GraphRAG 기반 에이전트형 AI 플랫폼으로, Neo4j, Amazon Bedrock, MCP를 사용하여 제조 추적성을 제공합니다.
┌─────────────────────────────────────────────────────────────────────┐
│ INGESTION & ENRICHMENT LAYER │
│ Connectors → Chunking → Embeddings → Entity Extraction → │
│ Entity Resolution → Graph Construction │
└──────────────────────────┬──────────────────────────────────────────┘
│
┌──────────────────────────▼──────────────────────────────────────────┐
│ KNOWLEDGE GRAPH (Neo4j) │
│ Product → Requirement → Component → TestCase → TestRun → │
│ Defect → ChangeRequest │
└──────────────────────────┬──────────────────────────────────────────┘
│
┌──────────────────────────▼──────────────────────────────────────────┐
│ RETRIEVAL LAYER │
│ VectorRetriever │ GraphRAGRetriever │ NL2CypherRetriever │ Hybrid │
└──────────────────────────┬──────────────────────────────────────────┘
│
┌──────────────────────────▼──────────────────────────────────────────┐
│ AGENT LAYER │
│ LangGraph Agent (plan→retrieve→reason→validate→respond) │
│ Strands Agent (tool-calling with 5 specialized graph tools) │
└──────────────────────────┬──────────────────────────────────────────┘
│
┌──────────────────────────▼──────────────────────────────────────────┐
│ INTERFACE LAYER │
│ FastAPI REST │ MCP Server (Claude Desktop / Cursor compatible) │
└─────────────────────────────────────────────────────────────────────┘Related MCP server: RAG MCP Server
Neo4j 5.x (APOC 플러그인 포함)
Python 3.11+
Bedrock 액세스 권한이 있는 AWS 자격 증명 (Claude 3.5 Sonnet + Titan Embed v2)
cd manufacturing-graphrag
python -m venv .venv
.venv\Scripts\activate # Windows
pip install -r requirements.txt
python -m spacy download en_core_web_sm
copy .env.example .env # Edit with your credentialsdocker-compose up neo4j -dset PYTHONPATH=src
python scripts/seed_data.py# API server
python main.py api
# MCP server (for Claude Desktop)
python main.py mcp
# Both
python main.py allpython scripts/ingest.py path/to/spec.pdf path/to/requirements.csv메서드 | 엔드포인트 | 설명 |
GET |
| 상태 확인 |
GET |
| 레이블별 노드 수 |
POST |
| 문서 업로드 및 수집 |
POST |
| 구조화된 API 레코드 수집 |
POST |
| 하이브리드 GraphRAG 쿼리 |
POST |
| LangGraph 추론 에이전트 |
POST |
| Strands 도구 호출 에이전트 |
GET |
| 전체 결함 추적성 체인 |
GET |
| 제품 추적성 요약 |
# Hybrid GraphRAG query
curl -X POST http://localhost:8000/query \
-H "Content-Type: application/json" \
-d '{"question": "What components are affected by the thermal runaway defect?"}'
# LangGraph agent — multi-step reasoning
curl -X POST http://localhost:8000/agent/langgraph \
-d '{"question": "Trace the full impact chain of DEF-001 and identify all change requests needed"}'
# Strands agent — tool-calling
curl -X POST http://localhost:8000/agent/strands \
-d '{"question": "Which critical defects are blocking the EV BMS release?"}'
# Defect traceability
curl http://localhost:8000/traceability/defect/DEF-002config/claude_desktop_mcp.json의 내용을 Claude Desktop의 claude_desktop_config.json에 복사하세요.
사용 가능한 MCP 도구:
ask_manufacturing_ai — 하이브리드 GraphRAG Q&A
semantic_search — 벡터 유사도 검색
graph_trace — 그래프 탐색 검색
natural_language_to_cypher — NL2Cypher
get_defect_chain — 전체 결함 추적성
get_requirement_traceability — 요구 사항 커버리지
product_health_dashboard — 제품 지표
(Product)-[:HAS_REQUIREMENT]->(Requirement)
(Component)-[:IMPLEMENTS]->(Requirement)
(TestCase)-[:VALIDATES]->(Requirement)
(TestRun)-[:INSTANCE_OF]->(TestCase)
(TestRun)-[:FOUND_IN]->(Defect)
(Defect)-[:AFFECTS]->(Component)
(Defect)-[:TRIGGERS_CHANGE]->(ChangeRequest)
(ChangeRequest)-[:MODIFIES]->(Component)
(Document)-[:CONTAINS_CHUNK]->(Chunk)
(Chunk)-[:MENTIONS]->(any entity)set PYTHONPATH=src
pytest tests/ -vThis server cannot be deployed
Answer questions using your semantic layer and company knowledge graph.
Knowledge graph ingestion, entity search, ontology analysis, and CoSync scoring.
Shared semantic graph for AI reviews, classification and structured memory across AI assistants.
AI knowledge graph for architecture, portfolio, and digital strategy management.
