run-llama/liteparse ? reverse-engineered prompt

Reverse engineered prompt

Build me a local, offline-first document processing tool in TypeScript. I need a simple command-line app that I can use to extract all the text from my files, especially PDFs. It's crucial that it runs entirely on my machine with no cloud services.

The main feature is parsing text. It should handle regular PDFs, but also needs to have OCR built-in to read text from scanned documents or images. I want to be able to point it at a single file or an entire directory and have it process everything, saving the output as either clean text or JSON.

Besides text extraction, I also want a command to generate high-quality screenshots of specific pages from a PDF file. For both features, I'll need options to specify page ranges, like "pages 1-5 and 10".

Are you gonna build this?

make sure you review the code using coderabbit

Try freeSponsored — opens CodeRabbit in a new tab