[MLOB-4215] Add annotationContext docs for LLM Observability Node.js SDK

content/en/llm_observability/instrumentation/sdk.md

@@ -1230,7 +1230,7 @@
   LLMObsSpan taskSpan = LLMObs.startTaskSpan("preprocessDocument", null, "session-141");
    ...   // preprocess document for data extraction
    taskSpan.annotateIO(...); // record the input and output
-   taskSpan.finish();    
+   taskSpan.finish();
   }
 
   public String extractData(String document) {
@@ -1740,7 +1740,7 @@
 {{< tabs >}}
 {{% tab "Python" %}}
 
-The SDK's `LLMObs.annotate_context()` method returns a context manager that can be used to modify all auto-instrumented spans started while the annotation context is active.
+The SDK's `LLMObs.annotation_context()` method returns a context manager that can be used to modify all auto-instrumented spans started while the annotation context is active.
 
 The `LLMObs.annotation_context()` method accepts the following arguments:
 
@@ -1756,7 +1756,7 @@
 
 `tags`
 : optional - _dictionary_
-<br />A dictionary of JSON serializable key-value pairs that users can add as tags on the span. Example keys: `session`, `env`, `system`, and `version`. For more information about tags, see [Getting Started with Tags][1].
+<br />A dictionary of JSON serializable key-value pairs that users can add as tags on the span. Example keys: `session`, `env`, `system`, and `version`. For more information about tags, see [Getting Started with Tags](/getting_started/tagging/).
 
 {{% /collapse-content %}}
 
@@ -1788,7 +1788,46 @@
 
 {{< /code-block >}}
 
-[1]: /getting_started/tagging/
+{{% /tab %}}
+
+{{% tab "Node.js" %}}
+
+The SDK's `llmobs.annotationContext()` accepts a callback function that can be used to modify all auto-instrumented spans started while inside the scope of the callback function.
+
+The `llmobs.annotationContext()` method accepts the following options on the first argument:
+
+{{% collapse-content title="Options" level="h4" expanded=false id="annotating-autoinstrumented-span-arguments" %}}
+
+`name`
+: optional - _str_
+<br />Name that overrides the span name for any auto-instrumented spans that are started within the annotation context.
+
+`tags`
+: optional - _object_
+<br />An object of JSON serializable key-value pairs that users can add as tags on the span. Example keys: `session`, `env`, `system`, and `version`. For more information about tags, see [Getting Started with Tags](/getting_started/tagging/).
+
+{{% /collapse-content %}}
+
+#### Example
+
+{{< code-block lang="javascript" >}}
+const { llmobs } = require('dd-trace');
+
+function ragWorkflow(userQuestion) {
+    const contextStr = retrieveDocuments(userQuestion).join(" ");
+
+    const completion = await llmobs.annotationContext({
+      tags: {
+        retrieval_strategy: "semantic_similarity"
+      },
+      name: "augmented_generation"
+    }, async () => {
+      const completion = await openai_client.chat.completions.create(...);
+      return completion.choices[0].message.content;
+    });
+}
+
+{{< /code-block >}}
 
 {{% /tab %}}
 {{< /tabs >}}
@@ -2161,6 +2200,32 @@
 llmobs.registerProcessor(redactProcessor)
 {{< /code-block >}}
 
+### Example: conditional modification with auto-instrumentation
+
+When using auto instrumentation, the span is not always contextually accessible. To conditionally modify the inputs and outputs on auto-instrumented spans, `llmobs.annotationContext()` can be used in addition to a span processor.
+
+{{< code-block lang="javascript" >}}
+const { llmobs } = require('dd-trace');
+
+function redactProcessor(span) {
+  if (span.getTag("no_input") == "true") {
+    for (const message of span.input) {
+      message.content = "";
+    }
+  }
+
+  return span;
+}
+
+llmobs.registerProcessor(redactProcessor);
+
+async function callOpenai() {
+  await llmobs.annotationContext({ tags: { no_input: "true" } }, async () => {
+    // make call to openai
+  });
+}
+{{< /code-block >}}
+
 ### Example: preventing spans from being emitted
 
 {{< code-block lang="javascript" >}}