mirror of
https://github.com/samvallad33/vestige.git
synced 2026-04-25 00:36:22 +02:00
495a88331f
Four internal optimizations for dramatically better performance: 1. F16 vector quantization (ScalarKind::F16 in USearch) — 2x storage savings 2. Matryoshka 256-dim truncation (768→256) — 3x embedding storage savings 3. Convex Combination fusion (0.3 keyword / 0.7 semantic) replacing RRF 4. Cross-encoder reranker (Jina Reranker v1 Turbo via fastembed TextRerank) Combined: 6x vector storage reduction, ~20% better retrieval quality. Cross-encoder loads in background — server starts instantly. Old 768-dim embeddings auto-migrated on load. 614 tests pass, zero warnings.
34 lines
703 B
TOML
34 lines
703 B
TOML
[workspace]
|
|
resolver = "2"
|
|
members = [
|
|
"crates/vestige-core",
|
|
"crates/vestige-mcp",
|
|
"tests/e2e",
|
|
]
|
|
|
|
[workspace.package]
|
|
version = "1.6.0"
|
|
edition = "2024"
|
|
license = "AGPL-3.0-only"
|
|
repository = "https://github.com/samvallad33/vestige"
|
|
authors = ["Sam Valladares"]
|
|
|
|
[workspace.dependencies]
|
|
# Share deps across workspace
|
|
tokio = { version = "1", features = ["full"] }
|
|
serde = { version = "1", features = ["derive"] }
|
|
serde_json = "1"
|
|
thiserror = "2"
|
|
chrono = { version = "0.4", features = ["serde"] }
|
|
uuid = { version = "1", features = ["v4", "serde"] }
|
|
tracing = "0.1"
|
|
|
|
[profile.release]
|
|
lto = true
|
|
codegen-units = 1
|
|
panic = "abort"
|
|
strip = true
|
|
opt-level = "z"
|
|
|
|
[profile.dev]
|
|
opt-level = 1
|