Add backend compatibility table to documentation

[MalyalaKarthik66]

Added a table showing compatible JAX, TensorFlow, and PyTorch versions for Keras as requested in Issue #21730.
This improves clarity for users on which backend versions are supported, helping prevent version conflicts and making it easier to start with Keras.

[google-cla]

Thanks for your pull request! It looks like this may be your first contribution to a Google open source project. Before we can look at your pull request, you'll need to sign a Contributor License Agreement (CLA).

View this failed invocation of the CLA check for more information.

For the most up to date status, view the checks section at the bottom of the pull request.

[gemini-code-assist]

Summary of Changes

Hello @MalyalaKarthik66, 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 enhances the project's documentation by introducing a comprehensive backend compatibility table within the README.md. The new section aims to provide users with clear guidance on the minimum supported versions of JAX, TensorFlow, and PyTorch for Keras v3.x, thereby preventing potential version conflicts and streamlining the initial setup process for developers.

Highlights

• New Documentation Section: A new section titled 'Backend Compatibility Table' has been added to the README.md file.
• Backend Version Compatibility: The added table clearly lists the minimum supported versions for TensorFlow (2.16.1), JAX (0.4.20), and PyTorch (2.1.0) when used with the latest stable release of Keras (v3.x).
• Detailed Compatibility Notes: Specific compatibility notes, such as jax==0.4.20 & keras==3.0, are provided for each backend to guide users.

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 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.

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 pull request 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

1. 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. ↩

[gemini-code-assist]

Code Review

Thank you for adding the backend compatibility table to the documentation. This is a valuable addition for users. I've provided a couple of suggestions to improve clarity and prevent potential confusion for developers working with the source code, mainly regarding the discrepancy between the versions listed and those in the requirements.txt files, and the format of the 'Detailed Compatibility' section.

[gemini-code-assist]

The backend versions in the table are quite different from those in the requirements.txt files, which could confuse developers setting up a local environment. To clarify this, I suggest expanding this note to mention that the requirements.txt files should be used for development environments.

Suggested change

	> **Note:** These versions are verified to be compatible with the latest stable release of Keras 3, according to the official documentation.
	> **Note:** These versions are verified to be compatible with the latest stable release of Keras 3, according to the official documentation. For setting up a development environment, please refer to the versions specified in the `requirements.txt` files.

[hertschuh]

I would remove this line altogether.

[gemini-code-assist]

This "Detailed Compatibility" section is redundant with the table above and uses a confusing format. The & symbol in jax==0.4.20 & keras==3.0 is not standard for specifying package versions and might be misinterpreted as a shell operator.

I recommend removing this section to improve clarity and reduce redundancy. The table and the note on line 69 provide sufficient information.

[hertschuh]

Agreed, the table provides the same information, please remove

[codecov-commenter]

Codecov Report

✅ All modified and coverable lines are covered by tests.
✅ Project coverage is 82.63%. Comparing base (2d4dce3) to head (bf3fcd2).
⚠️ Report is 439 commits behind head on master.

Additional details and impacted files

@@            Coverage Diff             @@
##           master   #21733      +/-   ##
==========================================
+ Coverage   82.55%   82.63%   +0.08%     
==========================================
  Files         571      577       +6     
  Lines       57628    59415    +1787     
  Branches     9002     9313     +311     
==========================================
+ Hits        47572    49097    +1525     
- Misses       7760     7913     +153     
- Partials     2296     2405     +109     

Flag	Coverage Δ
keras	82.45% <ø> (+0.10%)	⬆️
keras-jax	63.33% <ø> (-0.19%)	⬇️
keras-numpy	57.56% <ø> (-0.30%)	⬇️
keras-openvino	34.30% <ø> (-0.08%)	⬇️
keras-tensorflow	64.12% <ø> (-0.10%)	⬇️
keras-torch	63.63% <ø> (-0.11%)	⬇️

Flags with carried forward coverage won't be shown. Click here to find out more.

☔ View full report in Codecov by Sentry.
📢 Have feedback on the report? Share it here.

🚀 New features to boost your workflow:

• ❄️ Test Analytics: Detect flaky tests, report on failures, and find test suite problems.

[fchollet]

Thanks for the PR.

This information is going to get out of date really fast.

[hertschuh]

Thanks for the PR

[hertschuh]

I would remove this line altogether.

[hertschuh]

Agreed, the table provides the same information, please remove

[hertschuh]

Please also add | OpenVino | 2025.3.0 |

[MalyalaKarthik66]

Made the requested changes by removing the static note, deleting the detailed compatibility section, and adding OpenVINO to the table as suggested.

[hertschuh]

Thanks!