My chatbot has been down for the last few days (quota for free conversations has been exceeded), and I am seriously thinking of moving to a paid plan.
Please see attached the error returned when initiating a conversation from emulator.
The documentation to move to a paid plan is not clear at all.
Can someone please list the steps that I have to take or pinpoint me to the proper documentation please?
Technology : MS Botframework with nodejs (luis,qna,language detection)
I suppose I have to create a key in azure and insert it in the luis.ai app. But searching for LUIS in azure returns no result.
Grateful if you guys can help.enter image description here
Seems you are trying to implement LUIS on azure portal and want to know more about pricing but cannot get LUIS on azure portal.
Well,Follow the below steps to know how you would implement that.
LUIS :
Step 1:
For LUIS go to your azure portal then and click on Create a resource finally search by Language Understanding you would get that. See the below screen shot:
Step 2:
Once you type Language Understanding you would get below Option. See the screen shot below:
Once you are done with setup you should click Keys and Endpoint to call from your application. See the screen shot below:
though correct official document reference you would get there also given here as well.
1. Luis Official Document
2. Pricing
For your information pricing varies based on Region. Usual price is:
You can do 50 transaction per second and have to pay $1.5 per 1000
(one thousand transaction)
QnA Maker :
For QnA maker you could also follow above steps. See the following screen shot:
QnA Maker Official Document
Pricing
Language Detection:
If you plan to detect your language you could use Text Analytics which provides advanced natural language processing and identify the language of the text with language detection See the screen shot below:
Language Detection Official Document
Pricing
Note: All the service has language support for Node.js. Hope this would help.
Related
I am planning to build a chat bot using either azure framework composer, aws lex or google dialogflow but none seem to offer an easy way to have a map/location picker. It should be an straight forward interaction with user where based on a button click the user can then pick the precise location from the map.
Has anyone done something like that?
Many thanks.
I don't believe that any pure NLU framework is going to offer you that level of functionality.
The true purpose behind the likes of Amazon Lex, Google Diaglogflow is to perform intent detection and classification. It is up to the developer to build out the desired functionality associated with each of the configured intents.
What it may practically come down to is presenting the chat user with a map/location popup within the chat widget. The user could then select their current/desired location which gets sent back to the NLU framework for fulfillment.
We've just published our first app in Google Workspace Marketplace (a google docs add-on) and can't figure out how, or if, it is possible to setup an email or other notification (slack notification would be cool) for our Customer Success team to be notified when a user leaves a review of the app.
Appreciate that if we get thousands we will probably turn the notifications off (or filter them in some way), at this early stage though, we're very eager to act on any feedback.
Thanks!
Disclaimer: I am creator of Obsei, and this might be biased answer.
You can try Obsei: an open-source low-code AI powered automation tool.
It can monitor App and Play stores for customer reviews and send notification Slack when someone add review there. Also Obsei can classify review contextually to classify it into issue categories. Refer below image.Obsei workflow
All of these can be achieved free without any cloud hosting requirement. Refer link for more detail.
Happy to answer any queries in this regards.
Hi,
I'm unable to get suggestions for qna pair in qna maker after enabling active learning feature, and when filter by suggestions is ON I'm getting the display as above. Though the qna pairs are added i can not see them after the filter by suggestion option is ON. So can you please suggest me how to solve this senario. I can get the answer for the qna pair while testing in bot framework emulator.
Thanks
Active Learning suggestions will not appear immediately after turning the feature on in the portal. They'll appear after the qna model has received enough feedback to offer up a suggestion.
See comment I wrote back in Feb of last year regarding how suggestions are trigged and when they'll show up in the portal, in MS Docs discussion for full context of the conversation. But the main thing is this:
When there is a low confidence score difference between the top answers, we collect weighted implicit and explicit feedback to cluster suggestions for any QnA ID.
=> When enough feedback is collected for any given suggestion, it will show in the KB.
More specifically, we cluster similar user queries to generate suggestions. When minimum required feedback is collected, only then will the suggestions show in the KB.
The QnA team wants to avoid publicly divulging the exact logic of what
exactly is the "minimum required feedback" and how often suggestions
are generated (besides, the team is working on improving and
optimizing the logic behind active learning as well)
--however to see suggestions appear in the qnamaker.ai portal:
not only ensure that you've given the bot enough feedback
but also
give the back end "some time" to allow for the suggestions to appear
in the portal. Again, feedback is collected when your user types in a
query that returns answers from QnA that have confidence scores that
are close together.
It is also good to note that feedback is not collected in the Test
panel in the qnamaker.ai portal as of now. You will need to chat with
your bot via emulator or a channel to provide feedback to your bot
that it can use for active learning.
Additional resource: 48.qnamaker-active-learning-bot
I am evaluating MS Health Bot service and able to create and test custom scenarios. However, I was looking at extending existing in-built scenario like "I have a headache" and customize based on my need. I could see product features say we can extend existing scenarios but I don't see any documentation on how to do it. Anyone aware of how to extend existing scenario?
Thanks
Monu
Additional Information:
Health Bot Service provided three templates in the catalog - Provider Lookup, File a claim, Handoff to a human. There are few others with Coming Soon tag.
Scenarios template catalog
However, I thought, I can use any of the already trained bot scenario to handle medical conditions like "I have a headache" as shown in the diagram below.(which shows up in empty designer page on the right chat widget)
Demo chat for "I have a headache"
So my revised question is "we will be able to extend only scenario that is part of template catalog and our own created scenario". Is that correct understanding?
Thanks in advance
You can customize pre-built scenarios in the Healthcare Bot through the Scenario Designer. In the Healthcare bot service you created, click on Manage Account. If you do not have any scenarios configured, either select a template scenario or create a new blank scenario. Otherwise, click on the name of the scenario to open the designer. From here, you can customize the scenario as needed by either adding more scenario elements from the top pane or modifying elements in the scenario.
At the moment it appears that you are only able to modify the three provided templates. You do not have access to the other scenarios like 'I have a headache' in the healthcare manager. The Healthcare Bot Service is relatively new so that might change in future updates.
I would recommend looking at the topics under Scenario Authoring in the Healthcare Bot Documentation for more details on creating and editing scenarios.
Hope this helps!
I'm trying to set up a first-time project in the Google Spectrum Database API, but it's not showing as an option in the API list.
I read these instructions, and did the following :
Go to the Google Cloud Console.
Select a project.
In the sidebar on the left, select APIs & auth.
In the displayed list of APIs, make sure the Google Spectrum Database API status is set to ON. (Google Spectrum Database not showing)
I'm simply trying to set up a project for testing purposes, not commercial.
Any thoughts or guidance is greatly appreciated.
This has just been updated. I asked what's up here: https://support.google.com/spectrumdatabase/contact/spectrum_feedback
and they replied with:
It may have not shown up earlier today, but please take another look. The "Google Spectrum Database API" should be visible in the (long) list of APIs by now.
If you have further questions, please ask in the the support group (https://groups.google.com/d/forum/google-spectrum-db-discuss) linked from the getting started page: https://developers.google.com/spectrum/paws/gettingstarted#questions
Sincerely,
The Google Spectrum Database Team
I checked and it is indeed there now. Hope this helps.