-
Notifications
You must be signed in to change notification settings - Fork 0
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
Catch reasoning_content from litellm response #40
Conversation
Waiting for their release to validate this commit
@@ -44,7 +44,7 @@ dev = [ | |||
"fh-llm-client[local]", | |||
"fhaviary[xml]", | |||
"ipython>=8", # Pin to keep recent | |||
"litellm<1.57.2", # Pin for Router.acompletion typing break from https://github.com/BerriAI/litellm/pull/7594 | |||
"litellm>1.59.3", # Pin for deepseek support |
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.
Let's just remove this litellm
entry from dev
, #32 added it
@@ -29,7 +29,7 @@ dependencies = [ | |||
"pydantic~=2.0,>=2.10.1,<2.10.2", | |||
"tiktoken>=0.4.0", | |||
"typing-extensions; python_version <= '3.11'", # for typing.override | |||
'litellm; python_version < "3.13"', # NOTE: paper-qa==5.3 doesn't support 3.13 yet | |||
'litellm>1.59.3; python_version < "3.13"', # NOTE: paper-qa==5.3 doesn't support 3.13 yet |
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.
I think we just get rid of this python_version
thing and have one litellm>1.59.3
@@ -79,6 +79,9 @@ class LLMResult(BaseModel): | |||
logprob: float | None = Field( | |||
default=None, description="Sum of logprobs in the completion." | |||
) | |||
reasoning_content: str | None = Field( | |||
default=None, description="DeepSeek-R1 reasoning content from the LLM." |
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.
Reasoning content may come from other models besides DeepSeek-R1. Maybe adjust to say "Reasoning content from LLMs such as DeepSeek-R1"
No description provided.