AWS nova documentation change
Summary
Restructured documentation to focus solely on request schema, removed response structure details, clarified parameter requirements, and updated navigation links
Security assessment
Changes are primarily structural/organizational with no explicit security fixes or vulnerabilities addressed. The removal of response structure examples and redaction references appears to be documentation cleanup rather than security remediation. Parameter clarifications (like marking 'messages' as required) improve accuracy but don't indicate security fixes.
Diff
diff --git a/nova/latest/userguide/complete-request-schema.md b/nova/latest/userguide/complete-request-schema.md index 8baba3f30..7a69b1e3f 100644 --- a//nova/latest/userguide/complete-request-schema.md +++ b//nova/latest/userguide/complete-request-schema.md @@ -5,3 +5 @@ -Request structureResponse structure highlights - -# Complete request and response schema +# Complete request schema @@ -26,4 +23,0 @@ The timeout period for inference calls to Amazon Nova is 60 minutes. By default, -## Request structure - -The following shows the complete request structure for Amazon Nova understanding models: - @@ -135 +129 @@ The following shows the complete request structure for Amazon Nova understanding -The following are request parameters: +The following are required parameters: @@ -137 +131 @@ The following are request parameters: -`system` – (Optional) The system prompt for the request. + * `system` – (Optional) The system prompt for the request. @@ -141 +135 @@ A system prompt is a way of providing context and instructions to Amazon Nova, s -`messages` – (Required) The input messages. + * `messages` – (Required) The input messages. @@ -223,4 +217 @@ A system prompt is a way of providing context and instructions to Amazon Nova, s - - - -`inferenceConfig:` These are inference config values that can be passed in inference. + * `inferenceConfig:` These are inference config values that can be passed in inference. @@ -267 +255 @@ Parameter | Default value | Range -`toolConfig` – (Optional) JSON object following [ToolConfig schema](https://docs.aws.amazon.com/bedrock/latest/APIReference/API_runtime_ToolConfiguration.html), containing the tool specification and tool choice. This schema is the same followed [by the Converse API](https://docs.aws.amazon.com/bedrock/latest/userguide/tool-use.html) + * `toolConfig` – (Optional) JSON object following [ToolConfig schema](https://docs.aws.amazon.com/bedrock/latest/APIReference/API_runtime_ToolConfiguration.html), containing the tool specification and tool choice. This schema is the same followed [by the Converse API](https://docs.aws.amazon.com/bedrock/latest/userguide/tool-use.html) @@ -280,107 +267,0 @@ Parameter | Default value | Range -## Response structure highlights - -The following shows the key elements of the response structure returned by the non-streaming `Converse` and `InvokeModel` functions. For details on the full response structure as well as the request and response structures for the streaming functions, see the API documentation. - - - { - "ResponseMetadata": { - "RequestId": string, - "HTTPStatusCode": int, - "HTTPHeaders": { - "date": string, - "content-type": "application/json", - "content-length": string, - "connection": "keep-alive", - "x-amzn-requestid": string - }, - "RetryAttempts": 0 - }, - "output": { - "message": { - "role": "assistant", - "content": [ - { // Optional - "reasoningContent": { - "reasoningText": { - "text": string - } - } - }, - { // Optional - "toolUse": { - "toolUseId": string, - "name": string, - "input": object - } - }, - { // Optional - "text": string - }, - { // Optional - "image": { - "format": "png", - "source": { - "bytes": { - "bytes": image // Binary array (Converse API) or Base64-encoded string (Invoke API) - } - } - } - } - ] - } - }, - "stopReason": string, // "end_turn" | "content_filtered" | "max_tokens" | "malformed_model_output" | "malformed_tool_use" | etc. - "usage": { - "inputTokens": int, - "outputTokens": int, - "totalTokens": int - }, - "metrics": { - "latencyMs": int - } - } - -The following are key response elements: - -`output` – (Required) Contains the model's response message. - - * `message` – (Required) The assistant's response message. - - * `content` – (Required) An array of one or more content blocks that can include: - - * `reasoningContent` – (Optional) Returned if reasoning was enabled. Contains the reasoning text, which will always be `[REDACTED]` in the response. - - * `toolUse` – (Optional) Returned if a tool was called. Contains the tool use ID, name, and input arguments. - - * `text` – (Optional) Returned if the model responded with text content. - - * `image` – (Optional, only) Returned if the model generated an image. The format will always be PNG for images generated by . - - - - -`stopReason` – (Required) An enum value indicating why the model stopped generating output. Supported values include: - - * `end_turn` – The logical end of the turn was reached. - - * `max_tokens` – Output reached the `maxTokens` limit set by the user or the model's own maximum output token limit. - - * `content_filtered` – The model's output violated the AWS Responsible AI policy. - - * `malformed_model_output` – The model produced invalid output. - - * `malformed_tool_use` – The model produced invalid `toolUse` output. - - * `service_unavailable` – One of the built-in tool services could not be reached. - - * `invalid_query` – The query that the model sent to the built-in Web Grounding tool was invalid. - - * `max_tool_invocations` – Indicates a built-in tool was called but did not produce a valid result, even after multiple retries. - - - - -`usage` – (Required) Token usage information including input tokens, output tokens, and total tokens. - -`metrics` – (Required) Performance metrics including the total inference latency in milliseconds. - @@ -393 +274 @@ To use the Amazon Web Services Documentation, Javascript must be enabled. Please -Deploy a custom model for on-demand inference +Delete a custom model deployment @@ -395 +276 @@ Deploy a custom model for on-demand inference -Multimodal support +Response structure highlights