Converting Embedded image from Documents

[FeuRicardo]

Pull Request

Description

This PR introduces the following changes:

1. Initialization of New Attributes:

   • Added _mlm_client and _mlm_model attributes to the PptxConverter class, initialized using the kwargs dictionary.

2. Handling of Image Shapes:

   • Integrated a new method _convert_image_to_markdown to handle the conversion of image shapes to markdown within the presentation slides processing loop.

3. Handling of image within DataURI:

   • Integrated a new validation to identify DataURIs of the image type and, if the LLM model has been defined, converts the image to markdown.

4. Addition of _convert_image_to_markdown Method:

   • Added a new method _convert_image_to_markdown to the PptxConverter class to convert image shapes to markdown format.

Related Issue

Link to the related issue (if any).

Motivation and Context

• The new attributes _mlm_client and _mlm_model are required for additional functionality.
• The _convert_image_to_markdown method improves the handling of image shapes by converting them to markdown format, enhancing the overall functionality of the PptxConverter class.
• The new feature that identifying and converting image-type DataURIs improves handling of documents (such as .docx) that have embedded images, enhancing the overall functionality of the _CustomMarkdownify class and its dependents.

How Has This Been Tested?

• [ ] Unit tests
• [ ] Integration tests
• [ X ] Manual testing

Please describe the tests that you ran to verify your changes. Provide instructions so we can reproduce.

Screenshots (if appropriate):

Types of changes

• [ ] Bug fix
• [ X ] New feature
• [ ] Breaking change
• [ ] Documentation update

Checklist:

• [ X ] My code follows the code style of this project.
• [ ] My change requires a change to the documentation.
• [ ] I have updated the documentation accordingly.
• [ X ] I have added tests to cover my changes.
• [ X ] All new and existing tests passed.
• [ X ] The title of my pull request is a short description of the requested changes.

Additional Notes

This new feature reflects over .pptx, .docx and .html (including extends classes)

[gagb]

please expand the pr description.

[FeuRicardo]

please expand the pr description.

Pull Request

Description

This PR introduces the following changes:

1. Initialization of New Attributes:

   • Added _mlm_client and _mlm_model attributes to the PptxConverter class, initialized using the kwargs dictionary.

2. Handling of Image Shapes:

   • Integrated a new method _convert_image_to_markdown to handle the conversion of image shapes to markdown within the presentation slides processing loop.

3. Addition of _convert_image_to_markdown Method:

   • Added a new method _convert_image_to_markdown to the PptxConverter class to convert image shapes to markdown format.

Related Issue

Link to the related issue (if any).

Motivation and Context

• The new attributes _mlm_client and _mlm_model are required for additional functionality.
• The _convert_image_to_markdown method improves the handling of image shapes by converting them to markdown format, enhancing the overall functionality of the PptxConverter class.

How Has This Been Tested?

• [ ] Unit tests
• [ ] Integration tests
• [x] Manual testing

Please describe the tests that you ran to verify your changes. Provide instructions so we can reproduce.

Screenshots (if appropriate):

Types of changes

• [ ] Bug fix
• [x] New feature
• [ ] Breaking change
• [ ] Documentation update

Checklist:

• [x] My code follows the code style of this project.
• [ ] My change requires a change to the documentation.
• [ ] I have updated the documentation accordingly.
• [x] I have added tests to cover my changes.
• [x] All new and existing tests passed.
• [x] The title of my pull request is a short description of the requested changes.

Additional Notes

Add any additional information or context.

[thiner]

This is a mandate feature. When can this PR be merged?