-
Notifications
You must be signed in to change notification settings - Fork 404
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
Feat: Upgrade LangChain to Version 0.3 #784
Conversation
- Updated import paths for 'BaseLLM' to 'langchain_core.language_models.llms' across multiple files. - Ensured compatibility with the latest version of LangChain.
- Updated import paths for 'pydantic.v1' to ensure compatibility with the latest version of Pydantic. - Suppressed specific warnings related to protected namespaces in Pydantic models by adding a filter to ignore these warnings.
- Updated version constraints for 'langchain', 'langchain-core', and 'langchain-community' to allow versions up to <0.4.0.
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
LGTM 👍
# We set nvidia_ai_endpoints provider to None because it's only supported if `langchain_nvidia_ai_endpoints` is installed. | ||
_providers: Dict[str, Type[BaseLanguageModel]] = { | ||
_providers: Dict[str, Optional[Type[BaseLLM]]] = { |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Do we need here the Optional?
When is this develop going to be release? I believe it is kind of urgent |
Maybe a v 0.10.2 can be released as a patch to cover this issue |
This pull request makes the necessary changes to upgrade LangChain to version 0.3.
Update Pydantic Import Paths:
pydantic.v1
to ensure compatibility with the latest version of Pydantic.Update LangChain Version Constraints:
langchain
,langchain-core
, andlangchain-community
to allow versions up to <0.4.0.Refactor Import Paths for BaseLLM:
BaseLLM
tolangchain_core.language_models.llms
across multiple files to align with the latest version of LangChain.