Closed cmdoret closed 11 months ago
In case it is useful I leave here how I'm running this using a jupyter lab instance.
ENTRYPOINT
at the bottom of Dockerfile by ENTRYPOINT ["/bin/bash"]
docker build kg-llm-interface .
docker run -it --rm -p 8888:8888 kg-llm-interface
apt get install git
make install
pip install jupyter lab
poetry run python -m ipykernel install --user --name aikg
jupyter lab --allow-root --port 8888 --ip '0.0.0.0'
I have been able to run the ng_sparql.ipynb
without errors :)
P.S. Git is required to install aikg when running make install
This PR mainly adds two things (along with a lot of refactoring):
local execution works by setting:
It also adds a notebook documenting the whole process. It runs fully locally and can use the OpenAPI API.
Additional improvements: