I am simply asking if there is a way to have dialog flow read text off of a webpage and give answers based on said text? i am trying to get Disney world wait times to be read off of a google home mini
site : https://www.laughingplace.com/w/walt-disney-world/
Related
I have created a simple conversational flow in Dialogflow that accepts various questions and speaks pre-programmed replies, all defined in a series of intents. There are no external hooks etc.
When used on a screen based device (eg. mobile phone) I want to display more text than that which is spoken. (displayText) eg:
User: "What colour is the sky?"
Bot: "Blue" (spoken and displayed on screen). "At night it is black". (Additional information displayed on screen only.)
I want to do the same for each intent.
What is the simplest way of achieving that please? I would prefer to keep most of it in Dialogflow and to write the minimum amount of code possible.
It is ok, I found the solution thanks. In Dialogflow intents under Response there are two tabs, Default and Google Assistant. Under Google Assistant there is an option Customise audio output. When you select that you get two input fields, one for text and one for speech.
So to use the above example under intent training phrase I entered "What colour is the sky?"
Under Default Response I entered "Blue"
Under Google Assistant response, Text Output field I entered: "Blue. At night it is black."
Under Google Assistant response, Speech Output field I entered: "Blue".
It works perfectly in both Google Home (voice only) and Assistant on mobile phone (Speaks "Blue" but displays "Blue. At night it is black.")
It doesn't even seem necessary to enter anything in Default Response. It works fine on Google Home and Assistant on the phone without it. Not sure about other platforms though.
I have made a bot using QnA Maker and Node JS which is running on Skype.
When the user inputs a word which has got multiple matches in FAQ link or document uploaded in QnA Maker, it shows button of choice using QnAMakerTool module from Node. My question is when the multiple matches has same initial words then because of the size of the choice button in Skype the half of the texts get hide. For example, I have three matches like
Whom should I contact for parking?
Whom should I contact for canteen?
Whom should I contact for Stationery?
It shows in Skype as
Whom should I contact for...
Whom should I contact for...
Whom should I contact for...
If the option text is too long then few parts get hidden. What can I do for this?
First of all, there is a limitation on the max characters in Skype, so that's something you will have to live with. However, you can implement some custom logic to change the text being shown.
That current logic that you are seeing is on the QnAMakerTools file.
The way to go here is probably providing your own QnAMakerTools implementation (it needs to follow this interface).
The QnAMakerDialog receives an IQnAMakerOptions parameter. One of the properties of that interface is feedbackLib which basically is the QnAMakerTools instance that the dialog will later use to disambiguate the question as you can see here.
Telegram bot sends me a message with a text snippet, which I want to edit, and send back to the bot for further processing.
Copy and paste takes time. Typing message anew takes time.
Ideally I'd like to press an inline button "Edit" on the bot's message and get the message text appear in my reply input box for editing.(A message id attached to my reply somehow would be a plus).
I tried to use deep linking with parameters other than /start*, but that doesn't seem to work.
Can I use bot API (or any other telegram API) to have text ready for editing in my input box?
It's impossible in official apps yet. Your question is about working with drafts - there are no methods in both API to create them or clear.
Nevertheless, you could fork any official app stored on GiHub and implement what you need if you would prefer a hard way, but compared to that copy/past solution seems much more easier, isn't it?
UPD
I can offer to you a new idea how to solve your problem - hope it will be helpful.
This is about switch_inline_query_current_chat field of InlineKeyboardButton. Just attach an inline button to messages you need to edit. Set a text for this field gotten from recieved message and after pressing you will get this text to your input area. All seems good, but you will take bot's username before the text also.
First of all sorry for my bad English.
Is there a way to search google for the file name.
so a right click menu script that runs google and searches for the file name
the main questions are
is it possible?
which coding language to use?
does it already exist or do i need to make it myself (with help)?
Do you mean filename is a title of a webpage? If so you can use allintitle: keyword:
https://www.google.com/search?q=allintitle:stackoverflow
will search for any page contains stackoverflow in the title.
Or to search within a URL, useallinurl: keyword:
https://www.google.com/search?q=allinurl:stackoverflow
will search for any page contains stackoverflow in the URL.
To search for specific type of file, usefiletype: keyword:
https://www.google.com/search?q=stackoverflow+filetype:pdf
will search for any page contains a PDF document about stackoverflow.
If that is what you mean, then it is possible, and you can use almost any programing language you like.
I am working on an e-learning website and developing code editors for php.
I just want it to be like the Code Editor of W3Schools "Try IT Now".
I want to enter the code in the left side and want to get output in the right side.
As per my analysis, "ACE Code Editor" is the best one for this task, but I am unable to integrate that in my website.
I am trying to explain my problem.
I have created two text area with same CSS property
One is hidden and one is visible
When user type code then both text area get the entered code.
Post getting the PHP code, it need to send to server using AJAX..
Now I am having problem with AJAX. I don't know how to send PHP code to server using Ajax and how to get output in return.
I take reference from here