I'm building a chatbot with Facebook Messenger and Google Dialogflow. In messenger there is a commonly used sticker (a big blue thumbs up) which is basically a picture. For now the chatbot cant recognize the stickers url or id. Could anyone help me?
My suggestion here is to transform the receiving of a sticker in whatever your middleman API is that connects Facebook Messenger to Dialogflow. This echoes the pattern many Phone IVRs do when a user presses a button - it simply transforms that input into text such as DTMF Zero to hand to the detect intent request. You could similarly transform sending a sticker as Sticker and use that as your training phrase.
Related
Good evening!
Everything is configured with whatsapp.
I use auto reply app and dialogFlow to make a little robot that automatically responds to certain things already ordered on whatsapp. The problem is that I can only use text as an answer; I would like from dialogFlow to respond with an image. Maybe should I use custom payload?
I'm building a chatbot with Telegram and Google Dialogflow. When I integrate Dialogflow into Telegram via the Dialogflow "Integrations" tab, Dialogflow registers as a Webbhook service to intercept all received Telegram messages. Unfortunately, I cannot act on non-text messages like stickers, images and Telegram payment checkout messages.
I wish Dialogflow would forward all the received messages to my custom fulfillment webhook in the Fallback intent. In my webhook, I would be able to parse the received body and act on the unsupported telegram messages accordingly.
I know that there is a FACEBOOK_MEDIA event in Dialogflow. This event is fired when an image is sent via a Facebook messenger to Dialogflow. Is there something like a TELEGRAM_MEDIA or even a TELEGRAM_UNSUPPORTED event available?
I would really like to be able to act on more than just text messages in Dialogflow.
Do I need to add another layer between Telegram and Dialogflow to be able to act on all Telegram messages?
What I have analyzed so far:
I forward all Google Dialogflow interaction logs to Google Cloud stackdriver. It seems as if non-text messages are completely ignored by Dialogflow. I see no log entry at all when I send a non-text message to my telegram bot. On the other hand, when I send a text, the log and its JSON payload appears immediately in the stackdriver.
I created a fallback intent in Dialogflow and enabled "Enable webhook call for this intent" in the Fulfillment section. Unfortunately, my fulfillment function doesn't fire on any non-text events. Dialogflow blocks it in the first place.
For future reference, I will try to give a possible, but not an out-of-the-box solution to my own question. If someone has a better solution, this would be great.
It seems to me, that at the moment of writing this, a full interaction experience is only possible by implementing an intermediate layer between Telegram and Dialogflow. Telegram might contact this intermediate layer, which processes the received message and uses the Dialogflow SDK/API for the Google NLP goodness. For the (not yet) supported Telegram messages this intermediate layer must implement its own logic.
Currently, there seems to be no way to handle non-telegram text messages via dialogflow, however there is an open report about it here if it may interest https://issuetracker.google.com/issues/157202508
i have a Use Case where i need to receive image as input from user in dialogflow chatbot. This images is require to send in webhook request to rest end point as fulfillment.
I couldn't find anything which resembles to my requirement and also not sure whether it is supported in dialogflow or not.
Thanks in advance!
Dialogflow cannot take an image as input and map it to an intent directly. However, what you can do is process that image and send some text to dialogflow which will trigger specific intent and then proceed to perform the desired action.
You need to have a bridge between your user agent and Dialogflow, which will handle all the text/image request. It will do all the pre-processing and then call Dialogflow.
In this way, you need to send message to the messenger user using it's API's and call dialogflow using API/SDK as well.
Hope it helps.
I am using facebook messenger bot buliding with Nodejs. Can I disable text input using an API when the bot sends a message within a button? Is there any strategy possible when the bot only the message, input remains enabled and disabled when sends buttons/quick_replies?
Let me some add picture below to make my query most clear and
I need text input disabled where placeholder "type a message is written"
Unfortunately, this is not possible with Facebook Messenger. As suggested by Milton, you should validate incoming text and decide if the user meant certain input. You should be aware of typos and case however.
In my experience, when we don't get the user input we repeat the question with explanation and give quick replies again.
In Facebook's documentation they refer to wit.ai Bot Engine, but I can't find anywhere online where its explained how to connect the Story that you build in Wit with your Facebook Messenger App?
Wit.ai needs an input - user input. Sentence, phrase, word - to give you back the analysed results.
So first when you say "your Facebook Messenger app" - you need to make sure you are handling the messenger part by itself: have a code in your language of preference running on the server\your laptop which can receive the text which is sent to the messenger account on Facebook.
When you get that working, you will have to use one of Wit.ai libraries for the code language you are using to pass that phrase you receive from the user chatting through the messenger to Wit.ai "library" which will communicate it "to the wit.ai stories" you have and get the result from them.
For example for Python:
Library to handle FB Messenger chatting
Wit.ai library to pass the user input "to stories and get result"
You can integrate Wit to any messaging API. Using the Messenger Send/Receive API for example, you will be able to get and receive messages from/to Messenger users. Wit.ai can then parse the messages and predict the next response.
Here is an example in Node js: https://github.com/wit-ai/node-wit/blob/master/examples/messenger.js
I reviewed the latest updates on wit.ai. It seems that Wit.ai does not have an in-built integration with Facebook Messenger. That is, you can't plug it into Facebook Messenger directly by using the page access tokens etc.
What you'll need to do instead is set up a webhook where Messenger will send callbacks with the details of the user's message. If you want you can enable Facebook's in-built NLP too.
Then inside your webhook, send a call to Wit.ai, and get its output in JSON. Then you must process the JSON and send a reply back to the customer using a Sendmessage API call.
It's a bit long-winded, but if you have this setup, you can potentially use any AI engine in the backend. Including wit.ai or dialogflow.