Automatic Machine Learning for the Enterprise.
Driverless AI automates feature engineering, model building, visualization and interpretability.
Licensing
- Driverless AI is a commercially licensed product, and requires a license key. Request a free trial license key here.
Support
- This version of H2O Driverless AI is for standalone installations only (i.e., not part of H2O AI Cloud) and is supported until October 03, 2024.
Download
Linux (x86)
Windows
Mac
IBM Power
Python client
Package Type |
OS |
GPU |
CPU |
|
|
RPM |
RHEL 7/RHEL 8/CentOS 7/SLES 12 |
CUDA 11.8.0 and above/CPU only |
x86_64 |
Download |
Checksum |
DEB |
Ubuntu 16.04/Ubuntu 18.04/Ubuntu 20.04/Ubuntu 22.04 |
CUDA 11.8.0 and above/CPU only |
x86_64 |
Download |
Checksum |
TAR SH |
Most Linux |
CUDA 11.8.0 and above/CPU only |
x86_64 |
Download |
Checksum |
Docker |
Docker CE |
CUDA 11.8.0 and above/CPU only |
x86_64 |
Download |
Checksum |
Caution: |
Windows computers (laptops in particular) should only be used with small datasets for the purpose of exploring the software. For serious use, server hardware is required. Consider spinning up a more powerful instance in the cloud instead of using a laptop. Avoid laptops with less than 16 GB of RAM. GPUs are not supported on Windows. |
|
Caution: |
MacOS computers (laptops in particular) should only be used with small datasets for the purpose of exploring the software. For serious use, server hardware is required. Consider spinning up a more powerful instance in the cloud instead of using a laptop. Avoid laptops with less than 16 GB of RAM. GPUs are not supported on MacOS. |
|
The PowerPC PPC64le platform is no longer supported. The last H2O Driverless AI release supporting the PPC64le platform is 1.9.3.2.
Please contact support@h2o.ai for more information.
Python client for H2O.ai Driverless AI
Start using Driverless AI Python API
1. Install the driverlessai package using Pip
pip install driverlessai
3. Start Python session and connect to a running Driverless AI instance
import driverlessai
client = driverlessai.Client(address='http://localhost:12345', username="user", password="pw")
User Documentation
Booklets