AI Value Mapping
This feature is currently in Beta.
Contents
What is AI Value Mapping?
Getting Started
What is AI Value Mapping?
AI Value Mapping allows you to map end-user data into categories with your organization’s internal representation (commonly known as enumerations “enums”). Leveraging advanced Large Language Models (LLMs), this QuickFix automatically maps source data to its nearest semantic match in the destination schema. This saves your data operations teams hours of manual work while dynamically adapting to evolving source data without requiring updates to formulas or webhooks.
Value Mapping can be used throughout Osmos in both Uploaders and Pipelines. It is most commonly used with an Uploader where end users map enumerations ("enums"). Enums are integrated as part of the Uploader Validation. Users map a group of constants to a specific valid option. The list of valid options is configured in your validation and the mapping occurs in the Value Mapping QuickFix.
Getting Started
There are two primary types of configurations.
Create a Dataset Table to hold your list of valid options. Then, set up a foreign key column in your Dataset Table. This configuration can be used for Pipelines and Uploaders. See the scenario below.
Create a dropdown-controlled field that contains your list of valid options in the code snippet for your embedded Uploader. Here is a link to this configuration.
Scenario
Customer ABC is ingesting employee data. The employee data includes employee type, which needs to be narrowed down to Customer ABC's list of valid options. In this scenario, see how to use Value Mapping to group a field to a specific list of options.
Features
Datasets
Pipelines and/or Uploader
Build the Dataset and Tables
Two Dataset Tables are required.
Create the Dataset.
Within your new Dataset, create the first table. In the new table, we will call it Employee_Category, and it includes only one field. This field called, Employee Category, is a required field and also must be a primary key. Other fields can be included but won't be used for this scenario.
Within your new Dataset, create the second table. The second dataset table, which we will call Employees, is the destination of the ingested data. AI Value Mapping requires a foreign key relationship on the destination field where the valid option will reside. Thus, it requires using a Dataset Table as your destination. In this scenario, the destination field is called Employee_Type. We will add the foreign key to the Employee_Type field to the Employee_Category Table and associated field. Once you select Add Foreign Key, it will create a foreign key icon on the Employee_Type field.
Note 2: If this destination will be an uploader, don't forget to create the Uploader from the Dataset Table.
Performing the AI Value Mapping
Uploader Scenario Configuration
Step 1: Go to your newly created Uploader and upload your data. Once the AutoMapping is complete, select the field you wish to initiate the AI Value Mapping. In our scenario it is Employee_Type.
Step 2: Select Transform on the left-hand side column mapping field. In this scenario, it will be the destination Employee_Type field.
Step 3: Select the AI Value Mapping QuickFix. AI Value Mapping will automatically run and map. You can then make adjustments and/or map any fields left unmapped.
Step 4. Hit Save when you are done to save the mapping logic.
Last updated
