Adapting prompts for medical domain

SuperMedIntel / Medical-Graph-RAG

Medical Graph RAG: Graph RAG for the Medical Data

https://arxiv.org/html/2408.04187v1

MIT License

245 stars 40 forks source link

Adapting prompts for medical domain #4

Open oryx1729 opened 3 months ago

oryx1729 commented 3 months ago

Hi,

Thank you for open-sourcing this project. I've noticed that the prompts in nano-graphrag/nano_graphrag/prompt.py seem to closely follow the default prompts from Microsoft's official implementation, which includes entities like person, technology, mission, organization, and location.

I'm curious if you've experimented with adjusting these prompts to better extract medical-specific entities. If so, do you have any insights or findings from your experiments that you can share?

Thank you!

LinglongQian commented 2 months ago

Hi,

For medical concepts, there are also other tools like MedCAT. Medical entity extraction may be different from other entities, which have higher requirements for safety. Combining with other Medical NER tools may be a good solution.