WordPress Search

Cohere embeddings were indeed considered, on average, more accurate than OpenAI embeddings by a WooCommerce client

But of course, it entirely depends on the data. No solution is absolute.

This is why it is so important to be able to compare AI models before deploying a vector search.

Vertex Matching Engine (ANN similarity search) was also considered, but the lack of aggregations (faceting) was a no go, unfortunately. I hope it will be added in the future.

(Facets are the #1 feature on e-Commerce search)

WPSOLR & Cohere: https://wpsolr.com

#wpsolr #woocommerce #cohere #vectorsearch

Read more related content

How Weaviate can help with inventory management in WooCommerce

Introduction Inventory management is a critical aspect of running an eCommerce store. It ensures that you have the right products in stock at the right

RAG does not seem suitable for consumer application search like e-commerce. Shouldn’t we instead consider using RFI, aka “Retrieval From Instructions”?

RAG sends the retrieved information to a generative model to construct a specific response. A typical example is an SEO consultant summarizing documents relating to

Comparing classic search, vector search, and Hybrid search: is it even possible (part 4: multilingual)?

(This is a follow up of Part 3 https://www.wpsolr.com/comparing-classic-search-vector-search-and-hybrid-search-is-it-even-possible-part-3/) Multilingual search is a huge topic nowadays, especially for WooCommerce in a globalised market.