Why Formatting Matters
Providing clean, correctly formatted data is key to getting accurate results from Taxonomy Matcher. Our system expects a specific CSV (Comma Separated Values - although we use semicolons!) structure.
Required Columns
Your CSV file must include these columns in the header row:
id: A unique identifier for each product. This is used to link the results back to your original data.title: The name or title of the product.description: A textual description of the product.
Delimiter: Use Semicolons (;)
Unlike standard CSVs that use commas, Taxonomy Matcher requires semicolons (;) to separate the values in each row.
Correct Example:
id;title;description
101;Organic Cotton T-Shirt;Soft, breathable crew-neck t-shirt made from 100% organic cotton.
102;Wireless Noise-Cancelling Headphones;Over-ear headphones with active noise cancellation and Bluetooth 5.0.
Incorrect Example (Using Commas):
id,title,description
101,Organic Cotton T-Shirt,"Soft, breathable crew-neck t-shirt made from 100% organic cotton."
Character Limits
For optimal processing, the title and description fields are automatically truncated to 2000 characters if they exceed this limit.
Optional Columns
You can include other columns in your CSV (e.g., price, brand, image_url), but they will be ignored by the matching process. Only id, title, and description are used by the AI.
File Encoding
Save your CSV file using UTF-8 encoding to ensure special characters are handled correctly.
Uploading vs. Pasting
- Pasting: Copy the text directly from your spreadsheet or text editor (including the header row) and paste it into the text area on the Matcher page.
- Uploading: Save your spreadsheet as a
.csvfile (ensuring semicolon delimiter and UTF-8 encoding) and upload it using the file input on the Matcher page.
By following these simple formatting rules, you'll ensure Taxonomy Matcher can process your data smoothly and provide the most accurate category matches.