Add default document loader and parser for RAG

[AgentGenie]

Why are these changes needed?

Add document loader and parser (Docling) for RAG.

Related issue number

#438

Checks

• I've included any doc changes needed for https://docs.ag2.ai/. See https://docs.ag2.ai/docs/contributor-guide/documentation to build and test documentation locally.
• I've added tests (if relevant) corresponding to the changes introduced in this PR.
• I've made sure all auto checks have passed.

[marklysze]

Thanks @AgentGenie!

A couple of things:

• Can you change function names from docline to docling
• Tests are failing with missing packages, @davorrunje is there anything in particular needed here when using new packages

On the note of selenium, it may also be a worthwhile option to look at using the Crawl4AI package to scrape the page when loading a URL. They say "Creates smart, concise Markdown optimized for RAG and fine-tuning applications.".

[marklysze]

Thanks for updating the parser name, can you also add an extra and packages to the pyproject.toml for all the additional packages required.

[davorrunje]

Thanks for updating the parser name, can you also add an extra and packages to the pyproject.toml for all the additional packages required.

I fixed the packaging and related stuff, will push my changes soon.

[marklysze]

Thanks @AgentGenie and @davorrunje

[marklysze]

Gemini test failure unrelated.