-
Notifications
You must be signed in to change notification settings - Fork 992
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
How to process the data of the reasoning model? #334
Comments
That's up to you! For example, ChatGPT displays the reasoning before the message, in a toggleable container. |
@rm-openai Code Example: # Imports omitted for brevity
agent = Agent(
model="qwq-plus",
name="Assistant",
instructions="You are a helpful assistant that will help me search for information",
tools=[web_search]
)
async def main():
result = Runner.run_streamed(agent, input="What's the latest news about new energy?")
async for event in result.stream_events():
print(event)
if __name__ == "__main__":
asyncio.run(main()) Current Output:
Question:
Expected Behavior: {
"reasoning_content": "The user asked about new energy news. I started by searching the web using the web_search tool... [full reasoning process]"
} Notes:
Would appreciate guidance on how to properly access the model's reasoning process details! |
the same, i also checked the structed data format. there is no define about reasoning_content... and also cant findout where can take choices data customize |
This issue is stale because it has been open for 7 days with no activity. |
@zeke-chin it looks like the qwq model you're using doesn't have a separate reasoning item? it just outputs it as part of the text |
How to use the agent's API to process the reasoning data?
output
The text was updated successfully, but these errors were encountered: