What is it? 

The Mapping Module helps you align supplier data with your own format, making it easier to integrate into your systems (PIM, ERP, etc.). You can also let your suppliers manage this step through their supplier portals.

How does it work?

The module automatically matches columns from supplier files to your taxonomy. If needed, you can manually map any unmatched fields. Once mapped, the system remembers the settings for future imports.

• Required fields must be mapped before you can proceed.
• Optional fields can be skipped if not needed.

Key Features

• Automatic Mapping: The module tries to match fields based on your previous mappings.
• Manual Mapping: For unmatched fields, you can manually map them to your taxonomy.
• Visual Indicators:
  • Red asterisk = Required fields (must be mapped).
  • Green checkmark = Fields successfully mapped.    
  • Gray bubbles = Optional fields (can be skipped).
• AI Source Indicator: To know if the field is used by AI models in subsequent steps.

With this tool, you can quickly standardize supplier catalogs and ensure they integrate smoothly into your internal systems.

(Beta) AI-Powered mapping suggestions

What is AI Mapping?

When you reach the Mapping step, SDM can automatically suggest which columns from your source's file should be mapped to each target field, powered by AI.

Instead of manually reviewing every column and field, the AI analyses your source data and proposes the most likely matches, so you can validate or adjust rather than start from scratch.

How it works

When you click Generate AI mapping, the AI examines:

• Column names from the source file
• Sample values from each column (actual data rows)
• Target field names, types, and descriptions from your taxonomy

Based on this analysis, the AI suggests a source column (or a combination of columns) for each unmapped target field.

Only fields that are not yet mapped are analysed, already mapped fields are left untouched.

Confident scores

Every AI suggestion includes a confidence score between 0 and 100%, indicating how certain the AI is of the match.

Suggestions below 70% are automatically excluded, the AI only surfaces matches it considers plausible.

The confidence score is shown alongside each suggestion in the mapping interface, so you can quickly decide whether to accept, adjust, or ignore it.

Why didn't a field get a suggestion?

The AI may not suggest a match for every field. This can happen when:

• No source column is similar enough (confidence would be below 70%)
• The field is already mapped from a previous import
• The target field's name or description doesn't have a clear counterpart in the source file

In those cases, the field will remain unmapped, and you can fill it in manually.

Tips for better suggestions

The AI performs best when:

• Column headers in the source file are descriptive (e.g. `product_name` rather than `col_A`)
• Sample data is present and representative
• Target fields have clear names or descriptions in your taxonomy

If a source file uses generic or cryptic column names, the AI may produce fewer or lower-confidence suggestions, and manual mapping will be more helpful.

Common Questions (FAQ)

How does AI Mapping agent understand our data?
LLMs are trained on extensive sets of text, allowing them to effectively interpret and map attributes. SDM benefits from the best AI models on the market - GPT 4.1 mini. 

Limitations

• File size: AI mapping supports source files with up to 2,000 columns. If a file contains more than 2,000 columns, AI mapping will not be triggered. You will need to map fields manually in that case.