Azure Bot Services: Deploy an Endpoint (Microsoft Teams)

501691c-AzureBotServices.png 

Within our Cognigy.AI platform you're able to connect your Cognigy resources to Azure Bot Services (formerly known as Microsoft Bot Framework) by using our Endpoint integration.

Inject & Notify

You can use the Inject and Notify functionality with this type of Endpoint. For further details see the Inject & Notify Documentation page.

Microsoft Teams Deployment Options

When used for MS Teams, this Endpoint is used to deploy a virtual agent as a direct messaging bot that users can directly chat with in a private chat session. For deploying a virtual agent that answers when it is mentioned by a user in a team channel post , please use the Microsoft Teams Endpoint.

Description

This tutorial covers the necessary steps for creating and connecting a Azure Bot Services Endpoint to Azure Bot Service (Microsoft Bot Framework). If you want more information about assigning a Flow to the Endpoint and setting up the Data Management see Endpoints.

Whitelisting of URLs

The Azure Bot Services Endpoint needs to make requests to the following domains. You can whitelist these in your proxy if necessary:

  • login.botframework.com/v1/.well-known/openidconfiguration
  • login.microsoftonline.com/botframework.com/oauth2/v2.0/token
  • *.botframework.com matching to the corresponding channel (e.g. msteams.botframework.com)

Setup Process

  1. Create an Azure Bot Services Endpoint in Cognigy.AI
  2. Integrate Azure Bot Services with your Bot Framework team
  3. Send messages to your Bot

1. Create a Azure Bot Services Endpoint

Location: Cognigy.AI

The first thing you need to do is to create a Azure Bot Services Endpoint in Cognigy.AI. In order to do this, navigate to your Project, click on the button in the lower left corner and create an Endpoint.

71157ce-azureSettings.PNGCreating an Azure Bot Services Endpoint

After creating your Endpoint, you should be navigated to the Endpoint configuration of your Azure Bot Services Endpoint. Here you need to set the Flow that the Endpoint should point to, and you can change the NLU Connector of the Endpoint.

settings.PNG

The Azure Bot Services Endpoint settings

Now that you have created the Azure Bot Services Endpoint, all that is left to do is to connect it to the Azure Bot Services. The Azure Bot Services Endpoint contains Azure Bot Services Settings which are two settings we need in order to connect to the Endpoint of the Azure Bot Service. We will need:

  • The app ID of your bot in Azure Bot Service
  • A secret of your bot in Azure Bot Service

The next chapter will describe where you can find this setting in Azure Bot Services.

2. Creating a bot in Azure Bot Service

Location: Azure Bot Service

Requirements
✔ Endpoint URL

In order to create a bot in Azure Bot Service, log into the Azure portal and search for "Bot Services". Create a new bot and choose "Azure Bot".

ABS.PNG

Select "Create" which will take you to the "create an azure bot" menu.

ABS2.PNG

Creating the Azure Bot

Complete the information on the next page and finish the creation of the bot. 

Once the bot appears on your list of Bot Services, select the bot and navigate to the "Configuration" tab. Add the Cognigy Endpoint URL you as the Messaging endpoint

ABS3.PNGAdding the Endpoint URL to the bot

You will also find the Microsoft App ID on the configuration page, which will be required in step 3. 

3. Connecting your Azure Bot Services Endpoint to Azure Bot Service

Cognigy.AI

Requirements
✔ Endpoint URL
✔ Bot in Azure Bot Service

To connect your Endpoint in Cognigy.AI to the Azure Bot Service, we need the App ID and the App Password of the bot from Azure Bot Service. To get these, go to the Configuration page of your bot in the Azure Bot Service Dashboard and find the Microsoft App ID of the bot. Copy the value and save it e.g. in a text editor. Afterwards, click on the link just above which says "Manage". This takes to you the App Registrations page for your bot where you can create a Client Secret. Create a secret and save it temporary e.g. in a text editor.

6bccac7-Screenshot_from_2019-07-15_15-30-49.png

Client Secret for Bot

Additional Security settings for Secure Azure Tenants

Some Azure tenants will require a manual adjustment of the signInAudience parameter in the App's manifest. This will be evident if messages are not received when first testing the bot. To change this value, from the Azure portal homepage, navigate to App Registrations > {Your Bot Registration} > Manifest and change the signInAudience parameter to AzureADMultipleOrgs.

Now you have the App Id and the App Password (Client Secret) so you can open the Azure Bot Services Endpoint in Cognigy.AI and put in the values in the corresponding fields in the Bot Framework Settings Form.

bfsettings.PNG

Configuring the Endpoint with the app credentials

You are now finished with connecting your Endpoint with Azure Bot Service! Link a channel to your bot in Azure Bot Service and talk to your Conversation AI in Cognigy.AI.

There are many channels that you are able to connect to via Azure Bot Services, one such example is a direct messaging bot in Microsoft Teams as show below:

MSTeams.PNG

Example of the direct messaging MS teams chatbot


Comments

0 comments

Please sign in to leave a comment.

Was this article helpful?
0 out of 0 found this helpful