turbopuffer
@turbopuffer
{vector, full-text} search engine built on object storage. fast, cheap, 1T scale. powers Anthropic, Cursor, Notion, and more
加入 October 2023
5 正在关注 14.5K 粉丝
tpuf BM25 index tracks matching doc IDs per term:
[1, 8, 32, ... 1048576]
instead of IDs (big), we store the deltas (small):
[1, 7, 24, ... 16]
we prefix sum the deltas at query time to rebuild IDs
applying @lemire's SIMD speedup gave us up to 13% faster text search on ARM
显示更多
