hybrid-graphrag

Name: hybrid-graphrag
Availability: InStock
Author: Jada

Integrate vector search with knowledge graph traversal for hybrid retrieval.

Updated Aug 23, 2026

Search Tags:#rag #vector search #qdrant #graph #neo4j #hybrid

Ready to run

npx skills add https://github.com/lofibrainwav/AFO_Kingdom --skill hybrid-graphrag

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: hybrid-graphrag
Source: https://github.com/lofibrainwav/AFO_Kingdom/tree/main/skills/hybrid-graphrag
Command: npx skills add https://github.com/lofibrainwav/AFO_Kingdom --skill hybrid-graphrag

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This Skill combines vector search with knowledge graph traversal to deliver richer, more accurate context for AI answers.

Core Features & Use Cases

Graph Traversal: Navigate complex knowledge graphs for relationships.
Hybrid Search: Merge vector and graph results for robust context.
Entity & Relationship Mapping: Extract entities and map their relationships for improved reasoning.

Quick Start

result = hybrid_graphrag.query("Explain Trinity Score pillars with entities from the knowledge graph.")

Frequently Asked Questions about hybrid-graphrag

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

FAQPage Schema

How do I combine vector search with knowledge graphs for better context retrieval?▼

Hybrid vector and graph search merges semantic similarity from vector embeddings with structured relationship traversal through knowledge graphs, delivering richer context by capturing both unstructured meaning and explicit entity connections for multi-hop retrieval.

Can I use vector search and graph traversal together with Qdrant and Neo4j?▼

Yes. This Skill integrates vector search engines like Qdrant with graph databases like Neo4j to execute hybrid queries, enabling simultaneous semantic and relational lookups across enterprise data, research literature, and product catalogs.

What's the best way to extract entities and map relationships for AI reasoning?▼

Entity extraction identifies key concepts while relationship mapping documents their connections within a knowledge graph, enabling structured reasoning and improving answer accuracy when combined with vector-based semantic search.

When should I use hybrid RAG instead of vector search alone?▼

Use hybrid RAG when your data includes both unstructured text and structured relationships—such as enterprise systems with linked entities, research networks, or product hierarchies—where multi-hop reasoning and explicit relationship context improve retrieval quality.

What domains benefit most from hybrid vector and graph retrieval?▼

Enterprise data systems, research literature networks, and product catalogs benefit most because they contain interconnected entities with semantic meaning; hybrid search captures both implicit similarity and explicit relationships for comprehensive context synthesis.