Search

WordPress AI Recommendations
- SEO, conversions -

Demo guides for WordPress & WooCommerce

A new WooCommerce demo with Weaviate and sentence transformers

— The embedding model — The demo uses the MiniLM-L6-v2 embeddings model https://lnkd.in/eCwAzH_h, installed on a self-hosted Weaviate Kubernetes cluster. This model is considered to have the best performance vs quality for all sentence transformer models. — Bigger models are better — Notice that much bigger models (GPU(s) required?) are now trusting the top of the MTEB leaderboard for the retrieval task https://lnkd.in/efmNJyTP — Indexing time — Also notice that indexing takes quite some time (around 1 per second) on a (single :)) CPU. — Quality — Quality looks inferior to the same demos with PaLM2, OpenAI or Cohere embeddings. For instance, check out the position of a mattress for keywords “something to sleep on”: – MiniLM-L6-v2 (not on first page !): https://lnkd.in/eUQnVBXV – OpenAI (1st position): https://lnkd.in/eVdYpC-P – PaLM2 (1st position): https://lnkd.in/e4FFVcUj – Cohere (2nd position): https://lnkd.in/eb3yCw-C –