Skip to content
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

Improve typed task outputs #1651

Conversation

bhancockio
Copy link
Collaborator

No description provided.

Copy link

linear bot commented Nov 25, 2024

Copy link
Collaborator

@pythonbyte pythonbyte left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

LGTM ✅
Just left one suggestion (nitpick), and the tests are falling.
Aside from that all good 😄

@@ -214,3 +214,29 @@ def create_converter(
raise Exception("No output converter found or set.")

return converter


def generate_model_description(model: Type[BaseModel]) -> str:
Copy link
Collaborator

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Nitpick: Adding a docstring here could be good to inform the user about the function's goal

@bhancockio bhancockio merged commit 4069b62 into main Nov 26, 2024
4 checks passed
@bhancockio bhancockio deleted the brandon/cre-492-improve-task-execution-with-pydantic-or-json-output branch November 26, 2024 14:41
@ddragosd
Copy link

I confirmed that this is working well. I'm looking forward to the next release, which should improve the performance of all agents using Pydantic.

Having the prompt a bit larger (more tokens) in my use-case, I'm noticing a few more secs on avg, but that's 👌 from my perspective.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

Successfully merging this pull request may close these issues.

3 participants