skills.rest
neo4j-contrib
neo4j-contribOFFICIAL
Explore all skills by this author →
WebsiteGitHub

neo4j-graphrag-skill

Build GraphRAG retrieval pipelines on Neo4j with neo4j-graphrag retrievers.

101|35|Updated Jan 20, 2026
Search Tags:#llm#retrieval#vector search#hybrid search#neo4j#cypher#graphrag
One-click install
npx skills add https://github.com/neo4j-contrib/neo4j-skills --skill neo4j-graphrag-skill
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: neo4j-graphrag-skill
Source: https://github.com/neo4j-contrib/neo4j-skills/tree/main/neo4j-graphrag-skill
Command: npx skills add https://github.com/neo4j-contrib/neo4j-skills --skill neo4j-graphrag-skill

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

GraphRAG retrieval in Neo4j can be difficult to wire correctly, especially when choosing the right retriever type, creating the required indexes, and composing safe Cypher-based graph traversal after vector search.

Core Features & Use Cases

  • Retriever selection & configuration: Choose the right retriever (VectorRetriever, HybridRetriever, VectorCypherRetriever, HybridCypherRetriever, Text2CypherRetriever, ToolsRetriever, and external vector retriever variants) based on whether you have fulltext, need graph traversal, or want LLM-routed retrieval.
  • Graph-augmented retrieval logic: Define a retrieval_query Cypher fragment with automatic node and score injection, plus parameterized query_params and pre-filtering via filters.
  • Production-grade pipeline wiring: Assemble GraphRAG(retriever=..., llm=...) and run .search() with support for many LLM and embedder providers, plus retrieval quality debugging with return_context and response_fallback.
  • Index prerequisites & compatibility: Guides vector + fulltext index setup for hybrid retrievers, supports neo4j-graphrag v1.7+ (neo4j-genai rename), and aligns with Neo4j driver/Neo4j version requirements.

Quick Start

Install neo4j-graphrag, create the required vector (and fulltext for hybrid) indexes, write a retrieval_query that returns node and score, then run GraphRAG.search to get graph-augmented answers.

Frequently Asked Questions about neo4j-graphrag-skill

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

FAQPage Schema
How do I build a GraphRAG retrieval pipeline in Neo4j?▼

To build a GraphRAG retrieval pipeline in Neo4j, select a retriever type, create the required vector or fulltext indexes, write a parameterized Cypher retrieval_query fragment returning node and score, and wire GraphRAG with an LLM and embedder.

What is the difference between vector, hybrid, and Text2Cypher retrievers in Neo4j?▼

Vector retrievers perform semantic search, hybrid retrievers combine vector and fulltext search, and Text2Cypher retrievers use an LLM to route natural language queries into safe Cypher-based graph traversal flows.

Do I need to create vector and fulltext indexes before using hybrid search in Neo4j?▼

Yes, hybrid search in Neo4j requires setting up both vector and fulltext indexes beforehand, as the HybridRetriever and HybridCypherRetriever depend on these index prerequisites to function correctly.

Can I use an external vector database with Neo4j graph traversal for retrieval?▼

Yes, neo4j-graphrag supports external vector retriever variants, allowing you to integrate an external vector database while still applying graph traversal logic via Cypher retrieval_query fragments.

How do I debug retrieval quality issues in a Neo4j GraphRAG pipeline?▼

Debug retrieval quality in a Neo4j GraphRAG pipeline by using the return_context parameter to inspect retrieved context and applying response_fallback to handle cases where the LLM fails to generate a valid response.

What Neo4j driver and neo4j-graphrag package versions are required for GraphRAG?▼

GraphRAG pipelines require neo4j-graphrag v1.7 or higher, which includes the neo4j-genai rename, and your Neo4j driver and Neo4j database version must align with the specified compatibility requirements.

Related Skills

Explore More Data & Analytics Skills→
FindMalekFindMalek
9

prisma-database-setup

Configure Prisma for multiple database providers and set up the client.

Community
Intermediate
anukkrit149anukkrit149

rag-implementation

Build Retrieval-Augmented Generation systems grounding LLM answers in vector databases.

Community
Advanced
kryptodoggkryptodogg

Cipher Data Engineer Skill

Manage data encoding, serialization, and Neo4j/Qdrant database integration.

Community
Advanced
roy2392roy2392

graph-recall

Retrieve long-term memory via vector search and recursive graph traversal on SQLite.

Community
Advanced