Azure OpenAI Monitoring & Observability with OpenTelemetry

Microsoft has released a new monitoring and observability integration for Azure OpenAI that uses OpenTelemetry to export logs, traces, and metrics to SigNoz, enabling developers to track model performance, latency, error rates, and usage trends in real time. The integration, which supports both Python and JavaScript environments, provides enterprise-grade visibility into AI workflows for organizations using Azure OpenAI's security, compliance, and private network features. Developers can implement the monitoring with no-code auto-instrumentation and unified dashboards to debug issues, optimize performance, and configure alerts across their LLM applications.

Overview This guide walks you through setting up monitoring and observability for Azure OpenAi API using OpenTelemetry https://opentelemetry.io/ and exporting logs, traces, and metrics to SigNoz. With this integration, you can observe model 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 Azure OpenAi applications. Many developers choose Azure OpenAI over regular OpenAI for enterprise-grade features including enhanced security and compliance certifications, private network integration with Azure Virtual Networks, regional data residency options, integration with Azure Active Directory for identity management, dedicated capacity with provisioned throughput, and seamless integration with other Azure services. These capabilities make Azure OpenAI particularly valuable for organizations with strict regulatory requirements or those already invested in the Azure ecosystem. Instrumenting Azure OpenAi in your LLM 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 - SigNoz setup choose one : SigNoz Cloud account https://signoz.io/teams/ with an active ingestion key- Self-hosted SigNoz instance - Internet access to send telemetry data to SigNoz Cloud - An Microsoft Azure https://azure.microsoft.com/en-us/pricing/purchase-options/azure-account/ account with an OpenAI resource deployed and working API Key - For Python: pip installed for managing Python packages and optional but recommended a Python virtual environment to isolate dependencies - For JavaScript: Node.js version 14 or higher and npm installed for managing Node.js packages Monitoring Azure OpenAI The Azure OpenAI API uses an API format compatible with OpenAI. By modifying the configuration, you can use the OpenAI SDK or softwares compatible with the OpenAI API to access the Azure OpenAI API. Hence, a similar method to monitor OpenAI APIs can be used for monitoring Azure OpenAI APIs as well. To read more about this, you can read the Azure OpenAI API Docs https://learn.microsoft.com/en-us/azure/ai-foundry/openai/how-to/responses?tabs=python-key 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 \ opentelemetry-instrumentation-httpx \ opentelemetry-instrumentation-system-metrics \ openai \ openinference-instrumentation-openai Step 2: Add Automatic Instrumentation opentelemetry-bootstrap --action=install Step 3: Configure logging level To ensure logs are properly captured and exported, configure the root logger to emit logs at the INFO level or higher: python import logging logging.getLogger .setLevel logging.INFO This sets the minimum log level for the root logger to INFO, which ensures that logger.info calls and higher severity logs WARNING, ERROR, CRITICAL are captured by the OpenTelemetry logging auto-instrumentation and sent to SigNoz. Step 4: Run an example python import openai import os client = OpenAI api key=os.getenv "AZURE OPENAI API KEY" , base url="https://YOUR-RESOURCE-NAME.openai.azure.com/openai/v1/" response = client.chat.completions.create model="<your-model-deployment-name ", messages= {"role": "system", "content": "You are a helpful assistant"}, {"role": "user", "content": "What is SigNoz?"}, , stream=False print response.choices 0 .message.content 📌 Note: Before running this code, ensure that you have set the environment variable AZURE OPENAI API KEY with your working 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 \ opentelemetry-instrument <your run command 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 https://signoz.io/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 \ openai \ openinference-instrumentation-openai Step 2: Import the necessary modules in your Python application Traces: python from openinference.instrumentation.openai import OpenAIInstrumentor 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 https://signoz.io/docs/ingestion/cloud-vs-self-hosted/ cloud-to-self-hosted . Step 4: Instrument Azure OpenAI using OpenAInstrumentor and the configured Tracer Provider python from openinference.instrumentation.openai import OpenAIInstrumentor OpenAIInstrumentor .instrument tracer provider=provider 📌 Important: Place this code at the start of your application logic — before any Azure OpenAI functions are called or used — to ensure telemetry is correctly captured. Step 5 : 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 https://signoz.io/docs/ingestion/cloud-vs-self-hosted/ cloud-to-self-hosted . Step 6 : 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 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/ 📌 Note: SystemMetricsInstrumentor provides system metrics CPU, memory, etc. , and HTTPXClientInstrumentor provides outbound HTTP request metrics such as request duration. These are not Azure OpenAI-specific metrics. Azure OpenAI does not expose metrics as part of their SDK. If you want to add custom metrics to your Azure OpenAI application, see Python Custom Metrics . 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 https://signoz.io/docs/ingestion/cloud-vs-self-hosted/ cloud-to-self-hosted . Step 7: Run an example python import openai import os client = OpenAI api key=os.getenv "AZURE OPENAI API KEY" , base url="https://YOUR-RESOURCE-NAME.openai.azure.com/openai/v1/" response = client.chat.completions.create model="<your-model-deployment-name ", messages= {"role": "system", "content": "You are a helpful assistant"}, {"role": "user", "content": "What is SigNoz?"}, , stream=False print response.choices 0 .message.content 📌 Note: Before running this code, ensure that you have set the environment variable AZURE OPENAI API KEY with your working API key. Step 1: Install the necessary packages in your Node.js project. npm install \ @opentelemetry/api \ @opentelemetry/sdk-node \ @opentelemetry/sdk-trace-node \ @opentelemetry/sdk-logs \ @opentelemetry/sdk-metrics \ @opentelemetry/exporter-otlp-http \ @opentelemetry/instrumentation \ @opentelemetry/instrumentation-http \ @opentelemetry/host-metrics \ @opentelemetry/resources \ @opentelemetry/semantic-conventions \ @arizeai/openinference-instrumentation-openai \ openai Step 2: Import the necessary modules in your JavaScript/Node.js application Traces: js const { NodeSDK } = require '@opentelemetry/sdk-node' const { Resource } = require '@opentelemetry/resources' const { ATTR SERVICE NAME } = require '@opentelemetry/semantic-conventions' const { NodeTracerProvider } = require '@opentelemetry/sdk-trace-node' const { BatchSpanProcessor } = require '@opentelemetry/sdk-trace-base' const { OTLPTraceExporter } = require '@opentelemetry/exporter-otlp-http' const { registerInstrumentations } = require '@opentelemetry/instrumentation' const { OpenAIInstrumentation } = require '@arizeai/openinference-instrumentation-openai' Logs: js const { LoggerProvider, BatchLogRecordProcessor } = require '@opentelemetry/sdk-logs' const { OTLPLogExporter } = require '@opentelemetry/exporter-otlp-http' const { logs } = require '@opentelemetry/api' Metrics: js const { MeterProvider, PeriodicExportingMetricReader } = require '@opentelemetry/sdk-metrics' const { OTLPMetricExporter } = require '@opentelemetry/exporter-otlp-http' const { HttpInstrumentation } = require '@opentelemetry/instrumentation-http' const { HostMetrics } = require '@opentelemetry/host-metrics' const { metrics } = require '@opentelemetry/api' Step 3: Set up the OpenTelemetry Tracer Provider to send traces directly to SigNoz Cloud js const { NodeTracerProvider } = require '@opentelemetry/sdk-trace-node' const { BatchSpanProcessor } = require '@opentelemetry/sdk-trace-base' const { OTLPTraceExporter } = require '@opentelemetry/exporter-otlp-http' const { Resource } = require '@opentelemetry/resources' const { ATTR SERVICE NAME } = require '@opentelemetry/semantic-conventions' const { trace } = require '@opentelemetry/api' const resource = Resource.default { attributes: { ATTR SERVICE NAME : '<service name ', }, } const provider = new NodeTracerProvider { resource: resource, } const traceExporter = new OTLPTraceExporter { url: process.env.OTEL EXPORTER TRACES ENDPOINT, headers: { 'signoz-ingestion-key': process.env.SIGNOZ INGESTION KEY, }, } const spanProcessor = new BatchSpanProcessor traceExporter provider.addSpanProcessor spanProcessor provider.register 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 https://signoz.io/docs/ingestion/cloud-vs-self-hosted/ cloud-to-self-hosted . Step 4: Instrument Azure OpenAI using OpenAIInstrumentation and the configured Tracer Provider js const { registerInstrumentations } = require '@opentelemetry/instrumentation' const { OpenAIInstrumentation } = require '@arizeai/openinference-instrumentation-openai' registerInstrumentations { instrumentations: new OpenAIInstrumentation { tracerProvider: provider, } , , } 📌 Important: Place this code at the start of your application logic — before any Azure OpenAI functions are called or used — to ensure telemetry is correctly captured. Step 5 : Setup Logs js const { LoggerProvider, BatchLogRecordProcessor } = require '@opentelemetry/sdk-logs' const { OTLPLogExporter } = require '@opentelemetry/exporter-otlp-http' const { Resource } = require '@opentelemetry/resources' const { ATTR SERVICE NAME } = require '@opentelemetry/semantic-conventions' const { logs } = require '@opentelemetry/api' const logResource = Resource.default { attributes: { ATTR SERVICE NAME : '<service name ', }, } const loggerProvider = new LoggerProvider { resource: logResource, } const logExporter = new OTLPLogExporter { url: process.env.OTEL EXPORTER LOGS ENDPOINT, headers: { 'signoz-ingestion-key': process.env.SIGNOZ INGESTION KEY, }, } loggerProvider.addLogRecordProcessor new BatchLogRecordProcessor logExporter logs.setGlobalLoggerProvider loggerProvider // Create a logger instance const logger = logs.getLogger 'azure-openai-app' 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 https://signoz.io/docs/ingestion/cloud-vs-self-hosted/ cloud-to-self-hosted . Step 6 : Setup Metrics js const { MeterProvider, PeriodicExportingMetricReader } = require '@opentelemetry/sdk-metrics' const { OTLPMetricExporter } = require '@opentelemetry/exporter-otlp-http' const { Resource } = require '@opentelemetry/resources' const { ATTR SERVICE NAME } = require '@opentelemetry/semantic-conventions' const { metrics } = require '@opentelemetry/api' const { HttpInstrumentation } = require '@opentelemetry/instrumentation-http' const { registerInstrumentations } = require '@opentelemetry/instrumentation' const metricResource = Resource.default { attributes: { ATTR SERVICE NAME : '<service name ', }, } const metricExporter = new OTLPMetricExporter { url: process.env.OTEL EXPORTER METRICS ENDPOINT, headers: { 'signoz-ingestion-key': process.env.SIGNOZ INGESTION KEY, }, } const metricReader = new PeriodicExportingMetricReader { exporter: metricExporter, exportIntervalMillis: 10000, } const meterProvider = new MeterProvider { resource: metricResource, readers: metricReader , } metrics.setGlobalMeterProvider meterProvider // Create a meter instance const meter = metrics.getMeter 'azure-openai-app' // Register HTTP instrumentation for outbound HTTP metrics registerInstrumentations { instrumentations: new HttpInstrumentation , } // Initialize host metrics for system-level monitoring const hostMetrics = new HostMetrics { meterProvider: meterProvider, } hostMetrics.start 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/ 📌 Note: HostMetrics provides system-level metrics CPU, memory, disk, network, etc. , and HttpInstrumentation provides outbound HTTP request metrics such as request duration. These are not Azure OpenAI-specific metrics. Azure OpenAI does not expose metrics as part of their SDK. If you want to add custom metrics to your Azure OpenAI application, see JavaScript Custom Metrics . 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 https://signoz.io/docs/ingestion/cloud-vs-self-hosted/ cloud-to-self-hosted . Step 7: Run an example js const OpenAI = require 'openai' const client = new OpenAI { apiKey: process.env.AZURE OPENAI API KEY, baseURL: 'https://YOUR-RESOURCE-NAME.openai.azure.com/openai/v1/', } async function main { const response = await client.chat.completions.create { model: '<your-model-deployment-name ', messages: { role: 'system', content: 'You are a helpful assistant' }, { role: 'user', content: 'What is SigNoz?' }, , stream: false, } console.log response.choices 0 .message.content } main 📌 Note: Before running this code, ensure that you have set the environment variable AZURE OPENAI API KEY with your working API key. View Traces, Logs, and Metrics in SigNoz Your Azure OpenAI 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 Azure OpenAI 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: Dashboard You can also check out our custom Azure OpenAI API dashboard here https://signoz.io/docs/dashboards/dashboard-templates/azure-openai-dashboard/ which provides specialized visualizations for monitoring your Azure OpenAI API usage in applications. The dashboard includes pre-built charts specifically tailored for LLM usage, along with import instructions to get started quickly.