AgentDB Performance Optimization

Files (1)

• SKILL.md

SKILL.md (first lines)

# AgentDB Performance Optimization

## What This Skill Does

Provides comprehensive performance optimization techniques for AgentDB vector databases. Achieve 150x-12,500x performance improvements through quantization, HNSW indexing, caching strategies, and batch operations. Reduce memory usage by 4-32x while maintaining accuracy.

**Performance**: <100µs vector search, <1ms pattern retrieval, 2ms batch insert for 100 vectors.

## Prerequisites

- Node.js 18+
- AgentDB v1.0.7+ (via agentic-flow)
- Existing AgentDB database or application

---

## Quick Start

### Run Performance Benchmarks

```bash
# Comprehensive performance benchmarking
npx agentdb@latest benchmark

# Results show:
# ✅ Pattern Search: 150x faster (100µs vs 15ms)
# ✅ Batch Insert: 500x faster (2ms vs 1s for 100 vectors)
# ✅ Large-scale Query: 12,500x faster (8ms vs 100s at 1M vectors)
# ✅ Memory Efficiency: 4-32x reduction with quantization
```

### Enable Optimizations

```typescript
import { createAgentDBAdapter } from 'agentic-flow/reasoningbank';

// Optimized configuration
const adapter = await createAgentDBAdapter({
  dbPath: '.agentdb/optimized.db',
  quantizationType: 'binary',   // 32x memory reduction
  cacheSize: 1000,               // In-memory cache
  enableLearning: true,
  enableReasoning: true,
});
```

---

## Quantization Strategies

### 1. Binary Quantization (32x Reduction)

**Best For**: Large-scale deployments (1M+ vectors), memory-constrained environments
**Trade-off**: ~2-5% accuracy loss, 32x memory reduction, 10x faster

```typescript
const adapter = await createAgentDBAdapter({
  quantizationType: 'binary',
  // 768-dim float32 (3072 bytes) → 96 bytes binary
  // 1M vectors: 3GB → 96MB
});
```

**Use Cases**:
- Mobile/edge deployment
- Large-scale vector storage (millions of vectors)
- Real-time search with memory constraints

**Performance**:
- Memory: 32x smaller
- Search Speed: 10x faster (bit operations)
- Accuracy: 95-98% of original

### 2. Scalar Quantization (4x Reduction)

**Best For**: Balanced performance/accuracy, moderate datasets
**Trade-off**: ~1-2% accuracy loss, 4x memory reduction, 3x faster

```typescript
const adapter = await createAgentDBAdapter({
  quantizationType: 'scalar',
  // 768-dim float32 (3072 bytes) → 768 bytes (uint8)
  // 1M vectors: 3GB → 768MB
});
```

**Use Cases**:
- Production applications requiring high accuracy
- Medium-scale deployments (10K-1M vectors)
- General-purpose optimization

**Performance**:
- Memory: 4x smaller
- Search Speed: 3x faster
- Accuracy: 98-99% of original

### 3. Product Quantization (8-16x Reduction)

**Best For**: High-dimensional vectors, balanced compression
**Trade-off**: ~3-7% accuracy loss, 8-16x memory reduction, 5x faster

```typescript
const adapter = await createAgentDBAdapter({
  quantizationType: 'product',
  // 768-dim float32 (3072 bytes) → 48-96 bytes
  // 1M vectors: 3GB → 192MB
});
```

**Use Cases**:
- High-dimensional embeddings (>512 dims)
- Image/video embeddings
- Large-scale similarity search

**Performance**:
- Memory: 8-16x smaller
- Search Speed: 5x faster
- Accuracy: 93-97% of original

From aegntic/cldcde, MIT.

More from aegntic/cldcde