skills.rest
FrekiManagarm
FrekiManagarmCOMMUNITY
Explore all skills by this author →
WebsiteGitHub

AgentDB Vector Search

Perform semantic vector similarity search with metadata-aware filtering and MMR diversity.

Updated Feb 24, 2026
Search Tags:#embeddings#rag#agentdb#vector search#mcp server#hnsw indexing#semantic retrieval
One-click install
npx skills add https://github.com/FrekiManagarm/dunlo --skill agentdb-vector-search-frekimanagarm
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: AgentDB Vector Search
Source: https://github.com/FrekiManagarm/dunlo/tree/main/.claude/skills/agentdb-vector-search
Command: npx skills add https://github.com/FrekiManagarm/dunlo --skill agentdb-vector-search-frekimanagarm

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

It eliminates slow, brittle keyword-only search by enabling semantic vector similarity retrieval so relevant documents can be found even when wording differs.

Core Features & Use Cases

  • Vector-based semantic search: Store embeddings and retrieve the most similar content using fast vector indexing.
  • Context-aware retrieval for RAG: Generate richer query context for retrieval-augmented generation using similarity thresholds and diversity (MMR).
  • Hybrid filtering: Combine vector similarity with metadata filters (e.g., domain and date ranges) to narrow results to what matters.
  • Import/export and operations tooling: Manage persistence, statistics, and portability of your vector index for real workflows.

Use Case

Build a customer-support knowledge base where users ask questions in natural language, and the system returns the most relevant articles with metadata-aware filtering for faster, higher-quality answers.

Quick Start

Initialize a local vector database and then query it with an example embedding to confirm your semantic matches work end-to-end.

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 semantic vector search for a RAG pipeline?▼

Semantic search finds relevant documents even when exact wording differs by comparing text embeddings using vector similarity. It overcomes slow keyword-only matching through fast indexing and distance metrics.

How do I filter vector search results by metadata and date ranges?▼

Hybrid filtering narrows vector search results by combining semantic similarity scores with metadata constraints like domain and date ranges, returning only documents matching specific contextual requirements.

Can I use MMR to increase diversity in top-k semantic retrieval?▼

Yes, Maximal Marginal Relevance (MMR) diversifies top-k semantic retrieval by penalizing redundant similar documents, enriching context for generation, and preventing duplicate matches.

What is needed to initialize a vector database for local semantic search?▼

Initializing a vector database requires computing text embeddings, selecting a similarity or distance metric, and storing vectors for fast query execution, with optional CLI or API integration supported.

Does AgentDB vector search support import and export for index portability?▼

Yes, import and export tooling manages vector index persistence, statistics, and portability, enabling database migration and operational monitoring for real workflows.

Related Skills

Explore More Software Engineering Skills→
proffesor-for-testingproffesor-for-testing
43

AgentDB Vector Search

Store embeddings and query vectors for semantic document retrieval.

Community
Advanced
ruiyangruiyiruiyangruiyi

chroma

Store text embeddings and metadata for semantic retrieval with vector similarity queries.

Community
Basic
icyzhicyzh
1

pinecone

Manage Pinecone vector indexes, upserts, and similarity queries via the Python client.

Community
Intermediate
dabblersportdabblersport

AgentDB Vector Search

Implement vector-based semantic search with AgentDB using HNSW indexing.

Community
Advanced