Diagram of different python machine learning packages passing through a laptop, resulting in a docker container, which is sent to run on edge, on-prem, and cloud servers.

Build ML Model Containers, Automatically

Package ML models into containerized prediction APIs in just minutes, and run them anywhere - in the Cloud, On-Prem, or at the Edge

Get Started Join Community

Diagram of chassis containers running Modzy, Docker, Kubernetes, and Kserve.

What is Chassis?

Chassis is an open-source project that automatically turns your ML models into production containers.

With easy integration in mind, Chassis picks up right where your training code leaves off and builds containers for any target architecture. Execute a single Chassis job and run your models in the cloud, on-prem, or on edge devices ( Raspberry Pi, NVIDIA Jetson Nano, Intel NUC, and more!).

Benefits:
Turns models into containers, automatically
Creates easy-to-use prediction APIs
Containers can run on Modzy, KServe (v1), and more
Connects to Docker Hub and other registries
Compiles for both x86 and ARM processors
Supports GPU batch processing
No missing dependencies, perfect for edge AI

Getting Started

Getting started with Chassis is as easy as installing a Python package and incorporating a few lines of code into your existing workflow. Follow these short steps to start building your first ML container in just minutes!

What you will need:

Chassis SDK: The Chassis Python package enables you to interact with the Chassis service. Download via PyPi: pip install chassisml

Python model: Bring your model trained with your favorite Python ML framework (Scikit-learn, PyTorch, Tensorflow, or any framework you use!)

Registry Credentials: Chassis will build a container image and push it to your preferred registry, so make sure you either have a Docker Hub account or credentials to your private container registry. You can create a free Docker Hub account today if you need one!

Get Started GitHub


          import chassisml

          # NOTE: The below code snippet is pseudo code that
          # intends to demonstrate the general workflow when 
          # using Chassis and will not execute as is. Substitute
          # with your own Python framework, any revelant utility 
          # methods, and syntax specific to your model. 
          
          import framework 
          import preprocess, postprocess
          
          # load model
          model = framework.load("path/to/model/file")
          
          # define process function and create model
          def process(input_bytes):
              # preprocess data
              data = preprocess(input_bytes)
              # perform inference
              predictions = model.predict(data)
              # process output
              output = postprocess(predictions)
              return output
          
          # connect to Chassis, create and publish model
          chassis_client = chassisml.ChassisClient("https://chassis.app.modzy.com")
          chassis_model = chassis_client.create_model(process_fn=process)
          
          # publish model to Docker registry
          response = chassis_model.publish(
              model_name="My First Chassis Model!",
              model_version="0.0.1",
              registry_user="insert-dockerhub-username",
              registry_pass="insert-dockerhub-password",
          )