I get list of accounts by using getAccount() and discoverAndAddAccounts(). For each account type (CREDIT, LOAN, etc...), there are specific set of fields that I need to access. For example, I want to access creditMaxAmount field of CreditAccount. However, i dont seem to find a way to identify "type" of a given account object.
In summary, given output of above mentioned functions, how do I identify account type in order to access fields specific to that account type.
The type of account is identified by the Account header.
See https://ipp.developer.intuit.com/index.php?title=0010_Intuit_Partner_Platform/0020_Aggregation_%26_Categorization_Apps/AggCat_API/0020_API_Documentation/0050getLoginAccounts for the response XML.
As you can see there is InvestmentAccount, CreditAccount, BankingAccount, LoanAccount, ..., and OtherAccount.
If an account shows up as OtherAccount, that means that it has not been set to a specific account. You can use updateAccountType to set the type of account it should be.
<ns8:AccountList xmlns="http://schema.intuit.com/platform/fdatafeed/account/v1"
xmlns:ns2="http://schema.intuit.com/platform/fdatafeed/creditaccount/v1"
xmlns:ns3="http://schema.intuit.com/platform/fdatafeed/rewardsaccount/v1"
xmlns:ns4="http://schema.intuit.com/platform/fdatafeed/bankingaccount/v1"
xmlns:ns5="http://schema.intuit.com/platform/fdatafeed/investmentaccount/v1"
xmlns:ns6="http://schema.intuit.com/platform/fdatafeed/otheraccount/v1"
xmlns:ns7="http://schema.intuit.com/aggregation/loanaccount/v1"
xmlns:ns8="http://schema.intuit.com/platform/fdatafeed/accountlist/v1">
<ns7:**LoanAccount**>
<accountId>75000033014</accountId>
<accountNumber>9900009994</accountNumber>
<accountNickname>My Military Loan</accountNickname>
<displayPosition>5</displayPosition>
<institutionId>0</institutionId>
<description>Description</description>
<balanceAmount>90227.2</balanceAmount>
<aggrSuccessDate>2012-02-27T23:20:13.651-08:00</aggrSuccessDate>
<aggrAttemptDate>2012-02-27T23:20:13.651-08:00</aggrAttemptDate>
<aggrStatusCode>0</aggrStatusCode>
<currencyCode>USD</currencyCode>
<ns7:loanType>**MILITARY**</ns7:loanType>
There is no direct way to identify the Account type, the getBankingAccountsAndCreditAccountsAndLoanAccounts() method will return the Accounts, and you would need to check the Object type in order to determine the Account type.
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 am developing an api.ai bot that will search for the Vendor name in the database.
a ) if vendor exist -> provide username -> provide password
b) if vendor doesn't exist -> (add vendor -> yes ) or (add vendor -> No)
I have a webhook which is checking the vendor exist in database or not .
Bot Scenario: (Example )
Case1:
User: Do Alpha exist as a vendor?
Bot: yes, Alpha exist in Database. Please Provide User Name.
User: abc#gmail.com
Bot: Please Provide Password?
User: abcdef
Bot : Welcome
Case 2:
User: Do Beta exist as a vendor ?
Bot: No Beta is not a vendor. Do you want to Register?
Case 1:
User: Yes
Bot: Please fill this Form.
Case 2:
User: No
Bot: Is there any other way I can help
One thing I have figured out, I have to use output context to trigger the intent. But how can I do it in this complex case? and how can I call multiple to follow up intent using Output Context?
I might be using a bad approach, Is there any other way to solve this ?
I do have a follow-up question.
when we pass the fulfillment response back to dialogue flow. The response print on bot console will be the default text response, how can I get "fulfillmentText" to be the Response.
Thank you Guys. This is the followup Intent scenario.
This is not complex, you are doing it wrong by having two intents for collecting username/password.
Try the following way
When you detect that your vendor is present - set the context in webhook, as say, "vendor-present"
When the vendor is not present - set the context in webhook, as say, "vendor-new"
Use lifespan (the number at the left side of the context) to set the lifetime or validity of the context.
Create a separate intent for existing vendor - say "Vendor Data Collection" for collecting username and password. Set input context as "vendor-present" in the Dialogflow. Here you will collect these as parameters in the same intent (see image below). Mark these parameters as 'required' so that they must be collected by your bot. Use the Prompt section to put your response question for collecting information like "Please provide username".
If the vendor is not present, use existing intents and set input context as "vendor-new" in the Dialogflow.
Now, few things to note - the username parameter can be collected using the system entity #sys.given-name. But it is not very accurate with the Non-American/English names. I am not sure if this is improved or not. Secondly, there is no system entity to collect passwords, so you need to set the entity as #sys.any and in the webhook, you need to use regex to extract passwords on your own. BTW - you are not supposed to share passwords!
Hope this helped you!
if you have a REST API that is hypermedia-driven (HATEOAS) you can easily change a client's behavior by including or omitting links in the response (_links). That enables a client to completely forget about testing permissions for the operations that are possible in the current state of a resource (the link to the operation is present or not).
Additionally you can leave out properties in the response if the current user doesn't have permission to see it.
That way authorization is done entirely on the server (and controls actions and properties that are eligible to execute/view).
But what if I want to a have a read-only property? It is no problem for the REST API to ignore the property if it is present in the request (_POST_ OR _PUT_). it just won't get saved. But how can a client distinguish between write and read-only properties to present the user appropriate controls (like a disabled input field in HTML)?
The goal is to never ever have the client request a user's permissions, but to have a completely resource driven client/frontend.
Any help is greatly appreciated :-)
If I misunderstood your question, I apologize upfront. With that being said...
But how can a client distinguish between write and read-only
properties to present the user appropriate controls (like a disabled
input field in HTML)
Well, there are multiple solutions to this. The simplest one I can personally think of is to make each property an object having a simple structure of something like:
...
someProperty: {
value: 'some value',
access: 'read-only'
},
someOtherProperty: {
value: 'some value',
access: 'write'
}
...
You can obviously get as creative as you want with how you represent the "access" level of the property (using enums, booleans, changing access to be isReadOnly or whatever).
After that, the person using the API now knows they are read-only or not. If they submit a "write" value for a "read-only" property as part of the POST payload, then they should expect nothing less than a 403 response.
Edit:
In case you can't alter the properties in this manner, there are a number of other ways you can still achieve this:
write documentation that explains what access each property has
create a route that the user can submit 1 or more properties to in order to receive a response that indicates the access level of each property (response: { propName: 'read-only', propName2: 'write', etc.)
Return a propertyAccess map as part of the response (mapping properties to access levels).
end of the day, you just need a way to map a property with an access level. however that's done depends on what your restrictions and requirements are for the api, what changes you can make, and what is acceptable to both your client(s) and the business requirements.
I am sending a request for graph insights with the action type breakdown like this one given in an example on Facebook page : https://graph.facebook.com/XXXXXXXX/app_insights/story_publishes?since=1418112000&until=1426748400&summary=true&breakdowns[0]=client&breakdowns[1]=action_type&breakdowns[2]=auth_state&date_format=U
The result is however difficult to read because the type of action is represented by a numeric value (uuid) like this: "action_type"=>"465905580137487", so I dont know what it relates to- checkin, share or photo upload. Also for different apps those uuids are also different. Does anyone know what call I need to make to get the action type names as strings? Thanks for help
You need to call this URL:
https://graph.facebook.com/{action_id}
where action_id is the value returned by action_type. You'll receive the action details on the response.
Not sure if this is a security feature, an oversight, or me missing the ocean for the waves, but wondering why there is no value attribute for the password field constructor
This is not an issue for user signup and other form creation events, but becomes a headache when, for example, a user renewal form does not have the password field filled in (and thus fails validation, which is ironic given that they just logged in in order to be able to renew in the first place ;-))
My workaround has been to set the value attrib manually by supplying it as an extra argument:
#inputPassword(
_form("password"), '_label-> "Password*", 'class-> "required",
'value-> _form("password").value map{Some(_)} getOrElse Some("")
)
would prefer the value attribute included by default, however, as with other input elements. Yes, I can override it, but wondering what the dealy-O is regardless
To me, you shouldn't be able to retrieve the user password in any way, since the password should be encrypted before storing it somewhere.