LangChain is just too much, personal solutions are great, until you need to compare metrics or methodologies of prompt generation. Then the onus is on these n-parties who are sharing their resources to ensure that all of them used the same templates, they were generated the same way, with the only diff being the models these prompts were run on.

So maybe a simpler library like Microsoft's Guidance (https://github.com/microsoft/guidance)? It does this really well.

Also LangChain has a lot of integrations, that just pop up as soon as new API for anything LLM pops up, so that helps with new user onboarding as well.