I have developed a complex dialogflow bot, which uses complex dialogs to get data from user and then store it in database. And then give responses to users by querying db.
Can i use the same logic/webhooks/code to call from alexa skill? I don't want to write such a complex logic again for alexa skill.
What I want is whenever an alexa intent is called by user, i want to transfer that intent to my dialogflow webhook to handle it. Is it possible? If so then can you please provide any documentation/examples/tutorials ets.
My dialogflow model consists of 4 slot types:
Date
Number
any
some custom slots
I am certain this is not possible straight away as the REST API of Dialogflow will be different from that of Alexa. Also, Alexa is not fully supported for integration in Dialogflow like Facebook or Slack. If your code is well written and business logic is separate from the platform/request/response mapping then you will be able to use the same business logic in your Alexa webhook code. You just need to write the code for consuming the REST API of Alexa in this case.
Yes, this is possible. While Dialogflow and Alexa have different webhook JSON formats, fundamentally they both do the same thing. You will need to handle parsing the JSON to get what you need, and then formatting the response, so each uses their particular format - but the logic that you are using should still be sound and available to both.
Dialogflow lets you export the model into an Alexa compatible format that you can paste into the Alexa Skills Kit. This helps at least a bit.
Related
I am trying to wrap my head around using Dialogflow for developing and integrating an SMS chatbot with our custom CRM. The creation of an Intent is pretty powerful and straight forward. However, I am trying to understand best practices for something. If I have an intent used to return the price of a service at a certain location, I can model that very easily within dialog flow. However, when an SMS message comes in, it will be from a new customer or a known existing customer for a certain location. For existing customers, we already know the location and therefore don't want them to have to specify the location value in the intent. Prior to sending the inbound SMS message to the client API to match the intent, how can I pre-set the "location" parameter value in the intent so it does exists even if that inbound SMS message did not include it? For example a known customer in Dallas would just have to say "how much is a xxx" instead of "how much is a xxx in Dallas".
Can you use the API to set a parameter value prior to calling the API to try and match the intent? If so, how do you get do that without a session ID? The reason the "location" is needed is because when we get to the fulfillment, the prices for the same service are different based on the location so I will need to be known but we don't want to make existing customers say the location.
Maybe another option is to have a Location intent with an event that we can trigger through the API. this would have an output context on it called location and fulfillment that sets the parameter value. But even then I struggle with understanding how to pass in values like location, phone number, etc into dialogflow from the calling application so dialogflow has those parameter values to use in fulfillment.
Reading documentation, watching videos and starting to test client API v2
This is certainly possible. What you would want to do is use the Dialogflow API for this. Here you can find the languages for which Google has created client libraries: https://cloud.google.com/dialogflow/docs/reference/libraries/overview
As soon as you have any 'if' in your code you should use the fulfillment: https://dialogflow.com/docs/fulfillment
How I would handle this:
Client sends SMS
You check in your back-end if this user is known. If known -> don't ask location, else you ask the location
Match the user query against the Dialogflow client library
Dialogflow will return the intent if (any) is matched
You should define and implement any logic before calling the Dialogflow library.
I'm back again with a question about NLP. I made my own back-end, which on one side can connect to websites, the Google Assistant and Facebook Messenger, and on the other end to Dialogflow. On the side, is logs interactions and does some other database stuff.
Now, I'm trying to connect this back-end to Alexa. I made a project which calls my endpoint. This project has one intent, which has a paramater which should get the raw user input, send it to my back-end, process it, parse and send the response to get back. I feel like there is not a real way to collect and send the raw user input, so I can process it myself (on Dialogflow) instead of using the Amazon way of mapping intents and such.
I know Dialogflow can export to Alexa, but this is not an option for me. I really hope one of you can point me in the right direction.
I just need a way to collect the raw user input, and respond in an Alexa accepted response format.
For Actions on Google for example, I'm using a Custom Project Action Package.
Thanks a lot in advace!
To accept or get any user input, you can use sys.any in google assistant and AMAZON.SearchQuery in AMAZON ALEXA.
In Alexa, You have to add the carrier phrase to use AMAZON.SearchQuery. You can't combine any other slot with AMAZON.SearchQuery.
So there are also some limitations. I hope this answer will help you.
I'm trying to understand phone gateway implementation in dialogflow but dont see much of documentation for how to handle in backend code using nodejs or any third party apps like twilio,viber etc.
My doubt is whether is it available for now or not and is their any documents regarding phone gateway which can be done through google mini device for voice calling?
Please correct me if I'm wrong about what I understand.
Dialogflow phone gateway is a great feature provided by Dialogflow. It is simple to activate. Just follow the instructions in the Integrations tab.
All your intents and webhook will just work fine as they do in the bot. But the response type is little different from other platforms. So check that once before building responses.
It only supports speech response that is returned to the user in the phone call.
as per Google documentation, it uses the V2Beta1 version of the API. It means you have all the normal fields of the V2 API inside the body and parameters of the webhook call (+1 "MlEnabled" field, but not important for the telefony gateway). See more here https://dialogflow.com/docs/reference/v2-beta-v2-migration-guide-api . I have also been searching for extra fields like the phone number who is calling (to use it in backend tasks like CRM lookup), but this is not there yet (I analysed the JSON response, there is nothing so far).
Some tip to integrate with Twilio (my use case too) : you can perfectly route the twilio call to a simple Twilio callflow (like checking for opening hours) then to the incoming DialogFlow number (as you would do with the black number of an IVR provider) and transfer the Dialogflow call to another incoming phone numbers (controlled by Twilio) where you do the rest of the callflow (typically the skill based routing).
Example : after the call, Twilio checks for opening hours > OK > forward to Dialogflow phone nbr for intent recognition > identify intent nbr1 > route to phone nbr1 of Twilio which is connected to a routing/queue to agent group nbr1 (idem for intents nbr2, 3, 4 ...).
In this example, some useful fields are missing in the JSON like the phone nbr of the caller(CLI), the phone number dialed, eventually some UUI ISDN field, ... that you would like to use for a CRM lookup and CTI popup. Let's keep an eye on it and maybe Google will add it in V2beta2 ...?
We have a framework that implements chatbot / voice assistant logic for handling complex conversations in the health domain. Everything is implemented on our server side. This gives us full control of how responses are generated.
The channel (such as Alexa or Facebook Messenger cloud) calls our webhook:
When user messages, the platform sends these to our webhook: hashed user id, message text (chat message or transcribed voice)
Our webhook responds with the appropriately structured response, which includes text to be displayed, spoken, possibly choice buttons and some images etc. It also includes a flag whether the current session has finished or user input is expected.
Integrating a new channel involves conversion of the response returned into the form expected by a channel and setting some flags (has voice, has display etc.).
This simple framework has worked so far for Facebook Messenger, Cortana, Alexa (a little bit of hacking was needed to abandon it's intent and slot recognition), our web chatbot.
We wanted to write a thin layer of support for Google Assistant action.
Is there any way of passing all the input from Assistant user intact into a webhook such as the one described above and taking full control of the way responses are generated and the end of conversation is determined?
I'd rather not delve into those cumbersome ways of API.AI of structuring a conversation which seems good for a trivial scenarios such as ordering an Uber but seems very bad for longer conversation.
Since you already have a Natural Language Understanding layer for your system, you don't need API.AI/Dialogflow, and you can skip this layer completely. (The NLU is useful, even for large and extensive conversations, but doesn't make sense in your case where you've already defined the conversation through other means.)
You'll need to use the Actions SDK (sometimes known as actions.json after the configuration file it uses) to define triggering phrases, but after that you'll get all the text that the user says as part of your conversation through a webhook that delivers JSON to you. You'll reply with JSON that contains the text/audio response, images on cards, possibly suggestion chips, etc.
I've made a chatbot who can talk to people and make a normal conversation. I want to develop that chatbot so that user is able to, say order a pizza from Dominoz.com or Book a ticket on expedia or add something to cart in ebay.
I've made the bot using Google's Api.Ai (diagflow). How can I integrate it with any site performing some kind of transaction. Answer with an example booking/ordering site would be highly appreciated.
Just for additional info: I think it is possible by that webhook option in fulfillment section. But how exactly? How to implement it?
You should check if there are APIs available for ordering/booking through Expedia/eBay. Dominos have exposed their APIs for ordering purposes. Following is the link for bot ordering pizza & node-dominos-api
https://hellotars.com/bot-examples/featured/pizza-ordering-chatbot/
http://riaevangelist.github.io/node-dominos-pizza-api/
https://www.youtube.com/watch?v=F68HtCtJbGA
Webhook in Dialogflow is something where your actual logic lies. You can write it in any language you're confident of & host it somewhere for Dialogflow to communicate with it. There are 2 API references v1 & v2. Your web service receives a POST request from Dialogflow. Your request/response to/from webhook should include mandatory fields mentioned at following links:
https://dialogflow.com/docs/fulfillment
https://dialogflow.com/docs/reference/agent/query