emmi_data_management.cli_huggingface
====================================

.. py:module:: emmi_data_management.cli_huggingface


Attributes
----------

.. autoapisummary::

   emmi_data_management.cli_huggingface.RICH_MARKUP_MODE
   emmi_data_management.cli_huggingface.CTX
   emmi_data_management.cli_huggingface.hf_app


Classes
-------

.. autoapisummary::

   emmi_data_management.cli_huggingface.HuggingFaceRepoType


Functions
---------

.. autoapisummary::

   emmi_data_management.cli_huggingface.hf_docs
   emmi_data_management.cli_huggingface.hf_snapshot
   emmi_data_management.cli_huggingface.hf_file
   emmi_data_management.cli_huggingface.hf_ext
   emmi_data_management.cli_huggingface.hf_estimate


Module Contents
---------------

.. py:data:: RICH_MARKUP_MODE
   :type:  Literal['markdown', 'rich']
   :value: 'rich'


.. py:data:: CTX

.. py:data:: hf_app

.. py:class:: HuggingFaceRepoType

   Bases: :py:obj:`str`, :py:obj:`enum.Enum`


   str(object='') -> str
   str(bytes_or_buffer[, encoding[, errors]]) -> str

   Create a new string object from the given object. If encoding or
   errors is specified, then the object must expose a data buffer
   that will be decoded using the given encoding and error handler.
   Otherwise, returns the result of object.__str__() (if defined)
   or repr(object).
   encoding defaults to sys.getdefaultencoding().
   errors defaults to 'strict'.

   Initialize self.  See help(type(self)) for accurate signature.


   .. py:attribute:: MODEL
      :value: 'model'



   .. py:attribute:: DATASET
      :value: 'dataset'



.. py:function:: hf_docs()

   **HuggingFace commands**

   **Examples**
   ```
   # snapshot whole repo
   emmi-data huggingface snapshot user/dataset ./data

   # single file from a dataset repo
   emmi-data huggingface file user/dataset data.hd5 ./data --type dataset

   # all *.jsonl from a dataset
   emmi-data huggingface ext user/model .th ./data

   # size estimate (uses HEAD fallback for LFS files)
   emmi-data huggingface estimate EmmiAI/AB-UPT
   ```


.. py:function:: hf_snapshot(repo_id = typer.Argument(..., help='Repo ID, e.g. user/dataset'), local_dir = typer.Argument(..., help='Destination directory', dir_okay=True, file_okay=False), verify = typer.Option(False, '--verify', help='Run checksum verification'))

.. py:function:: hf_file(repo_id = typer.Argument(..., help='Repo ID'), filename = typer.Argument(..., help='Exact path in repo'), local_dir = typer.Argument(..., help='Destination directory', dir_okay=True, file_okay=False), repo_type = typer.Option(HuggingFaceRepoType.MODEL, '--type', '-t', case_sensitive=False, help='model|dataset', show_default=True), revision = typer.Option('main', '--revision', '-r', help='branch|tag|SHA', show_default=True))

.. py:function:: hf_ext(repo_id = typer.Argument(..., help='Dataset repo ID'), extension = typer.Argument(..., help='e.g. .jsonl, .csv, .parquet'), local_dir = typer.Argument(..., help='Destination directory', dir_okay=True, file_okay=False), revision = typer.Option('main', '--revision', '-r', help='branch|tag|SHA', show_default=True), repo_type = typer.Option(HuggingFaceRepoType.DATASET, '--type', '-t', case_sensitive=False), jobs = typer.Option(8, '--jobs', '-j', help='Parallel downloads'), verify = typer.Option(False, '--verify', help='Verify files after download using a manifest'), manifest = typer.Option(None, '--manifest', '-m', help='Path to manifest.json'), manifest_out = typer.Option(None, '--manifest-out', '-mo', help='Path to provenance manifest'), on_fail = typer.Option(FailAction.WARN, '--action', '-a', case_sensitive=False, help='Action on verification failures'))

.. py:function:: hf_estimate(repo_id = typer.Argument(..., help='Repo ID'), repo_type = typer.Option(HuggingFaceRepoType.MODEL, '--type', '-t', case_sensitive=False, help='model|dataset', show_default=True), extension = typer.Option(None, '--extension', '-e', help='Filter by extension'), revision = typer.Option('main', '--revision', '-r', help='branch|tag|SHA', show_default=True))