feat: Simplify grounding intro to focus on grounding with Google search only #1905
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 @diemtvu, 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 simplifies the grounding introduction notebook to focus solely on grounding with Google Search. It removes the sections related to Vertex AI Search data stores, streamlining the tutorial and making it easier to follow. The changes include removing references to Vertex AI Search, updating the steps performed, and modifying the code to reflect the focus on Google Search grounding.
Highlights
- Simplification: The notebook is simplified to focus only on grounding with Google Search, removing the complexity of Vertex AI Search data stores.
- Updated Steps: The tutorial steps are updated to reflect the focus on Google Search, removing steps related to setting up a data store in Vertex AI Search.
- API Updates: The notebook now only requires the Vertex AI API to be enabled, removing the need for the Vertex AI Agent Builder API.
- Code Modification: Code related to Vertex AI Search has been removed, including the
VertexAISearchtool and related functions.
Changelog
- gemini/grounding/intro-grounding-gemini.ipynb
- Removed references to Vertex AI Search as a grounding source.
- Updated the introduction to focus on Google Search grounding.
- Removed steps related to creating and using a data store in Vertex AI Search.
- Removed the need to enable the Vertex AI Agent Builder API.
- Removed code related to the
VertexAISearchtool and data store grounding. - Added a note about using
GoogleSearchRetrievalfor models before Gemini 2.0. - Removed citation metadata printing.
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 the realm of AI, where knowledge we seek,
Grounding our models, so they truly speak.
With Google Search, we anchor their words,
Simplifying the path, like songs of the birds.
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.
Code Review
The pull request simplifies the grounding introduction notebook by focusing solely on grounding with Google Search. This change streamlines the tutorial and makes it easier for users to understand the basics of grounding. The removal of the Vertex AI Search grounding examples makes the notebook more focused. Overall, the changes are well-executed and improve the clarity of the notebook.
Merge Readiness
The pull request effectively simplifies the grounding introduction notebook by focusing on Google Search grounding. The changes enhance the notebook's clarity and focus, making it easier for users to grasp the core concepts. Given the absence of critical or high severity issues, the pull request is nearly ready for merging. However, it's advisable to address the medium severity issue to further enhance the notebook's quality. I am unable to directly approve this pull request, and recommend that others review and approve this code before merging.
holtskinner
changed the title
| "source": [ | ||
| "> Note: For model before Gemini 2.0, please use the `GoogleSearchRetrieval` tool instead)\n", | ||
| "\n", | ||
| "```\n", | ||
| "response = client.models.generate_content(\n", | ||
| " model=MODEL_ID,\n", | ||
| " contents=PROMPT,\n", | ||
| " config=GenerateContentConfig(tools=[GoogleSearchRetrieval()]),\n", | ||
| ")\n", | ||
| "\n", | ||
| "```" | ||
| ] |
There was a problem hiding this comment.
We're trying to remove all references to previous models across our content, so can you remove this section?
Description
Thank you for opening a Pull Request!
Before submitting your PR, there are a few things you can do to make sure it goes smoothly:
CONTRIBUTINGGuide.CODEOWNERSfor the file(s).nox -s formatfrom the repository root to format).Fixes #<issue_number_goes_here> 🦕