Output Configurationsare rather simple as they contain prepared sentences that the Chatbot should reply to the user (depending on the
actionscoming from the
outputSet, which can contain one or more output objects.
actions" coming from the
Behavior Rules. If a rule succeeds, the defined action will be stored in the conversation memory.
action key. You can define multiple
output objects, which represent separate chat bubbles on the client side. If more than one
valueAlternativesis defined, one will be picked randomly. If this
outputwill be triggered again in a future
conversationStep, then another
outputof this array will be favored in order to avoid repetition. (If all available
outputshave been selected, it is randomized again like in the beginning). The
typeis mainly there to be able to distinguish the type of output on the client side (e.g.
QuickReply objects. Each
objectmust contain a value, which is the text that should be displayed to the user (e.g. as button) in the conversation flow. The
optional, you can define one or more comma separated expressions that define the meaning of this
expressionswill be temporarily taken into account in the
semantic parserin the next
conversationStep. So if a user chooses one of the quick replies, the parser would recognize them (even if not defined in any of the
dictionariesexplicitly) and resolve them with the
expressionsdefined within this quick reply.
actionshould have occurred within that
conversationin order to be selected as
outputto the user (thus, if
1, it would be chosen if the action occurs for the second time)