AWS nova documentation change
Summary
Restructured documentation with added sections (Request structure, Inference parameters, Reasoning parameters), expanded parameter descriptions, removed code examples, and clarified parameter constraints
Security assessment
The changes primarily reorganize content and clarify API usage parameters. While parameter constraints (e.g., temperature/topP being incompatible with high reasoning effort) are emphasized, this appears to be standard API usage guidance rather than addressing a specific security vulnerability. No explicit security vulnerabilities or security feature enhancements are mentioned in the diff.
Diff
diff --git a/nova/latest/nova2-userguide/using-converse-api.md b/nova/latest/nova2-userguide/using-converse-api.md index f9ff66326..5cd92395c 100644 --- a//nova/latest/nova2-userguide/using-converse-api.md +++ b//nova/latest/nova2-userguide/using-converse-api.md @@ -11 +11,14 @@ The Converse API provides a unified interface for interacting with Amazon Nova m -The Converse API supports the following features: +###### Topics + + * Request structure + + * Using system prompts + + * Inference parameters + + * Using reasoning + + + + +## Request structure @@ -30,2 +42,0 @@ The Converse API supports the following features: -## Request structure - @@ -85 +96,14 @@ System prompts provide context and instructions to the model: -Control the model's output using inference parameters: +Control the model's output using inference parameters. The following are available inference parameters. + + * maxTokens (integer): Maximum number of tokens to generate (up to 65,000). If not specified, the model uses a dynamic default based on the request context. + + * temperature (float): Controls randomness (0.0-1.0, default 0.7). Lower values make output more deterministic + + * topP (float): Nucleus sampling threshold (0-1, default 0.9). Lower values make output more focused + + * stopSequences (array): Sequences of characters that stop generation when encountered + + + + +Example: @@ -112,23 +135,0 @@ Control the model's output using inference parameters: -Available inference parameters: - - * `maxTokens` (integer): Maximum number of tokens to generate (up to 65,000). If not specified, the model uses a dynamic default based on the request context. - - * `temperature` (float): Controls randomness (0.0-1.0, default 0.7). Lower values make output more deterministic - - * `topP` (float): Nucleus sampling threshold (0-1, default 0.9). Lower values make output more focused - - * `stopSequences` (array): Sequences that stop generation when encountered - - - - -Amazon Nova also supports `topK` (1-128, not used by default) via `additionalModelRequestFields`: - - - response = bedrock.converse( - modelId='us.amazon.nova-2-lite-v1:0', - messages=[{'role': 'user', 'content': [{'text': 'Hello'}]}], - inferenceConfig={'maxTokens': 100}, - additionalModelRequestFields={'inferenceConfig': {'topK': 50}} - ) - @@ -139 +140 @@ Nova 2 Lite supports extended thinking for complex problem-solving. Enable reaso -By default, reasoning is disabled to optimize for speed and cost on simple queries. When you need more complex reasoning, you can enable it with three effort levels: +By default, reasoning is disabled to optimize for speed and cost on simple queries. When you needto go beyond these straightforward tasks, you can enable reasoning. Nova 2 provides flexible control over reasoning depth through three effort levels: @@ -144 +145 @@ Low effort (`maxReasoningEffort: "low"`) -Use for tasks requiring structured thinking, such as code review, multi-factor analysis, or methodical problem-solving. +BEST FOR: TASKS WITH ADDED COMPLEXITY REQUIRING STRUCTURED THINKING. For example, you can use this for code review and improvement suggestions where the model needs to carefully consider existing code quality, analysis tasks that require thoughtful consideration of multiple factors, or problem-solving scenarios that benefit from a methodical approach. Low effort is ideal for compound tasks where basic reasoning improves accuracy without requiring deep multi-step planning. @@ -149 +150 @@ Medium effort (`maxReasoningEffort: "medium"`) -Use for multi-step tasks like software development, debugging, multi-file code generation, or agentic workflows coordinating multiple tools. +BEST FOR: MULTI-STEP TASKS AND CODING WORKFLOWS. For example, you can use this for software development and debugging where the model needs to understand existing code structure before implementing changes, code generation that requires coordination across multiple files or components, multi-step calculations with interdependencies, or planning tasks with multiple constraints. Medium effort is optimal for agentic workflows that coordinate multiple tools and require the model to maintain context across several sequential operations. @@ -154 +155 @@ High effort (`maxReasoningEffort: "high"`) -Use for advanced problem-solving like mathematical proofs, scientific analysis, complex system design, or critical decision-making requiring thorough validation. +BEST FOR: STEM REASONING AND ADVANCED PROBLEM-SOLVING. For example, you can use this for advanced mathematical problems and proofs that require rigorous step-by-step verification, scientific analysis and research tasks demanding deep investigation, complex system design with architectural considerations across multiple dimensions, or critical decision-making scenarios with significant implications. High effort delivers maximum accuracy for tasks requiring sophisticated reasoning, careful evaluation of alternatives, and thorough validation of conclusions. @@ -186,34 +186,0 @@ Low effort - content_list = response["output"]["message"]["content"] - - for item in content_list: - if "reasoningContent" in item: - reasoning_text = item["reasoningContent"]["reasoningText"]["text"] - print("=== REASONING ===") - print(reasoning_text) - print() - elif "text" in item: - print("=== ANSWER ===") - print(item["text"]) - -High effort - - - - import boto3 - bedrock = boto3.client('bedrock-runtime', region_name='us-east-1') - - response = bedrock.converse( - modelId='us.amazon.nova-2-lite-v1:0', - messages=[ - { - 'role': 'user', - 'content': [{'text': 'Solve this logic puzzle: If all roses are flowers and some flowers fade quickly, what can we conclude?'}] - } - ], - additionalModelRequestFields={ - 'reasoningConfig': { - 'type': 'enabled', - 'maxReasoningEffort': 'high' - } - } - ) @@ -221,4 +188 @@ High effort - content_list = response["output"]["message"]["content"] - text = next((item["text"] for item in content_list if "text" in item), None) - if text is not None: - print(text) +**Reasoning parameters:** @@ -226 +190 @@ High effort -Reasoning parameters: +The following are reasoning parameters @@ -230 +194 @@ Reasoning parameters: - * `maxReasoningEffort`: `low`, `medium`, or `high` + * `maxReasoningEffort`: `low`, `medium`, or `high`. This is required when reasoning is enabled. @@ -237 +201 @@ Reasoning parameters: -Temperature, topP and topK cannot be used with `maxReasoningEffort` set to `high`. Using these parameters together causes an error. +Temperature, topP and topK cannot be used with `maxReasoningEffort` set to `high`. This will cause an error. @@ -239 +203 @@ Temperature, topP and topK cannot be used with `maxReasoningEffort` set to `high -The response includes reasoning content showing step-by-step analysis: +The response includes reasoning content: @@ -273 +237 @@ To use the Amazon Web Services Documentation, Javascript must be enabled. Please -Core inference +Important: Timeout Configuration