Skip to content

Latest commit

 

History

History
 
 

14.nlp-with-orchestrator

README.md

NLP with Orchestrator

Bot Framework v4 NLP with Orchestrator bot sample

This bot has been created using Bot Framework, it shows how to create a bot that relies on multiple LUIS.ai and QnAMaker.ai models for natural language processing (NLP).

Use the Orchestrator dispatch model in cases when:

  • Your bot consists of multiple language modules (LUIS + QnA) and you need assistance in routing user's utterances to these modules in order to integrate the different modules into your bot.
  • Create a text classification model from text files.

Overview

This bot uses Orchestrator to route user utterances to multiple LUIS models and QnA maker services to support multiple conversational scenarios.

Prerequisites

OS Version Architectures
Windows 10 (1607+) ia32 (x86), x64
MacOS 10.15+ x64
Linux Ubuntu 18.04, 20.04 x64

This sample requires prerequisites in order to run.

  • Install latest supported version of Visual C++ Redistributable

  • Install latest Bot Framework Emulator

  • .NET Core SDK version 3.1

    > dotnet --version

  • Install BF CLI with Orchestrator plugin

    > npm i -g @microsoft/botframework-cli

    Make sure bf orchestrator command is working and shows all available orchestrator commands

    > bf orchestrator

To try this bot sample

  • Clone the repository

    > git clone https://github.com/microsoft/botbuilder-samples.git

  • CD samples\csharp_dotnetcore\14.nlp-with-orchestrator

    > cd samples\csharp_dotnetcore\14.nlp-with-orchestrator

  • Configure the LUIS applications (HomeAutomation and Weather) required for this sample.

    > bf luis:build --in CognitiveModels --authoringKey <YOUR-KEY> --botName <YOUR-BOT-NAME>
    • Update application settings in ./appsettings.json

  • Configure the QnA Maker KB required for this sample.

    > bf qnamaker:build --in CognitiveModels --subscriptionKey <YOUR-KEY> --botName <YOUR-BOT-NAME>
    • Update kb information in ./appsettings.json

  • Configure Orchestrator to route utterances to LUIS/QnA language services set up above

    • Download Orchestrator base model
    > mkdir model
> bf orchestrator:basemodel:get --out ./model
    • Create the Orchestrator snapshot
    > mkdir generated
> bf orchestrator:create --hierarchical --in ./CognitiveModels --out ./generated --model ./model

    The hierarchical flag creates top level intents in the snapshot file derived from the .lu/.qna file names in the input folder. As a result, the example utterances are mapped to HomeAutomation, QnAMaker and Weather intents/labels.

    • Verify appsettings.json has the following:

      "Orchestrator": {
   "ModelFolder": ".\\model",
   "SnapshotFile": ".\\generated\\orchestrator.blu"
}

  • Run the bot from a terminal or from Visual Studio, choose option A or B. A) From a terminal

    > cd samples\csharp_dotnetcore\14.nlp-with-orchestrator
> dotnet run

    B) Or from Visual Studio

    • Launch Visual Studio
    • File -> Open -> Project/Solution
    • Navigate to Orchestrator folder
    • Select OrchestratorSamples.sln file
    • Right click on 01.dispatch-bot project in the solution and 'Set as Startup Project'
    • Press F5 to run the project

Connect to the bot using Bot Framework Emulator

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

Further reading