Grabbing the Image
Private AI is distributed via a single container image. No further downloads are required, as everything is packaged into the image, including the ML models. Updates are released on a monthly cadence via new container images.
Image Types
There are 5 different flavours of the Private AI container:
-
cpu
, which contains all features except for GPU support. -
cpu-text
, a cut down CPU image that contains only text functionality. -
gpu
, which contains all features except for synthetic entity functionality. -
gpu-text
, a GPU-accelerated version ofcpu-text
. -
gpu-synthetic
, a GPU-accelerated version that includes synthetic entity functionality.
It is recommended to use the text-only containers where possible, as they require less RAM and start quicker due to the smaller image size.
The supported feature matrix is below:
cpu | cpu-text | gpu | gpu-text | gpu-synthetic | |
---|---|---|---|---|---|
Multilingual Support | ✓ | ✓ | ✓ | ✓ | ✓ |
Synthetic Entity Support | ✓ | ✓ | |||
File Support | ✓ | ✓ | ✓ | ||
GPU Support | ✓ | ✓ | ✓ |
Versioning Scheme
Images are tagged with the release version followed by the image type. For example, the 4.0.3 release features the following images: 4.0.3-cpu
, 4.0.3-cpu-text
, 4.0.3-gpu
, 4.0.3-gpu-text
and 4.0.3-gpu-synthetic
. The container repository also contains cpu
, cpu-text
, gpu
, gpu-text
and gpu-synthetic
tags which point to the latest release version.
Getting the Image
The container image is distributed via an Azure Container Registry. Your customer portal account will have a login command pre-filled with your credentials that will look like this:
docker login -u INSERT_UNIQUE_CLIENT_ID -p INSERT_UNIQUE_CLIENT_PW crprivateaiprod.azurecr.io
Once you've logged in, the image can be pulled with this command:
docker pull crprivateaiprod.azurecr.io/deid:<version>