Skip to content

Azure machine learning

Category: Cognitive.

Description: This advanced extension module enables the use of Azure Machine Learning (Azure ML), a cloud-based service that facilitates the development, training, and deployment of machine learning models.

Functionality: Use this extension module to integrate with the Azure Machine Learning (Azure ML) model created and trained in Azure. Leverage the inference (interpretation) capabilities of that model for use in Lynn.

Prerequisites

  1. Create a machine learning model in Azure Machine Learning: For more information, see Creating a Model

  2. Train the model: Follow the Microsoft tutorial for more information on how to train a model Train a Model

  3. Publish the model: For more information on how to deploy a model, see Deploy a model

Implementation

Expression to evaluate: String field where you can enter the entity that stores the information to be analyzed, or specific text in single quotes.

REST endpoint - Basic consumption information: The field to specify the integration endpoint is found in the Azure Machine Learning. To locate it, access the created model and then its endpoint. In the Consume tab, you will find the endpoint URL for the connection.

Authentication - Primary or Secondary key: The field to specify the authentication key is found in the Azure Machine Learning. To locate it, access the created model and then its endpoint. In the Consume tab, you will find two available keys; it is recommended to preferably use the first one.

Entity where the evaluation result will be deposited: Field where you must select or create an entity in which you want to deposit the API result.

The intent to execute in case of an error. The action flow will be interrupted, and the error description will be passed to the selected intent with the name: 'MLazureError': Dropdown list where the name of the intent for error handling must be selected.

Implementation Example

Field Value
Name: PruebaAzureMachineLearning
Expression to evaluate: ID_CLIENTE
REST endpoint Basic consumption info: https://endpoint-online-WS-compras.inference.ml.azure.con/score
Authentication Primary key or Secondary key: fXX7X9XXXXdXXXoO
Entity where the evaluation result will be deposited: RESULT_WS_COMPRAS
The intent to execute in case of an error. The action flow will be interrupted, and the error description will be passed to the selected intent with the name: 'MLazureError'.: Error_Handler

Result: RESULT_WS_COMPRAS <--

    {
    "option_1": Product_A,
    "option_2": Product_N,
    "option_3": Product_M,
    "option_4": Product_C
    }