AgentDB Advanced Features

# AgentDB Advanced Features

## What This Skill Does

Covers advanced AgentDB capabilities for distributed systems, multi-database coordination, custom distance metrics, hybrid search (vector + metadata), QUIC synchronization, and production deployment patterns. Enables building sophisticated AI systems with sub-millisecond cross-node communication and advanced search capabilities.

**Performance**: <1ms QUIC sync, hybrid search with filters, custom distance metrics.

## Prerequisites

- Node.js 18+
- AgentDB v1.0.7+ (via agentic-flow)
- Understanding of distributed systems (for QUIC sync)
- Vector search fundamentals

---

## QUIC Synchronization

### What is QUIC Sync?

QUIC (Quick UDP Internet Connections) enables sub-millisecond latency synchronization between AgentDB instances across network boundaries with automatic retry, multiplexing, and encryption.

**Benefits**:
- <1ms latency between nodes
- Multiplexed streams (multiple operations simultaneously)
- Built-in encryption (TLS 1.3)
- Automatic retry and recovery
- Event-based broadcasting

### Enable QUIC Sync

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

// Initialize with QUIC synchronization
const adapter = await createAgentDBAdapter({
  dbPath: '.agentdb/distributed.db',
  enableQUICSync: true,
  syncPort: 4433,
  syncPeers: [
    '192.168.1.10:4433',
    '192.168.1.11:4433',
    '192.168.1.12:4433',
  ],
});

// Patterns automatically sync across all peers
await adapter.insertPattern({
  // ... pattern data
});

// Available on all peers within ~1ms
```

### QUIC Configuration

```typescript
const adapter = await createAgentDBAdapter({
  enableQUICSync: true,
  syncPort: 4433,              // QUIC server port
  syncPeers: ['host1:4433'],   // Peer addresses
  syncInterval: 1000,          // Sync interval (ms)
  syncBatchSize: 100,          // Patterns per batch
  maxRetries: 3,               // Retry failed syncs
  compression: true,           // Enable compression
});
```

### Multi-Node Deployment

```bash
# Node 1 (192.168.1.10)
AGENTDB_QUIC_SYNC=true \
AGENTDB_QUIC_PORT=4433 \
AGENTDB_QUIC_PEERS=192.168.1.11:4433,192.168.1.12:4433 \
node server.js

# Node 2 (192.168.1.11)
AGENTDB_QUIC_SYNC=true \
AGENTDB_QUIC_PORT=4433 \
AGENTDB_QUIC_PEERS=192.168.1.10:4433,192.168.1.12:4433 \
node server.js

# Node 3 (192.168.1.12)
AGENTDB_QUIC_SYNC=true \
AGENTDB_QUIC_PORT=4433 \
AGENTDB_QUIC_PEERS=192.168.1.10:4433,192.168.1.11:4433 \
node server.js
```

---

## Distance Metrics

### Cosine Similarity (Default)

Best for normalized vectors, semantic similarity:

```bash
# CLI
npx agentdb@latest query ./vectors.db "[0.1,0.2,...]" -m cosine

# API
const result = await adapter.retrieveWithReasoning(queryEmbedding, {
  metric: 'cosine',
  k: 10,
});
```

**Use Cases**:
- Text embeddings (BERT, GPT, etc.)
- Semantic search
- Document similarity
- Most general-purpose applications

**Formula**: `cos(θ) = (A · B) / (||A|| × ||B||)`
**Range**: [-1, 1] (1 = identical, -1 = opposite)

### Euclidean Distance (L2)

Best for spatial data, geometric similarity:

```bash
# CLI
npx agentdb@latest query ./vectors.db "[0.1,0.2,...]" -m euclidean

# API
const result = await adapter.retrieveWithReasoning(queryEmbedding, {
  metric: 'euclidean',
  k: 10,
});
```

**Use Cases**:
- Image embeddings
- Spatial data
- Computer vision
- When vector magnitude matters

**Formula**: `d = √(Σ(ai - bi)²)`
**Range**: [0, ∞] (0 = identical, ∞ = very different)

### Dot Product

Best for pre-normalized vectors, fast computation:

```bash
# CLI
npx agentdb@latest query ./vectors.db "[0.1,0.2,...]" -m dot

# API
const result = await adapter.retrieveWithReasoning(queryEmbedding, {
  metric: 'dot',
  k: 10,
});
```

**Use Cases**:
- Pre-normalized embeddings
- Fast similarity computation
- When vectors are already unit-length

**Formula**: `dot = Σ(ai × bi)`
**Range**: [-∞, ∞] (higher = more similar)

### Custom Distance Metrics

```typescript
// Implement custom distance function
function customDistance(vec1: number[], vec2: number[]): number {
  // Weighted Euclidean distance
  const weights = [1.0, 2.0, 1.5, ...];
  let sum = 0;
  for (let i = 0; i < vec1.length; i++) {
    sum += weights[i] * Math.pow(vec1[i] - vec2[i], 2);
  }
  return Math.sqrt(sum);
}

// Use in search (requires custom implementation)
```

---

## Hybrid Search (Vector + Metadata)

### Basic Hybrid Search

Combine vector similarity with metadata filtering:

```typescript
// Store documents with metadata
await adapter.insertPattern({
  id: '',
  type: 'document',
  domain: 'research-papers',
  pattern_data: JSON.stringify({
    embedding: documentEmbedding,
    text: documentText,
    metadata: {
      author: 'Jane Smith',
      year: 2025,
      category: 'machine-learning',
      citations: 150,
    }
  }),
  confidence: 1.0,
  usage_count: 0,
  success_count: 0,
  created_at: Date.now(),
  last_used: Date.now(),
});

// Hybrid search: vector similarity + metadata filters
const result = await adapter.retrieveWithReasoning(queryEmbedding, {
  domain: 'research-papers',
  k: 20,
  filters: {
    year: { $gte: 2023 },          // Published 2023 or later
    category: 'machine-learning',   // ML papers only
    citations: { $gte: 50 },       // Highly cited
  },
});
```

### Advanced Filtering

```typescript
// Complex metadata queries
const result = await adapter.retrieveWithReasoning(queryEmbedding, {
  domain: 'products',
  k: 50,
  filters: {
    price: { $gte: 10, $lte: 100 },      // Price range
    category: { $in: ['electronics', 'gadgets'] },  // Multiple categories
    rating: { $gte: 4.0 },                // High rated
    inStock: true,                        // Available
    tags: { $contains: 'wireless' },      // Has tag
  },
});
```

### Weighted Hybrid Search

Combine vector and metadata scores:

```typescript
const result = await adapter.retrieveWithReasoning(queryEmbedding, {
  domain: 'content',
  k: 20,
  hybridWeights: {
    vectorSimilarity