Container

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

A container that runs arbitrary code to execute a model.

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"},
... )

Attributes

args	(dict) - additional arguments to pass to the inference function
image	(str) - the name of the image to use
pull_secret_credential	(str) - name of the credential to use to pull the container
repository	(str) - the docker repository to pull from
tag	(str) - the tag of the image to use

Methods

clear()
copy()
fromkeys([value])	Create a new dictionary with keys from iterable and values set to value.
get(key[, default])	Return the value for key if key is in the dictionary, else default.
items()
keys()
pop(k[,d])	If the key is not found, return the default if given; otherwise, raise a KeyError.
popitem()	Remove and return a (key, value) pair as a 2-tuple.
setdefault(key[, default])	Insert key with a value of default if key is not in the dictionary.
update(*mapping, **kwargs)
values()