Qdrant发布了filterable HNSW，比ACORN更快实现高召回率向量搜索过滤，两种方法各有优势。
ACORN在查询时解决向量搜索过滤问题，通过跳过过滤掉的邻居保持连通性。Qdrant的filterable HNSW采用索引时解决方案，在共享负载值的点间添加边。在100万向量1%过滤测试中，filterable HNSW在1.0ms内达到99.8%召回率，ACORN在4.7ms内达到67.7%。ACORN在处理宽值和AND过滤器时仍有优势，在有专门构建的图时效果最佳。
ACORN fixes filtered search at query time. Qdrant's filterable HNSW fixes it in the index. Filters ...
ACORN fixes filtered search at query time. Qdrant's filterable HNSW fixes it in the index. Filters can break an HNSW graph into disconnected islands, leaving search stranded and recall behind. ACORN works around that at query time by stepping through filtered-out neighbors. Filterable HNSW takes a different approach: it adds edges between points that share an indexed payload value, so the filtered graph remains connected. On a 1% filter over 1M vectors, filterable HNSW reached 99.8% recall at 1.0ms. ACORN reached 67.7% at 4.7ms. ACORN still earns its place for gaps like broad values and AND filters. But it's most effective when it has a graph built for filters underneath it. Full benchmark: qdrant.tech/articles/filte… 💬 0 🔄 1 ❤️ 1 👀 242 📊 1 ⚡