The Microsoft LUIS NLU Connector uses the LUIS NLU engine to score the intent of the user's sentence and to extract slots. This guide covers the necessary prerequisites for setting up the LUIS NLU Connector, and how to connect a LUIS app to a LUIS NLU Connector.
In order to use the LUIS NLU Connector, a working LUIS app is required. To setup the app, follow the guides below:
Publishing in production
Note that it is required to publish your app in production in order for the NLU Connector to work
Use Cognigy Default Replies
To use Cognigy Default Replies, you have to replicate the LUIS intent name as a Cognigy intent, but without giving it any example sentences. Then you can use Default Replies just like you do with Cognigy.
To create a LUIS NLU Connector, navigate to the Cognigy.AI project and add a new resource of type
NLU Connector. Give it a name and select the type
In order for the NLU Connector to connect to the LUIS app, it needs an authentication URL, which can be found in the LUIS app. In the LUIS app, navigate to
Manage > Azure Resources and copy the
Example Query as seen in the screenshot below. Paste this URL into the
Authentication URL field in the
LUIS Settingsof the NLU Connector
To use the LUIS NLU Connector, open an Endpoint in Cognigy.AI, and select the LUIS NLU Connector from the list of NLU Connectors. The Endpoint will then forward the messages to your LUIS app for intent scoring and slots extraction.
Updated over 2 years ago