convez.ai
PluginDados & AnalyticsIntermediário
memgraph

Memgraph AI Toolkit

memgraph/ai-toolkit

Grafos de conhecimento + IA generativa para RAG avançado

Ver no GitHub
BomPluginScore · de 0 a 100

Toolkit completo para construir aplicações de IA com grafos de conhecimento usando Memgraph, LangChain e MCP. Integra RAG potencializado por grafos, transformação de documentos em grafos de conhecimento e agentes inteligentes para consultas e processamento de dados estruturados.

Instalação

$npx convez-ai memgraph/ai-toolkit

1 comando no terminal: detecta o formato do repositório (marketplace ou plugin avulso) e instala via Claude Code. Requer Node 18+ e o Claude Code instalado.

Métricas

Estrelas
119
Forks
16
Acompanhando
4
Saúde
50%
Último commit
há 2 dias
Versão
v0.2.6
Issues abertas
65
Contribuidores
9

Casos de uso

  • Construir sistemas RAG com grafos de conhecimento estruturados
  • Transformar documentos e PDFs em grafos consultáveis via IA
  • Criar agentes inteligentes que raciocinam sobre relações em grafos
  • Integrar bancos de dados em grafo com LangChain e pipelines GenAI

Veredito

Toolkit maduro e bem documentado que resolve um problema real: combinar grafos de conhecimento com IA generativa. Excelente para quem precisa de RAG estruturado além de embeddings vetoriais simples, mas requer familiaridade com Python, LangChain e conceitos de grafo.

README

A tradução para o português deste README ainda está na fila.

Memgraph AI Toolkit

PyPI - memgraph-toolbox PyPI - langchain-memgraph PyPI - mcp-memgraph PyPI - unstructured2graph Discord

Build powerful AI applications with graph-powered RAG using Memgraph. This toolkit provides everything you need to integrate knowledge graphs into your GenAI workflows.

🚀 Quick Setup

Start Memgraph

docker run -p 7687:7687 \
  --name memgraph \
  memgraph/memgraph-mage:latest \
  --schema-info-enabled=true

Install Packages

# Core toolbox
pip install memgraph-toolbox

# LangChain integration
pip install langchain-memgraph

# MCP server
pip install mcp-memgraph

# Unstructured to Graph
pip install unstructured2graph

📚 Usage Examples

unstructured2graph - Build Knowledge Graphs from Documents

Transform PDFs, URLs, and documents into queryable knowledge graphs:

import asyncio
from memgraph_toolbox.api.memgraph import Memgraph
from lightrag_memgraph import MemgraphLightRAGWrapper
from unstructured2graph import from_unstructured, create_index

async def main():
    memgraph = Memgraph()
    create_index(memgraph, "Chunk", "hash")

    lightrag = MemgraphLightRAGWrapper()
    await lightrag.initialize(working_dir="./lightrag_storage")

    # Ingest documents from URLs or local files
    await from_unstructured(
        sources=["https://example.com/doc.pdf", "./local_file.md"],
        memgraph=memgraph,
        lightrag_wrapper=lightrag,
        link_chunks=True,
    )
    await lightrag.afinalize()

asyncio.run(main())

👉 Full Documentation | Examples


langchain-memgraph - LangChain Integration

Natural Language Queries with MemgraphQAChain

from langchain_memgraph.graphs.memgraph import MemgraphLangChain
from langchain_memgraph.chains.graph_qa import MemgraphQAChain
from langchain_openai import ChatOpenAI

graph = MemgraphLangChain(url="bolt://localhost:7687")

chain = MemgraphQAChain.from_llm(
    ChatOpenAI(temperature=0),
    graph=graph,
    model_name="gpt-4-turbo",
    allow_dangerous_requests=True,
)

response = chain.invoke("Who are the main characters in the dataset?")
print(response["result"])

Build Agents with MemgraphToolkit

from langchain.chat_models import init_chat_model
from langchain_memgraph import MemgraphToolkit
from langchain_memgraph.graphs.memgraph import MemgraphLangChain
from langgraph.prebuilt import create_react_agent

llm = init_chat_model("gpt-4o-mini", model_provider="openai")
db = MemgraphLangChain(url="bolt://localhost:7687")
toolkit = MemgraphToolkit(db=db, llm=llm)

agent = create_react_agent(llm, toolkit.get_tools())
events = agent.stream({"messages": [("user", "Find all Person nodes")]})

👉 Full Documentation


mcp-memgraph - Model Context Protocol Server

Expose Memgraph to LLMs via MCP. Run with Docker:

# HTTP mode (recommended)
docker run --rm -p 8000:8000 memgraph/mcp-memgraph:latest

# Stdio mode for MCP clients
docker run --rm -i -e MCP_TRANSPORT=stdio memgraph/mcp-memgraph:latest

Available Tools:

ToolDescription
run_queryExecute Cypher queries
get_schemaFetch graph schema
get_page_rankCompute PageRank scores
get_node_neighborhoodFind nodes within distance
search_node_vectorsVector similarity search

👉 Full Documentation


sql2graph Agent - Automated Database Migration

Migrate from MySQL/PostgreSQL to Memgraph with AI assistance:

cd agents/sql2graph
uv run main.py

👉 Full Documentation


🛠️ Packages Overview

PackageDescriptionInstall
memgraph-toolboxCore utilities for Memgraphpip install memgraph-toolbox
langchain-memgraphLangChain tools and chainspip install langchain-memgraph
mcp-memgraphMCP server for LLMspip install mcp-memgraph
unstructured2graphDocument to graph conversionpip install unstructured2graph
sql2graphDatabase migration agentSee docs

❓ FAQ

Which databases are supported?
Memgraph is the primary target. The sql2graph agent supports MySQL and PostgreSQL as source databases.

Do I need an LLM API key?
Yes, for features like entity extraction (unstructured2graph) and natural language queries (langchain-memgraph).

Can I use local LLMs?
Yes! LangChain integration supports any LangChain-compatible model, including Ollama.


🤝 Community

⭐ If you find this toolkit helpful, please star the repository!


🧪 Developing Locally

You can build and test each package directly from your repo.

Core tests

uv pip install -e memgraph-toolbox[test]
pytest -s memgraph-toolbox/src/memgraph_toolbox/tests

LangChain integration tests

Create a .env file with your OPENAI_API_KEY, as the tests depend on LLM calls:

uv pip install -e integrations/langchain-memgraph[test]
pytest -s integrations/langchain-memgraph/tests

MCP integration tests

uv pip install -e integrations/mcp-memgraph[test]
pytest -s integrations/mcp-memgraph/tests

Agent integration tests

uv pip install -e integrations/agents[test]
pytest -s integrations/agents/tests

To run a complete migration workflow with the agent:

cd integrations/agents
uv run main.py

Note: The agent requires both MySQL and Memgraph connections. Set up your environment variables in .env based on .env.example.

If you are running any test on macOS in zsh, add "" to the command:

uv pip install -e memgraph-toolbox"[test]"
Ver o original no GitHub

Bom para

Relacionados