26.07 release notes preview & notebook refresh

[validbeck]

Pull Request Description

What and why?

Live preview for the https://github.com/validmind/release-notes/pull/90.

How to test

What needs special review?

Dependencies, breaking changes, and deployment notes

REMOVE THE REF TO THE WORKING release-notes BRANCH BEFORE MERGE!!

Release notes

Checklist

• What and why
• Screenshots or videos (Frontend)
• How to test
• What needs special review
• Dependencies, breaking changes, and deployment notes
• Labels applied
• PR linked to Shortcut
• Unit tests added (Backend)
• Tested locally
• Documentation updated (if required)
• Environment variable additions/changes documented (if required)

[github-actions]

Lighthouse check results

✓ INFO: No site pages to audit in this PR.

Commit SHA: 20753d5

[github-actions]

Lighthouse check results

✓ INFO: No site pages to audit in this PR.

Commit SHA: 20753d5

[github-actions]

Lighthouse check results

✓ INFO: No site pages to audit in this PR.

Commit SHA: a585962

[github-actions]

PR Summary

This pull request makes two primary updates:

1. In the template file (_template-schema-generated.qmd), the generated-by footer timestamp is updated. This change solely reflects a new generation date and time, ensuring that the documentation displays current metadata.

2. The notebook for configuring judge LLMs (configure_judge_llms.ipynb) has undergone extensive revisions. Major changes include:

   • A restructuring of the notebook’s cells and markdown content for improved clarity and flow.
   • Updated instructions for configuring and testing judge LLM and judge embeddings. Additional details now cover the use of the set_judge_config() function to explicitly set the judge models across evaluation paths.
   • Enhanced descriptions and updated code samples regarding how to initialize the ValidMind model and dataset objects for prompt-validation tests, RAGAS tests, and DeepEval scorers.
   • Expanded documentation sections, such as the introduction, key concepts, and next steps, to provide users with a clearer roadmap and troubleshooting guidelines.

These changes are intended to improve user guidance and ensure consistency in how judge configurations are set and tested within the notebook environment.

Test Suggestions

• Run the updated notebook in a clean environment to verify that all cells execute without errors.
• Validate that the generated-by footer in the HTML output shows the correct updated timestamp.
• Test the judge configuration functionality by simulating different environment variable setups (e.g. using OpenAI, Gemini, or Azure credentials) and confirming that the expected provider is resolved.
• Ensure the prompt-validation, RAGAS, and DeepEval test cells log the expected outputs.

[github-actions]

Validate docs site

✓ INFO: A live preview of the docs site is available — Open the preview