From fb2bb98517972bf77b12824ae20e97921d0b9316 Mon Sep 17 00:00:00 2001 From: Zach Groves Date: Thu, 11 Dec 2025 16:11:38 -0500 Subject: [PATCH 1/4] make the note just for when submitting evals directly to the api, since sdks automatically add the tag --- .../en/llm_observability/evaluations/external_evaluations.md | 3 ++- .../llm_observability/instrumentation/otel_instrumentation.md | 2 +- 2 files changed, 3 insertions(+), 2 deletions(-) diff --git a/content/en/llm_observability/evaluations/external_evaluations.md b/content/en/llm_observability/evaluations/external_evaluations.md index b46addf399d..428b6903f19 100644 --- a/content/en/llm_observability/evaluations/external_evaluations.md +++ b/content/en/llm_observability/evaluations/external_evaluations.md @@ -30,7 +30,6 @@ 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.
@@ -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. +
Submitting evaluations for OpenTelemetry spans directly to the evaluations API requires adding the source:otel tag to your 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..d36e712d25c 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 you are sending external evaluations for OpenTelemetry spans, you must add the source:otel tag to your evaluation.
+
If you are sending external evaluations directly to the API for OpenTelemetry spans, you must add the source:otel tag to your evaluation.
## Setup From aca4f604e685832e0362aa14426515d8ad2d0a68 Mon Sep 17 00:00:00 2001 From: Zachary Groves <32471391+ZStriker19@users.noreply.github.com> Date: Tue, 16 Dec 2025 19:27:45 -0500 Subject: [PATCH 2/4] Update content/en/llm_observability/evaluations/external_evaluations.md Co-authored-by: DeForest Richards <56796055+drichards-87@users.noreply.github.com> --- .../en/llm_observability/evaluations/external_evaluations.md | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/content/en/llm_observability/evaluations/external_evaluations.md b/content/en/llm_observability/evaluations/external_evaluations.md index 428b6903f19..9f9e4d61834 100644 --- a/content/en/llm_observability/evaluations/external_evaluations.md +++ b/content/en/llm_observability/evaluations/external_evaluations.md @@ -29,7 +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. +Evaluation labels must be unique for a given LLM application (ml_app) and organization.
From b6315f6ecd4ed26633f9a7233b2a053aa0b32071 Mon Sep 17 00:00:00 2001 From: Zachary Groves <32471391+ZStriker19@users.noreply.github.com> Date: Tue, 16 Dec 2025 19:28:04 -0500 Subject: [PATCH 3/4] Update content/en/llm_observability/instrumentation/otel_instrumentation.md Co-authored-by: DeForest Richards <56796055+drichards-87@users.noreply.github.com> --- .../llm_observability/instrumentation/otel_instrumentation.md | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/content/en/llm_observability/instrumentation/otel_instrumentation.md b/content/en/llm_observability/instrumentation/otel_instrumentation.md index d36e712d25c..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 directly to the API 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 From 6ea7337da231ffaca5671d29376cc427b8ec238a Mon Sep 17 00:00:00 2001 From: Zachary Groves <32471391+ZStriker19@users.noreply.github.com> Date: Tue, 16 Dec 2025 19:28:16 -0500 Subject: [PATCH 4/4] Update content/en/llm_observability/evaluations/external_evaluations.md Co-authored-by: DeForest Richards <56796055+drichards-87@users.noreply.github.com> --- .../en/llm_observability/evaluations/external_evaluations.md | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/content/en/llm_observability/evaluations/external_evaluations.md b/content/en/llm_observability/evaluations/external_evaluations.md index 9f9e4d61834..01d68b9c0ac 100644 --- a/content/en/llm_observability/evaluations/external_evaluations.md +++ b/content/en/llm_observability/evaluations/external_evaluations.md @@ -69,7 +69,7 @@ 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. -
Submitting evaluations for OpenTelemetry spans directly to the evaluations API requires adding the source:otel tag to your evaluation.
+To submit evaluations for OpenTelemetry spans directly to the Evaluations API, you must include the source:otel tag in the evaluation. ### Example