Consider an agent created on Dialogflow (api.ai) and deployed to Actions on Google. When a user at Google Assistant request some information to this agent, is this request intermediated by Dialogflow?
I've noted that sometimes the agent response time is too long, so was wondering if it's due to my webhook taking too long to answer, or from Dialogflow on answering to Actions on Google.
Yes, both requests and responses go through Dialogflow's servers.
However, if there is latency, the chances are high that this is a latency on your side (or between you and Google) rather than Google/Dialogflow's.
Make sure that you're logging both when the request arrives and when you send your response. There are analytics tools that assist with this as well and may be useful for this case.
Related
I have a PERN(Postgres, Express, React, Node) e-commerce app. I want to notify a user that the payment is successful by redirecting to a payment successful page after a user scans QR code to pay.
However, I'm not sure how do I achieve this.
Currently, after the user completed a payment, I will receive a REST's POST request for payment confirmation from a bank API. . However, I'm also using GraphQL and I think that Graphql's Subscription could be what I'm trying to achieve.
Does anyone know how am I supposed to achieve this?
Are there anyways to send a request from REST to Graphql on my own server?
Or are there any better ways to do this?
Just like what is done in this video:
Do I understand correctly that you are looking for a way to notify your client that the payment was successful?
I assume you know how to handle redirect logic so here are the ways you can notify your web-app from the server.
1. Regular HTTP request
The client sends a regular HTTP-request to your server and you withhold the response until you received the 'payment completed' request from the bank API. If your request times out before the bank API confirms the payment - you simply send the same request again. This pattern is also known as Long Polling
2. Server-Sent Events
Your client can open a channel to your server that allow your server to send Events to your client (one-way). It is fairly easy to implement and a solid way to handle one-way communication. Check out the MDN documentation.
3. Web-Sockets MDN
You are probably familiar with these since they are the de-facto standard nowadays. Similar to Server-Sent Events but they allow two-way communication.
Most libraries that handle client-server communication implement a combination of these technologies in order to provide a fallback solution. I would recommend to stick to one of these libraries as they handle many edge-cases that are otherwise work-intensive to cover.
As you pointed out, if you are already using GraphQL you can simply use its subscriptions api. It uses WebSockets with a fallback to long-polling underneath.
Other popular options include socket.io or graphql-sse.
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 creating a chatbot for a Facebook page to solve people's questions and I wanted to make the bot messages 1 or 2 seconds of delay between each of the bot's replies. Could someone tell me how to do it in dialog flow? I couldn't find any answer around my research so hopefully someone could help me.
This isn't possible if you're using Dialogflow's built-in rich messages. It also wouldn't be possible using only webhook fulfillment and the Dialogflow Facebook integration, as you can only deliver a full set of messages as a reply at one time, and can't specify how they are delivered.
The only way to achieve that level of control would be to build the bot yourself (perhaps using an existing Messenger bot framework), and make calls from that code to Dialogflow to handle natural language understanding.
I'm making a dialogflow agent that will be integrated with various platforms (Facebook messenger, slack and maybe a few others) that will have the basic functions of a informational chatbot.
The agent will be for a specific store and I'm wondering if it's possible to trigger some sort of welcome message once the user enters the geofence (in this case, the store)?
Thanks for the help. I haven't found any documentation for this on dialogflow specifically or anywhere else so anything will be awesome.
Note: I'm am not by any means dead set of dialogflow, if AWS Lex offers something like this and it's better, I will take a look. I'm just a bit more used to dialogflow.
This cannot be achieved just by using either Lex or Dialogflow. Because at the end of the day, you are using them to integrate with Messenger/Slack/Whatsapp and these apps will (for obvious good reasons) not share the user's location information with the bot. You will need a helper app which takes the user's location permission as well and triggers the bots for you.
Keep in mind that channels like Messenger and Whatsapp have restrictions over sending messages willy-nilly to users. Messenger has a '24+1' policy Whatsapp also you can only send free form messages in the 24 hour window. But after that you can send chargeable pre-approved "hsm" message templates.
I have a Actions on Google project that uses api.ai for its actions. This is working well and I can see request/responses appear on the google assistant interface (On mobiles and simulator)
One of my usecases for api.ai needs to broken into 2 parts, in that we have to inform the user that the processing has started and then inform them again once its completed (without them reprompting for the output).
Im trying for a way to inform the user who is using the Google assistant when the processing is completed, but have failed so far. Something like this
User: I would like to see if my loan request is approved
Google Assistant: Hold on, let me check and let u know .
.... (Makes a webservice call to the backend asynchronously)
.... After few seconds ...
.... Postback to google assistant from the webservice
Google Assistant: Thanks for holding, your request is approved.
Im not sure how to do the "postback to google assistant" call. I have tried to get the SessionId from the Api.AI call and then use that to make a event request , but that doesnt seem to send the response to the assistant. Google Assistant seems to be using the formats defined in https://developers.google.com/actions/reference/rest/Shared.Types/AppRequest, but Im unsure how to get the ConversationToken and use that for sending the response back to the user.
Short answer: you can't do that.
Slightly longer answer: At least right now, there is no good way to send a notification. Your Action can only respond to a specific statement from the user. You can say something like "ask again in a minute and I should have a result for you", but that isn't a great experience. At Google I/O 2017, they announced that notifications would be coming to the Google Home at some point... but gave neither a time frame nor any information about an API.
Long, but probably still unsatisfying answer: You can look into Transactions which let them initiate purchase or request of some sort and then "check out". Once they have checked out, you would confirm that a transaction is being processed with an OrderUpdates and then can send updates with the status of the "order". These status updates can turn into notifications or user's can query the state of the order at any time. Transactions don't require payment, so this may work depending on your needs.
However, there are a few things to note. This is still in developer preview, so things may change in the future. It also doesn't work on all surfaces where the Assistant runs, so while it does work on Assistant on phones, it does not work on the Google Home right now.