Skip to content

MindMap: Knowledge Graph Prompting Sparks Graph of Thoughts in Large Language Models

Notifications You must be signed in to change notification settings

xutianhan/MindMap

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

23 Commits
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

MindMap: Knowledge Graph Prompting Sparks Graph of Thoughts in Large Language Models

This is the official codebase of the MindMap ❄️ framework for eliciting the graph-of-thoughts reasoning capability in LLMs, proposed in MindMap: Knowledge Graph Prompting Sparks Graph of Thoughts in Large Language Models.

Overview

We present MindMap, a plug-and-play prompting approach, which enables LLMs to comprehend graphical inputs to build their own mind map that supports evidence-grounded generation. Here is an overview of our model architecture: https://github.com/willing510/MindMap/blob/main/fig/mind%20map.png

Run MindMap

As the chatdoctor5k dataset for example. First, you need to create a Blank Sandbox on https://sandbox.neo4j.com/, click "connect via drivers", find your url and user password. Then replace the following parts in MindMap.py:

uri = "Your_url"
username = "Your_user"     
password = "Your_password"

Note that the data of CMCKG is too large, and it will take about two days to wait. We recommend clicking "extend your project" in neo4j sandbox. But don't worry, the EMCKG used by chatdoctor5k will be ready to build on your facility in no time. Then, don't forget to replace your openai_key in MindMap.py.

Build your own MindMap

About

MindMap: Knowledge Graph Prompting Sparks Graph of Thoughts in Large Language Models

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages

  • Python 88.3%
  • Jupyter Notebook 11.7%