Time-series

mlflow

kubeflow

evidently

Predict Electricity Power Generation Based On Wind Forecast In Orkney, Scotland

Forecasting Wind Power Generation 

Computer Vision

One of AI's biggest potentials is to help improve and augment the quality of life, especially for people with disabilities. In this project, we show how ZenML empowers users to build, track and deploy a computer vision pipeline using the most popular tools in the industry. You will learn how to train a YOLOv5 model on Vertex AI, track experiments with MLflow, and deploy a BentoML bundle to the Vertex AI  endpoint. 

Sign Language Detection with YOLOv5

Natural Language Processing

github

Productionalizing LangChain and LlamaIndex with a ZenML MLOps Pipeline to Help Community Slack Support.

Community Support with an LLM-powered Slack bot

Tabular Data

deepchecks

A GitHub workflow that automates CI/CD with continuous model training and continuous model deployment to production

Use ZenML seamlessly with GitHub

Explore how ZenML, an MLOps framework, can be used with large language models (LLMs) like GPT-4 to analyze and version data from databases like Supabase. In this case study, we examine the you-tldr.com website, showcasing ZenML pipelines asynchronously processing video data and generating summaries with GPT-4. Understand how to tackle large language model limitations by versioning data and comparing summaries to unlock your data's potential. Learn how this approach can be easily adapted to work with other databases and LLMs, providing flexibility and versatility for your specific needs.

Using ZenML with LLMs to Analyze and Version Data from Databases: A Case Study with you-tldr.com and Supabase/GPT-4

Will they stay or will they go? Building a Customer Loyalty Predictor

Predicting Customer Loyalty

discord

sklearn

Predict the number of three-pointers in the next NBA match.

NBA Three-Pointer Predictor

Image generated by [StableDiffusion 2.1](https://huggingface.co/stabilityai/stable-diffusion-2-1)

A project focusing on implementing a pipeline that offers insight into our community.

Managing our community with a ZenML pipeline.

Predicting how a customer will feel about a product before they even ordered it

Predicting Customer Satisfaction About A Product

A tool powered by ZenML that can automate the summarization of news sources.

Summarize Articles with ZenNews

<p>Tired of setting up new MLOps tools, doing manual deployments, or having unreproducible experiments? Use ZenML to transform your ML workflows into production-ready solutions.</p>

ZenML Features

Write your core machine learning workflow code locally, and run it anywhere.

Write Local, Run Anywhere

No need to waste compute resources and time: ZenML automatically caches all artifacts that have not changed.

Automatically Cache Runs

All data that flows between steps is automatically versioned and tracked centrally in artifact and metadata stores.

Automatically Version Data

ZenML tracks all your machine learning metadata automatically so you have full lineage and reproducibility of your ML workflows.

Automatically Track Metadata

Deploy and manage your ML tools together with ZenML.

Deploy MLOps Stacks

Can't find something that fits? Extend ZenML to tailor specific needs in your workflow.

Customize To Your Needs

ZenML allows an entire team of machine learning practitioners to collaborate together seamlessly, from data scientists to ML engineers.

Collaborate With Your Team

Use pre-built visualizers to directly visualize results of pipelines using popular libraries like dash, plotly, and facets.

Visualize ML Workflows

ZenML allows you to continuously train and deploy your ML models.

Continuous Training and Deployment (CT/CD)

ZenML boasts a ton of production-ready MLOps features that help go from experimentation to production with machine learning pipelines. Write local, run anywhere. Extensibility. Centralized MLOps stacks. Automated metadata tracking. Collaboration. Continuous training and deployment.