    
|
50ecee99cc
|
ASR句首丢字问题 (#346)
* fix: ASR句首丢字问题 (#338)
* feat: 支持dify的多轮对话, chat工作流支持持久化conversation_id #296 (#313)
* TTS功能的一些修改 (#307)
* fix: tts音频转码兼容
* feat: 支持自定义tts接口服务
* feat: tts超时时间作为可配置项
* feat: 自定义tts音频格式兼容
* style: 使命名更符合语义
---------
Co-authored-by: Jad <i@nocilol.me>
Co-authored-by: yanyige <yige.yan@qq.com>
Co-authored-by: Jad <journey.adc@gmail.com>
|
2025-03-15 00:19:45 +08:00 |
|
  
|
2b662d3a14
|
fix:function call bug (#268)
* 优化function call消息处理
* fix:用户说话重复记录bug
* 2025-3-10-优化llm intent (#254)
Co-authored-by: 欣南科技 <huangrongzhuang@xin-nan.com>
* update:回复上版提示词，无需再二次识别歌曲名
---------
Co-authored-by: 玄凤科技 <eric230308@gmail.com>
Co-authored-by: hrz <1710360675@qq.com>
Co-authored-by: Jiao Haoyang <108573524+XuSenfeng@users.noreply.github.com>
|
2025-03-11 00:25:33 +08:00 |
|
|
|
4f3fae81c1
|
fix:修复长时间不说话关闭意图bug (#267)
Co-authored-by: hrz <1710360675@qq.com>
|
2025-03-10 22:45:03 +08:00 |
|
|
|
63f34e5a82
|
本地记忆+意图识别 (#250)
* 增加本地记忆功能，使用llm总结记忆
* update：增加统一非流式输出输出
* 增加意图识别内容，使用llm进行识别
* 初始化记忆模块
* 完善意图识别处理后的流程
* 通过使用function call实现意图识别
* update:优化意图识别的配置
* update:function call最优设置成doubao-pro-32k-functioncall-241028
---------
Co-authored-by: 玄凤科技 <eric230308@gmail.com>
Co-authored-by: hrz <1710360675@qq.com>
|
2025-03-09 21:33:45 +08:00 |
|
  
|
0e43748fdc
|
重新划分目录 (#214)
* 🦄 refactor(web): 修改zhikongtaiweb到web
* 🦄 refactor: 重写前端
路由守护尚未写完
* 🦄 refactor: 标准化路由
* update:前端重写，保留后端
* update:添加前端代码
* update:pip转成poetry启动
* update:增加mem0ai包依赖
* update:文档增加mem0ai的描述
* feat: play online mp3 (#181)
Co-authored-by: 欣南科技 <huangrongzhuang@xin-nan.com>
* 修改前端代码
* update:调整项目目录
* update:优化
* update:配置文件去除8002端口
* update:增加开发说明
* update:更新开发协议
---------
Co-authored-by: kalicyh <34980061+kaliCYH@users.noreply.github.com>
Co-authored-by: hrz <1710360675@qq.com>
Co-authored-by: freshlife001 <talent@mises.site>
Co-authored-by: CGD <3030332422@qq.com>
|
2025-03-05 23:13:24 +08:00 |
|