Skip to content
This repository was archived by the owner on Sep 11, 2025. It is now read-only.

Conversation

@jairad26
Copy link
Contributor

@jairad26 jairad26 commented Nov 22, 2024

Description

Instead of using a hardcoded list of supported shared models, this reads from a remotely hosted endpoint

Checklist

  • Code compiles correctly and linting passes locally
  • For all code changes, an entry added to the CHANGELOG.md file describing and linking to this PR
  • Tests added for new functionality, or regression tests for bug fixes added as applicable
  • For public APIs, new features, etc., PR on docs repo staged and linked here

@jairad26 jairad26 requested a review from a team November 22, 2024 22:45
Copy link
Contributor

@mattjohnsonpint mattjohnsonpint left a comment

Choose a reason for hiding this comment

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

Per discussion, the CLI should retrieve the file and keep it locally for the runtime to use. The runtime should also cache it on startup so it's not reading the file with every request.

@mattjohnsonpint
Copy link
Contributor

Per follow-up discussion, we shouldn't actually need the list at all. We can simply check for a distinct error status such as 404 when the model is invoked, to tell us that the model is not available.

@ryanfoxtyler ryanfoxtyler marked this pull request as draft December 3, 2024 14:57
@mattjohnsonpint
Copy link
Contributor

Closed in favor of #703

Sign up for free to subscribe to this conversation on GitHub. Already have an account? Sign in.

Labels

None yet

Development

Successfully merging this pull request may close these issues.

3 participants