Quite a few contributions on the

bentoctl

Google Cloud Run operator, could someone take these for review? https://github.com/bentoml/google-cloud-run-deploy/pull/18 https://github.com/bentoml/google-cloud-run-deploy/pull/19 https://github.com/bentoml/google-cloud-run-deploy/pull/20 https://github.com/bentoml/google-cloud-run-deploy/pull/21 https://github.com/bentoml/google-cloud-run-deploy/pull/22

will do

This message was deleted.

This message was deleted.

This message was deleted.

This message was deleted.

This message was deleted.

Merry Christmas and Happy Holidays to all members of BentoML community! We hope that this holiday season is filled with joy, love, and laughter for everyone. Thank you for being an integral part of our community and for your contributions to the advancement of technology through open source collaboration. We are grateful for your dedication, and we look forward to continuing to work together in the new year. Wishing you all the best during this holiday season and in the year ahead! 🍻

This message was deleted.

I'm from Mexico City by the way 🇲🇽 😀 All my respect and admiration for you guys 🙏

This message was deleted.

This message was deleted.

This message was deleted.

Hi team, should I create an issue for this? I am willing to create a PR, but a few things are unclear to me, which makes it difficult to know whether to categorise this under a bug or a feature suggestion. After the fastapi app is mounted to the service, shouldn't the fast api generated docs also be accessible from the service in open_api.py? And if that's not the case, then we have to look in inference_api.py to see how we can add the openapi.json docs to the service. Does this sound correct?

Hi there

This message was deleted.

This message was deleted.

This message was deleted.

Ah, sorry, started taking a look at your PR and never finished; I've added a comment now.

This message was deleted.

This message was deleted.

This message was deleted.

Hello team! I am new to this channel and would like to make a contribution, so recently we used BentoML for our model training and inferencing API and we used ARIMA time series model, so we created a custom runner and used that to create prediction service, could you please guide on how to proceed with this? Also I did refer to the guidelines but I am just a bit new and not sure where to begin with so would appreciate your help. Thank you!

Hi Team, I am Aleric. I am interested in contributing to the community. We currently have a security blocker ie BentoML exposing the Server header. I have read the contributing and development documents and currently tinkering with the codebase to get a feel of how things work. I have also raised a feature request: https://github.com/bentoml/BentoML/issues/4663

Hello. I’m Lim. We have a problem we need to add uvicorn timeout options (keep-alive and graceful-shutdown) to the configuration. So I made a PR, please check it 🙏🏼 Thank you.

Hi there everyone! I want to possibly become a contributor to BentoML. Hoping someone is willing to hop on a quick call tomorrow or so where we can discuss the main parts of it, the codebase, etc. Thank you in advance!

👋 Hello, team!