I think LangChain is already outdated and it (and its copycats) are going to cripple the entire field.
No, the design from an old academic paper was used with a much newer model. And now everyone is just copying that.
It works, because new models are impressive. But the design is far from being elegant or particularly efficient. And now, because tons of data like that is going to be generated, we’ll be stuck with it.
[0]: https://ai.googleblog.com/2022/11/react-synergizing-reasonin...
So essentially you have an approach, designed to work on these models that are not really instruction following models and that truly are stochastic parrots.
The models had changed substantially since. But the approach of chaining them in this particular way stuck. And is getting copied everywhere, without much thought.
I don’t want to see further expansion of this. I’m not offering higher level design, because I’m not sure about safety of all of this.
But having a poor and potentially unstable design like LangChain also doesn’t contribute to it :-/
Similarly, I expect creative hackers to pursue new approaches in the space of LLM frameworks and for some of those to catch on, and that they don't need to uproot langchain to do so.
An analogy of a file format is a close one. Imagine someone invents something nasty and bulky, like a twisted form of XML or something. And, simply because it is early, it catches on. It could be buggy and unstable and ugly, but it still wins, because it is early.
The call here is to try to examine LangChain design a bit closer. And maybe consider that a start from scratch is a good idea.