search

MaartenGr / BERTopic

Leveraging BERT and c-TF-IDF to create easily interpretable topics.
https://maartengr.github.io/BERTopic/
MIT License
6.03k stars 756 forks source link

Include guidance for saving Representative Documents #1811

Open mepearson opened 7 months ago

mepearson commented 7 months ago

Default saving methods #1 and #2 don't store Representative Documents. This is intentional, but prevents downstream LLM topic analysis on previously run models. Include guidance in the documentation for storing these documents in a separate dataframe for integration in future analyses.

MaartenGr commented 7 months ago

Thanks for the suggestion! I'll put it on the backlog but if you want to help out with a PR that would be greatly appreciated!