agentsclimarketplace

Agentdb vector search optimization

Skill bg-szy/TOP-SKILLS/skills/marketplace/agentdb-vector-search-optimization

全球最大的 Claude Code 技能聚合库 · 收录 3900+ 来自 12+ 来源的技能，提供在线搜索与趋势分析看板 / The world's largest Claude Code skill aggregation hub — 3900+ skills from 12+ sources with online search and trend dashboard

Install
npx -y skills add bg-szy/TOP-SKILLS --skill agentdb-vector-search-optimization

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

2 things to look at

  • no licenseNo license file was found in the repository. Code published without one is not open source by default, so using it at work is a question for whoever answers licensing questions where you are.
  • 4 stars4 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.

What its author says it does

Copied from the file, not written here

Optimize AgentDB vector search performance using quantization for 4-32x memory reduction, HNSW indexing for 150x faster search, caching, and batch operations for scaling to millions of vectors.

SKILL.md

3.2 KB, 562 tokens by cl100k_base, as published. Nobody here has run it

AgentDB Vector Search Optimization

Overview

Optimize AgentDB performance with quantization (4-32x memory reduction), HNSW indexing (150x faster search), caching, and batch operations for scaling to millions of vectors.

SOP Framework: 5-Phase Optimization

Phase 1: Baseline Performance (1 hour)

  • Measure current metrics (latency, throughput, memory)
  • Identify bottlenecks
  • Set optimization targets

Phase 2: Apply Quantization (1-2 hours)

  • Configure product quantization
  • Train codebooks
  • Apply compression
  • Validate accuracy

Phase 3: Implement HNSW Indexing (1-2 hours)

  • Build HNSW index
  • Tune parameters (M, efConstruction, efSearch)
  • Benchmark speedup

Phase 4: Configure Caching (1 hour)

  • Implement query cache
  • Set TTL and eviction policies
  • Monitor hit rates

Phase 5: Benchmark Results (1-2 hours)

  • Run comprehensive benchmarks
  • Compare before/after
  • Validate improvements

Quick Start

import { AgentDB, Quantization, QueryCache } from 'agentdb-optimization';

const db = new AgentDB({ name: 'optimized-db', dimensions: 1536 });

// Quantization (4x memory reduction)
const quantizer = new Quantization({
  method: 'product-quantization',
  compressionRatio: 4
});
await db.applyQuantization(quantizer);

// HNSW indexing (150x speedup)
await db.createIndex({
  type: 'hnsw',
  params: { M: 16, efConstruction: 200 }
});

// Caching
db.setCache(new QueryCache({
  maxSize: 10000,
  ttl: 3600000
}));

Optimization Techniques

Quantization

  • Product Quantization: 4-8x compression
  • Scalar Quantization: 2-4x compression
  • Binary Quantization: 32x compression

Indexing

  • HNSW: 150x faster, high accuracy
  • IVF: Fast, partitioned search
  • LSH: Approximate search

Caching

  • Query Cache: LRU eviction
  • Result Cache: TTL-based
  • Embedding Cache: Reuse embeddings

Success Metrics

  • Memory reduction: 4-32x
  • Search speedup: 150x
  • Accuracy maintained: > 95%
  • Cache hit rate: > 70%

Additional Resources

What ships with it: 4 files

13.8 KB alongside SKILL.md

Keep looking

Skills are one crate of 327,069. Ordering is by how many stacks a row turns up in, so the top of any crate is what has actually been picked rather than what has the most stars.