feat: migrate embeddings to Candle WASM + remove semantic type inference
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>
This commit is contained in:
parent
81cd16e41b
commit
da7d2ed29d
60 changed files with 3887 additions and 448557 deletions
|
|
@ -1,13 +1,11 @@
|
|||
/**
|
||||
* Asset Loader
|
||||
*
|
||||
* Resolves paths to model files (ONNX model, vocabulary) across environments.
|
||||
* Handles Node.js, Bun, and bundled scenarios.
|
||||
* @deprecated This class is no longer used. Model weights are now embedded
|
||||
* in the Candle WASM binary at compile time. Kept for backward compatibility.
|
||||
*
|
||||
* Asset Resolution Order:
|
||||
* 1. Environment variable: BRAINY_MODEL_PATH
|
||||
* 2. Package-relative: node_modules/@soulcraft/brainy/assets/models/
|
||||
* 3. Project-relative: ./assets/models/
|
||||
* Previously: Resolved paths to ONNX model files across environments.
|
||||
* Now: Use CandleEmbeddingEngine which loads embedded model automatically.
|
||||
*/
|
||||
|
||||
import { MODEL_CONSTANTS } from './types.js'
|
||||
|
|
|
|||
Loading…
Add table
Add a link
Reference in a new issue