https://github.com/codealchemyml/graph-based-rag-system

This project involves implementing a graph-based RAG system using Langgraph and Langchain for a cybersecurity use case. It builds a dynamic graph from cybersecurity data, which can answer specific penetration testing-related questions.
https://github.com/codealchemyml/graph-based-rag-system

cybersecurity generative-ai langchain langgraph large-language-models retrieval-augmented-generation

Last synced: about 1 month ago
JSON representation

This project involves implementing a graph-based RAG system using Langgraph and Langchain for a cybersecurity use case. It builds a dynamic graph from cybersecurity data, which can answer specific penetration testing-related questions.

• Host: GitHub
• URL: https://github.com/codealchemyml/graph-based-rag-system
• Owner: CodeAlchemyML
• Created: 2024-11-08T16:13:40.000Z (over 1 year ago)
• Default Branch: main
• Last Pushed: 2024-11-08T18:09:53.000Z (over 1 year ago)
• Last Synced: 2025-01-02T03:14:27.617Z (over 1 year ago)
• Topics: cybersecurity, generative-ai, langchain, langgraph, large-language-models, retrieval-augmented-generation
• Language: Python
• Homepage:
• Size: 68.4 KB
• Stars: 0
• Watchers: 2
• Forks: 0
• Open Issues: 0
• Metadata Files:
  • Readme: README.md

Awesome Lists containing this project

README

          
# Graph-based Retrieval Augment Generation (RAG) System

---

**Project Overview:**

This project involves implementing a graph-based RAG system using Langgraph and Langchain for a cybersecurity use case. It builds a dynamic graph from cybersecurity data, which can answer specific penetration testing-related questions.

---

**Requirements:**

- Language: ![Python](https://img.shields.io/badge/-Python-3776AB?style=flat-square&logo=python&logoColor=white)

- Dependency: ![Poetry](https://img.shields.io/badge/Package%20Manager-Poetry-blue?logo=poetry)

- API: ![FastAPI](https://img.shields.io/badge/-FastAPI-009688?style=flat-square&logo=fastapi&logoColor=white)

- Database: Chroma Vector Database, with ingestion support from ![MongoDB](https://img.shields.io/badge/Database-MongoDB-green?logo=mongodb)

---

**Implementation:**

- *Graph Entity Design:* Defining entities (hosts, ports, services) and relationships dynamically based on the HackTheBox data and walkthroughs.

- *Data Ingestion:* Building an ingestion pipeline to handle irregular data updates.

- *Inference Pipeline:* Answering Cybersecurity-related queries using graph-based RAG with optimized response times.

---

**Usage:**

- Setup the Python environment with Poetry.

- Run the graph pipeline and ingestion process.

- Query the graph for penetration testing insights.