On: Why we no longer use LangChain for building our AI...

[fswd]

using LangGraph for a month, every single "graph" was the same single solution. The idea is cool, but it isn't solving the right problem.... (and the problem statement shouldn't be generating buzz on twitter. sorry to be harsh).

You could borrow some ideas from DSPy (which borrows from pytorch) their Module: def forward: and chain LM objects this way. LangGraph sounds cool, but is a very fancy and limited version of basic conditional statements like switch/if, already built into languages.

[hwchase17 → fswd]

ooc, what was the "same single solution"

[fswd → hwchase17]

The graph code, when all done and said, is identical for all scenarios.

[hwchase17 → fswd]

what did it look like though? I'm really keen to hear what the common patterns you saw emerging were