https://github.com/gbikram/threatintelrag
Experimental RAG that consumes Cyber Security articles via RSS
https://github.com/gbikram/threatintelrag
chromadb cyber cybersecurity cyberthreatintelligence experminental langchain llm ollama rag threatintel
Last synced: over 1 year ago
JSON representation
Experimental RAG that consumes Cyber Security articles via RSS
- Host: GitHub
- URL: https://github.com/gbikram/threatintelrag
- Owner: gbikram
- Created: 2024-11-27T19:33:39.000Z (over 1 year ago)
- Default Branch: master
- Last Pushed: 2024-11-29T10:56:22.000Z (over 1 year ago)
- Last Synced: 2025-03-22T21:46:16.433Z (over 1 year ago)
- Topics: chromadb, cyber, cybersecurity, cyberthreatintelligence, experminental, langchain, llm, ollama, rag, threatintel
- Language: Jupyter Notebook
- Homepage:
- Size: 41.1 MB
- Stars: 3
- Watchers: 1
- Forks: 2
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
Awesome Lists containing this project
README
# Custom RAG for Cyber Threat Intel
Experimental code for building a custom RAG model for CTI.
**References:**
* https://www.youtube.com/watch?v=0zgYu_9WF7A
* https://www.youtube.com/watch?v=75uBcITe0gU&t=565s
```mermaid
---
config:
theme: neutral
---
flowchart TD
A1["RSS Sources"] --> B["Python Jupyter Notebook"]
A2["CSV Sources"] --> B
A3["PDF Sources"] --> B
B --> C{"Langchain"}
C -- Convert to Documents --> D["Document Transformation"]
D --> E{"ChromaDB"}
E -- Create Vectorstore --> F["Indexed Vector Embeddings"]
F --> G{"Ollama LLM"}
G -- Query Vectorstore --> H["Retrieval & Generation"]
H --> I["User Query Response"]
A1:::sources
B:::process
A2:::sources
A3:::sources
C:::process
D:::process
E:::storage
F:::storage
G:::model
H:::model
I:::model
classDef sources fill:#f9f,stroke:#333,stroke-width:2px
classDef process fill:#bbf,stroke:#333,stroke-width:2px
classDef storage fill:#bfb,stroke:#333,stroke-width:2px
classDef model fill:#fb0,stroke:#333,stroke-width:2px
```