skills.rest
wandreandrade2018-maker
wandreandrade2018-makerCOMMUNITY
Explore all skills by this author →
GitHub

AgentDB Vector Search

Implements semantic vector search with AgentDB for document retrieval and similarity matching.

Updated Aug 18, 2026
Search Tags:#semantic search#embeddings#rag#agentdb#vector search#similarity search#hnsw
One-click install
npx skills add https://github.com/wandreandrade2018-maker/claude-config --skill agentdb-vector-search-wandreandrade2018-maker
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: AgentDB Vector Search
Source: https://github.com/wandreandrade2018-maker/claude-config/tree/main/.claude/skills/agentdb-vector-search
Command: npx skills add https://github.com/wandreandrade2018-maker/claude-config --skill agentdb-vector-search-wandreandrade2018-maker

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires agentdb, agentic-flow.

What problem does it solve? Building semantic search and RAG pipelines requires a vector database that can store embeddings, index them efficiently, and return relevant results fast. This Skill provides ready-to-use CLI commands and API patterns for AgentDB so you can set up vector storage, similarity search, and hybrid retrieval without designing the infrastructure from scratch. ## Core Features & Use Cases - Vector Storage & Search: Initialize databases with preset dimensions (1536/768/384), store documents with embeddings, and run similarity queries with cosine, euclidean, or dot-product metrics. - RAG Pipelines: Retrieve relevant context with MMR diversity and metadata filtering, then feed it into an LLM for retrieval-augmented generation. - Memory-Efficient Scaling: Apply binary, scalar, or product quantization for 4-32x memory reduction, with HNSW indexing for sub-millisecond search over 1M+ vectors. - Use Case: Build a knowledge base where support documents are embedded and stored in AgentDB, then answer user questions by retrieving the top-5 most similar passages and passing them to an LLM. ## Quick Start Initialize an AgentDB vector database and run a semantic similarity search over my documents using the agentdb CLI.

Frequently Asked Questions about AgentDB Vector Search

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

FAQPage Schema
How do I set up vector search with AgentDB?▼

Initialize a database with npx agentdb@latest init ./vectors.db, optionally specifying embedding dimensions or a size preset. Then store documents with embeddings via the API and query with npx agentdb@latest query using a vector and top-k parameter.

How do I build a RAG pipeline with a vector database?▼

Embed the user question, run a similarity search against AgentDB with a threshold around 0.7, and inject the retrieved passages into the LLM prompt as context. The Skill includes a complete ragQuery example using retrieveWithReasoning and MMR.

What embedding dimensions does AgentDB support?▼

AgentDB supports any dimension configured at initialization. Common presets are 1536 for OpenAI ada-002, 768 for sentence-transformers, and 384 for all-MiniLM-L6-v2, set with the --dimension flag.

Does AgentDB support metadata filtering with vector search?▼

Yes, hybrid search combines vector similarity with metadata filters such as category or date ranges. Use the hybridSearch method with a query, filters object, and result limit.

Why is my vector search using too much memory?▼

High memory usage comes from storing full-precision vectors. Enable binary quantization for 32x reduction, scalar for 4x, or product quantization for 8-16x reduction via the quantizationType adapter option.

Can I use AgentDB with Claude Code via MCP?▼

Yes, run npx agentdb@latest mcp to start the MCP server and register it with claude mcp add. This exposes agentdb_query, agentdb_store, and agentdb_stats tools inside Claude Code.

Related Skills

Explore More Software Engineering Skills→
AI-Foundry-CoreAI-Foundry-Core
4

embedding-strategies

Generate domain-specific embeddings for text collections using multi-backend templates.

Official
Advanced
JhabbigJhabbig

rag-implementation

Build retrieval-augmented generation systems that ground LLM answers in external knowledge.

Community
Advanced
davila7davila7
30.5k

rag-implementation

Implements retrieval-augmented generation systems with chunking, embeddings, vector stores, and reranking.

Community
Intermediate
ancolemanancoleman
503

using-vector-databases

Implement vector databases for AI/ML semantic search and RAG systems.

Community
Advanced