HackerNews中文版

大家好，我开发了 brinicle，一个基于进程的 C++ 向量引擎，带有 Python 封装器，它在保持速度的同时，显著降低了内存消耗。在 120 万个亚马逊商品上，它实现了亚毫秒级的 P99 延迟。它还支持词汇搜索和混合搜索。在混合搜索中，我们没有尝试构建两个索引然后融合结果，而是创建了一个 HNSW 图，并将其用于语义、词汇和混合搜索。基准测试比较：https://brinicle.bicardinal.com/benchmark 混合搜索基准测试比较：https://brinicle.bicardinal.com/search_benchmark 代码库：github.com/bicardinal/brinicle

查看原文

Hey all, I built brinicle, an in-process C++ vector engine with a python wrapper that consumes substantially less memory, while staying quite fast. On 1.2 million Amazon products, it achieves sub-ms P99 latency. It also supports lexical search, and hybrid search. In the hybrid search, we did not try to build two indexes and then fuse results, we create ONE HNSW Graph and utilize it for semantic, lexical, and hybrid search. benchmark comparisons: https://brinicle.bicardinal.com/benchmark hybrid search benchmark comparisons: https://brinicle.bicardinal.com/search_benchmark Repository:: github.com/bicardinal/brinicle

磁盘优先的 C++ 向量引擎