BentoML

Hi Everyone,
From the documentation, I saw that BentoML automatically configures the Dockerfile and gRPC protofile, client, and server from `service.py`. Is there any way that I can configure the Docker and gRPC setup manually as a traditional Docker and gRPC setup?

For a summary of the services, how can I deploy them into Docker, and how can I connect my services using proto files, gRPC clients, and gRPC servers?

are you looking to build a custom gRPC server?

in that case, i’d recommend build and deploy your gRPC server separately, and from your gRPC services code, invoke another BentoML deployment where your model inference code are deployed