Skip to content

Latest commit

 

History

History
56 lines (36 loc) · 2.38 KB

NLUTrainTask.md

File metadata and controls

56 lines (36 loc) · 2.38 KB
Raw

NLU CI/CD with NLUTrain Azure Pipelines task

To train an NLU model, add the following configuration to your pipeline:

- task: NLUTrain@0
  inputs:
    service: luis
    modelSettings: path/to/luis.json

You can also train a model from the generic utterances model using the utterances input.

See the endpoint configuration documentation for LUIS and Lex for more information on required and optional pipeline variables to set for the NLUTrain task.

Inputs to consider when using the NLUClean task:

Inputs

service

Specifies the NLU provider to use when deleting the model. Works for luis, luisV3 and lex.

utterances

(Optional) The path to the JSON array of generic utterances to include when training the model, relative to the workingDirectory.

modelSettings

(Optional) The path to the model settings file, relative to the workingDirectory. Find more information on configuring the model settings for LUIS and Lex.

includePath

(Optional) Path to custom NLU provider DLL. See documentation about Specifying the include path for more details.

workingDirectory

(Optional) Specifies the working directory to use when running the train command. Defaults to the Azure DevOps default working directory (i.e., the root directory of the repository).

nupkgPath

(Optional) Specifies the folder containing a .nupkg for dotnet-nlu to install from. When not specified, dotnet-nlu is installed from the default NuGet repository.

toolVersion

(Optional) Specifies the version of dotnet-nlu to install from the default NuGet repository. You cannot specify both the nupkgPath input and toolVersion.

toolPath

(Optional) Specifies the --tool-path option to use when installing dotnet-nlu. If not provided, the default tool path will be $(Agent.TempDirectory)/.dotnet.