Viewing Telemetry data

View metrics, logs, and traces for your Generative AI applications in Instana.

Viewing metrics

To view metrics for your Generative AI applications:

  1. On the Instana UI, select Infrastructure.

  2. Click Analyze Infrastructure.

  3. From the list of entity types, select GenAI app.

  4. Click the entity instance to view the associated dashboard with metrics.

Viewing logs

To view logs for your Generative AI applications:

  1. On the Instana UI, click Analytics.

  2. From the drop-down list, select Logs.

  3. Click Add filter and filter for your application name. For example, 'Logs -> Custom Tags -> otelServiceName' equals hello_genai (the app_name parameter in Traceloop.init() becomes the service name in Instana, which is why we search for otelServiceName).

Troubleshooting logs

If you do not see any OpenTelemetry logs, make sure that the following settings are configured:

  • The feature flag feature.logging.enabled is set to true.

  • The feature flag feature.logging.opentelemetry.integration.enabled is set to * or some specific tenant-unit combination, such as <tenant1>-<unit1>,<tenant2>-<unit2>.

  • Restart the otlp-acceptor component for the feature flag to take effect.

Viewing traces

To view traces for your Generative AI applications:

  1. On the Instana UI, click Analytics.

  2. Click Add filter and filter for your service name. For example, 'Trace -> Service Name' equals hello_genai (the app_name parameter in Traceloop.init() becomes the service name).

  3. You can view trace information showing LLM API calls, including details like model used, tokens consumed, and latency.

On the Analytics dashboard, you can use application, service, and endpoint to analyze calls. Instana presents the data by using service, endpoint, and call names. You can filter and group traces or calls by using arbitrary tags. In addition, you can view log information with the trace information. For more information, see Analyzing traces and calls.

Figure 1. Traces view
Traces view

Creating application perspectives

To create an application perspective for viewing trace information from your Generative AI applications:

  1. On the Instana UI, open the New Application Perspective wizard in one of the following ways:

    • In Applications, click Add application.

    • Click Applications > Add, and then select New Application Perspective.

  2. Select Services or Endpoints and click Next.

  3. Click Add filter and select a service name. You can select multiple services and endpoints by using OR conditions. The service name is specified by the app_name parameter in Traceloop.init(). For example, hello_genai.

  4. In the Application Perspective Name field, enter a name for your application perspective. Then, click Create.

The new application perspective is created. You can use this application perspective to view and analyze the performance of your Generative AI application.