Output Configuration

Version: 4.0.x

Output Configurations are rather simple as they contain prepared sentences the Chatbot should reply to the user (depending on the actions coming from the behavior rules).

Simple Output Configuration looks like this:

Simple Output Configuration

{
    "outputs" : [ 
        {
            "key" : "welcome",
            "outputValues" : [ 
                "Welcome! I am E.D.D.I."
            ]
		}
    ]
}

The configuration contains an array of "outputs", which can contain one or more output objects.

The minimum amount of values that you need to provide in order be functional are key and outputValues

Now let's look at a more complex output configuration file:

Complex Output Configuration

{
    "outputs" : [ 
        {
            "key" : "welcome",
            "outputValues" : [ 
                "Welcome! I am E.D.D.I. How are you doing today?"
            ]
            "occurrence" : 0
        }, 
        {
            "key" : "greet",
            "outputValues" : [ 
                "Hi there! Nice to meet up! :-)",
				"Hello you! It is a pleasure meeting you.. :-)"
            ],
            "occurrence" : 0
        }, 
        {
            "key" : "greet",
            "outputValues" : [ 
                "Did we already say hi ?! Well, twice is better than not at all! ;-)",
				"I like it if people are polite and greet twice, rather than not at all ;-)"
            ],
            "occurrence" : 1
        }, 
        {
            "key" : "say_goodbye",
            "outputValues" : [ 
                "See you soon!"
            ]
        }
    ]
}

key	desciption
key	This will be the "actions" coming from the behavior rules. If a rule succeeds, the defined action will be stored in the conversation memory. Those stored actions will be match with this key
outputValues	This array of outputValues are the output sentences that will be replied back to the user in case the action matched the key. If more than one output is defined, one will be picked randomly. If this output will be triggered again in a future conversation step, then another output of this array will be favored in order to avoid repetition. (If all available outputs have been selected, it is randomized again like in the beginning)
occurrence	How often this action should have occurred within that conversation in order to be selected as output to the user (thus, if value of 1, it would be chosen if the action occurs for the second time)