微软机器人框架技能

Question

Is it possible to have a separate dispatcher for skill (dispatch template and QnA model of its own)? I am not seeing this option in the skill template. Also if I can configure one how do you make it work with a parent LUIS dispatcher? I am very new to skills and following the below documentation ... https://microsoft.github.io/botframework-solutions/skills/tutorials/customize-skill/csharp/1-intro/ Thanks

Answer 1

Just to provide more context to the Dispatch model in Virtual Assistant as you are new to skills.

The Dispatch model brings together the LUIS models and QnAMaker Knowledge bases into one experience by extracting utterances from each configured LUIS model and questions from QnA Maker and then creating a central dispatch LUIS model . The Dispatch model is used at the core of each project created using the template. It is referenced within the MainDialog class to identify whether the target is a LUIS model or QnA . In the case of LUIS, the secondary LUIS model is invoked returning the intent and entities as usual.

Dispatcher is also used for interruption detection and Skill processing whereby your Dispatch model will be updated each time you add a new Skill . The Virtual Assistant integrates Skill support for your assistant, enabling you to easily register skills through the execution of the botskills command-line tool. The ability to trigger skills based on utterances relies heavily on the Dispatcher which is automatically provisioned as part of your assistant deployment .

I would suggest you to read through the following this documentation to get a hang of the terminologies and components involved and then follow the tutorial.