Neo4J Graphrag Kg

B 82 completed
Library
cli / python · tiny
40
Files
2,786
LOC
1
Frameworks
5
Languages

Pipeline State

completed
Run ID
#347278
Phase
done
Progress
1%
Started
Finished
2026-04-13 01:31:02
LLM tokens
0

Pipeline Metadata

Stage
Skipped
Decision
skip_scaffold_dup
Novelty
24.61
Framework unique
Isolation
Last stage change
2026-04-16 18:15:42
Deduplication group #47941
Member of a group with 1 similar repo(s) — canonical #9446 view group →
Top concepts (2)
Project DescriptionTesting
Repobility · code-quality intelligence platform · https://repobility.com

AI Prompt

Create a command-line tool using Python that manages a Neo4j knowledge graph for GraphRAG pipelines. The tool should allow users to ingest unstructured text documents by reading them, chunking the content, and then extracting entities and relationships. I need functionality to run this extraction using either a default heuristic extractor or by integrating with an LLM provider like OpenAI. The tool must support batch upserting of data into Neo4j and provide commands to check the connection status, initialize the database schema, and query the resulting graph using Cypher. Please structure this as a CLI application.
python cli neo4j knowledge-graph graphrag llm docker cypher
Generated by gemma4:latest

Catalog Information

A Python library that constructs and manages a Neo4j knowledge graph to support GraphRAG pipelines.

Description

This library provides tools to ingest structured and unstructured data into a Neo4j graph database, creating a knowledge graph optimized for Retrieval-Augmented Generation (RAG) workflows. It offers utilities for node and relationship creation, embedding generation via OpenAI or Anthropic models, and query interfaces that return contextually relevant subgraphs. Designed for AI developers and data engineers, it streamlines the integration of semantic embeddings with graph structures, enabling efficient retrieval for large language model prompts. The library abstracts complex Cypher queries, allowing users to focus on data modeling rather than database syntax. It supports incremental updates, schema validation, and performance tuning for large-scale knowledge graphs.

الوصف

توفر هذه المكتبة أدوات لاستيراد البيانات المهيكلة وغير المهيكلة إلى قاعدة بيانات Neo4j، مما يخلق مخطط معارف مُحسَّن لعمليات Retrieval-Augmented Generation (RAG). تتضمن وظائف لإنشاء العقد والعلاقات، وتوليد التمثيلات المضمنة باستخدام نماذج OpenAI أو Anthropic، وتوفير واجهات استعلام تُرجع أجزاء مخطط معتمدة على السياق. صُممت لتلبية احتياجات مطوري الذكاء الاصطناعي ومهندسي البيانات، وتُسهل دمج التمثيلات الدلالية مع هياكل الرسم البياني، مما يتيح استرجاعًا فعالًا للمدخلات في نماذج اللغة الكبيرة. تُجرد المكتبة من تعقيدات استعلامات Cypher، وتسمح للمستخدمين بالتركيز على نمذجة البيانات بدلاً من صياغة الاستعلامات. كما تدعم التحديثات التدريجية، والتحقق من صحة المخطط، وضبط الأداء لمخططات المعارف الضخمة.

Novelty

7/10

Tags

knowledge-graph graph-database retrieval-augmented-generation semantic-search ai-data-modeling

Technologies

anthropic openai typer

Claude Models

claude-opus-4.6

Quality Score

B
82.3/100
Structure
81
Code Quality
87
Documentation
80
Testing
70
Practices
79
Security
100
Dependencies
60

Strengths

  • Good test coverage (100% test-to-source ratio)
  • Code linting configured (ruff (possible))
  • Consistent naming conventions (snake_case)
  • Good security practices \u2014 no major issues detected
  • Containerized deployment (Docker)

Weaknesses

  • No LICENSE file \u2014 legal ambiguity for contributors
  • No CI/CD configuration \u2014 manual testing and deployment

Recommendations

  • Set up CI/CD (GitHub Actions recommended) to automate testing and deployment
  • Add a LICENSE file (MIT recommended for open source)

Security & Health

5.3h
Tech Debt (D)
A
OWASP (100%)
PASS
Quality Gate
A
Risk (5)
Repobility · severity-and-effort ranking · https://repobility.com
Unknown
License
1.0%
Duplication
Full Security Report AI Fix Prompts SARIF SBOM

Languages

python
84.2%
markdown
11.5%
text
2.0%
toml
1.6%
yaml
0.6%

Frameworks

pytest

Concepts (2)

Analysis by Repobility (https://repobility.com) · MCP-ready
CategoryNameDescriptionConfidence
Citation: Repobility (2026). State of AI-Generated Code. https://repobility.com/research/
auto_descriptionProject DescriptionA lightweight, Neo4j-first knowledge graph toolkit for building GraphRAG pipelines.80%
auto_categoryTestingtesting70%

Quality Timeline

1 quality score recorded.

View File Metrics

Embed Badge

Add to your README:

![Quality](https://repos.aljefra.com/badge/71356.svg)
Quality BadgeSecurity Badge
Export Quality CSVDownload SBOMExport Findings CSV