Add instructions for creating custom EIS inference endpoints

[charlotte-hoblik]

Updates inference-api.md to document how to create custom Elastic Inference Service (EIS) endpoints in the Kibana UI, including a list of supported Model IDs.

• Added a new section.
• Documented the UI flow: Service selection → Model ID → Task Type (under "Additional settings").
• Added a table of supported EIS models and their required configuration strings.

⚠️ Feedback Required
I have drafted a table of supported models but need confirmation on the exact strings before merging:

• Completeness: Are ELSER, Jina Embeddings, and Jina Rerankers the only supported custom EIS models?
• Accuracy: Please confirm the exact model_id strings and task_type mappings

Connected to: https://github.com/elastic/docs-content-internal/issues/542

[github-actions]

Vale Linting Results

Summary: 1 suggestion found

💡 Suggestions (1)

File	Line	Rule	Message
explore-analyze/elastic-inference/inference-api.md	71	Elastic.Wordiness	Consider using 'usually' instead of 'In most cases'.

---

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.

[github-actions]

🔍 Preview links for changed docs

• explore-analyze/elastic-inference/inference-api.md