This repo provides various guides to show how easy it is to setup and monitor the key tiers and components of the NVIDIA enterprise stack, LLMs, and Generative AI applications with Dynatrace.
These guides are structured according the visual shown below.
Dynatrace AI Observability brings End-to-End visibility to user interactions, prompt flows, and AI/LLM model performance of your Generative AI, agentic, and LLM services.
- AI-observability setup guide
The NVIDIA NeMo Agent toolkit is a flexible, lightweight, and unifying library that allows you to easily connect existing enterprise agents to data sources and tools across any framework. The NeMo Agent toolkit uses a flexible, plugin-based observability system that provides comprehensive support for configuring logging, tracing, and metrics for workflows.
Expanded observability coverage of exposed Prometheus metrics and OpenTelemetry telemetry from the various NVIDIA generative AI and lifecycle management tools and technologies.
- NVIDIA NIM setup guide
Real-time auto-discovery and analysis of applications, NVIDIA platform components, and infrastructure.
- Kubernetes setup guide
Understand workload behavior or monitor GPUs in clusters
- DCGM-Exporter setup guide