Hydrosphere.io
GithubPython SDKContact UsSlack Community
master
master
  • Hydrosphere
  • 🌊About Hydrosphere
    • Overview
    • Concepts
    • Platform Architecture
      • Serving
      • Monitoring
      • Interpretability
    • Key Features
      • Model Registry
      • Inference Pipelines
      • A/B Model Deployments
      • Traffic Shadowing
      • Language-Agnostic
      • Automatic Outlier Detection
      • Data Drift Report
      • Monitoring Dashboard
      • Alerts
      • Prediction Explanation
      • Data Projection
      • Kubeflow Components
      • AWS Sagemaker
  • πŸ„Quickstart
    • Installation
      • CLI
      • Python SDK
      • Configuring Helm charts
    • Getting Started
    • Tutorials
      • A/B Analysis for a Recommendation Model
      • Using Deployment Configurations
      • Train & Deploy Census Income Classification Model
      • Monitoring Anomalies with a Custom Metric
      • Monitoring External Models
    • How-To
      • Invoke applications
      • Write definitions
      • Develop runtimes
      • Use private pip repositories
  • πŸ’§Resources
    • Troubleshooting
    • Reference
      • Libraries
      • Runtimes
    • Contribution
      • Contributing Pull Requests
  • Advanced
    • AWS infrastructure
Powered by GitBook
On this page
  • Gateway
  • Manager

Was this helpful?

Export as PDF
  1. About Hydrosphere
  2. Platform Architecture

Serving

PreviousPlatform ArchitectureNextMonitoring

Last updated 3 years ago

Was this helpful?

Gateway

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.

Manager

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

🌊
Gateway enables data flow between different stages in an Application Pipeline