skills.rest
qiphon
qiphonCOMMUNITY
Explore all skills by this author →
WebsiteGitHub

AgentDB Vector Search

Rank documents by vector similarity for semantic retrieval in RAG pipelines.

2|Updated Jul 26, 2019
Search Tags:#semantic search#embeddings#RAG#vector search#hybrid search#AgentDB
One-click install
npx skills add https://github.com/qiphon/learn --skill agentdb-vector-search-qiphon
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: AgentDB Vector Search
Source: https://github.com/qiphon/learn/tree/main/.opencode/skills/agentdb-vector-search
Command: npx skills add https://github.com/qiphon/learn --skill agentdb-vector-search-qiphon

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This skill enables fast, accurate semantic retrieval by ranking documents through vector similarity, powering knowledge bases, RAG workflows, and intelligent search across large document collections.

Core Features & Use Cases

  • Vector storage & embeddings: store and compare document embeddings to quickly find relevant content.
  • Similarity and hybrid search: perform vector similarity plus metadata filters for precise results; supports MMR for diverse results.
  • RAG-ready workflows: integrate into Retrieval Augmented Generation pipelines to fetch context and answer questions.
  • Use Case: Build an enterprise search or knowledge base that returns the most contextually relevant documents for a user query.

Quick Start

Start by initializing a vector store with default dimensions, then ingest text to create embeddings and run a semantic search query against your corpus.

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 vector search for a RAG pipeline?▼

Semantic vector search for a RAG pipeline ranks documents through vector similarity, matching user queries to stored content. You ingest text to create embeddings and run queries against your corpus to retrieve context.

What is hybrid search and how does it filter vector similarity results?▼

Hybrid search performs vector similarity alongside metadata filters for precise retrieval. It also supports Maximal Marginal Relevance (MMR) to ensure diverse results when fetching contextually relevant documents.

How do I store document embeddings for an enterprise knowledge base?▼

To store document embeddings for an enterprise knowledge base, initialize a vector store with default dimensions and ingest text. This creates embeddings to quickly find and compare relevant content.

Does AgentDB Vector Search support advanced indexing like HNSW and quantization?▼

Yes, AgentDB Vector Search supports advanced indexing features including HNSW, quantization, and caching. These features optimize vector storage and enhance retrieval speed for large document collections.

What is the best way to retrieve diverse documents using vector search?▼

The best way to retrieve diverse documents using vector search is applying Maximal Marginal Relevance (MMR). This hybrid search mechanism ranks contextually relevant documents while reducing redundancy in results.

Related Skills

Explore More Data & Analytics Skills→
antonyfmunozantonyfmunoz

fastembed

Generate local dense text embeddings with ONNX Runtime for semantic search.

Community
Intermediate
ContextJet-aiContextJet-ai
29

monitor-rag-quality

Evaluate RAG pipelines using context precision, recall, faithfulness, and answer relevance.

Official
Intermediate
enigmaicon-engenigmaicon-eng
1

rag-architect

Design production RAG pipelines with chunking, embeddings, and vector store indexing.

Community
Advanced
ccfccf

hybrid-search-implementation

Combine vector similarity with keyword matching for hybrid retrieval.

Community
Intermediate