Pre-Filtering vs Post-Filtering (and Why Qdrant Does Neither) - Qdrant
Aug 7, 2026Dylan Couzon

Summary
This post introduces and details the ACORN-1 algorithm as a query-time repair mechanism for filtered vector search, complementing the index-time optimizations of Filterable HNSW. It explains how ACORN enables traversal through neighbors that fail the filter, addressing cases where Filterable HNSW's extra edges are insufficient (e.g., values shared by too many points, AND filters over broad values). The post also highlights Qdrant's query planner, which dynamically selects the optimal routing strategy (Filterable HNSW, ACORN, payload index, or full scan) based on estimated filter selectivity, moving beyond static pre-filtering or post-filtering architectures.
More from the Filtered Vector Search trail
- How Lucy Built a Source-of-Truth Retrieval Layer for 2.8M+ SEC and DART Filings with Qdrant - Qdrant
- How Himalayas Built Semantic Job Matching for 100,000+ Remote Listings with Qdrant - Qdrant
- How to Tune Vector Search Without Guessing - Qdrant
- Filtered Vector Search: What ACORN Fixes, and What Fixes ACORN - Qdrant
- Lessons From Building E-Commerce Search on Qdrant - Qdrant