MINOR: Add language-specific prompt to kapa.ai bot

[thisisnic]

Rationale for this change

Asks users to specify language when using the kapa.ai bot

What changes are included in this PR?

Update user instructions

Are these changes tested?

Nah but I'll build the docs here to look

Are there any user-facing changes?

Yeah, the instructions

[github-actions]

Thanks for opening a pull request!

If this is not a minor PR. Could you open an issue for this pull request on GitHub? https://github.com/apache/arrow/issues/new/choose

Opening GitHub issues ahead of time contributes to the Openness of the Apache Arrow project.

Then could you also rename the pull request title in the following format?

GH-${GITHUB_ISSUE_ID}: [${COMPONENT}] ${SUMMARY}

or

MINOR: [${COMPONENT}] ${SUMMARY}

See also:

• Other pull requests
• Contribution Guidelines - Contributing Overview

[thisisnic]

@github-actions crossbow submit preview-docs

[github-actions]

Revision: 76b0b10

Submitted crossbow builds: ursacomputing/crossbow @ actions-000f62d346

Task	Status
preview-docs

[thisisnic]

@github-actions crossbow submit preview-docs

[github-actions]

Revision: 76b0b10

Submitted crossbow builds: ursacomputing/crossbow @ actions-4fc789648f

Task	Status
preview-docs

[amoeba]

LGTM.

[conbench-apache-arrow]

After merging your PR, Conbench analyzed the 4 benchmarking runs that have been run so far on merge-commit 66733a1.

There were 67 benchmark results with an error:

• Commit Run on amd64-m5-4xlarge-linux at 2025-06-05 17:34:34Z
  • tpch (R) with engine=arrow, format=parquet, language=R, memory_map=False, query_id=TPCH-04, scale_factor=10
  • tpch (R) with engine=arrow, format=native, language=R, memory_map=False, query_id=TPCH-12, scale_factor=1
• and 65 more (see the report linked below)

There were no benchmark performance regressions. 🎉

The full Conbench report has more details.