soulcraft/brainy
1
0
Fork 0
Code Issues 1 Pull requests Projects Releases 335 Packages Wiki Activity Actions
565 commits 8 branches 522 tags 189 MiB
Commit graph

4 commits

Author SHA1 Message Date
David Snelling
677e2d6624 perf: 580x faster embedding init - separate model from WASM 
Cloud Run cold starts taking 139 seconds due to 90MB WASM file with
embedded 87MB model weights. WASM compilation scales with file size.

Solution: Split into 2.4MB WASM (code only) + external model files.
- WASM compile: 139,000ms → 6-8ms
- Model load: N/A → 30-115ms
- Total init: 139,000ms → 136-240ms

New modelLoader.ts handles all environments:
- Node.js: fs.readFile()
- Bun: Bun.file()
- Bun --compile: auto-embedded assets
- Browser: fetch()

Zero config - same API, npm package includes model files.

🤖 Generated with [Claude Code](https://claude.com/claude-code)

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
 2026-01-06 17:18:58 -08:00
David Snelling
5d9ec5bb16 fix: resolve WASM loading for Bun --compile single-binary executables 
Both roaring-wasm and candle-wasm now work correctly in all environments:
- Node.js (fs.readFileSync)
- Bun runtime (Bun.file)
- Bun --compile (embedded assets via import { type: 'file' })
- Browser (fetch)

roaring-wasm:
- Created src/utils/roaring/index.ts wrapper
- Uses browser bundle which has WASM embedded as base64
- Top-level await ensures initialization before use
- Zero environment detection needed (works everywhere)

candle-wasm:
- Created src/embeddings/wasm/wasmLoader.ts universal loader
- Uses Bun's import { type: 'file' } to embed 93MB WASM in compiled binary
- Fixed browser detection (Bun defines 'self', check for 'document' instead)
- Simplified CandleEmbeddingEngine.ts to use wasmLoader

Binary size verification:
- Minimal Bun binary: 100MB (runtime only)
- Brainy binary: 199MB (100MB runtime + 93MB WASM + 6MB JS)
- No duplication: WASM embedded exactly once

Test results:
- Node.js: 1190/1190 tests pass
- Bun runtime: 8/8 tests pass
- Bun --compile: 8/8 tests pass

🤖 Generated with [Claude Code](https://claude.com/claude-code)

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
 2026-01-06 14:09:02 -08:00
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
David Snelling
1f59aa2013 feat: replace transformers.js with direct ONNX WASM for Bun compatibility 
- Remove @huggingface/transformers dependency (539MB native binaries)
- Add direct ONNX Runtime Web embedding engine
- Bundle all-MiniLM-L6-v2-q8 model (24MB, no runtime downloads)
- Works with Node.js, Bun, and bun build --compile
- Air-gap compatible: fully self-contained, no internet required

New WASM embedding components:
- WASMEmbeddingEngine: Main integration class
- WordPieceTokenizer: Pure TypeScript tokenizer
- EmbeddingPostProcessor: Mean pooling + L2 normalization
- ONNXInferenceEngine: Direct ONNX Runtime Web wrapper
- AssetLoader: Model file loading

Tests added:
- 11 WASM embedding integration tests
- 8 Bun compatibility tests

New npm scripts:
- test:wasm - Run WASM embedding tests
- test:bun - Run tests with Bun
- test:bun:compile - Build and run compiled binary
 2025-12-17 17:42:37 -08:00