Replies: 2 comments 3 replies
-
Do you mean embedding the page, or want a real-time output from LLM in the slides? |
Beta Was this translation helpful? Give feedback.
1 reply
-
Perhaps embedding https://github.com/jupyterlite/jupyterlite could be a solution here? Not sure how well slidev interacts with Jupyter. |
Beta Was this translation helpful? Give feedback.
2 replies
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
-
Is your feature request related to a problem? Please describe.
I need to demo our approach at @onefact to leveraging large language models like ChatGPT for non-profit use cases (I'm giving a talk in a few days).
Here are the outputs I need to demo:
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
https://onefact.github.io/synthetic-healthcare-data/
https://jaanli.github.io/new-york-real-estate/
https://jaanli.github.io/american-community-survey/new-york-area/income-by-race
Describe the solution you'd like
Very little of the above code is written by our team. It is mainly written by claude.ai.
We need a way to communicate this concept to the audiences we are presenting to over the summer, including government entities and investors.
It is difficult to make an API call from Powerpoint or Keynote, so I thought I should try something based on
vite
because of how flexible and fast it is (these LLM APIs are the opposite of fast...).Describe alternatives you've considered
Having a screen recording is the worst case scenario (then people looking at our non-profit website after will need to see youtube ads, or other ways of hosting it - we use GitHub pages).
Beta Was this translation helpful? Give feedback.
All reactions