Ecosyste.ms: Awesome
An open API service indexing awesome lists of open source software.
https://github.com/hydrospheredata/hydro-serving
MLOps Platform
https://github.com/hydrospheredata/hydro-serving
machine-learning models pipelines realtime scikit-learn scoring serverless serving spark tensorflow
Last synced: about 16 hours ago
JSON representation
MLOps Platform
- Host: GitHub
- URL: https://github.com/hydrospheredata/hydro-serving
- Owner: Hydrospheredata
- License: apache-2.0
- Created: 2017-05-22T10:27:30.000Z (over 7 years ago)
- Default Branch: master
- Last Pushed: 2024-10-28T22:30:56.000Z (about 2 months ago)
- Last Synced: 2024-12-18T01:07:29.004Z (8 days ago)
- Topics: machine-learning, models, pipelines, realtime, scikit-learn, scoring, serverless, serving, spark, tensorflow
- Language: Mustache
- Homepage: http://docs.hydrosphere.io
- Size: 29.4 MB
- Stars: 271
- Watchers: 24
- Forks: 40
- Open Issues: 2
-
Metadata Files:
- Readme: README.md
- License: LICENSE
Awesome Lists containing this project
README
Hydrosphere Serving
Platform for deploying your Machine Learning to production
Check out Hydrosphere.io docs »
Report bug
·
Contact Us
---
[![GitHub license](https://img.shields.io/badge/license-apache-blue.svg)](https://github.com/Hydrospheredata/hydro-serving/blob/update-readme/LICENSE)
[![](https://img.shields.io/badge/chat-on%20slack-%23E01E5A)](https://hydrospheredata.slack.com/join/shared_invite/zt-tt4j24xj-TpnI_D2aJDBHIbA~EmPSlQ#/shared-invite/email)
[![](https://img.shields.io/badge/documentation-latest-af1a97.svg)](https://docs.hydrosphere.io)
[![Helm chart Lint and Testing](https://github.com/Hydrospheredata/hydro-serving/actions/workflows/Lint%20helm.yaml/badge.svg)](https://github.com/Hydrospheredata/hydro-serving/actions/workflows/Lint%20helm.yaml)Hydrosphere Serving is a cluster for deploying and versioning your machine learning models in production.
- **Framework Agnostic**. Serve machine learning models developed in any language or framework. Hydrosphere Serving will wrap them in a Docker image and deploy on your production cluster, exposing HTTP, gRPC and Kafka interfaces.
- **Traffic shadowing**. Shadow your traffic between different model versions to examine how different model versions behave on the same traffic.
- **Model Version Control**. Version control your models and pipelines as they are deployed.## Getting Started
You can refer to our [documentation](https://hydrosphere.io/serving-docs/latest/index.html) to see tutorials, check out [example projects]([https://github.com/Hydrospheredata/hydro-serving-example](https://github.com/Hydrospheredata/hydro-serving-example)), and learn about all features of Hydrosphere.
## Installation
There are two main ways of installing Hydropshere:
* [Docker](https://docs.hydrosphere.io/quickstart/installation#docker-installation);
* [Kubernetes](https://docs.hydrosphere.io/quickstart/installation#kubernetes-installation).### Docker
Before installing Hydrosphere Serving, please install its prerequisites:
* [Docker 20+, with BuildKit enabled](https://docs.docker.com/install/);
* [Docker Compose 1.29+](https://docs.docker.com/compose/install/#install-compose).To deploy the Hydrosphere platform from master branch, follow the instructions below:
1. Download the latest release version from the [releases](https://github.com/Hydrospheredata/hydro-serving/releases) page;
```sh
### __released_version__
export HYDROSPHERE_RELEASE=3.0.3wget -O hydro-serving-${HYDROSPHERE_RELEASE}.tar.gz https://github.com/Hydrospheredata/hydro-serving/archive/${HYDROSPHERE_RELEASE}.tar.gz
```
1. Unpack the tar ball;
```sh
tar -xvf hydro-serving-${HYDROSPHERE_RELEASE}.tar.gz
```
1. Set up an environment.
```sh
cd hydro-serving-${HYDROSPHERE_RELEASE}
docker-compose up
```To deploy the Hydrosphere platform from the master branch, follow the instructions below:
1. Clone umbrella repository locally.
```sh
git clone ...
cd hydro-serving
```
1. Build the docker-compose.yaml.
```sh
./build-compose.sh
docker-compose up
```
1. Set up an environment.
```sh
docker-compose up
```To check installation, open http://localhost/. By default Hydrosphere UI is available at port 80.
**Note**, other installation options are described in the [documentation](https://hydrosphere.io/serving-docs/latest/index.html).
### Kubernetes
Before installing Hydrosphere Serving, please install its prerequisites:
* [Helm 3.0+](https://docs.helm.sh/using_helm/#install-helm) with the tiller installed on the cluster;
* [Kubernetes 1.16+ with v1 API](https://kubernetes.io/docs/setup/) with beta APIs enabled.To install Hydrosphere Serving, follow the instructions below:
```shell
helm repo add hydrosphere https://hydrospheredata.github.io/hydro-serving/helm/
helm install --name serving --namespace hydrosphere hydrosphere/serving
```To reach the cluster, port-forward `ui` service locally.
```
kubectl port-forward -n hydrosphere svc/serving-ui 8080:9090
```To check installation, open http://localhost:8080/.
**Note**, other installation options are described in the [documentation](https://hydrosphere.io/serving-docs/latest/index.html).
## Community
Keep up to date and get Hydrosphere.io support via [![](https://img.shields.io/badge/chat-on%20slack-%23E01E5A)](https://hydrospheredata.slack.com/join/shared_invite/zt-tt4j24xj-TpnI_D2aJDBHIbA~EmPSlQ#/shared-invite/email) or contact us directly at [[email protected]](mailto:[email protected])### Contributing
We'd be glad to receive any help from the community!
Check out our issues for anything labeled with `help-wanted`, they will be the perfect starting point! If you don't see any, just let us know, we would be happy to hear from you.