Blog

Retail: semantic catalog search and shelf computer vision

Postgres + pgvector vs a Dedicated Vector Database for Product Search

pgvector vs a dedicated vector database: at catalog scale, keeping embeddings in Postgres wins on consistency and ops; the crossover is millions of vectors.

Hybrid Search: Combining Keyword and Semantic Retrieval in One Ranking

Hybrid search runs keyword and semantic retrieval together and fuses the results with reciprocal rank fusion, so exact SKUs and descriptive queries both work.

A Checklist for Choosing a Site Search Vendor for a Large Catalog

A site search vendor checklist: relevance tested on your own catalog, index freshness against a fast feed, merchandising control, and pricing at scale.

Build vs Buy: Managed Search Platforms vs a Custom Semantic Search Stack

Build vs buy for semantic search: a managed platform, a full in-house build, or a custom stack on a managed embedding API and a vector extension.

Semantic Search vs Keyword Search: What Actually Changes for Shoppers

What changes for shoppers when a catalog moves from keyword to semantic search - and what gets harder: infrastructure, explainability, and per-query cost.

How Often Should a Product Catalog Be Re-Indexed for Search?

Catalog re-indexing frequency isn't one schedule: price and stock update near-real-time, semantic content re-embeds on change, and a full re-index stays rare.

What Does It Cost to Add Semantic Search to a Retail Catalog?

Semantic search cost has three parts: a one-time build, a per-search runtime cost, and infra to keep a retail catalog's index fresh, plus a one-off bulk embed.

A Checklist for Choosing a Computer Vision Vendor for Retail

A computer vision vendor checklist for retail: capture hardware fit, connectivity model, packaging retrain cadence, false-alert handling, and estate pricing.

How to Measure ROI on Semantic Search for E-commerce Catalogs

Semantic search ROI is mostly search-session conversion uplift, plus recovered zero-result sessions and merchandising hours saved - measured on search traffic.

Common Mistakes When Indexing a Catalog for Semantic Search

Semantic search catalog indexing mistakes: embedding raw HTML, ignoring price and stock, re-embedding on every write, and having no re-index path for new SKUs.