Semantic Kernel Observability - Monitor AI Orchestration

Semantic Kernel now supports observability via OpenTelemetry, enabling monitoring of AI orchestration with logs, traces, and metrics exported to SigNoz. The integration provides real-time visibility into latency, error rates, and usage trends for AI workflows. Developers can set up automatic instrumentation with environment variables to capture sensitive or non-sensitive telemetry data.

Overview This guide walks you through setting up observability and monitoring for Semantic Kernel using OpenTelemetry https://opentelemetry.io/ and exporting logs, traces, and metrics to SigNoz. With this integration, you can observe various models performance, capture request/response details, and track system-level metrics in SigNoz, giving you real-time visibility into latency, error rates, and usage trends for your Semantic Kernel applications. Instrumenting Semantic Kernel in your AI applications with telemetry ensures full observability across your AI workflows, making it easier to debug issues, optimize performance, and understand user interactions. By leveraging SigNoz, you can analyze correlated traces, logs, and metrics in unified dashboards, configure alerts, and gain actionable insights to continuously improve reliability, responsiveness, and user experience. Prerequisites - A SigNoz Cloud account https://signoz.io/teams/ with an active ingestion key - Internet access to send telemetry data to SigNoz Cloud - Python 3.10+ with Semantic Kernel installed - For Python: pip installed for managing Python packages and optional but recommended a Python virtual environment to isolate dependencies Monitoring Semantic Kernel For more detailed info on tracing your Semantic Kernel applications click here https://learn.microsoft.com/en-us/semantic-kernel/concepts/enterprise-readiness/observability/telemetry-with-console?tabs=Bash-CreatFile%2CBash-EnvironmentVariable&pivots=programming-language-python . For more detailed info on Semantic Kernel telemetry data click here https://learn.microsoft.com/en-us/semantic-kernel/concepts/enterprise-readiness/observability/?pivots=programming-language-python . No-code auto-instrumentation is recommended for quick setup with minimal code changes. It's ideal when you want to get observability up and running without modifying your application code and are leveraging standard instrumentor libraries. Step 1: Install the necessary packages in your Python environment. pip install \ opentelemetry-distro \ opentelemetry-exporter-otlp \ httpx \ opentelemetry-instrumentation-httpx \ opentelemetry-instrumentation-system-metrics \ semantic-kernel Step 2: Add Automatic Instrumentation opentelemetry-bootstrap --action=install Step 3: Instrument your Semantic Kernel application By default, the kernel doesn't emit spans for the AI connectors, because these spans carry gen ai attributes that are considered experimental. To enable the feature, you can set one of the following environment variables: SEMANTICKERNEL EXPERIMENTAL GENAI ENABLE OTEL DIAGNOSTICS=true - Emits non-sensitive data model name, operation name, token usage SEMANTICKERNEL EXPERIMENTAL GENAI ENABLE OTEL DIAGNOSTICS SENSITIVE=true - Emits all telemetry including sensitive data prompts and completions In this guide, we use the sensitive variant for comprehensive observability: export SEMANTICKERNEL EXPERIMENTAL GENAI ENABLE OTEL DIAGNOSTICS SENSITIVE=true Step 4: Run an example python from semantic kernel import Kernel from semantic kernel.connectors.ai.open ai import OpenAIChatCompletion from semantic kernel.prompt template import InputVariable, PromptTemplateConfig import asyncio import logging import os async def main : kernel = Kernel kernel.add service OpenAIChatCompletion ai model id="gpt-4.1", api key=os.getenv "OPENAI API KEY" prompt = """{{$input}} Answer the question above. """ prompt template config = PromptTemplateConfig template=prompt, name="summarize", template format="semantic-kernel", input variables= InputVariable name="input", description="The user input", is required=True , summarize = kernel.add function function name="summarizeFunc", plugin name="summarizePlugin", prompt template config=prompt template config, input text = "What is SigNoz?" summary = await kernel.invoke summarize, input=input text print summary if name == " main ": asyncio.run main 📌 Note: Before running this code, ensure that you have set the environment variable OPENAI API KEY with your generated API key. Step 5: Run your application with auto-instrumentation OTEL RESOURCE ATTRIBUTES="service.name=<service name " \ OTEL EXPORTER OTLP ENDPOINT="https://ingest.<region .signoz.cloud:443" \ OTEL EXPORTER OTLP HEADERS="signoz-ingestion-key=<your-ingestion-key " \ OTEL EXPORTER OTLP PROTOCOL=grpc \ OTEL TRACES EXPORTER=otlp \ OTEL METRICS EXPORTER=otlp \ OTEL LOGS EXPORTER=otlp \ OTEL PYTHON LOG CORRELATION=true \ OTEL PYTHON LOGGING AUTO INSTRUMENTATION ENABLED=true \ OTEL PYTHON DISABLED INSTRUMENTATIONS=openai \ opentelemetry-instrument <your run command 📌 Note: We're using OTEL PYTHON DISABLED INSTRUMENTATIONS=openai in the run command to disable the OpenAI instrumentor for tracing. This avoids duplicate OpenAI spans with Semantic Kernel's native telemetry/instrumentation, ensuring that telemetry is captured exclusively through Semantic Kernel's built-in instrumentation. is the name of your service <service name <region : Your SigNoz Cloud region https://signoz.io/docs/ingestion/signoz-cloud/overview/ endpoint <your-ingestion-key : Your SigNoz ingestion key https://signoz.io/docs/ingestion/signoz-cloud/keys/ - Replace <your run command with the actual command you would use to run your application. For example: python main.py Using self-hosted SigNoz? Most steps are identical. To adapt this guide, update the endpoint and remove the ingestion key header as shown in Cloud → Self-Hosted /docs/ingestion/cloud-vs-self-hosted/ cloud-to-self-hosted . Code-based instrumentation gives you fine-grained control over your telemetry configuration. Use this approach when you need to customize resource attributes, sampling strategies, or integrate with existing observability infrastructure. Step 1: Install the necessary packages in your Python environment. pip install \ opentelemetry-api \ opentelemetry-sdk \ opentelemetry-exporter-otlp \ opentelemetry-instrumentation-httpx \ opentelemetry-instrumentation-system-metrics \ semantic-kernel Step 2: Import the necessary modules in your Python application Traces: python from opentelemetry import trace from opentelemetry.sdk.resources import Resource from opentelemetry.sdk.trace import TracerProvider from opentelemetry.sdk.trace.export import BatchSpanProcessor from opentelemetry.exporter.otlp.proto.http.trace exporter import OTLPSpanExporter Logs: python from opentelemetry.sdk. logs import LoggerProvider, LoggingHandler from opentelemetry.sdk. logs.export import BatchLogRecordProcessor from opentelemetry.exporter.otlp.proto.http. log exporter import OTLPLogExporter from opentelemetry. logs import set logger provider import logging Metrics: python from opentelemetry.sdk.metrics import MeterProvider from opentelemetry.exporter.otlp.proto.http.metric exporter import OTLPMetricExporter from opentelemetry.sdk.metrics.export import PeriodicExportingMetricReader from opentelemetry import metrics from opentelemetry.instrumentation.system metrics import SystemMetricsInstrumentor from opentelemetry.instrumentation.httpx import HTTPXClientInstrumentor Step 3: Set up the OpenTelemetry Tracer Provider to send traces directly to SigNoz Cloud python from opentelemetry.sdk.resources import Resource from opentelemetry.sdk.trace import TracerProvider from opentelemetry.sdk.trace.export import BatchSpanProcessor from opentelemetry.exporter.otlp.proto.http.trace exporter import OTLPSpanExporter from opentelemetry import trace import os resource = Resource.create {"service.name": "<service name "} provider = TracerProvider resource=resource span exporter = OTLPSpanExporter endpoint= os.getenv "OTEL EXPORTER TRACES ENDPOINT" , headers={"signoz-ingestion-key": os.getenv "SIGNOZ INGESTION KEY" }, processor = BatchSpanProcessor span exporter provider.add span processor processor trace.set tracer provider provider is the name of your service <service name → SigNoz Cloud trace endpoint with appropriate OTEL EXPORTER TRACES ENDPOINT region https://signoz.io/docs/ingestion/signoz-cloud/overview/ endpoint : https://ingest.<region .signoz.cloud:443/v1/traces → Your SigNoz SIGNOZ INGESTION KEY ingestion key https://signoz.io/docs/ingestion/signoz-cloud/keys/ Using self-hosted SigNoz? Most steps are identical. To adapt this guide, update the endpoint and remove the ingestion key header as shown in Cloud → Self-Hosted /docs/ingestion/cloud-vs-self-hosted/ cloud-to-self-hosted . Step 4 : Setup Logs python import logging from opentelemetry.sdk.resources import Resource from opentelemetry. logs import set logger provider from opentelemetry.sdk. logs import LoggerProvider, LoggingHandler from opentelemetry.sdk. logs.export import BatchLogRecordProcessor from opentelemetry.exporter.otlp.proto.http. log exporter import OTLPLogExporter import os resource = Resource.create {"service.name": "<service name "} logger provider = LoggerProvider resource=resource set logger provider logger provider otlp log exporter = OTLPLogExporter endpoint= os.getenv "OTEL EXPORTER LOGS ENDPOINT" , headers={"signoz-ingestion-key": os.getenv "SIGNOZ INGESTION KEY" }, logger provider.add log record processor BatchLogRecordProcessor otlp log exporter Attach OTel logging handler to root logger handler = LoggingHandler level=logging.INFO, logger provider=logger provider logging.basicConfig level=logging.INFO, handlers= handler logger = logging.getLogger name is the name of your service <service name → SigNoz Cloud endpoint with appropriate OTEL EXPORTER LOGS ENDPOINT region https://signoz.io/docs/ingestion/signoz-cloud/overview/ endpoint : https://ingest.<region .signoz.cloud:443/v1/logs → Your SigNoz SIGNOZ INGESTION KEY ingestion key https://signoz.io/docs/ingestion/signoz-cloud/keys/ Using self-hosted SigNoz? Most steps are identical. To adapt this guide, update the endpoint and remove the ingestion key header as shown in Cloud → Self-Hosted /docs/ingestion/cloud-vs-self-hosted/ cloud-to-self-hosted . Step 5 : Setup Metrics python from opentelemetry.sdk.resources import Resource from opentelemetry.sdk.metrics import MeterProvider from opentelemetry.exporter.otlp.proto.http.metric exporter import OTLPMetricExporter from opentelemetry.sdk.metrics.export import PeriodicExportingMetricReader from opentelemetry import metrics from opentelemetry.instrumentation.system metrics import SystemMetricsInstrumentor from opentelemetry.instrumentation.httpx import HTTPXClientInstrumentor import os resource = Resource.create {"service.name": "<service-name "} metric exporter = OTLPMetricExporter endpoint= os.getenv "OTEL EXPORTER METRICS ENDPOINT" , headers={"signoz-ingestion-key": os.getenv "SIGNOZ INGESTION KEY" }, reader = PeriodicExportingMetricReader metric exporter metric provider = MeterProvider metric readers= reader , resource=resource metrics.set meter provider metric provider meter = metrics.get meter name turn on out-of-the-box metrics SystemMetricsInstrumentor .instrument HTTPXClientInstrumentor .instrument is the name of your service <service name → SigNoz Cloud endpoint with appropriate OTEL EXPORTER METRICS ENDPOINT region https://signoz.io/docs/ingestion/signoz-cloud/overview/ endpoint : https://ingest.<region .signoz.cloud:443/v1/metrics → Your SigNoz SIGNOZ INGESTION KEY ingestion key https://signoz.io/docs/ingestion/signoz-cloud/keys/ Using self-hosted SigNoz? Most steps are identical. To adapt this guide, update the endpoint and remove the ingestion key header as shown in Cloud → Self-Hosted /docs/ingestion/cloud-vs-self-hosted/ cloud-to-self-hosted . 📌 Note: SystemMetricsInstrumentor provides system metrics CPU, memory, etc. , and HTTPXClientInstrumentor provides outbound HTTP request metrics such as request duration. If you want to add custom metrics to your Semantic Kernel application, see Python Custom Metrics . Step 6: Instrument your Semantic Kernel application By default, the kernel doesn't emit spans for the AI connectors, because these spans carry gen ai attributes that are considered experimental. To enable the feature, you can set one of the following environment variables: SEMANTICKERNEL EXPERIMENTAL GENAI ENABLE OTEL DIAGNOSTICS=true - Emits non-sensitive data model name, operation name, token usage SEMANTICKERNEL EXPERIMENTAL GENAI ENABLE OTEL DIAGNOSTICS SENSITIVE=true - Emits all telemetry including sensitive data prompts and completions In this guide, we use the sensitive variant for comprehensive observability: export SEMANTICKERNEL EXPERIMENTAL GENAI ENABLE OTEL DIAGNOSTICS SENSITIVE=true Step 7: Run an example python from semantic kernel import Kernel from semantic kernel.connectors.ai.open ai import OpenAIChatCompletion from semantic kernel.prompt template import InputVariable, PromptTemplateConfig import asyncio import logging import os async def main : kernel = Kernel kernel.add service OpenAIChatCompletion ai model id="gpt-4.1", api key=os.getenv "OPENAI API KEY" prompt = """{{$input}} Answer the question above. """ prompt template config = PromptTemplateConfig template=prompt, name="summarize", template format="semantic-kernel", input variables= InputVariable name="input", description="The user input", is required=True , summarize = kernel.add function function name="summarizeFunc", plugin name="summarizePlugin", prompt template config=prompt template config, input text = "What is SigNoz?" summary = await kernel.invoke summarize, input=input text print summary if name == " main ": asyncio.run main 📌 Note: Before running this code, ensure that you have set the environment variable OPENAI API KEY with your generated API key. View Traces, Logs, and Metrics in SigNoz Your Semantic Kernel commands should now automatically emit traces, logs, and metrics. You should be able to view traces in Signoz Cloud under the traces tab: When you click on a trace in SigNoz, you'll see a detailed view of the trace, including all associated spans, along with their events and attributes. You should be able to view logs in Signoz Cloud under the logs tab. You can also view logs by clicking on the “Related Logs” button in the trace view to see correlated logs: When you click on any of these logs in SigNoz, you'll see a detailed view of the log, including attributes: You should be able to see Semantic Kernel related metrics in Signoz Cloud under the metrics tab: When you click on any of these metrics in SigNoz, you'll see a detailed view of the metric, including attributes: Troubleshooting If you don't see your telemetry data: Verify network connectivity - Ensure your application can reach SigNoz Cloud endpoints Check ingestion key - Verify your SigNoz ingestion key is correct Wait for data - OpenTelemetry batches data before sending, so wait 10-30 seconds after making API calls Try a console exporter — Enable a console exporter locally to confirm that your application is generating telemetry data before it’s sent to SigNoz Next Steps You can also check out our custom Semantic Kernel dashboard here https://signoz.io/docs/dashboards/dashboard-templates/semantic-kernel-dashboard/ which provides specialized visualizations for monitoring your Semantic-kernel usage in applications. The dashboard includes pre-built charts specifically tailored for LLM usage, along with import instructions to get started quickly. Additional resources: - Set up alerts https://signoz.io/docs/alerts/ for high latency or error rates - Learn more about querying traces https://signoz.io/docs/userguide/traces/ - Explore log correlation https://signoz.io/docs/userguide/logs query builder/