Change sample to use Gemini Embedding model #13368
Conversation
There was a problem hiding this comment.
Hello @skarukas, 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 modifies the embeddings_docretrieval_with_txt.py sample to use the gemini-embedding-001 model instead of text-embedding-005. It also updates the output_dimensionality parameter in the EmbedContentConfig from 768 to 3072, and modifies the contents parameter to take a single string instead of a list of strings. This change is related to fixing issue b/417800265.
Highlights
- Model Update: The sample now uses the
gemini-embedding-001model for embeddings. - Dimensionality Change: The
output_dimensionalityis updated to 3072 to align with the new model. - Content Type: The
contentsparameter now accepts a single string instead of a list of strings.
Changelog
- genai/embeddings/embeddings_docretrieval_with_txt.py
- Updated the model from
text-embedding-005togemini-embedding-001on line 23. - Changed the
contentsparameter to accept a single string on line 24. - Updated the
output_dimensionalityto 3072 on line 27.
- Updated the model from
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.
From text to Gemini's grace,
Embeddings find a new space.
Dimensions expand,
A single command,
Knowledge blooms at a faster pace.
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 updates the sample code to use the Gemini Embedding model instead of the 'text-embedding-005' model. This involves changing the model name and the output dimensionality. The change seems straightforward and necessary for utilizing the new Gemini Embedding model.
Summary of Findings
- Model Name Verification: Ensure that 'gemini-embedding-001' is the correct and available model name.
- Contents Parameter Type: Verify that the
embed_contentmethod accepts a single string as input for the 'gemini-embedding-001' model. - Output Dimensionality: Confirm that 3072 is the correct output dimensionality for the 'gemini-embedding-001' model and add a comment explaining the change.
Merge Readiness
The pull request updates the sample code to use the Gemini Embedding model. While the changes seem straightforward, it's crucial to verify the model name, input parameter type, and output dimensionality to ensure the code functions correctly with the new model. I recommend addressing the review comments before merging. I am unable to approve this pull request, and other reviewers should review and approve this code before merging.
Description
Fixes b/417800265
Note: Before submitting a pull request, please open an issue for discussion if you are not associated with Google.
Checklist
nox -s py-3.9(see Test Environment Setup)nox -s lint(see Test Environment Setup)