Chats are exported to paste.gg, are unlisted by default, and expire
in 30 days by default. The user is also provided with the deletion
key which will be only shown at the time of creation, and it's needed
to take down the paste.
Rendering looks quite great, including code and turns.
The package makes the App slower to load, and I am not
aware of people using the Code
Execution feature
If someone still wants it, we can quickly revert
this commit and add it back (or you can use an older
official/preview build on Vercel)
Note: some older chats will lost the name of the model
but they'll regain it fast. And now the system purpose
that originated the message is captured, as well as
the typing indication
Closes#18 and closes#16. Interesting find: the "code":"model_not_found" shows
that the model is just not authorized for this API key. If the model is really
non-existing and can't be found, the error code will be "null", and the message
will be "The model 'XYZ' does not exist".
Behind the scenes, we detect the model name from the OpenAI
streaming API (it's in all the chunks), and stream it back
to the UI as a serialized JSON object. This is more of a
workaround, required by virtue of the streaming API, and can
be cleaned up later.
Model names available when hovering 'gpt-4' / '3.5-turbo'.
Warning: this adds 203kb of JS to the app, more than 4x'ing
the size of the app. Will remove if not worth it. Uses Sandpack
from Codesandbox.io, which stands up full execution environments
for the code.
Enrico Ros