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

Add models.openai and tools.langchain namespaces #4601

Conversation

lspinheiro
Copy link
Collaborator

Why are these changes needed?

Similar to agents and code executors, moving openai models to its own namespace.

Related issue number

Related to #4408

Checks

@lspinheiro lspinheiro changed the title Add models.openai namespace Add models.openai and tools.langchain namespaces Dec 7, 2024
@lspinheiro
Copy link
Collaborator Author

@jackgerrits , there seems to be an test failing that is unrelated to the changes in the PR. I'm not sure what is the expected behavior of the code failing the test. Tagging for awareness

FAILED tests/test_tools.py::test_get_typed_signature_string - AssertionError: assert (<class 'str'>, True) is str
 +  where (<class 'str'>, True) = <Signature () -> (<class 'str'>, True)>.return_annotation

@lspinheiro lspinheiro requested a review from ekzhu December 10, 2024 00:04
@jackgerrits jackgerrits merged commit 253fe21 into microsoft:main Dec 10, 2024
45 checks passed
ekzhu pushed a commit that referenced this pull request Dec 10, 2024
* add models.openai namespace

* refactor tools namespace

* update lock file

* revert pyproject changes

* update docs and add cast

* update ext models doc ref

* increase underline

* add reply models namespace

* update imports

* fix test

* linting

* fix missing conflicts

* revert pydantic changes

* rename to replay

* replay

* fix reply

* Fix test

* formatting

* example

---------

Co-authored-by: Leonardo Pinheiro <[email protected]>
Co-authored-by: Jack Gerrits <[email protected]>
Co-authored-by: Jack Gerrits <[email protected]>
eranco74 added a commit to eranco74/autogen that referenced this pull request Dec 10, 2024
Update the Python example in the readme to import OpenAIChatCompletionClient from the new path

Currently, the example fails with this error:
ImportError: cannot import name 'OpenAIChatCompletionClient' from 'autogen_ext.models' (unknown location)

This change relates to: microsoft#4601
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.

4 participants