Automatic parent item creation for non-scientific pdfs?

Hi all. I go through a lot of grey literature and lecture slides, which naturally lack the standardized formatting of scientific papers and many times even an ISBN number. Thus, "Retrieve metadata" or magic wand seldom work for creating parent items for these files, and I have to engage in a lot of manual work to keep my library organized.

Has anyone found good workarounds for this problem?

I'm so desperate that I'm thinking about building an "educated guesser" using Pyzotero + Ollama. However, I just wanted to see if something already exists.

Thanks in advance!
  • edited June 29, 2025
    If the documents are available or referenced on suitable platforms (document repositories, maybe library catalogues), get the metadata from there using the browser connector. Whenever it's possible, it's the best method - even for scientific PDFs it usually yields more detailed metadata than the "Retrieve metadata" feature.

Sign In or Register to comment.