I haven’t looked under the hood here but to make simple text replacement via command line is an LLM even required? A human driven command line tool to do basic substitution on batches of files reliably would be amazing.
Not really - if you wanna do a text replacement you can extract it yourself and do some work (or just use this CLI). The library is designed for longer workloads.
sed, awk. docx is just zipped xml.
there is a python library for docx handling. my thinking was the use case for this was for larger scale automations / document processing.