soulcraft/brainy
1
0
Fork 0
Code Issues 1 Pull requests Projects Releases 335 Packages Wiki Activity Actions
brainy/docs/guides
History
David Snelling da7d2ed29d 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>
2026-01-06 12:52:34 -08:00
..
distributed-system.md docs: update documentation for accurate v3.9.0 API examples and technical claims 2025-09-22 16:19:27 -07:00
enterprise-for-everyone.md feat: v5.1.0 - VFS auto-initialization and complete API documentation 2025-11-02 10:58:52 -08:00
framework-integration.md feat: enhance framework integration and simplify codebase 2025-09-15 14:54:13 -07:00
import-anything.md fix: update all Stage 2 references to Stage 3 CANONICAL type counts 2025-11-06 09:40:33 -08:00
import-flow.md feat: migrate embeddings to Candle WASM + remove semantic type inference 2026-01-06 12:52:34 -08:00
import-progress-examples.md docs: remove external project references from documentation 2025-11-14 16:11:37 -08:00
import-progress-implementation.md feat: comprehensive import progress tracking for all 7 formats 2025-10-24 14:45:46 -07:00
import-quick-reference.md fix: resolve HNSW concurrency race condition across all storage adapters 2025-10-29 15:24:20 -07:00
migrating-to-v4.md feat: add import API validation and v4.x migration guide 2025-10-21 15:25:12 -07:00
MIGRATING_TO_V5.11.md docs: v5.11.1 brain.get() metadata-only optimization (Phase 3) 2025-11-18 15:44:48 -08:00
migration-3.36.0.md feat: implement always-adaptive caching with getCacheStats monitoring 2025-10-10 14:09:30 -07:00
model-loading.md feat: migrate embeddings to Candle WASM + remove semantic type inference 2026-01-06 12:52:34 -08:00
natural-language.md feat: v5.1.0 - VFS auto-initialization and complete API documentation 2025-11-02 10:58:52 -08:00
neural-api.md fix(vfs): prevent race condition in bulkWrite by ordering operations 2025-12-11 13:26:07 -08:00
nextjs-integration.md feat: enhance framework integration and simplify codebase 2025-09-15 14:54:13 -07:00
standard-import-progress.md docs: remove external project references from documentation 2025-11-14 16:11:37 -08:00
streaming-imports.md feat: implement progressive flush intervals for streaming imports 2025-10-22 17:36:27 -07:00
vue-integration.md feat: enhance framework integration and simplify codebase 2025-09-15 14:54:13 -07:00