AWS cli documentation change
Summary
Updated AWS CLI command reference for bedrock-agent update-agent, including reordered parameters, added new configuration options (instruction, foundation-model, orchestration-type, prompt-override-configuration), expanded documentation for model IDs, and restructured output descriptions.
Security assessment
The changes add documentation for encryption key usage (customer-encryption-key-arn) and IAM role permissions (agent-resource-role-arn), which are security-related features. However, there is no evidence these changes address a specific vulnerability or security incident.
Diff
diff --git a/cli/latest/reference/bedrock-agent/update-agent.md b/cli/latest/reference/bedrock-agent/update-agent.md index 87dc95e1a..208818a28 100644 --- a//cli/latest/reference/bedrock-agent/update-agent.md +++ b//cli/latest/reference/bedrock-agent/update-agent.md @@ -15 +15 @@ - * [AWS CLI 2.28.8 Command Reference](../../index.html) » + * [AWS CLI 2.28.11 Command Reference](../../index.html) » @@ -69 +68,0 @@ See also: [AWS API Documentation](https://docs.aws.amazon.com/goto/WebAPI/bedroc - [--agent-collaboration <value>] @@ -72 +71,4 @@ See also: [AWS API Documentation](https://docs.aws.amazon.com/goto/WebAPI/bedroc - --agent-resource-role-arn <value> + [--instruction <value>] + --foundation-model <value> + [--description <value>] + [--orchestration-type <value>] @@ -73,0 +76,2 @@ See also: [AWS API Documentation](https://docs.aws.amazon.com/goto/WebAPI/bedroc + [--idle-session-ttl-in-seconds <value>] + --agent-resource-role-arn <value> @@ -75,2 +79 @@ See also: [AWS API Documentation](https://docs.aws.amazon.com/goto/WebAPI/bedroc - [--description <value>] - --foundation-model <value> + [--prompt-override-configuration <value>] @@ -78,2 +80,0 @@ See also: [AWS API Documentation](https://docs.aws.amazon.com/goto/WebAPI/bedroc - [--idle-session-ttl-in-seconds <value>] - [--instruction <value>] @@ -81,2 +82 @@ See also: [AWS API Documentation](https://docs.aws.amazon.com/goto/WebAPI/bedroc - [--orchestration-type <value>] - [--prompt-override-configuration <value>] + [--agent-collaboration <value>] @@ -107 +107 @@ See also: [AWS API Documentation](https://docs.aws.amazon.com/goto/WebAPI/bedroc -`--agent-collaboration` (string) +`--agent-id` (string) @@ -109 +109,13 @@ See also: [AWS API Documentation](https://docs.aws.amazon.com/goto/WebAPI/bedroc -> The agent’s collaboration role. +> The unique identifier of the agent. + +`--agent-name` (string) + +> Specifies a new name for the agent. + +`--instruction` (string) + +> Specifies new instructions that tell the agent what it should do and how it should interact with users. + +`--foundation-model` (string) + +> The identifier for the model that you want to be used for orchestration by the agent you create. @@ -111 +123 @@ See also: [AWS API Documentation](https://docs.aws.amazon.com/goto/WebAPI/bedroc -> Possible values: +> The `modelId` to provide depends on the type of model or throughput that you use: @@ -113,3 +125,5 @@ See also: [AWS API Documentation](https://docs.aws.amazon.com/goto/WebAPI/bedroc -> * `SUPERVISOR` -> * `SUPERVISOR_ROUTER` -> * `DISABLED` +> * If you use a base model, specify the model ID or its ARN. For a list of model IDs for base models, see [Amazon Bedrock base model IDs (on-demand throughput)](https://docs.aws.amazon.com/bedrock/latest/userguide/model-ids.html#model-ids-arns) in the Amazon Bedrock User Guide. +> * If you use an inference profile, specify the inference profile ID or its ARN. For a list of inference profile IDs, see [Supported Regions and models for cross-region inference](https://docs.aws.amazon.com/bedrock/latest/userguide/cross-region-inference-support.html) in the Amazon Bedrock User Guide. +> * If you use a provisioned model, specify the ARN of the Provisioned Throughput. For more information, see [Run inference using a Provisioned Throughput](https://docs.aws.amazon.com/bedrock/latest/userguide/prov-thru-use.html) in the Amazon Bedrock User Guide. +> * If you use a custom model, first purchase Provisioned Throughput for it. Then specify the ARN of the resulting provisioned model. For more information, see [Use a custom model in Amazon Bedrock](https://docs.aws.amazon.com/bedrock/latest/userguide/model-customization-use.html) in the Amazon Bedrock User Guide. +> * If you use an [imported model](https://docs.aws.amazon.com/bedrock/latest/userguide/model-customization-import-model.html) , specify the ARN of the imported model. You can get the model ARN from a successful call to [CreateModelImportJob](https://docs.aws.amazon.com/bedrock/latest/APIReference/API_CreateModelImportJob.html) or from the Imported models page in the Amazon Bedrock console. @@ -119,3 +133 @@ See also: [AWS API Documentation](https://docs.aws.amazon.com/goto/WebAPI/bedroc -`--agent-id` (string) - -> The unique identifier of the agent. +`--description` (string) @@ -123 +135 @@ See also: [AWS API Documentation](https://docs.aws.amazon.com/goto/WebAPI/bedroc -`--agent-name` (string) +> Specifies a new description of the agent. @@ -125 +137 @@ See also: [AWS API Documentation](https://docs.aws.amazon.com/goto/WebAPI/bedroc -> Specifies a new name for the agent. +`--orchestration-type` (string) @@ -127 +139,7 @@ See also: [AWS API Documentation](https://docs.aws.amazon.com/goto/WebAPI/bedroc -`--agent-resource-role-arn` (string) +> Specifies the type of orchestration strategy for the agent. This is set to `DEFAULT` orchestration type, by default. +> +> Possible values: +> +> * `DEFAULT` +> * `CUSTOM_ORCHESTRATION` +> @@ -129 +146,0 @@ See also: [AWS API Documentation](https://docs.aws.amazon.com/goto/WebAPI/bedroc -> The Amazon Resource Name (ARN) of the IAM role with permissions to invoke API operations on the agent. @@ -163 +180 @@ JSON Syntax: -`--customer-encryption-key-arn` (string) +`--idle-session-ttl-in-seconds` (integer) @@ -165 +182,3 @@ JSON Syntax: -> The Amazon Resource Name (ARN) of the KMS key with which to encrypt the agent. +> The number of seconds for which Amazon Bedrock keeps information about a user’s conversation with the agent. +> +> A user interaction remains active for the amount of time specified. If no conversation occurs during this time, the session expires and Amazon Bedrock deletes any data provided before the timeout. @@ -167 +186 @@ JSON Syntax: -`--description` (string) +`--agent-resource-role-arn` (string) @@ -169 +188 @@ JSON Syntax: -> Specifies a new description of the agent. +> The Amazon Resource Name (ARN) of the IAM role with permissions to invoke API operations on the agent. @@ -171 +190 @@ JSON Syntax: -`--foundation-model` (string) +`--customer-encryption-key-arn` (string) @@ -173 +192,5 @@ JSON Syntax: -> The identifier for the model that you want to be used for orchestration by the agent you create. +> The Amazon Resource Name (ARN) of the KMS key with which to encrypt the agent. + +`--prompt-override-configuration` (structure) + +> Contains configurations to override prompts in different parts of an agent sequence. For more information, see [Advanced prompts](https://docs.aws.amazon.com/bedrock/latest/userguide/advanced-prompts.html) . @@ -175 +198 @@ JSON Syntax: -> The `modelId` to provide depends on the type of model or throughput that you use: +> promptConfigurations -> (list) @@ -177,5 +200,70 @@ JSON Syntax: -> * If you use a base model, specify the model ID or its ARN. For a list of model IDs for base models, see [Amazon Bedrock base model IDs (on-demand throughput)](https://docs.aws.amazon.com/bedrock/latest/userguide/model-ids.html#model-ids-arns) in the Amazon Bedrock User Guide. -> * If you use an inference profile, specify the inference profile ID or its ARN. For a list of inference profile IDs, see [Supported Regions and models for cross-region inference](https://docs.aws.amazon.com/bedrock/latest/userguide/cross-region-inference-support.html) in the Amazon Bedrock User Guide. -> * If you use a provisioned model, specify the ARN of the Provisioned Throughput. For more information, see [Run inference using a Provisioned Throughput](https://docs.aws.amazon.com/bedrock/latest/userguide/prov-thru-use.html) in the Amazon Bedrock User Guide. -> * If you use a custom model, first purchase Provisioned Throughput for it. Then specify the ARN of the resulting provisioned model. For more information, see [Use a custom model in Amazon Bedrock](https://docs.aws.amazon.com/bedrock/latest/userguide/model-customization-use.html) in the Amazon Bedrock User Guide. -> * If you use an [imported model](https://docs.aws.amazon.com/bedrock/latest/userguide/model-customization-import-model.html) , specify the ARN of the imported model. You can get the model ARN from a successful call to [CreateModelImportJob](https://docs.aws.amazon.com/bedrock/latest/APIReference/API_CreateModelImportJob.html) or from the Imported models page in the Amazon Bedrock console. +>> Contains configurations to override a prompt template in one part of an agent sequence. For more information, see [Advanced prompts](https://docs.aws.amazon.com/bedrock/latest/userguide/advanced-prompts.html) . +>> +>> (structure) +>> +>>> Contains configurations to override a prompt template in one part of an agent sequence. For more information, see [Advanced prompts](https://docs.aws.amazon.com/bedrock/latest/userguide/advanced-prompts.html) . +>>> +>>> promptType -> (string) +>>> +>>>> The step in the agent sequence that this prompt configuration applies to. +>>> +>>> promptCreationMode -> (string) +>>> +>>>> Specifies whether to override the default prompt template for this `promptType` . Set this value to `OVERRIDDEN` to use the prompt that you provide in the `basePromptTemplate` . If you leave it as `DEFAULT` , the agent uses a default prompt template. +>>> +>>> promptState -> (string) +>>> +>>>> Specifies whether to allow the agent to carry out the step specified in the `promptType` . If you set this value to `DISABLED` , the agent skips that step. The default state for each `promptType` is as follows. +>>>> +>>>> * `PRE_PROCESSING` – `DISABLED` +>>>> * `ORCHESTRATION` – `ENABLED` +>>>> * `KNOWLEDGE_BASE_RESPONSE_GENERATION` – `ENABLED` +>>>> * `POST_PROCESSING` – `DISABLED` +>>>> + +>>> +>>> basePromptTemplate -> (string) +>>> +>>>> Defines the prompt template with which to replace the default prompt template. You can use placeholder variables in the base prompt template to customize the prompt. For more information, see [Prompt template placeholder variables](https://docs.aws.amazon.com/bedrock/latest/userguide/prompt-placeholders.html) . For more information, see [Configure the prompt templates](https://docs.aws.amazon.com/bedrock/latest/userguide/advanced-prompts-configure.html) . +>>> +>>> inferenceConfiguration -> (structure) +>>> +>>>> Contains inference parameters to use when the agent invokes a foundation model in the part of the agent sequence defined by the `promptType` . For more information, see [Inference parameters for foundation models](https://docs.aws.amazon.com/bedrock/latest/userguide/model-parameters.html) . +>>>> +>>>> temperature -> (float) +>>>> +>>>>> The likelihood of the model selecting higher-probability options while generating a response. A lower value makes the model more likely to choose higher-probability options, while a higher value makes the model more likely to choose lower-probability options. +>>>> +>>>> topP -> (float) +>>>> +>>>>> While generating a response, the model determines the probability of the following token at each point of generation. The value that you set for `Top P` determines the number of most-likely candidates from which the model chooses the next token in the sequence. For example, if you set `topP` to 0.8, the model only selects the next token from the top 80% of the probability distribution of next tokens. +>>>> +>>>> topK -> (integer) +>>>> +>>>>> While generating a response, the model determines the probability of the following token at each point of generation. The value that you set for `topK` is the number of most-likely candidates from which the model chooses the next token in the sequence. For example, if you set `topK` to 50, the model selects the next token from among the top 50 most likely choices. +>>>> +>>>> maximumLength -> (integer) +>>>> +>>>>> The maximum number of tokens to allow in the generated response. +>>>> +>>>> stopSequences -> (list) +>>>> +>>>>> A list of stop sequences. A stop sequence is a sequence of characters that causes the model to stop generating the response. +>>>>> +>>>>> (string) +>>> +>>> parserMode -> (string) +>>> +>>>> Specifies whether to override the default parser Lambda function when parsing the raw foundation model output in the part of the agent sequence defined by the `promptType` . If you set the field as `OVERRIDDEN` , the `overrideLambda` field in the [PromptOverrideConfiguration](https://docs.aws.amazon.com/bedrock/latest/APIReference/API_agent_PromptOverrideConfiguration.html) must be specified with the ARN of a Lambda function. +>>> +>>> foundationModel -> (string) +>>> +>>>> The agent’s foundation model. +>>> +>>> additionalModelRequestFields -> (document) +>>> +>>>> If the Converse or ConverseStream operations support the model, `additionalModelRequestFields` contains additional inference parameters, beyond the base set of inference parameters in the `inferenceConfiguration` field. +>>>> +>>>> For more information, see _Inference request parameters and response fields for foundation models_ in the Amazon Bedrock user guide. +> +> overrideLambda -> (string) @@ -182,0 +271,27 @@ JSON Syntax: +>> The ARN of the Lambda function to use when parsing the raw foundation model output in parts of the agent sequence. If you specify this field, at least one of the `promptConfigurations` must contain a `parserMode` value that is set to `OVERRIDDEN` . For more information, see [Parser Lambda function in Amazon Bedrock Agents](https://docs.aws.amazon.com/bedrock/latest/userguide/lambda-parser.html) . + +JSON Syntax: + + + { + "promptConfigurations": [ + { + "promptType": "PRE_PROCESSING"|"ORCHESTRATION"|"POST_PROCESSING"|"KNOWLEDGE_BASE_RESPONSE_GENERATION"|"MEMORY_SUMMARIZATION", + "promptCreationMode": "DEFAULT"|"OVERRIDDEN", + "promptState": "ENABLED"|"DISABLED", + "basePromptTemplate": "string", + "inferenceConfiguration": { + "temperature": float, + "topP": float,