pip install -r requirements.txt
Run using main.py:
- Search for corresponding books by ISBN/Title
- Gather metadata for books, if matching ones are found
- Download preferred extension (ideally epub, txt, or html)
- Extract text from the downloaded file
- Extract questions from extracted text
- Compute topic mixtures for the books
This generates a file at data/library.json. Move this to cybersym/data/library.json.