Hacker Newsnew | past | comments | ask | show | jobs | submitlogin

I am always suspicious with frameworks. There are two reasons of that. First is that because of the inversion of control they are more rigid than libraries. This is quite fundamental - but there are cases where the trade off is totally worth it. The second one is because of how they are created - it often starts with an application which is then gradually made generic. This is good for advertising - you can always show how useful the framework with an application that uses it. But this "making it generic" is a very tricky process that often fails. It is a top down, the authors need to imagine possible uses and then enable them in the framework - while with libraries the users have much more freedom to discover them in a bottom up process. Users always have surprising ideas.

There are now libraries that cover some of the features of Langchain. There is Instructor and mine LLMEasyTools for function calling, there is LiteLLM for API unification.



from the first glance of the example, it seems like the 1st use case is invoking a function (selected by chatgpt) and the 2nd use case is similar to instructor.

can you comment how your library differs from instructor (what yours can do that instructor can't and vice versa?)

thanks




Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact

Search: