HNSW vector index: 100K search in 27ms (58x faster than brute-force)

- instant-distance HNSW implementation for approximate nearest neighbors
- HnswStore: build from stored embeddings, in-memory index, thread-safe
- POST /vectors/hnsw/build — build index from Parquet (100K in 35s release)
- POST /vectors/hnsw/search — fast ANN search
- GET /vectors/hnsw/list — list loaded indexes

Benchmark (100K × 768d, release build):
  Brute-force: 1,567ms
  HNSW:           31ms (50x)
  HNSW warm:      27ms (58x)

Build cost: 35s one-time for 100K vectors (release mode)
ef_construction=40, ef_search=50 — good recall/speed balance

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

This commit is contained in:

root

2026-03-27 20:00:50 -05:00

co-authored by

Claude Opus 4.6

parent 8282842eaf

commit 04770c97eb

7 changed files with 289 additions and 2 deletions

									
										crates/vectord/Cargo.toml
									
		+1
		
												View File
												
				@@ -17,3 +17,4 @@ object_store = { workspace = true }

				parquet = { workspace = true }

				arrow = { workspace = true }

				chrono = { workspace = true }

				instant-distance = { workspace = true }