A proof-of-concept jupyter extension which converts english queries into relevant python code
MIT License
pip uninstall mopp
For Mac and other Ubuntu installations not having a nvidia GPU, we need to explicitly set an environment variable at time of install.
export JUPYTER_TEXT2CODE_MODE="cpu"
sudo apt-get install libopenblas-dev libomp-dev
git clone https://github.com/deepklarity/jupyter-text2code.git
cd jupyter-text2code
pip install .
jupyter nbextension enable jupyter-text2code/main
pip uninstall jupyter-text2code
jupyter notebook
Nbextensions
tab in Jupyter notebook run the following command:jupyter contrib nbextension install --user
notebooks/ctds.ipynb
notebook for testingtensorflow_hub
Terminal
Icon which appears on the menu (to activate the extension)We have published CPU and GPU images to docker hub with all dependencies pre-installed.
1.51 GB
2.56 GB
The plugin now supports pandas commands + quick snippet insertion of available snippets from awesome-notebooks. With this change, we can now get snippets for most popular integrations from within the jupyter tab. eg:
paraphrase-MiniLM-L6-v2
ner_templates
with a new intent_idgenerate_training_data.py
if different generation techniques are needed or if introducing a new entity.jupyter_text2code/jupyter_text2code_serverextension/__init__.py
with new intent's condition and add actual code for the intentpip install .