microsoft / microsoft/markitdown

while i try to convert a .pptx into a markdown it is not extracting the text from the images.

Open
#1,125 3 comments 0 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

Dominant language
Python
Stars
186k
Forks
13.7k
Avg merge
1d 4h
Merged PRs (30d)
49

Description

When I try to convert a .pptx file into a .md file, it does not extract the text from the images. It just gives an image number. I am using it with llm. I am using model gpt-4o. Is this because of a model or something else, and is there any capability at all?

Contributor guide

No contributing guide indexed for this repository

First steps

  1. Read the whole issue, then the project's contributing guide.
  2. Comment on the issue to say you are picking it up — it saves two people doing the same work.
  3. Fork the repository and make your change on a branch.
  4. Open a pull request that references the issue number.

Research direction

Start by reproducing the .pptx-to-.md conversion with text embedded in images, then inspect the image handling in the PowerPoint conversion path and the LLM usage with gpt-4o. Done means determining whether image text extraction is supported and, if so, extracting the text instead of emitting only an image number; otherwise document the limitation.

Written by the indexing model from the issue text.

Assessment

Tech stack
python
Domain
content
Issue type
Bug
Difficulty
4/5
Estimated time
3-5 days
Activity status
Stale
Clarity
Needs clarification
Newbie friendliness
25/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.