Data Cleaning with 'markitdown'

[stefanfrench]

Motivation

The data cleaning part of the document-to-podcast workflow could be made more robust, as currently it does not take into account all possible cases.

Alternatives

Have also considered: https://github.com/VikParuchuri/marker, which could be an interesting alternative to 'markitdown'.

Contribution

Re-implementing the data cleaning component to use markitdown

This would make the data cleaning component for robust, and potentially re-useable across many Blueprints.

There is potential to submit a PR related to updating the data cleaning compoenent to leverage markitdown

Have you searched for similar issues before submitting this one?

• Yes, I have searched for similar issues