Skip to content
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.

Sign up for GitHub

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

Jump to bottom

Audio input, app layout tweaks, better background startup, use ExtendedTask #224

Merged
merged 48 commits into from
Aug 31, 2024
Merged

Audio input, app layout tweaks, better background startup, use ExtendedTask #224

merged 48 commits into from
Aug 31, 2024

Conversation

JamesHWade
Copy link
Collaborator

@JamesHWade JamesHWade commented Aug 23, 2024 •
edited
Loading

Related issue

Description of changes

This is a rather big PR. It includes:

  • A new audio input option (this may only show up if you open the app in a browser)
  • Changes to gathering editor theme to improve compatibility with Positron
  • Changes the name of run_chatgpt_app to gptstudio_run_chat_app
  • Revamps the bg app startup to work better with linux
  • Change the default openai model to gpt-4o
  • Adds tests for creating API skeletons
  • Restyles chat app to feel more chat-like
  • Uses ExtendedTask to run api calls in non-blocking (async) mode
  • Add code syntax highlighting based on selected theme (defaults to github styling)

For contributors

  • I have added the relevant changes to the NEWS.md file
  • I have added relevant tests or documentation with my changes
    • We should update app screenshots to showcase the changes for our next release.

For reviewers

  • Changes meet the acceptance criteria of the related issue
  • The contribution follows style conventions and code of conduct
  • Branch passes automated testing
  • I have incremented the package version in the DESCRIPTION file before merging

JamesHWade and others added 23 commits August 23, 2024 13:46
@JamesHWade
use input_task_button for chat
f5d3e74
@JamesHWade
shorten notification time
c1b68f1
@JamesHWade
add audio input functions
78c3078
@JamesHWade
[wip] audio input option
f302d96
@JamesHWade
first working audio input
20a6456
@JamesHWade
fix theme info fetching to run in positron Fixes #217
5595d35
@JamesHWade
dynamic UI for audio and devtools::document()
0fb2b73
@JamesHWade
change name of run_chatgpt_app to gptstudio_run_chat_app
469dff5
@JamesHWade
minor refactor to app server code
45dde96
@JamesHWade
revamp bg app startup to work on linux Fixes #179
fc80c92
@JamesHWade
cleanup audio app option
3380ee8
@JamesHWade
lint cleanup and a start on vision #222
9eb110e
@JamesHWade
devtools::document()
a664030
@JamesHWade
use gpt-4o as default model
2f408e4
@JamesHWade
api skeleton tests
ea55e20
@JamesHWade
fix tests and update NEWS
0a88caf
@JamesHWade
lint and style with grkstyle
f1ac74e
@JamesHWade
convert app styling to be more chat-like (and repair streaming)
48ce475
@JamesHWade
fix linting
1eb0cf0
@JamesHWade
use ExtendedTask for async job
f3be247
@JamesHWade
document, apply styling, fix linting
1343f53
@JamesHWade
update news
5511e5d
@JamesHWade
refactor audio transcription and add tests
fcb826b
@JamesHWade JamesHWade changed the title Audio input Audio input, app layout tweaks, better background startup, use ExtendedTask Aug 26, 2024
This was linked to issues Aug 26, 2024
Viewer Connection Refused" when starting chat session from add in #179
Closed
[FR]: Support vision features #222
Open
Add voice command integration with whisper #66
Closed
@JamesHWade JamesHWade marked this pull request as ready for review August 26, 2024 00:07
@JamesHWade
Copy link
Collaborator Author

For testing the audio input, you'll need to open the app in a browser instead of RStudio viewer. I haven't found a workaround to that. Same behavior in Positron.

@JamesHWade
Copy link
Collaborator Author

#222 should not be marked as ready to close. It's still WIP. That's my bad.

@JamesHWade JamesHWade removed a link to an issue Aug 26, 2024
[FR]: Support vision features #222
Open
1 task
JamesHWade
JamesHWade commented Aug 27, 2024
View reviewed changes
Copy link
Collaborator Author

@JamesHWade JamesHWade left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

I've gone through these changes and will be ready to merge once I hear from you @calderonsamuel

NEWS.md
- Add audio input option for chat app. #224
- Fix bug with chat app not loading on linux. #224
- Allow chat app to run in Positron (not yet as background job) #224
- API calls now run async with ExtendedTask. #224
Copy link
Collaborator Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Update on this, ExtendedTask needs a promise to be returned. I've moved promises to Suggests, but it's not really another dependency because shiny already depends on the package.

@calderonsamuel
Copy link
Collaborator

Works ok in Positron's viewer

image

But not when moving to browser:

image

Or in Rstudio's viewer:

image

@JamesHWade
Copy link
Collaborator Author

JamesHWade commented Aug 28, 2024 •
edited
Loading

Hmm... can you try reinstalling the package see what's at that location? That should be the right spot that tools::R_user_dir("gptstudio") uses.

I think I fixed it.

@JamesHWade JamesHWade merged commit ea51010 into main Aug 31, 2024
8 checks passed
@JamesHWade JamesHWade deleted the audio-input branch September 2, 2024 19:28
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Reviewers

@calderonsamuel calderonsamuel calderonsamuel left review comments

Assignees
No one assigned
Labels
None yet
Projects
None yet
Milestone
No milestone
Development

Successfully merging this pull request may close these issues.

Viewer Connection Refused" when starting chat session from add in Add voice command integration with whisper
2 participants
@JamesHWade @calderonsamuel