- SQ8 scalar quantization (8-bit) for 4x vector storage reduction - Lazy vector loading: evict float32 vectors after graph construction, load on-demand from storage via UnifiedCache - Two-phase search: over-retrieve with SQ8 approximate distances, rerank top candidates with exact float32 distances - Configuration surface: hnsw.quantization and hnsw.vectorStorage in BrainyConfig - All features disabled by default (zero behavior change for existing users) - 27 new tests covering quantization accuracy, lazy loading, reranking - Remove GitHub Actions CI (build locally, cortex CI handles native builds) |
||
|---|---|---|
| .. | ||
| api | ||
| augmentations | ||
| cli | ||
| config | ||
| cortex | ||
| critical | ||
| data | ||
| distributed | ||
| embeddings | ||
| errors | ||
| graph | ||
| hnsw | ||
| import | ||
| importers | ||
| integrations | ||
| interfaces | ||
| mcp | ||
| neural | ||
| patterns | ||
| scripts | ||
| shared | ||
| storage | ||
| streaming | ||
| transaction | ||
| triple | ||
| types | ||
| universal | ||
| utils | ||
| versioning | ||
| vfs | ||
| augmentationManager.ts | ||
| augmentationPipeline.ts | ||
| brainy.ts | ||
| coreTypes.ts | ||
| cortex.ts | ||
| index.ts | ||
| internals.ts | ||
| pipeline.ts | ||
| plugin.ts | ||
| setup.ts | ||
| unified.ts | ||
| worker.ts | ||