Being as charitable as possible here, and Rerank 3 might be the bee's knees, but the examples are absolutely <i>awful</i>. Do you really need to use embeddings + a large language model to search for "action" and "Christian Bale" in two columns[1]?<p>Your interface can literally just be two dropdowns. I'd like to see things like "the actor that played the Joker in that movie about Bob Dylan" if you're really trying to flex your semantic search muscles.<p>[1] <a href="https://colab.research.google.com/drive/1sKEZY_7G9icbsVxkeEIA_qUthEfPrK3G?usp=sharing&ref=txt.cohere.com" rel="nofollow">https://colab.research.google.com/drive/1sKEZY_7G9icbsVxkeEI...</a>
Someone correct me if I'm mistaken, but Cohere appears to be using BM25 and semantic search (Embed Multilingual) individually as baselines in order to look better. A more suitable baseline would be the Reciprocal rank fusion (RRF) of BM25 and semantic search. And those latencies seem high; seconds to rerank?