nginx.conf

events {
    # determines how many requests can simultaneously be served
    # https://www.digitalocean.com/community/tutorials/how-to-optimize-nginx-configuration
    # for more information
    worker_connections 2048;
}

http {
  server {
    # configures the server to listen to the port 8080
    # Amazon SageMaker sends inference requests to port 8080.
    # For more information: https://docs.aws.amazon.com/sagemaker/latest/dg/your-algorithms-inference-code.html#your-algorithms-inference-code-container-response
    listen 8080 deferred;

    # redirects requests from SageMaker to TF Serving
    location /invocations {
      proxy_pass http://localhost:8501/v1/models/deepctr_model:predict;
    }

    # Used by SageMaker to confirm if server is alive.
    # https://docs.aws.amazon.com/sagemaker/latest/dg/your-algorithms-inference-code.html#your-algorithms-inference-algo-ping-requests
    location /ping {
      return 200 "OK";
    }
  }
}