[Vertex AI] Update DocC links to Firebase docsite where available #14555
Conversation
![gemini-code-assist[bot]](https://avatars.githubusercontent.com/in/956858?s=60&v=4){kind=small}
There was a problem hiding this comment.
Hello @andrewheard, 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!
Summary of Changes
This pull request updates the DocC links in the Vertex AI in Firebase SDK to point to the Firebase documentation site where available, instead of the Google Cloud documentation. This change affects several files, including CHANGELOG.md, CountTokensRequest.swift, FunctionCalling.swift, GenerationConfig.swift, Safety.swift, ImagenGenerationConfig.swift, ImagenModel.swift, Part.swift, and VertexAI.swift. The primary goal is to ensure that developers using the Firebase SDK are directed to the most relevant and up-to-date documentation on the Firebase site.
Highlights
- Documentation Links: Updated documentation links to refer to the Firebase documentation site instead of Google Cloud for resources related to Vertex AI in Firebase SDK.
- Function Calling: Modified the link for function calling documentation to point to the Firebase-specific page.
- Generation Configuration: Updated links related to
temperature,topP,topK, and structured output inGenerationConfigto the Firebase documentation. - Safety Settings: Added a link to the Firebase documentation for safety settings in the
SafetySettingstruct. - Imagen Configuration: Added a link to the Firebase documentation for parameters related to Imagen models.
- Imagen Model: Updated the documentation link for image generation capabilities offered by the Imagen model to the Firebase documentation.
- File Data Part: Updated the documentation link for supported input files and requirements for
FileDataPartto the Firebase documentation. - VertexAI Model Versions: Updated the documentation link for model versions to the Firebase documentation.
Changelog
Click here to see the changelog
- FirebaseVertexAI/CHANGELOG.md
- Updated the link for controlling generated output to the Firebase documentation site.
- FirebaseVertexAI/Sources/CountTokensRequest.swift
- Updated the link for Vertex AI pricing to the Firebase documentation site.
- FirebaseVertexAI/Sources/FunctionCalling.swift
- Updated the link for function calling details and use cases to the Firebase documentation site.
- FirebaseVertexAI/Sources/GenerationConfig.swift
- Updated the links for temperature, topP, topK, and structured output to the Firebase documentation site.
- Replaced the Cloud documentation link with the Firebase documentation link for
temperatureparameter details (line 69). - Replaced the Cloud documentation link with the Firebase documentation link for
topPparameter details (line 77). - Replaced the Cloud documentation link with the Firebase documentation link for
topKparameter details (line 87). - Replaced the Cloud documentation link with the Firebase documentation link for structured output details (line 140).
- FirebaseVertexAI/Sources/Safety.swift
- Added a link to the Firebase documentation for safety settings for Gemini models.
- FirebaseVertexAI/Sources/Types/Public/Imagen/ImagenGenerationConfig.swift
- Added a link to the Firebase documentation for parameters available for use with Imagen models.
- FirebaseVertexAI/Sources/Types/Public/Imagen/ImagenModel.swift
- Updated the link for image generation capabilities to the Firebase documentation site.
- FirebaseVertexAI/Sources/Types/Public/Part.swift
- Updated the link for supported input files and requirements to the Firebase documentation site.
- FirebaseVertexAI/Sources/VertexAI.swift
- Updated the link for model versions to the Firebase documentation site.
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 is currently in preview and 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 to provide feedback.
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.
In realms of code, where links reside,
A quest to Firebase, our helpful guide.
From Cloud's domain, we gently steer,
To docs more fitting, crystal clear.
For Vertex's might, in Firebase's grace,
A developer's smile, upon their face.
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. ↩
|
Warning Gemini encountered an error creating the review. You can try again by commenting |
Updated DocC links in the Vertex AI in Firebase SDK to refer to resources on the Firebase documentation site (
https://firebase.google.com/docs/vertex-ai), instead of Google Cloud, where equivalent pages are available.