feat: Layout + VLM model with layout prompt

[cau-git]

Establishes a pipeline targeting VLMs that:

• Produce DocTags
• Accept a prompt with injected layout (box locations) from a layout model

⚠️ Note: This is an experimental pipeline, hence it resides in the docling.experimental module path.

Checklist:

• Documentation has been updated, if necessary.
• Examples have been added, if necessary.
• Tests have been added, if necessary.

[mergify]

Merge Protections

Your pull request matches the following merge protections and will not be merged until they are valid.

🟢 Enforce conventional commit

Wonderful, this rule succeeded.

Make sure that we follow https://www.conventionalcommits.org/en/v1.0.0/

• title ~= ^(fix|feat|docs|style|refactor|perf|test|build|ci|chore|revert)(?:\(.+\))?(!)?:

[github-actions]

✅ DCO Check Passed

Thanks @cau-git, all your commits are properly signed off. 🎉

[codecov]

Codecov Report

❌ Patch coverage is 3.71747% with 259 lines in your changes missing coverage. Please review.

Files with missing lines	Patch %	Lines
...erimental/pipeline/threaded_layout_vlm_pipeline.py	0.00%	195 Missing ⚠️
docling/models/api_vlm_model.py	14.03%	49 Missing ⚠️
.../datamodel/threaded_layout_vlm_pipeline_options.py	0.00%	13 Missing ⚠️
.../models/vlm_models_inline/hf_transformers_model.py	0.00%	1 Missing ⚠️
docling/models/vlm_models_inline/mlx_model.py	0.00%	1 Missing ⚠️

📢 Thoughts on this report? Let us know!