David Snelling
da7d2ed29d
Major architectural changes: 1. EMBEDDINGS ENGINE (ONNX → Candle WASM): - Replace ONNX Runtime with Rust Candle compiled to WASM - Embedded model in WASM binary (no external downloads) - Quantized Q8 precision with <50MB memory footprint - Zero-download, offline-first operation - Same embedding quality (all-MiniLM-L6-v2) 2. REMOVE SEMANTIC TYPE INFERENCE: - Delete embeddedKeywordEmbeddings.ts (14MB of pre-computed embeddings) - Remove typeAwareQueryPlanner.ts and semanticTypeInference.ts - Remove VerbExactMatchSignal (uses keyword embeddings) - Update SmartRelationshipExtractor to 3 signals (55%/30%/15% weights) API CHANGES (requires v7.0.0): - Removed: inferTypes(), inferNouns(), inferVerbs(), inferIntent() - Removed: getSemanticTypeInference(), SemanticTypeInference class - Removed: TypeInference, SemanticTypeInferenceOptions types Users can still use natural language queries in find() - they just need to specify type explicitly for type-optimized searches. PACKAGE SIZE IMPACT: - Compressed: 90.1 MB → 86.2 MB (-4.3%) - Uncompressed: 114.4 MB → 100.3 MB (-12%) - ~448K lines of code removed 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
55 lines
1.5 KiB
TOML
55 lines
1.5 KiB
TOML
[package]
|
|
name = "candle-embeddings"
|
|
version = "0.1.0"
|
|
edition = "2021"
|
|
description = "WASM-based sentence embeddings using Candle and all-MiniLM-L6-v2"
|
|
license = "MIT"
|
|
|
|
[lib]
|
|
crate-type = ["cdylib", "rlib"]
|
|
|
|
[dependencies]
|
|
# Candle ML framework
|
|
candle-core = "0.8"
|
|
candle-nn = "0.8"
|
|
candle-transformers = "0.8"
|
|
|
|
# HuggingFace tokenizer with WASM support
|
|
# Use unstable_wasm feature which provides fancy-regex instead of onig
|
|
tokenizers = { version = "0.20", default-features = false, features = ["unstable_wasm"] }
|
|
|
|
# WASM bindings
|
|
wasm-bindgen = "0.2"
|
|
wasm-bindgen-futures = "0.4"
|
|
js-sys = "0.3"
|
|
web-sys = { version = "0.3", features = ["console"] }
|
|
|
|
# Serialization for model loading
|
|
serde = { version = "1.0", features = ["derive"] }
|
|
serde_json = "1.0"
|
|
|
|
# Error handling
|
|
anyhow = "1.0"
|
|
|
|
# Async
|
|
futures = "0.3"
|
|
|
|
# WASM compatibility - force getrandom with js/wasm_js features
|
|
# getrandom 0.2 (from tokenizers->rand) needs "js" feature
|
|
# getrandom 0.3 (from candle->rand 0.9) needs "wasm_js" feature + rustflags
|
|
[target.'cfg(target_arch = "wasm32")'.dependencies]
|
|
getrandom_02 = { package = "getrandom", version = "0.2", features = ["js"] }
|
|
getrandom = { version = "0.3", features = ["wasm_js"] }
|
|
|
|
[dev-dependencies]
|
|
wasm-bindgen-test = "0.3"
|
|
|
|
[profile.release]
|
|
opt-level = "z" # Optimize for size
|
|
lto = true # Link-time optimization
|
|
codegen-units = 1 # Single codegen unit for better optimization
|
|
panic = "abort" # Abort on panic (smaller binary)
|
|
|
|
[features]
|
|
default = []
|
|
simd = [] # Enable SIMD when browser support is available
|