Mostly Harmless Ideas
Welcome to the first coding lesson in Mostly Harmless Ideas. This is an experimental section where I want to share very concrete, project-based coding lessons for all types of learners and all experience levels. I’m still figuring out the best format for these, so please let me know what works and what doesn’t for you.
Today’s lesson is about building a bare-bones app to answer arbitrary questions from a PDF file. We will use mistral.ai as the provider of language models, which has some incredibly powerful open-source LLMs 1 .
Here’s a quick look at the final application, answering questions on the latest draft of my upcoming book The Science of Computation.
This lesson is somewhat advanced, so I expect you to be comfortable with basic Python and building simple apps in streamlit, although most of the streamlit code will be self-explanatory.
You must also know how to set up a basic Python project using a virtual environment and install dependencies from requirement files. If you need help with any of these topics, check out The Python Coding Stack • by Stephen Gruppetta and Mostly Python for plenty of beginner-friendly articles.
