lakehouse

Go to file

root 04770c97eb 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>

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

crates

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

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

data

100K embedding COMPLETE: 177/sec, 9.5 min, zero failures

2026-03-27 09:53:47 -05:00

docs

Sync memory + phases: all 15 phases marked complete

2026-03-27 19:34:15 -05:00

proto

Phase 5: hardening — gRPC, observability, auth, config