Initial Release of Openize.MarkItDown for Python
The **Openize.MarkItDown for Python** library is a utility tool for converting various files to Markdown, making it useful for indexing, text analysis, and further processing. Additionally, it supports integrating the converted Markdown data into LLM models for enhanced AI-driven applications.
It presently supports:
- **PDF** (.pdf)
- **PowerPoint** (.pptx)
- **Word** (.docx)
- **Excel** (.xlsx)
Simple API Usage
python
from openize.markitdown.core import MarkItDown
Define input file and output directory
input_file = "report.pdf"
output_dir = "output_markdown"
Create MarkItDown instance
converter = MarkItDown(output_dir)
Convert document and send output to LLM
converter.convert_document(input_file, insert_into_llm=True)
print("Conversion completed and data sent to LLM.")
We welcome feedback and contributions to enhance Openize.MarkItDown. Feel free to submit issues, suggestions, or pull requests to our repository.
Happy converting!