How Shopify Improved Consumer Search Intent With Real Time Ml
Source
Shopify Engineering
Author
Shopify Engineering
Date
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.
inference — Running a trained model to get answers — the phase where AI is actually used, as opposed to trained.
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.
Why it matters
A concrete architecture for keeping 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 → fresh at scale — shared embedding primitives plus 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 →inferenceRunning a trained model to get answers — the phase where AI is actually used, as opposed to trained.Full definition → — which is the hard part of shipping semantic search that batch reindexing quietly hides.
