-
Notifications
You must be signed in to change notification settings - Fork 390
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
New (Python) example: simple drawings (rectangle, ellipse, arrow) #238
base: main
Are you sure you want to change the base?
Conversation
The idea is that you can write a small amount of JavaScript that reads the JSON and renders in an HTML5 canvas, or some Python that renders it in Tkinter, or anything else that strikes your fancy. I would like to use this to draw diagrams representing the stack and memory layout for an interpreter, to be used in internal docs.
There's some stuff here that makes intuitive sense, but I'll need to check in with others (CC @ahejlsberg) I would think that the best format for incorporating chat history would be something like
That gives background for the current convo, plus reinforces the current task at hand. This PR is pretty close to that. |
I wonder how to proceed. Clearly this PR two things (adding history and adding a new example) and that's not great. Your fixes to the translator (#240) broke my PR and I would rather not try to merge it back. I propose to add my example without chat history and start a separate discussion on chat history -- okay? |
(Just append the inputs, separated by newlines.)
For me, this works best with openai model gpt-3.5-turbo; gpt-4 seems worse (?!).
Here's a sample session (no longer valid without history support)