soulcraft/brainy
1
0
Fork 0
Code Issues 1 Pull requests Projects Releases 335 Packages Wiki Activity Actions
brainy/src
History
David Snelling 8cca096d7e feat: expose neural entity extraction APIs (v5.7.6 - Workshop request) 
Addresses Workshop team's request for direct access to neural extraction classes.

**Changes:**

1. **New Exports** (src/index.ts):
   - `NeuralEntityExtractor` - Full extraction orchestrator
   - `SmartExtractor` - Entity type classifier (4-signal ensemble)
   - `SmartRelationshipExtractor` - Relationship type classifier
   - Types: `ExtractedEntity`, `ExtractionResult`, `RelationshipExtractionResult`, etc.

2. **Package.json Subpath Exports**:
   ```typescript
   // Enable direct imports:
   import { NeuralEntityExtractor } from '@soulcraft/brainy/neural/entityExtractor'
   import { SmartExtractor } from '@soulcraft/brainy/neural/SmartExtractor'
   import { SmartRelationshipExtractor } from '@soulcraft/brainy/neural/SmartRelationshipExtractor'
   ```

3. **New brain.extractEntities() Method** (brainy.ts:3254):
   - Alias for `brain.extract()` with clearer naming
   - Documented with examples and architecture details
   - 4-signal ensemble: ExactMatch (40%) + Embedding (35%) + Pattern (20%) + Context (5%)

4. **Comprehensive Documentation** (docs/neural-extraction.md):
   - Complete neural extraction guide (200+ lines)
   - API reference for all extraction classes
   - Performance optimization tips
   - Import preview mode documentation
   - Confidence scoring explanation
   - 42 NounType detection methods
   - Troubleshooting guide
   - Real-world examples

5. **README Updates**:
   - Added "Entity Extraction" section with examples
   - Links to neural extraction guide
   - Import preview mode link

**Features:**
- ⚡ Fast extraction: ~15-20ms per entity
- 🎯 4-signal ensemble architecture
- 📊 Format intelligence (Excel, CSV, PDF, YAML, DOCX, JSON, Markdown)
- 🌍 42 universal noun types + 127 verb types
- 💾 LRU caching built-in
- 🧪 Production-tested in import pipeline

**Usage:**

```typescript
// Simple API (recommended)
const entities = await brain.extractEntities('John Smith founded Acme Corp', {
  types: [NounType.Person, NounType.Organization],
  confidence: 0.7
})

// Advanced API (custom configuration)
import { SmartExtractor } from '@soulcraft/brainy'

const extractor = new SmartExtractor(brain, { minConfidence: 0.8 })
const result = await extractor.extract('CEO', {
  formatContext: { format: 'excel', columnHeader: 'Title' }
})
```

**Backward Compatible:** All existing APIs unchanged. New exports are pure additions.

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

Co-Authored-By: Claude <noreply@anthropic.com>
2025-11-13 09:01:56 -08:00
..
api feat: add ImageHandler with EXIF extraction and comprehensive MIME detection (v5.2.0) 2025-11-03 14:06:17 -08:00
augmentations fix: update tests for Stage 3 CANONICAL taxonomy (42 nouns, 127 verbs) 2025-11-11 10:09:01 -08:00
cli fix: update all Stage 2 references to Stage 3 CANONICAL type counts 2025-11-06 09:40:33 -08:00
config fix: enable GCS native storage with Application Default Credentials 2025-10-09 10:39:54 -07:00
cortex feat: Stage 3 CANONICAL taxonomy with 169 types (v5.5.0) 2025-11-06 09:02:23 -08:00
critical feat: add browser environment compatibility support 2025-09-17 15:48:02 -07:00
data feat: Phase 3 - Unified Semantic Type Inference (Nouns + Verbs) 2025-10-16 10:59:26 -07:00
distributed feat(v4.0.0): Complete metadata/vector separation architecture with Azure support 2025-10-17 12:29:27 -07:00
embeddings feat(v4.0.0): Complete metadata/vector separation architecture with Azure support 2025-10-17 12:29:27 -07:00
errors feat: Brainy 3.0 - Production-ready Triple Intelligence database 2025-09-11 16:23:32 -07:00
graph perf: optimize imports with background deduplication (12-24x speedup) 2025-11-11 14:10:14 -08:00
hnsw fix: update all Stage 2 references to Stage 3 CANONICAL type counts 2025-11-06 09:40:33 -08:00
import fix: resolve v5.7.3 race condition by persisting write-through cache (v5.7.4) 2025-11-12 13:18:53 -08:00
importers fix: update all Stage 2 references to Stage 3 CANONICAL type counts 2025-11-06 09:40:33 -08:00
interfaces feat: implement always-adaptive caching with getCacheStats monitoring 2025-10-10 14:09:30 -07:00
mcp refactor: streamline core API surface 2025-10-04 08:52:06 -07:00
neural fix: resolve getRelations() empty array bug for ALL storage adapters (v5.5.0) 2025-11-06 10:47:59 -08:00
patterns 🧠 Brainy 2.0.0 - Zero-Configuration AI Database with Triple Intelligence™ 2025-08-26 12:32:21 -07:00
query fix: update remaining 31x→42x speedup references in typeAwareQueryPlanner 2025-11-06 09:41:22 -08:00
scripts feat: add node: protocol to all Node.js built-in imports for bundler compatibility 2025-09-17 14:20:21 -07:00
shared refactor: remove deprecated BrainyData class completely 2025-09-30 16:04:00 -07:00
storage fix: unwrap binary data in COW adapter to fix blob integrity check (v5.7.5) 2025-11-12 16:01:25 -08:00
streaming feat: Brainy 3.0 - Production-ready Triple Intelligence database 2025-09-11 16:23:32 -07:00
triple feat: Phase 3 - Unified Semantic Type Inference (Nouns + Verbs) 2025-10-16 10:59:26 -07:00
types feat: Stage 3 CANONICAL taxonomy with 169 types (v5.5.0) 2025-11-06 09:02:23 -08:00
universal fix: prevent fs adapter from throwing on import in browser 2025-09-17 16:22:02 -07:00
utils feat: Stage 3 CANONICAL taxonomy with 169 types (v5.5.0) 2025-11-06 09:02:23 -08:00
versioning fix: resolve critical COW ref resolution and versioning bugs 2025-11-04 13:05:59 -08:00
vfs fix: resolve HNSW race condition and verb weight extraction (v5.4.0) 2025-11-05 17:05:07 -08:00
augmentationManager.ts feat: Brainy 3.0 - Production-ready Triple Intelligence database 2025-09-11 16:23:32 -07:00
augmentationPipeline.ts feat: Brainy 3.0 - Production-ready Triple Intelligence database 2025-09-11 16:23:32 -07:00
brainy.ts feat: expose neural entity extraction APIs (v5.7.6 - Workshop request) 2025-11-13 09:01:56 -08:00
coreTypes.ts perf: 48-64× faster HNSW bulk imports via concurrent neighbor updates 2025-10-29 16:10:40 -07:00
cortex.ts 🧠 Brainy 2.0.0 - Zero-Configuration AI Database with Triple Intelligence™ 2025-08-26 12:32:21 -07:00
index.ts feat: expose neural entity extraction APIs (v5.7.6 - Workshop request) 2025-11-13 09:01:56 -08:00
pipeline.ts 🧠 Brainy 2.0.0 - Zero-Configuration AI Database with Triple Intelligence™ 2025-08-26 12:32:21 -07:00
setup.ts chore: enforce consistent coding style and semicolon removal 2025-09-29 09:50:59 -07:00
unified.ts chore: enforce consistent coding style and semicolon removal 2025-09-29 09:50:59 -07:00
worker.ts 🧠 Brainy 2.0.0 - Zero-Configuration AI Database with Triple Intelligence™ 2025-08-26 12:32:21 -07:00