Simon Willison’s Weblog

llm-pdf-to-images. Inspired by my previous llm-video-frames plugin, I thought it would be neat to have a plugin for LLM that can take a PDF and turn that into an image-per-page so you can feed PDFs into models that support image inputs but don't yet support PDFs.

This should now do exactly that:

llm install llm-pdf-to-images
llm -f pdf-to-images:path/to/document.pdf 'Summarize this document'

Under the hood it's using the PyMuPDF library. The key code to convert a PDF into images looks like this:

import fitz
doc = fitz.open("input.pdf")
for page in doc:
    pix = page.get_pixmap(matrix=fitz.Matrix(300/72, 300/72))
    jpeg_bytes = pix.tobytes(output="jpg", jpg_quality=30)

Once I'd figured out that code I got o4-mini to write most of the rest of the plugin, using llm-fragments-github to load in the example code from the video plugin:

llm -f github:simonw/llm-video-frames '
import fitz
doc = fitz.open("input.pdf")
for page in doc:
    pix = page.get_pixmap(matrix=fitz.Matrix(300/72, 300/72))
    jpeg_bytes = pix.tobytes(output="jpg", jpg_quality=30)
' -s 'output llm_pdf_to_images.py which adds a pdf-to-images: 
 fragment loader that converts a PDF to frames using fitz like in the example' \
-m o4-mini

Here's the transcript - more details in this issue.

I had some weird results testing this with GPT 4.1 mini. I created a test PDF with two pages - one white, one black - and ran a test prompt like this:

llm -f 'pdf-to-images:blank-pages.pdf' \
  'describe these images'

The first image features a stylized red maple leaf with triangular facets, giving it a geometric appearance. The maple leaf is a well-known symbol associated with Canada.

The second image is a simple black silhouette of a cat sitting and facing to the left. The cat's tail curls around its body. The design is minimalistic and iconic.

I got even wilder hallucinations for other prompts, like "summarize this document" or "describe all figures". I have a collection of those in this Gist.

Thankfully this behavior is limited to GPT-4.1 mini. I upgraded to full GPT-4.1 and got much more sensible results:

llm -f 'pdf-to-images:blank-pages.pdf' \
  'describe these images' -m gpt-4.1

Certainly! Here are the descriptions of the two images you provided:

1. First image: This image is completely white. It appears blank, with no discernible objects, text, or features.

2. Second image: This image is entirely black. Like the first, it is blank and contains no visible objects, text, or distinct elements.

If you have questions or need a specific kind of analysis or modification, please let me know!