In the past few weeks we’ve been working on implementing a fast and cheap version of graphrag. I hope that it can be helpful for your projects and it’d be great to have feedback to keep improving it and keep moving in the right direction.
We’re trying to keep the code tidy and organized. We enforced typing, and we’re raising the bar on test coverage. We’re still working on the docs, but the readme should help you get started.
We’re still adding features and improving it based on the latest research and community input. We’d love to get feedback and see what people build with it. Any contribution is welcomed.
Great work! Makes me wonder how we will experience books (and knowledge in general) in the future. It's obvious that the static/linear representation of knowledge + the information overload we are all immersed into needs to evolve.
You're right! Static knowledge is definitely one of the main limitations of other rag methods. Encoding information that changes over time is such a powerful feature of graphrag
3 comments
[ 3.9 ms ] story [ 26.0 ms ] threadWe’re trying to keep the code tidy and organized. We enforced typing, and we’re raising the bar on test coverage. We’re still working on the docs, but the readme should help you get started.
Check it out here on GitHub: https://github.com/circlemind-ai/fast-graphrag
We’re still adding features and improving it based on the latest research and community input. We’d love to get feedback and see what people build with it. Any contribution is welcomed.