QnA Maker enables you to power a question and answer service from your semi-structured content.

One of the basic requirements in writing your own bot is to seed it with questions and answers. In many cases, the questions and answers already exist in content like FAQ URLs/documents, product manuals, etc. With QnA Maker, users can query your application in a natural, conversational manner. QnA Maker uses machine learning to extract relevant question-answer pairs from your content. It also uses powerful matching and ranking algorithms to provide the best possible match between the user query and the questions.

Bot Framework v4 QnA Maker bot sample with ASP.Net Core 2.

This bot has been created using Microsoft Bot Framework, it shows how to create a bot that uses the QnA Maker Cognitive AI service.

The QnA Maker Service enables you to build, train and publish a simple question and answer bot based on FAQ URLs, structured documents or editorial content in minutes. In this sample, we demonstrate how to use the QnA Maker service to answer questions based on the knowledge base used as input.

• Follow instructions here to create a QnA Maker service.
• Follow instructions here to import a knowledgebase to your newly created QnA Maker service.
• Update the appsettings.json of the Bot with your kbid (KnowledgeBase Id), hostname, and endpointKey. You can find this information under "Settings" tab for your QnA Maker Knowledge Base at QnAMaker.ai
• (Optional) Follow instructions here to set up the QnA Maker CLI to deploy the model.

• Download the bot code from the Build blade in the Azure Portal (make sure you click "Yes" when asked "Include app settings in the downloaded zip file?").
  • If you clicked "No" you will need to copy all the Application Settings properties from your App Service to your local appsettings.json file.
  • This includes the QnAKnowledgebaseId, QnAAuthKey and QnAEndpointHostName.

• Navigate to the downloaded folder and open QnABot.sln in Visual Studio.
• Run the project (press F5 key)

• Install the .NET Core CLI tools.
• Using the command line, navigate to botbuilder-samples/samples/csharp_dotnetcore/11.qnamaker folder.
• Type dotnet run.

Microsoft Bot Framework Emulator is a desktop application that allows bot developers to test and debug their bots on localhost or running remotely through a tunnel.

• Install the Bot Framework Emulator version 4.3.0 or greater from here.

• Launch Bot Framework Emulator
• File -> Open Bot Configuration
• Enter a Bot URL of http://localhost:3978/api/messages

After creating the bot and testing it locally, you can deploy it to Azure to make it accessible from anywhere. To learn how, see Deploy your bot to Azure for a complete set of deployment instructions.

• Bot Framework Documentation
• Bot Basics
• QnA Maker Documentation
• Activity Processing
• Azure Bot Service Introduction
• Azure Bot Service Documentation
• Azure CLI
• msbot CLI
• QnA Maker CLI
• Azure Portal
• Restify
• dotenv