AWS bedrock medium security documentation change
Summary
Restructured table of contents: added OpenAI API reference, removed tool-use/prompt caching sections, and changed 'Model compatibility' to 'Control permissions'
Security assessment
The change from 'Model compatibility' to 'Control permissions' introduces explicit access control documentation. This adds security-relevant content about permission management for model inference, though no specific vulnerability is addressed.
Diff
diff --git a/bedrock/latest/userguide/inference.md b/bedrock/latest/userguide/inference.md index a49f8ad17..24ef9cf99 100644 --- a//bedrock/latest/userguide/inference.md +++ b//bedrock/latest/userguide/inference.md @@ -36 +36 @@ Embeddings | Provide text, images, or both text and images and generate a vector - * [Service tiers for optimizing performance and cost](./service-tiers-inference.html) + * [Generate responses using OpenAI APIs](./bedrock-mantle.html) @@ -40,2 +39,0 @@ Embeddings | Provide text, images, or both text and images and generate a vector - * [Use a tool to complete an Amazon Bedrock model response](./tool-use.html) - @@ -46,4 +43,0 @@ Embeddings | Provide text, images, or both text and images and generate a vector - * [Prompt caching for faster model inference](./prompt-caching.html) - - * [Generate responses using OpenAI APIs](./bedrock-mantle.html) - @@ -59 +53 @@ To use the Amazon Web Services Documentation, Javascript must be enabled. Please -Model compatibility +Control permissions @@ -61 +55 @@ Model compatibility -Use cases for different inference methods +Different inference methods