AWS bedrock documentation change
Summary
Added descriptive alt text to all icon images throughout the document
Security assessment
Changes only add accessibility-focused alt text descriptions for visual elements (e.g., 'Green circle with white checkmark icon'). No modifications to security features, vulnerabilities, or security-related content. The mentions of 'Guardrails' and 'Abuse detection' remain unchanged except for their icon alt text.
Diff
diff --git a/bedrock/latest/userguide/model-card-openai-gpt-oss-20b.md b/bedrock/latest/userguide/model-card-openai-gpt-oss-20b.md index 9fc02b064..da26bdda9 100644 --- a//bedrock/latest/userguide/model-card-openai-gpt-oss-20b.md +++ b//bedrock/latest/userguide/model-card-openai-gpt-oss-20b.md @@ -7 +7 @@ -OpenAI — gpt-oss-20bModel DetailsCapabilities and FeaturesPricingProgrammatic AccessService TiersRegional AvailabilityQuotas and LimitsSample Code +Icon showing a circular pattern with interwoven curved segments forming a pinwheel design. OpenAI — gpt-oss-20bModel DetailsCapabilities and FeaturesPricingProgrammatic AccessService TiersRegional AvailabilityQuotas and LimitsSample Code @@ -11 +11 @@ OpenAI — gpt-oss-20bModel DetailsCapabilities and FeaturesPricingProgrammatic -##  OpenAI — gpt-oss-20b +##  OpenAI — gpt-oss-20b @@ -34,5 +34,5 @@ GPT OSS 20B is OpenAI's 20-billion parameter open-source model for efficient tex - Audio|  Embedding|  `Responses`|  `bedrock-runtime` - Image|  Image|  `Chat Completions`|  `bedrock-mantle` - Speech|  Speech|  `Invoke`| - Text|  Text|  `Converse`| - Video|  Video| | + Audio|  Embedding|  `Responses`|  `bedrock-runtime` + Image|  Image|  `Chat Completions`|  `bedrock-mantle` + Speech|  Speech|  `Invoke`| + Text|  Text|  `Converse`| + Video|  Video| | @@ -53,3 +53,3 @@ Whenever possible, we recommend you use the `bedrock-mantle` endpoint. - *  [Server-side tool calling](https://docs.aws.amazon.com/bedrock/latest/userguide/tool-use.html) - *  [Projects](https://docs.aws.amazon.com/bedrock/latest/userguide/projects.html) - *  [Client-side tool calling](https://docs.aws.amazon.com/bedrock/latest/userguide/tool-use.html) + *  [Server-side tool calling](https://docs.aws.amazon.com/bedrock/latest/userguide/tool-use.html) + *  [Projects](https://docs.aws.amazon.com/bedrock/latest/userguide/projects.html) + *  [Client-side tool calling](https://docs.aws.amazon.com/bedrock/latest/userguide/tool-use.html) @@ -64,3 +64,3 @@ Whenever possible, we recommend you use the `bedrock-mantle` endpoint. - *  [Response streaming](https://docs.aws.amazon.com/bedrock/latest/APIReference/API_runtime_InvokeModelWithResponseStream.html) - *  [Guardrails](https://docs.aws.amazon.com/bedrock/latest/userguide/guardrails.html) - *  [Structured outputs](https://docs.aws.amazon.com/bedrock/latest/userguide/structured-outputs.html) + *  [Response streaming](https://docs.aws.amazon.com/bedrock/latest/APIReference/API_runtime_InvokeModelWithResponseStream.html) + *  [Guardrails](https://docs.aws.amazon.com/bedrock/latest/userguide/guardrails.html) + *  [Structured outputs](https://docs.aws.amazon.com/bedrock/latest/userguide/structured-outputs.html) @@ -70,9 +70,9 @@ Whenever possible, we recommend you use the `bedrock-mantle` endpoint. - *  [Intelligent prompt routing](https://docs.aws.amazon.com/bedrock/latest/userguide/prompt-routing.html) - *  [Abuse detection](https://docs.aws.amazon.com/bedrock/latest/userguide/abuse-detection.html) - *  [Prompt optimization](https://docs.aws.amazon.com/bedrock/latest/userguide/prompt-management-optimize.html) - *  [Count tokens](https://docs.aws.amazon.com/bedrock/latest/userguide/count-tokens.html) - *  [Knowledge base](https://docs.aws.amazon.com/bedrock/latest/userguide/knowledge-base.html) - *  [Model evaluation](https://docs.aws.amazon.com/bedrock/latest/userguide/evaluation.html) - *  [Prompt management](https://docs.aws.amazon.com/bedrock/latest/userguide/prompt-management.html) - *  [Flows](https://docs.aws.amazon.com/bedrock/latest/userguide/flows.html) - *  [Agents](https://docs.aws.amazon.com/bedrock/latest/userguide/agents.html) + *  [Intelligent prompt routing](https://docs.aws.amazon.com/bedrock/latest/userguide/prompt-routing.html) + *  [Abuse detection](https://docs.aws.amazon.com/bedrock/latest/userguide/abuse-detection.html) + *  [Prompt optimization](https://docs.aws.amazon.com/bedrock/latest/userguide/prompt-management-optimize.html) + *  [Count tokens](https://docs.aws.amazon.com/bedrock/latest/userguide/count-tokens.html) + *  [Knowledge base](https://docs.aws.amazon.com/bedrock/latest/userguide/knowledge-base.html) + *  [Model evaluation](https://docs.aws.amazon.com/bedrock/latest/userguide/evaluation.html) + *  [Prompt management](https://docs.aws.amazon.com/bedrock/latest/userguide/prompt-management.html) + *  [Flows](https://docs.aws.amazon.com/bedrock/latest/userguide/flows.html) + *  [Agents](https://docs.aws.amazon.com/bedrock/latest/userguide/agents.html) @@ -103 +103 @@ Amazon Bedrock offers multiple service tiers to match your workload requirements - |  |  |  + |  |  |  @@ -113,15 +113,15 @@ Bedrock offers three inference options: **In-Region** keeps requests within a si -`us-east-1` (N. Virginia)| | |  -`us-east-2` (Ohio)| | |  -`us-west-2` (Oregon)| | |  -`eu-central-1` (Frankfurt)| | |  -`eu-north-1` (Stockholm)| | |  -`eu-south-1` (Milan)| | |  -`eu-west-1` (Ireland)| | |  -`eu-west-2` (London)| | |  -`ap-northeast-1` (Tokyo)| | |  -`ap-south-1` (Mumbai)| | |  -`ap-southeast-2` (Sydney)| | |  -`ap-southeast-3` (Jakarta)| | |  -`sa-east-1` (São Paulo)| | |  -`ap-southeast-4` (Melbourne)| | |  -`us-gov-west-1` (GovCloud)| | |  +`us-east-1` (N. Virginia)| | |  +`us-east-2` (Ohio)| | |  +`us-west-2` (Oregon)| | |  +`eu-central-1` (Frankfurt)| | |  +`eu-north-1` (Stockholm)| | |  +`eu-south-1` (Milan)| | |  +`eu-west-1` (Ireland)| | |  +`eu-west-2` (London)| | |  +`ap-northeast-1` (Tokyo)| | |  +`ap-south-1` (Mumbai)| | |  +`ap-southeast-2` (Sydney)| | |  +`ap-southeast-3` (Jakarta)| | |  +`sa-east-1` (São Paulo)| | |  +`ap-southeast-4` (Melbourne)| | |  +`us-gov-west-1` (GovCloud)| | | 