lakehouse/Cargo.toml
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

48 lines
1.2 KiB
TOML

[workspace]
resolver = "2"
members = [
"crates/shared",
"crates/proto",
"crates/storaged",
"crates/catalogd",
"crates/queryd",
"crates/aibridge",
"crates/ingestd",
"crates/vectord",
"crates/journald",
"crates/gateway",
"crates/ui",
]
[workspace.dependencies]
tokio = { version = "1", features = ["full"] }
axum = "0.8"
serde = { version = "1", features = ["derive"] }
serde_json = "1"
tracing = "0.1"
tracing-subscriber = { version = "0.3", features = ["env-filter", "json"] }
thiserror = "2"
uuid = { version = "1", features = ["v4", "serde"] }
chrono = { version = "0.4", features = ["serde"] }
tower-http = { version = "0.6", features = ["cors", "trace"] }
object_store = { version = "0.12", features = ["aws"] }
arrow = "55"
parquet = { version = "55", features = ["arrow", "async"] }
datafusion = "47"
bytes = "1"
futures = "0.3"
sha2 = "0.10"
url = "2"
tonic = "0.13"
prost = "0.13"
tonic-build = "0.13"
opentelemetry = "0.28"
opentelemetry_sdk = { version = "0.28", features = ["rt-tokio"] }
opentelemetry-stdout = { version = "0.28", features = ["trace"] }
tracing-opentelemetry = "0.29"
toml = "0.8"
csv = "1"
lopdf = "0.35"
encoding_rs = "0.8"
instant-distance = "0.6"