[toomuchtodo]

Paper. Goes in a pile. Pile goes in a scanner. Digital files from scanner get automatically processed into digital files, OCR, indexed, etc.

[mcsgroi]

That makes sense.

I am curious what you are using for indexing and how you typically search through the scanned content. Is it mostly keyword based search, or do you have any way of surfacing things beyond exact matches?

[toomuchtodo]

Digital files go into a Dropbox folder, that folder is exposed for RAG to enable querying with an LLM. I can also get to the raw PDFs through the Dropbox web interface and mobile app.

[mcsgroi]

Interesting - thanks for sharing.