brainy/src/utils/metadataIndexCache.ts

151 lines
3.6 KiB
TypeScript
Raw Normal View History

🧠 Brainy 2.0.0 - Zero-Configuration AI Database with Triple Intelligence™ MAJOR RELEASE: Complete evolution of Brainy with groundbreaking features and performance. 🎯 KEY FEATURES: ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ ✨ Triple Intelligence™ Engine - Unified Vector + Metadata + Graph search - O(log n) performance on all operations - 3ms average search latency at any scale ✨ API Consolidation - 15+ search methods → 2 clean APIs - search() for vector similarity - find() for natural language queries ✨ Natural Language Processing - 220+ pre-computed NLP patterns - Instant context understanding - "Show me recent React components with tests" ✨ Zero Configuration - Works instantly, no setup required - Built-in embedding models (no API keys) - Smart defaults for everything - Automatic optimization ✨ Enterprise Features (Free for Everyone) - Scales to 10M+ items - Write-Ahead Logging (WAL) for durability - Distributed architecture with sharding - Read/write separation - Connection pooling & request deduplication - Built-in monitoring & health checks ✨ Universal Compatibility - Node.js, Browser, Edge Workers - 4 Storage Adapters (Memory, FileSystem, OPFS, S3) - TypeScript with full type safety - Worker-based embeddings 📦 WHAT'S INCLUDED: ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ • Core AI Database with HNSW indexing • 19 Production-ready augmentations • Universal Memory Manager • Complete CLI with all commands • Brain Cloud integration (soulcraft.com) • Comprehensive documentation • 52 test files with 400+ tests • Migration guide from 1.x 📊 PERFORMANCE: ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ • Initialize: 450ms (24MB memory) • Search: 3ms average (up to 10M items) • Metadata Filter: 0.8ms (O(log n)) • Bulk Import: 2.3s per 1000 items • Production Scale: 5.8ms at 10M items 🔧 TECHNICAL IMPROVEMENTS: ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ • TypeScript compilation: 153 errors → 0 • Memory usage: 200MB → 24MB baseline • Circular dependencies resolved • Worker thread communication fixed • Storage adapter consistency • Request coalescing for 3x performance 🛠️ CLI FEATURES: ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ • brainy add - Smart data ingestion • brainy find - Natural language search • brainy search - Vector similarity • brainy chat - AI conversation mode • brainy cloud - Brain Cloud integration • brainy augment - Manage extensions • 100% API compatibility 📚 DOCUMENTATION: ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ • Professional README with examples • Quick Start guide (5 minutes) • Enterprise Features guide • Migration guide from 1.x • API reference • Architecture documentation 🌟 USE CASES: ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ • AI memory layer for chatbots • Semantic document search • Code intelligence platforms • Knowledge management systems • Real-time recommendation engines • Customer support automation MIT License - Enterprise features included free for everyone. No premium tiers, no paywalls, no limits. Built with ❤️ by the Brainy community. Visit https://soulcraft.com for Brain Cloud integration.
2025-08-26 12:32:21 -07:00
/**
* MetadataIndexCache - Caches metadata index data for improved performance
* Reuses the same pattern as SearchCache for consistency
*/
export interface MetadataCacheEntry {
data: any // Field index or value chunk data
timestamp: number
hits: number
}
export interface MetadataIndexCacheConfig {
maxAge?: number // Maximum age in milliseconds (default: 5 minutes)
maxSize?: number // Maximum number of cached entries (default: 500)
enabled?: boolean // Whether caching is enabled (default: true)
hitCountWeight?: number // Weight for hit count in eviction policy (default: 0.3)
}
export class MetadataIndexCache {
private cache = new Map<string, MetadataCacheEntry>()
private maxAge: number
private maxSize: number
private enabled: boolean
private hitCountWeight: number
// Cache statistics
private hits = 0
private misses = 0
private evictions = 0
constructor(config: MetadataIndexCacheConfig = {}) {
this.maxAge = config.maxAge ?? 5 * 60 * 1000 // 5 minutes
this.maxSize = config.maxSize ?? 500 // More entries than SearchCache since indexes are smaller
this.enabled = config.enabled ?? true
this.hitCountWeight = config.hitCountWeight ?? 0.3
}
/**
* Get cached entry
*/
get(key: string): any | undefined {
if (!this.enabled) return undefined
const entry = this.cache.get(key)
if (!entry) {
this.misses++
return undefined
}
// Check if entry is expired
if (Date.now() - entry.timestamp > this.maxAge) {
this.cache.delete(key)
this.misses++
return undefined
}
// Update hit count
entry.hits++
this.hits++
return entry.data
}
/**
* Set cache entry
*/
set(key: string, data: any): void {
if (!this.enabled) return
// Evict entries if at max size
if (this.cache.size >= this.maxSize) {
this.evictLeastValuable()
}
this.cache.set(key, {
data,
timestamp: Date.now(),
hits: 0
})
}
/**
* Evict least valuable entry based on age and hit count
*/
private evictLeastValuable(): void {
let leastValuableKey: string | null = null
let lowestScore = Infinity
for (const [key, entry] of this.cache.entries()) {
const age = Date.now() - entry.timestamp
const ageScore = age / this.maxAge
const hitScore = entry.hits * this.hitCountWeight
const score = hitScore - ageScore
if (score < lowestScore) {
lowestScore = score
leastValuableKey = key
}
}
if (leastValuableKey) {
this.cache.delete(leastValuableKey)
this.evictions++
}
}
/**
* Invalidate cache entries matching a pattern
*/
invalidatePattern(pattern: string): void {
const keysToDelete: string[] = []
for (const key of this.cache.keys()) {
if (key.includes(pattern)) {
keysToDelete.push(key)
}
}
keysToDelete.forEach(key => this.cache.delete(key))
}
/**
* Clear all cache entries
*/
clear(): void {
this.cache.clear()
}
/**
* Get cache statistics
*/
getStats() {
return {
size: this.cache.size,
hits: this.hits,
misses: this.misses,
hitRate: this.hits / (this.hits + this.misses) || 0,
evictions: this.evictions
}
}
/**
* Get estimated memory usage
*/
getMemoryUsage(): number {
// Rough estimate: 100 bytes per entry + data size
let totalSize = 0
for (const entry of this.cache.values()) {
totalSize += 100 // Base overhead
totalSize += JSON.stringify(entry.data).length * 2 // Unicode chars
}
return totalSize
}
}