Vendor-neutral standard for logs, metrics and traces. Application Insights in Azure Monitor and Foundry tracing both build on it, GenAI semantic conventions included.
Also called OTel.
Read more: Microsoft Learn
In the Ultra Transcenders books
Each book explains OpenTelemetry in context, with comparison tables and the common traps.
Terms in this definition
- Standard deployment type
A Foundry deployment type billed per token that keeps processing of prompts and responses inside the Azure geography of the resource, meeting data residency needs at lower volumes.
- Application Insights
APM service within Azure Monitor providing application telemetry, availability tests, usage analytics and Application Map. Data from workspace-based instances lives in Log Analytics.
- Azure Monitor
Observability platform for Azure that brings together metrics, logs and traces from both Azure and hybrid resources so they can be analysed and alerted on.
Related terms
- azure-core-tracing-opentelemetry
Python package connecting Azure SDK calls to OpenTelemetry; for tracing agents on the client side it is installed together with
opentelemetry-sdkandazure-ai-projects. - Azure Monitor OpenTelemetry Distro
Recommended way to instrument applications for Application Insights today: Microsoft's packaged OpenTelemetry, sending logs, metrics and traces there. Python apps switch it on by calling configure_azure_monitor().
- AzureAIOpenTelemetryTracer
Callback tracer for LangChain and LangGraph that sends OpenTelemetry spans to Foundry and Azure Monitor, but only if supplied as
config={'callbacks':[tracer]}; theenable_content_recordingsetting decides whether message content is captured. - Cloud role name
Labels a service as a node on Application Insights' Application Map. Under OpenTelemetry its value comes from service.name and service.namespace, which can be set with OTEL_SERVICE_NAME, for instance.
- OTEL_SERVICE_NAME
Environment variable in OpenTelemetry that fills the
service.nameresource attribute, which becomes the cloud role name and distinguishes services sending to the same Application Insights resource. - Tracing (Foundry)
Request-level observability in Foundry that must be switched on first. Each request becomes an OpenTelemetry trace in the connected Application Insights resource, showing latency, token usage, tool calls, inputs and outputs.