Deployment and MLOps · MLD-0829
Observability
The ability to understand system behavior using signals such as logs, metrics, and traces.
Original reference page · detailed expansion pending. Original definitions, examples, notes and citations are preserved below. New examples are illustrative, not benchmark results.
Original example
Investigate a failed multi-step model workflow.
Original caveat
Logging everything is neither necessary nor automatically privacy-preserving.
Context and aliases
Level: Intermediate. Stages: Deployment · Monitoring.
Tags: ML · DL · LLM · SLM · MLOps.
Aliases: None recorded.
Related concepts
Concepts linking here
Technology connections
- Arize Phoenix — Open-source AI observability and evaluation tooling.
- Docker — Container packaging and runtime tooling.
- Evidently — Data and ML monitoring/evaluation library.
- Grafana — Dashboarding and observability application.
- Kubernetes — Container scheduling and orchestration platform.
- Langfuse — LLM application tracing, prompt and evaluation platform.
- LangSmith — Observability, evaluation and development platform for LLM applications.
- OpenTelemetry — Vendor-neutral APIs and conventions for telemetry.
- Prometheus — Metrics collection and alerting system.
- whylogs — Data profiling library using compact statistical summaries.
Original references
- Transformers glossary ↗ · Consulted
- Google Cloud MLOps architecture ↗ · Reference link
- scikit-learn User Guide ↗ · Consulted
- Original reference URL ↗