Add multi-modal example

[bellkev]

Description

This adds a new example for using multi-modal tools, specifically generate_image and image_reader, as there aren't any examples for these yet.

Type of Change

• New content addition

• Content update/revision

• Structure/organization improvement

• Typo/formatting fix

• Bug fix

• Other (please describe):

• New content addition

Motivation and Context

While Strands handles image input/output well, and provides default tools for e.g. image generation and reading, there are no examples yet for this functionality in the docs.

Areas Affected

Screenshots

Checklist

• I have read the CONTRIBUTING document
• My changes follow the project's documentation style
• I have tested the documentation locally using mkdocs serve
• Links in the documentation are valid and working
• Images/diagrams are properly sized and formatted
• All new and existing tests pass

Additional Notes

By submitting this pull request, I confirm that you can use, modify, copy, and redistribute this contribution, under the terms of your choice.

[bellkev]

Note that this example requires strands-agents/tools#89 currently but otherwise works with the release version.

[zastrowm]

Sorry for the delay, looks pretty good. Would you be able to confirm that it still works with the latest SDK + tools? If so, I think we're good to merge

[bellkev]

I confirmed the example works as-is now with the release versions:

strands-agents==0.3.0
strands-agents-tools==0.1.9

And I moved the images as suggested.