nemo-relay-setup-observability

작성자: nvidia

Choose and set up the right NeMo Relay observability path for an application

npx skills add https://github.com/nvidia/nemo-relay --skill nemo-relay-setup-observability

Set Up Observability

Use this skill when an application developer wants visibility into NeMo Relay activity but has not yet decided which output they need.

Choose The Output

  • Console or custom event handling Use subscribers.
  • Portable execution trajectories Use AtifExporter.
  • General OTLP tracing Use the OpenTelemetry subscriber.
  • OpenInference-aware backends Use the OpenInference subscriber.

Embedded Event And Subscriber Model

  • NeMo Relay emits one canonical event stream from scopes, marks, managed tool calls, managed LLM calls, middleware, and manual lifecycle APIs.
  • Subscribers consume events without defining the event model. Multiple subscribers can observe the same stream for logging, export, analytics, or diagnostics.
  • Global subscribers remain active process-wide until removed.
  • Scope-local subscribers are owned by one active scope and disappear when that scope closes.
  • Plugin-installed subscribers are reusable, configuration-driven runtime components.
  • Exporter-oriented subscribers translate the event stream into ATIF, OpenTelemetry, or OpenInference output.
  • Event payloads reflect sanitized post-guardrail input and output when calls use managed helpers or manual lifecycle params provide those fields.
  • Event fields include semantic input/output through the ATOF data field, typed profile data such as model_name and tool_call_id, and codec-provided annotated LLM request/response data for in-process subscribers and exporters.

Shared Lifecycle

  1. Create the exporter or subscriber.
  2. Register it with a unique name before the relevant scoped work.
  3. Run NeMo Relay-instrumented work inside scopes.
  4. Deregister it.
  5. Flush or shut down if the binding supports it and deterministic delivery is needed.

Binding Names

  • Python: nemo_relay.subscribers.register(...), AtifExporter, OpenTelemetrySubscriber, and OpenInferenceSubscriber
  • Node.js: root exports registerSubscriber(...), AtifExporter, OpenTelemetrySubscriber, and OpenInferenceSubscriber
  • Rust: nemo_relay::api::subscriber and nemo_relay::observability::*
  • Go: source-first wrappers expose equivalent register, exporter, and subscriber lifecycle methods

Use Another Skill When

  • You already know you need ATIF -> nemo-relay-export-atif-trajectories
  • You already know you need OTEL -> nemo-relay-export-otel
  • You already know you need OpenInference -> nemo-relay-export-openinference
  • You need to package subscriber-based export behavior as a reusable plugin -> nemo-relay-build-plugin
  • You are debugging missing telemetry -> nemo-relay-debug-runtime-integration

Related Skills

  • nemo-relay-export-atif-trajectories
  • nemo-relay-export-otel
  • nemo-relay-export-openinference
  • nemo-relay-build-plugin

nvidia의 다른 스킬

compileiq-debug
nvidia
Use when something is wrong: Search() hangs, all evaluations return INVALID_SCORE, scores aren't improving, every config returns the same number, ptxas errors…
official
create-github-pr
nvidia
gh CLI를 사용하여 GitHub 풀 리퀘스트를 생성합니다. 사용자가 새 PR을 만들거나, 코드 리뷰를 제출하거나, 풀 리퀘스트를 열고자 할 때 사용합니다. 트리거 키워드 -…
official
diagnose-perf
nvidia
First-responder performance triage for Isaac Sim and Isaac Lab. Identifies bottleneck category (GPU-bound, CPU-bound, VRAM, loading) using nvidia-smi and…
official
eagle3-review-logs
nvidia
Review EAGLE3 pipeline experiment logs from the launcher's experiments/ directory. Summarizes pass/fail status for all 4 tasks, diagnoses failures with root…
official
nemoclaw-maintainer-cross-issue-sweep
nvidia
다른 열린 이슈들을 스캔하여 주어진 PR이 함께 수정하거나 실수로 망가뜨릴 수 있는 이슈를 찾습니다. 인접 수정 기회와 모순 위험을 file:line…과 함께 출력합니다.
official
karpathy-guidelines
nvidia
일반적인 LLM 코딩 실수를 줄이기 위한 행동 지침입니다. 코드 작성, 검토 또는 리팩토링 시 과도한 복잡성을 피하고 정밀한 변경을 위해 사용하세요.
official
fhir-basics
nvidia
에이전트에게 FHIR R4 API의 작동 방식, 사용 가능한 리소스, 검색 매개변수를 사용한 쿼리 방법, 모든 응답 형식을 올바르게 파싱하는 방법을 가르칩니다…
official
underdeclared-agent
nvidia
A helpful assistant agent
official