higress-group/higress

Observability 建议参考 litellm 的实现，通过openai 协议的 metadata 来支持

Open

#1,692 opened on Jan 18, 2025

View on GitHub
 (0 comments) (2 reactions) (1 assignee)Go (1,219 forks)github user discovery
area/aihelp wantedlevel/normal

Repository metrics

Stars
 (9,036 stars)
PR merge metrics
 (Avg merge 7d 9h) (18 merged PRs in 30d)

Description

Why do you need it?

商业化的使用场景中，对可观测能力的需求很重要，既希望不破坏原有的 API 协议，又希望拥有更多的扩展能力。

How could it be?

  • Observability 能力通过 metadata 来支持，各种第三方的集成，例如 langfuse/otel/postHG/langfire/sentry 等等都可以适配
  • 另外对于 /chat 而言，很多观测平台是对 [用户][会话][Prompt][Caching][Stream] 都做了深度支持，所以还是基于 OpenAI 的 标准API 是可以办到的，user/session/thread + metadata 来做好不同第三方平台的映射关系。
  • 除了统一观测以外，metadata 也能扩展出数据隔离，比如增加：team_id / project_id / agent_id 之类，配合 token 消耗情况，可以做到很好的三方集成

Links

OpenAI for metadata Litellm for metadata

Contributor guide

Research direction
Review litellm's metadata based observability and map to Higress's architecture.
Tech stack
go
Domain
backend
Issue type
Feature
DifficultyEstimated implementation difficulty for a new contributor, from 1 for very small changes to 5 for expert-level work.
3
Estimated timeA rough time range for an experienced contributor to investigate, implement, test, and prepare a pull request.
1-2 days
Activity statusHow available the issue appears right now: fresh, active, stale, blocked, or waiting on maintainer input.
Active
ClarityHow clearly the issue explains the expected change, acceptance criteria, and next step.
Clear
Prerequisites
GitGo
Newbie friendlinessA 1-100 score estimating how approachable this issue is for first-time contributors.
60