-
Notifications
You must be signed in to change notification settings - Fork 2.5k
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
fix: Improvements to Gradio MM Live API Sample App #1622
Conversation
- Add System instruction - Remove unsupported regions - Maintenance/style improvements
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Hi team,
I'm currently reviewing this pull request and will provide feedback shortly. In the meantime, here's a summary for you and other reviewers to quickly get up to speed:
This pull request, "fix: Improvements to Gradio MM Live API Sample App", aims to improve the Gradio-based sample application for the Gemini multimodal live API. The changes include:
- Added System Instruction: A new textbox allows users to specify a system instruction, enhancing the conversational context and control over Gemini's responses (app.py lines 57-62, 140-146, 161).
- Removed Unsupported Regions: The application now only supports the
us-central1
region, simplifying the user experience and avoiding errors related to unsupported locations (app.py lines 124-128). - Maintenance and Style Improvements: Minor code cleanup and style adjustments were made to improve readability and maintainability (various files).
- Removed Extra Encoding/Decoding: The unnecessary base64 encoding/decoding of audio data has been removed, streamlining the audio processing pipeline (app.py lines 1-12, 84-90).
- Updated Header: The header was updated to reflect the changes and improve clarity (header.html lines 1-12).
The core changes involve modifying app.py
to incorporate system instructions, remove unsupported regions from the dropdown, and simplify audio handling. The header.html
file also received updates for better clarity.
I'll provide a more detailed review shortly.
And now for a little haiku to lighten the mood:
Code flows like a stream,
Fixes merge, a smoother flow,
Progress lights the way.
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
This pull request introduces several improvements to the Gradio multimodal live API sample app, enhancing its functionality and usability. The changes are well-structured and generally improve the code. A few minor suggestions are included below.
Description