註冊並分享邀請連結,可獲得影片播放與邀請獎勵。

turbopuffer
@turbopuffer
{vector, full-text} search engine built on object storage. fast, cheap, trillion scale. powers Anthropic, Harvey, Notion, Cognition, and more
加入 October 2023
6 正在關注    17.8K 粉絲
new: i8 vectors f32: 4 bytes/dim i8: 1 byte/dim 4x fewer bytes → 75% lower storage and query costs + faster queries when embedded with a quantization-aware model (e.g. voyage-4-large) trained on i8 vectors, recall loss can be ~0! docs:
顯示更多
0
2
160
11
轉發到社區