Knowledge graphs, also known as semantic networks, are a specialized application of graph databases used to store information about entities (person, location, organization, etc) and their relationships. They allow you to explore your data with an in...
blog.greenflux.us16 min read
Great walkthrough! I run Ollama on a Mac Mini (64GB unified memory) and have been experimenting with different models for structured data extraction. Curious — have you tried any of the newer Qwen3 models for the text-to-cypher task? I've been using qwen3:30b for code generation and it handles structured output surprisingly well.
The Obsidian integration idea is brilliant. I've been thinking about building something similar for my game dev notes — turning scattered devlogs into a queryable knowledge graph could be really useful for tracking dependencies between game systems.
This is exactly my kind of setup! I'm running Ollama on a Mac Mini (64GB unified memory) and the local inference capability is a game changer for privacy-sensitive data.
Currently testing qwen3:30b and deepseek-r1:70b locally — the 70b models are surprisingly capable for knowledge extraction tasks. Have you benchmarked different Ollama models for entity extraction accuracy? I'm curious whether smaller quantized models (like 8b) lose too much nuance for relationship detection compared to the 30b+ models.
The Neo4j + Obsidian integration is brilliant. I've been thinking about building a knowledge graph for my AI agent's memory system — right now it uses flat markdown files, but graph-based memory could enable much better contextual recall across sessions.
One question: how do you handle entity deduplication? In my experience, LLMs generate slightly different entity names for the same concept ("React.js" vs "React" vs "ReactJS"), which creates phantom nodes. Any strategies for merging those?
Great project! Bookmarked for reference. 🔥
Running a text-to-Cypher model through Ollama instead of calling a hosted LLM keeps the entire knowledge graph pipeline local — that tradeoff between latency and data privacy is underrated for sensitive datasets.
Running Neo4j + Ollama locally is such a smart approach for privacy-sensitive use cases. The enterprise world is moving hard toward local AI processing — no one wants their knowledge graphs on someone else servers. This is exactly the philosophy behind what we build with Genie 007 — keeping everything local in the browser. Voice commands + local knowledge graphs could be incredibly powerful for enterprise workflows.
Thanks for being patience with me. All my questions were answered and the support continued even after the delivery of the service . I will continue to work with you and I have already started referring family to you that needed similar assistance. Thanks JBEE SPY TEAM on telegram +44 7456 058620
That’s sick — local knowledge graphs with LLMs feels like giving your data a conspiracy-board upgrade.
Are you planning to run it mostly for fun experiments (like mapping your own notes) or for a real use case like rec engines / fraud detection?
This is EXACTLY what i was looking for, even though i didn’t know it!
Thank you so much for putting this out there when you did! i will pay it forward once i finish the project I’m working on by posting an article of my own and linking back to this one — thanks 🙏
Serghei Pogor
Serghei Pogor
Solid post. The thing I'd add: the tooling for contact verification has gotten genuinely good over the past couple years and the ROI on running your list through it before any campaign is probably the highest leverage thing you can do in the outbound stack. It's not glamorous but it consistently moves the numbers.