Skip to main content

mb.deploy(deployment_function, ...)

Deploys a Python function and dependencies to Modelbit. Return values of the function must be JSON-serializable.

Parameters​

  • deployment_function: Callable The function to deploy to Modelbit. If the function uses Python type hints for its parameters and return type, Modelbit will generate smarter sample code.
  • name: Optional[str] The name of the deployment. If omitted, the name of the deployment_function is used.
  • python_version: Optional[str, 3.6|3.7|3.8|3.9|3.10|3.11] Python version to run in production.
  • python_packages: Optional[List[str]] The pip packages to install in the deployment's environment. E.g. ["scikit-learn==1.0.2"]. Git URLs to WHL files may also be specified, e.g. for Detectron2 packages.
  • system_packages: Optional[List[str]] The apt-get packages to install in the deployment's environment. E.g. ["libgomp1"].
  • dataframe_mode: Optional[bool] Whether to deploy in [DataFrame mode]/deployments/dataframe-mode). If True, example_dataframe must be specified.
  • example_dataframe: Optional[pandas.DataFrame] DataFrame with the columns and column types to expect in production in DataFrame mode. If specified, dataframe_mode must be True.
  • extra_files: Optional[str, List[str], Dict[str, str]] Additional files to include with the deployment.
    • as str: The path to a single file or directory.
    • as List[str]: Paths to multiple files or directories.
    • as Dict[str, str]: Pairs of file paths or directories. The key is the local file path, the value is the file path in common files.
  • skip_extra_files_dependencies: Optional[bool] If True then mb.deploy will not parse extra_files to determine additional environment dependencies. Default is False.

Returns​

The call to mb.deploy is typically done in an interactive environment, like a Python notebook. The command will print out status, and then show link to open the deployment in Modelbit.

Examples​

Deploying a simple function​

def example_deployment_function(a: int):
  return a * 2

mb.deploy(example_deployment_function)

Deploying into a specific Python version​

mb.deploy(example_deployment_function, python_version="3.8")

Deploying with specific Python packages​

See more examples in the custom Python environments documentation.

mb.deploy(example_deployment_function, python_packages=["pandas==2.0.3"])

Deploying with dataframe_mode​

See the DataFrame mode documentation for more examples.

mb.deploy(get_predictions, dataframe_mode = True, example_dataframe = X_train)

Deploying with a package built from git​

mb.deploy(find_cat, python_packages=["git+https://github.com/facebookresearch/segment-anything.git"])

Including local python files​

mb.deploy(example_deployment_function, extra_files=["utils.py"])

Deploying an sklearn object​

As a special case, you can pass a SciKit-Learn model or pipeline as the deployment function. When this model's API is called in production, sklearn_object.predict will be called.

mb.deploy(my_sklearn_model)

See also​

  • Read the Deployments section of the docs for more info on deploying to Modelbit.