skills.rest
smith-horn
smith-hornOFFICIAL
Explore all skills by this author →
WebsiteGitHub

AgentDB Vector Search

Perform vector-based semantic search over document collections with AgentDB.

75|17|Updated Jan 11, 2026
Search Tags:#embeddings#RAG#retrieval#AgentDB#semantic-search#vector-search#information-retrieval
One-click install
npx skills add https://github.com/smith-horn/skillsmith --skill agentdb-vector-search-smith-horn
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: AgentDB Vector Search
Source: https://github.com/smith-horn/skillsmith/tree/main/.claude/skills/agentdb-vector-search
Command: npx skills add https://github.com/smith-horn/skillsmith --skill agentdb-vector-search-smith-horn

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This Skill enables fast retrieval of relevant documents by performing vector-based semantic search against large corpora using AgentDB. It helps in knowledge management, research, and retrieval-augmented generation tasks.

Core Features & Use Cases

  • Vector indexing and fast similarity search with HNSW
  • Hybrid search combining embeddings with metadata
  • MCP server integration for Claude Code workflows
  • Use cases include knowledge-base search, document QA, and efficient content discovery.

Quick Start

Start the AgentDB MCP server and connect it to Claude Code. Then perform a first search to validate setup.

  • Install and run: npx agentdb@latest mcp
  • Add to Claude Code: claude mcp add agentdb npx agentdb@latest mcp
  • Example search: npx agentdb@latest query ./vectors.db "quantum computing" -k 5

Frequently Asked Questions about AgentDB Vector Search

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I perform semantic search over document collections for a RAG pipeline?▼

Hybrid search combines vector embeddings with metadata filtering to improve document retrieval accuracy. This Skill uses AgentDB to merge semantic similarity matching with metadata constraints for knowledge-base search and content discovery.

Can I use vector search with metadata filtering for more accurate retrieval?▼

Hybrid search combines vector embeddings with metadata filtering to improve document retrieval accuracy. This Skill uses AgentDB to merge semantic similarity matching with metadata constraints for knowledge-base search and content discovery.

Does AgentDB vector search work with Claude Code workflows?▼

Vector search requires AgentDB integration and embedding models to generate document vectors. You need an environment that supports HNSW indexing and quantization to execute fast similarity matching over large corpora.

Do I need embedding models to run vector-based similarity matching?▼

Vector search requires AgentDB integration and embedding models to generate document vectors. You need an environment that supports HNSW indexing and quantization to execute fast similarity matching over large corpora.

What is the best way to index large corpora for fast document retrieval?▼

Fast document retrieval over large corpora is achieved using HNSW indexing and quantization. This Skill leverages AgentDB to perform vector-based semantic search, ensuring efficient similarity matching for research and knowledge management tasks.

When should I use hybrid search instead of pure vector similarity matching?▼

Hybrid search is used when pure vector similarity matching is insufficient for precise document retrieval. By combining embeddings with metadata, this Skill via AgentDB delivers more targeted results for complex information-retrieval queries.

Related Skills

Explore More Data & Analytics Skills→
Awannaphasch2016Awannaphasch2016

AgentDB Vector Search

Perform semantic vector search against AgentDB stores using embedding similarity.

Community
Intermediate
Mathews-TomMathews-Tom
310

rag-auditor

Evaluate RAG pipeline retrieval and generation quality with metrics.

Community
Advanced
sixscripts-aisixscripts-ai

rag-engineer

Optimize retrieval-augmented generation pipelines for LLM-powered tasks.

Community
Advanced
dalagerdalager
1

AgentDB Vector Search

Enable high-speed semantic vector search with HNSW indexing and metadata filtering.

Community
Advanced