docs(core): clarify supported formats for multimodal inputs in ModelProfile

[ling (qinqining)]

Description:
This PR resolves several # TODO comments in libs/core/langchain_core/language_models/model_profile.py regarding multimodal input formats.

It explicitly documents that image, pdf, audio, and video inputs typically accept base64-encoded strings or raw bytes. This minor documentation update helps clarify the expected input types for developers working with multimodal agents.

Issue: N/A (Minor documentation cleanup)

[codspeed-hq]

Merging this PR will not alter performance

⚠️ Unknown Walltime execution environment detected

Using the Walltime instrument on standard Hosted Runners will lead to inconsistent data.

For the most accurate results, we recommend using CodSpeed Macro Runners: bare-metal machines fine-tuned for performance measurement consistency.

✅ 13 untouched benchmarks
⏩ 27 skipped benchmarks¹

---

_{Comparing qinqining:docs/update-modelprofile-formats (b0b6291) with master (063739b)²}

Footnotes

1. 27 benchmarks were skipped, so the baseline results were used instead. If they were deleted from the codebase, click here and archive them to remove them from the performance reports. ↩

2. No successful run was found on master (491eb9d) during the generation of this report, so 063739b was used instead as the comparison base. There might be some changes unrelated to this pull request in this report. ↩

[github-actions]

This PR is missing a linked issue. All external contributions must reference an approved issue or discussion.

Please add one of the following to your PR description:

• Fixes #<issue_number>
• Closes #<issue_number>
• Resolves #<issue_number>

If no issue exists yet, open one and wait for maintainer approval before proceeding.