DEV Community

Cover image for Contribute to Flyte for Hacktoberfest
Michelle Duke
Michelle Duke

Posted on

Contribute to Flyte for Hacktoberfest

There are lots of projects who have been involved in Hacktoberfest this year. As Hacktoberfest heads into its last few days, it's time to get your final pull requests in.

If you're yet to start contributing, sign up to start hacking today. Any PRs you've made throughout the month of October will be counted, even if you signed up late! You'll need to make sure the project or projects you've contributed to have the #hacktoberfest tag on the repo. Your PRs should then be counted. Provided your pull requested are accepted and meet the Hacktoberfest values.

While I was on my recent Hacktoberfest live stream we discovered Flyte. It's an open source project for machine learning and data processing. Flyte is a platform enabling workflows.

If you're into machine learning and data science you definitely need to check out Flyte. Let's look at little closer at the project, and how to contribute.

What is Flyte

Flyte was created by Lyft in collaboration with Spotify, Freenome, and the broader community (it is open source of course). It enables and builds workflows for machine learning and data processing.

Instead of writing *.yaml files (which are what workflow run on), you can spend your time writing code, and leave the workflows to Flyte. It's built on Kubernetes, and there's lots of SDKs so you can program exactly what you want.

Getting started with Flyte

One of the cool things about Flyte is they have a tonne of tutorials. These tutorials are here to teach you how to use Flyte and start processing data, training models, or performing batch predictions. The tutorials are affectionately named Flytesnacks. All the code for the tutorials is available on GitHub for easy access.

GitHub logo flyteorg / flytesnacks

Flyte Documentation πŸ“–

Flyte Logo

Flyte User Guide & Tutorials

Flytesnacks encompasses code examples showcasing Flytekit Python

Slack

πŸš€ Quick Start

To get the hang of Python SDK, refer to the Getting Started tutorial before exploring the examples.

The User Guide section has code examples, tips, and tricks that showcase the usage of Flyte features and integrations.

The Tutorials section has real-world examples, ranging from machine learning training, data processing to feature engineering.

the Integrations section demonstrates how to use Flyte with other tools and frameworks.

Flytesnacks currently has all examples in Python (Flytekit Python SDK).

πŸ“– How to Contribute to Flytesnacks

You can find the detailed contribution guide here.

🐞 File an Issue

Refer to the issues section in the contribution guide if you'd like to file an issue.




Once you're familiar with Flyte, and using it, you might want to contribute back to the community. It's the perfect time to contribute with Hacktoberfest still running.

Contributing to Flyte

Being part of Flyte is great, because there are so many ways to contribute. You can contribute to Flytesnacks which will count towards your Hacktoberfest contributions too.

The main Flyte repo is perfect if you're wanting to contribute to Flyte's core product.

GitHub logo flyteorg / flyte

Scalable and flexible workflow orchestration platform that seamlessly unifies data, ML and analytics stacks.

Flyte and LF AI & Data Logo

Flyte

πŸ—οΈ πŸš€ πŸ“ˆ

Current Release label Sandbox Status label Test Status label License label OpenSSF Best Practices label Flyte Helm Chart label Flyte Slack label

Flyte is an open-source orchestrator that facilitates building production-grade data and ML pipelines. It is built for scalability and reproducibility, leveraging Kubernetes as its underlying platform. With Flyte, user teams can construct pipelines using the Python SDK, and seamlessly deploy them on both cloud and on-premises environments, enabling distributed processing and efficient resource utilization.

Build

Write code in Python or any other language and leverage a robust type engine

Getting started with Flyte

Deploy & Scale


Either locally or on a remote cluster, execute your models with ease.

Getting started with Flyte

Table of contents


Quick start

  1. Install Flyte's Python SDK
pip install flytekit
Enter fullscreen mode Exit fullscreen mode
  1. Create a workflow (see example)
  2. Run it locally with:
pyflyte run hello_world.py hello_world_wf
Enter fullscreen mode Exit fullscreen mode

Ready to try a Flyte cluster?

  1. Create a new sandbox cluster, running as a Docker container:
…
Enter fullscreen mode Exit fullscreen mode

If you're coming to Flyte for the first time, there are lots of good-first-issue you can work on. Pick something and get started. There's issues for fixing bugs, documentation writing, building lightweight features, and adding enhancements.

Image description

As always, if you're planning on contributing, or you're thinking about contributing to a project, remember to read the contribution guidelines. Flyte has a whole page on their website just for detailing community contributions. Check this out before opening your pull request.

Hacktoberfest

What will you build in the final days of Hacktoberfest? Will you contribute to Flyte? Will you dive into Flyte snackables?

Check out our Hacktoberfest series to find other cool projects to contribute to this October.

Top comments (0)