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
Implemented something in hackathon with langgraph (python), intended to be in a chat with two users in turns (roles as buyer and sellers) and agent being a mediator, the graph starts with user prompting with a query, ultimately it leads to a node starting a live call with the other user,
Question is
The node making the call relies on the conversation happening on the call, to evaluate conditional edge conditions to whether stay or go the next node, now if let's, a message has been transcribed which after invoking the LLM, results in a signal that says leave the node and the call has not disconnected by the user, how the flow would be managed
To tell you, I tried to implement it with twilio, (cartesia tts) and Google stt, all of which is natively node js friendly
And I had to retract
How could this be achieved with python? Would anyone like to tell?
I would love a code snippet too just for that node and a conditional edge, also llm responses are structured with one of the keys signalling exit
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.
-
Implemented something in hackathon with langgraph (python), intended to be in a chat with two users in turns (roles as buyer and sellers) and agent being a mediator, the graph starts with user prompting with a query, ultimately it leads to a node starting a live call with the other user,
Question is
The node making the call relies on the conversation happening on the call, to evaluate conditional edge conditions to whether stay or go the next node, now if let's, a message has been transcribed which after invoking the LLM, results in a signal that says leave the node and the call has not disconnected by the user, how the flow would be managed
To tell you, I tried to implement it with twilio, (cartesia tts) and Google stt, all of which is natively node js friendly
And I had to retract
How could this be achieved with python? Would anyone like to tell?
I would love a code snippet too just for that node and a conditional edge, also llm responses are structured with one of the keys signalling exit
Beta Was this translation helpful? Give feedback.
All reactions