You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
In the last example, there is a lot of repetitive copy and pasting (about 40 copy and pastes needed to rerun the parent prompt on each of the files in the current working directory).
Open to any suggestions on ways to reduce the overhead! This library is already making complex analytics pipelines accessible to my students, so I'm very grateful 🙏
The text was updated successfully, but these errors were encountered:
Problem
I am building educational materials for my data thinking lectures, such as:
https://colab.research.google.com/github/onefact/datathinking.org-codespace/blob/main/notebooks/princeton-university/week-1-visualizing-33-million-phone-calls-in-new-york-city.ipynb
https://colab.research.google.com/github/jaanli/language-model-notebooks/blob/main/notebooks/getting-started.ipynb
https://colab.research.google.com/github/onefact/electronic-health-records/blob/main/notebooks/loading_physionet_mimic_data.ipynb
In the last example, there is a lot of repetitive copy and pasting (about 40 copy and pastes needed to rerun the parent prompt on each of the files in the current working directory).
Proposed Solution
There should be a way to accept additional input such as
--format
or create cells automatically: https://stackoverflow.com/questions/13614783/programmatically-add-cells-to-an-ipython-notebook-for-report-generation (though this seems complicated).Additional context
Guidance (https://github.com/guidance-ai/guidance) comes to mind and SGLang (https://github.com/sgl-project/sglang) and aici (https://github.com/microsoft/aici).
Open to any suggestions on ways to reduce the overhead! This library is already making complex analytics pipelines accessible to my students, so I'm very grateful 🙏
The text was updated successfully, but these errors were encountered: