- 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) |
||
|---|---|---|
| .. | ||
| roaring | ||
| adaptiveBackpressure.ts | ||
| adaptiveSocketManager.ts | ||
| autoConfiguration.ts | ||
| BoundedRegistry.ts | ||
| brainyTypes.ts | ||
| contentExtractor.ts | ||
| crypto.ts | ||
| deletedItemsIndex.ts | ||
| distance.ts | ||
| embedding.ts | ||
| enhancedLogger.ts | ||
| ensureDeleted.ts | ||
| entityIdMapper.ts | ||
| environment.ts | ||
| fieldNameTracking.ts | ||
| fieldTypeInference.ts | ||
| import-progress-tracker.ts | ||
| index.ts | ||
| intelligentTypeMapper.ts | ||
| jsonProcessing.ts | ||
| logger.ts | ||
| memoryDetection.ts | ||
| metadataFilter.ts | ||
| metadataIndex.ts | ||
| metadataIndexCache.ts | ||
| metadataIndexChunking.ts | ||
| metadataNamespace.ts | ||
| metadataWriteBuffer.ts | ||
| mutex.ts | ||
| nodeVersionCheck.ts | ||
| operationUtils.ts | ||
| paramValidation.ts | ||
| performanceMonitor.ts | ||
| periodicCleanup.ts | ||
| rateLimiter.ts | ||
| rebuildCounts.ts | ||
| requestCoalescer.ts | ||
| requestDeduplicator.ts | ||
| searchCache.ts | ||
| statisticsCollector.ts | ||
| structuredLogger.ts | ||
| textEncoding.ts | ||
| typeUtils.ts | ||
| typeValidation.ts | ||
| unifiedCache.ts | ||
| vectorQuantization.ts | ||
| version.ts | ||
| workerUtils.ts | ||
| writeBuffer.ts | ||