WeCommerce demo uses Weaviate and hybrid search to find products by vibe, not keywords
victorialslocum · x · 2026-07-29
A demo fashion e-commerce site called WeCommerce shows how product discovery can work with semantic search instead of exact keyword matching.
The stack stores each product in Weaviate with embeddings, then uses hybrid search that combines BM25 keyword matching with vector similarity. Users can search by vibe phrases like “garden tea party” or “berlin techno rave”, then refine results with standard filters such as category, price, and collection. The same approach is used for recommendations, replacing “customers also bought” with nearest-neighbor retrieval in embedding space.
More from Infra
- SK hynix reportedly signs long-term contracts with about 10 major customers — dejavucoder · 2026-07-29
- Shanghai Aishengna is said to be manufacturing DUV lithography tools — zephyr_z9 · 2026-07-29
- A vendor-agnostic Vulkan backend cuts edge inference latency from 30 ms to 3 ms — ppchaos · 2026-07-29
- pdf-mcp turns technical PDFs into structured text, images, and searchable context — tom_doerr · 2026-07-29
- Moonshot’s Kimi K3 is a 2.8T open-weight MoE model with 1M-token context — alex_verem · 2026-07-29
- New scaling law paper says repetition can beat paraphrasing for some pretraining regimes — burny_tech · 2026-07-29