I deal with scanned PDFs and handwritten notes sometimes, and while agents can do it unsupervised, it sometimes gets stuck or fails. My solution was feeding said files to other llms separately via @simonwillison.net 's llm utility. Like a baton pass from my main K2.5 Opencode session/s to Gemini.
gist.github.compdf-parse-with-llm - skill to process PDFs with `llm`pdf-parse-with-llm - skill to process PDFs with `llm` - README.md
0 reposts0 likes