Repository navigation
|
Hey everyone, I am trying to stream LLM responses and looking for a way to separate one logical part (LLM call, function call, etc.) from another. However, I noticed that the Here is the code: run_config = RunConfig(streaming_mode=StreamingMode.SSE, support_cfc=False)
# Use runner.run_async(), which is an async generator for events.
async for event in runner.run_async(
user_id=user_id,
session_id=session_id,
new_message=new_message,
run_config=run_config,
):
print(event.id) # it is different for every LLM token |
Answered by
boyangsvl
May 21, 2025
Replies: 1 comment
|
I think you can look at event.partial to see if it's part of a stream. |
0 replies
Answer selected by
llalitkumarrr
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
I think you can look at event.partial to see if it's part of a stream.