Update the documentation of the semantic router deployment to use helm

[szedan-rh]

Update the documentation of the semantic router deployment to use helm

[gemini-code-assist]

Summary of Changes

Hello @szedan-rh, 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 refines the deployment documentation for the vLLM Semantic Router within a Kubernetes environment. The primary goal is to enhance the clarity and maintainability of the installation process by migrating from imperative kubectl apply commands to a more declarative and manageable Helm-based approach. This change simplifies the setup for users and ensures consistency with modern Kubernetes deployment practices.

Highlights

• Deployment Method Update: The documentation for deploying the vLLM Semantic Router in Kubernetes has been updated to use Helm charts instead of direct kubectl apply -k commands, streamlining the installation process.
• External Resource References: References to Kubernetes resource files (like base-model.yaml and gwapi-resources.yaml) have been updated to point directly to raw GitHub URLs, ensuring users always fetch the latest versions.
• Improved Cleanup Instructions: A new 'Cleanup' section has been added to the tutorial, providing clear helm uninstall commands to easily remove all deployed components, including the semantic router, AI gateway, and Envoy gateway.

🧠 New Feature in Public Preview: You can now enable Memory to help Gemini Code Assist learn from your team's feedback. This makes future code reviews more consistent and personalized to your project's style. Click here to enable Memory in your admin console.

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

This pull request updates the documentation for semantic router deployment to use Helm instead of kubectl. The changes are well-structured and improve the clarity of the guides, including adding a helpful cleanup section. My review focuses on enhancing the reproducibility of the instructions by suggesting the use of specific version tags and commit-pinned URLs instead of floating tags like -latest and references to the main branch. This will ensure a more stable and predictable experience for users following the documentation.

[gemini-code-assist]

Using a floating version tag like v0.0.0-latest can cause unexpected issues for users if the chart it points to is updated with breaking changes. For better reproducibility, it is recommended to use a specific, immutable version (e.g., v0.1.0). This ensures that everyone following the guide gets the same setup. This suggestion also applies to the other Helm commands in this document.

[gemini-code-assist]

Using a URL that points to the main branch for the values file can lead to inconsistencies for users if the file is updated with breaking changes. To ensure the documentation remains accurate and reproducible, it's better to link to a file from a specific Git tag or commit hash. This applies to all raw GitHub content URLs in this file.

For example:
.../semantic-router/@<tag-or-commit>/...

[gemini-code-assist]

Using a floating version tag like v0.0.0-latest can cause unexpected issues for users if the chart it points to is updated with breaking changes. For better reproducibility, it is recommended to use a specific, immutable version (e.g., v0.1.0). This ensures that everyone following the guide gets the same setup. This suggestion also applies to the other Helm commands in this document.

[gemini-code-assist]

Using a URL that points to the main branch for the values file can lead to inconsistencies for users if the file is updated with breaking changes. To ensure the documentation remains accurate and reproducible, it's better to link to a file from a specific Git tag or commit hash. This applies to all raw GitHub content URLs in this file.

For example:
.../semantic-router/@<tag-or-commit>/...

[zerofishnoodles]

LGTM! Thanks for the contribution!