Rerank models can be started/updated from Trained Models page

[nastasha-solomon]

Summary

Fixes #6496 by documenting that rerank models can be started and updated from the Trained Models page

Summary

Documents that rerank models can be started and updated from the Trained Models page in Stack 9.5+ and Serverless, and that the Optimize for use case options (Ingest, Search, Balanced) do not apply to rerank models.

Previews:

• Elastic Rerank: The "Download and deploy" section now covers both the inference API and the Trained Models page. A new subsection (9.5+) walks through Start deployment and Update deployment from the Actions menu, notes that rerank models do not show the optimization selector, and uses main-menu / global-search navigation so the steps work for serverless projects as well as stack deployments.
• Trained models: A new "Model management actions section" summarizes which actions apply to each model type (data frame analytics, NLP, rerank). A rerank subsection describes Start deployment and Update deployment actions and clarifies that the optimization selector is not shown for rerank models.
• Deploy the model in your cluster: Added a note explaining that optimization options apply only to embedding models, that rerank models support Start deployment and Update deployment actions from the Trained Models page, and links to the Elastic Rerank API steps.

Generative AI disclosure

1. Did you use a generative AI (GenAI) tool to assist in creating this contribution?

• Yes - Cursor auto mode
• No

[github-actions]

Elastic Docs AI PR menu

Check the box to run an AI review for this pull request.

• Review docs changes (docs-review). Status: not started.

Powered by GitHub Agentic Workflows and docs-actions. For more information, reach out to the docs team.

[github-actions]

🔍 Preview links for changed docs

• explore-analyze/machine-learning/data-frame-analytics/ml-trained-models.md
• explore-analyze/machine-learning/nlp/ml-nlp-deploy-model.md
• explore-analyze/machine-learning/nlp/ml-nlp-rerank.md

[github-actions]

✅ Vale Linting Results

No issues found on modified lines!

---

The Vale linter checks documentation changes against the Elastic Docs style guide.

To use Vale locally or report issues, refer to Elastic style guide for Vale.