I finished my bot in NodeJS, unfortunately, I’m having some issues when I try to connect it with some channels.
I tried to link it with Messenger and Microsoft Teams but when I launch the Bot I receive this message : “Oops. Something went wrong!” without any explanation.
But when I use the bot on my local environment, on the Azure environment or in an iFrame, it works perfectly.
Did I miss something?
Tanks a lot,
Related
I want to develop an action to google assistant. So i red the documentation here https://developers.google.com/assistant/conversational/overview and i followed this tutorial https://www.youtube.com/watch?v=Z1hxvniJ18s
It s worked and i was allow to develop and test my app in the simulator. The problem is that when it's come to webhook i don't totaly understand how it's work. On the webhook icon i got this
The seconde one allow me to use Google cloud function and firebase but i had to add my billing account to make it available. I also get a console where i can code my fonctions and my responses.
And if i am correct, the first one allow me to connect to my own Api. But i can only enter one field that is the URL adresse and nothing else so how do i code it? Also i see everywhere people using node.js and i would like to use php is it possible?
To sum up my problem, i would like to know how i could connect my action builder to an other service(Api) than google ones? If it's possible to run my server in php and how do i interact with my google action?(I think it's by sending json back and forth but i'am not sure how to do it?) Finally i would like to know if it's possible to test it in local server with mamp and phpmyadmin for exemple to test the answer of the server?
I would be very grateful if someone could help me, show me how to set up all this.
But i can only enter one field that is the URL adresse and nothing else so how do i code it?
When you develop your webhook, you will need to have a single publicly accessible endpoint to connect with. This endpoint will receive an HTTP POST request and you will need to respond with an appropriate response.
Also i see everywhere people using node.js and i would like to use php is it possible?
Any language that can run on a web server can work. Node.js is one that is used a lot, but PHP can work just as well. You can create an actions.php file and then enter an endpoint address https://example.com/actions.php that will be called. You may need to refer to the Request and Response reference for the expected format.
if it's possible to test it in local server with mamp and phpmyadmin for exemple to test the answer of the server?
It's somewhat possible. You'll need to have some method of sending mock requests to your local server, which might be as easy as using cURL or other tools like Postman.
Unfortunately my personal experience with PHP tools is limited, so I can't necessarily walk-through the specifics. But it does seem like you know these tools a bit more and should be familiar enough to be able to get started.
I'm investigating by days with no results about this exception that my NextJS app is currently throwing, in particular when I try to open a single specific URL:
502: BAD_GATEWAY
Code: NO_STATUS_CODE_FROM_FUNCTION
ID: zrh1:4zx5l-1572269318137-64d401b5d058
Here's the screenshot:
Basically, I have on https://lucacattide.dev/about/en a page that this app should open. This is linked to a MongoDB third-party cloud API platform - Squidex - which is responsible to populate the page itself, via GraphQL queries. The app uses Apollo as GraphQL client. The app instead, is hosted on ZEIT.co serverless cloud, with Now 2.0 version.
During the development process, everything works fine. The page loads up and data is fetched in the right way. Notice that for development, I'm working on now-dev environment instead of a custom Express server, in order to reproduce the production one, as suggested by ZEIT itself.
The exception is being thrown on the production environment - the live one on the hosting platform, not on localhost; the main problem is that no errors are being shown on live logs or local development. So I'm literally going mad in inspecting the possible cause.
I've already tried to test the involved page, by splitting it in sections and trying to exclude child components, or focusing the inspection on the GraphQL query. But the first hasn't produced results and the latter works fine in every environment.
As last try, I deleted and re-created the back-end contents related to that page, because in the past I had a similar issue due to an old GraphQL edited schema that didn't reflected its modifications through the API - so in that case I was still receiving 502 errors. But this time it didn't worked.
Anyone could help me to understand what's going on, please?
Thanks everyone in advance
The issue was caused by an incompatibility between the d3-cloud library and the Now environment.
By replacing it with the react-wordcloud one, the error has been solved.
Thanks everyone for your assistance.
My question might sound basic or lame to you but I really have zero experience with this. I am so new to Google Actions and I don't have that much idea with Javascript. My question is how do I develop a Google Action without using the online editor google provided? Can you please narrate it to me step by step? I tried enrolling myself in codelab exercises that I hope might help me but in the codelab exercise, there was already a bunch of codes I cloned from github and that was what I used to make it all work. But now that I want to code for our real project, I don't know how to start from scratch. I know how to create an agent and stuff.. but I don't know how to develop locally. PLEASE HELP ME. THIS IS FOR OUR THESIS.
If you have followed the Build Actions for the Google Assistant (Level 2) codelab, you'll see that it talks about setting up for local development in step 3 using Firebase Cloud Functions. If you scroll down to part 4 on that page, what follows replaces some things in part 4.
Instead of typing firebase deploy as it suggests, instead type
firebase serve --only functions
What this does is, instead of sending the code to the server, you run the code locally in an environment that emulates the Firebase Cloud Function configuration. It will show the full path that is available on localhost. If your function is named something like "webhook", it will show something like:
functions: webhook: http://localhost:5000/your-project/us-central1/webhook
This now lets you use the ngrok command in another window with something like
ngrok http 5000
and that window will show the URL and hostname that are the external point. So it might be something like:
forwarding https://8ba32042.ngrok.io -> localhost:5000
You would combine these two to make the URL that you should use as the fulfillment webhook URL. Using our example, it would be something like
https://8ba32042.ngrok.io/your-project/us-central1/webhook
that you would put into the Dialogflow fulfillment URL setting.
You can then stop and start the local firebase hosting as you change things in your code and examine the request and response using the ngrok console. If you ever stop the ngrok command line, when you start it again you'll get a new hostname, and you'll need to change this in Dialogflow as well.
Download NGROK
Download NODEJS
Develop a local webhook using Express on NodeJS
Expose this local webhook to the internet using NGROK
Use the NGROK generated URL as the fulfilment to your Dialogflow agent.
Integrate Google Assistant with Dialogflow and test it.
Here is a tutorial to start with
I am new to Raspberry and VOIP. I am interested to make a door intercom system using raspberry, as I read most of the post here and those are really helpful,one of the raspberry is acting as server (Asterisk and PBX). I was able to call using sflphonebut that was only for desktop mode and I am interested to call using CLI and for that I installed "PJSIP" as reffered by most of users, but don't have any idea what to do next (I mean how should i start). As it is written after installation I am supposed to try for "pjsua" and "pjsystest" in pjsip-apps/bin, but it doesn't ring any bell for me.
Sorry for my level as beginner but if you don't begin how are you supposed to masters it.
I shall be very thankful.
so i can't explain all of the stuff you need to know, but with this Site you should be able to register to you PBX. It's an documentation to the high level API of PJSUA. If you go further on that site they will lead you through the things you have to do to establish a call.
Although this can be very frustrating because there are many error that can appear. There are some python test application under pjproject/pjsip-apps/src/python/samples, here you should firstly try to establish a call between two clients to be sure you server is well configured.
Just for info, the dest_uri you have to give in the call.py is like so sip:ip:port and you have to change the values in the register.py to your client infos. Then run the register.py in one shell and the call.py in an other shell.
Hopefully i could help you over some barriers, feel free to ask if something was unclear.
We made a simple application and using GoogleAppEngineLauncher (GAEL) ran that locally. Then we deployed, using GAEL again, to our appid. It works fine.
Now, we made a web service. We ran that locally using GAEL and a very thin local python client. It works fine.
We deployed that, and we get this message when we try to visit our default page:
"Move along people, there is nothing to see here"
We modified our local client and tried to run that against our google site and we got an error that looked like:
Response is "text/plain", not "text/xml"
Any ideas where we are falling down in our deployment or config for using a web service with google app engine?
Any help appreciated!
Thanks // :)
Looks like you're not setting the Content-Type header correctly in your service (assuming you ARE actually trying to send XML -- e.g. SOAP, XML-RPC, &c). What code are you using to set that header? Without some indication about what protocol you're implementing and via what framework, it's impossible to help in detail...!
Looks like we aren't going to get to the bottom of this one. Just not enough information available at debug time. We've managed to affect a fix on the service, although I hate ot admit it we never found out what was causing this bug.