Add media description feature using Azure Content Understanding

[pamelafox]

Purpose

This PR adds a new optional feature that will extract figures in documents (using Azure Document Intelligence) figures output mode and send those figures to Azure Content Understanding (a new service that uses multimodal models) to generate a figure description. It will then insert that figure description into the content, which will then get sent for chunking. If the figure is of a graph or chart, it will include an HTML table with the data.
This gives developers a more lightweight approach to ingest media-rich documents and can be compared to the more heavyweight GPT-4-vision approach.

Does this introduce a breaking change?

When developers merge from main and run the server, azd up, or azd deploy, will this produce an error?
If you're not sure, try it out on an old environment.

[ ] Yes
[X] No

Does this require changes to learn.microsoft.com docs?

This repository is referenced by this tutorial
which includes deployment, settings and usage instructions. If text or screenshot need to change in the tutorial,
check the box below and notify the tutorial author. A Microsoft employee can do this for you if you're an external contributor.

[ ] Yes
[X] No

Type of change

[ ] Bugfix
[X] Feature
[ ] Code style update (formatting, local variables)
[ ] Refactoring (no functional changes, no api changes)
[ ] Documentation content changes
[ ] Other... Please describe:

Code quality checklist

See CONTRIBUTING.md for more details.

• The current tests all pass (python -m pytest).
• I added tests that prove my fix is effective or that my feature works
• I ran python -m pytest --cov to verify 100% coverage of added lines
• I ran python -m mypy to check for type errors
• I either used the pre-commit hooks or ran ruff and black manually on my code.

[github-actions]

Check Broken Paths

We have automatically detected the following broken relative paths in your files.
Review and fix the paths to resolve this issue.

Check the file paths and associated broken paths inside them. For more details, check our Contributing Guide.

File Full Path	Issues
CONTRIBUTING.md	# Link Line Number 1 ./main.parameters.json 169 2 ./main.bicep 170

[github-actions]

Check Country Locale in URLs

We have automatically detected added country locale to URLs in your files.
Review and remove country-specific locale from URLs to resolve this issue.

Check the file paths and associated URLs inside them. For more details, check our Contributing Guide.

File Full Path	Issues
README.md	# Link Line Number 1 https://azure.microsoft.com/en-us/pricing/details/cognitive-services/computer-vision/ 96

[pamelafox]

I need to do some cleanup, per the CI. This also needs a few more tests, as it currently only has a test for the changes to the splitting algorithm.

[mattgotteiner]

should we pull this into the data directory? or not check this in at all?

[github-actions]

Check Broken Paths

We have automatically detected the following broken relative paths in your files.
Review and fix the paths to resolve this issue.

Check the file paths and associated broken paths inside them. For more details, check our Contributing Guide.

File Full Path	Issues
CONTRIBUTING.md	# Link Line Number 1 ./main.parameters.json 169 2 ./main.bicep 170

[github-actions]

Check Country Locale in URLs

We have automatically detected added country locale to URLs in your files.
Review and remove country-specific locale from URLs to resolve this issue.

Check the file paths and associated URLs inside them. For more details, check our Contributing Guide.

File Full Path	Issues
README.md	# Link Line Number 1 https://azure.microsoft.com/en-us/pricing/details/cognitive-services/computer-vision/ 96

[pamelafox]

I have now completed both unit testing and manual testing, and this is good to merge. We will merge/release on Monday.