diff --git a/content/en/llm_observability/evaluations/external_evaluations.md b/content/en/llm_observability/evaluations/external_evaluations.md index b46addf399d..01d68b9c0ac 100644 --- a/content/en/llm_observability/evaluations/external_evaluations.md +++ b/content/en/llm_observability/evaluations/external_evaluations.md @@ -29,8 +29,7 @@ While LLM Observability provides a few out-of-the-box evaluations for your trace
-- Evaluation labels must be unique for a given LLM application (ml_app) and organization. -- External evaluations are supported for [OpenTelemetry spans][5], but require adding the source:otel tag to your evaluation. +Evaluation labels must be unique for a given LLM application (ml_app) and organization.
@@ -70,6 +69,8 @@ def llm_call(): You can use the evaluations API provided by LLM Observability to send evaluations associated with spans to Datadog. See the [Evaluations API][2] for more details on the API specifications. +To submit evaluations for OpenTelemetry spans directly to the Evaluations API, you must include the source:otel tag in the evaluation. + ### Example {{< code-block lang="json" >}} diff --git a/content/en/llm_observability/instrumentation/otel_instrumentation.md b/content/en/llm_observability/instrumentation/otel_instrumentation.md index 1ee5dca056e..fa9b4fa19a6 100644 --- a/content/en/llm_observability/instrumentation/otel_instrumentation.md +++ b/content/en/llm_observability/instrumentation/otel_instrumentation.md @@ -12,7 +12,8 @@ LLM Observability supports ingesting OpenTelemetry traces that follow the [OpenT - A [Datadog API key][2] - An application instrumented with OpenTelemetry that emits traces following the [OpenTelemetry 1.37+ semantic conventions for generative AI][1] -
If you are sending external evaluations for OpenTelemetry spans, you must add the source:otel tag to your evaluation.
+To send external evaluations directly to the API for OpenTelemetry spans, you must include the source:otel tag in the evaluation. + ## Setup