I have a mobile native app using Bing Speech & LUIS services. After the intent "text" is received I call my business app API with the intent text.
Basically 2 server calls - one to get the intent the other to my API with the intent.
So, is it possible to call Bing + LUIS and have an event handler on my Azure App Server to receive the intent i.e. without going back to mobile interface and invoking the API call from mobile.
regards
-Ravi
Is there a reason you cannot just route through the server? e.g. the chatbot sends the user's text to the server, and the server calls LUIS, receives and handles the response, then formulate a response to send to the chatbot.
Related
I am using an exteranl API that do some work for 15min, when it finish it will call any URL you define in your initial request to send the results to.
Is it possible for dialogFlow to accept this result in 15min? Is there like a built-in async response handler in DialogFlow?
If you are calling external APIs via webhook, it would be subject to the maximum webhook timeout limit of 30 seconds. After the response timeout is exceeded, Dialogflow invokes a webhook error or timeout built-in event and continues processing as usual. Therefore, Dialogflow would no longer accept webhook responses more than the set timeout limit.
Note that conversational interfaces are meant to be designed as a continuous message exchange between the end user and the app/bot. If your web service requires more time for executing operations in the background and this cannot be optimized, consider redesigning the conversation flow in such a way that end users don't wait for the app/bot to reply for more than the set webhook timeout limit.
If you have your own custom application (integrated using APIs or Client Libraries), you can instead call/invoke the function that needs 15 minutes of work (let’s call this function_1) from your custom application.
Here’s a basic setup:
User enters a query from the interface of your custom application.
Your custom application sends the user query with the Detect Intent
request to the Dialogflow agent (using APIs or Client Libraries).
After your custom application receives a Detect Intent response from
the agent, you can create code to get the intent name or event name
from the detectIntentResponse.queryResult.match.intent.displayName
or match.event response json respectively and then call/invoke
function_1 based on the intent or event matched.
Once function_1 is finished processing, you can either send a direct response to the
user in your custom application’s interface or send a Detect Intent
request to your agent so it matches an Intent and sends the intent
response back to your custom application.
No, it won't be possible as you describe it. The only way to call external services is through webhooks, but these are thought as calls that return a very specific object which Dialogflow then returns as an answer to the user directly, so they are inherently synchronous.
What you could do instead is think of a workaround. I don't know the specific of what service you're calling, but you could set up a small server to handle the webhook response from dialogflow which doesn't do anything except trigger the call to the external api, and when you get the answer you could process it (put the relevant content inside a "fulfilment" object as per Dialogflow specification) and trigger an event in your agent through the dialogflow API.
so the final process could look something like this.
user asks for e.g. "pizza": the right intent is triggered and the route for that intent calls a webhook server
your webhook server receives the call from dialogflow and calls the external api asking for the list of all pizzas ever created. it returns an empty fulfilment to the server
when the webhook server receives the response after 15 mins it triggers an event in the agent (look into the dialogflow api for your programming language of choice: python, node, java) and injects some parameters in the request, which you can then use to form a sentence in the agent
when I was just starting out I found this very useful to get a grasp of what the platform expects you to do in terms of interacting with external services, take a look at the graph especially which I think makes it clearer
I want to utilise Google Meet api, which is used in Hangouts integration for Slack, description follows
TL;DR:
Links such as https://meet.google.com/new?gid=123&gd=qwe987 can be generated, so a modal is shown which can ask user's confirmation and then some request is sent from user's browser (where the Google Meet page is opened) to some endpoint (probably it is determined from gid which seems to be google application id). Is there a way to configure my application to have a webhook, so I can generate these custom links?
There's Google+ Hangouts app for Slack. Here's how it works (after you add the app in your workspace):
you send /hangout command in any Slack channel
slackbot sends an "Only visible to you" message in this channel with a link to start a new hangout. it looks smth like this (I changed data in the link): https://meet.google.com/new?gid=691521906844&gd=THTJ30X6W%7CU01113BD13M%7CD01113BDB5Z%7Csuren%7C%7C1846381238693%7C1%7CB01QFGG5GJF%7CE1MDm4DWcuVa0RbN5ZT9o5KF
when you visit the link, a new meeting is started instantly, and the page shows modal with text "To bring others into this video call, post a link it to your Slack channel" with buttons 'Cancel' and 'Post'.
when you click 'Post', a new message is sent to the Slack channel, where the command was sent. Text is "#Suren Khorenyan has started a Google+ Hangout and would like you to join. Join Hangout." and contains a link to the meet, which was created previously
How can I utilise this integration for another app, like Mattermost (or anything else like Telegram chats via bots)?
As I see, data in the url slightly changes. Probably it's payload for Google Meet to trigger Slack to send a message with link to the channel.
gid seems to be something like google app id
gd seems to be something like google data. If I url-decode it, it becomes THTJ30X6W|U01113BD13M|D01113BDB5Z|suren||1846381238693|1|B01QFGG5GJF|E1MDm4DWcuVa0RbN5ZT9o5KF. This is some kind of payload, separated by pipes (obviously), but I don't know what any part of this means (suren is my username in the Slack workspace, probably this is used for creating an invitation message).
When I click Post, this happens:
a new POST request to https://hooks.slack.com/services/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 is sent with form-data
hangout_id: 1812381238693
hangout_url: https://meet.google.com//abc-iuqx-def
a new message is posted to the Slack channel
Google meet somehow knows where to post back! Is this configured at the Google application (application id is provided via gid)? How can I configure my application for such behaviour? Where can I setup webhook url?
If we breakdown the request, we can see that url contains some parts of the gd payload:
THTJ27X6W - this is the first part of the gd payload
B01ABCD5GJF - last but one
E1MDm4DWcuVa0RbK5ZT9o5KD - the last part of the gd payload
and form-data contains:
hangout_id - this is in the gd payload after my name
hangout_url - obviously, this is the url for the new created meeting
How can I change it for my needs?
I created a new application at Google APIs dashboard (here console.developers.google.com/apis), but can't find any docs for this integration. There's Google+ Hangouts API in API Library, but it says Apps will continue to function until April 25, 2017..
I tried to approach it from another side:
In the API Library there's Google Calendar. I found mattermost-hangout app on GitHub (had to update it a bit, so it works with updated api). Here's how it works:
oauth2 for authorising at google (single account)
it handles POST request, which is meant to be received from Mattermost (triggered by a slash command),
creates a new calendar event using Google Calendar API (with conference),
takes hangouts url from the response and sends a new message in the Mattermost channel with invitation to join the meeting.
But it has some downsides:
you have to use one account to authorise all event creation events (yeah, it can be upgraded to authorise any number of users, but it'll be inconvenient. why to force anyone to provide access to their Google Account, when Google Meet authorisation just happens in browser, we don't need to create events)
account, used for auth, now has events in his calendar. of course, events can be deleted, but it's not the way.
Is there any documentation on utilising gid and gd params?
Generally, I want to find a way to configure a webhook in my app, so when Google Meet finds my application's ID in the gid query param, it looks at the app's config and sends a request to my app (previously configured endpoint (I assume it works this way)).
Of course there's a chance that it's some kind of internal API and it cannot be used by everyone, but I could not find any information on this.
I'm using zapier with slack and want to catch an event when message_replied event was created as referred here.
To use event API, it needs URL verification, which is unable on zapier webhook catching. The following error occurs repeatedly; Request URL Your URL didn't respond with the value of the challenge parameter.
Are there any workarounds?
I'd really appreciate any help you can provide.
some related informations:
app used in zapier : Webhooks by Zapier
Event in zapier : Catch Hook
feature used in slack bot : Event Subscriptions
This is not currently possible. "Webhooks by Zapier" will only respond with the default "success" response because it's intended to be used with any incoming webhook. For that product, there's not special cases for any particular service.
If you're trying to integration with the Slack Events API (something I implemented at Zapier), then I recommend writing your own web service to catch Slack hooks, do business logic, and then send relevant webhooks onto Zapier as needed. This will afford you much more control over the process.
I am developing a Notification Only bot to enable proactive Teams notifications.
As far as I am aware it is necessary to store the ServiceUrl from an incoming message to the bot endpoint. I have read that it is also possible that service Url can change in the future (although unlikely) and that if this happens the serviceUrl should be updated and used for future messages.
Using a test O365 instance in UK region I see the following behaviour:
When I add member to team or install the app to a team, the service Url comes through as:
https://smba.trafficmanager.net/uk/
When I remove a member from team or remove the app from team, the service Url comes through as:
https://smba.trafficmanager.net/emea/
If our service tries to send a notification via the rest api, using the /emea ServiceUrl it returns a 403 Forbidden
Doing the same using an O365 instance in US region the service Url is allways:
https://smba.trafficmanager.net/amer/
Is this expected behaviour or a bug?
Are there any rules on when the Service Url should be updated and when it should not?
Many Thanks.
I am thinking of a simple chat application in Window Phone using Microsoft Push Notification Service.
I read a guide at http://msdn.microsoft.com/en-us/library/hh202967(v=VS.92).aspx which talks about creating a client application that receive toast notification.
This is a first time for me to develop a mobile application so I do not get some part of it.
The question that I have is, is it possible for a client (window phone) to send toast notification directly to other client? I have found below image from the web. It seems that I need to have Cloud Application(probably webserver?) to play with notification service.
Would it be possible to build a Window phone application that directly request to MPNS to send notification to other window phone application? (so from the picture above, '2' will directly point to Microsoft Push Notification Service)
If it is not, what is the reason for that?
There is a good explanation of the push notification service here.
From the above link.
Registration Phase 2: Now that the MPNS known the presence of the
phone on the network, it is required the phone itself provide the Uri
to the Earthquake service. Until this not happen the service doesn't
know there is a phone that need to be notified so it is not able to
provide the notifications. The phone must call a method on the
Earthquake service to provide the Uri that has been answered by the
MPNS. Once the Earthquake service gets this url it can store this
informations somewhere for a later use.
In your case you'll need communication between your devices before any notifications can be sent. This is to know the uri of your phone. A server has to store these uris for all devices registered for notifications. This is why you'll need an application which sends the xml to the MPNS.