This product is not supported for your selected Datadog site. ().
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_prompt

account_id

Type: STRING

arn

Type: STRING
Provider name: arn
Description: The Amazon Resource Name (ARN) of the prompt or the prompt version (if you specified a version in the request).

created_at

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

customer_encryption_key_arn

Type: STRING
Provider name: customerEncryptionKeyArn
Description: The Amazon Resource Name (ARN) of the KMS key that the prompt is encrypted with.

default_variant

Type: STRING
Provider name: defaultVariant
Description: The name of the default variant for the prompt. This value must match the name field in the relevant PromptVariant object.

description

Type: STRING
Provider name: description
Description: The descriptino of the prompt.

id

Type: STRING
Provider name: id
Description: The unique identifier of the prompt.

name

Type: STRING
Provider name: name
Description: The name of the prompt.

tags

Type: UNORDERED_LIST_STRING

updated_at

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

variants

Type: UNORDERED_LIST_STRUCT
Provider name: variants
Description: A list of objects, each containing details about a variant of the prompt.

  • additional_model_request_fields
    Type: STRUCT
    Provider name: additionalModelRequestFields
    Description: Contains model-specific inference configurations that aren’t in the inferenceConfiguration field. To see model-specific inference parameters, see Inference request parameters and response fields for foundation models.

  • gen_ai_resource
    Type: STRUCT
    Provider name: genAiResource
    Description: Specifies a generative AI resource with which to use the prompt.

    • agent
      Type: STRUCT
      Provider name: agent
      Description: Specifies an Amazon Bedrock agent with which to use the prompt.
      • agent_identifier
        Type: STRING
        Provider name: agentIdentifier
        Description: The ARN of the agent with which to use the prompt.

  • inference_configuration
    Type: STRUCT
    Provider name: inferenceConfiguration
    Description: Contains inference configurations for the prompt variant.

    • text
      Type: STRUCT
      Provider name: text
      Description: Contains inference configurations for a text prompt.
      • max_tokens
        Type: INT32
        Provider name: maxTokens
        Description: The maximum number of tokens to return in the response.
      • stop_sequences
        Type: UNORDERED_LIST_STRING
        Provider name: stopSequences
        Description: A list of strings that define sequences after which the model will stop generating.
      • temperature
        Type: FLOAT
        Provider name: temperature
        Description: Controls the randomness of the response. Choose a lower value for more predictable outputs and a higher value for more surprising outputs.
      • top_p
        Type: FLOAT
        Provider name: topP
        Description: The percentage of most-likely candidates that the model considers for the next token.

  • metadata
    Type: UNORDERED_LIST_STRUCT
    Provider name: metadata
    Description: An array of objects, each containing a key-value pair that defines a metadata tag and value to attach to a prompt variant.

    • key
      Type: STRING
      Provider name: key
      Description: The key of a metadata tag for a prompt variant.
    • value
      Type: STRING
      Provider name: value
      Description: The value of a metadata tag for a prompt variant.

  • model_id
    Type: STRING
    Provider name: modelId
    Description: The unique identifier of the model or inference profile with which to run inference on the prompt.

  • name
    Type: STRING
    Provider name: name
    Description: The name of the prompt variant.

  • template_configuration
    Type: STRUCT
    Provider name: templateConfiguration
    Description: Contains configurations for the prompt template.

    • chat
      Type: STRUCT
      Provider name: chat
      Description: Contains configurations to use the prompt in a conversational format.
      • input_variables
        Type: UNORDERED_LIST_STRUCT
        Provider name: inputVariables
        Description: An array of the variables in the prompt template.
        • name
          Type: STRING
          Provider name: name
          Description: The name of the variable.
      • messages
        Type: UNORDERED_LIST_STRUCT
        Provider name: messages
        Description: Contains messages in the chat for the prompt.
        • content
          Type: UNORDERED_LIST_STRUCT
          Provider name: content
          Description: The content in the message.
          • cache_point
            Type: STRUCT
            Provider name: cachePoint
            Description: Creates a cache checkpoint within a message.
            • type
              Type: STRING
              Provider name: type
              Description: Indicates that the CachePointBlock is of the default type
          • text
            Type: STRING
            Provider name: text
            Description: The text in the message.
        • role
          Type: STRING
          Provider name: role
          Description: The role that the message belongs to.
      • system
        Type: UNORDERED_LIST_STRUCT
        Provider name: system
        Description: Contains system prompts to provide context to the model or to describe how it should behave.
        • cache_point
          Type: STRUCT
          Provider name: cachePoint
          Description: Creates a cache checkpoint within a tool designation
          • type
            Type: STRING
            Provider name: type
            Description: Indicates that the CachePointBlock is of the default type
        • text
          Type: STRING
          Provider name: text
          Description: The text in the system prompt.
      • tool_configuration
        Type: STRUCT
        Provider name: toolConfiguration
        Description: Configuration information for the tools that the model can use when generating a response.
        • tool_choice
          Type: STRUCT
          Provider name: toolChoice
          Description: Defines which tools the model should request when invoked.

          • any
            Type: STRUCT
            Provider name: any
            Description: Defines tools, at least one of which must be requested by the model. No text is generated but the results of tool use are sent back to the model to help generate a response.

          • auto
            Type: STRUCT
            Provider name: auto
            Description: Defines tools. The model automatically decides whether to call a tool or to generate text instead.

          • tool
            Type: STRUCT
            Provider name: tool
            Description: Defines a specific tool that the model must request. No text is generated but the results of tool use are sent back to the model to help generate a response.

            • name
              Type: STRING
              Provider name: name
              Description: The name of the tool.
        • tools
          Type: UNORDERED_LIST_STRUCT
          Provider name: tools
          Description: An array of tools to pass to a model.
          • cache_point
            Type: STRUCT
            Provider name: cachePoint
            Description: Creates a cache checkpoint within a tool designation
            • type
              Type: STRING
              Provider name: type
              Description: Indicates that the CachePointBlock is of the default type
          • tool_spec
            Type: STRUCT
            Provider name: toolSpec
            Description: The specification for the tool.
            • description
              Type: STRING
              Provider name: description
              Description: The description of the tool.
            • input_schema
              Type: STRUCT
              Provider name: inputSchema
              Description: The input schema for the tool.
              • json
                Type: STRUCT
                Provider name: json
                Description: A JSON object defining the input schema for the tool.
            • name
              Type: STRING
              Provider name: name
              Description: The name of the tool.
    • text
      Type: STRUCT
      Provider name: text
      Description: Contains configurations for the text in a message for a prompt.
      • cache_point
        Type: STRUCT
        Provider name: cachePoint
        Description: A cache checkpoint within a template configuration.
        • type
          Type: STRING
          Provider name: type
          Description: Indicates that the CachePointBlock is of the default type
      • input_variables
        Type: UNORDERED_LIST_STRUCT
        Provider name: inputVariables
        Description: An array of the variables in the prompt template.
        • name
          Type: STRING
          Provider name: name
          Description: The name of the variable.
      • text
        Type: STRING
        Provider name: text
        Description: The message for the prompt.

  • template_type
    Type: STRING
    Provider name: templateType
    Description: The type of prompt template to use.

version

Type: STRING
Provider name: version
Description: The version of the prompt.