Re:Re-implementing LangChain in 100 lines of code
by 19h on Thursday May 04, 2023 @11:12PM
(#35824811)
Comparing Langchain to Hugging Face Transformers is apples and oranges. One is for research, one is for production. Production ML requires more abstraction, not less.
[ Parent
| on HN ]
Re:Re-implementing LangChain in 100 lines of code
by crazyedgar on Friday May 05, 2023 @01:14AM
(#35825446)
I disagree. Production systems don't need to be full of AbstractSingletonProxyFactoryBeans which is basically what LangChain is. For example, Linux certainly isn't.