Cette page n'est pas encore disponible en français, sa traduction est en cours.
Si vous avez des questions ou des retours sur notre projet de traduction actuel, n'hésitez pas à nous contacter.

aws_bedrock_agent

account_id

Type: STRING

agent_arn

Type: STRING
Provider name: agentArn
Description: The Amazon Resource Name (ARN) of the agent.

agent_collaboration

Type: STRING
Provider name: agentCollaboration
Description: The agent’s collaboration settings.

agent_id

Type: STRING
Provider name: agentId
Description: The unique identifier of the agent.

agent_name

Type: STRING
Provider name: agentName
Description: The name of the agent.

agent_resource_role_arn

Type: STRING
Provider name: agentResourceRoleArn
Description: The Amazon Resource Name (ARN) of the IAM role with permissions to invoke API operations on the agent.

agent_status

Type: STRING
Provider name: agentStatus
Description: The status of the agent and whether it is ready for use. The following statuses are possible:

  • CREATING – The agent is being created.
  • PREPARING – The agent is being prepared.
  • PREPARED – The agent is prepared and ready to be invoked.
  • NOT_PREPARED – The agent has been created but not yet prepared.
  • FAILED – The agent API operation failed.
  • UPDATING – The agent is being updated.
  • DELETING – The agent is being deleted.

agent_version

Type: STRING
Provider name: agentVersion
Description: The version of the agent.

client_token

Type: STRING
Provider name: clientToken
Description: A unique, case-sensitive identifier to ensure that the API request completes no more than one time. If this token matches a previous request, Amazon Bedrock ignores the request, but does not return an error. For more information, see Ensuring idempotency.

created_at

Type: TIMESTAMP
Provider name: createdAt
Description: The time at which the agent was created.

custom_orchestration

Type: STRUCT
Provider name: customOrchestration
Description: Contains custom orchestration configurations for the agent.

  • executor
    Type: STRUCT
    Provider name: executor
    Description: The structure of the executor invoking the actions in custom orchestration.
    • lambda
      Type: STRING
      Provider name: lambda
      Description: The Amazon Resource Name (ARN) of the Lambda function containing the business logic that is carried out upon invoking the action.

customer_encryption_key_arn

Type: STRING
Provider name: customerEncryptionKeyArn
Description: The Amazon Resource Name (ARN) of the KMS key that encrypts the agent.

description

Type: STRING
Provider name: description
Description: The description of the agent.

failure_reasons

Type: UNORDERED_LIST_STRING
Provider name: failureReasons
Description: Contains reasons that the agent-related API that you invoked failed.

foundation_model

Type: STRING
Provider name: foundationModel
Description: The foundation model used for orchestration by the agent.

guardrail_configuration

Type: STRUCT
Provider name: guardrailConfiguration
Description: Details about the guardrail associated with the agent.

  • guardrail_identifier
    Type: STRING
    Provider name: guardrailIdentifier
    Description: The unique identifier of the guardrail.
  • guardrail_version
    Type: STRING
    Provider name: guardrailVersion
    Description: The version of the guardrail.

idle_session_ttl_in_seconds

Type: INT32
Provider name: idleSessionTTLInSeconds
Description: 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.

instruction

Type: STRING
Provider name: instruction
Description: Instructions that tell the agent what it should do and how it should interact with users.

memory_configuration

Type: STRUCT
Provider name: memoryConfiguration
Description: Contains memory configuration for the agent.

  • enabled_memory_types
    Type: UNORDERED_LIST_STRING
    Provider name: enabledMemoryTypes
    Description: The type of memory that is stored.
  • session_summary_configuration
    Type: STRUCT
    Provider name: sessionSummaryConfiguration
    Description: Contains the configuration for SESSION_SUMMARY memory type enabled for the agent.
    • max_recent_sessions
      Type: INT32
      Provider name: maxRecentSessions
      Description: Maximum number of recent session summaries to include in the agent’s prompt context.
  • storage_days
    Type: INT32
    Provider name: storageDays
    Description: The number of days the agent is configured to retain the conversational context.

orchestration_type

Type: STRING
Provider name: orchestrationType
Description: Specifies the orchestration strategy for the agent.

prepared_at

Type: TIMESTAMP
Provider name: preparedAt
Description: The time at which the agent was last prepared.

prompt_override_configuration

Type: STRUCT
Provider name: promptOverrideConfiguration
Description: Contains configurations to override prompt templates in different parts of an agent sequence. For more information, see Advanced prompts.

  • override_lambda
    Type: STRING
    Provider name: overrideLambda
    Description: 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.
  • prompt_configurations
    Type: UNORDERED_LIST_STRUCT
    Provider name: promptConfigurations
    Description: Contains configurations to override a prompt template in one part of an agent sequence. For more information, see Advanced prompts.

    • additional_model_request_fields
      Type: STRUCT
      Provider name: additionalModelRequestFields
      Description: 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.

    • base_prompt_template
      Type: STRING
      Provider name: basePromptTemplate
      Description: 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. For more information, see Configure the prompt templates.

    • foundation_model
      Type: STRING
      Provider name: foundationModel
      Description: The agent’s foundation model.

    • inference_configuration
      Type: STRUCT
      Provider name: inferenceConfiguration
      Description: 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.

      • maximum_length
        Type: INT32
        Provider name: maximumLength
        Description: The maximum number of tokens to allow in the generated response.
      • stop_sequences
        Type: UNORDERED_LIST_STRING
        Provider name: stopSequences
        Description: A list of stop sequences. A stop sequence is a sequence of characters that causes the model to stop generating the response.
      • temperature
        Type: FLOAT
        Provider name: temperature
        Description: 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.
      • top_k
        Type: INT32
        Provider name: topK
        Description: 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.
      • top_p
        Type: FLOAT
        Provider name: topP
        Description: 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 80, the model only selects the next token from the top 80% of the probability distribution of next tokens.

    • parser_mode
      Type: STRING
      Provider name: parserMode
      Description: 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 OVERRIDEN, the overrideLambda field in the PromptOverrideConfiguration must be specified with the ARN of a Lambda function.

    • prompt_creation_mode
      Type: STRING
      Provider name: promptCreationMode
      Description: 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.

    • prompt_state
      Type: STRING
      Provider name: promptState
      Description: 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 – ENABLED
      • ORCHESTRATION – ENABLED
      • KNOWLEDGE_BASE_RESPONSE_GENERATION – ENABLED
      • POST_PROCESSING – DISABLED

    • prompt_type
      Type: STRING
      Provider name: promptType
      Description: The step in the agent sequence that this prompt configuration applies to.

Type: UNORDERED_LIST_STRING
Provider name: recommendedActions
Description: Contains recommended actions to take for the agent-related API that you invoked to succeed.

tags

Type: UNORDERED_LIST_STRING

updated_at

Type: TIMESTAMP
Provider name: updatedAt
Description: The time at which the agent was last updated.