AI产品精选

Qdrant Edge 本地检索:延迟从52ms降至0.1ms

0.1ms vs 52ms. That’s what happens when you remove the network. For robots, drones, wearables, and...

精选理由

Qdrant Edge 把检索延迟从52ms降到0.1ms,适合机器人无人机等边缘设备,不用再等云端响应了。

AI 摘要

Qdrant Edge 在 Vector Space Day SF 上演示了完整的本地检索管线,无需网络跳转。相比云端52ms的延迟,本地运行仅需0.1ms。该方案面向机器人、无人机、可穿戴设备等边缘场景,使用与云端相同的 API 和引擎。Dylan Couzon 展示了这一对比结果,完整演讲视频已上线。

原文 · Qdrant

0.1ms vs 52ms. That’s what happens when you remove the network. For robots, drones, wearables, and...

0.1ms vs 52ms. That’s what happens when you remove the network. For robots, drones, wearables, and other edge devices, that’s often the difference between waiting on the cloud and responding immediately. At Vector Space Day SF, @DylanCouzon demoed Qdrant Edge, running the entire retrieval pipeline locally. Same retrieval engine. Same API. Same queries. Just no network hop. Full talk: youtube.com/watch?v=RRhbOR… 💬 0 🔄 1 ❤️ 4 👀 157 📊 1 ⚡