Describing Images Inline in PDFs for Better RAG

Title: Describing Images Inline in PDFs for Better RAG

I've been using LLMs to describe images like this, but its just support pass image directly:

from markitdown import MarkItDown
from openai import OpenAI

client = OpenAI()
md = MarkItDown(llm_client=client, llm_model="gpt-4o")
result = md.convert("example.jpg")
print(result.text_content)

However, in many cases, my PDF files contain both text and embedded images. I want to extract both and generate inline image descriptions in Markdown to improve retrieval quality in GenAI.

Is there a way to achieve something like this?

Original PDF content:

Lorem ipsum dolor sit amet...  
<-- image 1 - contains an orange cat --!>

Expected Markdown output:

Lorem ipsum dolor sit amet...

The image shows a fat orange cat sleeping on a white background.

How can I process both text and images together like this in a single conversion step?

Start by tracing the repository’s PDF conversion path and comparing it with the documented image conversion example using MarkItDown and an LLM client. Determine how embedded images and surrounding text are currently handled; done should mean a single PDF conversion preserves the text and inserts generated image descriptions in the expected Markdown order.