im a noob at making chatbots, and Im having some difficulties understanding how to make the bot reply back to queries and intents dynamically. My chatbot depends on replying back meaningful messages, more than fulfilling a request. Im was working with dialogflow but I thought Wit.ai would be more suitable, so I switched recently. But I still cant find how to train the bot to reply using RNN so it can first parse the intents, then reply back based on them. Any suggestions ? Kuddos.
The request flow with wit.ai as follows,
First request is made by the user using the message provider(i.e, facebook messanger, slack, ect...), this request is received by the wit.ai. Then the all the required information is extracted by the wit.ai, then all the request parameters is sent to the webhook you specified in the wit.ai.
In the webhook you process the input parameters and respond to it according to it(e.g: user querying for restaurant search, wit provides the the name of the restaurant, you query data base using the name and prepares the response).
Then the prepared response is sent back to the wit.ai from webhook, then wit delivers your message to the respective user and message provider..
So you no need to train any rnn for responding the user.but if your business logic requires the rnn training you have to do it in the webhook (it's your web server).
You can refer to this link for more info: https://dialogflow.com/docs/fulfillment