run-llama / llama-hub

A library of data loaders for LLMs made by the community -- to be used with LlamaIndex and/or LangChain
https://llamahub.ai/
MIT License
3.44k stars 732 forks source link

Added handling of filename_as_id and file_extractor to SharePointReader #934

Closed ferdinandosimonetti closed 7 months ago

ferdinandosimonetti commented 7 months ago

Description

I've taken MinioReader's handling of file_extractor parameter for SimpleDirectoryReader This allows to choose a customized matching between file extension and its Reader/Decoder, and *shouldn't wreak havoc on SharePointReader's functionality.

Type of Change

Please delete options that are not relevant.

How Has This Been Tested?

Suggested Checklist:

anoopshrma commented 7 months ago

You'll need to look at linting and test case as well on this.

review-notebook-app[bot] commented 7 months ago

Check out this pull request on  ReviewNB

See visual diffs & provide feedback on Jupyter Notebooks.


Powered by ReviewNB

ferdinandosimonetti commented 7 months ago

Solved the last complaint about importing Union, that is unused