Deepankar Mahapatro

Can you please check if passing [`--platform linux/amd64`](https://github.com/jina-ai/langchain-serve#jcloud-deployment-failed-at-pushing-image-to-jina-hubble-what-should-i-do) helps during the deployment? If not, please add `--verbose` to the deploy jcloud command and share the logs.

There's no way right now to achieve this. We'd try to pick it up this week using an environment variable. Feel free to add a PR if you'd like.

Hi @Arcadia822, apologies about missing this, I moved it to the appropriate repo now. Can you please enable verbose logging by passing the `--verbose` flag during deployment to jcloud? That...

@danny-avila do you want to use transformers agents with the model hosted via huggingface inference endpoint, or are looking for langchain-serve to host the model in addition to the agent?

We'll look into implementing this next week @danny-avila

@simonw I've added a proposal for this in https://github.com/simonw/llm/pull/1195. Instead of implementing an async version for all the non-async versions, we can use `await asyncio.to_thread(sync_function)`, which should be safe for...