Skip to content

Implemented dynamic load list of models with caching#9

Open
s2005 wants to merge 4 commits intotonybaloney:mainfrom
s2005:dynamic_load2
Open

Implemented dynamic load list of models with caching#9
s2005 wants to merge 4 commits intotonybaloney:mainfrom
s2005:dynamic_load2

Conversation

@s2005
Copy link
Copy Markdown

@s2005 s2005 commented Feb 2, 2025

No description provided.

@tonybaloney tonybaloney requested a review from Copilot February 3, 2025 22:53
Copy link
Copy Markdown
Contributor

Copilot AI left a comment

Choose a reason for hiding this comment

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

Copilot reviewed 2 out of 2 changed files in this pull request and generated 1 comment.

Comments suppressed due to low confidence (2)

llm_github_models.py:51

  • [nitpick] The class name GitHubModelsConfig is too generic. Consider renaming it to something more specific like GitHubModelsFetchConfig.
class GitHubModelsConfig(BaseModel):

llm_github_models.py:87

  • Ensure that the new dynamic fetching logic in fetch_models is covered by tests.
def fetch_models() -> List[Tuple[str, bool, List[str], List[str]]]:

Comment thread llm_github_models.py
@tonybaloney
Copy link
Copy Markdown
Owner

sorry I made some big changes so you'll need to rebase.

I've been asking the team behind this about a better API and apparently one is coming, that should include the parameters and whether the model supports streaming. So I think it's best to wait to implement some dynamic fetching.

@s2005
Copy link
Copy Markdown
Author

s2005 commented Feb 5, 2025

np

@s2005 s2005 marked this pull request as draft March 1, 2025 19:12
@s2005 s2005 marked this pull request as ready for review March 1, 2025 21:52
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