Build Bots With Microsoft Teams Manual
User Manual:
Open the PDF directly: View PDF .
Page Count: 32
Download | |
Open PDF In Browser | View PDF |
Building Bots with Microsoft Teams Lab Manual Office365 Dev Bootcamp, Chennai. 1|Page Table of Contents 1)Overview of Microsoft Bot and Teams 2)Getting Started 3)Prerequisites 4)Creating QnA Service 5)Creating a QnA Maker Knowledge Base 6)Adding Chit Chat to KB 7)Creating a QnA Bot with Azure Bot Service 8)Testing Bot 9)Connecting QnA KB to QnA Bot 10)Testing FAQ Bot 11)Adding Bot to teams 12)Conclusion 2|Page --------------------------------------------Hands on Lab: Creating an Intelligent Bot using QnA Maker Service and Azure Bot Service ---------------------------------------------Microsoft Bot Chat bots are services that people interact with through conversation and messaging. It can perform automated tasks varying from simple to complex in nature. A very simple example of a Bot is a chatbot – which answers user queries based on keywords typed in by users. Microsoft Teams Microsoft Teams is the digital hub that brings conversations, content, assignments, and apps together in one place. ✓ ✓ ✓ ✓ ✓ Communicate through chat, meetings, and calls Collaborate together with integrated Office 365 apps Customize your workplace and achieve more Make calls in Office 365 and Teams Connect across devices 3|Page 1.Getting Started We’ll be running through an example of how to build, train, and deploy a question-andanswer bot based on FAQs. We will be using Microsoft’s Cognitive Services and Web App Bot Service, both of which can be found in the Azure portal (portal.azure.com). Then integrate it within Microsoft Teams. It will go over the complete start to finish process and show a working bot in MS Teams that answers Azure Bot Service FAQs. 2.Prerequisites We will need the below tools/apps to get started ✓ ✓ ✓ ✓ Visual Studio Azure Subscription Access to an MS Account MS Teams app installed 3.Creating a QnA Service QnA Maker allows you to quickly create a knowledge base to which you can link existing data sources to be used as a data repository for your bot. Before you can create a knowledge base, however, you have to create a QnA Service. Navigate here, sign in with you Azure credentials, then select Create a QnA Service 4|Page In the QnA Maker, fill out the required fields: 5|Page • • • • • • • • Fill in the Name with a unique name to identify this service. I will be using the name TeamsQnAService Select Free Trial as the Subscription Select F0 (3 calls per second) as the Management Pricing Tier Create a new Resource Group Choose the Free tier for the Search pricing tier option. If this option is greyed out, it means you already have a Free Azure Search tier deployed and you will need to use the Basic Azure Search Tier. Select East US or West US as the Search Location. This is where your Azure Search data will be deployed. Choose an App Name for your service Choose East US or West US or Central India(based on your region) for both the Website Location and App Insights Location. (Note: the search location can be different from the website location.) 6|Page Once all the fields are filled out and validated, click on Create to start deploying these services. You will see your new QnA Service show up in your list of subscriptions once the deployment is complete (this usually takes a few minutes). 7|Page 4.Creating a QnA Maker Knowledge Base Now that your QnA Service has been created, return here and scroll down to Step 2: Connect your QnA Service to your KB 8|Page • • • Select the same tenant as your Microsoft Azure account for the Microsoft Azure Directory ID Choose the Free Tier option for the Azure Subscription Name Finally, select the name of the QnA Service you created in the previous step from the Azure QnA Service dropdown, which should now be available In Step 3, name your KB for your reference (you can change it anytime). I have named my KB Test QnA KB. In Step 4, choose a source to populate your KB. Microsoft’s QnA Maker supports formats including .pdf, .doc, .docx, .xlsx, and others. For this demo, enter https://azure.microsoft.com/en-us/support/faq/ 9|Page into the URL field. This is the FAQ page for Microsoft Azure. When complete, your bot will be able to answer all the questions listed in this FAQ page. 5. Adding Chit Chat to your KB. ➢ Adding chit-chat to your bot makes it more conversational and engaging. The chit-chat feature in QnA maker allows you to easily add a pre-populated set of the top chit-chat, into your knowledge base (KB). ➢ This can be a starting point for your bot's personality, and it will save you the time and cost of writing them from scratch. ➢ This dataset has about 100 scenarios of chit-chat in the voice of three personas - The Professional, The Friend, The Comic. Choose the persona that most closely resembles your bot's voice. Given a user query, QnA Maker tries to match it with the closest known chit-chat QnA. 10 | P a g e Finally, select Create your KB in step 5. This will go through the link you provided and create a knowledge base for your service. When the KB is created, it opens the Knowledge Base page from which you can edit the contents of your KB. 11 | P a g e Now you can see the list of questions and answers which is pulled from the FAQ URL Click on Add QnA Pair to add a new row to the KB and enter the following. 12 | P a g e Select Save and train to save your changes and train the QnA Maker model. You can test your KB by choosing Test from the top bar. If you enter "Hi", the KB should respond with the answer you just entered. 13 | P a g e You also have the option of Inspecting this response by selecting the Inspect link. From here, you can add different phrasings for the same question and also view the Confidence Score the service assigned to the answer it returned. Remember to select Save and train to save your changes. You can now select Publish from the top bar. This will deploy your service to an endpoint that, once published successfully, can be used to feed your QnA Bot! You can always select Edit Service to return to your KB and make changes. 14 | P a g e In just a few minutes, you have easily created a QnA Maker Service using Microsoft’s Cognitive Services without writing a single line of code! 15 | P a g e 6. Creating a QnA Bot with Azure Bot Service Now that you’ve successfully created a QnA Maker Service, you can create a bot that uses the KB you created to respond to questions via the QnAMakerDialog. From the Azure Portal, Create a new bot service 1. Click Create new resource link found on the upper left-hand corner of the Azure portal, then select AI + Machine Learning > Web App bot. 2. A new blade will open with information about the Web App Bot. 16 | P a g e 3. In the Bot Service blade, provide the requested information about your bot as specified in the table below the image. 17 | P a g e 18 | P a g e ✓ ✓ ✓ ✓ ✓ ✓ ✓ ✓ ✓ Set Bot Name to your bot’s desired name. I will be using TeamsFAQBotIntegration for mine. Choose Free Trial for the Subscription Select Create new for Resource Group Choose Location Choose F0 (10K Premium Messages) for the Pricing Tier Select Question and Answer C# for the Bot template and hit Select Choose Create New for Azure Storage Choose App Insights Location Select Create 19 | P a g e Reference Setting Suggested value Description Bot name Your bot's display name The display name for the bot that appears in channels and directories. This name can be changed at anytime. Subscription Your subscription Select the Azure subscription you want to use. Resource Group myResourceGrou p You can create a new resource group or choose from an existing one. Location The default location Select the geographic location for your resource group. Your location choice can be any location listed, though it's often best to choose a location closest to your customer. The location cannot be changed once the bot is created. Pricing tier F0 Select a pricing tier. You may update the pricing tier at any time. For more information, see Bot Service pricing. App name A unique name The unique URL name of the bot. For example, if you name your bot myawesomebot, then your bot's URL will be http://myawesomebot.azurewebsites.net . The name must use alphanumeric and underscore characters only. There is a 35 character limit to this field. The App name cannot be changed once the bot is created. 20 | P a g e Setting Suggested value Description Bot template Echo bot Choose SDK v4. Select either C# or Node.js for this quickstart, then click Select. App service plan/Locatio n Your app service plan Select an app service plan location. Your location choice can be any location listed, though it's often best to choose the same location as the bot service. Azure Storage Your Azure storage account You can create a new data storage account or use an existing one. By default, the bot will use Table Storage. Application Insights On Decide if you want to turn Application Insights On or Off. If you select On, you must also specify a regional location. Your location choice can be any location listed, though it's often best to choose the same location as the bot service. Microsoft App ID and password Auto create App ID and password Use this option if you need to manually enter a Microsoft App ID and password. Otherwise, a new Microsoft App ID and password will be created for you in the bot creation process. The deployment will take a few minutes. Once the notification displays Deployment Succeeded, select Go To Resource on that notification. 21 | P a g e 7.Testing the Bot Once the bot’s resource window is open, click Test in Web Chat and type “hi” into the chat box. 22 | P a g e The bot should respond with “Please set QnAKnowledgebaseId and QnASubscriptionKey in App Settings. Get them at https://qnamker.ai. This is letting you know that your bot is not yet linked to the KB you created earlier. Let’s do that next. 8.Connecting your QnA KB to your QnA Bot Navigate back to the QnA Maker page and select the “My Knowledge Bases” tab. 23 | P a g e Select View Code from the row that lists the KB you created earlier to locate the appropriate values. Now navigate back to the Azure portal and select the Web App bot you just created. Select the Application Settings tab under App Service Settings and edit the QnAKnowledgebaseId, QnAAuthKey, and the QnAEndpointHostName fields to add the values of the QnA KB that you previously created. 24 | P a g e 25 | P a g e Click Save 9.Testing the FAQ Bot Once again in the Azure Portal, select the QnA Bot you created and hit Test in Web Chat and type “hi” into the chat box. The bot should respond with “Hello, ask me about Microsoft Azure!” as expected. 26 | P a g e This bot is now fully connected to your knowledge base! You can continue asking questions normally found in the FAQ directly through this bot. 27 | P a g e 10.Adding the Bot to teams This section will describe how to add the Bot that has been created into teams. 1. Navigate to the Channels tab. This shows all the supported channels that the Bot can be added to. In this demo, the Bot will be added to MS Teams. Select the team’s icon. Once selected select the Done. The Microsoft Teams now appears under connect to channels section. Agree to the terms and Conditions 28 | P a g e 29 | P a g e Now you can find the Teams channel added under Channels list 2. Click Settings Tab and Upload Icon for Bot 30 | P a g e 3. Now click the Microsoft Teams Text. This will open a new tab asking you to open the bot in Microsoft Teams. Depending on the browser being used the dialogue may be different. If using Chrome select ‘Open Microsoft Teams’. The bot will then open in MS Teams. Now try and type something else and see what the response is 31 | P a g e 11. Conclusion Hopefully this provides enough information in a clear and concise way to create a Bot and surfacing the Bot in Microsoft Teams. The one key point from using the QnA bots service is the more time you spend in the test and knowledge base sections the more reliable the answer would be. For more information on the QnA Maker visit: https://docs.microsoft.com/en-us/azure/cognitiveservices/qnamaker/overview/overview 32 | P a g e
Source Exif Data:
File Type : PDF File Type Extension : pdf MIME Type : application/pdf PDF Version : 1.7 Linearized : No Page Count : 32 Language : en-US Tagged PDF : Yes XMP Toolkit : 3.1-701 Producer : Microsoft® Word for Office 365 Creator : Jayanthi P Creator Tool : Microsoft® Word for Office 365 Create Date : 2018:10:23 00:48:47+05:30 Modify Date : 2018:10:23 00:48:47+05:30 Document ID : uuid:100A0814-8D56-4987-87B8-CE2E4487941C Instance ID : uuid:100A0814-8D56-4987-87B8-CE2E4487941C Author : Jayanthi PEXIF Metadata provided by EXIF.tools