Stats
Actions
Tags
From memgraph
Blueprint for building language-agnostic GraphRAG systems with Memgraph, covering architecture, schema, ingestion, hybrid retrieval, tool contracts, and evaluation.
How this skill is triggered — by the user, by Claude, or both
Slash command
/memgraph:memgraph-graph-ragThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
Build Graph Retrieval-Augmented Generation systems that combine vector similarity search with graph traversal, and expose retrieval as tools for agents across any programming language.
Build Graph Retrieval-Augmented Generation systems that combine vector similarity search with graph traversal, and expose retrieval as tools for agents across any programming language.
Use this skill when:
Do NOT use this skill for:
By following this skill, you will deliver:
Sources (files, URLs, APIs)
│
▼
┌──────────────────────┐
│ Ingestion Pipeline │ Parse → chunk → entity extract
└──────────────────────┘
│
▼
┌──────────────────────┐
│ Memgraph │ Graph + embeddings + indexes
└──────────────────────┘
│
▼
┌──────────────────────┐
│ Hybrid Retriever │ Vector search + graph expansion
└──────────────────────┘
│
▼
┌──────────────────────┐
│ Agent Tools │ run_query / retrieve_context
└──────────────────────┘
│
▼
┌──────────────────────┐
│ LLM Response │ Answer with citations
└──────────────────────┘
Document the following before implementation:
Pick one of these:
unstructured2graph + lightrag-memgraphIngestion must always produce:
Use a stable schema so any client can query consistently:
Nodes
Document {id, title, source, created_at}Chunk {id, text, source, embedding}Entity {id, name, type, description}Concept {id, name}Relationships
(Document)-[:HAS_CHUNK]->(Chunk)(Entity)-[:MENTIONED_IN]->(Chunk)(Entity)-[:RELATES_TO]->(Entity)(Chunk)-[:NEXT]->(Chunk)Chunk.embeddingChunk(embedding)Keep embeddings consistent across ingestion and queries.
Default retrieval flow:
Recommended query pattern (pseudo-Cypher):
ChunkExpose retrieval and diagnostics as tools. Minimal contract:
Tool: run_query
{ cypher: string, params?: object }{ rows: array }Tool: retrieve_context
{ question: string, vector_k?: number, hop_limit?: number }{ chunks: [{text, source, entities[]}], graph_stats }Tool: ingest_sources
{ sources: string[], mode?: "append" | "replace" }{ documents, chunks, entities, duration_ms }Agents should:
get_schema once per sessionMemgraph supports the Bolt protocol. Use a Bolt-compatible driver in your language of choice.
Integration responsibilities in each language:
Minimum evaluation suite:
Log for each request:
Use the Memgraph AI Toolkit for faster setup:
memgraph-toolbox for core utilitiesunstructured2graph for parsing and ingestionlightrag-memgraph for entity extractionlangchain-memgraph for agent toolingTreat these as implementation options, not requirements.
npx claudepluginhub memgraph/skillsSearches MemPalace before answering questions about past work, people, projects, or prior decisions. Returns verbatim stored content instead of guessing from model memory.
Guides Payload CMS config (payload.config.ts), collections, fields, hooks, access control, APIs. Debugs validation errors, security, relationships, queries, transactions, hook behavior.
Implements vector databases with Pinecone, Weaviate, Qdrant, Milvus, pgvector for semantic search, RAG, recommendations, and similarity systems. Optimizes embeddings, indexing, and hybrid search.