How do I use this in more complex scenarios?

[samgregson]

The examples are somewhat lacking. I would love to use TextGrad for prompts which have a combination of non-optimisable context as well as optimisable text (like RAG). I'd also like to see examples of chains of LLM calls (not just a single LLM as per examples). Finally, the paper mentions optimisation for tool calling, how do we achieve this? Thanks for the awesome development, just wish I new how to use it in more complex settings!

[belmarca]

The examples do need a bit of love. E.g., in the Prompt Optimization tutorial notebook run_validation_revert has a val_set parameter which it passes to eval_dataset. However eval_dataset uses the name test_set for this variable.