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

Update specification #2165

Conversation

aymeric-roucher
Copy link

What does this PR do?

Add specification for response_format in openapi.json to allow for huggingface_hub.InferenceClient to use it.

@aymeric-roucher aymeric-roucher requested a review from drbh July 2, 2024 10:08
@Narsil
Copy link
Collaborator

Narsil commented Jul 2, 2024

This file is normally generated directly from the spec as defined here:

https://github.com/huggingface/text-generation-inference/blob/main/router/src/lib.rs#L825

@drbh Is this normal the spec is out of date ? (If yes, we should have something in CI check it, if not, we should update the Rust code to get that thing in).

@Wauplin
Copy link
Contributor

Wauplin commented Jul 2, 2024

+1 on having openapi.json up to date with a CI check. We are now using it to generate InferenceClient types and automating this would help getting things on-par! 🙏

@drbh
Copy link
Collaborator

drbh commented Jul 2, 2024

It shouldn't be out of sync but currently CI doesn't check if it is up to date.

However, this PR should fix those issues and will ensure that the spec is up to date #2169. It also includes an updated openapi.json.

@Narsil
Copy link
Collaborator

Narsil commented Jul 3, 2024

Going ahead an closing this since #2169 takes care of it (Happy to make you a contributor @aymeric-roucher if you're not already)

@Narsil Narsil closed this Jul 3, 2024
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.

None yet

4 participants