Blog

Retail: semantic catalog search and shelf computer vision

Semantic Search for Sporting Goods: Sport, Skill Level, and Fit

Semantic search for sporting goods reads sport, skill level, and conditions from a query, with size and spec kept as filters so the result actually fits.

Semantic Search for Jewelry and Watches: Occasion, Material, and Gift Intent

Semantic search for jewelry reads occasion, material, and gift intent from natural queries, while price and metal specifics stay as exact filters.

Semantic Search for Furniture and Home Decor: Style, Room, and Dimensions

Semantic search for furniture handles style, room, and dimension queries - and dimensions have to work as hard filters so results actually fit the space.

Semantic Search for Home Improvement: Project Queries and Compatibility

Semantic search for home improvement handles project queries and compatibility - the parts have to fit each other, and fitment data is the real dependency.

Semantic Search for Pharmacy and Health Retail: Symptoms, Not Just SKUs

Semantic search for pharmacy retail maps symptom and need queries to product categories, with a firm line before anything that reads as medical advice.

B2B and Parts Catalogs: Why Search Needs Exact Match First, Semantic Second

B2B parts catalog search is known-item first - part numbers, codes, and fitment need exact lexical match; semantic retrieval covers the descriptive queries.

Semantic Search for Fashion: Style, Occasion, and Fit Queries

Semantic search for fashion ecommerce handles occasion and style queries only if that data is in the catalog - visual similarity is a separate image problem.

Semantic Search for Grocery: Substitutions, Pack Sizes, and Dietary Filters

Semantic search for grocery handles substitution and recipe queries well - but dietary and allergen constraints belong in hard filters, not soft ranking.

What to Put in a Product Embedding: Composing the Text You Index

Product embedding text should be a clean composed field - title, key attributes, category, short description - not raw HTML or boilerplate.

The Async Re-Embed Pipeline: Keeping a Vector Index Fresh Without Blocking Writes

An async re-embedding pipeline: a write trigger, a filter for semantic-field changes, and a queue worker - so catalog updates never block on an embedding call.