[Main Update] Doc to messages feature support and Split simple and chat mode

[kcz358]

Before you open a pull-request, please check if a similar issue already exists or has been closed before.

When you open a pull-request, please be sure to include the following

• A descriptive title: [xxx] XXXX
• A detailed description

If you meet the lint warnings, you can use following scripts to reformat code.

pip install pre-commit
pre-commit install
pre-commit run --all-files

Thank you for your contributions!

[kcz358]

Current major changes:

• Split chat and simple model for doc_to_messages and original doc_to_visual and doc_to_text
• Auto doc to messages for undefined task (currently only auto for image task)
• Setup a protocol for messages for simple extract media
• Add up a new task type for building different request
• Set up an example chat model for llava_hf