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

Upgrade to version 0.1.3 #18

Merged
merged 20 commits into from
Nov 21, 2024
Merged

Upgrade to version 0.1.3 #18

merged 20 commits into from
Nov 21, 2024

Conversation

chinganc
Copy link
Collaborator

@chinganc chinganc commented Nov 19, 2024

In this upgrade, two features are introduced.

  1. An abstraction of LLM models, AutoGenLLM class (which shares the same API as autogen OpenAIWrapper). User can subclass this class for their backend. AutoGenLLM is a subclass of AbstractModel which is a abstract class to support auto-refreshing model instances and serialization. As a result, AutoGenLLM can be deep copied and optimizers in trace.optimizers which is useful for reproducing experiments. Originally OpenAIWrapper is rlocked and cannot be serialized.
  2. trace.bundle is refactored to support python asyncio. Now async functions can be bundled. The bundled function is still an async function. Running the function will return a coroutine. Await the coroutine gets the result as a MessageNode. Error handling works too.

@chinganc chinganc changed the title Upgrade to version 0.1.4 Upgrade to version 0.1.3 Nov 19, 2024
@chinganc
Copy link
Collaborator Author

@microsoft-github-policy-service agree company="Microsoft"

Copy link
Collaborator

@allenanie allenanie left a comment

Choose a reason for hiding this comment

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

The refactoring looks good

@@ -67,6 +67,7 @@ class FunModule(Module):
description (str): a description of the operator; see the MessageNode for syntax.
_process_inputs (bool): if True, the input is extracted from the container of nodes; if False, the inputs are passed directly to the underlying function.
trainable (bool): if True, the block of code is treated as a variable in the optimization
traceable_code (bool): if True, the operator's code is traceable by Trace
Copy link
Collaborator

Choose a reason for hiding this comment

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

Unclear what this means...

@allenanie allenanie merged commit 29fc5ea into main Nov 21, 2024
4 checks passed
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.

2 participants