Mickael W.

will try tomorrow 🙂 basically it becomes kind of a full manual tracing from what I read high level Honestly I think this code deserve to be in the documentation for langgraph, because... neat and pretty cool for a manual example ! 😄

Great ! 🙂

Inside every nodes of the langgraph I am using langchain as much as possible very high level stack looks like this :

Using langgraph mostly to simplify the async "parallel" calls to API 🙂 (modifié)

No I think it is good to share if someone else have same 'issue' 🙂 I will port that convo on the dedicated thread arize-platform-support 😉 inside every nodes of the langgraph I am using langchain as much as possible very high level stack looks like this :

Using langgraph mostly to simplify the async "parallel" calls to API 🙂

thank you Jason ! keep me posted 🙂

for now I am just starting with arize so I am only using UI but in long term it would be also cool to be able to pull it from the span For now my quick fix is that I add the pydantic class at the top of te playground prompt and instruct model to return me the exact string of the dictionary that would represent the class. but I am pretty sure someone thought about something smarter 😛

thank you ! I was wondering if there was a ressource specific to langgraph. because in langgraph we have consequent states and I am wondering if I can select what can be considered by arize at each langgraph node. 🙂 the langgraph format is really not convenient with the Arize evaluation system ^^