You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
I have implemented a graph with a MongoDBSaver checkpointer. I tested the compiled graph and call stream() function, and it used the MongoDBSaver correctly.
However, when I start it as "langgraph dev" and use langgraph_sdk client (get_client()) to call streaming using client.runs.stream function, it is found that the checkpointer is not using the MongoDBSaver checkpointer. It is using langgraph_storage.checkpoint.InMemorySaver instead. Why?
reacted with thumbs up emoji reacted with thumbs down emoji reacted with laugh emoji reacted with hooray emoji reacted with confused emoji reacted with heart emoji reacted with rocket emoji reacted with eyes emoji
Uh oh!
There was an error while loading. Please reload this page.
-
I have implemented a graph with a MongoDBSaver checkpointer. I tested the compiled graph and call stream() function, and it used the MongoDBSaver correctly.
However, when I start it as "langgraph dev" and use
langgraph_sdk
client (get_client()
) to call streaming usingclient.runs.stream
function, it is found that the checkpointer is not using the MongoDBSaver checkpointer. It is using langgraph_storage.checkpoint.InMemorySaver instead. Why?Beta Was this translation helpful? Give feedback.
All reactions