AWS bedrock documentation change
Summary
Improved documentation formatting and clarified capabilities for Marengo Embed 3.0 model
Security assessment
Changes consist of grammatical improvements and sentence restructuring without introducing security content. The updates clarify technical specifications (e.g., file size limits, async invocation) but don't address security controls, vulnerabilities, or security-related features.
Diff
diff --git a/bedrock/latest/userguide/model-parameters-marengo-3.md b/bedrock/latest/userguide/model-parameters-marengo-3.md index 54fcd51be..a8c50b0b5 100644 --- a//bedrock/latest/userguide/model-parameters-marengo-3.md +++ b//bedrock/latest/userguide/model-parameters-marengo-3.md @@ -20 +20 @@ Marengo Embed 3.0 delivers several key enhancements: - * **Extended video processing capacity** – Process up to 4 hours of video and audio content and files up to 6 GB—double the capacity of previous versions—making it ideal for analyzing full sporting events, extended training videos, and complete film productions. + * **Extended video processing capacity** – Process up to 4 hours of video and audio content. Files can be up to 6 GB, which is double the capacity of previous versions. This makes it ideal for analyzing full sporting events, extended training videos, and complete film productions. @@ -22 +22 @@ Marengo Embed 3.0 delivers several key enhancements: - * **Enhanced sports analysis** – The model delivers significant improvements with better understanding of gameplay dynamics, player movements, and event detection. + * **Enhanced sports analysis** – The model delivers significant improvements. It provides better understanding of gameplay dynamics, player movements, and event detection. @@ -24 +24 @@ Marengo Embed 3.0 delivers several key enhancements: - * **Global multilingual support** – Expanded language capabilities from 12 to 36 languages, enabling global organizations to build unified search and retrieval systems that work seamlessly across diverse regions and markets. + * **Global multilingual support** – Expanded language capabilities from 12 to 36 languages. This enables global organizations to build unified search and retrieval systems that work seamlessly across diverse regions and markets. @@ -26 +26 @@ Marengo Embed 3.0 delivers several key enhancements: - * **Multimodal search precision** – Combine images and descriptive text in a single embedding request, merging visual similarity with semantic understanding to deliver more accurate and contextually relevant search results. + * **Multimodal search precision** – Combine images and descriptive text in a single embedding request. This merges visual similarity with semantic understanding to deliver more accurate and contextually relevant search results. @@ -28 +28 @@ Marengo Embed 3.0 delivers several key enhancements: - * **Reduced embedding dimension** – Reduced from 1024 to 512, cutting storage costs. + * **Reduced embedding dimension** – Reduced from 1024 to 512, which can help reduce storage costs. @@ -377 +377 @@ The segmentation object contains a `method` field and method-specific parameters - * Audio: Uses fixed segmentation, dividing content as evenly as possible with segments close to 10 seconds. + * Audio: Uses fixed segmentation. Content is divided as evenly as possible with segments close to 10 seconds. @@ -425 +425 @@ Where you see this response depends on the API method you used: - * StartAsyncInvoke – Appears at the S3 location that you specified in the request. The response returns an `invocationArn` that you can use to get metadata about the asynchronous invocation, including the status and the S3 location to which the results are written. + * StartAsyncInvoke – Appears at the S3 location that you specified in the request. The response returns an `invocationArn`. You can use this to get metadata about the asynchronous invocation. This includes the status and the S3 location where the results are written. @@ -492 +492 @@ The end offset of the clip. Not applicable for text, image and text_image embedd -This section shows how to use the TwelveLabs Marengo Embed 3.0 model with different input types using Python. +This section shows how to use the TwelveLabs Marengo Embed 3.0 model with different input types using Python. The examples demonstrate how to define model-specific input and run model invocations. @@ -496 +496 @@ This section shows how to use the TwelveLabs Marengo Embed 3.0 model with differ -Currently, InvokeModel supports text, image, and text and image interleaved input. +InvokeModel supports text, image, and text with image interleaved input. For video and audio input, use StartAsyncInvoke.