
|
||||
}
|
||||
|
||||
public static List<String> names() {
|
||||
return Arrays.stream(values()).map(AgentSnapshotField::getFieldName).toList();
|
||||
}
|
||||
|
||||
public static String canonicalName(String fieldName) {
|
||||
return "tags".equals(fieldName) ? TAG_NAMES.getFieldName() : fieldName;
|
||||
}
|
||||
|
||||
public Object snapshotValue(AgentSnapshotDataDTO data) {
|
||||
return data == null ? null : snapshotGetter.apply(data);
|
||||
}
|
||||
|
||||
public Object updateValue(AgentUpdateDTO data) {
|
||||
return data == null ? null : updateGetter.apply(data);
|
||||
}
|
||||
|
||||
public boolean isRestorableAgentField() {
|
||||
return restoreApplier != null;
|
||||
}
|
||||
|
||||
public void applyTo(AgentEntity agent, AgentSnapshotDataDTO data) {
|
||||
if (restoreApplier != null) {
|
||||
restoreApplier.accept(agent, data);
|
||||
}
|
||||
}
|
||||
}
|
||||
+36
-50
@@ -28,13 +28,10 @@ import io.swagger.v3.oas.annotations.tags.Tag;
|
||||
import jakarta.validation.Valid;
|
||||
import lombok.AllArgsConstructor;
|
||||
import xiaozhi.common.constant.Constant;
|
||||
import xiaozhi.common.exception.ErrorCode;
|
||||
import xiaozhi.common.exception.RenException;
|
||||
import xiaozhi.common.page.PageData;
|
||||
import xiaozhi.common.redis.RedisKeys;
|
||||
import xiaozhi.common.redis.RedisUtils;
|
||||
import xiaozhi.common.user.UserDetail;
|
||||
import xiaozhi.common.utils.JsonUtils;
|
||||
import xiaozhi.common.utils.Result;
|
||||
import xiaozhi.common.utils.ResultUtils;
|
||||
import xiaozhi.modules.agent.dto.AgentChatHistoryDTO;
|
||||
@@ -51,10 +48,15 @@ import xiaozhi.modules.agent.service.AgentTagService;
|
||||
import xiaozhi.modules.agent.service.AgentChatAudioService;
|
||||
import xiaozhi.modules.agent.service.AgentChatHistoryService;
|
||||
import xiaozhi.modules.agent.service.AgentChatSummaryService;
|
||||
import xiaozhi.modules.agent.service.AgentContextProviderService;
|
||||
import xiaozhi.modules.agent.service.AgentPluginMappingService;
|
||||
import xiaozhi.modules.agent.service.AgentService;
|
||||
import xiaozhi.modules.agent.service.AgentTemplateService;
|
||||
import xiaozhi.modules.correctword.service.CorrectWordFileService;
|
||||
import xiaozhi.modules.agent.vo.AgentChatHistoryUserVO;
|
||||
import xiaozhi.modules.agent.vo.AgentInfoVO;
|
||||
import xiaozhi.modules.device.entity.DeviceEntity;
|
||||
import xiaozhi.modules.device.service.DeviceService;
|
||||
import xiaozhi.modules.security.user.SecurityUser;
|
||||
|
||||
@Tag(name = "智能体管理")
|
||||
@@ -62,39 +64,17 @@ import xiaozhi.modules.security.user.SecurityUser;
|
||||
@RestController
|
||||
@RequestMapping("/agent")
|
||||
public class AgentController {
|
||||
private static final long AUDIO_PLAY_TOKEN_EXPIRE_SECONDS = 300L;
|
||||
|
||||
private final AgentService agentService;
|
||||
private final AgentTemplateService agentTemplateService;
|
||||
private final DeviceService deviceService;
|
||||
private final AgentChatHistoryService agentChatHistoryService;
|
||||
private final AgentChatAudioService agentChatAudioService;
|
||||
private final AgentPluginMappingService agentPluginMappingService;
|
||||
private final AgentContextProviderService agentContextProviderService;
|
||||
private final AgentChatSummaryService agentChatSummaryService;
|
||||
private final RedisUtils redisUtils;
|
||||
private final AgentTagService agentTagService;
|
||||
|
||||
private void requireAgentPermission(String agentId) {
|
||||
if (!agentService.checkAgentPermission(agentId, SecurityUser.getUserId())) {
|
||||
throw new RenException(ErrorCode.NO_PERMISSION);
|
||||
}
|
||||
}
|
||||
|
||||
private String requireSessionAgent(String sessionId) {
|
||||
String agentId = agentChatHistoryService.getAgentIdBySessionId(sessionId);
|
||||
if (StringUtils.isBlank(agentId)) {
|
||||
throw new RenException(ErrorCode.AGENT_NOT_FOUND);
|
||||
}
|
||||
agentService.getAgentById(agentId);
|
||||
return agentId;
|
||||
}
|
||||
|
||||
private String requireAudioPermission(String audioId) {
|
||||
String agentId = agentChatHistoryService.getAgentIdByAudioId(audioId);
|
||||
if (StringUtils.isBlank(agentId)) {
|
||||
throw new RenException(ErrorCode.NO_PERMISSION);
|
||||
}
|
||||
requireAgentPermission(agentId);
|
||||
return agentId;
|
||||
}
|
||||
private final CorrectWordFileService correctWordFileService;
|
||||
|
||||
@GetMapping("/list")
|
||||
@Operation(summary = "获取用户智能体列表")
|
||||
@@ -126,7 +106,7 @@ public class AgentController {
|
||||
@Operation(summary = "获取智能体详情")
|
||||
@RequiresPermissions("sys:role:normal")
|
||||
public Result<AgentInfoVO> getAgentById(@PathVariable("id") String id) {
|
||||
AgentInfoVO agent = agentService.getAgentById(id, SecurityUser.getUserId());
|
||||
AgentInfoVO agent = agentService.getAgentById(id);
|
||||
return ResultUtils.success(agent);
|
||||
}
|
||||
|
||||
@@ -140,16 +120,20 @@ public class AgentController {
|
||||
|
||||
@PutMapping("/saveMemory/{macAddress}")
|
||||
@Operation(summary = "根据设备id更新智能体")
|
||||
@RequiresPermissions("sys:role:normal")
|
||||
public Result<Void> updateByDeviceId(@PathVariable String macAddress, @RequestBody @Valid AgentMemoryDTO dto) {
|
||||
agentService.updateAgentMemoryByDeviceMacAddress(macAddress, dto, SecurityUser.getUserId());
|
||||
return new Result<Void>().ok(null);
|
||||
DeviceEntity device = deviceService.getDeviceByMacAddress(macAddress);
|
||||
if (device == null) {
|
||||
return new Result<>();
|
||||
}
|
||||
AgentUpdateDTO agentUpdateDTO = new AgentUpdateDTO();
|
||||
agentUpdateDTO.setSummaryMemory(dto.getSummaryMemory());
|
||||
agentService.updateAgentById(device.getAgentId(), agentUpdateDTO);
|
||||
return new Result<>();
|
||||
}
|
||||
|
||||
@PostMapping("/chat-summary/{sessionId}/save")
|
||||
@Operation(summary = "根据会话ID生成聊天记录总结并保存（异步执行）")
|
||||
public Result<Void> generateAndSaveChatSummary(@PathVariable String sessionId) {
|
||||
requireSessionAgent(sessionId);
|
||||
try {
|
||||
// 异步执行总结生成任务，立即返回成功响应
|
||||
new Thread(() -> {
|
||||
@@ -171,7 +155,6 @@ public class AgentController {
|
||||
@PostMapping("/chat-title/{sessionId}/generate")
|
||||
@Operation(summary = "根据会话ID生成聊天标题")
|
||||
public Result<Void> generateAndSaveChatTitle(@PathVariable String sessionId) {
|
||||
requireSessionAgent(sessionId);
|
||||
agentChatSummaryService.generateAndSaveChatTitle(sessionId);
|
||||
return new Result<Void>().ok(null);
|
||||
}
|
||||
@@ -180,7 +163,7 @@ public class AgentController {
|
||||
@Operation(summary = "更新智能体")
|
||||
@RequiresPermissions("sys:role:normal")
|
||||
public Result<Void> update(@PathVariable String id, @RequestBody @Valid AgentUpdateDTO dto) {
|
||||
agentService.updateAgentById(id, dto, SecurityUser.getUserId());
|
||||
agentService.updateAgentById(id, dto);
|
||||
return new Result<>();
|
||||
}
|
||||
|
||||
@@ -188,7 +171,18 @@ public class AgentController {
|
||||
@Operation(summary = "删除智能体")
|
||||
@RequiresPermissions("sys:role:normal")
|
||||
public Result<Void> delete(@PathVariable String id) {
|
||||
agentService.deleteAgentById(id, SecurityUser.getUserId());
|
||||
// 先删除关联的设备
|
||||
deviceService.deleteByAgentId(id);
|
||||
// 删除关联的聊天记录
|
||||
agentChatHistoryService.deleteByAgentId(id, true, true);
|
||||
// 删除关联的插件
|
||||
agentPluginMappingService.deleteByAgentId(id);
|
||||
// 删除关联的上下文源配置
|
||||
agentContextProviderService.deleteByAgentId(id);
|
||||
// 删除关联的替换词文件关联记录
|
||||
correctWordFileService.deleteMappingsByAgentId(id);
|
||||
// 再删除智能体
|
||||
agentService.deleteById(id);
|
||||
return new Result<>();
|
||||
}
|
||||
|
||||
@@ -211,7 +205,6 @@ public class AgentController {
|
||||
public Result<PageData<AgentChatSessionDTO>> getAgentSessions(
|
||||
@PathVariable("id") String id,
|
||||
@Parameter(hidden = true) @RequestParam Map<String, Object> params) {
|
||||
requireAgentPermission(id);
|
||||
params.put("agentId", id);
|
||||
PageData<AgentChatSessionDTO> page = agentChatHistoryService.getSessionListByAgentId(params);
|
||||
return new Result<PageData<AgentChatSessionDTO>>().ok(page);
|
||||
@@ -259,7 +252,6 @@ public class AgentController {
|
||||
@RequiresPermissions("sys:role:normal")
|
||||
public Result<String> getContentByAudioId(
|
||||
@PathVariable("id") String id) {
|
||||
requireAudioPermission(id);
|
||||
// 查询聊天记录
|
||||
String data = agentChatHistoryService.getContentByAudioId(id);
|
||||
return new Result<String>().ok(data);
|
||||
@@ -269,13 +261,12 @@ public class AgentController {
|
||||
@Operation(summary = "获取音频下载ID")
|
||||
@RequiresPermissions("sys:role:normal")
|
||||
public Result<String> getAudioId(@PathVariable("audioId") String audioId) {
|
||||
requireAudioPermission(audioId);
|
||||
byte[] audioData = agentChatAudioService.getAudio(audioId);
|
||||
if (audioData == null) {
|
||||
return new Result<String>().error("音频不存在");
|
||||
}
|
||||
String uuid = UUID.randomUUID().toString();
|
||||
redisUtils.set(RedisKeys.getAgentAudioIdKey(uuid), audioId, AUDIO_PLAY_TOKEN_EXPIRE_SECONDS);
|
||||
redisUtils.set(RedisKeys.getAgentAudioIdKey(uuid), audioId);
|
||||
return new Result<String>().ok(uuid);
|
||||
}
|
||||
|
||||
@@ -331,7 +322,6 @@ public class AgentController {
|
||||
@Operation(summary = "获取智能体的标签")
|
||||
@RequiresPermissions("sys:role:normal")
|
||||
public Result<List<AgentTagDTO>> getAgentTags(@PathVariable String id) {
|
||||
requireAgentPermission(id);
|
||||
List<AgentTagDTO> tags = agentTagService.getTagsByAgentId(id);
|
||||
return new Result<List<AgentTagDTO>>().ok(tags);
|
||||
}
|
||||
@@ -340,14 +330,10 @@ public class AgentController {
|
||||
@Operation(summary = "保存智能体的标签")
|
||||
@RequiresPermissions("sys:role:normal")
|
||||
public Result<Void> saveAgentTags(@PathVariable String id, @RequestBody Map<String, Object> params) {
|
||||
requireAgentPermission(id);
|
||||
List<String> tagIds = JsonUtils.toList(params.get("tagIds"), String.class);
|
||||
List<String> tagNames = JsonUtils.toList(params.get("tagNames"), String.class);
|
||||
AgentUpdateDTO dto = new AgentUpdateDTO();
|
||||
dto.setTagIds(tagIds);
|
||||
dto.setTagNames(tagNames);
|
||||
agentService.updateAgentById(id, dto);
|
||||
List<String> tagIds = (List<String>) params.get("tagIds");
|
||||
List<String> tagNames = (List<String>) params.get("tagNames");
|
||||
agentTagService.saveAgentTags(id, tagIds, tagNames);
|
||||
return new Result<Void>().ok(null);
|
||||
}
|
||||
|
||||
}
|
||||
}
|
||||
-79
@@ -1,79 +0,0 @@
|
||||
package xiaozhi.modules.agent.controller;
|
||||
|
||||
import org.apache.shiro.authz.annotation.RequiresPermissions;
|
||||
import org.springdoc.core.annotations.ParameterObject;
|
||||
import org.springframework.web.bind.annotation.DeleteMapping;
|
||||
import org.springframework.web.bind.annotation.GetMapping;
|
||||
import org.springframework.web.bind.annotation.PathVariable;
|
||||
import org.springframework.web.bind.annotation.PostMapping;
|
||||
import org.springframework.web.bind.annotation.RequestBody;
|
||||
import org.springframework.web.bind.annotation.RequestMapping;
|
||||
import org.springframework.web.bind.annotation.RestController;
|
||||
|
||||
import io.swagger.v3.oas.annotations.Operation;
|
||||
import io.swagger.v3.oas.annotations.tags.Tag;
|
||||
import jakarta.validation.Valid;
|
||||
import lombok.AllArgsConstructor;
|
||||
import xiaozhi.common.exception.RenException;
|
||||
import xiaozhi.common.page.PageData;
|
||||
import xiaozhi.common.user.UserDetail;
|
||||
import xiaozhi.common.utils.Result;
|
||||
import xiaozhi.modules.agent.dto.AgentSnapshotPageDTO;
|
||||
import xiaozhi.modules.agent.dto.AgentSnapshotRestoreDTO;
|
||||
import xiaozhi.modules.agent.service.AgentService;
|
||||
import xiaozhi.modules.agent.service.AgentSnapshotService;
|
||||
import xiaozhi.modules.agent.vo.AgentSnapshotVO;
|
||||
import xiaozhi.modules.security.user.SecurityUser;
|
||||
|
||||
@Tag(name = "智能体快照")
|
||||
@AllArgsConstructor
|
||||
@RestController
|
||||
@RequestMapping("/agent/{agentId}/snapshots")
|
||||
public class AgentSnapshotController {
|
||||
private final AgentSnapshotService agentSnapshotService;
|
||||
private final AgentService agentService;
|
||||
|
||||
@GetMapping
|
||||
@Operation(summary = "获取智能体快照列表")
|
||||
@RequiresPermissions("sys:role:normal")
|
||||
public Result<PageData<AgentSnapshotVO>> page(
|
||||
@PathVariable String agentId,
|
||||
@ParameterObject AgentSnapshotPageDTO params) {
|
||||
checkPermission(agentId);
|
||||
return new Result<PageData<AgentSnapshotVO>>().ok(agentSnapshotService.page(agentId, params));
|
||||
}
|
||||
|
||||
@GetMapping("/{snapshotId}")
|
||||
@Operation(summary = "获取智能体快照详情")
|
||||
@RequiresPermissions("sys:role:normal")
|
||||
public Result<AgentSnapshotVO> getSnapshot(@PathVariable String agentId, @PathVariable String snapshotId) {
|
||||
checkPermission(agentId);
|
||||
return new Result<AgentSnapshotVO>().ok(agentSnapshotService.getSnapshot(agentId, snapshotId));
|
||||
}
|
||||
|
||||
@PostMapping("/{snapshotId}/restore")
|
||||
@Operation(summary = "恢复智能体快照")
|
||||
@RequiresPermissions("sys:role:normal")
|
||||
public Result<Void> restore(@PathVariable String agentId, @PathVariable String snapshotId,
|
||||
@RequestBody @Valid AgentSnapshotRestoreDTO request) {
|
||||
checkPermission(agentId);
|
||||
agentSnapshotService.restoreSnapshot(agentId, snapshotId, request.getCurrentStateToken());
|
||||
return new Result<>();
|
||||
}
|
||||
|
||||
@DeleteMapping("/{snapshotId}")
|
||||
@Operation(summary = "删除智能体历史快照")
|
||||
@RequiresPermissions("sys:role:normal")
|
||||
public Result<Void> deleteSnapshot(@PathVariable String agentId, @PathVariable String snapshotId) {
|
||||
checkPermission(agentId);
|
||||
agentSnapshotService.deleteSnapshot(agentId, snapshotId);
|
||||
return new Result<>();
|
||||
}
|
||||
|
||||
private void checkPermission(String agentId) {
|
||||
UserDetail user = SecurityUser.getUser();
|
||||
if (user == null || !agentService.checkAgentPermission(agentId, user.getId())) {
|
||||
throw new RenException("没有权限访问该智能体快照");
|
||||
}
|
||||
}
|
||||
}
|
||||
@@ -36,20 +36,4 @@ public interface AgentDao extends BaseDao<AgentEntity> {
|
||||
* @param agentId 智能体ID
|
||||
*/
|
||||
AgentInfoVO selectAgentInfoById(@Param("agentId") String agentId);
|
||||
|
||||
/**
|
||||
* 锁定智能体主记录，用于串行化同一智能体的配置写入
|
||||
*
|
||||
* @param agentId 智能体ID
|
||||
*/
|
||||
AgentEntity selectByIdForUpdate(@Param("agentId") String agentId);
|
||||
|
||||
/**
|
||||
* 精确写入快照覆盖的智能体字段，包括目标快照中的 null 值。
|
||||
* 不更新所属用户、创建信息等不属于快照的字段。
|
||||
*
|
||||
* @param agent 已应用目标快照的智能体
|
||||
* @return 受影响行数
|
||||
*/
|
||||
int updateSnapshotFields(@Param("agent") AgentEntity agent);
|
||||
}
|
||||
|
||||
@@ -1,29 +0,0 @@
|
||||
package xiaozhi.modules.agent.dao;
|
||||
|
||||
import java.util.List;
|
||||
|
||||
import org.apache.ibatis.annotations.Mapper;
|
||||
import org.apache.ibatis.annotations.Param;
|
||||
|
||||
import xiaozhi.common.dao.BaseDao;
|
||||
import xiaozhi.modules.agent.entity.AgentSnapshotEntity;
|
||||
|
||||
@Mapper
|
||||
public interface AgentSnapshotDao extends BaseDao<AgentSnapshotEntity> {
|
||||
Integer selectMaxVersionNo(@Param("agentId") String agentId);
|
||||
|
||||
AgentSnapshotEntity selectLatestSnapshot(@Param("agentId") String agentId);
|
||||
|
||||
AgentSnapshotEntity selectNextSnapshot(@Param("agentId") String agentId, @Param("versionNo") Integer versionNo);
|
||||
|
||||
int insertWithNextVersion(@Param("snapshot") AgentSnapshotEntity snapshot);
|
||||
|
||||
int deleteOlderThanKeepLimit(@Param("agentId") String agentId, @Param("keepLimit") int keepLimit);
|
||||
|
||||
List<AgentSnapshotEntity> selectLegacyRedactionBatch(@Param("afterId") String afterId,
|
||||
@Param("limit") int limit,
|
||||
@Param("targetRedactionVersion") int targetRedactionVersion);
|
||||
|
||||
int updateRedactedSnapshots(@Param("snapshots") List<AgentSnapshotEntity> snapshots,
|
||||
@Param("redactionVersion") int redactionVersion);
|
||||
}
|
||||
@@ -39,7 +39,7 @@ public class AgentDTO {
|
||||
private String systemPrompt;
|
||||
|
||||
@Schema(description = "总结记忆", example = "构建可生长的动态记忆网络，在有限空间内保留关键信息的同时，智能维护信息演变轨迹\n" +
|
||||
"根据对话记录，总结user的重要信息，以便在未来的对话中提供更个性化的服务", requiredMode = Schema.RequiredMode.NOT_REQUIRED)
|
||||
"根据对话记录，总结user的重要信息，以便在未来的对话中提供更个性化的服务", required = false)
|
||||
private String summaryMemory;
|
||||
|
||||
@Schema(description = "最后连接时间", example = "2024-03-20 10:00:00")
|
||||
@@ -50,4 +50,4 @@ public class AgentDTO {
|
||||
|
||||
@Schema(description = "标签列表")
|
||||
private List<AgentTagDTO> tags;
|
||||
}
|
||||
}
|
||||
@@ -14,6 +14,6 @@ public class AgentMemoryDTO implements Serializable {
|
||||
private static final long serialVersionUID = 1L;
|
||||
|
||||
@Schema(description = "总结记忆", example = "构建可生长的动态记忆网络，在有限空间内保留关键信息的同时，智能维护信息演变轨迹\n" +
|
||||
"根据对话记录，总结user的重要信息，以便在未来的对话中提供更个性化的服务", requiredMode = Schema.RequiredMode.NOT_REQUIRED)
|
||||
"根据对话记录，总结user的重要信息，以便在未来的对话中提供更个性化的服务", required = false)
|
||||
private String summaryMemory;
|
||||
}
|
||||
}
|
||||
@@ -1,40 +0,0 @@
|
||||
package xiaozhi.modules.agent.dto;
|
||||
|
||||
import java.io.Serializable;
|
||||
import java.util.List;
|
||||
|
||||
import io.swagger.v3.oas.annotations.media.Schema;
|
||||
import lombok.Data;
|
||||
|
||||
@Data
|
||||
@Schema(description = "智能体快照数据")
|
||||
public class AgentSnapshotDataDTO implements Serializable {
|
||||
private static final long serialVersionUID = 1L;
|
||||
|
||||
private String agentCode;
|
||||
private String agentName;
|
||||
private String asrModelId;
|
||||
private String vadModelId;
|
||||
private String llmModelId;
|
||||
private String slmModelId;
|
||||
private String vllmModelId;
|
||||
private String ttsModelId;
|
||||
private String ttsVoiceId;
|
||||
private String ttsLanguage;
|
||||
private Integer ttsVolume;
|
||||
private Integer ttsRate;
|
||||
private Integer ttsPitch;
|
||||
private String memModelId;
|
||||
private String intentModelId;
|
||||
private Integer chatHistoryConf;
|
||||
private String systemPrompt;
|
||||
private String summaryMemory;
|
||||
private String langCode;
|
||||
private String language;
|
||||
private Integer sort;
|
||||
private List<AgentUpdateDTO.FunctionInfo> functions;
|
||||
private List<ContextProviderDTO> contextProviders;
|
||||
private List<String> correctWordFileIds;
|
||||
private List<String> tagNames;
|
||||
private List<AgentSnapshotTagDTO> tags;
|
||||
}
|
||||
@@ -1,28 +0,0 @@
|
||||
package xiaozhi.modules.agent.dto;
|
||||
|
||||
import io.swagger.v3.oas.annotations.media.Schema;
|
||||
import lombok.Data;
|
||||
|
||||
@Data
|
||||
@Schema(description = "智能体快照分页查询参数")
|
||||
public class AgentSnapshotPageDTO {
|
||||
@Schema(description = "当前页码，从1开始", example = "1")
|
||||
private Integer page = 1;
|
||||
|
||||
@Schema(description = "每页数量", example = "10")
|
||||
private Integer limit = 10;
|
||||
|
||||
@Schema(description = "版本锚点，只查询小于等于该版本号的历史快照", example = "20")
|
||||
private Integer maxVersionNo;
|
||||
|
||||
public int pageOrDefault() {
|
||||
return page == null || page < 1 ? 1 : page;
|
||||
}
|
||||
|
||||
public int limitOrDefault() {
|
||||
if (limit == null || limit < 1) {
|
||||
return 10;
|
||||
}
|
||||
return limit;
|
||||
}
|
||||
}
|
||||
@@ -1,13 +0,0 @@
|
||||
package xiaozhi.modules.agent.dto;
|
||||
|
||||
import io.swagger.v3.oas.annotations.media.Schema;
|
||||
import jakarta.validation.constraints.NotBlank;
|
||||
import lombok.Data;
|
||||
|
||||
@Data
|
||||
@Schema(description = "智能体快照恢复请求")
|
||||
public class AgentSnapshotRestoreDTO {
|
||||
@NotBlank
|
||||
@Schema(description = "预览时由服务端生成的当前配置状态指纹")
|
||||
private String currentStateToken;
|
||||
}
|
||||
@@ -1,16 +0,0 @@
|
||||
package xiaozhi.modules.agent.dto;
|
||||
|
||||
import java.io.Serializable;
|
||||
|
||||
import io.swagger.v3.oas.annotations.media.Schema;
|
||||
import lombok.Data;
|
||||
|
||||
@Data
|
||||
@Schema(description = "智能体快照标签")
|
||||
public class AgentSnapshotTagDTO implements Serializable {
|
||||
private static final long serialVersionUID = 1L;
|
||||
|
||||
private String id;
|
||||
private String tagName;
|
||||
private Integer sort;
|
||||
}
|
||||
@@ -4,12 +4,9 @@ import java.io.Serializable;
|
||||
import java.math.BigDecimal;
|
||||
import java.util.HashMap;
|
||||
import java.util.List;
|
||||
import java.util.Map;
|
||||
|
||||
import com.fasterxml.jackson.core.type.TypeReference;
|
||||
import io.swagger.v3.oas.annotations.media.Schema;
|
||||
import lombok.Data;
|
||||
import xiaozhi.common.utils.JsonUtils;
|
||||
|
||||
/**
|
||||
* 智能体更新DTO
|
||||
@@ -39,10 +36,10 @@ public class AgentUpdateDTO implements Serializable {
|
||||
@Schema(description = "小模型标识", example = "slm_model_02", nullable = true)
|
||||
private String slmModelId;
|
||||
|
||||
@Schema(description = "VLLM模型标识", example = "vllm_model_02", requiredMode = Schema.RequiredMode.NOT_REQUIRED)
|
||||
@Schema(description = "VLLM模型标识", example = "vllm_model_02", required = false)
|
||||
private String vllmModelId;
|
||||
|
||||
@Schema(description = "语音合成模型标识", example = "tts_model_02", requiredMode = Schema.RequiredMode.NOT_REQUIRED)
|
||||
@Schema(description = "语音合成模型标识", example = "tts_model_02", required = false)
|
||||
private String ttsModelId;
|
||||
|
||||
@Schema(description = "音色标识", example = "voice_02", nullable = true)
|
||||
@@ -94,50 +91,15 @@ public class AgentUpdateDTO implements Serializable {
|
||||
@Schema(description = "替换词文件ID列表", nullable = true)
|
||||
private List<String> correctWordFileIds;
|
||||
|
||||
@Schema(description = "标签名称列表", nullable = true)
|
||||
private List<String> tagNames;
|
||||
|
||||
@Schema(description = "标签ID列表", nullable = true)
|
||||
private List<String> tagIds;
|
||||
|
||||
@Data
|
||||
@Schema(description = "插件函数信息")
|
||||
public static class FunctionInfo implements Serializable {
|
||||
private static final TypeReference<HashMap<String, Object>> PARAM_INFO_TYPE = new TypeReference<>() {
|
||||
};
|
||||
|
||||
@Schema(description = "插件ID", example = "plugin_01")
|
||||
private String pluginId;
|
||||
|
||||
@Schema(description = "函数参数信息", nullable = true)
|
||||
private HashMap<String, Object> paramInfo = new HashMap<>();
|
||||
|
||||
public void setParamInfo(Object paramInfo) {
|
||||
this.paramInfo = normalizeParamInfo(paramInfo);
|
||||
}
|
||||
|
||||
private static HashMap<String, Object> normalizeParamInfo(Object paramInfo) {
|
||||
if (paramInfo == null) {
|
||||
return new HashMap<>();
|
||||
}
|
||||
if (paramInfo instanceof String value) {
|
||||
if (value.trim().isEmpty()) {
|
||||
return new HashMap<>();
|
||||
}
|
||||
return JsonUtils.parseObject(value, PARAM_INFO_TYPE);
|
||||
}
|
||||
if (paramInfo instanceof Map<?, ?> value) {
|
||||
HashMap<String, Object> normalized = new HashMap<>();
|
||||
value.forEach((key, val) -> {
|
||||
if (key != null) {
|
||||
normalized.put(String.valueOf(key), val);
|
||||
}
|
||||
});
|
||||
return normalized;
|
||||
}
|
||||
return JsonUtils.parseObject(JsonUtils.toJsonString(paramInfo), PARAM_INFO_TYPE);
|
||||
}
|
||||
private HashMap<String, Object> paramInfo;
|
||||
|
||||
private static final long serialVersionUID = 1L;
|
||||
}
|
||||
}
|
||||
}
|
||||
@@ -0,0 +1,48 @@
|
||||
package xiaozhi.modules.agent.dto;
|
||||
|
||||
import lombok.Data;
|
||||
|
||||
/**
|
||||
* MCP JSON-RPC 响应 DTO
|
||||
*/
|
||||
@Data
|
||||
public class McpJsonRpcResponse {
|
||||
private String jsonrpc = "2.0";
|
||||
private Integer id;
|
||||
private McpResult result;
|
||||
private McpError error;
|
||||
|
||||
public McpJsonRpcResponse() {
|
||||
}
|
||||
|
||||
@Data
|
||||
public static class McpResult {
|
||||
private String type;
|
||||
private String message;
|
||||
private String agent_id;
|
||||
private McpTool[] tools;
|
||||
|
||||
public McpResult() {
|
||||
}
|
||||
}
|
||||
|
||||
@Data
|
||||
public static class McpTool {
|
||||
private String name;
|
||||
private String description;
|
||||
private Object inputSchema;
|
||||
|
||||
public McpTool() {
|
||||
}
|
||||
}
|
||||
|
||||
@Data
|
||||
public static class McpError {
|
||||
private Integer code;
|
||||
private String message;
|
||||
private Object data;
|
||||
|
||||
public McpError() {
|
||||
}
|
||||
}
|
||||
}
|
||||
+2
-2
@@ -7,11 +7,11 @@ import com.baomidou.mybatisplus.annotation.IdType;
|
||||
import com.baomidou.mybatisplus.annotation.TableField;
|
||||
import com.baomidou.mybatisplus.annotation.TableId;
|
||||
import com.baomidou.mybatisplus.annotation.TableName;
|
||||
import com.baomidou.mybatisplus.extension.handlers.JacksonTypeHandler;
|
||||
|
||||
import io.swagger.v3.oas.annotations.media.Schema;
|
||||
import lombok.Data;
|
||||
import xiaozhi.modules.agent.dto.ContextProviderDTO;
|
||||
import xiaozhi.modules.agent.typehandler.ContextProviderListTypeHandler;
|
||||
|
||||
@Data
|
||||
@TableName(value = "ai_agent_context_provider", autoResultMap = true)
|
||||
@@ -26,7 +26,7 @@ public class AgentContextProviderEntity {
|
||||
private String agentId;
|
||||
|
||||
@Schema(description = "上下文源配置")
|
||||
@TableField(typeHandler = ContextProviderListTypeHandler.class)
|
||||
@TableField(typeHandler = JacksonTypeHandler.class)
|
||||
private List<ContextProviderDTO> contextProviders;
|
||||
|
||||
@Schema(description = "创建者")
|
||||
|
||||
@@ -74,7 +74,7 @@ public class AgentEntity {
|
||||
private String systemPrompt;
|
||||
|
||||
@Schema(description = "总结记忆", example = "构建可生长的动态记忆网络，在有限空间内保留关键信息的同时，智能维护信息演变轨迹\n" +
|
||||
"根据对话记录，总结user的重要信息，以便在未来的对话中提供更个性化的服务", requiredMode = Schema.RequiredMode.NOT_REQUIRED)
|
||||
"根据对话记录，总结user的重要信息，以便在未来的对话中提供更个性化的服务", required = false)
|
||||
private String summaryMemory;
|
||||
|
||||
@Schema(description = "语言编码")
|
||||
@@ -97,4 +97,4 @@ public class AgentEntity {
|
||||
|
||||
@Schema(description = "更新时间")
|
||||
private Date updatedAt;
|
||||
}
|
||||
}
|
||||
@@ -1,53 +0,0 @@
|
||||
package xiaozhi.modules.agent.entity;
|
||||
|
||||
import java.util.Date;
|
||||
|
||||
import com.baomidou.mybatisplus.annotation.IdType;
|
||||
import com.baomidou.mybatisplus.annotation.TableId;
|
||||
import com.baomidou.mybatisplus.annotation.TableName;
|
||||
|
||||
import io.swagger.v3.oas.annotations.media.Schema;
|
||||
import lombok.Data;
|
||||
|
||||
@Data
|
||||
@TableName("ai_agent_snapshot")
|
||||
@Schema(description = "智能体配置快照")
|
||||
public class AgentSnapshotEntity {
|
||||
|
||||
@TableId(type = IdType.ASSIGN_UUID)
|
||||
@Schema(description = "快照ID")
|
||||
private String id;
|
||||
|
||||
@Schema(description = "智能体ID")
|
||||
private String agentId;
|
||||
|
||||
@Schema(description = "所属用户ID")
|
||||
private Long userId;
|
||||
|
||||
@Schema(description = "版本号")
|
||||
private Integer versionNo;
|
||||
|
||||
@Schema(description = "快照数据JSON")
|
||||
private String snapshotData;
|
||||
|
||||
@Schema(description = "变更字段JSON")
|
||||
private String changedFields;
|
||||
|
||||
@Schema(description = "快照来源")
|
||||
private String source;
|
||||
|
||||
@Schema(description = "恢复来源快照ID")
|
||||
private String restoreFromSnapshotId;
|
||||
|
||||
@Schema(description = "恢复来源版本号")
|
||||
private Integer restoreFromVersionNo;
|
||||
|
||||
@Schema(description = "创建者")
|
||||
private Long creator;
|
||||
|
||||
@Schema(description = "创建时间")
|
||||
private Date createdAt;
|
||||
|
||||
@Schema(description = "快照数据脱敏规则版本")
|
||||
private Integer redactionVersion;
|
||||
}
|
||||
+2
-2
@@ -1,6 +1,6 @@
|
||||
package xiaozhi.modules.agent.service;
|
||||
|
||||
import com.baomidou.mybatisplus.extension.repository.IRepository;
|
||||
import com.baomidou.mybatisplus.extension.service.IService;
|
||||
|
||||
import xiaozhi.modules.agent.entity.AgentChatAudioEntity;
|
||||
|
||||
@@ -11,7 +11,7 @@ import xiaozhi.modules.agent.entity.AgentChatAudioEntity;
|
||||
* @version 1.0, 2025/5/8
|
||||
* @since 1.0.0
|
||||
*/
|
||||
public interface AgentChatAudioService extends IRepository<AgentChatAudioEntity> {
|
||||
public interface AgentChatAudioService extends IService<AgentChatAudioEntity> {
|
||||
/**
|
||||
* 保存音频数据
|
||||
*
|
||||
|
||||
+4
-20
@@ -3,9 +3,9 @@ package xiaozhi.modules.agent.service;
|
||||
import java.util.List;
|
||||
import java.util.Map;
|
||||
|
||||
import com.baomidou.mybatisplus.extension.repository.IRepository;
|
||||
|
||||
import xiaozhi.common.page.PageData;
|
||||
import com.baomidou.mybatisplus.extension.service.IService;
|
||||
|
||||
import xiaozhi.common.page.PageData;
|
||||
import xiaozhi.modules.agent.dto.AgentChatHistoryDTO;
|
||||
import xiaozhi.modules.agent.dto.AgentChatSessionDTO;
|
||||
import xiaozhi.modules.agent.entity.AgentChatHistoryEntity;
|
||||
@@ -18,7 +18,7 @@ import xiaozhi.modules.agent.vo.AgentChatHistoryUserVO;
|
||||
* @version 1.0, 2025/4/30
|
||||
* @since 1.0.0
|
||||
*/
|
||||
public interface AgentChatHistoryService extends IRepository<AgentChatHistoryEntity> {
|
||||
public interface AgentChatHistoryService extends IService<AgentChatHistoryEntity> {
|
||||
|
||||
/**
|
||||
* 根据智能体ID获取会话列表
|
||||
@@ -37,14 +37,6 @@ public interface AgentChatHistoryService extends IRepository<AgentChatHistoryEnt
|
||||
*/
|
||||
List<AgentChatHistoryDTO> getChatHistoryBySessionId(String agentId, String sessionId);
|
||||
|
||||
/**
|
||||
* 根据会话ID获取智能体ID
|
||||
*
|
||||
* @param sessionId 会话ID
|
||||
* @return 智能体ID
|
||||
*/
|
||||
String getAgentIdBySessionId(String sessionId);
|
||||
|
||||
/**
|
||||
* 根据智能体ID删除聊天记录
|
||||
*
|
||||
@@ -70,14 +62,6 @@ public interface AgentChatHistoryService extends IRepository<AgentChatHistoryEnt
|
||||
*/
|
||||
String getContentByAudioId(String audioId);
|
||||
|
||||
/**
|
||||
* 根据音频ID获取智能体ID
|
||||
*
|
||||
* @param audioId 音频ID
|
||||
* @return 智能体ID
|
||||
*/
|
||||
String getAgentIdByAudioId(String audioId);
|
||||
|
||||
|
||||
/**
|
||||
* 查询此音频id是否属于此智能体
|
||||
|
||||
+4
-11
@@ -2,7 +2,7 @@ package xiaozhi.modules.agent.service;
|
||||
|
||||
import java.util.List;
|
||||
|
||||
import com.baomidou.mybatisplus.extension.repository.IRepository;
|
||||
import com.baomidou.mybatisplus.extension.service.IService;
|
||||
|
||||
import xiaozhi.modules.agent.entity.AgentPluginMapping;
|
||||
|
||||
@@ -10,11 +10,11 @@ import xiaozhi.modules.agent.entity.AgentPluginMapping;
|
||||
* @description 针对表【ai_agent_plugin_mapping(Agent与插件的唯一映射表)】的数据库操作Service
|
||||
* @createDate 2025-05-25 22:33:17
|
||||
*/
|
||||
public interface AgentPluginMappingService extends IRepository<AgentPluginMapping> {
|
||||
public interface AgentPluginMappingService extends IService<AgentPluginMapping> {
|
||||
|
||||
/**
|
||||
* 根据智能体id获取插件参数
|
||||
*
|
||||
*
|
||||
* @param agentId
|
||||
* @return
|
||||
*/
|
||||
@@ -22,15 +22,8 @@ public interface AgentPluginMappingService extends IRepository<AgentPluginMappin
|
||||
|
||||
/**
|
||||
* 根据智能体id删除插件参数
|
||||
*
|
||||
*
|
||||
* @param agentId
|
||||
*/
|
||||
void deleteByAgentId(String agentId);
|
||||
|
||||
/**
|
||||
* 根据插件ID删除所有智能体的插件映射
|
||||
*
|
||||
* @param pluginId 插件ID
|
||||
*/
|
||||
void deleteByPluginId(String pluginId);
|
||||
}
|
||||
|
||||
@@ -7,7 +7,6 @@ import xiaozhi.common.page.PageData;
|
||||
import xiaozhi.common.service.BaseService;
|
||||
import xiaozhi.modules.agent.dto.AgentCreateDTO;
|
||||
import xiaozhi.modules.agent.dto.AgentDTO;
|
||||
import xiaozhi.modules.agent.dto.AgentMemoryDTO;
|
||||
import xiaozhi.modules.agent.dto.AgentUpdateDTO;
|
||||
import xiaozhi.modules.agent.entity.AgentEntity;
|
||||
import xiaozhi.modules.agent.vo.AgentInfoVO;
|
||||
@@ -36,15 +35,6 @@ public interface AgentService extends BaseService<AgentEntity> {
|
||||
*/
|
||||
AgentInfoVO getAgentById(String id);
|
||||
|
||||
/**
|
||||
* 根据ID获取当前用户有权访问的智能体
|
||||
*
|
||||
* @param id 智能体ID
|
||||
* @param userId 当前用户ID
|
||||
* @return 智能体实体
|
||||
*/
|
||||
AgentInfoVO getAgentById(String id, Long userId);
|
||||
|
||||
/**
|
||||
* 插入智能体
|
||||
*
|
||||
@@ -60,13 +50,6 @@ public interface AgentService extends BaseService<AgentEntity> {
|
||||
*/
|
||||
void deleteAgentByUserId(Long userId);
|
||||
|
||||
/**
|
||||
* 删除智能体及其关联数据
|
||||
*
|
||||
* @param agentId 智能体ID
|
||||
*/
|
||||
void deleteAgent(String agentId);
|
||||
|
||||
/**
|
||||
* 获取用户智能体列表
|
||||
*
|
||||
@@ -110,41 +93,6 @@ public interface AgentService extends BaseService<AgentEntity> {
|
||||
*/
|
||||
void updateAgentById(String agentId, AgentUpdateDTO dto);
|
||||
|
||||
/**
|
||||
* 更新当前用户有权访问的智能体
|
||||
*
|
||||
* @param agentId 智能体ID
|
||||
* @param dto 更新智能体所需的信息
|
||||
* @param userId 当前用户ID
|
||||
*/
|
||||
void updateAgentById(String agentId, AgentUpdateDTO dto, Long userId);
|
||||
|
||||
/**
|
||||
* 根据设备MAC地址更新当前用户有权访问的智能体记忆
|
||||
*
|
||||
* @param macAddress 设备MAC地址
|
||||
* @param dto 智能体记忆
|
||||
* @param userId 当前用户ID
|
||||
*/
|
||||
void updateAgentMemoryByDeviceMacAddress(String macAddress, AgentMemoryDTO dto, Long userId);
|
||||
|
||||
/**
|
||||
* 删除当前用户有权访问的智能体
|
||||
*
|
||||
* @param agentId 智能体ID
|
||||
* @param userId 当前用户ID
|
||||
*/
|
||||
void deleteAgentById(String agentId, Long userId);
|
||||
|
||||
/**
|
||||
* 更新智能体
|
||||
*
|
||||
* @param agentId 智能体ID
|
||||
* @param dto 更新智能体所需的信息
|
||||
* @param createSnapshot 是否创建配置快照
|
||||
*/
|
||||
void updateAgentById(String agentId, AgentUpdateDTO dto, boolean createSnapshot);
|
||||
|
||||
/**
|
||||
* 创建智能体
|
||||
*
|
||||
|
||||
-25
@@ -1,25 +0,0 @@
|
||||
package xiaozhi.modules.agent.service;
|
||||
|
||||
import xiaozhi.common.page.PageData;
|
||||
import xiaozhi.common.service.BaseService;
|
||||
import xiaozhi.modules.agent.dto.AgentSnapshotPageDTO;
|
||||
import xiaozhi.modules.agent.entity.AgentSnapshotEntity;
|
||||
import xiaozhi.modules.agent.vo.AgentSnapshotVO;
|
||||
|
||||
public interface AgentSnapshotService extends BaseService<AgentSnapshotEntity> {
|
||||
void createSnapshot(String agentId, String source);
|
||||
|
||||
PageData<AgentSnapshotVO> page(String agentId, AgentSnapshotPageDTO params);
|
||||
|
||||
AgentSnapshotVO getSnapshot(String agentId, String snapshotId);
|
||||
|
||||
void restoreSnapshot(String agentId, String snapshotId, String currentStateToken);
|
||||
|
||||
void deleteSnapshot(String agentId, String snapshotId);
|
||||
|
||||
Integer getCurrentVersionNo(String agentId);
|
||||
|
||||
void deleteByAgentId(String agentId);
|
||||
|
||||
long redactLegacySnapshots();
|
||||
}
|
||||
+3
-3
@@ -1,7 +1,7 @@
|
||||
package xiaozhi.modules.agent.service;
|
||||
|
||||
import com.baomidou.mybatisplus.extension.repository.IRepository;
|
||||
|
||||
import com.baomidou.mybatisplus.extension.service.IService;
|
||||
|
||||
import xiaozhi.modules.agent.entity.AgentTemplateEntity;
|
||||
|
||||
/**
|
||||
@@ -9,7 +9,7 @@ import xiaozhi.modules.agent.entity.AgentTemplateEntity;
|
||||
* @description 针对表【ai_agent_template(智能体配置模板表)】的数据库操作Service
|
||||
* @createDate 2025-03-22 11:48:18
|
||||
*/
|
||||
public interface AgentTemplateService extends IRepository<AgentTemplateEntity> {
|
||||
public interface AgentTemplateService extends IService<AgentTemplateEntity> {
|
||||
|
||||
/**
|
||||
* 获取默认模板
|
||||
|
||||
+2
-2
@@ -2,7 +2,7 @@ package xiaozhi.modules.agent.service.impl;
|
||||
|
||||
import org.springframework.stereotype.Service;
|
||||
|
||||
import com.baomidou.mybatisplus.spring.repository.CrudRepository;
|
||||
import com.baomidou.mybatisplus.extension.service.impl.ServiceImpl;
|
||||
|
||||
import xiaozhi.modules.agent.dao.AiAgentChatAudioDao;
|
||||
import xiaozhi.modules.agent.entity.AgentChatAudioEntity;
|
||||
@@ -16,7 +16,7 @@ import xiaozhi.modules.agent.service.AgentChatAudioService;
|
||||
* @since 1.0.0
|
||||
*/
|
||||
@Service
|
||||
public class AgentChatAudioServiceImpl extends CrudRepository<AiAgentChatAudioDao, AgentChatAudioEntity>
|
||||
public class AgentChatAudioServiceImpl extends ServiceImpl<AiAgentChatAudioDao, AgentChatAudioEntity>
|
||||
implements AgentChatAudioService {
|
||||
@Override
|
||||
public String saveAudio(byte[] audioData) {
|
||||
|
||||
+3
-29
@@ -14,7 +14,7 @@ import com.baomidou.mybatisplus.core.conditions.query.LambdaQueryWrapper;
|
||||
import com.baomidou.mybatisplus.core.conditions.query.QueryWrapper;
|
||||
import com.baomidou.mybatisplus.core.metadata.IPage;
|
||||
import com.baomidou.mybatisplus.extension.plugins.pagination.Page;
|
||||
import com.baomidou.mybatisplus.spring.repository.CrudRepository;
|
||||
import com.baomidou.mybatisplus.extension.service.impl.ServiceImpl;
|
||||
|
||||
import xiaozhi.common.constant.Constant;
|
||||
import xiaozhi.common.page.PageData;
|
||||
@@ -39,7 +39,7 @@ import xiaozhi.modules.agent.vo.AgentChatHistoryUserVO;
|
||||
*/
|
||||
@Service
|
||||
@RequiredArgsConstructor
|
||||
public class AgentChatHistoryServiceImpl extends CrudRepository<AiAgentChatHistoryDao, AgentChatHistoryEntity>
|
||||
public class AgentChatHistoryServiceImpl extends ServiceImpl<AiAgentChatHistoryDao, AgentChatHistoryEntity>
|
||||
implements AgentChatHistoryService {
|
||||
|
||||
private final AgentChatTitleService agentChatTitleService;
|
||||
@@ -88,19 +88,6 @@ public class AgentChatHistoryServiceImpl extends CrudRepository<AiAgentChatHisto
|
||||
return ConvertUtils.sourceToTarget(historyList, AgentChatHistoryDTO.class);
|
||||
}
|
||||
|
||||
@Override
|
||||
public String getAgentIdBySessionId(String sessionId) {
|
||||
if (sessionId == null || sessionId.isBlank()) {
|
||||
return null;
|
||||
}
|
||||
AgentChatHistoryEntity entity = baseMapper.selectOne(
|
||||
new LambdaQueryWrapper<AgentChatHistoryEntity>()
|
||||
.select(AgentChatHistoryEntity::getAgentId)
|
||||
.eq(AgentChatHistoryEntity::getSessionId, sessionId)
|
||||
.last("LIMIT 1"));
|
||||
return entity == null ? null : entity.getAgentId();
|
||||
}
|
||||
|
||||
@Override
|
||||
@Transactional(rollbackFor = Exception.class)
|
||||
public void deleteByAgentId(String agentId, Boolean deleteAudio, Boolean deleteText) {
|
||||
@@ -167,7 +154,7 @@ public class AgentChatHistoryServiceImpl extends CrudRepository<AiAgentChatHisto
|
||||
|
||||
// 尝试解析为 JSON
|
||||
try {
|
||||
Map<String, Object> jsonMap = JsonUtils.parseMap(content);
|
||||
Map<String, Object> jsonMap = JsonUtils.parseObject(content, Map.class);
|
||||
if (jsonMap != null && jsonMap.containsKey("content")) {
|
||||
Object contentObj = jsonMap.get("content");
|
||||
return contentObj != null ? contentObj.toString() : content;
|
||||
@@ -189,19 +176,6 @@ public class AgentChatHistoryServiceImpl extends CrudRepository<AiAgentChatHisto
|
||||
return agentChatHistoryEntity == null ? null : agentChatHistoryEntity.getContent();
|
||||
}
|
||||
|
||||
@Override
|
||||
public String getAgentIdByAudioId(String audioId) {
|
||||
if (audioId == null || audioId.isBlank()) {
|
||||
return null;
|
||||
}
|
||||
AgentChatHistoryEntity entity = baseMapper.selectOne(
|
||||
new LambdaQueryWrapper<AgentChatHistoryEntity>()
|
||||
.select(AgentChatHistoryEntity::getAgentId)
|
||||
.eq(AgentChatHistoryEntity::getAudioId, audioId)
|
||||
.last("LIMIT 1"));
|
||||
return entity == null ? null : entity.getAgentId();
|
||||
}
|
||||
|
||||
@Override
|
||||
public boolean isAudioOwnedByAgent(String audioId, String agentId) {
|
||||
// 查询是否有指定音频id和智能体id的数据，如果有且只有一条说明此数据属性此智能体
|
||||
|
||||
+2
-2
@@ -118,7 +118,7 @@ public class AgentChatSummaryServiceImpl implements AgentChatSummaryService {
|
||||
{
|
||||
setSummaryMemory(summaryDTO.getSummary());
|
||||
}
|
||||
}, false);
|
||||
});
|
||||
log.info("成功保存会话 {} 的聊天记录总结到智能体 {}", sessionId, agentId);
|
||||
} else {
|
||||
log.info("生成总结失败: {}", summaryDTO.getErrorMessage());
|
||||
@@ -518,4 +518,4 @@ public class AgentChatSummaryServiceImpl implements AgentChatSummaryService {
|
||||
return null;
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
+10
-10
@@ -76,7 +76,7 @@ public class AgentMcpAccessPointServiceImpl implements AgentMcpAccessPointServic
|
||||
// 等待初始化响应 (id=1) - 移除固定延迟，改为响应驱动
|
||||
List<String> initResponses = client.listenerWithoutClose(response -> {
|
||||
try {
|
||||
Map<String, Object> jsonMap = JsonUtils.parseMap(response);
|
||||
Map<String, Object> jsonMap = JsonUtils.parseObject(response, Map.class);
|
||||
if (jsonMap != null && Integer.valueOf(1).equals(jsonMap.get("id"))) {
|
||||
// 检查是否有result字段，表示初始化成功
|
||||
return jsonMap.containsKey("result") && !jsonMap.containsKey("error");
|
||||
@@ -92,7 +92,7 @@ public class AgentMcpAccessPointServiceImpl implements AgentMcpAccessPointServic
|
||||
boolean initSucceeded = false;
|
||||
for (String response : initResponses) {
|
||||
try {
|
||||
Map<String, Object> jsonMap = JsonUtils.parseMap(response);
|
||||
Map<String, Object> jsonMap = JsonUtils.parseObject(response, Map.class);
|
||||
if (jsonMap != null && Integer.valueOf(1).equals(jsonMap.get("id"))) {
|
||||
if (jsonMap.containsKey("result")) {
|
||||
log.info("MCP初始化成功，智能体ID: {}", id);
|
||||
@@ -123,7 +123,7 @@ public class AgentMcpAccessPointServiceImpl implements AgentMcpAccessPointServic
|
||||
// 等待工具列表响应 (id=2)
|
||||
List<String> toolsResponses = client.listener(response -> {
|
||||
try {
|
||||
Map<String, Object> jsonMap = JsonUtils.parseMap(response);
|
||||
Map<String, Object> jsonMap = JsonUtils.parseObject(response, Map.class);
|
||||
return jsonMap != null && Integer.valueOf(2).equals(jsonMap.get("id"));
|
||||
} catch (Exception e) {
|
||||
log.warn("解析工具列表响应失败: {}", response, e);
|
||||
@@ -134,18 +134,18 @@ public class AgentMcpAccessPointServiceImpl implements AgentMcpAccessPointServic
|
||||
// 处理工具列表响应
|
||||
for (String response : toolsResponses) {
|
||||
try {
|
||||
Map<String, Object> jsonMap = JsonUtils.parseMap(response);
|
||||
Map<String, Object> jsonMap = JsonUtils.parseObject(response, Map.class);
|
||||
if (jsonMap != null && Integer.valueOf(2).equals(jsonMap.get("id"))) {
|
||||
// 检查是否有result字段
|
||||
Object resultObj = jsonMap.get("result");
|
||||
if (resultObj instanceof Map<?, ?>) {
|
||||
Map<String, Object> resultMap = JsonUtils.toStringObjectMap(resultObj);
|
||||
if (resultObj instanceof Map) {
|
||||
Map<String, Object> resultMap = (Map<String, Object>) resultObj;
|
||||
Object toolsObj = resultMap.get("tools");
|
||||
if (toolsObj instanceof List<?>) {
|
||||
List<Map<String, Object>> toolsList = JsonUtils.toStringObjectMapList(toolsObj);
|
||||
if (toolsObj instanceof List) {
|
||||
List<Map<String, Object>> toolsList = (List<Map<String, Object>>) toolsObj;
|
||||
// 提取工具名称列表
|
||||
List<String> result = toolsList.stream()
|
||||
.map(tool -> String.class.cast(tool.get("name")))
|
||||
.map(tool -> (String) tool.get("name"))
|
||||
.filter(name -> name != null)
|
||||
.sorted()
|
||||
.collect(Collectors.toList());
|
||||
@@ -232,4 +232,4 @@ public class AgentMcpAccessPointServiceImpl implements AgentMcpAccessPointServic
|
||||
// 加密后成token值
|
||||
return AESUtils.encrypt(key, json);
|
||||
}
|
||||
}
|
||||
}
|
||||
+2
-9
@@ -9,7 +9,7 @@ import org.apache.commons.lang3.StringUtils;
|
||||
import org.springframework.stereotype.Service;
|
||||
|
||||
import com.baomidou.mybatisplus.core.conditions.update.UpdateWrapper;
|
||||
import com.baomidou.mybatisplus.spring.repository.CrudRepository;
|
||||
import com.baomidou.mybatisplus.extension.service.impl.ServiceImpl;
|
||||
|
||||
import lombok.RequiredArgsConstructor;
|
||||
import lombok.extern.slf4j.Slf4j;
|
||||
@@ -29,7 +29,7 @@ import xiaozhi.modules.model.service.ModelConfigService;
|
||||
@Service
|
||||
@RequiredArgsConstructor
|
||||
@Slf4j
|
||||
public class AgentPluginMappingServiceImpl extends CrudRepository<AgentPluginMappingMapper, AgentPluginMapping>
|
||||
public class AgentPluginMappingServiceImpl extends ServiceImpl<AgentPluginMappingMapper, AgentPluginMapping>
|
||||
implements AgentPluginMappingService {
|
||||
private final AgentPluginMappingMapper agentPluginMappingMapper;
|
||||
private final KnowledgeBaseService knowledgeBaseService;
|
||||
@@ -104,11 +104,4 @@ public class AgentPluginMappingServiceImpl extends CrudRepository<AgentPluginMap
|
||||
agentPluginMappingMapper.delete(updateWrapper);
|
||||
}
|
||||
|
||||
@Override
|
||||
public void deleteByPluginId(String pluginId) {
|
||||
UpdateWrapper<AgentPluginMapping> updateWrapper = new UpdateWrapper<>();
|
||||
updateWrapper.eq("plugin_id", pluginId);
|
||||
agentPluginMappingMapper.delete(updateWrapper);
|
||||
}
|
||||
|
||||
}
|
||||
|
||||
+93
-233
@@ -15,8 +15,8 @@ import org.springframework.stereotype.Service;
|
||||
import org.springframework.transaction.annotation.Transactional;
|
||||
|
||||
import com.baomidou.mybatisplus.core.conditions.query.QueryWrapper;
|
||||
import com.baomidou.mybatisplus.core.conditions.update.UpdateWrapper;
|
||||
import com.baomidou.mybatisplus.core.metadata.IPage;
|
||||
import com.baomidou.mybatisplus.extension.repository.IRepository;
|
||||
|
||||
import lombok.AllArgsConstructor;
|
||||
import xiaozhi.common.constant.Constant;
|
||||
@@ -34,7 +34,6 @@ import xiaozhi.modules.agent.dao.AgentDao;
|
||||
import xiaozhi.modules.agent.dao.AgentTagDao;
|
||||
import xiaozhi.modules.agent.dto.AgentCreateDTO;
|
||||
import xiaozhi.modules.agent.dto.AgentDTO;
|
||||
import xiaozhi.modules.agent.dto.AgentMemoryDTO;
|
||||
import xiaozhi.modules.agent.dto.AgentTagDTO;
|
||||
import xiaozhi.modules.agent.dto.AgentUpdateDTO;
|
||||
import xiaozhi.modules.agent.entity.AgentContextProviderEntity;
|
||||
@@ -44,10 +43,9 @@ import xiaozhi.modules.agent.entity.AgentTagEntity;
|
||||
import xiaozhi.modules.agent.entity.AgentTemplateEntity;
|
||||
import xiaozhi.modules.agent.service.AgentChatHistoryService;
|
||||
import xiaozhi.modules.agent.service.AgentContextProviderService;
|
||||
import xiaozhi.modules.agent.service.AgentPluginMappingService;
|
||||
import xiaozhi.modules.agent.service.AgentService;
|
||||
import xiaozhi.modules.agent.service.AgentSnapshotService;
|
||||
import xiaozhi.modules.agent.service.AgentTagService;
|
||||
import xiaozhi.modules.agent.service.AgentPluginMappingService;
|
||||
import xiaozhi.modules.agent.service.AgentService;
|
||||
import xiaozhi.modules.agent.service.AgentTagService;
|
||||
import xiaozhi.modules.agent.service.AgentTemplateService;
|
||||
import xiaozhi.modules.agent.vo.AgentInfoVO;
|
||||
import xiaozhi.modules.correctword.service.CorrectWordFileService;
|
||||
@@ -58,9 +56,9 @@ import xiaozhi.modules.model.dto.VoiceDTO;
|
||||
import xiaozhi.modules.model.entity.ModelConfigEntity;
|
||||
import xiaozhi.modules.model.service.ModelConfigService;
|
||||
import xiaozhi.modules.model.service.ModelProviderService;
|
||||
import xiaozhi.modules.security.user.SecurityUser;
|
||||
import xiaozhi.modules.sys.enums.SuperAdminEnum;
|
||||
import xiaozhi.modules.timbre.service.TimbreService;
|
||||
import xiaozhi.modules.security.user.SecurityUser;
|
||||
import xiaozhi.modules.sys.enums.SuperAdminEnum;
|
||||
import xiaozhi.modules.timbre.service.TimbreService;
|
||||
|
||||
@Service
|
||||
@AllArgsConstructor
|
||||
@@ -75,10 +73,9 @@ public class AgentServiceImpl extends BaseServiceImpl<AgentDao, AgentEntity> imp
|
||||
private final AgentChatHistoryService agentChatHistoryService;
|
||||
private final AgentTemplateService agentTemplateService;
|
||||
private final ModelProviderService modelProviderService;
|
||||
private final AgentContextProviderService agentContextProviderService;
|
||||
private final AgentTagService agentTagService;
|
||||
private final CorrectWordFileService correctWordFileService;
|
||||
private final AgentSnapshotService agentSnapshotService;
|
||||
private final AgentContextProviderService agentContextProviderService;
|
||||
private final AgentTagService agentTagService;
|
||||
private final CorrectWordFileService correctWordFileService;
|
||||
|
||||
@Override
|
||||
public PageData<AgentEntity> adminAgentList(Map<String, Object> params) {
|
||||
@@ -95,7 +92,6 @@ public class AgentServiceImpl extends BaseServiceImpl<AgentDao, AgentEntity> imp
|
||||
if (agent == null) {
|
||||
throw new RenException(ErrorCode.AGENT_NOT_FOUND);
|
||||
}
|
||||
requireCurrentUserPermissionIfPresent(agent);
|
||||
|
||||
if (agent.getMemModelId() != null && agent.getMemModelId().equals(Constant.MEMORY_NO_MEM)) {
|
||||
agent.setChatHistoryConf(Constant.ChatHistoryConfEnum.IGNORE.getCode());
|
||||
@@ -110,74 +106,14 @@ public class AgentServiceImpl extends BaseServiceImpl<AgentDao, AgentEntity> imp
|
||||
agent.setContextProviders(contextProviderEntity.getContextProviders());
|
||||
}
|
||||
|
||||
// 查询替换词文件ID列表
|
||||
List<String> correctWordFileIds = correctWordFileService.getAgentCorrectWordFileIds(id);
|
||||
agent.setCorrectWordFileIds(correctWordFileIds);
|
||||
agent.setCurrentVersionNo(agentSnapshotService.getCurrentVersionNo(id));
|
||||
|
||||
// 无需额外查询插件列表，已通过SQL查询出来
|
||||
return agent;
|
||||
// 查询替换词文件ID列表
|
||||
List<String> correctWordFileIds = correctWordFileService.getAgentCorrectWordFileIds(id);
|
||||
agent.setCorrectWordFileIds(correctWordFileIds);
|
||||
|
||||
// 无需额外查询插件列表，已通过SQL查询出来
|
||||
return agent;
|
||||
}
|
||||
|
||||
@Override
|
||||
public AgentInfoVO getAgentById(String id, Long userId) {
|
||||
AgentInfoVO agent = getAgentById(id);
|
||||
requireAgentPermission(agent, userId);
|
||||
return agent;
|
||||
}
|
||||
|
||||
private AgentEntity getAgentEntityOrThrow(String agentId) {
|
||||
AgentEntity agent = agentDao.selectById(agentId);
|
||||
if (agent == null) {
|
||||
throw new RenException(ErrorCode.AGENT_NOT_FOUND);
|
||||
}
|
||||
return agent;
|
||||
}
|
||||
|
||||
private boolean isCurrentUserSuperAdmin() {
|
||||
UserDetail user = SecurityUser.getUser();
|
||||
return user != null && Integer.valueOf(SuperAdminEnum.YES.value()).equals(user.getSuperAdmin());
|
||||
}
|
||||
|
||||
private void requireCurrentUserPermissionIfPresent(AgentEntity agent) {
|
||||
Long userId = SecurityUser.getUserId();
|
||||
if (userId != null) {
|
||||
requireAgentPermission(agent, userId);
|
||||
}
|
||||
}
|
||||
|
||||
private boolean hasAgentPermission(AgentEntity agent, Long userId) {
|
||||
if (agent == null) {
|
||||
return false;
|
||||
}
|
||||
if (isCurrentUserSuperAdmin()) {
|
||||
return true;
|
||||
}
|
||||
return userId != null && userId.equals(agent.getUserId());
|
||||
}
|
||||
|
||||
private void requireAgentPermission(AgentEntity agent, Long userId) {
|
||||
if (!hasAgentPermission(agent, userId)) {
|
||||
throw new RenException(ErrorCode.NO_PERMISSION);
|
||||
}
|
||||
}
|
||||
|
||||
private boolean hasDevicePermission(DeviceEntity device, Long userId) {
|
||||
if (device == null) {
|
||||
return false;
|
||||
}
|
||||
if (isCurrentUserSuperAdmin()) {
|
||||
return true;
|
||||
}
|
||||
return userId != null && userId.equals(device.getUserId());
|
||||
}
|
||||
|
||||
private void requireDevicePermission(DeviceEntity device, Long userId) {
|
||||
if (!hasDevicePermission(device, userId)) {
|
||||
throw new RenException(ErrorCode.NO_PERMISSION);
|
||||
}
|
||||
}
|
||||
|
||||
@Override
|
||||
public boolean insert(AgentEntity entity) {
|
||||
// 如果ID为空，自动生成一个UUID作为ID
|
||||
@@ -198,35 +134,15 @@ public class AgentServiceImpl extends BaseServiceImpl<AgentDao, AgentEntity> imp
|
||||
return super.insert(entity);
|
||||
}
|
||||
|
||||
@Override
|
||||
@Transactional(rollbackFor = Exception.class)
|
||||
public void deleteAgentByUserId(Long userId) {
|
||||
List<AgentEntity> agents = baseDao.selectList(new QueryWrapper<AgentEntity>()
|
||||
.select("id")
|
||||
.eq("user_id", userId));
|
||||
for (AgentEntity agent : agents) {
|
||||
deleteAgent(agent.getId());
|
||||
}
|
||||
}
|
||||
|
||||
@Override
|
||||
@Transactional(rollbackFor = Exception.class)
|
||||
public void deleteAgent(String agentId) {
|
||||
if (agentDao.selectByIdForUpdate(agentId) == null) {
|
||||
return;
|
||||
}
|
||||
deviceService.deleteByAgentId(agentId);
|
||||
agentChatHistoryService.deleteByAgentId(agentId, true, true);
|
||||
agentPluginMappingService.deleteByAgentId(agentId);
|
||||
agentContextProviderService.deleteByAgentId(agentId);
|
||||
correctWordFileService.deleteMappingsByAgentId(agentId);
|
||||
agentTagService.deleteAgentTags(agentId);
|
||||
agentSnapshotService.deleteByAgentId(agentId);
|
||||
deleteById(agentId);
|
||||
}
|
||||
|
||||
@Override
|
||||
public List<AgentDTO> getUserAgents(Long userId, String keyword, String searchType) {
|
||||
@Override
|
||||
public void deleteAgentByUserId(Long userId) {
|
||||
UpdateWrapper<AgentEntity> wrapper = new UpdateWrapper<>();
|
||||
wrapper.eq("user_id", userId);
|
||||
baseDao.delete(wrapper);
|
||||
}
|
||||
|
||||
@Override
|
||||
public List<AgentDTO> getUserAgents(Long userId, String keyword, String searchType) {
|
||||
QueryWrapper<AgentEntity> queryWrapper = new QueryWrapper<>();
|
||||
queryWrapper.eq("user_id", userId).orderByDesc("created_at");
|
||||
|
||||
@@ -337,56 +253,42 @@ public class AgentServiceImpl extends BaseServiceImpl<AgentDao, AgentEntity> imp
|
||||
}
|
||||
|
||||
@Override
|
||||
public boolean checkAgentPermission(String agentId, Long userId) {
|
||||
AgentEntity agent = agentDao.selectById(agentId);
|
||||
return hasAgentPermission(agent, userId);
|
||||
}
|
||||
|
||||
// 根据id更新智能体信息
|
||||
@Override
|
||||
@Transactional(rollbackFor = Exception.class)
|
||||
public void updateAgentById(String agentId, AgentUpdateDTO dto) {
|
||||
updateAgentById(agentId, dto, true);
|
||||
}
|
||||
|
||||
@Override
|
||||
@Transactional(rollbackFor = Exception.class)
|
||||
public void updateAgentById(String agentId, AgentUpdateDTO dto, Long userId) {
|
||||
updateAgentById(agentId, dto, userId, true);
|
||||
}
|
||||
|
||||
// 根据id更新智能体信息
|
||||
@Override
|
||||
@Transactional(rollbackFor = Exception.class)
|
||||
public void updateAgentById(String agentId, AgentUpdateDTO dto, boolean createSnapshot) {
|
||||
updateAgentById(agentId, dto, null, createSnapshot);
|
||||
}
|
||||
|
||||
private void updateAgentById(String agentId, AgentUpdateDTO dto, Long userId, boolean createSnapshot) {
|
||||
AgentEntity lockedAgent = agentDao.selectByIdForUpdate(agentId);
|
||||
if (lockedAgent == null) {
|
||||
throw new RenException(ErrorCode.AGENT_NOT_FOUND);
|
||||
}
|
||||
if (userId == null) {
|
||||
requireCurrentUserPermissionIfPresent(lockedAgent);
|
||||
} else {
|
||||
requireAgentPermission(lockedAgent, userId);
|
||||
}
|
||||
|
||||
// 锁定后查询现有实体和关联配置
|
||||
AgentEntity existingEntity = this.getAgentById(agentId);
|
||||
if (createSnapshot) {
|
||||
int currentVersionNo = agentSnapshotService.getCurrentVersionNo(agentId);
|
||||
agentSnapshotService.createSnapshot(agentId, currentVersionNo == 0 ? "initial" : "current");
|
||||
}
|
||||
|
||||
// 只更新提供的非空字段
|
||||
if (dto.getAgentName() != null) {
|
||||
existingEntity.setAgentName(dto.getAgentName());
|
||||
}
|
||||
if (dto.getAgentCode() != null) {
|
||||
existingEntity.setAgentCode(dto.getAgentCode());
|
||||
}
|
||||
public boolean checkAgentPermission(String agentId, Long userId) {
|
||||
if (SecurityUser.getUser() == null || SecurityUser.getUser().getId() == null) {
|
||||
return false;
|
||||
}
|
||||
// 获取智能体信息
|
||||
AgentEntity agent = getAgentById(agentId);
|
||||
if (agent == null) {
|
||||
return false;
|
||||
}
|
||||
|
||||
// 如果是超级管理员，直接返回true
|
||||
if (SecurityUser.getUser().getSuperAdmin() == SuperAdminEnum.YES.value()) {
|
||||
return true;
|
||||
}
|
||||
|
||||
// 检查是否是智能体的所有者
|
||||
return userId.equals(agent.getUserId());
|
||||
}
|
||||
|
||||
// 根据id更新智能体信息
|
||||
@Override
|
||||
@Transactional(rollbackFor = Exception.class)
|
||||
public void updateAgentById(String agentId, AgentUpdateDTO dto) {
|
||||
// 先查询现有实体
|
||||
AgentEntity existingEntity = this.getAgentById(agentId);
|
||||
if (existingEntity == null) {
|
||||
throw new RenException(ErrorCode.AGENT_NOT_FOUND);
|
||||
}
|
||||
|
||||
// 只更新提供的非空字段
|
||||
if (dto.getAgentName() != null) {
|
||||
existingEntity.setAgentName(dto.getAgentName());
|
||||
}
|
||||
if (dto.getAgentCode() != null) {
|
||||
existingEntity.setAgentCode(dto.getAgentCode());
|
||||
}
|
||||
if (dto.getAsrModelId() != null) {
|
||||
existingEntity.setAsrModelId(dto.getAsrModelId());
|
||||
}
|
||||
@@ -483,10 +385,10 @@ public class AgentServiceImpl extends BaseServiceImpl<AgentDao, AgentEntity> imp
|
||||
.toList();
|
||||
|
||||
if (!toUpdate.isEmpty()) {
|
||||
agentPluginMappingService.updateBatchById(toUpdate, IRepository.DEFAULT_BATCH_SIZE);
|
||||
agentPluginMappingService.updateBatchById(toUpdate);
|
||||
}
|
||||
if (!toInsert.isEmpty()) {
|
||||
agentPluginMappingService.saveBatch(toInsert, IRepository.DEFAULT_BATCH_SIZE);
|
||||
agentPluginMappingService.saveBatch(toInsert);
|
||||
}
|
||||
|
||||
// 5. 删除本次不在提交列表里的插件映射
|
||||
@@ -495,7 +397,7 @@ public class AgentServiceImpl extends BaseServiceImpl<AgentDao, AgentEntity> imp
|
||||
.map(AgentPluginMapping::getId)
|
||||
.toList();
|
||||
if (!toDelete.isEmpty()) {
|
||||
agentPluginMappingService.removeByIds(toDelete);
|
||||
agentPluginMappingService.removeBatchByIds(toDelete);
|
||||
}
|
||||
}
|
||||
|
||||
@@ -524,48 +426,17 @@ public class AgentServiceImpl extends BaseServiceImpl<AgentDao, AgentEntity> imp
|
||||
}
|
||||
|
||||
// 更新替换词文件关联
|
||||
if (dto.getCorrectWordFileIds() != null) {
|
||||
correctWordFileService.saveAgentCorrectWords(agentId, dto.getCorrectWordFileIds());
|
||||
}
|
||||
|
||||
// 更新智能体标签
|
||||
if (dto.getTagNames() != null || dto.getTagIds() != null) {
|
||||
agentTagService.saveAgentTags(agentId, dto.getTagIds(), dto.getTagNames());
|
||||
}
|
||||
|
||||
boolean b = validateLLMIntentParams(existingEntity.getLlmModelId(), existingEntity.getIntentModelId());
|
||||
if (!b) {
|
||||
throw new RenException(ErrorCode.LLM_INTENT_PARAMS_MISMATCH);
|
||||
}
|
||||
this.updateById(existingEntity);
|
||||
if (createSnapshot) {
|
||||
agentSnapshotService.createSnapshot(agentId, "config");
|
||||
}
|
||||
}
|
||||
if (dto.getCorrectWordFileIds() != null) {
|
||||
correctWordFileService.saveAgentCorrectWords(agentId, dto.getCorrectWordFileIds());
|
||||
}
|
||||
|
||||
boolean b = validateLLMIntentParams(dto.getLlmModelId(), dto.getIntentModelId());
|
||||
if (!b) {
|
||||
throw new RenException(ErrorCode.LLM_INTENT_PARAMS_MISMATCH);
|
||||
}
|
||||
this.updateById(existingEntity);
|
||||
}
|
||||
|
||||
@Override
|
||||
@Transactional(rollbackFor = Exception.class)
|
||||
public void updateAgentMemoryByDeviceMacAddress(String macAddress, AgentMemoryDTO dto, Long userId) {
|
||||
DeviceEntity device = deviceService.getDeviceByMacAddress(macAddress);
|
||||
if (device == null || StringUtils.isBlank(device.getAgentId()) || dto == null) {
|
||||
return;
|
||||
}
|
||||
|
||||
requireDevicePermission(device, userId);
|
||||
|
||||
AgentUpdateDTO agentUpdateDTO = new AgentUpdateDTO();
|
||||
agentUpdateDTO.setSummaryMemory(dto.getSummaryMemory());
|
||||
updateAgentById(device.getAgentId(), agentUpdateDTO, userId, false);
|
||||
}
|
||||
|
||||
@Override
|
||||
@Transactional(rollbackFor = Exception.class)
|
||||
public void deleteAgentById(String agentId, Long userId) {
|
||||
AgentEntity agent = getAgentEntityOrThrow(agentId);
|
||||
requireAgentPermission(agent, userId);
|
||||
deleteAgent(agentId);
|
||||
}
|
||||
|
||||
/**
|
||||
* 验证大语言模型和意图识别的参数是否符合匹配
|
||||
*
|
||||
@@ -616,22 +487,16 @@ public class AgentServiceImpl extends BaseServiceImpl<AgentDao, AgentEntity> imp
|
||||
template.setTtsVoiceId(timbre.getId());
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
entity.setTtsVoiceId(template.getTtsVoiceId());
|
||||
entity.setTtsLanguage(defaultIfBlank(template.getTtsLanguage(),
|
||||
timbreModelService.getDefaultLanguageById(entity.getTtsVoiceId())));
|
||||
entity.setMemModelId(template.getMemModelId());
|
||||
entity.setIntentModelId(template.getIntentModelId());
|
||||
entity.setSystemPrompt(template.getSystemPrompt());
|
||||
entity.setSummaryMemory(template.getSummaryMemory());
|
||||
if (Constant.MEMORY_NO_MEM.equals(entity.getMemModelId())
|
||||
|| Constant.MEMORY_MEM_REPORT_ONLY.equals(entity.getMemModelId())) {
|
||||
entity.setSummaryMemory("");
|
||||
}
|
||||
|
||||
// 根据记忆模型类型设置默认的chatHistoryConf值
|
||||
if (template.getMemModelId() != null) {
|
||||
}
|
||||
|
||||
entity.setTtsVoiceId(template.getTtsVoiceId());
|
||||
entity.setMemModelId(template.getMemModelId());
|
||||
entity.setIntentModelId(template.getIntentModelId());
|
||||
entity.setSystemPrompt(template.getSystemPrompt());
|
||||
entity.setSummaryMemory(template.getSummaryMemory());
|
||||
|
||||
// 根据记忆模型类型设置默认的chatHistoryConf值
|
||||
if (template.getMemModelId() != null) {
|
||||
if (template.getMemModelId().equals("Memory_nomem")) {
|
||||
// 无记忆功能的模型，默认不记录聊天记录
|
||||
entity.setChatHistoryConf(0);
|
||||
@@ -677,7 +542,7 @@ public class AgentServiceImpl extends BaseServiceImpl<AgentDao, AgentEntity> imp
|
||||
mapping.setPluginId(pluginId);
|
||||
|
||||
Map<String, Object> paramInfo = new HashMap<>();
|
||||
List<Map<String, Object>> fields = JsonUtils.parseMapList(provider.getFields());
|
||||
List<Map<String, Object>> fields = JsonUtils.parseObject(provider.getFields(), List.class);
|
||||
if (fields != null) {
|
||||
for (Map<String, Object> field : fields) {
|
||||
paramInfo.put((String) field.get("key"), field.get("default"));
|
||||
@@ -686,18 +551,13 @@ public class AgentServiceImpl extends BaseServiceImpl<AgentDao, AgentEntity> imp
|
||||
mapping.setParamInfo(JsonUtils.toJsonString(paramInfo));
|
||||
mapping.setAgentId(entity.getId());
|
||||
toInsert.add(mapping);
|
||||
}
|
||||
// 保存默认插件
|
||||
agentPluginMappingService.saveBatch(toInsert, IRepository.DEFAULT_BATCH_SIZE);
|
||||
agentSnapshotService.createSnapshot(entity.getId(), "initial");
|
||||
return entity.getId();
|
||||
}
|
||||
|
||||
private String defaultIfBlank(String value, String defaultValue) {
|
||||
return StringUtils.isBlank(value) ? defaultValue : value;
|
||||
}
|
||||
|
||||
private String getDefaultLLMModelId() {
|
||||
}
|
||||
// 保存默认插件
|
||||
agentPluginMappingService.saveBatch(toInsert);
|
||||
return entity.getId();
|
||||
}
|
||||
|
||||
private String getDefaultLLMModelId() {
|
||||
try {
|
||||
List<ModelConfigEntity> llmConfigs = modelConfigService.getEnabledModelsByType("LLM");
|
||||
if (llmConfigs == null || llmConfigs.isEmpty()) {
|
||||
@@ -716,4 +576,4 @@ public class AgentServiceImpl extends BaseServiceImpl<AgentDao, AgentEntity> imp
|
||||
}
|
||||
}
|
||||
|
||||
}
|
||||
}
|
||||
-59
@@ -1,59 +0,0 @@
|
||||
package xiaozhi.modules.agent.service.impl;
|
||||
|
||||
import java.util.concurrent.TimeUnit;
|
||||
|
||||
import org.springframework.beans.factory.SmartInitializingSingleton;
|
||||
import org.springframework.scheduling.annotation.Scheduled;
|
||||
import org.springframework.stereotype.Component;
|
||||
|
||||
import lombok.RequiredArgsConstructor;
|
||||
import lombok.extern.slf4j.Slf4j;
|
||||
import xiaozhi.modules.agent.service.AgentSnapshotService;
|
||||
|
||||
@Slf4j
|
||||
@Component
|
||||
@RequiredArgsConstructor
|
||||
public class AgentSnapshotRedactionRunner implements SmartInitializingSingleton {
|
||||
static final long ROLLING_DEPLOYMENT_INITIAL_DELAY_MILLIS = 5_000;
|
||||
static final long ROLLING_DEPLOYMENT_FIXED_DELAY_MILLIS = 15_000;
|
||||
|
||||
private final AgentSnapshotService agentSnapshotService;
|
||||
|
||||
@Override
|
||||
public void afterSingletonsInstantiated() {
|
||||
redactAndReport("startup");
|
||||
}
|
||||
|
||||
@Scheduled(initialDelay = ROLLING_DEPLOYMENT_INITIAL_DELAY_MILLIS,
|
||||
fixedDelay = ROLLING_DEPLOYMENT_FIXED_DELAY_MILLIS)
|
||||
public void redactLateRollingDeploymentWrites() {
|
||||
redactAndReport("rolling-deployment");
|
||||
}
|
||||
|
||||
private void redactAndReport(String trigger) {
|
||||
long startedAt = System.nanoTime();
|
||||
try {
|
||||
long migrated = agentSnapshotService.redactLegacySnapshots();
|
||||
long durationMillis = TimeUnit.NANOSECONDS.toMillis(System.nanoTime() - startedAt);
|
||||
if (migrated > 0) {
|
||||
log.warn("Agent snapshot legacy redaction trigger={} migrated={} durationMs={}. Rotate credentials "
|
||||
+ "that may have appeared in historical snapshot URLs, cookies, sessions, or structured "
|
||||
+ "headers.", trigger, migrated, durationMillis);
|
||||
} else if ("startup".equals(trigger)) {
|
||||
log.info("Agent snapshot legacy redaction startup pass completed: migrated=0 durationMs={}; "
|
||||
+ "rolling-deployment compensation starts after {} ms and repeats every {} ms.",
|
||||
durationMillis, ROLLING_DEPLOYMENT_INITIAL_DELAY_MILLIS,
|
||||
ROLLING_DEPLOYMENT_FIXED_DELAY_MILLIS);
|
||||
}
|
||||
} catch (RuntimeException exception) {
|
||||
if ("startup".equals(trigger)) {
|
||||
log.error("Agent snapshot legacy redaction failed during startup; blocking application startup "
|
||||
+ "before it can accept traffic.", exception);
|
||||
} else {
|
||||
log.error("Agent snapshot legacy redaction failed during rolling-deployment compensation; the "
|
||||
+ "scheduler will retry on its next run.", exception);
|
||||
}
|
||||
throw exception;
|
||||
}
|
||||
}
|
||||
}
|
||||
-1772
File diff suppressed because it is too large
Load Diff
+1
-1
@@ -133,7 +133,7 @@ public class AgentTagServiceImpl extends BaseServiceImpl<AgentTagDao, AgentTagEn
|
||||
}
|
||||
|
||||
if (tagIds != null && !tagIds.isEmpty()) {
|
||||
List<AgentTagEntity> tagIdEntities = baseDao.selectByIds(tagIds);
|
||||
List<AgentTagEntity> tagIdEntities = baseDao.selectBatchIds(tagIds);
|
||||
for (AgentTagEntity tag : tagIdEntities) {
|
||||
if (tag != null && (currentTagNames.contains(tag.getTagName()) ||
|
||||
newTagNames.contains(tag.getTagName()))) {
|
||||
|
||||
+3
-3
@@ -4,8 +4,8 @@ import org.springframework.stereotype.Service;
|
||||
|
||||
import com.baomidou.mybatisplus.core.conditions.query.LambdaQueryWrapper;
|
||||
import com.baomidou.mybatisplus.core.conditions.update.UpdateWrapper;
|
||||
import com.baomidou.mybatisplus.spring.repository.CrudRepository;
|
||||
|
||||
import com.baomidou.mybatisplus.extension.service.impl.ServiceImpl;
|
||||
|
||||
import xiaozhi.modules.agent.dao.AgentTemplateDao;
|
||||
import xiaozhi.modules.agent.entity.AgentTemplateEntity;
|
||||
import xiaozhi.modules.agent.service.AgentTemplateService;
|
||||
@@ -21,7 +21,7 @@ import com.baomidou.mybatisplus.core.conditions.query.QueryWrapper;
|
||||
* @createDate 2025-03-22 11:48:18
|
||||
*/
|
||||
@Service
|
||||
public class AgentTemplateServiceImpl extends CrudRepository<AgentTemplateDao, AgentTemplateEntity>
|
||||
public class AgentTemplateServiceImpl extends ServiceImpl<AgentTemplateDao, AgentTemplateEntity>
|
||||
implements AgentTemplateService {
|
||||
|
||||
/**
|
||||
|
||||
+2
-2
@@ -22,7 +22,7 @@ import org.springframework.util.MultiValueMap;
|
||||
import org.springframework.web.client.RestTemplate;
|
||||
|
||||
import com.baomidou.mybatisplus.core.conditions.query.LambdaQueryWrapper;
|
||||
import com.baomidou.mybatisplus.spring.repository.CrudRepository;
|
||||
import com.baomidou.mybatisplus.extension.service.impl.ServiceImpl;
|
||||
|
||||
import lombok.extern.slf4j.Slf4j;
|
||||
import xiaozhi.common.constant.Constant;
|
||||
@@ -46,7 +46,7 @@ import xiaozhi.modules.sys.service.SysParamsService;
|
||||
*/
|
||||
@Service
|
||||
@Slf4j
|
||||
public class AgentVoicePrintServiceImpl extends CrudRepository<AgentVoicePrintDao, AgentVoicePrintEntity>
|
||||
public class AgentVoicePrintServiceImpl extends ServiceImpl<AgentVoicePrintDao, AgentVoicePrintEntity>
|
||||
implements AgentVoicePrintService {
|
||||
private final AgentChatAudioService agentChatAudioService;
|
||||
private final RestTemplate restTemplate;
|
||||
|
||||
-59
@@ -1,59 +0,0 @@
|
||||
package xiaozhi.modules.agent.typehandler;
|
||||
|
||||
import java.sql.CallableStatement;
|
||||
import java.sql.PreparedStatement;
|
||||
import java.sql.ResultSet;
|
||||
import java.sql.SQLException;
|
||||
import java.util.Collections;
|
||||
import java.util.List;
|
||||
|
||||
import org.apache.commons.lang3.StringUtils;
|
||||
import org.apache.ibatis.type.BaseTypeHandler;
|
||||
import org.apache.ibatis.type.JdbcType;
|
||||
|
||||
import com.fasterxml.jackson.core.type.TypeReference;
|
||||
|
||||
import xiaozhi.common.utils.JsonUtils;
|
||||
import xiaozhi.modules.agent.dto.ContextProviderDTO;
|
||||
|
||||
/**
|
||||
* JSON type handler for context providers.
|
||||
*
|
||||
* <p>Do not extend MyBatis-Plus {@code AbstractJsonTypeHandler}: its constructor and JSON handler
|
||||
* contract changed in MyBatis-Plus 3.5.6. {@link BaseTypeHandler} is part of MyBatis itself and
|
||||
* keeps this handler compatible with both 3.5.5 and newer MyBatis-Plus releases.</p>
|
||||
*/
|
||||
public class ContextProviderListTypeHandler extends BaseTypeHandler<List<ContextProviderDTO>> {
|
||||
private static final TypeReference<List<ContextProviderDTO>> CONTEXT_PROVIDER_LIST_TYPE = new TypeReference<>() {
|
||||
};
|
||||
|
||||
@Override
|
||||
public void setNonNullParameter(PreparedStatement ps, int i, List<ContextProviderDTO> parameter,
|
||||
JdbcType jdbcType) throws SQLException {
|
||||
ps.setString(i, JsonUtils.toJsonString(parameter));
|
||||
}
|
||||
|
||||
@Override
|
||||
public List<ContextProviderDTO> getNullableResult(ResultSet rs, String columnName) throws SQLException {
|
||||
return parseNullable(rs.getString(columnName));
|
||||
}
|
||||
|
||||
@Override
|
||||
public List<ContextProviderDTO> getNullableResult(ResultSet rs, int columnIndex) throws SQLException {
|
||||
return parseNullable(rs.getString(columnIndex));
|
||||
}
|
||||
|
||||
@Override
|
||||
public List<ContextProviderDTO> getNullableResult(CallableStatement cs, int columnIndex) throws SQLException {
|
||||
return parseNullable(cs.getString(columnIndex));
|
||||
}
|
||||
|
||||
private List<ContextProviderDTO> parseNullable(String json) {
|
||||
if (StringUtils.isBlank(json)) {
|
||||
return null;
|
||||
}
|
||||
List<ContextProviderDTO> providers = JsonUtils.parseObject(json, CONTEXT_PROVIDER_LIST_TYPE);
|
||||
return providers == null ? Collections.emptyList() : providers;
|
||||
}
|
||||
|
||||
}
|
||||
@@ -1,5 +1,7 @@
|
||||
package xiaozhi.modules.agent.vo;
|
||||
|
||||
import com.baomidou.mybatisplus.annotation.TableField;
|
||||
import com.baomidou.mybatisplus.extension.handlers.JacksonTypeHandler;
|
||||
import io.swagger.v3.oas.annotations.media.Schema;
|
||||
import lombok.Data;
|
||||
import lombok.EqualsAndHashCode;
|
||||
@@ -18,6 +20,7 @@ import java.util.List;
|
||||
public class AgentInfoVO extends AgentEntity
|
||||
{
|
||||
@Schema(description = "插件列表Id")
|
||||
@TableField(typeHandler = JacksonTypeHandler.class)
|
||||
private List<AgentPluginMapping> functions;
|
||||
|
||||
@Schema(description = "上下文源配置")
|
||||
@@ -25,7 +28,4 @@ public class AgentInfoVO extends AgentEntity
|
||||
|
||||
@Schema(description = "替换词文件ID列表")
|
||||
private List<String> correctWordFileIds;
|
||||
|
||||
@Schema(description = "当前配置版本号")
|
||||
private Integer currentVersionNo;
|
||||
}
|
||||
|
||||
@@ -1,34 +0,0 @@
|
||||
package xiaozhi.modules.agent.vo;
|
||||
|
||||
import java.util.Date;
|
||||
import java.util.List;
|
||||
|
||||
import io.swagger.v3.oas.annotations.media.Schema;
|
||||
import lombok.Data;
|
||||
import xiaozhi.modules.agent.dto.AgentSnapshotDataDTO;
|
||||
|
||||
@Data
|
||||
@Schema(description = "智能体配置快照")
|
||||
public class AgentSnapshotVO {
|
||||
private String id;
|
||||
private String agentId;
|
||||
@Schema(description = "所属用户ID，表示该快照归属的智能体所有者")
|
||||
private Long userId;
|
||||
private Integer versionNo;
|
||||
private List<String> changedFields;
|
||||
private List<String> fieldOrder;
|
||||
private String source;
|
||||
@Schema(description = "恢复来源快照ID，仅恢复结果版本有值")
|
||||
private String restoreFromSnapshotId;
|
||||
@Schema(description = "恢复来源版本号，仅恢复结果版本有值")
|
||||
private Integer restoreFromVersionNo;
|
||||
@Schema(description = "创建者，表示触发本次快照写入的操作人")
|
||||
private Long creator;
|
||||
private Date createdAt;
|
||||
private AgentSnapshotDataDTO snapshotData;
|
||||
private AgentSnapshotDataDTO afterSnapshotData;
|
||||
@Schema(description = "恢复预览对应的脱敏当前配置，仅详情接口有值")
|
||||
private AgentSnapshotDataDTO currentSnapshotData;
|
||||
@Schema(description = "恢复预览对应的当前配置状态指纹，仅详情接口有值")
|
||||
private String currentStateToken;
|
||||
}
|
||||
@@ -9,7 +9,6 @@ import xiaozhi.common.constant.Constant;
|
||||
import xiaozhi.common.redis.RedisKeys;
|
||||
import xiaozhi.common.redis.RedisUtils;
|
||||
import xiaozhi.modules.config.service.ConfigService;
|
||||
import xiaozhi.modules.device.service.DeviceAddressBookService;
|
||||
import xiaozhi.modules.sys.service.SysParamsService;
|
||||
|
||||
@Configuration
|
||||
@@ -25,9 +24,6 @@ public class SystemInitConfig {
|
||||
@Autowired
|
||||
private RedisUtils redisUtils;
|
||||
|
||||
@Autowired
|
||||
private DeviceAddressBookService deviceAddressBookService;
|
||||
|
||||
@PostConstruct
|
||||
public void init() {
|
||||
// 检查版本号
|
||||
@@ -41,8 +37,5 @@ public class SystemInitConfig {
|
||||
|
||||
sysParamsService.initServerSecret();
|
||||
configService.getConfig(false);
|
||||
|
||||
// 初始化设备通讯录缓存
|
||||
deviceAddressBookService.refreshCache();
|
||||
}
|
||||
}
|
||||
@@ -10,7 +10,7 @@ public interface ConfigService {
|
||||
* @param isCache 是否缓存
|
||||
* @return 配置信息
|
||||
*/
|
||||
Map<String, Object> getConfig(Boolean isCache);
|
||||
Object getConfig(Boolean isCache);
|
||||
|
||||
/**
|
||||
* 获取智能体模型配置
|
||||
@@ -28,4 +28,4 @@ public interface ConfigService {
|
||||
* @return 替换词列表，格式如 ["模板1|模板01", "模板2|模板02"]
|
||||
*/
|
||||
List<String> getCorrectWords(String macAddress);
|
||||
}
|
||||
}
|
||||
+7
-7
@@ -65,12 +65,12 @@ public class ConfigServiceImpl implements ConfigService {
|
||||
private final CorrectWordFileService correctWordFileService;
|
||||
|
||||
@Override
|
||||
public Map<String, Object> getConfig(Boolean isCache) {
|
||||
public Object getConfig(Boolean isCache) {
|
||||
if (isCache) {
|
||||
// 先从Redis获取配置
|
||||
Object cachedConfig = redisUtils.get(RedisKeys.getServerConfigKey());
|
||||
if (cachedConfig != null) {
|
||||
return JsonUtils.toStringObjectMap(cachedConfig);
|
||||
return cachedConfig;
|
||||
}
|
||||
}
|
||||
|
||||
@@ -123,7 +123,7 @@ public class ConfigServiceImpl implements ConfigService {
|
||||
if (isAdminRequest != null && "true".equals(isAdminRequest)) {
|
||||
// 管理控制台请求，返回getConfig的结果
|
||||
redisUtils.delete(redisKey); // 使用后清理
|
||||
return getConfig(true);
|
||||
return (Map<String, Object>) getConfig(true);
|
||||
}
|
||||
// 根据MAC地址查找设备
|
||||
DeviceEntity device = deviceService.getDeviceByMacAddress(macAddress);
|
||||
@@ -277,10 +277,10 @@ public class ConfigServiceImpl implements ConfigService {
|
||||
// 遍历除最后一个key之外的所有key
|
||||
for (int i = 0; i < keys.length - 1; i++) {
|
||||
String key = keys[i];
|
||||
Object nestedConfig = current.computeIfAbsent(key, ignored -> new HashMap<String, Object>());
|
||||
Map<String, Object> nestedMap = JsonUtils.toStringObjectMap(nestedConfig);
|
||||
current.put(key, nestedMap);
|
||||
current = nestedMap;
|
||||
if (!current.containsKey(key)) {
|
||||
current.put(key, new HashMap<String, Object>());
|
||||
}
|
||||
current = (Map<String, Object>) current.get(key);
|
||||
}
|
||||
|
||||
// 处理最后一个key
|
||||
|
||||
+4
-56
@@ -8,7 +8,6 @@ import org.apache.shiro.authz.annotation.RequiresPermissions;
|
||||
import org.springframework.beans.BeanUtils;
|
||||
import org.springframework.web.bind.annotation.GetMapping;
|
||||
import org.springframework.web.bind.annotation.PathVariable;
|
||||
import org.springframework.web.bind.annotation.RequestParam;
|
||||
import org.springframework.web.bind.annotation.PostMapping;
|
||||
import org.springframework.web.bind.annotation.PutMapping;
|
||||
import org.springframework.web.bind.annotation.RequestBody;
|
||||
@@ -23,17 +22,13 @@ import xiaozhi.common.redis.RedisKeys;
|
||||
import xiaozhi.common.redis.RedisUtils;
|
||||
import xiaozhi.common.user.UserDetail;
|
||||
import xiaozhi.common.utils.Result;
|
||||
import xiaozhi.modules.device.dto.DeviceAddressBookAliasDTO;
|
||||
import xiaozhi.modules.device.dto.DeviceAddressBookPermissionDTO;
|
||||
import xiaozhi.modules.device.dto.DeviceManualAddDTO;
|
||||
import xiaozhi.modules.device.dto.DeviceRegisterDTO;
|
||||
import xiaozhi.modules.device.dto.DeviceToolsCallReqDTO;
|
||||
import xiaozhi.modules.device.dto.DeviceUnBindDTO;
|
||||
import xiaozhi.modules.device.dto.DeviceUpdateDTO;
|
||||
import xiaozhi.modules.device.entity.DeviceEntity;
|
||||
import xiaozhi.modules.device.service.DeviceAddressBookService;
|
||||
import xiaozhi.modules.device.service.DeviceService;
|
||||
import xiaozhi.modules.device.vo.UserShowDeviceListVO;
|
||||
import xiaozhi.modules.security.user.SecurityUser;
|
||||
import xiaozhi.modules.sys.service.SysParamsService;
|
||||
|
||||
@@ -42,14 +37,11 @@ import xiaozhi.modules.sys.service.SysParamsService;
|
||||
@RequestMapping("/device")
|
||||
public class DeviceController {
|
||||
private final DeviceService deviceService;
|
||||
private final DeviceAddressBookService deviceAddressBookService;
|
||||
private final RedisUtils redisUtils;
|
||||
private final SysParamsService sysParamsService;
|
||||
|
||||
public DeviceController(DeviceService deviceService, DeviceAddressBookService deviceAddressBookService,
|
||||
RedisUtils redisUtils, SysParamsService sysParamsService) {
|
||||
public DeviceController(DeviceService deviceService, RedisUtils redisUtils, SysParamsService sysParamsService) {
|
||||
this.deviceService = deviceService;
|
||||
this.deviceAddressBookService = deviceAddressBookService;
|
||||
this.redisUtils = redisUtils;
|
||||
this.sysParamsService = sysParamsService;
|
||||
}
|
||||
@@ -86,10 +78,10 @@ public class DeviceController {
|
||||
@GetMapping("/bind/{agentId}")
|
||||
@Operation(summary = "获取已绑定设备")
|
||||
@RequiresPermissions("sys:role:normal")
|
||||
public Result<List<UserShowDeviceListVO>> getUserDevices(@PathVariable String agentId) {
|
||||
public Result<List<DeviceEntity>> getUserDevices(@PathVariable String agentId) {
|
||||
UserDetail user = SecurityUser.getUser();
|
||||
List<UserShowDeviceListVO> devices = deviceService.getUserDeviceList(user.getId(), agentId);
|
||||
return new Result<List<UserShowDeviceListVO>>().ok(devices);
|
||||
List<DeviceEntity> devices = deviceService.getUserDevices(user.getId(), agentId);
|
||||
return new Result<List<DeviceEntity>>().ok(devices);
|
||||
}
|
||||
|
||||
@PostMapping("/bind/{agentId}")
|
||||
@@ -167,48 +159,4 @@ public class DeviceController {
|
||||
response.setMsg("Tools called successfully");
|
||||
return response.ok(result);
|
||||
}
|
||||
|
||||
@GetMapping("/address-book/{macAddress}")
|
||||
@Operation(summary = "获取设备通讯录")
|
||||
@RequiresPermissions("sys:role:normal")
|
||||
public Result<Object> getAddressBook(@PathVariable String macAddress) {
|
||||
return new Result<Object>().ok(deviceAddressBookService.getAddressBookList(macAddress));
|
||||
}
|
||||
|
||||
@GetMapping("/address-book/call")
|
||||
@Operation(summary = "根据昵称发起呼叫")
|
||||
public Result<Map<String, Object>> callByNickname(String callerMac, String nickname,
|
||||
@RequestParam(required = false, defaultValue = "false") boolean answer) {
|
||||
Map<String, Object> result = deviceAddressBookService.callByNickname(callerMac, nickname, answer);
|
||||
if (result == null) {
|
||||
return new Result<Map<String, Object>>().error("未找到对应设备");
|
||||
}
|
||||
return new Result<Map<String, Object>>().ok(result);
|
||||
}
|
||||
|
||||
@PutMapping("/address-book/alias")
|
||||
@Operation(summary = "更新设备通讯录别名")
|
||||
@RequiresPermissions("sys:role:normal")
|
||||
public Result<Void> updateAlias(@Valid @RequestBody DeviceAddressBookAliasDTO dto) {
|
||||
UserDetail user = SecurityUser.getUser();
|
||||
DeviceEntity callerDevice = deviceService.getDeviceByMacAddress(dto.getMacAddress());
|
||||
if (callerDevice == null || !callerDevice.getUserId().equals(user.getId())) {
|
||||
return new Result<Void>().error("无权限操作该设备");
|
||||
}
|
||||
deviceAddressBookService.saveOrUpdate(dto.getMacAddress(), dto.getTargetMac(), dto.getAlias(), null);
|
||||
return new Result<Void>();
|
||||
}
|
||||
|
||||
@PutMapping("/address-book/permission")
|
||||
@Operation(summary = "更新设备通讯录权限")
|
||||
@RequiresPermissions("sys:role:normal")
|
||||
public Result<Void> updatePermission(@Valid @RequestBody DeviceAddressBookPermissionDTO dto) {
|
||||
UserDetail user = SecurityUser.getUser();
|
||||
DeviceEntity callerDevice = deviceService.getDeviceByMacAddress(dto.getMacAddress());
|
||||
if (callerDevice == null || !callerDevice.getUserId().equals(user.getId())) {
|
||||
return new Result<Void>().error("无权限操作该设备");
|
||||
}
|
||||
deviceAddressBookService.saveOrUpdate(dto.getMacAddress(), dto.getTargetMac(), null, dto.getHasPermission());
|
||||
return new Result<Void>();
|
||||
}
|
||||
}
|
||||
@@ -1,39 +0,0 @@
|
||||
package xiaozhi.modules.device.dao;
|
||||
|
||||
import java.util.List;
|
||||
|
||||
import org.apache.ibatis.annotations.Mapper;
|
||||
import org.apache.ibatis.annotations.Param;
|
||||
|
||||
import com.baomidou.mybatisplus.core.mapper.BaseMapper;
|
||||
|
||||
import xiaozhi.modules.device.entity.DeviceAddressBookEntity;
|
||||
|
||||
@Mapper
|
||||
public interface DeviceAddressBookDao extends BaseMapper<DeviceAddressBookEntity> {
|
||||
|
||||
/**
|
||||
* 新增设备通讯录记录
|
||||
*/
|
||||
int insertAddressBook(DeviceAddressBookEntity entity);
|
||||
|
||||
/**
|
||||
* 获取设备通讯录列表
|
||||
*/
|
||||
List<DeviceAddressBookEntity> getAddressBookList(@Param("macAddress") String macAddress);
|
||||
|
||||
/**
|
||||
* 更新别名
|
||||
*/
|
||||
void updateAlias(@Param("macAddress") String macAddress, @Param("targetMac") String targetMac, @Param("alias") String alias);
|
||||
|
||||
/**
|
||||
* 更新权限
|
||||
*/
|
||||
void updatePermission(@Param("macAddress") String macAddress, @Param("targetMac") String targetMac, @Param("hasPermission") Boolean hasPermission);
|
||||
|
||||
/**
|
||||
* 批量删除设备相关的通讯录记录
|
||||
*/
|
||||
void deleteByMacAddresses(@Param("macAddresses") List<String> macAddresses);
|
||||
}
|
||||
-21
@@ -1,21 +0,0 @@
|
||||
package xiaozhi.modules.device.dto;
|
||||
|
||||
import io.swagger.v3.oas.annotations.media.Schema;
|
||||
import jakarta.validation.constraints.NotBlank;
|
||||
import lombok.Data;
|
||||
|
||||
@Data
|
||||
@Schema(description = "更新设备通讯录别名")
|
||||
public class DeviceAddressBookAliasDTO {
|
||||
|
||||
@NotBlank(message = "MAC地址不能为空")
|
||||
@Schema(description = "本设备MAC地址")
|
||||
private String macAddress;
|
||||
|
||||
@NotBlank(message = "目标MAC地址不能为空")
|
||||
@Schema(description = "对方设备MAC地址")
|
||||
private String targetMac;
|
||||
|
||||
@Schema(description = "我对对方的称呼")
|
||||
private String alias;
|
||||
}
|
||||
-21
@@ -1,21 +0,0 @@
|
||||
package xiaozhi.modules.device.dto;
|
||||
|
||||
import io.swagger.v3.oas.annotations.media.Schema;
|
||||
import jakarta.validation.constraints.NotBlank;
|
||||
import lombok.Data;
|
||||
|
||||
@Data
|
||||
@Schema(description = "更新设备通讯录权限")
|
||||
public class DeviceAddressBookPermissionDTO {
|
||||
|
||||
@NotBlank(message = "MAC地址不能为空")
|
||||
@Schema(description = "本设备MAC地址")
|
||||
private String macAddress;
|
||||
|
||||
@NotBlank(message = "目标MAC地址不能为空")
|
||||
@Schema(description = "对方设备MAC地址")
|
||||
private String targetMac;
|
||||
|
||||
@Schema(description = "是否有权限呼叫")
|
||||
private Boolean hasPermission;
|
||||
}
|
||||
@@ -0,0 +1,27 @@
|
||||
package xiaozhi.modules.device.dto;
|
||||
|
||||
import io.swagger.v3.oas.annotations.media.Schema;
|
||||
import lombok.AllArgsConstructor;
|
||||
import lombok.Data;
|
||||
|
||||
/**
|
||||
* 设备绑定的DTO
|
||||
*
|
||||
* @author zjy
|
||||
* @since 2025-3-28
|
||||
*/
|
||||
@Data
|
||||
@AllArgsConstructor
|
||||
@Schema(description = "设备连接头信息")
|
||||
public class DeviceBindDTO {
|
||||
|
||||
@Schema(description = "mac地址")
|
||||
private String macAddress;
|
||||
|
||||
@Schema(description = "所属用户id")
|
||||
private Long userId;
|
||||
|
||||
@Schema(description = "智能体id")
|
||||
private String agentId;
|
||||
|
||||
}
|
||||
Some files were not shown because too many files have changed in this diff Show More
Reference in New Issue
Block a user