Ivan Lugo
04/05/2023, 8:00 PMlangchain
and agents
are specifically built prompt templates that are backed with some fun interprocess coms, passing the results to various piped tools like a python / JS script to get the next ‘prompt piece’, and then looping until something ‘correct’ comes up? I feel https://github.com/mpaepper/llm_agents simplified the abstractions a bit to help me understand what was going on.