OpenLIT Observability - Monitor LLMs & GenAI Apps

SigNoz has published a guide for integrating its observability platform with OpenLIT to monitor LLM and generative AI applications. The integration uses OpenTelemetry to export traces and metrics from AI workloads to SigNoz Cloud, with setup requiring Python 3.10+, the openlit and openai packages, and environment variables for the OTLP endpoint and ingestion key. Users can then view detailed traces and metrics in SigNoz, with troubleshooting steps and an optional OpenTelemetry Collector setup provided.

Overview This guide walks you through integrating SigNoz with OpenLIT to gain visibility into your LLM and AI applications. By combining OpenLIT's specialized LLM instrumentation with SigNoz's observability platform, you can monitor and analyze traces and metrics from your AI workloads. Prerequisites - A SigNoz Cloud account https://signoz.io/teams/ with an active ingestion key or Self Hosted SigNoz instance https://signoz.io/docs/install/self-host/ - Internet access to send telemetry data to SigNoz Cloud - Python 3.10+ with openlit installed - For Python: pip installed for managing Python packages - For this example: An OpenAI API key. You can get it from OpenAI platform https://platform.openai.com/settings/organization/api-keys Integrate SigNoz with OpenLIT For more information on getting started with OpenLIT in your Python environment, refer to the OpenLIT Overview https://docs.openlit.io/latest/overview . For more information on integrating SigNoz with OpenLIT, refer to the OpenLIT SigNoz Guide https://docs.openlit.io/latest/operator/destinations/signoz . Step 1: Install the necessary packages in your Python environment. pip install \ openlit \ openai Step 2: Create an example LLM application using OpenAI in this example python import openlit import os from openai import OpenAI openlit.init application name="<service name " client = OpenAI chat completion = client.chat.completions.create messages= { "role": "user", "content": "What is SigNoz?", } , model="gpt-3.5-turbo", print chat completion.choices 0 .message.content <service name is the name of your service Step 3: Run your application with env variables Run your application with the following environment variables set. This configures OpenTelemetry to export traces to SigNoz. OTEL EXPORTER OTLP ENDPOINT="https://ingest.<region .signoz.cloud:443" \ OTEL EXPORTER OTLP HEADERS="signoz-ingestion-key=<your-ingestion-key " \ <your run command <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. In this case we would use: python main.py View Traces and Metrics in SigNoz Your AI usage should now automatically emit traces. 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 see OpenLIT 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 Troubleshooting 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 Setup OpenTelemetry Collector Optional Setup OpenTelemetry Collector Optional setup-opentelemetry-collector-optional What is the OpenTelemetry Collector? Think of the OTel Collector as a middleman between your app and SigNoz. Instead of your application sending data directly to SigNoz, it sends everything to the Collector first, which then forwards it along. Why use it? Cleaning up data — Filter out noisy traces you don't care about, or remove sensitive info before it leaves your servers. Keeping your app lightweight — Let the Collector handle batching, retries, and compression instead of your application code. Adding context automatically — The Collector can tag your data with useful info like which Kubernetes pod or cloud region it came from. Future flexibility — Want to send data to multiple backends later? The Collector makes that easy without changing your app. See Switch from direct export to Collector https://signoz.io/docs/opentelemetry-collection-agents/opentelemetry-collector/switch-to-collector/ for step-by-step instructions to convert your setup. For more details, see Why use the OpenTelemetry Collector? https://signoz.io/docs/opentelemetry-collection-agents/opentelemetry-collector/why-to-use-collector/ and the Collector configuration guide https://signoz.io/docs/opentelemetry-collection-agents/opentelemetry-collector/configuration/ . Related integrations Use the same OpenTelemetry pipeline for the frameworks and providers you instrument: Instrument LLM apps with Langtrace https://signoz.io/docs/langtrace/ - an OpenTelemetry-native SDK that exports LLM spans straight to SigNoz Instrument LLM apps with Traceloop OpenLLMetry https://signoz.io/docs/traceloop/ - an OpenTelemetry SDK that auto-instruments 20+ LLM providers Monitor Mistral AI with OpenTelemetry https://signoz.io/docs/mistral-observability/ - track Mistral model latency, token usage, and error rates Monitor Hermes with OpenTelemetry https://signoz.io/docs/hermes-monitoring/ - trace long-running agent sessions, skill execution, and subagent runs Semantic Kernel observability with OpenTelemetry https://signoz.io/docs/semantic-kernel-observability/ - trace plugins, planners, and kernel function calls Browse all LLM observability integrations https://signoz.io/docs/llm-observability/ to instrument the rest of your stack.