invinciblejha01/Cybersecurity_RAG_Knowledge_Graph-25-Topics-75-Articles-200-Chunks

---
license: other
tags:
- cybersecurity
- rag
- knowledge-graph
- synthetic
- ai-dataset
- embeddings
- llm
- chunked
- enterprise
size_categories:
- 100K<n<1M
dataset_info:
topics: 25
categories: 5
clusters: 4
articles: 75
chunks: 200
language:
- en
pretty_name: Cybersecurity RAG Knowledge Graph
task_categories:
- text-retrieval
- text-generation
- question-answering
---
Cybersecurity RAG Knowledge Graph (25 Topics, 75 Articles, 200 Chunks)
Preview dataset — full commercial package available at:
https://automatekc.gumroad.com/l/cybersecurity-rag-graph

Overview
This is a structured, synthetic, commercially‑safe cybersecurity knowledge graph designed for RAG systems, AI copilots, fine‑tuning, and domain‑specific retrieval.

This repo contains a preview only.
The full dataset (25 topics, 75 articles, ~200 chunks, graph metadata, and structured JSON files) is available for purchase at:
https://automatekc.gumroad.com/l/cybersecurity-rag-graph

What’s Included in the Full Version
25 cybersecurity topics

75 synthetic articles (3 per topic)

~200 RAG‑ready chunks

5 categories + 4 clusters

topic → category → cluster mapping

graph.json (relationships + hierarchy)

chunks.json (clean, consistent, embedding‑ready)

articles.json (full structured content)

metadata.json (slugs, IDs, timestamps)

All content is synthetic, original, and safe for commercial use.

Use Cases
Retrieval‑Augmented Generation (RAG)

Cybersecurity copilots

SOC automation assistants

Fine‑tuning domain‑specific LLMs

Embedding evaluation

Knowledge graph demos

AI agent context stores

Preview Files in This Repo
sample_chunks/ — small subset of chunks

sample_topics.json — limited preview of topic structure

README.md — this file

LICENSE.md — custom license terms

Full Dataset Access
Unlock the complete dataset:
https://automatekc.gumroad.com/l/cybersecurity-rag-graph