Can LLMs extract knowledge graphs from unstructured text? Introducing GraphGPT! Pass in any text (summary of a movie, passage from Wikipedia, etc.) to generate a visualization of entities and their relationships. A quick example:

Here's GraphGPT creating a knowledge graph from the synopsis of Veep:

In case you want to play with it yourself, here's the repo. All you need is an OpenAI API key.

GraphGPT is on the front page of HN 🎉

Play with GraphGPT without having to do any of the dev setup. All you need is an OpenAI API key! Thanks @sfzhu for the idea + PR 🚀

is that localhost?

🚢 🚢 🚢

What!! This is crazy useful. Great that you can append and edit with further Input. It probably wouldn't be hard to extend this to explore any domain/market with web search/summarization @codexeditor

Great stuff, especially for generating small & focused visualizations! But the output is simply a graph, not a #KnowledgeGraph, since it's missing #semantics & schema information. Also, it would be great if the output was available in a machine-processible format as well.

Nice project. How does one go about building a gpt-like training with custom data (without using openAI) ? For eg I have say a million spreadsheets of unstructured data and I want to chat with my data asking it to draw plots, graphs , asking questions to my data in English ..

man's shipping velocity crazy 🫡