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
I have a few ideas on how we can use Markdown’s flexibility to enhance our UI without a lot of extra work.
1. Dynamic Content Binding in Markdown
We could set it up so that Markdown can link to code outputs, something like {{ cellName.xxx }}. We could also later allow users to select cells directly from the UI. This would allow us to display different types of outputs—text, images, HTML, whatever—right in Markdown. Sure, we’ll need to design some mechanisms to support this. This would make the interface more richer in content.
2. Code-Notebook Interaction API
Another idea is to create an API that lets the code read and interact with notebook cells, with functions like getCells, insertCell or modifyCell. This could be useful for a bunch of LLM chat use cases, like:
• Code reading user-input prompt cells
• Appending responses to existing cells or creating new ones
• Using the output cell as context for the next interaction if we can read all the cells in the code
This would basically turn the notebook into a natural chat interface
reacted with thumbs up emoji reacted with thumbs down emoji reacted with laugh emoji reacted with hooray emoji reacted with confused emoji reacted with heart emoji reacted with rocket emoji reacted with eyes emoji
-
I have a few ideas on how we can use Markdown’s flexibility to enhance our UI without a lot of extra work.
We could set it up so that Markdown can link to code outputs, something like {{ cellName.xxx }}. We could also later allow users to select cells directly from the UI. This would allow us to display different types of outputs—text, images, HTML, whatever—right in Markdown. Sure, we’ll need to design some mechanisms to support this. This would make the interface more richer in content.
Another idea is to create an API that lets the code read and interact with notebook cells, with functions like getCells, insertCell or modifyCell. This could be useful for a bunch of LLM chat use cases, like:
• Code reading user-input prompt cells
• Appending responses to existing cells or creating new ones
• Using the output cell as context for the next interaction if we can read all the cells in the code
This would basically turn the notebook into a natural chat interface
Beta Was this translation helpful? Give feedback.
All reactions