While Defining the Dialog in the Watson Conversation I'm not able to greet user with his/her name or I'm not able to detect contact number sent by the user and rephrase it to the user. Is it possible to do it in the Watson Conversation Api or not.
Although Mitch's response is correct, here is an example of doing a personalised response.
1. Set your conversation_start node text to "Hello <? context.username ?>".
2. In your code you would do something like this (Python).
import json
from watson_developer_cloud import ConversationV1
conversation = ConversationV1(
username='SERVICE_USERNAME',
password='SERVICE_PASSWORD',
version='2016-07-11')
workspace_id = 'WORKSPACE_ID_CONVERSATION'
response = conversation.message(workspace_id=workspace_id, context= {'username':'Simon'})
print json.dumps(response)
3. When you run this, it should output the following, with the "text" part being what the user sees.
{
"entities":[],
"intents":[],
"output":{
"log_messages":[],
"nodes_visited":["node_1_1472298724972],
"text":["Hello Simon"]
},
"context":{
"username":"Simon",
"conversation_id":"9dc1501b-ac53-4b51-a299-37f5314ebf89",
"system":{
"dialog_turn_counter":1,
"dialog_stack":["root"],
"dialog_request_counter":1
}
},
"input":{}
}
One thing to be aware is that, the context object is used to maintain the state of the conversation. So if you plan to use just REST API's then you need to merge your context variables into the preceding context object before sending it. You do only need to do this at points where you do know the conversation needs that context.
Do you already have access to this information? You can send these values through as context, and refer to them using $context_variable
The same goes for collecting information from a user. You can capture things using regular expressions via your application, or using some Spring Expressions, you can see the text.matches here:
https://www.ibm.com/watson/developercloud/doc/conversation/dialog_reference.shtml
You would store this as context, and then refer to it using $context_variable again.
Information like names and phone numbers is quite open ended, so can be difficult to capture without using an open entity extraction engine, which we are researching best ways to incorporate this.
To get the user's input, use:
"context": {"yourVariable": "<?input.text?>"}
And to show:
"output": {"text": "You entered this $yourVariable"}
Related
i would like to have a type that represent proper nom, such as family name for exemple but i can't find anything on this.
My goal is to send a info to an other personne using google assistant and my backend.
For exemple the user can say "Send this info to john smith" the info is stored in my backend so i have no problem finding and i got the id of the personne who is talking to the google assistant so this is no problem either.
The problem is how can i get john smith as a parameter that i send to my webhook? So my backend can verify the user list in my database and send the info if the user existe. I tried to use Type but a family doesn't match any pattern because it's can be anything...
If anyone know how to use google action builder with proper noun i would be grateful to know how i can manage to do it.
You have generally two options.
Free form text approach
First you can create a "Free form text" type which can catch pretty much anything being said.
Then a custom intent can be trained with a few examples to pull out the correct proper noun (or anything else). Your webhook will be able to match at that point.
Type Overrides approach
Alternatively, you can create a new type that starts with a preset of sample names that you use in your custom intent. Then, when the action starts, you can get the user's personal contact list in the webhook and set session type overrides.
Here's an example of the code I got from a music player action:
conv.session.typeOverrides = [{
name: 'genre',
mode: Mode.TypeReplace,
synonym: {
entries: Array.from(trackGenres).map(genre => ({
name: genre,
synonyms: [genre]
}))
}
}]
Depending on your system architecture, one of these may make more sense than the other. The first is better at capturing everything, but may require more post-processing on your webhook. The latter is better at precision, but may mean names may not match if they don't match entirely.
I'm sending emails using: https://github.com/sendgrid/sendgrid-nodejs/tree/master/packages/mail
I have not been able to find out HOW I can add the Unsubscribe equivalent. This is documented in here: https://sendgrid.com/docs/Classroom/Basics/Marketing_Campaigns/unsubscribe_groups.html#-Using-a-Custom-Unsubscribe-Link
On the website, you just use a shortcode [Unsubscribe], this does not work when sending emails via the sendgrid/mail package.
One tip that would have saved me an hour or two is that:
It's possible to send the following in the api json along with other stuff:
"asm":{
"group_id":123,
"groups_to_display": [123],
}
then the following variables become available to use within the template:
<%asm_group_unsubscribe_raw_url%>
<%asm_preferences_raw_url%>
If you want to keep things simple don't include the following variable as it fiddles with too many things (this wasn't obvious from the documentation so obviously I did so and wasted time :( ):
"tracking_settings": {
"subscription_tracking": {
"enable": true,
"substitution_tag": "[unsubscribe_url]"
}
}
Just use them in their raw format and you shall be fine.
Since you're sending using code, it's a "transactional" type of message. You'll want to either turn on the Subscription Tracking filter at the account level (via [UI](subscription tracking setting) or API), or turn it on as you send the message, as part of the mail/send API call, under tracking_settings.
It's important to note that you can't mix those. If you define anything in the mail/send API call, you'll need to define everything for Subscription Tracking in that call. SendGrid won't look at some settings at the mail level, and some at the account level.
Most users will just set it at the account level. There, you can customize the HTML & Text of the Unsubscribe footer, customize the HTML of the landing page, or redirect landing to a URL of your choosing, which will send the recipient there with ?email=test#domain.com in the URL string for your system to catch. You can also define the "replacement tag" like [%unsubscribe%], so that you can place the URL wherever you want within your HTML.
https://app.sendgrid.com/ > Suppressions > Unsubscribe Groups > Create New Group
Note down group_id/ids. e.g 123 (Only number !Not string)
Send email using node.js
const sgMail = require('#sendgrid/mail');
sgMail.setApiKey(SENDGRID_API_KEY);
const tags = { invitedBy : Alex }
const msg = {
to: email,
from: { "email": SENDER_EMAIL,
"name": SENDER_NAME
},
templateId: TEMPLATE_ID,
dynamic_template_data: {
Sender_Name: name,
...tags
},
asm: {
group_id: 123,
groups_to_display: [
123
],
},
};
await sgMail.send(msg);
The best approach is to use Group Unsubscribes.
First create a group in Sendgrid:
Groups > Unsubscribe Groups > Create a group
Next, insert a module into the Sendgrid template that creates specific tags in your email, which are populated when you make an API request
Go to your template
Insert an unsubscribe module in an HTML block
Save
Finally make an API request and specify the group created in step 1:
"asm":{
"group_id":544,
"groups_to_display": [544, 788],
}
These will be inserted into the module mentioned in step 2 when the email is sent.
Unfortunately Sendgrid unsubscribe links are not as straightforward as they could be. They are explained in more detail here
The easiest way is to do this via the SendGrid GUI.
Go to Settings -> Tracking -> Subscription Tracking
There is a new feature in the conversation service where you can define slots/ entities for specific intents to extract the relevant information from the user input like currencies or specific string inputs. Those slots can be set mandatory in case you need them to proceed and the user will be asked for missing slots until he provides them.
Is it possible to define sth. like quit parameter so I can easily interrupt this conversation? The general documentation does not provide any information regarding this problem.
https://console.bluemix.net/docs/services/conversation/entities.html#defining-entities
You can do it by adding node-level handler which will listen to your cancellation intent and fill the slots with dummy values.
You can read more about this approach in the documentation: https://console.bluemix.net/docs/services/conversation/dialog-build.html (paragraph "Handle requests to exit the process")
We have stock website and we help buyers connect with the sellers. We are creating API to let buyers push their contact details and get back the seller details. This is transaction and get logged in our database. We have created following API:
The request is POST, the URL looks like:
/api/leads
The request body looks like:
{
"buyermobile": "9999999999",
"stockid": "123"
}
The response looks like:
{
"sellermobile" : "8888888888",
"selleraddress": "123 avenue park"
}
We have a new requirement, i.e. we need to send back PDF URL (instead of "sellermobile" & "selleraddress"). This PDF URL would contain the seller details in case it comes from one of our client.
We have modified the same API, now the request body looks like:
{
"buyermobile": "9999999999",
"stockid": "123",
"ispdf": true
}
The response looks like:
{
"sellerdetailspdf" : "https://example.com/sellerdetails-1.pdf",
}
Is it RESTFUL to do this? OR we should create separate API for getting response as PDF?
I wouldn't approach it this way. What happens when you need to add XLS? Do you add "isxls" to the request too?
Things I'd consider:
Use a mime type for content negotiation. Post the same request, and specify in the Accept header what you expect back - JSON, PDF, etc. You're then actually getting the report instead of a link to the report, which may or may not be better.
- or -
Include a link in the typical lead response.
{
"sellermobile" : "8888888888",
"selleraddress": "123 avenue park",
"_links": {
"seller-details-pdf": "https://example.com/sellerdetails-1.pdf"
}
}
- or -
Support a query parameter that specifies the type in the response.
- or -
Have a single property that specifies the type in the response, rather than a boolean. Much cleaner to extend when you add new response types.
The first two options have the bonus that you don't require clients to handle multiple response types to a single request. That's not forbidden by any spec, but it's annoying for clients. Try not to annoy the people who you want to pay you. :)
Again the implementation looks good to me, however you could potentially look at breaking the return of the PDF URL to another endpoint maybe something like api/lead/pdf that way your request body is the same for api/lead and all subsequent endpoints under /lead. Allowing your routes and other code to handle small portioned tasks instead of having a route that handles multiple flags and multiple code routes.
That looks good to me - the same type of input should give the same type of response but in your case you have two different types of input - one with the "ispdf" flag and one without. So it's consistent to responds with two different types of response, one with the PDF link and one without.
That's still something you'll want to document but basically it's a correct implementation.
i am using this example to send messages to my friends.
the problem i get into is how do i use the data property to add some tracking info.
I would like to pass a var $test and then be able to read it in a json format, or even an array.
In other words, I would like to pass a var when i send the message and when they accept it and it redirect them to the canvas, i would like to be able to grab it from somewhere:
ex:
"data":[
{
"id":"167548189960088",
"application":{
"name":"Cat's Test Site",
"id":"314268391344"
},
"to":{
"name":"Cissy Lim",
"id":"100001147247007"
},
"data":"'here is my var'",
"message":"'INSERT_UT8_STRING_MSG'",
"created_time":"2011-02-16T08:37:02+0000"
},
Thanks
The "data" parameter currently only supports a string. Very annoying since Facebook seems to support json objects everywhere else. You could put a "json string" there and then eval that to a json object when you want to read it.