-
Notifications
You must be signed in to change notification settings - Fork 3.7k
Add Live to Firebase AI sample app #903
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
base: master
Are you sure you want to change the base?
Conversation
Add a new entry in the right sidebar that allows users to use the Live Audio Conversation (`startAudioConversation()`) API.
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.
Summary of Changes
Hello @dlarocque, I'm Gemini Code Assist1! I'm currently reviewing this pull request and will post my feedback shortly. In the meantime, here's a summary to help you and other reviewers quickly get up to speed!
This pull request introduces a new 'Live Audio Conversation' feature to the Firebase AI sample application. It allows users to engage in real-time voice interactions with an AI model by adding a dedicated UI mode, integrating the startAudioConversation()
API, and providing a new view component to manage the live conversation experience.
Highlights
- New 'Live' Application Mode: A new 'live' mode has been introduced into the application's core AppMode type, enabling the integration of real-time audio conversation features.
- UI Integration: The user interface now includes a dedicated 'Live Conversation' option in the left sidebar, allowing users to easily access the new feature.
- Dedicated Live Conversation View: A new
LiveView
component has been added, which handles the logic and rendering for real-time audio conversations, including starting/stopping conversations and displaying status. - Backend Model Configuration for Live Audio: The application now configures specific AI models for live conversations based on the chosen backend type (Google AI or Vertex AI), ensuring compatibility and optimal performance.
Using Gemini Code Assist
The full guide for Gemini Code Assist can be found on our documentation page, here are some quick tips.
Invoking Gemini
You can request assistance from Gemini at any point in your pull request via creating an issue comment (i.e. comment on the pull request page) using either /gemini <command>
or @gemini-code-assist <command>
. Below is a summary of the supported commands.
Feature | Command | Description |
---|---|---|
Code Review | /gemini review |
Performs a code review for the current pull request in its current state. |
Pull Request Summary | /gemini summary |
Provides a summary of the current pull request in its current state. |
Comment | @gemini-code-assist | Responds in comments when explicitly tagged, both in issue comments and review comments. |
Help | /gemini help |
Displays a list of available commands. |
Customization
To customize Gemini Code Assist for GitHub experience, repository maintainers can create a configuration file and/or provide a custom code review style guide (such as PEP-8 for Python) by creating and adding files to a .gemini/
folder in the base of the repository. Detailed instructions can be found here.
Limitations & Feedback
Gemini Code Assist may make mistakes. Please leave feedback on any instances where its feedback is incorrect or counter productive. You can react with 👍 and 👎 on @gemini-code-assist comments. If you're interested in giving your feedback about your experience with Gemini Code Assist for Github and other Google products, sign up here.
You can also get AI-powered code generation, chat, as well as code reviews directly in the IDE at no cost with the Gemini Code Assist IDE Extension.
Footnotes
-
Review the Privacy Notices, Generative AI Prohibited Use Policy, Terms of Service, and learn how to configure Gemini Code Assist in GitHub here. Gemini can make mistakes, so double check it and use code with caution. ↩
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.
Code Review
This pull request successfully adds a new 'Live Conversation' feature to the application, introducing a LiveView
component that utilizes the startAudioConversation
API. The changes are well-structured, including updates to routing, state management, and UI components. My review focuses on improving robustness, state management, and code consistency. I've identified a potential runtime crash due to an unsafe type assertion, a state management issue that affects user experience, an instance of an unused prop, and an inconsistent hardcoded value in the CSS. Addressing these points will make the new feature more reliable and maintainable.
Add a new entry in the right sidebar that allows users to use the Live Audio Conversation (
startAudioConversation()
) API.