Tuan Anh Nguyen Dang (Tadashi)

Please check the latest version and instruction for setting up GraphRAG here https://github.com/Cinnamon/kotaemon#setup-graphrag.

@soichisumi moving LightRAG to a separated service is a good idea. Will consider this in some future updates. However, keep in mind that you moving the setup problem to another...

To use Ollama in Docker, you might want to change the base URL of the Ollama server https://stackoverflow.com/questions/31324981/how-to-access-host-port-from-docker-container

@phv2312 sorry for the late comment. Overall the logic is fine but the current settings UI is a bit cluttered. I will push a small change to improve this prior...

Hi please check out installation from latest release, or alternatively try online installation method here https://cinnamon.github.io/kotaemon/online_install/

Also, follow this guide to setup local models from Ollama correctly https://github.com/Cinnamon/kotaemon/blob/main/docs/local_model.md#use-local-models-for-rag

Seems the configuration is correct. This issue might happen if your ollama API calling a big model and since the QA prompt has pretty long context it can cause out-of-memory...

Hi @ravaidly, basically you can try to send a really long message :D If it is due to memory error, any long message can cause this issue. You can try...

It okay to just run `pip install graphrag future` after installing all kotaemon base requirement and ignore those version conflict. Since `graphrag` base package continuously update their pipeline, we will...

Seem GraphRAG indexing is not working well. Please check this issue for more insight on setting up the env var required for GraphRAG :D https://github.com/Cinnamon/kotaemon/issues/140 Also, please check the log...