跳转到主要内容
此内容尚未提供您的语言版本,正在以英文显示。

AgentDB Vector Search

技能 已验证 活跃

Implement semantic vector search with AgentDB for intelligent document retrieval, similarity matching, and context-aware querying. Use when building RAG systems, semantic search engines, or intelligent knowledge bases.

目的

To enable intelligent document retrieval and similarity matching by implementing advanced semantic vector search with AgentDB, supporting the creation of RAG systems and knowledge bases.

功能

  • Implement semantic vector search with AgentDB
  • Support for HNSW indexing and quantization
  • Sub-millisecond search (<100µs) and fast batch operations
  • Provide CLI and API for vector database operations
  • Enable RAG systems, semantic search engines, and knowledge bases

使用场景

  • Building RAG systems for enhanced LLM context
  • Creating intelligent document retrieval systems
  • Implementing similarity matching for large datasets
  • Developing context-aware querying interfaces

非目标

  • Replacing general-purpose databases
  • Providing natural language querying without vector embeddings
  • Handling non-vector data without conversion

工作流

  1. Initialize vector database with specified dimensions or presets.
  2. Store documents with their computed embeddings.
  3. Perform similarity searches using vector queries, optionally with thresholds, metrics, or MMR.
  4. Combine vector search with metadata filtering for hybrid search.
  5. Export and import vectors for backup or migration.

先决条件

  • Node.js 18+
  • AgentDB v1.0.7+ (via agentic-flow or standalone)
  • OpenAI API key (for embeddings) or custom embedding model

安装

npx skills add ruvnet/ruflo

通过 npx 运行 Vercel skills CLI(skills.sh)— 需要本地安装 Node.js,以及至少一个兼容 skills 的智能体(Claude Code、Cursor、Codex 等)。前提是仓库遵循 agentskills.io 格式。

质量评分

已验证
99 /100
about 22 hours ago 分析

信任信号

最近提交about 23 hours ago
星标50.2k
许可证MIT
状态
查看源代码