Use this file to discover all available pages before exploring further.
Semantic Kernel is Microsoft’s open-source SDK for blending LLMs with traditional code — kernel functions, planners, and prompt templates. Semantic Kernel emits OpenTelemetry spans natively when OpenLIT is initialized; the openinference-instrumentation-openlit span processor reshapes them into the OpenInference format Arize AX expects.
This guide covers the Python implementation of Semantic Kernel. The same OpenTelemetry principles apply to Semantic Kernel for C# and Java.
Arize AX tracing initialized for Semantic Kernel.The ocean is salty because rivers continuously dissolve mineral salts from rocks and soil and carry them to the sea, where they accumulate over millions of years. Water leaves the ocean through evaporation but the salts remain, steadily concentrating until reaching today's roughly 3.5% salinity.
Open your Arize AX space and select project semantic-kernel-tracing-example.
You should see a new trace within ~30 seconds containing a chat gpt-5 span (the span name reflects whichever model you called) emitted by OpenLIT and reshaped by the OpenInference processor, with the prompt, response, and token usage attached.
No traces in Arize. Confirm ARIZE_SPACE_ID and ARIZE_API_KEY are set in the same shell that runs example.py. Enable OpenTelemetry debug logs with export OTEL_LOG_LEVEL=debug and re-run.
Code ran but no spans appear. OpenLIT must be initialized after the global tracer provider is set. Confirm otel_trace.set_tracer_provider(tracer_provider) and openlit.init() both run before any Semantic Kernel call.
401 from OpenAI. Verify OPENAI_API_KEY is set and has access to gpt-5. Swap for a model your key can call.
Other LLM providers. Semantic Kernel supports many AI services — Azure OpenAI, Anthropic, Google, and others via the matching connectors.ai.<provider> modules. The same OpenLIT + OpenInference setup covers them.