Show HN: DuckDB community extension for prefiltered HNSW using ACORN-1

This is a fork of duckdb/duckdb-vss that adds ACORN-1 filtered HNSW search. The upstream extension has a critical limitation: WHERE clauses are applied after the HNSW index returns results, so SELECT ... WHERE category = 'X' ORDER BY distance LIMIT 10 often returns fewer than 10 rows. This fork pushes filter predicates into the HNSW graph traversal using the ACORN-1 algorithm, ensuring filtered queries return the correct number of results with high recall.

What changed:

• Filter predicates are evaluated during HNSW graph traversal, not after.
• ACORN-1 two-hop expansion through failed neighbors recovers graph connectivity under selective filtering.
• Selectivity-based strategy switching: >60% selectivity uses post-filter, 1-60% uses ACORN-1, <1% uses brute-force exact scan.
• Per-node expansion threshold (Lucene's 90% rule) skips two-hop when the neighborhood is already well-connected.
• Configurable thresholds: SET hnsw_acorn_threshold = 0.6 and SET hnsw_bruteforce_threshold = 0.01.

Benchmark (228k movies, 768-dim Nomic embeddings):

• Filter Selectivity ~1% to 5%: Upstream returns 0/10 results, while ACORN-1 returns 10/10.

Usage is seamless with standard SQL. The optimizer automatically detects the pattern and applies the filtered HNSW search. It supports prepared statements for parameterized query vectors. Currently, only FLOAT vectors are supported, and the index must fit into RAM, though it is persisted to disk during checkpoints.