AWS Security ChangesHomeSearch

AWS bedrock documentation change

Service: bedrock · 2025-11-19 · Documentation low

File: bedrock/latest/userguide/model-parameters-marengo.md

Summary

Updated documentation for Marengo model parameters including S3 bucket owner specification, example formatting changes, and clarification about async invocation for video/audio inputs

Security assessment

Changes are documentation improvements and clarifications about model parameters and input types without any security-specific context or vulnerability mitigation

Diff

diff --git a/bedrock/latest/userguide/model-parameters-marengo.md b/bedrock/latest/userguide/model-parameters-marengo.md
index 3babb1e1c..50814cd1f 100644
--- a//bedrock/latest/userguide/model-parameters-marengo.md
+++ b//bedrock/latest/userguide/model-parameters-marengo.md
@@ -245 +245 @@ The format of the `mediaSource` object in the request body depends on whether th
-  * **S3 location** – Specify the S3 URI and the 
+  * **S3 location** – Specify the S3 URI and the bucket owner.
@@ -312 +312 @@ The time in seconds, counting from the `startSec` time point, after which proces
-For example:
+Example:
@@ -318 +318 @@ For example:
-  * Result: The clip will be processed from 0:05 to 0:20.
+  * Result: The clip is processed from 0:05 to 0:25 (5 seconds + 20 seconds).
@@ -333 +333 @@ The duration of each clip for which the model should generate an embedding.
-    * **Video:** Divided dynamically by shot boundary detection
+    * **Video:** Divided dynamically by shot boundary detection.
@@ -335 +335 @@ The duration of each clip for which the model should generate an embedding.
-    * **Audio:** Divided evenly and as close to 10 as possible. For example:
+    * **Audio:** Divided evenly with segments as close to 10 seconds as possible.
@@ -337 +337 @@ The duration of each clip for which the model should generate an embedding.
-      * A 50 second clip will be divided into 5 10-second segments.
+Examples:
@@ -339 +339,3 @@ The duration of each clip for which the model should generate an embedding.
-      * A 16 second clip will be divided into 2 8-second segments.
+      * A 50-second clip is divided into 5 10-second segments.
+
+      * A 16-second clip is divided into 2 8-second segments.
@@ -434 +436 @@ The end offset of the clip, in seconds.
-This section shows how to use the TwelveLabs Marengo Embed 2.7 model with different input types using Python.
+This section shows how to use the TwelveLabs Marengo Embed 2.7 model with different input types using Python. The examples demonstrate how to define model-specific input and run model invocations.
@@ -438 +440 @@ This section shows how to use the TwelveLabs Marengo Embed 2.7 model with differ
-Currently, InvokeModel only supports text and image input.
+InvokeModel supports text and image input only. For video and audio input, use StartAsyncInvoke.