Observability of the audio model #812

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

Open

inlines10 wants to merge 5 commits into alibaba:main from inlines10:future/Observability-of-audio-models

+669 −140

Contributor

inlines10 commented May 10, 2025 •

edited

Loading

为 DashScope 语音合成模型添加可观测性支持

描述

本次PR为DashScope语音合成模型添加了可观测性支持，通过实现Spring AI的观测框架，使模型运行状态可监控、可追踪。主要改进包括：

新增 SpeechSynthesisContext 用于追踪合成指标
实现 DashScopeAudioObservationConvention 自定义观测约定
在同步和异步合成方法中集成观测支持
新增以下指标监控：
- 输入文本长度
- 输出音频大小
- 模型名称
- 响应格式
- 采样率
- 错误追踪

改动内容

新增观测上下文类 SpeechSynthesisContext
新增观测约定类 DashScopeAudioObservationConvention
修改 DashScopeSpeechSynthesisModel 以支持观测
为 call() 和 stream() 方法添加观测支持

测试计划

添加观测上下文的单元测试
验证同步和异步场景下的指标收集
测试错误追踪和报告功能

inlines10 added 2 commits

May 10, 2025 15:53


          Observability of the audio model

01bcfab


          code format

96579c8

myeyestore commented May 10, 2025

Great implementation of this feature. I particularly like the approach to error handling.

yuluo-yx reviewed

View reviewed changes

Collaborator

yuluo-yx left a comment

ptal @PolarishT @Cirilla-zmh

inlines10 added 3 commits

May 10, 2025 18:40


          Merge branch 'future/Observability-of-audio-models'

c1d5922


          code format


          code format

856301f

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet