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!
Related
I need to declare a parameter to store username as input in the first message of dialogflow session, "My name is John" will be the first message the user type to dialogflow cx,
I noticed it's not possible to create a parameter on the Start page, is there is a way to detect parameters using EntityType from the first message of the session ?
To detect parameter values from the first end-user input, you can use intent parameters.
First, create an intent and add training phrases like "My name is John" and similar. See how the intent may look like.
Then, add an intent route on the Start page and define agent response in fulfillment. See how the route and a simulator test may look like.
You can also check the general agent design best practices for more information.
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.
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")
I am currently programming a REST service and a website that mostly uses this REST service.
Model:
public class User {
private String realname;
private String username;
private String emailAddress;
private String password;
private Role role;
..
}
View:
One form to update
realname
email address
username
Another form to update the role
And a third form to change the password
.
Focussing on the first view, which pattern would be a good practice?
PUT /user/{userId}
imho not because the form contains only partial data (not role, not password). So it cannot send a whole user object.
PATCH /user/{userId}
may be ok. Is a good way to implement it like:
1) read current user entity
2)
if(source.getRealname() != null) // Check if field was set (partial update)
dest.setRealname(source.getRealname());
.. for all available fields
3) save dest
POST /user/{userId}/generalInformation
as summary for realname, email, username
.
Thank you!
One problem with this approach is that user cannot nullify optional fields since code is not applying the value if (input is empty and value) is null.
This might be ok for password or other required entity field but for example if you have an optional Note field then the user cannot "clean" the field.
Also, if you are using a plain FORM you cannot use PATCH method, only GET or POST.
If you are using Ajax you might be interested in JSON Merge Patch (easier) and/or JavaScript Object Notation (JSON) Patch (most complete); for an overview of the problems that one can find in partial updates and in using PATCH see also this page.
A point is that a form can only send empty or filled value, while a JSON object property can have three states: value (update), null (set null) and no-property (ignore).
An implementation I used with success is ZJSONPATCH
Focussing on the first view, which pattern would be a good practice?
My suggestion starts from a simple idea: how would you do this as web pages in HTML?
You probably start from a page that offers a view of the user, with hyperlinks like "Update profile", "Update role", "Change password". Clicking on update profile would load an html form, maybe with a bunch of default values already filled in. The operator would make changes, then submit the form, which would send a message to an endpoint that knows how to decode the message body and update the model.
The first two steps are "safe" -- the operator isn't proposing any changes. In the last step, the operator is proposing a change, so safe methods would not be appropriate.
HTML, as a hypermedia format, is limited to two methods (GET, POST), so we might see the browser do something like
GET /user/:id
GET /forms/updateGeneralInformation?:id
POST /updates/generalInformation/:id
There are lots of different spellings you can use, depending on how to prefer to organize your resources. The browser doesn't care, because it's just following links.
You have that same flexibility in your API. The first trick in the kit should always be "can I solve this with a new resource?".
Ian S Robinson observed: specialization and innovation depend on an open set. If you restrict yourself to a closed vocabulary of HTTP methods, then the open set you need to innovate needs to lie elsewhere: the RESTful approach is to use an open set of resources.
Update of a profile really does sound like an operation that should be idempotent, so you'd like to use PUT if you can. Is there anything wrong with:
GET /user/:id/generalInformation
PUT /user/:id/generalInformation
It's a write, it's idempotent, it's a complete replacement of the generalInformation resource, so the HTTP spec is happy.
Yes, changing the current representation of multiple resources with a single request is valid HTTP. In fact, this is one of the approaches described by RFC 7231
Partial content updates are possible by targeting a separately identified resource with state that overlaps a portion of the larger resource
If you don't like supporting multiple views of a resource and supporting PUT on each, you can apply the same heuristic ("add more resources") by introducing a command queue to handle changes to the underlying model.
GET /user/:id/generalInformation
PUT /changeRequests/:uuid
Up to you whether you want to represent all change requests as entries in the same collection, or having specialized collections of change requests for subsets of operations. Tomato, tomahto.
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"}