skills.rest
33may
33mayCOMMUNITY
Explore all skills by this author →
GitHub

AgentDB Vector Search

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

1|1|Updated Nov 28, 2025
Search Tags:#semantic search#embeddings#rag#agentdb#vector search#similarity search#hnsw
One-click install
npx skills add https://github.com/33may/robotics --skill agentdb-vector-search-33may
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: AgentDB Vector Search
Source: https://github.com/33may/robotics/tree/main/humanoid/.claude/skills/agentdb-vector-search
Command: npx skills add https://github.com/33may/robotics --skill agentdb-vector-search-33may

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires agentdb, agentic-flow.

What problem does it solve? Building semantic search and RAG systems requires a vector database that can store embeddings, index them efficiently, and retrieve similar documents with low latency, which is complex to implement from scratch. ## Core Features & Use Cases - Vector Storage & Similarity Search: Store documents with embeddings and query by cosine, euclidean, or dot-product distance using HNSW indexing. - Hybrid Search & MMR: Combine vector similarity with metadata filters and Maximal Marginal Relevance for diverse, relevant results. - Quantization & Performance: Reduce memory usage 4-32x with binary, scalar, or product quantization while maintaining sub-millisecond search. - Use Case: Build a RAG pipeline where user questions are embedded, matched against a knowledge base of documents, and the retrieved context is passed to an LLM for answer generation. ## Quick Start Initialize an AgentDB vector database with npx agentdb@latest init ./vectors.db, then store documents with embeddings and run semantic queries against it.

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 or CLI and query them using similarity search with your chosen distance metric.

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

Embed the user question, run a similarity search against stored document embeddings with a threshold around 0.7, and pass the retrieved context to an LLM prompt. AgentDB supports this workflow through its retrieveWithReasoning API with MMR for diverse results.

What embedding dimensions does AgentDB support?▼

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

Does AgentDB support metadata filtering with vector search?▼

Yes, hybrid search combines vector similarity with metadata filters such as category or date ranges. You pass a filters object alongside the query to constrain results before ranking by similarity.

Why is my vector search using too much memory?▼

High memory usage comes from storing full-precision embeddings. Enable binary quantization for 32x reduction, scalar for 4x, or product quantization for 8-16x reduction when creating the AgentDB adapter.

How do I fix poor relevance in semantic search results?▼

Raise the similarity threshold, for example from 0.7 to 0.8, to filter weak matches. You can also enable MMR (Maximal Marginal Relevance) to balance relevance with diversity and reduce redundant results.

Related Skills

Explore More Software Engineering Skills→
tanaertanaer

vector-db

Teach vector database fundamentals and RAG applications with Milvus and Python.

Community
Intermediate
JhabbigJhabbig

rag-implementation

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

Community
Advanced
seb1nseb1n
147

context-ranking

Rank retrieved context chunks by relevance, diversity, and utility for RAG systems.

Community
Advanced
SanketAdlakSanketAdlak

similarity-search-patterns

Implement vector similarity search with Pinecone, Qdrant, pgvector, and Weaviate.

Community
Advanced