Document metadata and enriched eval model for node js + add SDS link (#34596)

* Document metadata and enriched eval model for node js

* add SDS link

* Update content/en/llm_observability/instrumentation/sdk.md

Co-authored-by: DeForest Richards <56796055+drichards-87@users.noreply.github.com>

* Update content/en/llm_observability/instrumentation/sdk.md

Co-authored-by: DeForest Richards <56796055+drichards-87@users.noreply.github.com>

* Update content/en/llm_observability/instrumentation/sdk.md

Co-authored-by: DeForest Richards <56796055+drichards-87@users.noreply.github.com>

* Update content/en/llm_observability/instrumentation/sdk.md

Co-authored-by: DeForest Richards <56796055+drichards-87@users.noreply.github.com>

* Update content/en/llm_observability/evaluations/_index.md

Co-authored-by: DeForest Richards <56796055+drichards-87@users.noreply.github.com>

---------

Co-authored-by: DeForest Richards <56796055+drichards-87@users.noreply.github.com>

Author: gsvigruha

content/en/llm_observability/evaluations/_index.md

@@ -42,7 +42,7 @@ Datadog also supports integrations with some 3rd party evaluation frameworks, su
 
 ### Sensitive Data Scanner integration
 
-In addition to evaluating the input and output of LLM requests, agents, workflows, or the application, LLM Observability integrates with [Sensitive Data Scanner][6], which helps prevent data leakage by identifying and redacting any sensitive information.
+In addition to evaluating the input and output of LLM requests, agents, workflows, or the application, LLM Observability integrates with [Sensitive Data Scanner][6], which helps prevent data leakage by identifying and redacting any sensitive information. For a list of the out-of-the-box rules included with Sensitive Data Scanner, see [Library Rules][12].
 
 ### Security
 
@@ -73,4 +73,5 @@ LLM Observability offers an [Export API][9] that you can use to retrieve spans f
 [9]: /llm_observability/evaluations/export_api
 [10]: /llm_observability/guide/evaluation_developer_guide
 [11]: /llm_observability/evaluations/annotation_queues
+[12]: /security/sensitive_data_scanner/scanning_rules/library_rules/
 

content/en/llm_observability/instrumentation/sdk.md

@@ -2093,6 +2093,10 @@ The `LLMObs.submit_evaluation()` method accepts the following arguments:
 `reasoning`
 : optional - _string_
 <br />A text explanation of the evaluation result.
+
+`metadata`
+: optional - _dictionary_
+<br />A dictionary containing arbitrary structured metadata associated with the evaluation result.
 {{% /collapse-content %}}
 
 #### Example
@@ -2122,7 +2126,8 @@ def llm_call():
         value=10,
         tags={"evaluation_provider": "ragas"},
         assessment="fail",
-        reasoning="Malicious intent was detected in the user instructions."
+        reasoning="Malicious intent was detected in the user instructions.",
+        metadata={"details": ["jailbreak", "SQL injection"]}
     )
 
     # joining an evaluation to a span via span ID and trace ID
@@ -2135,7 +2140,8 @@ def llm_call():
         value=10,
         tags={"evaluation_provider": "ragas"},
         assessment="fail",
-        reasoning="Malicious intent was detected in the user instructions."
+        reasoning="Malicious intent was detected in the user instructions.",
+        metadata={"details": ["jailbreak", "SQL injection"]}
     )
     return completion
 {{< /code-block >}}
@@ -2168,15 +2174,27 @@ The `evaluationOptions` object can contain the following:
 
 `metricType`
 : required - _string_
-<br />The type of the evaluation. Must be one of "categorical" or "score".
+<br />The type of the evaluation. Must be one of "categorical", "score", "boolean" or "json".
 
 `value`
 : required - _string or numeric type_
-<br />The value of the evaluation. Must be a string (for categorical `metric_type`) or number (for score `metric_type`).
+<br />The value of the evaluation. Must be a string (for categorical `metric_type`), number (for score `metric_type`), boolean (for boolean `metric_type`), or a JSON object (for json `metric_type`).
 
 `tags`
 : optional - _dictionary_
 <br />A dictionary of string key-value pairs that users can add as tags regarding the evaluation. For more information about tags, see [Getting Started with Tags](/getting_started/tagging/).
+
+`assessment`
+: optional - _string_
+<br />An assessment of this evaluation. Accepted values are `pass` and `fail`.
+
+`reasoning`
+: optional - _string_
+<br />A text explanation of the evaluation result.
+
+`metadata`
+: optional - _dictionary_
+<br />A JSON object containing arbitrary structured metadata associated with the evaluation result.
 {{% /collapse-content %}}
 
 #### Example