From 4419eec154e8c36ccc8f2aea25bd9cbdf04700fe Mon Sep 17 00:00:00 2001 From: Zach Groves Date: Thu, 4 Dec 2025 11:52:51 -0500 Subject: [PATCH 1/2] add source otel tag update --- .../llm_observability/evaluations/external_evaluations.md | 6 ++++-- .../instrumentation/otel_instrumentation.md | 2 +- 2 files changed, 5 insertions(+), 3 deletions(-) diff --git a/content/en/llm_observability/evaluations/external_evaluations.md b/content/en/llm_observability/evaluations/external_evaluations.md index 3f64f0e81d2..b46addf399d 100644 --- a/content/en/llm_observability/evaluations/external_evaluations.md +++ b/content/en/llm_observability/evaluations/external_evaluations.md @@ -30,7 +30,7 @@ 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 not supported for [OpenTelemetry spans][5]. +- External evaluations are supported for [OpenTelemetry spans][5], but require adding the source:otel tag to your evaluation.
@@ -93,7 +93,9 @@ You can use the evaluations API provided by LLM Observability to send evaluation "timestamp_ms": 1609479200, "metric_type": "score", "label": "Accuracy", - "score_value": 3 + "score_value": 3, + // source:otel required only for OpenTelemetry spans + "tags": ["source:otel"] } ] } diff --git a/content/en/llm_observability/instrumentation/otel_instrumentation.md b/content/en/llm_observability/instrumentation/otel_instrumentation.md index 685cae372c3..4924dedc1d3 100644 --- a/content/en/llm_observability/instrumentation/otel_instrumentation.md +++ b/content/en/llm_observability/instrumentation/otel_instrumentation.md @@ -12,7 +12,7 @@ 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] -
External evaluations in LLM Observability are not applied to OpenTelemetry spans. Evaluations are only available for spans generated with the Datadog LLM Observability SDK or submitted directly to the HTTP API intake.
+
If sending external evaluations for OpenTelemetry spans, you must add the source:otel tag to your evaluation.
## Setup From 614e2ee63f4aa172e447a75542f22bfd9aa9b9e0 Mon Sep 17 00:00:00 2001 From: cecilia saixue wat-kim Date: Thu, 4 Dec 2025 14:43:46 -0800 Subject: [PATCH 2/2] Update otel_instrumentation.md --- .../llm_observability/instrumentation/otel_instrumentation.md | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/content/en/llm_observability/instrumentation/otel_instrumentation.md b/content/en/llm_observability/instrumentation/otel_instrumentation.md index 4924dedc1d3..1ee5dca056e 100644 --- a/content/en/llm_observability/instrumentation/otel_instrumentation.md +++ b/content/en/llm_observability/instrumentation/otel_instrumentation.md @@ -12,7 +12,7 @@ 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 sending external evaluations for OpenTelemetry spans, you must add the source:otel tag to your evaluation.
+
If you are sending external evaluations for OpenTelemetry spans, you must add the source:otel tag to your evaluation.
## Setup