Skip to main content
Glama
anils123
by anils123

Plattform für Fertigungs-Rückverfolgbarkeits-Intelligenz

GraphRAG-gestützte agentische KI-Plattform für Fertigungs-Rückverfolgbarkeit mit Neo4j, Amazon Bedrock und MCP.

Architektur

┌─────────────────────────────────────────────────────────────────────┐
│                    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

Schnellstart

1. Voraussetzungen

  • Neo4j 5.x (mit APOC-Plugin)

  • Python 3.11+

  • AWS-Anmeldedaten mit Bedrock-Zugriff (Claude 3.5 Sonnet + Titan Embed v2)

2. Einrichtung

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 credentials

3. Neo4j starten (Docker)

docker-compose up neo4j -d

4. Wissensgraph befüllen

set PYTHONPATH=src
python scripts/seed_data.py

5. Plattform starten

# API server
python main.py api

# MCP server (for Claude Desktop)
python main.py mcp

# Both
python main.py all

6. Dokumente erfassen

python scripts/ingest.py path/to/spec.pdf path/to/requirements.csv

API-Endpunkte

Methode

Endpunkt

Beschreibung

GET

/health

Gesundheitsprüfung

GET

/graph/stats

Knotenanzahl nach Label

POST

/ingest/file

Dokument hochladen und erfassen

POST

/ingest/record

Strukturierten API-Datensatz erfassen

POST

/query

Hybride GraphRAG-Abfrage

POST

/agent/langgraph

LangGraph-Argumentationsagent

POST

/agent/strands

Strands-Tool-Aufruf-Agent

GET

/traceability/defect/{id}

Vollständige Fehler-Rückverfolgbarkeitskette

GET

/traceability/product/{id}

Produkt-Rückverfolgbarkeitsübersicht

Beispielabfragen

# 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

MCP-Integration (Claude Desktop)

Kopieren Sie den Inhalt von config/claude_desktop_mcp.json in Ihre Claude-Desktop-claude_desktop_config.json.

Verfügbare MCP-Tools:

  • ask_manufacturing_ai — hybride GraphRAG-Fragen & Antworten

  • semantic_search — Vektorähnlichkeitssuche

  • graph_trace — Graph-Traversal-Abruf

  • natural_language_to_cypher — NL2Cypher

  • get_defect_chain — vollständige Fehler-Rückverfolgbarkeit

  • get_requirement_traceability — Anforderungsabdeckung

  • product_health_dashboard — Produktmetriken

Wissensgraph-Schema

(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)

Tests ausführen

set PYTHONPATH=src
pytest tests/ -v

Related MCP Connectors

Related MCP Servers

  • F
    license
    Not graded
    quality
    D
    maintenance
    Enables storage and retrieval of knowledge in a graph database format, allowing users to create, update, search, and delete entities and relationships in a Neo4j-powered knowledge graph through natural language.
    5
    -
  • A
    license
    C
    quality
    D
    maintenance
    Combines a knowledge graph with RAG (Retrieval-Augmented Generation) capabilities for semantic code indexing and search. Enables creating entity relationships, managing observations, and performing semantic searches across indexed codebases.
    13
    MIT
  • F
    license
    Not graded
    quality
    C
    maintenance
    Transforms code repositories and development documentation into a queryable Neo4j knowledge graph, enabling AI assistants to perform intelligent code analysis, dependency mapping, impact assessment, and automated documentation generation across 15+ programming languages.
    7
    -