How Shopify Improved Consumer Search Intent With Real Time Ml
Source
shopify.engineering
Author
Shopify Engineering
Date
Context
Shopify's search infrastructure updates numerical representations of product text and images as merchants change their listings. These representations, called embeddingA list of numbers representing a piece of text's meaning, so that similar meanings end up numerically close and can be searched.Full definition →, let search compare meaning and similarity rather than requiring identical words. Keeping them current helps the search system reflect newly added or edited products.
The company describes a streamingSending a model's response token by token as it is generated, so the reader sees text immediately instead of waiting for the whole answer.Full definition → pipeline that responds to content changes, prepares the new material, generates its embedding and sends the result to search systems. This adds operational complexity compared with periodic batch processing, but addresses a specific storefront need: merchants expect their edits to become searchable promptly.
Terms in this piece · Glossary
embedding — A list of numbers representing a piece of text's meaning, so that similar meanings end up numerically close and can be searched.
streaming — Sending a model's response token by token as it is generated, so the reader sees text immediately instead of waiting for the whole answer.
inference — Running a trained model to get answers — the phase where AI is actually used, as opposed to trained.
