AWS bedrock documentation change
Summary
Added curl example with AWS SigV4 authentication and temporary credentials note; updated feature references and documentation links
Security assessment
The curl example explicitly documents how to include AWS credentials and session tokens for authentication using SigV4. This demonstrates secure API access methods but doesn't address a specific vulnerability. The change improves security documentation by showing proper credential handling.
Diff
diff --git a/bedrock/latest/userguide/inference-messages-api.md b/bedrock/latest/userguide/inference-messages-api.md index 36cf1356a..f10a6c9be 100644 --- a//bedrock/latest/userguide/inference-messages-api.md +++ b//bedrock/latest/userguide/inference-messages-api.md @@ -86 +86 @@ bedrock-runtime (Python) -bedrock-runtime (curl) +bedrock-runtime (AWS CLI) @@ -103,0 +104,23 @@ Use the AWS CLI to invoke the model: +bedrock-runtime (curl) + + +You can call `bedrock-runtime` directly with curl by signing the request with AWS SigV4. The example below uses curl's built-in `--aws-sigv4` flag (available in curl 7.75.0 and later): + + + curl -X POST \ + "https://bedrock-runtime.us-east-1.amazonaws.com/model/anthropic.claude-sonnet-4-6-v1/invoke" \ + -H "Content-Type: application/json" \ + --aws-sigv4 "aws:amz:us-east-1:bedrock" \ + --user "$AWS_ACCESS_KEY_ID:$AWS_SECRET_ACCESS_KEY" \ + -d '{ + "anthropic_version": "bedrock-2023-05-31", + "max_tokens": 1024, + "messages": [ + {"role": "user", "content": "Explain quantum computing in one sentence."} + ] + }' + +###### Note + +If you are using temporary credentials from AWS STS (for example, an assumed role), also pass the session token by adding `-H "X-Amz-Security-Token: $AWS_SESSION_TOKEN"` to the request. For most use cases we recommend the AWS SDKs or CLI, which handle request signing and credential refresh automatically. + @@ -152 +175 @@ bedrock-runtime (Python) -The Messages API supports the following advanced features with Claude models: +In addition to the [Extended thinking](./claude-messages-extended-thinking.html), [Adaptive thinking](./claude-messages-adaptive-thinking.html), [Structured outputs](./claude-messages-structured-outputs.html), [Compaction](./claude-messages-compaction.html), and [Mid-conversation system messages](./claude-messages-mid-conversation-system.html) sections above, the Messages API supports the following features with Claude models: @@ -162,2 +184,0 @@ The Messages API supports the following advanced features with Claude models: - * **Extended thinking** – Enable chain-of-thought reasoning. See [Enhance model responses with model reasoning](./inference-reasoning.html). - @@ -169 +190 @@ The Messages API supports the following advanced features with Claude models: -For the full Messages API request and response format, including all parameters and features, see [Anthropic Claude Messages API](./model-parameters-anthropic-claude-messages.html). +For the full Messages API request and response field reference, see [Request and Response](./model-parameters-anthropic-claude-messages-request-response.html). @@ -183 +204 @@ Chat Completions API -Invoke API +Extended thinking