Ask HN: How's LangGraph for Prod?

[chaos_emergent]

I was pretty burned by langchain in the AI hype cycle of 2021, curious if anyone has been using either LC or LG in production more recently? FSM graph traversal is an interesting abstraction for an LLM runtime, but curious if anyone has been able to deliver real customer value with the engineering accoutrements (observably, logging, debugging, avoiding unnecessary abstractions) needed for Adult Development.

[karpatic]

The langchain docs are God awful, impossible to navigate with every page half baked. It was made even worse by their trying to push lg to the point you can barely find their lc docs. And, It's like they just shove jsdoc output into docusaurus pages for the api and call it a day. The api works well but thr api makes excessive calls imo and the output is still harder to grok then setting some of this stuff up manually.

[chaos_emergent → karpatic]

Thanks man. Basically sounds like they haven’t gotten better.

We have an advisor that’s pushing us towards langgraph but he’s the CAIO at a LargeCo and they have an entire team that’s devoted to building tooling for working with it. Which in and of itself is insane - the whole point of using a library is to avoid doing it yourself - but is also damning against LG because as an early stage startup I can’t afford the time sink of needing to work around a weird abstraction.

[nfcampos → karpatic]

Hi do you mind sharing more what you mean by "the api makes excessive calls"?