Visual Scout & Vertex AI Vector Search

Visual Scout by Google, lets users browse the lowes.com product library and quickly find products

Visual Scout is intended for consumers who consider products’ aesthetic qualities when making specific selections

Visual Scout dynamically changes the panel with elements that reflect client style and design preferences based on this feedback

For a given item, the Visual Scout API generates a vector match request

To obtain the most recent image embedding vector for an item, the request first makes a call to Vertex AI Feature Store

Visual Scout then uses the item embedding to search a Vertex  AI Vector Search index for the most similar embedding vectors

The Visual Scout API receives the available goods together with their metadata so that lowes.com can serve them

Vertex AI Feature Store online serving nodes receive new image embedding vectors, which are indexed by the item ID and the ingestion timestamp

Visual Scout uses Vector Search and Feature Store, two Vertex AI services, to replace items in the recommendation panel in real time