# Serving

## Gateway

![](https://2921833647-files.gitbook.io/~/files/v0/b/gitbook-legacy-files/o/assets%2F-MESaD8WY3ggQLtBByXl%2Fsync%2F7cec50fa1e5758f84d03af1280b3ee7c0a1a70a7.png?generation=1603095658336431\&alt=media)

Gateway is a service responsible for routing requests to/from or between Servables and Applications and validating these requests for matching a Model's/Application signature.

The Gateway maps a model’s name to a corresponding container. Whenever it receives a request via HTTP API, GRPC, or Kafka Streams, it communicates with that container via the gRPC protocol.

![Gateway enables data flow between different stages in an Application Pipeline](https://2921833647-files.gitbook.io/~/files/v0/b/gitbook-legacy-files/o/assets%2F-MESaD8WY3ggQLtBByXl%2Fsync%2F21d194c9ff522343434c138e467b6505d6526d25.png?generation=1603095658264118\&alt=media)

## Manager

![](https://2921833647-files.gitbook.io/~/files/v0/b/gitbook-legacy-files/o/assets%2F-MESaD8WY3ggQLtBByXl%2Fsync%2F3bd2147b4aeed8828c187f2e9f0ff28339517497.png?generation=1603095658293501\&alt=media)

Manager is responsible for:

* Building a Docker Image from your ML model for future deployment
* Storing these images inside a Docker Registry deployed alongside with

  manager service
* Versioning these images as Model Versions
* Creating running instances of these Model Versions called Servables

  inside Kubernetes cluster
* Combining multiple Model Versions into a linear graph with a single

  endpoint called Application