AWS bedrock documentation change
Summary
Added prompt caching documentation, added link to complete request schema, and updated API example structure
Security assessment
Adds feature documentation for prompt caching, provides reference to complete API schema, and updates example format. These are documentation improvements without security implications or security feature additions.
Diff
diff --git a/bedrock/latest/userguide/model-card-amazon-nova-micro.md b/bedrock/latest/userguide/model-card-amazon-nova-micro.md index 9e18acba0..86f49e4a0 100644 --- a//bedrock/latest/userguide/model-card-amazon-nova-micro.md +++ b//bedrock/latest/userguide/model-card-amazon-nova-micro.md @@ -41,0 +42,10 @@ Nova Micro is Amazon's fastest text-only model, optimized for speed and low cost +**Prompt caching using`bedrock-runtime` endpoint** + +For more information, see [Prompt caching for faster model inference](https://docs.aws.amazon.com/bedrock/latest/userguide/prompt-caching.html). + +**Prompt caching supported** | **Min tokens per cache checkpoint** | **Max cache checkpoints per request** | **Supported TTL** | **Fields that accept prompt cache checkpoints** +---|---|---|---|--- +Yes | 1K* | 4 | 5 minutes | `system` and `messages` + +_* Amazon Nova models support a maximum of 20K tokens for prompt caching._ + @@ -133,0 +144,2 @@ Your AWS account has default quotas to maintain the performance of the service a +For the complete request and response schema, including all supported parameters such as `system` prompts, `temperature`, `topP`, `stopSequences`, and `toolConfig`, see [Complete request schema](https://docs.aws.amazon.com/nova/latest/userguide/complete-request-schema.html) in the Amazon Nova User Guide. + @@ -145,2 +157,7 @@ Invoke API - 'messages': [{ 'role': 'user', 'content': 'Can you explain the features of Amazon Bedrock?'}], - 'max_tokens': 1024 + 'messages': [{ + 'role': 'user', + 'content': [{'text': 'Can you explain the features of Amazon Bedrock?'}] + }], + 'inferenceConfig': { + 'maxTokens': 1024 + }