Blog

AI agents, RAG, and integrations — notes from production.

Semantic Search for Gifting: Recipient, Occasion, and Budget Queries

Semantic search for a gift finder extracts recipient, occasion, and budget from a query and ranks across categories by fit to the person, not keyword match.

Semantic Search at Marketplace Scale: Millions of SKUs, Thousands of Sellers

At millions of SKUs, semantic search outgrows a single Postgres instance - a dedicated vector store, ANN tuning, and a CDC re-embedding pipeline take over.

Semantic Search for a Small Catalog: When It Is Overkill

For a small catalog, semantic search is often overkill - good synonyms, clean filters, and a tidy attribute set usually beat an embedding pipeline.

Semantic Search for Books and Media: Theme, Mood, and Read-Alike Queries

Semantic search for books and media handles theme, mood, and read-alike queries, where the text is rich but the structured metadata is thin.

Semantic Search for Electronics Retail: Spec Queries and Comparison Intent

Semantic search for electronics retail turns spec queries into structured filters and handles comparison intent, so "32GB RAM under 1000" returns real matches.

Semantic Search for a Multi-Seller Marketplace: Ranking Across Sellers

Marketplace search ranking has to group the same product across sellers, weigh seller quality, and balance relevance against fairness and take rate.

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.