Wallaroo SDK Install Guides

How to install the Wallaroo SDK

The following guides demonstrate how to install the Wallaroo SDK in different environments. The Wallaroo SDK is installed by default into a Wallaroo instance for use with the JupyterHub service.

The Wallaroo SDK requires Python 3.8.6 and above and is available through the Wallaroo SDK Page.

When using the Wallaroo SDK, it is recommended that the Python modules used are the same as those used in the Wallaroo JupyterHub environments to ensure maximum compatibility. When installing modules in the Wallaroo JupyterHub environments, do not override the following modules or versions, as that may impact how the JupyterHub environments performance.

appdirs == 1.4.4
gql == 3.4.0
ipython == 7.24.1
matplotlib == 3.5.0
numpy == 1.22.3
orjson == 3.8.0
pandas == 1.3.4
pyarrow == 9.0.0
PyJWT == 2.4.0
python_dateutil == 2.8.2
PyYAML == 6.0
requests == 2.25.1
scipy == 1.8.0
seaborn == 0.11.2
tenacity == 8.0.1
# Required by gql?
requests_toolbelt>=0.9.1<1
# Required by the autogenerated ML Ops client
httpx >= 0.15.4<0.24.0
attrs >= 21.3.0
# These are documented as part of the autogenerated ML Ops requirements
# python = ^3.7
# python-dateutil = ^2.8.0

Supported Model Versions and Libraries

The following ML Model versions and Python libraries are supported by Wallaroo. When using the Wallaroo autoconversion library or working with a local version of the Wallaroo SDK, use the following versions for maximum compatibility.

Library Supported Version
Python 3.8.6 and above
onnx 1.12.0
tensorflow 2.9.1
keras 2.9.0
pytorch 1.13.1
sk-learn aka scikit-learn 1.1.2
statsmodels 0.13.2
XGBoost 1.6.2
MLFlow 1.30.0

Supported Data Types

The following data types are supported for transporting data to and from Wallaroo in the following run times:

  • ONNX
  • TensorFlow
  • MLFlow

Data Type Conditions

The following conditions apply to data types used in inference requests.

  • None or Null data types are not submitted. All fields must have submitted values that match their data type. For example, if the schema expects a float value, then some value of type float must be submitted and can not be None or Null. If a schema expects a string value, then some value of type string must be submitted, etc.
  • datetime data types must be converted to string.
  • ONNX models support multiple inputs only of the same data type.
Runtime BFloat16* Float16 Float32 Float64
ONNX X X
TensorFlow X X X
MLFlow X X X
  • * (Brain Float 16, represented internally as a f32)

Runtime Int8 Int16 Int32 Int64
ONNX X X X X
TensorFlow X X X X
MLFlow X X X X
Runtime Uint8 Uint16 Uint32 Uint64
ONNX X X X X
TensorFlow X X X X
MLFlow X X X X
Runtime Boolean Utf8 (String) Complex 64 Complex 128 FixedSizeList*
ONNX X
Tensor X X X
MLFlow X X X
  • * Fixed sized lists of any of the previously supported data types.


Wallaroo SDK AWS Sagemaker Install Guide

How to install the Wallaroo SDK in AWS Sagemaker

Wallaroo SDK AzureML Install Guide

How to install the Wallaroo SDK in AzureML

Wallaroo SDK Azure Databricks Install Guide

How to install the Wallaroo SDK in Azure Databricks

Wallaroo SDK Google Vertex Install Guide

How to install the Wallaroo SDK in Google Vertex

Wallaroo SDK Standard Install Guide

How to install the Wallaroo SDK in typical environment