AutoMap

Getting started on your Data Transformation with AutoMap.

Overview

Data Transformation begins with column mapping. Our AutoMap makes column mapping –typically a manual process–faster (and more accurate) than before by automatically suggesting mappings. AutoMap uses generative AI to significantly reduce the need for manual column mapping that is required during data ingestion. AutoMap takes that task and automatically maps your columns quickly and more accurately. Immediately map things like “MSRP” to “Price” and “Energy” to “Calories”. No additional setup is required.

To automate this process, the underlying engine needs to understand the semantics of not just the field names but also the values in the field. The goal is to automate this process as much as possible, minimizing the need for manual mapping by data specialists. Files often have hundreds of columns that need to be mapped, and this is not just a matter of matching similar names; understanding the semantics is crucial. Generative AI is perfectly positioned to automate this time-consuming and laborious process.

Osmos uses LLMs (Large Language Models) to map the source schema to the destination schema. For example, this column was AutoMapped, leveraging a semantic understanding of information that allows Osmos to determine that the Drug Code maps to the NDC (which stands for the National Drug Code).

Getting Started

Step 1: Once the data is loaded the AutoMapping process automatically kicks off.

AutoMap in Action

Step 2: You can then review the mapped data and make any adjustments.

Step 3: If you want to clean up or modify the data in the cleaned column (or resolve errors), click on any cell in the cleaned column to trigger the Data Cleanup panel (on the left side panel).

The left side panel toggles between column mapping and data cleanup.

Step 3: Review the available options in the Data Cleanup panel and select one that best fits your data cleanup needs for this column:

1. QuickFixes - One-click, data-cleanup buttons that allow you to easily clean up your data for the most common scenarios for that data type (i.e. Date, Text, Numeric, etc.).

2. AI Value Mapping - LLM-driven data transformation that automatically maps source data to its nearest semantic match in the destination schema

3. Lookups - Data transformation that searches and returns specific data based on record matching. It often involves accessing a set of values or records stored in a Dataset Table.

4. SmartFill - Simple to use AI-powered data cleanup that learns and detects a pattern from examples of the clean data.

5. Formulas - Spreadsheet-style formulas used for complex transformations and data cleanup.

Note: If you are using the Uploader and need to edit specific cells in the output column after applying QuickFixes, click on any cell in the output column and provide a single-cell edit.

Step 4: Use the tabs at the top of the page to filter for rows with errors and rows flagged for review to confirm all issues with your data have been addressed.

Step 5: Once you have repeated Steps 1 through 4 for each of the required output columns (and any of the optional columns you want to include), you can proceed to the next step.