Movatterモバイル変換

[0]ホーム
URL:

Skip to content

Navigation Menu

Sign in
Appearance settings

Search code, repositories, users, issues, pull requests...

Provide feedback

We read every piece of feedback, and take your input very seriously.

Saved searches

Use saved searches to filter your results more quickly

 Sign up
Appearance settings

feat(genai): add live samples (2)#10208

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 ourterms of service andprivacy statement. We’ll occasionally send you account related emails.

Already on GitHub?Sign in to your account

Open
jdomingr wants to merge5 commits intoGoogleCloudPlatform:main
base:main
Choose a base branch
Loading
fromjdomingr:genai-sdk-live-samples-2

Conversation

@jdomingr
Copy link
Contributor

Description

Add new live samples

  • Live audio response with text input
  • Live Conversation audio with audio
  • Live function calling with text input
  • Live grounding with text input
  • Live structured output using the OpenAI client
  • Live text response with audio input.

Checklist

  • I have followedSample Format Guide
  • Tests pass:mvn clean verifyrequired
  • Lint passes:mvn -P lint checkstyle:checkrequired
  • Static Analysis:mvn -P lint clean compile pmd:cpd-check spotbugs:checkadvisory only
  • Pleasemerge this PR for me once it is approved

@snippet-bot
Copy link

snippet-botbot commentedDec 10, 2025•
edited
Loading

Here is the summary of changes.

You are about to add 6 region tags.

This comment is generated bysnippet-bot.
If you find problems with this result, please file an issue at:
https://github.com/googleapis/repo-automation-bots/issues.
To update this comment, addsnippet-bot:force-run label or use the checkbox below:

  • Refresh this comment

@product-auto-labelproduct-auto-labelbot added the samplesIssues that are directly related to samples. labelDec 10, 2025
@gemini-code-assist
Copy link
Contributor

Summary of Changes

Hello@jdomingr, 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 significantly expands the Generative AI SDK's live samples, providing developers with practical examples for integrating advanced AI capabilities. The new samples cover a range of interactive scenarios, from real-time audio conversations and text-to-speech generation to complex function calling, grounding with RAG engines, and structured data extraction. These additions aim to enhance understanding and ease of use for various live AI applications.

Highlights

  • New Live Samples Added: Introduced six new live samples demonstrating various functionalities of the Generative AI SDK.
  • Audio Interaction: Added samples for live audio response from text input, and live conversation with audio input and audio output.
  • Function Calling: Included a new sample showcasing live function calling with text input.
  • Grounding with RAG Engine: Provided a sample demonstrating live grounding using Vertex AI RAG Engine with text input.
  • Structured Output: Added a sample for live structured output using the OpenAI client.
  • Text Response from Audio: Implemented a sample to get live text responses from audio input.
Using Gemini Code Assist

The full guide for Gemini Code Assist can be found on ourdocumentation page, here are some quick tips.

Invoking Gemini

You can request assistance from Gemini at any point by creating a comment using either/gemini <command> or@gemini-code-assist <command>. Below is a summary of the supported commands on the current page.

FeatureCommandDescription
Code Review/gemini reviewPerforms a code review for the current pull request in its current state.
Pull Request Summary/gemini summaryProvides a summary of the current pull request in its current state.
Comment@gemini-code-assistResponds in comments when explicitly tagged, both in pull request comments and review comments.
Help/gemini helpDisplays 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 foundhere.

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 uphere.

You can also get AI-powered code generation, chat, as well as code reviews directly in the IDE at no cost with theGemini Code Assist IDE Extension.

Footnotes

  1. Review thePrivacy Notices,Generative AI Prohibited Use Policy,Terms of Service, and learn how to configure Gemini Code Assist in GitHubhere. Gemini can make mistakes, so double check it anduse code with caution.↩

Copy link
Contributor

@gemini-code-assistgemini-code-assistbot left a 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 introduces several new live samples for the GenAI SDK, covering audio responses, conversation, function calling, grounding, structured output, and text responses from audio. The changes include adding a new dependency for OpenAI client and new Java files for each sample. Overall, the new samples demonstrate various capabilities of the Live API effectively. However, there are several instances of hardcoded values and placeholders that should be made configurable for better reusability and clarity.

Copy link

@GuinersGuiners left a comment

Choose a reason for hiding this comment

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

LGTM

@msampathkumarmsampathkumar added the kokoro:runAdd this label to force Kokoro to re-run the tests. labelDec 15, 2025
@kokoro-teamkokoro-team removed the kokoro:runAdd this label to force Kokoro to re-run the tests. labelDec 15, 2025
@iennae
Copy link
Contributor

@msampathkumar do y'all have a storage bucket where you can host the wav resource file that is needed for this sample? It shouldn't really be in the repo itself.


publicstaticvoidmain(String[]args) {
// TODO(developer): Replace these variables before running the sample
StringmodelId ="gemini-2.0-flash-live-preview-04-09";
Copy link
Contributor

Choose a reason for hiding this comment

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

Same as before, should work with Text

Suggested change
StringmodelId ="gemini-2.0-flash-live-preview-04-09";
StringmodelId ="gemini-live-2.5-flash-native-audio";

Copy link
ContributorAuthor

Choose a reason for hiding this comment

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

Here, I can't use gemini-live-2.5-flash-native-audio because the sample generates text output, and when I use the suggested model, I get the following exception: "Text output is not supported for native audio output model".


publicstaticvoidmain(String[]args) {
// TODO(developer): Replace these variables before running the sample
StringmodelId ="gemini-2.0-flash-live-preview-04-09";
Copy link
Contributor

Choose a reason for hiding this comment

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

Same as before

Suggested change
StringmodelId ="gemini-2.0-flash-live-preview-04-09";
StringmodelId ="gemini-live-2.5-flash-native-audio";

Copy link
ContributorAuthor

Choose a reason for hiding this comment

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

I have the same problem here with the text output.


publicstaticvoidmain(String[]args)throwsIOException {
// TODO(developer): Replace these variables before running the sample.
StringmodelId ="gemini-2.0-flash-live-preview-04-09";
Copy link
Contributor

Choose a reason for hiding this comment

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

Suggested change
StringmodelId ="gemini-2.0-flash-live-preview-04-09";
StringmodelId ="gemini-live-2.5-flash-native-audio";

Copy link
ContributorAuthor

Choose a reason for hiding this comment

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

I have the same problem here with the text output.


@Test
publicvoidtestLiveAudioWithTxt() {
LiveAudioWithTxt.generateContent(GEMINI_FLASH_LIVE_PREVIEW);
Copy link
Contributor

Choose a reason for hiding this comment

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

Be sure to update all of these tests to run with the GA Model

Copy link
ContributorAuthor

Choose a reason for hiding this comment

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

Done, the only exception is those samples that still use gemini-2.0-flash-live-preview-04-09 because they generate text output

…versation sample and update gemini model in other samples
Sign up for freeto join this conversation on GitHub. Already have an account?Sign in to comment

Reviewers

@holtskinnerholtskinnerholtskinner requested changes

@yoshi-approveryoshi-approverAwaiting requested review from yoshi-approveryoshi-approver is a code owner

+2 more reviewers

@gemini-code-assistgemini-code-assist[bot]gemini-code-assist[bot] left review comments

@GuinersGuinersGuiners approved these changes

Reviewers whose approvals may not affect merge requirements

Requested changes must be addressed to merge this pull request.

Assignees

@jdomingrjdomingr

Labels

samplesIssues that are directly related to samples.

Projects

None yet

Milestone

No milestone

Development

Successfully merging this pull request may close these issues.

6 participants

@jdomingr@iennae@holtskinner@Guiners@msampathkumar@kokoro-team
[8]ページ先頭
©2009-2025 Movatter.jp