microsoft/markitdown

LLM Integration

Open

#12 opened on Dec 13, 2024

View on GitHub
 (16 comments) (9 reactions) (0 assignees)Python (123,207 stars) (8,330 forks)batch import
enhancementgood first issue

Description

As a feature suggestion, I would love if this could allow you to plug in an LLM (such as GPT-4o) where images that are included in the content could be sent to the LLM for further understanding. For example, if it was say a bar chart or graph, it would be sent to convert that to a Markdown table and be integrated in the final Markdown output.

Contributor guide

Tech stack
python
Domain
backendcli
Issue type
feature
DifficultyEstimated implementation difficulty for a new contributor, from 1 for very small changes to 5 for expert-level work.
4
Estimated timeA rough time range for an experienced contributor to investigate, implement, test, and prepare a pull request.
over 1 week
Activity statusHow available the issue appears right now: fresh, active, stale, blocked, or waiting on maintainer input.
active
ClarityHow clearly the issue explains the expected change, acceptance criteria, and next step.
needs investigation
Prerequisites
Python programmingHTTP API callsFamiliarity with markitdown
Newbie friendlinessA 1-100 score estimating how approachable this issue is for first-time contributors.
20
Research direction
Review the markitdown source code for current image handling, likely in the conversion logic. Investigate integrating an LLM API like OpenAI's GPT 4o for image to text conversion. Consider how to pass images, handle API keys, and format results into Markdown tables. Also check the issue comments for any additional constraints or desired flexibility.