基于 GraphRAG 的智能体 AI 平台，用于制造可追溯性，使用 Neo4j、Amazon Bedrock 和 MCP。
┌─────────────────────────────────────────────────────────────────────┐
│ 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（带 APOC 插件）
Python 3.11+
具有 Bedrock 访问权限的 AWS 凭证（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.csv方法 | 端点 | 描述 |
GET |
| 健康检查 |
GET |
| 按标签统计节点数量 |
POST |
| 上传并摄取文档 |
POST |
| 摄取结构化 API 记录 |
POST |
| 混合 GraphRAG 查询 |
POST |
| LangGraph 推理智能体 |
POST |
| Strands 工具调用智能体 |
GET |
| 完整缺陷可追溯链 |
GET |
| 产品可追溯性摘要 |
# 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-002将 config/claude_desktop_mcp.json 的内容复制到你的 Claude Desktop claude_desktop_config.json 中。
可用的 MCP 工具：
ask_manufacturing_ai — 混合 GraphRAG 问答
semantic_search — 向量相似性搜索
graph_trace — 图遍历检索
natural_language_to_cypher — 自然语言转 Cypher
get_defect_chain — 完整缺陷可追溯性
get_requirement_traceability — 需求覆盖
product_health_dashboard — 产品指标
(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/ -vAnswer 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.
