Aidan Gomez· @aidangomez · X·· 2 小时前AI 评分25
AI 导读
这里有一些很棒的结果!: 通过在 Model Vault 上使用 Cohere Embed,@ada_cx 实现了: * 77 毫秒中位检索延迟,实现更快、更准确的 AI 语音交互 * 离线嵌入的每美元吞吐量提升 2.7 倍,提高成本效率 * 向量存储占用缩小 4 倍,且检索质量无可测量的下降 * 90.7% 的 top-10 召回率,实现准确的信息检索 https://cohere.com/customer-stories/ada
正文 · 原文
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
来源:Aidan Gomez · x.com