Books

FeynmanLM treats books differently from articles and papers. Instead of generating cards for an entire book at once (which would be overwhelming), it works chapter by chapter — letting you build your knowledge base gradually as you read.

Where to Store Books

Save book PDFs to this iCloud Drive folder:

~/Library/Mobile Documents/com~apple~CloudDocs/Documents/FeynmanLM/Books/

In Finder, this appears under iCloud Drive → Documents → FeynmanLM → Books. Create the folder if it doesn't exist.

Organize books into subfolders by title or author if you have many:

Books/
├── Deep Learning (Goodfellow)/
│   ├── deep-learning-ch01-intro.pdf
│   ├── deep-learning-ch02-linear-algebra.pdf
│   └── deep-learning-ch03-probability.pdf
├── The Pragmatic Programmer.pdf
└── Thinking Fast and Slow.pdf

Chapter Splitting

Long books need to be split into chapter-sized chunks before FeynmanLM can generate focused flashcards. The app works best with PDFs in the 20–80 page range per source.

Why split by chapter:

• The AI generates more targeted, coherent cards when the source is focused on one topic
• You can generate cards for chapters as you read them, rather than processing the whole book upfront
• Source context during review is more useful when it points to a specific chapter

Splitting a PDF on Mac:

Open the book PDF in Preview, then:

1. Go to View → Thumbnails to see the page sidebar
2. Select the pages for a chapter (click + Shift-click to select a range)
3. Drag the selected pages to the Finder folder, or use File → Export as PDF for the selection

Alternatively, use a tool like pdftk or pdfcrop in Terminal:

# Extract pages 45–78 (Chapter 3) from a book
pdftk book.pdf cat 45-78 output deep-learning-ch03-probability.pdf

Adding a Book Chapter

1. Save the chapter PDF to ~/Library/Mobile Documents/com~apple~CloudDocs/Documents/FeynmanLM/Books/.
2. Open FeynmanLM on Mac or iPhone.
3. In the Studio tab, the chapter PDF will appear in your queue automatically (the app scans the Books/ folder).
4. Select the chapter and click Generate Flashcards.
5. Review and accept cards as usual. Accepted cards go to the Books deck.

Context Files for Deep Review

For richer feedback during review — where the AI can cite specific passages from the book when evaluating your answers — upload the chapter as a Context File:

1. Tap the book icon in the top toolbar.
2. Tap + and select the chapter PDF from iCloud Drive.
3. During review, turn on Book context on the question screen.

The AI will read the relevant chapter passages when evaluating your answer, giving feedback that's grounded in the book's exact phrasing and examples.

Multiple Chapters Over Time

A common workflow:

• Week 1: Read Chapter 1, add ch01.pdf to Books/, generate and review proposals
• Week 2: Read Chapter 2, add ch02.pdf, generate and review
• As you progress, the Books deck grows organically

This mirrors how you actually read — you don't need to process a book all at once.

Tips

• Rename chapters descriptively: chapter-01.pdf is fine, but deep-learning-ch03-probability-and-information-theory.pdf gives the AI better context and makes the source name more useful during review.
• Skip appendices and references: Usually not worth generating flashcards for bibliography sections or appendices. Process only the chapters you're actively reading.
• Heavily illustrated books: Diagrams don't extract as text. For books where figures are central (e.g., anatomy atlases), use the Generate Diagram button during review to create AI-generated visual explanations of the concepts.