Amazon HealthLake

{'AgentResponse': {'EndOfOutputEvent': {'ConversationId': 'string',
                                        'FinalResponseMessage': 'string',
                                        'Options': ['string']},
                   'ErrorEvent': {'Error': 'InternalServerException | '
                                           'ResourceNotFoundException | '
                                           'ValidationException | '
                                           'AccessDeniedException | '
                                           'ThrottlingException',
                                  'Message': 'string'},
                   'HeartbeatEvent': {},
                   'ProgressEvent': {'Message': 'string'},
                   'TextMessageEvent': {'Message': 'string'}}}

Updates a data transformation profile using chat-based interaction with an agent. Supports multi-turn conversations for iteratively customizing profiles.

See also: AWS API Documentation

Request Syntax

client.update_profile_with_agent(
    ProfileId='string',
    InputMessage={
        'Body': 'string',
        'Type': 'normal'|'confirmation_response'
    },
    ConversationId='string'
)

type ProfileId:

string

param ProfileId:

[REQUIRED]

The unique identifier of the profile to update via the agent.

type InputMessage:

dict

param InputMessage:

[REQUIRED]

The message to send to the agent.

• Body (string) -- [REQUIRED]

  The text of your message to the agent.

• Type (string) -- [REQUIRED]

  The type of input message, which determines how the agent processes your request. Valid values:

  • normal: A regular message to the agent.

  • confirmation_response: A response to a confirmation request from the agent.

type ConversationId:

string

param ConversationId:

The conversation identifier for multi-turn interactions. Omit to start a new conversation.

rtype:

dict

returns:

The response of this operation contains an :class:`.EventStream` member. When iterated the :class:`.EventStream` will yield events based on the structure below, where only one of the top level keys will be present for any given event.

Response Syntax

{
    'AgentResponse': EventStream({
        'TextMessageEvent': {
            'Message': 'string'
        },
        'ProgressEvent': {
            'Message': 'string'
        },
        'HeartbeatEvent': {},
        'ErrorEvent': {
            'Error': 'InternalServerException'|'ResourceNotFoundException'|'ValidationException'|'AccessDeniedException'|'ThrottlingException',
            'Message': 'string'
        },
        'EndOfOutputEvent': {
            'FinalResponseMessage': 'string',
            'Options': [
                'string',
            ],
            'ConversationId': 'string'
        }
    })
}

Response Structure

• (dict) --

  The response from the UpdateProfileWithAgent operation.

  • AgentResponse (:class:`.EventStream`) --

    The streaming response from the agent.

    • TextMessageEvent (dict) --

      An incremental text update from the agent.

      • Message (string) --

        An incremental text update from the agent.

    • ProgressEvent (dict) --

      An incremental progress update from the agent.

      • Message (string) --

        An incremental progress update message by the agent

    • HeartbeatEvent (dict) --

      Periodically emitted event to keep the connection alive.

    • ErrorEvent (dict) --

      An exception encountered while serving the request.

      • Error (string) --

        The type of the exception.

      • Message (string) --

        The exception message.

    • EndOfOutputEvent (dict) --

      The final event in the response stream from the agent during chat-based profile customization. The caller can assume that the stream has ended upon receiving this event.

      • FinalResponseMessage (string) --

        The final response message from the agent.

      • Options (list) --

        The response options that you can use to easily answer follow-up questions from the agent.

        • (string) --

      • ConversationId (string) --

        The conversation ID of the request. You can use this ID to continue the profile mapping based on this request's context at a later time.