nemo-relay-export-otel

por nvidia

Configure and use NeMo Relay OpenTelemetry export for OTLP-compatible tracing backends

npx skills add https://github.com/nvidia/nemo-relay --skill nemo-relay-export-otel

Export OpenTelemetry Traces

Use this skill when the destination is an OTLP/OpenTelemetry backend such as an OpenTelemetry Collector, Jaeger, Tempo, or Honeycomb.

Default Path

  • Build the binding-specific OpenTelemetryConfig
  • Set endpoint, service name, and any required headers
  • Construct the subscriber
  • Register it before running scoped work
  • Deregister, flush, and shut down when the process or subsystem is done

Embedded OpenTelemetry Semantics

  • OpenTelemetry export maps NeMo Relay runtime events into OTLP traces for tracing backends and collectors.
  • Configure transport, endpoint, service_name, optional namespace and version, instrumentation scope, headers, resource attributes, and timeout.
  • Start with http_binary transport and an OTLP traces endpoint such as a local collector on port 4318 unless deployment requirements differ.
  • grpc transport is available when a Tokio runtime is active.
  • Use explicit config objects in application code; environment variables may be honored by the underlying exporter but should not be the only source of application behavior.
  • Register before the first instrumented request, use stable service identity, keep auth and endpoints out of source code, flush during graceful shutdown, and redact sensitive payloads before production export.
  • Validate export by checking subscriber construction, collector requests, backend spans for scopes/tools/LLMs, and span grouping by root scope.

Things To Confirm

  • Transport: http_binary vs grpc
  • Endpoint and auth headers
  • Service naming and resource attributes
  • Whether deterministic flush-before-exit is required
  • Whether the chosen binding and target support the desired transport

Troubleshooting Focus

  • No spans visible
  • Wrong endpoint or auth headers
  • Events emitted outside active scopes
  • grpc selected without a Tokio runtime
  • Forgetting register/deregister or flush/shutdown steps

Related Skills

  • nemo-relay-setup-observability
  • nemo-relay-export-openinference
  • nemo-relay-debug-runtime-integration

Más skills de nvidia

compileiq-debug
nvidia
Úsalo cuando algo esté mal: Search() se cuelga, todas las evaluaciones devuelven INVALID_SCORE, las puntuaciones no mejoran, cada configuración devuelve el mismo número, errores de ptxas…
official
create-github-pr
nvidia
Crear solicitudes de extracción de GitHub usando la CLI gh. Usar cuando el usuario quiera crear un nuevo PR, enviar código para revisión o abrir una solicitud de extracción. Palabras clave de activación -…
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
Revisa los registros de experimentos del pipeline EAGLE3 desde el directorio experiments/ del lanzador. Resume el estado de aprobación/fallo para las 4 tareas, diagnostica fallos con la causa raíz…
official
nemoclaw-maintainer-cross-issue-sweep
nvidia
Scans other open issues to find ones a given PR may also fix or accidentally break. Outputs adjacent-fix opportunities and contradiction risks with file:line…
official
karpathy-guidelines
nvidia
Pautas de comportamiento para reducir errores comunes de codificación en LLM. Úselas al escribir, revisar o refactorizar código para evitar la sobrecomplicación, realizar cambios quirúrgicos,…
official
fhir-basics
nvidia
Enseña a los agentes cómo funcionan las APIs de FHIR R4, qué recursos están disponibles, cómo consultarlos con parámetros de búsqueda y cómo analizar correctamente todos los formatos de respuesta…
official
underdeclared-agent
nvidia
A helpful assistant agent
official