Measured Results of Cohere Embed on Model Vault
AI summary
Aidan Gomez shares the results of ada_cx using Cohere Embed on Model Vault: median retrieval latency of 77 ms, 2.7x higher throughput per dollar for offline embedding, 4x smaller vector storage footprint with no significant drop in retrieval quality, and a top-10 recall rate of 90.7%.
Body
Some great results in here!:
By using Cohere Embed on Model Vault, @ada_cx achieved: * 77 ms median retrieval latency for faster, more accurate AI voice interactions * 2.7x greater throughput-per-dollar for offline embedding, increasing cost efficiency * 4x smaller vector storage footprint with no measurable retrieval degradation * 90.7% top-10 recall for accurate information retrieval
https://t.co/anwO9zwJtV