I had a scenario in which I need to forward call from two phone's using same Nexmo LVN.
So its like this
1. Phone_1 forwards call to Number_2 using LVN_1.
2. Phone_2 will forward call to NUMBER_2 using same LVN_1.
Is this doable? If yes then how can we do it. I think call center does this type of scenario.
This is possible with a single LVN. When you receive a call, you can use a connect action to dial out to another number. You'll need to change from to your LVN, and number to the phone number you want to forward on to in this example
[
{
"action": "connect",
"eventUrl": ["https://example.com/events"],
"timeout": "45",
"from": "447700900000",
"endpoint": [
{
"type": "phone",
"number": "447700900001"
}
]
}
]
Related
Trying to setup dynamic tax calcuation using Stripe Orders API. Using these docs:
https://stripe.com/docs/orders
https://stripe.com/docs/orders/dynamic-shipping-taxes
result = {
"order_update": {
"items": [
{
"parent": None,
"type": "tax",
"description": "Sales taxes",
"amount": 100,
"currency": "usd"
}
],
"shipping_methods": [
{
"id": "free_shipping",
"description": "Free 7-day shipping",
"amount": 0,
"currency": "usd",
"delivery_estimate": {
"type": "exact",
"date": "2020-08-11"
},
"tax_items": []
}
]
}
}
print(result)
return Response(result, status=status.HTTP_200_OK)
Even dummy response without any sophisticated computations failed to create an order object with HTTP 402 error for script trying to create Order
Creating order with no tax specified works as well and allows to create order.
Webservice running a callback receives a request from the Stripe as it must and works as well.
Stripe support says only "we no longer recommend developing your integration around this system" and does not answer directy if they turn off this feature.
If they turn off this feature I do not understand why it is available in the dashboard.
The issue was in the middleware of my service. It transformed response keys from snake_case to camelCase. Resolved.
I have an application within watson assistant that consumes many services from other endpoints. and I would like to call this conversation (from watson) within a google assistant conversation in a certain intention. for example i will develop a rich conversation on google assistant and in one of the options i will call watson's conversation.
I tried as follows, but it didn't work. does anyone know any example that can help me?
{"locale": "pt-BR",
"actions": [
{
"description": "Launch intent",
"name": "MAIN",
"fulfillment": {
"conversationName": "mainConversation"
},
"intent": {
"name": "actions.intent.MAIN"
}
},
{
"description": "Direct access",
"name": "BUY",
"fulfillment": {
"conversationName": "ExampleAction"
},
"intent": {
"name": "com.example.ExampleAction.BUY",
"trigger": {
"queryPatterns": [
"teste",
"azul",
"start"
]
}
}
}
],
"conversations": {
"mainConversation": {
"name": "mainConversation",
"url": "https://us-central1-ericanovo-798cc.cloudfunctions.net/webhook",
"fulfillmentApiVersion": 2
},
"BUY": {
"name": "ExampleAction",
"url": "https://orquestrador-sulamerica-teste.mybluemix.net/api/v1/chat/google?externaltoken=574213c0-e904-11e9-9970-ff484aa25334",
"fulfillmentApiVersion": 2
}
}
}
thanks
That won't work because the webhook for everything published under the same project has to be the same URL. You are expected to handle all the Intents and "actions" at that webhook.
In your case, you would also need to make sure the request is formatted the way the Watson API would be expecting it. The Assistant will send it using the Conversation Webhook Format, and it sounds like you would send it using Watson's Analyze Text API.
You're not showing any of your code, so it is difficult to be sure - but the first would be in a JSON format that you can extract. You can then use a library in Node (such as request-promise to make the calls to Watson. Based on the result from Watson, you'd need to format the results as a response and return it to the Assistant.
It isn't clear why you'd need multiple webhooks specifically, although it is certainly possible that some Intents may make different API calls than others.
Keep in mind that your custom Intents will only be valid on invocation. Subsequent Intents will all be TEXT Intents.
I'm trying to make a realtime application with Asterisk 15 ARI, and I need to get all agents/users (sip) status in queue...
I need to know if the user has logged in queue, is on pause, in a call...
I'm reading the Asterisk ARI docs but not found anything about that.
I'm using node-ari-client to watch the Stasis events.
Thanks for u help.
I think AMI is more adequate for this purpose, as ARI is more suitable to build your dialplan application.
You may use AMI action QueueStatus to see who is logged in, paused, etc.
Maybe https://www.npmjs.com/package/asterisk-ami-client will help you to build the client.
ARI allows to get current state of SIP peers via
http://localhost:8088/ari/endpoints/SIP
[
{
"technology": "SIP",
"resource": "111",
"state": "online",
"channel_ids": []
},
{
"technology": "SIP",
"resource": "222",
"state": "offline",
"channel_ids": []
},
{
"technology": "SIP",
"resource": "333",
"state": "unknown",
"channel_ids": []
},
]
I have an intent where I might say 'Transfer 4 to Bob' and it identifies this as 'Transfer for to Bob'
Also I might say 'Transfer 10 to Bob and it identifies this as 'Transfer 102 Bob' treating to word to as 2 on the end of the previous number.
What is the best way to get API.AI to recognise these parts correctly so 4 is not for and to is not 2?
You mentioned that you're using the Actions on Google platform. This means that speech recognition - the process of translating what the user says into text - is happening before the data gets to API.AI.
The problem you're experiencing is that Actions on Google is misrecognizing some numbers as words, e.g. four becomes for.
Because this happens before - and separately from - API.AI, you won't be able to fix the misrecognition.
Below, I'll explain how you can work around this issue in API.AI. However, it's also worth thinking about how you could make your conversation design as robust as possible so that issues like this are less likely to cause problems.
One way you could increase robustness would be to mark the number as a required parameter in API.AI so the user is prompted if it isn't detected due to a recognition error. In that case, the dialog would go like this:
User: Give me four lattes.
App: Sure, four lattes coming up.
User: Give me for lattes.
App: How many do you want?
User: Four.
App: Sure, four lattes coming up.
Regardless, here's a workaround you can use to help recover from misrecognition:
In your intent, provide examples of these commonly misrecognized values. Highlight and mark them as numbers.
Test out your intent out in the console and you'll see that "for" is now matched as a "number" entity with value "for".
In your fulfillment webhook, check the parameter for this value and convert it to the appropriate number using a dictionary. Here's the JSON for the above query:
{
"id": "994c4e39-be49-4eae-94b0-077700ef87a3",
"timestamp": "2017-08-03T19:50:26.314Z",
"lang": "en",
"result": {
"source": "agent",
"resolvedQuery": "Get me for lattes",
"action": "",
"actionIncomplete": false,
"parameters": {
"drink": "lattes",
"number": "for" // NOTE: Convert this to "4" in your webhook
},
"contexts": [],
"metadata": {
"intentId": "0e1b0e72-78ba-4c61-a4fd-a73788034de1",
"webhookUsed": "false",
"webhookForSlotFillingUsed": "false",
"intentName": "get drink"
},
"fulfillment": {
"speech": "",
"messages": [
{
"type": 0,
"speech": ""
}
]
},
"score": 1
},
"status": {
"code": 200,
"errorType": "success"
},
"sessionId": "8b0891c1-50c8-43c6-99c4-8f77261acf86"
}
I'm new to Api.ai , i read the doc. but i didn't understand how Api.ai works better with many parameters.
I'll try to explain by an example :
I have a Management software which manages the members/actions/projects , where i can get the actions of any member at any project using the normal interface.
let's replace this with a smart bot where the chat will run as i expected below,
USER : i want to see my actions for ANY PROJECT NAME HERE
bot : your action is XXXXXX.
OR
USER: give me all the members of the project ANY PROJECT NAME
Bot: Members are "1-2-3-4-5-...."
i think you got what i mean , if you need more i can explain more.How can i let Api.ai understands this ?
For API.ai to 'remember' values (ie store and retrieve information such as the names of projects, actions and team members) you will need to connect API.ai to a webhook/database of your own, there isn't anyway for API.ai to do this on its own.
Once you connect API.ai to a custom webhook/database you can use the variables that API.ai will parse for you to run your query. You simply need to build the intents corresponding to the search and parameters involved
Here's how the process would flow:
User asks "I want to see my actions for [ANY PROJECT NAME HERE]"
API ai logic recognizes this as the intent 'search-action' for $project_name, you having set this up in API.ai like this
Your custom webhook receives JSON response from API.ai that in this case would look like this:
{
"id": "REDACTED",
"timestamp": "2017-04-19T03:18:18.028Z",
"lang": "en",
"result": {
"source": "agent",
"resolvedQuery": "I want to see my actions for project Unicorn",
"action": "search-action",
"actionIncomplete": false,
"parameters": {
"project_name": "project Unicorn"
},
"contexts": [],
"metadata": {
"intentId": "REDACTED",
"webhookUsed": "false",
"webhookForSlotFillingUsed": "false",
"intentName": "Search - Actions"
},
"fulfillment": {
"speech": "",
"messages": [
{
"type": 0,
"speech": ""
}
]
},
"score": 1
},
"status": {
"code": 200,
"errorType": "success"
},
"sessionId": "REDACTED"
}
So, your webhook has logic that recognizes when result.action is 'search-action' is should run a database search for actions in project result.parameters.project_name
Your webhook fulfills the API.ai request, or alternatively, sends message to message platform directly (ie Facebook messenger)