Can someone please provide the solution for integrate LUIS with multiple QnA KB.
You would basically create a LUIS app, then for each intent have it call the appropriate QnA KB. Tutorial on how to do this is here, "Integrate QnA Maker and LUIS to distribute your knowledge base".
Related
I'm creating a new bot using the Bot Composer and QnA Maker. The general set-up is pretty straight forward and the bot now answers questions from the QnA Maker knowledgebase. However it's looking like there are some limitations that I can't find reference to in the documentation. Specifically:
We have an existing qna knowledgebase that is used with a custom coded bot. It's updated by various scripts and custom user interfaces. To use this knowledgebase in the composer I seem to need to connect to it so it creates a local copy within composer. At this point I can only update it via composer?
Using the QnA intent recognised trigger with the pre-configured actions doesn't seem to offer any customisable parameters, such as accuracy threshold and metadata filtering?
Using the QnA intent recognised trigger with the pre-configured actions doesn't seem to offer the users alternative answers (if multiple results are returned from qna maker) or allow any form of user feedback to qna maker.
Please can anyone confirm that these points are correct or if I'm missing something. I have attempted to use the 'QnA Maker dialog' action which enabled you to add various parameters etc. but can't see any documentation on how to process questions and answers with it.
Thanks
We want to use sprinklr platform to use qna and LUIS. How can it be integrated?
You can use these docs for LUIS and QnA integration
https://learn.microsoft.com/en-us/azure/cognitive-services/qnamaker/choose-natural-language-processing-service
https://learn.microsoft.com/en-us/azure/bot-service/bot-builder-tutorial-dispatch?view=azure-bot-service-4.0&tabs=cs
I have created the Knowledge base in the QnA maker and tested it as well. It is working fine. But while creating the Web app bot service in Azure portal I selected Basic Bot for which it asked for a Luis Account. I did not have any but there was a provision to create new and I did so. Post which the bot service was deployed successfully.
The problem is I am not able to connect it to the QnA maker knowledge base. The fields like QnAKnowledgebaseId, QnAAuthKey, and the QnAEndpointHostName are not at all present under application settings where I can input the values. I tried to add an additional application string with the details but still it did not work. My knowledgebase is ready but the bot service does not work with it. Clearly you can see in the images there is no fields where I can put my QnA knowledgebase configurations
Bot application setting:
Application setting:
The bot service can be integrated with the QnA maker just through portal itself.I created the Bot service directly from the QnA maker and it picked up the Details of the QnA maker automatically.The webapp bot is up and running answering the questions as per the repo in the QnA Maker
I am using a dispatch model with 2 LUIS model and 1 QnA maker. On emulator everything works but after publishing, when I debug it on Web Chat channel on Azure or on Teams my QnA Maker utterances always returns
No such host is known.
I have tried using both the host names one from the settings page in QnA maker portal and westus.api.cognitive.microsoft.com/Qnamaker
Can someone help.
Well, I found out the reason it wasn't just QnA Maker but also LUIS , I have to update the LuisAPIHostName in the appsettings.json from westus to westus.api.cognitive.microsoft.comand update LUIS Host Name as $"https://{configuration["LuisAPIHostName"]}") in BotServices
And off course has to publish it again.
We are automating our internal policies using Chat BOT. Most of the policies are in pdfs and word documents, what is the best way to store data for responses ? To extract content from documents and store in databases or any other way ? Because in each document there are many possible questions users can ask.
One way is if you look into MS's Cognitive Service called QnA Maker.
What is QnA Maker here.
Sample Bot implementing QnA Maker here.