Type to search.

LLM observability with Elastic OpenTelemetry

Serverless Observability

Elastic Cloud Serverless projects are autoscaled environments, fully managed by Elastic and available on Elastic Cloud.

Availability

  • Generally available

    This functionality is generally available and ready for production usage.

Stack

The Elastic Stack includes Elastic's core products such as Elasticsearch, Kibana, Logstash, and Beats.

Availability

  • Generally available

    This functionality is generally available and ready for production usage.

Unless stated otherwise on the page, this functionality is available when your Elastic Stack is deployed on Elastic Cloud Hosted, Elastic Cloud Enterprise, Elastic Cloud on Kubernetes, and self-managed environments.

This documentation corresponds to the latest patch available for each minor version. If you're not using the latest patch, check the release notes for changes.

Elastic Agent Preview

Elastic Agent can run in OpenTelemetry mode to retrieve traces, metrics, and logs from your infrastructure and applications, and forward them to Elastic Observability.

Availability

  • Preview

    This functionality is in technical preview and is ready for evaluation. Use with caution in production; it is not recommended for mission-critical workloads. Elastic will work to fix any issues, but features in technical preview are not subject to the support SLA of official GA features. Specific Support terms apply.

This documentation corresponds to the latest patch available for each minor version. If you're not using the latest patch, check the release notes for changes.

Applications make more and more use of Generative Artificial Intelligence (GenAI). Telemetry data in terms of spans, metrics and logs when communicating with the GenAI APIs becomes more and more important to operate the application in production and understand the application's behavior and health state.

Elastic currently supports LLM observability through the Elastic OpenTelemetry. The EDOT Java, EDOT Node.js, and EDOT Python distributions support LLM observability as a tech preview.

The following LLM platforms are supported:

Technology EDOT Java EDOT Node.js EDOT Python
OpenAI Client ✅ ✅ ✅
AWS Bedrock ❌ ❌ ✅
Google Vertex AI ❌ ❌ ✅

See the Supported Technologies section in the corresponding EDOT SDK for detailed information on supported versions.

To collect traces from the Claude Platform, you don't need EDOT instrumentation. The Claude Platform sends traces to Elastic from a destination that you add in the Claude Console. Refer to Send Claude Platform traces to Elastic.

Follow these steps to instrument LLMs using Elastic OpenTelemetry.

Select the environment and target system from the quick start overview and follow the setup instructions to instrument your LLM application. Instrumentation for the supported technologies is enabled by default.

See the Configuration section in the corresponding EDOT SDK to turn on or off specific instrumentations and check which instrumentation is active by default.

When you complete the setup and configuration of the EDOT SDK and there is a workload on your application, start checking for telemetry data in Kibana. If there's no data showing up, see the troubleshooting of the corresponding EDOT SDK.

Serverless Preview

Elastic Cloud Serverless projects are autoscaled environments, fully managed by Elastic and available on Elastic Cloud.

Availability

  • Preview

    This functionality is in technical preview and is ready for evaluation. Use with caution in production; it is not recommended for mission-critical workloads. Elastic will work to fix any issues, but features in technical preview are not subject to the support SLA of official GA features. Specific Support terms apply.

Serverless interfaces and procedures might differ from classic Elastic Stack deployments.

Stack Planned

The Elastic Stack includes Elastic's core products such as Elasticsearch, Kibana, Logstash, and Beats.

Availability

  • Planned

    We plan to add this functionality in a future Elastic Stack update. Subject to changes.

Unless stated otherwise on the page, this functionality is available when your Elastic Stack is deployed on Elastic Cloud Hosted, Elastic Cloud Enterprise, Elastic Cloud on Kubernetes, and self-managed environments.

This documentation corresponds to the latest patch available for each minor version. If you're not using the latest patch, check the release notes for changes.

After your application sends trace data, use the GenAI tab in Kibana to review model details and token usage, along with prompts and responses when your instrumentation records them: