Messy insurance emails, property listings, and medical prescriptions are important documents in my daily workflow, but most of the time, it is difficult to get usable data out of them. Traditional ...

Compare prompt variations — run the same dataset through different prompts and see which performs better. Benchmark models — evaluate GPT-4o vs GPT-4o-mini vs Claude on the same test set. Test RAG ...

This repository documents and implements the end-to-end release workflow used by the LangChain Python monorepo. It covers every stage of taking a package from "ready to release" to "published on PyPI, ...