Container

class geodesic.tesseract.components.Container(*args, **kwargs)

Bases: geodesic.bases._APIObject

A container that runs arbitrary code to execute a model for aggregation, machine learning, etc.

Containers can be on any image repository that docker can pull from. The container must have been built using the Tesseract Python SDK in order to run in Tesseract. If containers are stored in a private repository you must provide the pull secret to use. This needs to be a Credential stored in the Geodesic platform.

Example

>>> Container(
...    repository="docker.io",
...    image="seerai/my-model",
...    tag="latest",
...    pull_secret_credential="my-credential",
...    args={"model_arg": "argument"},
... )

repository

(str) - the docker repository to pull from

Descriptor: _StringDescr

image

(str) - the name of the image to use

Descriptor: _StringDescr

tag

(str) - the tag of the image to use

Descriptor: _StringDescr

pull_secret_credential

(str) - name of the credential to use to pull the container

Descriptor: _StringDescr

args

(dict) - additional arguments to pass to the inference function

Descriptor: _DictDescr