ell is a lightweight prompt engineering library treating prompts as functions, that enables prompt versioning, optimization, tracing, readability, and visualization via lexical closures.

I built ell based on some ideas during my time as a research scientist at OpenAI around language model programming, with the aim of building the PyTorch of prompt engineering. AI engineering needs good, open-source and free tooling, so we've built a tensorboard-like visualization tool (studio) packaged along side ell to fully leverage this new library.

really excited about this, and would love some feedback!

also i'd like to kill langchain once and for all

This looks excellent. Thank you!

Somehow doesn't get the attention it deserves. Developing AI applications needs a new take and I welcome any fresh ideas. Will check it out.

Really exciting stuff! I can clearly see from the GitHub issue list that you do NOT intend to repeat the mistakes of LangChain, i.e. minimize bloat and abstraction level.

How would you say this compares to DSPy? At first glance, ell is very application developer focused, while DSPy is more designed as a lower level framework on top of which others can build. Curious to see how this evolves for ell. Also, prompt "optimization" as per the docs is a fuzzy term - what is being optimized exactly? Basically, if I want to minimize my time doing prompt engineering (which I hate), is ell the framework for me?